Artificial neural network has been widely used in various fields as an intelligent tool in recent years, such
as artificial intelligence, pattern recognition, medical diagnosis, machine learning and so on. The
classification of breast cancer is a medical application that poses a great challenge for researchers and
scientists. Recently, the neural network has become a popular tool in the classification of cancer datasets.
Classification is one of the most active research and application areas of neural networks. Major
disadvantages of artificial neural network (ANN) classifier are due to its sluggish convergence and always
being trapped at the local minima. To overcome this problem, differential evolution algorithm (DE) has
been used to determine optimal value or near optimal value for ANN parameters. DE has been applied
successfully to improve ANN learning from previous studies. However, there are still some issues on DE
approach such as longer training time and lower classification accuracy. To overcome these problems,
island based model has been proposed in this system. The aim of our study is to propose an approach for
breast cancer distinguishing between different classes of breast cancer. This approach is based on the
Wisconsin Diagnostic and Prognostic Breast Cancer and the classification of different types of breast
cancer datasets. The proposed system implements the island-based training method to be better accuracy
and less training time by using and analysing between two different migration topologies
ENHANCED SYSTEM FOR COMPUTER-AIDED DETECTION OF MRI BRAIN TUMORSsipij
The brain images are indicating what condition the brain has. The objective of this research is to design a software that will automatically classifies the brain images to their associated disorders. In order to achieve the objective of this research, a database for training and testing the software of brain images must to be found. In this research we have 105 number of images in data set. In order to differentiate between the classes of those brain images, features had to be extracted from the images. Then, images will be classified into two classes normal and abnormal by using SVM and KNN classifier. The features that were extracted were used in the classification process. The classifiers performed really well, whereas the SVM classifier performed better since its accuracy is 100% on testing set. In the end, the software was successful in separating the two classes.
AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...ijsc
As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the
availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection
based ensemble learning models is to classify the high dimensional data with high computational efficiency
and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray
datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.
Comparison of Image Segmentation Algorithms for Brain Tumor DetectionIJMTST Journal
This paper deals with the implementation of Simple Algorithms for detection of size and shape of tumor in brain using MRI images. Generally, CT scan or MRI that is directed into intracranial cavity produces a complete image of brain. This image is visually examined by the physician for detection & diagnosis of brain tumor. However this method of detection resists the accurate determination of stage & size of tumor. To avoid that, this project uses computer aided method for segmentation (detection) of brain tumor by applying Fuzzy C-Means, K-Means, Gaussian Kernel and Pillar K-means algorithms. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system applies FCM, Gaussian kernel and K-means clustering to the image later optimized by Pillar Algorithm. It designates the initial centroids’ positions by calculating the Euclidian distance metric between each data point and all previous centroids. Then it selects data points which have the maximum distance as new initial centroids. This algorithm distributes all initial centroids according to the maximum accumulated distance metric. In addition, it also reduces the time for analysis. At the end of the process the tumor is extracted from the MRI image and its exact position and the shape is also determined. This paper evaluates the proposed approach for Brain tumor detection by comparing with K-means, Fuzzy C means, Gaussian Kernel and manually segmented algorithms. The experimental results clarify the effectiveness of proposed approach to improve the segmentation quality in aspects of precision and computational time.
MRI Brain Tumour Classification Using SURF and SIFT FeaturesIJMTST Journal
The features of an image are very important to classify different images. The classification of images is
done by feature extraction using Speeded Up Robust Features (SURF) and Scale Invariant Feature Transform
(SIFT) methods for extraction. SIFT method is used to detect the images with larger corners and extract them.
SURF, the name itself represents a speed method to extract the features when compared to SIFT. KNN
classifier is used to classify the images based on the features extracted from both techniques. So these
combined processes are applied to classify tumour and non-tumour images more accurately.
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATAIJSCAI Journal
Advancement in information and technology has made a major impact on medical science where the
researchers come up with new ideas for improving the classification rate of various diseases. Breast cancer
is one such disease killing large number of people around the world. Diagnosing the disease at its earliest
instance makes a huge impact on its treatment. The authors propose a Binary Bat Algorithm (BBA) based
Feedforward Neural Network (FNN) hybrid model, where the advantages of BBA and efficiency of FNN is
exploited for the classification of three benchmark breast cancer datasets into malignant and benign cases.
Here BBA is used to generate a V-shaped hyperbolic tangent function for training the network and a fitness
function is used for error minimization. FNNBBA based classification produces 92.61% accuracy for
training data and 89.95% for testing data.
Robust Breast Cancer Diagnosis on Four Different Datasets Using Multi-Classif...ahmad abdelhafeez
Abstract- The goal of this paper is to compare between different classifiers or multi-classifiers fusion with respect to accuracy in discovering breast cancer for four different data sets. We present an implementation among various classification techniques which represent the most known algorithms in this field on four different datasets of breast cancer two for diagnosis and two for prognosis. We present a fusion between classifiers to get the best multi-classifier fusion approach to each data set individually. By using confusion matrix to get classification accuracy which built in 10-fold cross validation technique. Also, using fusion majority voting (the mode of the classifier output). The experimental results show that no classification technique is better than the other if used for all datasets, since the classification task is affected by the type of dataset. By using multi-classifiers fusion the results show that accuracy improved in three datasets out of four.
Simplified Knowledge Prediction: Application of Machine Learning in Real LifePeea Bal Chakraborty
Machine learning is the scientific study of algorithms and statistical models that is used by the machines to perform a specific task depending on patterns and inference rather than explicit instructions. This research and analysis aims to observe how precisely a machine can predict that a patient suspected of breast cancer is having malignant or benign cancer.In this paper the classification of cancer type and prediction of risk levels is done by various model of machine learning and is pictorially depicted by various tools of visual analytics.
BREAST CANCER DIAGNOSIS USING MACHINE LEARNING ALGORITHMS –A SURVEYijdpsjournal
Breast cancer has become a common factor now-a-days. Despite the fact, not all general hospitals
have the facilities to diagnose breast cancer through mammograms. Waiting for diagnosing a breast
cancer for a long time may increase the possibility of the cancer spreading. Therefore a computerized
breast cancer diagnosis has been developed to reduce the time taken to diagnose the breast cancer and
reduce the death rate. This paper summarizes the survey on breast cancer diagnosis using various machine
learning algorithms and methods, which are used to improve the accuracy of predicting cancer. This survey
can also help us to know about number of papers that are implemented to diagnose the breast cancer.
ENHANCED SYSTEM FOR COMPUTER-AIDED DETECTION OF MRI BRAIN TUMORSsipij
The brain images are indicating what condition the brain has. The objective of this research is to design a software that will automatically classifies the brain images to their associated disorders. In order to achieve the objective of this research, a database for training and testing the software of brain images must to be found. In this research we have 105 number of images in data set. In order to differentiate between the classes of those brain images, features had to be extracted from the images. Then, images will be classified into two classes normal and abnormal by using SVM and KNN classifier. The features that were extracted were used in the classification process. The classifiers performed really well, whereas the SVM classifier performed better since its accuracy is 100% on testing set. In the end, the software was successful in separating the two classes.
AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...ijsc
As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the
availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection
based ensemble learning models is to classify the high dimensional data with high computational efficiency
and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray
datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.
Comparison of Image Segmentation Algorithms for Brain Tumor DetectionIJMTST Journal
This paper deals with the implementation of Simple Algorithms for detection of size and shape of tumor in brain using MRI images. Generally, CT scan or MRI that is directed into intracranial cavity produces a complete image of brain. This image is visually examined by the physician for detection & diagnosis of brain tumor. However this method of detection resists the accurate determination of stage & size of tumor. To avoid that, this project uses computer aided method for segmentation (detection) of brain tumor by applying Fuzzy C-Means, K-Means, Gaussian Kernel and Pillar K-means algorithms. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system applies FCM, Gaussian kernel and K-means clustering to the image later optimized by Pillar Algorithm. It designates the initial centroids’ positions by calculating the Euclidian distance metric between each data point and all previous centroids. Then it selects data points which have the maximum distance as new initial centroids. This algorithm distributes all initial centroids according to the maximum accumulated distance metric. In addition, it also reduces the time for analysis. At the end of the process the tumor is extracted from the MRI image and its exact position and the shape is also determined. This paper evaluates the proposed approach for Brain tumor detection by comparing with K-means, Fuzzy C means, Gaussian Kernel and manually segmented algorithms. The experimental results clarify the effectiveness of proposed approach to improve the segmentation quality in aspects of precision and computational time.
MRI Brain Tumour Classification Using SURF and SIFT FeaturesIJMTST Journal
The features of an image are very important to classify different images. The classification of images is
done by feature extraction using Speeded Up Robust Features (SURF) and Scale Invariant Feature Transform
(SIFT) methods for extraction. SIFT method is used to detect the images with larger corners and extract them.
SURF, the name itself represents a speed method to extract the features when compared to SIFT. KNN
classifier is used to classify the images based on the features extracted from both techniques. So these
combined processes are applied to classify tumour and non-tumour images more accurately.
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATAIJSCAI Journal
Advancement in information and technology has made a major impact on medical science where the
researchers come up with new ideas for improving the classification rate of various diseases. Breast cancer
is one such disease killing large number of people around the world. Diagnosing the disease at its earliest
instance makes a huge impact on its treatment. The authors propose a Binary Bat Algorithm (BBA) based
Feedforward Neural Network (FNN) hybrid model, where the advantages of BBA and efficiency of FNN is
exploited for the classification of three benchmark breast cancer datasets into malignant and benign cases.
Here BBA is used to generate a V-shaped hyperbolic tangent function for training the network and a fitness
function is used for error minimization. FNNBBA based classification produces 92.61% accuracy for
training data and 89.95% for testing data.
Robust Breast Cancer Diagnosis on Four Different Datasets Using Multi-Classif...ahmad abdelhafeez
Abstract- The goal of this paper is to compare between different classifiers or multi-classifiers fusion with respect to accuracy in discovering breast cancer for four different data sets. We present an implementation among various classification techniques which represent the most known algorithms in this field on four different datasets of breast cancer two for diagnosis and two for prognosis. We present a fusion between classifiers to get the best multi-classifier fusion approach to each data set individually. By using confusion matrix to get classification accuracy which built in 10-fold cross validation technique. Also, using fusion majority voting (the mode of the classifier output). The experimental results show that no classification technique is better than the other if used for all datasets, since the classification task is affected by the type of dataset. By using multi-classifiers fusion the results show that accuracy improved in three datasets out of four.
Simplified Knowledge Prediction: Application of Machine Learning in Real LifePeea Bal Chakraborty
Machine learning is the scientific study of algorithms and statistical models that is used by the machines to perform a specific task depending on patterns and inference rather than explicit instructions. This research and analysis aims to observe how precisely a machine can predict that a patient suspected of breast cancer is having malignant or benign cancer.In this paper the classification of cancer type and prediction of risk levels is done by various model of machine learning and is pictorially depicted by various tools of visual analytics.
BREAST CANCER DIAGNOSIS USING MACHINE LEARNING ALGORITHMS –A SURVEYijdpsjournal
Breast cancer has become a common factor now-a-days. Despite the fact, not all general hospitals
have the facilities to diagnose breast cancer through mammograms. Waiting for diagnosing a breast
cancer for a long time may increase the possibility of the cancer spreading. Therefore a computerized
breast cancer diagnosis has been developed to reduce the time taken to diagnose the breast cancer and
reduce the death rate. This paper summarizes the survey on breast cancer diagnosis using various machine
learning algorithms and methods, which are used to improve the accuracy of predicting cancer. This survey
can also help us to know about number of papers that are implemented to diagnose the breast cancer.
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...Devansh16
YouTube video: https://www.youtube.com/watch?v=Ao-19L0sLOI
SinGAN-Seg: Synthetic Training Data Generation for Medical Image Segmentation
Vajira Thambawita, Pegah Salehi, Sajad Amouei Sheshkal, Steven A. Hicks, Hugo L.Hammer, Sravanthi Parasa, Thomas de Lange, Pål Halvorsen, Michael A. Riegler
Processing medical data to find abnormalities is a time-consuming and costly task, requiring tremendous efforts from medical experts. Therefore, Ai has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. AI tools highly depend on data for training the models. However, there are several constraints to access to large amounts of medical data to train machine learning algorithms in the medical domain, e.g., due to privacy concerns and the costly, time-consuming medical data annotation process. To address this, in this paper we present a novel synthetic data generation pipeline called SinGAN-Seg to produce synthetic medical data with the corresponding annotated ground truth masks. We show that these synthetic data generation pipelines can be used as an alternative to bypass privacy concerns and as an alternative way to produce artificial segmentation datasets with corresponding ground truth masks to avoid the tedious medical data annotation process. As a proof of concept, we used an open polyp segmentation dataset. By training UNet++ using both the real polyp segmentation dataset and the corresponding synthetic dataset generated from the SinGAN-Seg pipeline, we show that the synthetic data can achieve a very close performance to the real data when the real segmentation datasets are large enough. In addition, we show that synthetic data generated from the SinGAN-Seg pipeline improving the performance of segmentation algorithms when the training dataset is very small. Since our SinGAN-Seg pipeline is applicable for any medical dataset, this pipeline can be used with any other segmentation datasets.
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as: arXiv:2107.00471 [eess.IV]
(or arXiv:2107.00471v1 [eess.IV] for this version)
Reach out to me:
Check out my other articles on Medium. : https://machine-learning-made-simple....
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn: https://www.linkedin.com/in/devansh-d...
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75
Brain Image Fusion using DWT and Laplacian Pyramid Approach and Tumor Detecti...INFOGAIN PUBLICATION
Image fusion is the process of combining important information from two or more images into a single image. The resulting image will be more enhanced than any of the input pictures. The idea of combining multiple image modalities to furnish a single, more enhanced image is well established, special fusion methods have been proposed in literature. This paper is based on image fusion using laplacian pyramid and Discreet Wavelet Transform (DWT) methods. This system uses an easy and effective algorithm for multi-focus image fusion which uses fusion rules to create fused image. Subsequently, the fused image is obtained by applying inverse discreet wavelet transform. After fused image is obtained, watershed segmentation algorithm is applied to detect the tumor part in fused image.
Breast cancer detection from histopathological images is done using deep learning and transfer learning techniques. Image processing is done for better accuracy. CNN and DenseNet-121 algorithms are used. 90.9 % accuracy is achieved using CNN and 88% accuracy is achieved using Transfer learning.
FACIAL AGE ESTIMATION USING TRANSFER LEARNING AND BAYESIAN OPTIMIZATION BASED...sipij
Age estimation of unrestricted imaging circumstances has attracted an augmented recognition as it is
appropriate in several real-world applications such as surveillance, face recognition, age synthesis, access
control, and electronic customer relationship management. Current deep learning-based methods have
displayed encouraging performance in age estimation field. Males and Females have a variable type of
appearance aging pattern; this results in age differently. This fact leads to assuming that using gender
information may improve the age estimator performance. We have proposed a novel model based on
Gender Classification. A Convolutional Neural Network (CNN) is used to get Gender Information, then
Bayesian Optimization is applied to this pre-trained CNN when fine-tuned for age estimation task.
Bayesian Optimization reduces the classification error on the validation set for the pre-trained model.
Extensive experiments are done to assess our proposed model on two data sets: FERET and FG-NET. The
experiments’ result indicates that using a pre-trained CNN containing Gender Information with Bayesian
Optimization outperforms the state of the arts on FERET and FG-NET data sets with a Mean Absolute
Error (MAE) of 1.2 and 2.67 respectively.
An Artificial Neural Network Model for Neonatal Disease DiagnosisWaqas Tariq
The significance of disease diagnosis by artificial intelligence is not obscure now days. The increasing demand of Artificial Neural Network application for predicting the disease shows better performance in the field of medical decision making. This paper represents the use of artificial neural networks in predicting neonatal disease diagnosis. The proposed technique involves training a Multi Layer Perceptron with a BP learning algorithm to recognize a pattern for the diagnosing and prediction of neonatal diseases. A comparative study of using different training algorithm of MLP, Quick Propagation, Conjugate Gradient Descent, shows the higher prediction accuracy. The Backpropogation algorithm was used to train the ANN architecture and the same has been tested for the various categories of neonatal disease. About 94 cases of different sign and symptoms parameter have been tested in this model. This study exhibits ANN based prediction of neonatal disease and improves the diagnosis accuracy of 75% with higher stability. Key words: Artificial Intelligence, Multi Layer Perceptron, Neural Network, Neonate
When deep learners change their mind learning dynamics for active learningDevansh16
Abstract:
Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
3D Segmentation of Brain Tumor ImagingIJAEMSJORNAL
A brain tumor is a collection of anomalous cells that grow in or around the brain. Brain tumors affect the humans badly, it can disrupt proper brain function and be life-threatening. In this project, we have proposed a system to detect, segment, and classify the tumors present in the brain. Once the brain tumor is identified at the very beginning, proper treatments can be done and it may be cured.
Classification of MR medical images Based Rough-Fuzzy KMeansIOSRJM
Image classification is very significant for many vision of computer and it has acquired significant solicitude from industry and research over last years. We, explore an algorithm via the approximation of Fuzzy -Rough- K-means (FRKM), to bring to light data reliance, data decreasing, estimated of the classification (partition) of the set, and induction of rule from databases of the image. Rough theory provide a successful approach of carrying on precariousness and furthermore applied for image classification feature similarity dimensionality reduction and style categorization. The suggested algorithm is derived from a k means classifier using rough theory for segmentation (or processing) of the image which is moreover split into two portions. Exploratory conclusion output that, suggested method execute well and get better the classification outputs in the fuzzy areas of the image. The results explain that the FRKM execute well than purely using rough set, it can get 94.4% accuracy figure of image classification that, is over 88.25% by using only rough set.
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...Devansh16
YouTube video: https://www.youtube.com/watch?v=Ao-19L0sLOI
SinGAN-Seg: Synthetic Training Data Generation for Medical Image Segmentation
Vajira Thambawita, Pegah Salehi, Sajad Amouei Sheshkal, Steven A. Hicks, Hugo L.Hammer, Sravanthi Parasa, Thomas de Lange, Pål Halvorsen, Michael A. Riegler
Processing medical data to find abnormalities is a time-consuming and costly task, requiring tremendous efforts from medical experts. Therefore, Ai has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. AI tools highly depend on data for training the models. However, there are several constraints to access to large amounts of medical data to train machine learning algorithms in the medical domain, e.g., due to privacy concerns and the costly, time-consuming medical data annotation process. To address this, in this paper we present a novel synthetic data generation pipeline called SinGAN-Seg to produce synthetic medical data with the corresponding annotated ground truth masks. We show that these synthetic data generation pipelines can be used as an alternative to bypass privacy concerns and as an alternative way to produce artificial segmentation datasets with corresponding ground truth masks to avoid the tedious medical data annotation process. As a proof of concept, we used an open polyp segmentation dataset. By training UNet++ using both the real polyp segmentation dataset and the corresponding synthetic dataset generated from the SinGAN-Seg pipeline, we show that the synthetic data can achieve a very close performance to the real data when the real segmentation datasets are large enough. In addition, we show that synthetic data generated from the SinGAN-Seg pipeline improving the performance of segmentation algorithms when the training dataset is very small. Since our SinGAN-Seg pipeline is applicable for any medical dataset, this pipeline can be used with any other segmentation datasets.
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as: arXiv:2107.00471 [eess.IV]
(or arXiv:2107.00471v1 [eess.IV] for this version)
Reach out to me:
Check out my other articles on Medium. : https://machine-learning-made-simple....
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn: https://www.linkedin.com/in/devansh-d...
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75
Brain Image Fusion using DWT and Laplacian Pyramid Approach and Tumor Detecti...INFOGAIN PUBLICATION
Image fusion is the process of combining important information from two or more images into a single image. The resulting image will be more enhanced than any of the input pictures. The idea of combining multiple image modalities to furnish a single, more enhanced image is well established, special fusion methods have been proposed in literature. This paper is based on image fusion using laplacian pyramid and Discreet Wavelet Transform (DWT) methods. This system uses an easy and effective algorithm for multi-focus image fusion which uses fusion rules to create fused image. Subsequently, the fused image is obtained by applying inverse discreet wavelet transform. After fused image is obtained, watershed segmentation algorithm is applied to detect the tumor part in fused image.
Breast cancer detection from histopathological images is done using deep learning and transfer learning techniques. Image processing is done for better accuracy. CNN and DenseNet-121 algorithms are used. 90.9 % accuracy is achieved using CNN and 88% accuracy is achieved using Transfer learning.
FACIAL AGE ESTIMATION USING TRANSFER LEARNING AND BAYESIAN OPTIMIZATION BASED...sipij
Age estimation of unrestricted imaging circumstances has attracted an augmented recognition as it is
appropriate in several real-world applications such as surveillance, face recognition, age synthesis, access
control, and electronic customer relationship management. Current deep learning-based methods have
displayed encouraging performance in age estimation field. Males and Females have a variable type of
appearance aging pattern; this results in age differently. This fact leads to assuming that using gender
information may improve the age estimator performance. We have proposed a novel model based on
Gender Classification. A Convolutional Neural Network (CNN) is used to get Gender Information, then
Bayesian Optimization is applied to this pre-trained CNN when fine-tuned for age estimation task.
Bayesian Optimization reduces the classification error on the validation set for the pre-trained model.
Extensive experiments are done to assess our proposed model on two data sets: FERET and FG-NET. The
experiments’ result indicates that using a pre-trained CNN containing Gender Information with Bayesian
Optimization outperforms the state of the arts on FERET and FG-NET data sets with a Mean Absolute
Error (MAE) of 1.2 and 2.67 respectively.
An Artificial Neural Network Model for Neonatal Disease DiagnosisWaqas Tariq
The significance of disease diagnosis by artificial intelligence is not obscure now days. The increasing demand of Artificial Neural Network application for predicting the disease shows better performance in the field of medical decision making. This paper represents the use of artificial neural networks in predicting neonatal disease diagnosis. The proposed technique involves training a Multi Layer Perceptron with a BP learning algorithm to recognize a pattern for the diagnosing and prediction of neonatal diseases. A comparative study of using different training algorithm of MLP, Quick Propagation, Conjugate Gradient Descent, shows the higher prediction accuracy. The Backpropogation algorithm was used to train the ANN architecture and the same has been tested for the various categories of neonatal disease. About 94 cases of different sign and symptoms parameter have been tested in this model. This study exhibits ANN based prediction of neonatal disease and improves the diagnosis accuracy of 75% with higher stability. Key words: Artificial Intelligence, Multi Layer Perceptron, Neural Network, Neonate
When deep learners change their mind learning dynamics for active learningDevansh16
Abstract:
Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
3D Segmentation of Brain Tumor ImagingIJAEMSJORNAL
A brain tumor is a collection of anomalous cells that grow in or around the brain. Brain tumors affect the humans badly, it can disrupt proper brain function and be life-threatening. In this project, we have proposed a system to detect, segment, and classify the tumors present in the brain. Once the brain tumor is identified at the very beginning, proper treatments can be done and it may be cured.
Classification of MR medical images Based Rough-Fuzzy KMeansIOSRJM
Image classification is very significant for many vision of computer and it has acquired significant solicitude from industry and research over last years. We, explore an algorithm via the approximation of Fuzzy -Rough- K-means (FRKM), to bring to light data reliance, data decreasing, estimated of the classification (partition) of the set, and induction of rule from databases of the image. Rough theory provide a successful approach of carrying on precariousness and furthermore applied for image classification feature similarity dimensionality reduction and style categorization. The suggested algorithm is derived from a k means classifier using rough theory for segmentation (or processing) of the image which is moreover split into two portions. Exploratory conclusion output that, suggested method execute well and get better the classification outputs in the fuzzy areas of the image. The results explain that the FRKM execute well than purely using rough set, it can get 94.4% accuracy figure of image classification that, is over 88.25% by using only rough set.
An Efficient PSO Based Ensemble Classification Model on High Dimensional Data...ijsc
As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to
analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection based ensemble learning models is to classify the high dimensional data with high computational efficiency and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
MEDICAL DIAGNOSIS CLASSIFICATION USING MIGRATION BASED DIFFERENTIAL EVOLUTION...cscpconf
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
Clustering and Classification of Cancer Data Using Soft Computing Technique IOSR Journals
Clustering and classification of cancer data has been used with success in field of medical side. In
this paper the two algorithm K-means and fuzzy C-means proposed for the comparison and find the accuracy of
the result. this paper address the problem of learning to classify the cancer data with two different method and
information derived from the training and testing .various soft computing based classification and show the
comparison of classification technique and classification of this health care data .this paper present the
accuracy of the result in cancer data.
The current big challenge facing radiologists in healthcare is the automatic detection and classification of masses in breast mammogram images. In the last few years, many researchers have proposed various solutions to this problem. These solutions are effectively dependent and work on annotated breast image data. But these solutions fail when applied to unlabeled and non-annotated breast image data. Therefore, this paper provides the solution to this problem with the help of a neural network that considers any kind of unlabeled data for its procedure. In this solution, the algorithm automatically extracts tumors in images using a segmentation approach, and after that, the features of the tumor are extracted for further processing. This approach used a double thresholding-based segmentation technique to obtain a perfect location of the tumor region, which was not possible in existing techniques in the literature. The experimental results also show that the proposed algorithm provides better accuracy compared to the accuracy of existing algorithms in the literature.
A NEW APPROACH OF BRAIN TUMOR SEGMENTATION USING FAST CONVERGENCE LEVEL SETijbesjournal
Segmentation of region of interest has a critical task in image processing applications. The accuracy of Segmentation is based on processing methodology and limiting value used. In this paper, an enhanced approach of region segmentation using level set (LS) method is proposed, which is achieved by using cross over point in the valley point as a new dynamic stopping criterion in the level set segmentation. The proposed method has been tested with developed database of MR Images. From the test results, it is found that proposed method improves the convergence performance such as complexity in terms of number of iterations, delay and resource overhead as compared to conventional level set based segmentation
approach.
Machine Learning Based Approaches for Cancer Classification Using Gene Expres...mlaij
The classification of different types of tumor is of great importance in cancer diagnosis and drug discovery.
Earlier studies on cancer classification have limited diagnostic ability. The recent development of DNA
microarray technology has made monitoring of thousands of gene expression simultaneously. By using this
abundance of gene expression data researchers are exploring the possibilities of cancer classification.
There are number of methods proposed with good results, but lot of issues still need to be addressed. This
paper present an overview of various cancer classification methods and evaluate these proposed methods
based on their classification accuracy, computational time and ability to reveal gene information. We have
also evaluated and introduced various proposed gene selection method. In this paper, several issues
related to cancer classification have also been discussed.
Breast cancer is the leading cause of death for women worldwide. Cancer can be discovered early, lowering the rate of death. Machine learning techniques are a hot field of research, and they have been shown to be helpful in cancer prediction and early detection. The primary purpose of this research is to identify which machine learning algorithms are the most successful in predicting and diagnosing breast cancer, according to five criteria: specificity, sensitivity, precision, accuracy, and F1 score. The project is finished in the Anaconda environment, which uses Python's NumPy and SciPy numerical and scientific libraries as well as matplotlib and Pandas. In this study, the Wisconsin diagnostic breast cancer dataset was used to evaluate eleven machine learning classifiers: decision tree, quadratic discriminant analysis, AdaBoost, Bagging meta estimator, Extra randomized trees, Gaussian process classifier, Ridge, Gaussian nave Bayes, k-Nearest neighbors, multilayer perceptron, and support vector classifier. During performance analysis, extremely randomized trees outperformed all other classifiers with an F1-score of 96.77% after data collection and data analysis.
Classification of Breast Cancer Diseases using Data Mining Techniquesinventionjournals
Medical data mining has great deal for exploring new knowledge from large amount of data. Classification is one of the important data mining techniques for classification of data. In this research work, we have used various data mining based classification techniques for classification of cancer diseases patient or not. We applied the Breast Cancer-Wisconsin (Original) data set into different data mining techniques and compared the accuracy of models with two different data partitions. BayesNet achieved highest accuracy as 97.13% in case of 10-fold data partitions. We have also applied the info gain feature selection technique on BayesNet and Support Vector Machine (SVM) and achieved best accuracy 97.28% accuracy with BayesNet in case of 6 feature subset.
Computer Aided System for Detection and Classification of Breast CancerIJITCA Journal
Breast cancer is one of the most important causes of death among all type of cancers for grown-up and
older women, mainly in developed countries, and its rate is rising. Since the cause of this disease is not yet
known, early detection is the best way to decrease the breast cancer mortality. At present, early detection of
breast cancer is attained by means of mammography. An intelligent computer-aided diagnosis system can
be very helpful for radiologist in detecting and diagnosing cancerous cell patterns earlier and faster than
typical screening programs. This paper proposes a computer aided system for automatic detection and
classification of breast cancer in mammogram images. Intuitionistic Fuzzy C-Means clustering technique
has been used to identify the suspicious region or the Region of Interest automatically. Then, the feature
data base is designed using histogram features, Gray Level Concurrence wavelet features and wavelet
energy features. Finally, the feature database is submitted to self-adaptive resource allocation network
classifier for classification of mammogram image as normal, benign or malignant. The proposed system is
verified with 322 mammograms from the Mammographic Image Analysis Society Database. The results
show that the proposed system produces better results.
Robust Breast Cancer Diagnosis on Four Different Datasets Using Multi-Classif...ahmad abdelhafeez
The goal of this paper is to compare between different classifiers or multi-classifiers fusion with respect to accuracy in discovering breast cancer for four different data sets. We present an implementation among various classification techniques which represent the most known algorithms in this field on four different datasets of breast cancer two for diagnosis and two for prognosis. We present a fusion between classifiers to get the best multi-classifier fusion approach to each data set individually. By using confusion matrix to get classification accuracy which built in 10-fold cross validation technique. Also, using fusion majority voting (the mode of the classifier output). The experimental results show that no classification technique is better than the other if used for all datasets, since the classification task is affected by the type of dataset. By using multi-classifiers fusion the results show that accuracy improved in three datasets out of four.
Controlling informative features for improved accuracy and faster predictions...Damian R. Mingle, MBA
Identification of suitable biomarkers for accurate prediction of phenotypic outcomes is a goal for personalized medicine. However, current machine learning approaches are either too complex or perform poorly.
For more information:
http://societyofdatascientists.com/controlling-informative-features-for-improved-accuracy-and-faster-predictions-in-omentum-cancer-models/?src=slideshare
Twin support vector machine using kernel function for colorectal cancer detec...journalBEEI
Nowadays, machine learning technology is needed in the medical field. therefore, this research is useful for solving problems in the medical field by using machine learning. Many cases of colorectal cancer are diagnosed late. When colorectal cancer is detected, the cancer is usually well developed. Machine learning is an approach that is part of artificial intelligence and can detect colorectal cancer early. This study discusses colorectal cancer detection using twin support vector machine (SVM) method and kernel function i.e. linear kernels, polynomial kernels, RBF kernels, and gaussian kernels. By comparing the accuracy and running time, then we will know which method is better in classifying the colorectal cancer dataset that we get from Al-Islam Hospital, Bandung, Indonesia. The results showed that polynomial kernels has better accuracy and running time. It can be seen with a maximum accuracy of twin SVM using polynomial kernels 86% and 0.502 seconds running time.
SVM &GA-CLUSTERING BASED FEATURE SELECTION APPROACH FOR BREAST CANCER DETECTIONijscai
Mortality leading among women in developed countries is breast cancer. Breast cancer is women's second most prominent cause of cancer mortality worldwide. In recent decades, women's high prevalence of breast cancer has risen dramatically. This paper discussed several data analysis methods used to detect breast cancer early. Breast cancer diagnosis distinguishes benign and malignant breast lumps. Using data processing tools, we tackled this disease analysis. Data mining is an important step of library discovery where intelligent methods are used to detect patterns. Several clinical breast cancer studies were conducted using soft computing and machine learning techniques. Sometimes their algorithms are easier, easier, or more comprehensive than others. This research is focused on genetic programming and machine learning algorithms to reliably identify benign and malignant breast cancer. This study aimed to optimise the testing algorithm. We used genetic programming methods to choose classification machines' best features and parameter values. Data mining is an important step of library discovery where intelligent methods are used to detect patterns. We are analysing data accessible from the U.C.I. deep-learning data set in Wisconsin. In this experiment, we equate four Weka clustering strategies with genetic clustering. A comparison of results reveals that sequential minimal optimization (S.M.O.) is better than I.B.K. and B.F. Tree processes, i.e. 97.71%.
Advanced Computing: An International Journal (ACIJ) is a peer-reviewed, open access peer-reviewed journal that publishes articles which contribute new results in all areas of the advanced computing. The journal focuses on all technical and practical aspects of high performance computing, green computing, pervasive computing, cloud computing etc. The goal of this journal is to bring together researchers and a practitioners from academia and industry to focus on understanding advances in computing and establishing new collaborations in these areas.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of computing.
Call for Papers - Advanced Computing An International Journal (ACIJ) (2).pdfacijjournal
Submit your Research Papers!!!
Advanced Computing: An International Journal ( ACIJ )
ISSN: 2229 -6727 [Online] ; 2229 - 726X [Print]
Webpage URL: http://airccse.org/journal/acij/acij.html
Submission URL: http://coneco2009.com/submissions/imagination/home.html
Submission Deadline : April 08, 2023
Here's where you can reach us : acijjournal@yahoo.com or acij@aircconline
Advanced Computing: An International Journal (ACIJ
)
is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of the advancedcomputing. The journal focuses on all technical and practical aspects of high performancecomputing, green computing, pervasive computing, cloud computing etc. The goal of this journalis to bring together researchers anda practitioners from academia and industry to focus onunderstanding advances in computing and establishing new collaborations in these areas
Submit your Research Papers!!!
Advanced Computing: An International Journal ( ACIJ )
ISSN: 2229 -6727 [Online] ; 2229 - 726X [Print]
Webpage URL: http://airccse.org/journal/acij/acij.html
Submission URL: http://coneco2009.com/submissions/imagination/home.html
Here's where you can reach us : acijjournal@yahoo.com or acij@aircconline.com
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)acijjournal
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)provides a forum for researchers who address this issue and to present their work in a peer-reviewed forum.
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)acijjournal
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)provides a forum for researchers who address this issue and to present their work in a peer-reviewed forum.
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)acijjournal
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)provides a forum for researchers who address this issue and to present their work in a peer-reviewed forum.
4thInternational Conference on Machine Learning & Applications (CMLA 2022)acijjournal
4thInternational Conference on Machine Learning & Applications (CMLA 2022)will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)acijjournal
7thInternational Conference on Data Mining & Knowledge Management (DaKM 2022)provides a forum for researchers who address this issue and to present their work in a peer-reviewed forum.Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas, but are not limited to these topics only.
3rdInternational Conference on Natural Language Processingand Applications (N...acijjournal
3rdInternational Conference on Natural Language Processing and Applications (NLPA 2022)will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Natural Language Computing and its applications. The Conference looks for significant contributions to all major fieldsof the Natural Language processing in theoretical and practical aspects.
4thInternational Conference on Machine Learning & Applications (CMLA 2022)acijjournal
4thInternational Conference on Machine Learning & Applications (CMLA 2022)will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
Graduate School Cyber Portfolio: The Innovative Menu For Sustainable Developmentacijjournal
In today’s milieu, new demands and trends emerge in the field of Education giving teachers of Higher Education Institutions (HEI’s) no choice but to be innovative to cope with the fast changing technology. To be naturally innovative, a graduate school teacher needs to be technologically and pedagogically competent. One of the ways to be on this level is by creating his cyber portfolio to support students’ eportfolio for lifelong learning. Cyber portfolio is an innovative menu for teachers who seek out strategies to integrate technology in their lessons. This paper presents a straightforward preparation on how to innovate a cyber portfolio that has its practical and breakthrough solution against expensive and inflexible vended software which often saddle many universities. Additionally, this cyber portfolio is free and it addresses the 21st century skills of graduate students blended with higher order thinking skills, multiple intelligence, technology and multimedia.
Genetic Algorithms and Programming - An Evolutionary Methodologyacijjournal
Genetic programming (GP) is an automated method for creating a working computer program from a high-level problem statement of a problem. Genetic programming starts from a high-level statement of “what needs to be done” and automatically creates a computer program to solve the problem. In artificial intelligence, genetic programming (GP) is an evolutionary algorithm-based methodology inspired by biological evolution to find computer programs that perform a user defined task. It is a specialization of genetic algorithms (GA) where each individual is a computer program. It is a machine learning technique used to optimize a population of computer programs according to a fitness span determined by a program's ability to perform a given computational task. This paper presents a idea of the various principles of genetic programming which includes, relative effectiveness of mutation, crossover, breeding computer programs and fitness test in genetic programming. The literature of traditional genetic algorithms contains related studies, but through GP, it saves time by freeing the human from having to design complex algorithms. Not only designing the algorithms but creating ones that give optimal solutions than traditional counterparts in noteworthy ways.
Data Transformation Technique for Protecting Private Information in Privacy P...acijjournal
Data mining is the process of extracting patterns from data. Data mining is seen as an increasingly important tool by modern business to transform data into an informational advantage. Data
Mining can be utilized in any organization that needs to find patterns or relationships in their data. A group of techniques that find relationships that have not previously been discovered. In many situations, the extracted patterns are highly private and it should not be disclosed. In order to maintain the secrecy of data,
there is in need of several techniques and algorithms for modifying the original data in order to limit the extraction of confidential patterns. There have been two types of privacy in data mining. The first type of privacy is that the data is altered so that the mining result will preserve certain privacy. The second type of privacy is that the data is manipulated so that the mining result is not affected or minimally affected. The aim of privacy preserving data mining researchers is to develop data mining techniques that could be
applied on data bases without violating the privacy of individuals. Many techniques for privacy preserving data mining have come up over the last decade. Some of them are statistical, cryptographic, randomization methods, k-anonymity model, l-diversity and etc. In this work, we propose a new perturbative masking technique known as data transformation technique can be used for protecting the sensitive information. An
experimental result shows that the proposed technique gives the better result compared with the existing technique.
Advanced Computing: An International Journal (ACIJ) acijjournal
Advanced Computing: An International Journal (ACIJ) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of the advanced computing. The journal focuses on all technical and practical aspects of high performance computing, green computing, pervasive computing, cloud computing etc. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on understanding advances in computing and establishing new collaborations in these areas.
E-Maintenance: Impact Over Industrial Processes, Its Dimensions & Principlesacijjournal
During the course of the industrial 4.0 era, companies have been exponentially developed and have
digitized almost the whole business system to stick to their performance targets and to keep or to even
enlarge their market share. Maintenance function has obviously followed the trend as it’s considered one
of the most important processes in every enterprise as it impacts a group of the most critical performance
indicators such as: cost, reliability, availability, safety and productivity. E-maintenance emerged in early
2000 and now is a common term in maintenance literature representing the digitalized side of maintenance
whereby assets are monitored and controlled over the internet. According to literature, e-maintenance has
a remarkable impact on maintenance KPIs and aims at ambitious objectives like zero-downtime.
10th International Conference on Software Engineering and Applications (SEAPP...acijjournal
10th International Conference on Software Engineering and Applications (SEAPP 2021) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Software Engineering and Applications. The goal of this Conference is to bring together researchers and practitioners from academia and industry to focus on understanding Modern software engineering concepts and establishing new collaborations in these areas.
10th International conference on Parallel, Distributed Computing and Applicat...acijjournal
10th International conference on Parallel, Distributed Computing and Applications (IPDCA 2021) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Parallel, Distributed Computing. Original papers are invited on Algorithms and Applications, computer Networks, Cyber trust and security, Wireless networks and mobile Computing and Bioinformatics. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
DETECTION OF FORGERY AND FABRICATION IN PASSPORTS AND VISAS USING CRYPTOGRAPH...acijjournal
In this paper, we present a novel solution to detect forgery and fabrication in passports and visas using
cryptography and QR codes. The solution requires that the passport and visa issuing authorities obtain a
cryptographic key pair and publish their public key on their website. Further they are required to encrypt
the passport or visa information with their private key, encode the ciphertext in a QR code and print it on
the passport or visa they issue to the applicant.
The issuing authorities are also required to create a mobile or desktop QR code scanning app and place it
for download on their website or Google Play Store and iPhone App Store. Any individual or immigration
authority that needs to check the passport or visa for forgery and fabrication can scan its QR code, which
will decrypt the ciphertext encoded in the QR code using the public key stored in the app memory and
displays the passport or visa information on the app screen. The details on the app screen can be
compared with the actual details printed on the passport or visa. Any mismatch between the two is a clear
indication of forgery or fabrication.
Discussed the need for a universal desktop and mobile app that can be used by immigration authorities and
consulates all over the world to enable fast checking of passports and visas at ports of entry for forgery
and fabrication.
Detection of Forgery and Fabrication in Passports and Visas Using Cryptograph...acijjournal
In this paper, wepresenta novel solution to detect forgery and fabrication in passports and visas using cryptography and QR codes. The solution requires that the passport and visa issuing authorities obtain a cryptographic key pair and publish their public key on their website. Further they are required to encrypt the passport or visa information with their private key, encode the ciphertext in a QR code and print it on the passport or visa they issue to the applicant.
The issuing authorities are also required to create a mobile or desktop QR code scanning app and place it for download on their website or Google Play Store and iPhone App Store. Any individual or immigration authority that needs to check the passport or visa for forgery and fabrication can scan its QR code, which will decrypt the ciphertext encoded in the QR code using the public key stored in the app memory and displays the passport or visa information on the app screen. The details on the app screen can be compared with the actual details printed on the passport or visa. Any mismatch between the two is a clear indication of forgery or fabrication.
Discussed the need for a universal desktop and mobile app that can be used by immigration authorities and consulates all over the world to enable fast checking of passports and visas at ports of entry for forgery and fabrication.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualityInflectra
In this insightful webinar, Inflectra explores how artificial intelligence (AI) is transforming software development and testing. Discover how AI-powered tools are revolutionizing every stage of the software development lifecycle (SDLC), from design and prototyping to testing, deployment, and monitoring.
Learn about:
• The Future of Testing: How AI is shifting testing towards verification, analysis, and higher-level skills, while reducing repetitive tasks.
• Test Automation: How AI-powered test case generation, optimization, and self-healing tests are making testing more efficient and effective.
• Visual Testing: Explore the emerging capabilities of AI in visual testing and how it's set to revolutionize UI verification.
• Inflectra's AI Solutions: See demonstrations of Inflectra's cutting-edge AI tools like the ChatGPT plugin and Azure Open AI platform, designed to streamline your testing process.
Whether you're a developer, tester, or QA professional, this webinar will give you valuable insights into how AI is shaping the future of software delivery.
Essentials of Automations: Optimizing FME Workflows with ParametersSafe Software
Are you looking to streamline your workflows and boost your projects’ efficiency? Do you find yourself searching for ways to add flexibility and control over your FME workflows? If so, you’re in the right place.
Join us for an insightful dive into the world of FME parameters, a critical element in optimizing workflow efficiency. This webinar marks the beginning of our three-part “Essentials of Automation” series. This first webinar is designed to equip you with the knowledge and skills to utilize parameters effectively: enhancing the flexibility, maintainability, and user control of your FME projects.
Here’s what you’ll gain:
- Essentials of FME Parameters: Understand the pivotal role of parameters, including Reader/Writer, Transformer, User, and FME Flow categories. Discover how they are the key to unlocking automation and optimization within your workflows.
- Practical Applications in FME Form: Delve into key user parameter types including choice, connections, and file URLs. Allow users to control how a workflow runs, making your workflows more reusable. Learn to import values and deliver the best user experience for your workflows while enhancing accuracy.
- Optimization Strategies in FME Flow: Explore the creation and strategic deployment of parameters in FME Flow, including the use of deployment and geometry parameters, to maximize workflow efficiency.
- Pro Tips for Success: Gain insights on parameterizing connections and leveraging new features like Conditional Visibility for clarity and simplicity.
We’ll wrap up with a glimpse into future webinars, followed by a Q&A session to address your specific questions surrounding this topic.
Don’t miss this opportunity to elevate your FME expertise and drive your projects to new heights of efficiency.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. What’s changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
State of ICS and IoT Cyber Threat Landscape Report 2024 previewPrayukth K V
The IoT and OT threat landscape report has been prepared by the Threat Research Team at Sectrio using data from Sectrio, cyber threat intelligence farming facilities spread across over 85 cities around the world. In addition, Sectrio also runs AI-based advanced threat and payload engagement facilities that serve as sinks to attract and engage sophisticated threat actors, and newer malware including new variants and latent threats that are at an earlier stage of development.
The latest edition of the OT/ICS and IoT security Threat Landscape Report 2024 also covers:
State of global ICS asset and network exposure
Sectoral targets and attacks as well as the cost of ransom
Global APT activity, AI usage, actor and tactic profiles, and implications
Rise in volumes of AI-powered cyberattacks
Major cyber events in 2024
Malware and malicious payload trends
Cyberattack types and targets
Vulnerability exploit attempts on CVEs
Attacks on counties – USA
Expansion of bot farms – how, where, and why
In-depth analysis of the cyber threat landscape across North America, South America, Europe, APAC, and the Middle East
Why are attacks on smart factories rising?
Cyber risk predictions
Axis of attacks – Europe
Systemic attacks in the Middle East
Download the full report from here:
https://sectrio.com/resources/ot-threat-landscape-reports/sectrio-releases-ot-ics-and-iot-security-threat-landscape-report-2024/
JMeter webinar - integration with InfluxDB and GrafanaRTTS
Watch this recorded webinar about real-time monitoring of application performance. See how to integrate Apache JMeter, the open-source leader in performance testing, with InfluxDB, the open-source time-series database, and Grafana, the open-source analytics and visualization application.
In this webinar, we will review the benefits of leveraging InfluxDB and Grafana when executing load tests and demonstrate how these tools are used to visualize performance metrics.
Length: 30 minutes
Session Overview
-------------------------------------------
During this webinar, we will cover the following topics while demonstrating the integrations of JMeter, InfluxDB and Grafana:
- What out-of-the-box solutions are available for real-time monitoring JMeter tests?
- What are the benefits of integrating InfluxDB and Grafana into the load testing stack?
- Which features are provided by Grafana?
- Demonstration of InfluxDB and Grafana using a practice web application
To view the webinar recording, go to:
https://www.rttsweb.com/jmeter-integration-webinar
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
Connector Corner: Automate dynamic content and events by pushing a buttonDianaGray10
Here is something new! In our next Connector Corner webinar, we will demonstrate how you can use a single workflow to:
Create a campaign using Mailchimp with merge tags/fields
Send an interactive Slack channel message (using buttons)
Have the message received by managers and peers along with a test email for review
But there’s more:
In a second workflow supporting the same use case, you’ll see:
Your campaign sent to target colleagues for approval
If the “Approve” button is clicked, a Jira/Zendesk ticket is created for the marketing design team
But—if the “Reject” button is pushed, colleagues will be alerted via Slack message
Join us to learn more about this new, human-in-the-loop capability, brought to you by Integration Service connectors.
And...
Speakers:
Akshay Agnihotri, Product Manager
Charlie Greenberg, Host
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Albert Hoitingh
In this session I delve into the encryption technology used in Microsoft 365 and Microsoft Purview. Including the concepts of Customer Key and Double Key Encryption.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
An approach for breast cancer diagnosis classification using neural network
1. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
DOI:10.5121/acij.2015.6101 1
AN APPROACH FOR BREAST CANCER DIAGNOSIS
CLASSIFICATION USING NEURAL NETWORK
Htet Thazin Tike Thein1
and Khin Mo Mo Tun2
1
Ph.D Student, University of Computer Studies, Yangon, Myanmar
2
Department of Computational Mathematics, University of Computer Studies, Yangon,
Myanmar
ABSTRACT
Artificial neural network has been widely used in various fields as an intelligent tool in recent years, such
as artificial intelligence, pattern recognition, medical diagnosis, machine learning and so on. The
classification of breast cancer is a medical application that poses a great challenge for researchers and
scientists. Recently, the neural network has become a popular tool in the classification of cancer datasets.
Classification is one of the most active research and application areas of neural networks. Major
disadvantages of artificial neural network (ANN) classifier are due to its sluggish convergence and always
being trapped at the local minima. To overcome this problem, differential evolution algorithm (DE) has
been used to determine optimal value or near optimal value for ANN parameters. DE has been applied
successfully to improve ANN learning from previous studies. However, there are still some issues on DE
approach such as longer training time and lower classification accuracy. To overcome these problems,
island based model has been proposed in this system. The aim of our study is to propose an approach for
breast cancer distinguishing between different classes of breast cancer. This approach is based on the
Wisconsin Diagnostic and Prognostic Breast Cancer and the classification of different types of breast
cancer datasets. The proposed system implements the island-based training method to be better accuracy
and less training time by using and analysing between two different migration topologies.
KEYWORDS
Neural Network, Differential Evolution, Island Model, Classification, Breast Cancer Diagnosis
1. INTRODUCTION
Breast cancer, is cancer that affects today more women in the world. Thus, the fight against
cancer is far from completed. Medicine advances on all fronts to improve the care of patients and
defeat this disease of the century. Because of this, it is essential that several disciplines continue
to make their contribution and particularly data mining or artificial Intelligence. To provide
assistance to the medical, robust and reliable diagnosis, neural networks can be a powerful tool
for distributed diagnosis [1]. In this paper, we tested the performance of the neural networks
based on the Wisconsin Breast Cancer Database (WBCD). The problem of breast cancer
detection led researchers and experts in this field to focus on other trends, such that new
technologies other human to address this social problem. The objective of our work is to create a
new approach that allows whether a patient has a benign cancer or malignant following several
descriptors. To achieve this, we propose a solution based on the concept of neural networks [2]
[3] [4]. Recently, the neural network has become a popular tool in the classification of Cancer
Dataset [5] [6] [7] [8]. This is particularly due to its ability to represent the behaviour of linear or
2. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
2
nonlinear functions multidimensional and complex.
Wisconsin Breast Cancer Data (WBCD) is analysed by various researchers on medical
diagnosis of breast cancer in neural network literature [15],[16],[17],[18],[19]. In [20] Breast
cancer is diagnosed using feed forward neural networks by comparing the hidden neurons. In
[21], the performance comparison of the multi-layered perceptron networks using various back
propagation algorithms for breast cancer diagnosis is discussed. The training algorithms used are
gradient descent with momentum and adaptive learning, resilient back propagation, Quasi-
Newton and Levenberg-Marquardt. The performances of these four algorithms are compared with
the standard steepest descent back propagation algorithm. The MLP network using the
Levenberg-Marquardt algorithm displays the best performance. The seventh attribute called Bare
Nuclei of WBCD has 16 missing values. In [20], the 16 missing value instances have been left
out while using WBCD for Breast Cancer diagnosis. The constructed feed forward neural
network has been evaluated for breast cancer detection without replacing missing values [22].
Eliminating some instances will affect the diagnosis accuracy.
In this paper, the network is trained by DE which has been parallelized in order to achieve better
performance. This paper presents a result of direct classification of data after replacing missing
values using median method for the WBCD dataset by using island differential evolution
algorithm. The training algorithms are compared using accuracy and computing time. In this
work, a parallel approach, which uses neural network technique, is proposed to help in the
diagnosis of breast cancer. The neural network is trained with breast cancer data by using feed
forward neural network model and island differential evolution learning algorithm with
momentum and variable learning rate. The performance of the network is evaluated. The
proposed system implements the island-based training method to be better accuracy and less
training time by using and analysing between two different migration topologies.
2. DIFFERENTIAL EVOLUTION ALGORITHM
Having developed an ANN-based process model, a DE algorithm is used to optimize the N-
dimensional input space of the ANN model. Conventionally, various deterministic gradient-based
methods are used for performing optimization of the phenomenological models. Most of these
methods require that the objective function should simultaneously satisfy the smoothness,
continuity, and differentiability criteria. Although the nonlinear relationships approximated by an
ANN model can be expressed in the form of generic closed-form expressions, the objective
function(s) derived thereby cannot be guaranteed to satisfy the smoothness criteria. Thus, the
gradient-based methods cannot be efficiently used for optimizing the input space of an ANN
model and, therefore, it becomes necessary to explore alternative optimization formalisms, which
are lenient towards the form of the objective function.
In the recent years, Differential Evolution (DE) that are members of the stochastic optimization
formalisms have been used with a great success in solving problems involving very large search
spaces [14]. The DEs were originally developed as the genetic engineering models mimicking the
population evolution in natural systems. Specifically, DE like genetic algorithm (GA) enforces
the ―survival-of-the-fittest‖ and ―genetic propagation of characteristics‖ principles of biological
evolution for searching the solution space of an optimization problem. The principal features
possessed by the DEs are: (i) they require only scalar values and not the second- and/or first-order
derivatives of the objective function, (ii) the capability to handle nonlinear and noisy objective
functions, (iii) they perform global search and thus are more likely to arrive at or near the global
optimum and (iv) DEs do not impose pre-conditions, such as smoothness, differentiability and
3. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
3
continuity, on the form of the objective function.
Differential Evolution (DE), an improved version of GA, is an exceptionally simple evolution
strategy that is significantly faster and robust at numerical optimization and is more likely to find
a function‘s true global optimum. Unlike simple GA that uses a binary coding for representing
problem parameters, DE uses real coding of floating point numbers. The mutation operator here is
the addition instead of bit-wise flipping used in GA. And DE uses non-uniform crossover and
tournament selection operators to create new solution strings. Among the DEs advantages are its
simple structure, ease of use, speed and robustness. It can be used for optimizing functions with
real variables and many local optima.
This paper demonstrates a successful application of DE with island model. As already stated, DE
in principle is similar to GA. So, as in GA, we use a population of points in our search for the
optimum. The population size is denoted by NP. The dimension of each vector is denoted by D.
The main operation is the NP number of competitions that are to be carried out to decide the next
generation. To start with, we have a population of NP vectors within the range of the objective
function. We select one of these NP vectors as our target vector. We then randomly select two
vectors from the population and find the difference between them (vector subtraction). This
difference is multiplied by a factor F (specified at the start) and added to the third randomly
selected vector. The result is called the noisy random vector. Subsequently, the crossover is
performed between the target vector and noisy random vector to produce the trial vector. Then, a
competition between the trial vector and target vector is performed and the winner is replaced into
the population. The same procedure is carried out NP times to decide the next generation of
vectors. This sequence is continued till some convergence criterion is met. This summarizes the
basic procedure carried out in differential evolution.
3. ISLAND MODEL STRATEGY
The main difference between the island model and the single population model is the separation
of individuals into islands. As against the master-slave model the communication to computation
ratio of the island model approach is low, owing to the low communication frequency between
the islands. Also, separating individuals separately from each other results in a qualitative
changes in the behaviour of the algorithm.
In the island model approach, each island executes a standard sequential evolutionary algorithm.
The communication between sub-population is assured by a migration process. Some randomly
selected individuals (migration size) migrate from one island to another after every certain
number of generations (migration interval) depending upon a communication topology (migration
topology). The two basic and most sensitive parameters of island model strategy are: migration
size, which indicates the number of individuals migrating and controls the quantitative aspect of
migration; and migration interval denoting the frequency of migration.
3.1. Migration Topology
The migration topology describes which islands send individuals to which islands. There are
many topologies. This system investigates the random topology and torus topology and compares
their results. In this paper, simulations were run with setups of five islands [11].
3.2. Migration Policy
A migration policy consists of two parts. The first part is the selection of individuals, which shall
4. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
4
be migrated to another island. The second part is to choose which individuals are replaced by the
newly obtained individuals. The policy of migration used was random-random policy in which
any random string from an island replaces any other random string of another island based on the
random topology.
3.3. Migration Interval
In order to distribute information about good individuals among the islands, migration has to take
place. This can either be done in synchronous way every n
th
generation or in an asynchronous
way, meaning migration takes place at non-periodical times. It is commonly accepted that a more
frequent migration leads to a higher selection pressure and therefore a faster convergence. But as
always with a higher selection pressure come the susceptibility to get stuck in local optima. In this
system, various migration intervals are experimented to find the best solution for the neural
network training.
3.4. Migration Size
A further important factor is the number of individuals which are exchanged. According to these
studies the migration size has to be adapted to the size of a subpopulation of an island. When one
migrates only a very small percentage, the influence of the exchange is negligible but if too much
individuals are migrated, these new individuals take over the existing population, leading to a
decrease of the global diversity. In this system, the migration sizes were chosen to be
approximately 10% of the size of a subpopulation.
4. ISLAND DIFFERENTIAL EVOLUTION APPROACH TO
NEURAL NETWORK
4.1. Neural Network as Breast Classifier
Neural networks (NNs) have been widely used in various fields as an intelligent tool in recent
years, such as artificial intelligence, pattern recognition, medical diagnosis, machine learning and
so on [10]. Among them, pattern recognition is a class of problem that neural network is
particularly suitable for solving. In fact, NN can be viewed as the mapping from input to output.
If each different input is regarded as a kind of input mode, the mapping to the output is
considered as output response model, the mapping from input to output is undoubtedly the issue
of pattern classification. Nevertheless, learning is the first step to design classifier, that is,
ascertain the requirements for the classification error rate and choose appropriate discrimination
rule.
Strictly speaking, the learning algorithm of NN is a supervised learning method by training feed
forward neural network using error back propagation technique to determine the parameters of
neural network. Its unique advantages lie in the greatest tolerance of the noisy data, as well as the
ability to classify untrained data pattern. When it comes to breast cancer data classification, the
major steps of using neural network learning algorithm can be summarized as follows; to begin
with, through the provision of training samples and the class of sample, the network prediction of
each sample is compared with the actual known class label, and then the weight of each training
sample is adjusted to achieve the purpose of classifying other sample data. The use of neural
network to classify breast cancer data is illustrated in Fig. 1. Each node in the network
corresponds to the output node of a network unit, while the real lines from the bottom into node
are regarded as its input. Intermediate cell is called the hidden layer units, whose output are only
in the internal network, not a part of all the network output. The output of the hidden layer is
5. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
5
considered as the input of two output units, corresponding to a result of the diagnosis of breast
cancer, benign or malignant tumor.
Benign Malignant
Output Layer
Hidden Layer
Input Layer
diameter perimeter area tightness symmetry
Fig 1. Neural network topology
4.2. Processing Procedure of Island Differential Evolution Algorithm
The DE algorithm was proposed by Price and Storn [9]. The DE algorithm has the following
advantages over the traditional genetic algorithm: it is easy to use and it has efficient memory
utilization, lower computational complexity (it scales better when handling large problems), and
lower computational effort (faster convergence) [10]. DE is quite effective in nonlinear constraint
optimization and is also useful for optimizing multimodal problems [23]. The major steps of IDE
are as follows:
Initialize population pop: Create a population from randomly chosen object vectors with
dimension P*d, where P is the number of population and d is the number of weights of
the neural network.
Pg = ( w1,g, … wp,g)
T
, g = 1, …, gmax
wi,g = (w1,i,g, … w d,i,g), i = 1, …P
where d is the number of weights in the weight vector and in wi,g, i is index to the
population and g is the iteration (generation) to which belongs.
Evaluate all the candidate solutions inside the pop for a specified number of iterations.
For each i
th
candidate in pop, select the random population members, r1,r2,r3 ϵ {1,2, …
P}
Apply a mutation operator to each candidate in a population to yield a mutant vector i,e.
vj,i,g-1 = wj,r1,g + F ( wj,r2,g- wj,r3,g ), for j = 1, … d ( i ≠ r1 ± r2 ≠ r3) ϵ {1, … P } and F ϵ
[0,1]
where F denotes the mutation factor.
Apply crossover i.e. each vector in the current population is recombined with a mutant
vector to produce trail vector.
6. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
6
t
j ,i , g 1
v
j ,i , g 1
,
if randi [0,1] CR
w
j ,i , g otherwise
where CR ϵ [0,1]
Apply selection operation.
If MSE (wj,i,g) < MSE (tj,i,g+1) then
replace tj,i,g+1 by wj,i,g in the new population
Else leave tj,i,g+1 in the new population
Select individuals from step 6 according to random-random migration strategy.
Migrate and replace optimal solution according to migration topology.
Repeat steps 1 to 8 until stopping criteria is reached.
In summary, differential evolution algorithm proceeds from an initial population, such as,
selection, crossover and mutation, to search a better space step by step until reach the optimal
solution. It is obvious that differential evolution algorithm is an optimization methodology. Here,
differential evolution algorithm with global optimization strategies is integrated into the neural
network model to improve the classification rate of breast cancer diagnosis. The recommended
population size in DE is ten times the number of gens in a string. Large population size makes the
objective functions expensive. Reducing the population size may lead to reduction in search space
resulting in poor quality of search.
5. DESCRIPTION OF WISCONSIN BREAST CANCER DATABASE
(WBCD)
Breast cancer becomes one of the leading causes of death of women in the world. The
mammography technique has been proved to be an effective tool for the detection of breast
cancer in its earlier phase. Detection of Clusters is an important sign in the identification of micro
calcification of mammograms. In our paper, a medical data based on breast cancer attributes was
used for the purpose of classification between two types of cancers, benign and malignant.
5.1. Breast Cancer Dataset
The database used for detection of breast cancer by artificial neural networks is publicly available
in the Internet [12]. The dataset is provided by university of Wisconsin hospital, Madison from
Dr. William H. Wolberg. This database has 699 instances and 10 attributes including the class
attribute. Attribute 1 through 9 are used to represent instances. Each instance has one of two
possible classes: benign or malignant. According to the class distribution 458 or 65.5% instances
are Benign and 241 or 34.5% instances are Malignant. Table 1 provides the attribute information.
The original data can be presented in the form of analog values with values ranging from 0-10.
Conversion of the given data sets into binary can be done based on certain ranges, which are
defined for each attribute [13].
7. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
7
Table 1. Attributes of breast cancer data
S.no Attribute Domain
1 Clump thickness 1 -10
2 Uniformity of cell size 1 -10
3 Uniformity of cell shape 1 -10
4 Marginal adhesion 1 -10
5 Single epithelial cell size 1 -10
6 Bare nuclei 1 -10
7 Bland chromatin 1 -10
8 Normal nucleoli 1 -10
9 Mitosis 1 -10
Class 2 for benign, 4 for malignant
6. EXPERIMENTAL DETAILS
Java programming language, which is the platform independent and a general-purpose
development language, is used to implement the proposed system. First of all, load data set and
replace missing values by using Median method. And then, normalize the data using min-max
normalization. The training patterns of breast cancer dataset are used as input data. Attributes are
scaled to fall within a small specific range by using min-mix normalization. At the start of the
algorithm, dataset were loaded from the database. In the next step, each chromosome or vector is
randomly initialized with random neural network weight. Fitness of each chromosome is
evaluated using following step. Fitness defined how well a chromosome solves the problem in
hand. The first step converts chromosome‘s genes into neural network and fitness is calculated for
each individuals. Mutation operator produce the trial vector from parent vector and randomly
selected three vectors. Crossover recombines the parent vector and trial vector to produce
offspring. By using mutation and crossover, some genes are modified that mean weights are
updated. Fitness of offspring is calculated and compare with fitness of parent vector, the
chromosome with high fitness survive and next generation begin. Choose individuals according to
migration policy. Migrate and replace individuals according to migration topology. Experiments
are performed with random-random migration policy and two different migration topologies. In
the experiments we used identical islands, i.e islands with same parameters. Simulations were run
with setups of five, seven and nine islands. As can be observed that the error value of test data are
nearly same for the five and seven island models, it goes a little high for nine islands, but no
significant change in the number of islands. Some experiments were also conducted with four
islands and it had no significant influence on the algorithmic behavior. We therefore chose a
modest five island setup for our rest of the experiments. The policy of migration used was
8. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
8
random-random policy in which random string from an island replaces other random string of
another island based on migration topology.
6.1. Data Normalization
The data normalization is considered as the most important pre-processing step using neural
networks. To improve the performance of multilayer neural networks, it is better to normalize the
data entry such that will be found in the interval of [0 1]. To transform the data into digital form,
and use it as inputs of the neural network, scaling or normalization should be realized for each
attribute. The nine numerical attributes, in the analog form, are scaled with a range of 0 and 1.
There are many types of normalization that are found in the literature. The new values obtained
after normalization, follow this equation:
(1)
6.2. Replacement of Missing Values using Median Method
1. Find median for the Bare Nuclei (This attribute contains missing values). The median is
calculated using the formula,
Median sizeof (N 1) (2)
2
2. All the missing value of this attribute replaced by this median value.
6.3. Performance analysis
As far as the classification performance of the model is concerned, the classification rate (C)
denotes the percentage of correctly classified samples, which is computed by the following
formula.
(3)
where, nc, nt represent the number of correctly classified samples and the total number of the
samples, respectively.
6.4. Accuracy Comparison on Breast Cancer Dataset
This analysis is carried out to compare the results of two different migration topologies. To do
this, the learning patterns for the proposed system is compared using breast cancer medical
dataset. The comparative correct classification percentage for breast cancer dataset is shown in
Table 2. It can be obviously seen that the recognition rate in terms of the right classification
percentage has distinctly increased, which is measured by our IDE model. The experiments show
that torus migration topology is more require computing time than random topology.
9. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
9
Table 2. Comparison between migration topology
Torus Topology Random Topology
Datasets
Accuracy Time Accuracy Time
(%) (sec) (%) (sec)
Breast
99.97 16 99.97 3
Cancer
7. EXPERIMENTAL RESULTS
Fig 2. Time Comparison between two different migration topologies
This analysis is carried out to compare the results of two different migration topologies. To do
this, the learning patterns for the proposed system are compared using breast cancer medical
dataset. The time comparison between two different migration topologies on breast cancer
datasets is presented in Fig 2. For torus topology, the computing time is more require than
random topology. Random topology is more suitable than torus topology for the classification of
breast cancer dataset.
Fig 3. Comparative of correct classification percentage of migration topology
In this paper, we have introduced the analysis of two different migration topologies with random-
random migration policy and compared their results. Fig 3 shows the accuracy comparison
between two different migration topologies on breast cancer medical dataset. Breast cancer
medical dataset is used to implement this proposed system which shows better experiments with
10. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
10
higher accuracy. The proposed system also reduces the computing time. For breast cancer
medical dataset, the experiments show that random migration topology has better results on
convergence time and correct classification percentage than torus migration topology. The
proposed algorithm converges in a short time with high correct classification percentage.
8. CONCLUSIONS
In this research a feed forward neural network is constructed and island differential evolution
propagation algorithm is used to train the network. The proposed algorithm is tested on a real life
problem, the Wisconsin Breast Cancer Diagnosis problem. The objective of this study is to create
an effective tool for building neural models to help us making a proper classification of various
classes of breast cancer. The interest in neural networks is justified by their own properties:
learning ability, generalization and reminiscence. Island differential evolution neural network
approach drove by the learning algorithm works well, in terms of accuracy, efficiency and
reliability. Using this model, an automated classification of various types of breast cancer was
performed by avoiding the question of the expert concerning the recognition of cancer required,
improving the identification of breast cancer classification. Through the results analysis it was
found that the subpopulation model reduces significantly the computing time and the solutions
quality is improved significantly. In this paper, we have proposed two different migration
topologies with random-random policy and compared their results. According to experiments, the
torus topology is more require long training time than random topology but it solution quality
results are similar to random topology.
REFERENCES
[1] Arun George Eapen, master thesis, Application of Data Mining in Medical Applications, Waterloo,
Ontario, Canada, 2004.
[2] Choi J.P., Han T.H. and Park R.W., ―A Hybrid Bayesian Network Model for Predicting Breast
Cancer Prognosis‖, J Korean Soc Med Inform, pp. 49-57, 2009.
[3] Hassanien Ella Aboul and Ali H.M. Jafar, ―Rough set approach for generation of classification rules
of Breast Cancer data,‖ Journal Informatica, vol. 15, pp. 23–38, 2004.
[4] Jamarani S. M. h., Behnam H. and Rezairad G. A., ―Multiwavelet Based Neural Network for
Breast Cancer Diagnosis‖, GVIP 05 Conference, pp. 19-21, 2005.
[5] A. Cichocki and R. Unbehauen, ‗‘ Neural Networks for optimization and signal processing,‘‘ J.
Wiley, Sons Ltd. And B.G. Teubner, Stuttgart, 1993.
[6] Abdelaal Ahmed, Mohamed Medhat and Farouq Wael Muhamed, ―Using data mining for assessing
diagnosis of breast cnacer,‖ in Proc. International multiconference on computer science and
information Technology, pp. 11 -17, 2010.
[7] Bellaachia Abdelghani and Erhan Guven, "Predicting Breast Cancer Survivability using Data Mining
Techniques," Ninth Workshop on Mining Scientific and Engineering Datasets in conjunction with the
Sixth SIAM International Conference on Data Mining,‖ 2006.
[8] Burke H. B. Et al, ―Artificial Neural Networks Improve the Accuracy of Cancer Survival
Prediction‖, Cancer, vol.79, pp.857-862, 1997
[9] R. Storn and K. Price, ―Differential evolution—A simple and efficient heuristic for global
optimization over continuous spaces,‖ J. Glob. Optim., vol. 11, no. 4, pp. 341–359, Dec. 1997.
[10] K. V. Price, R. M. Storn, and J. A. Lampinen, Differential Evolution—A Practical Approach to
Global Optimization. Berlin, Germany: SpringerVerlag, 2005.
[11] Z. Skolicki and K. De Jong. The influence of migration sizes and intervals on island models. In
GECCO‘05: Proceedings of the 2005 conference on Genetic and evolutionary computation, pages
1295-1302, New York, NY, USA, ACM, 2005.
[12] Breast Cancer Wisconsin Data [online]. Available: http://archive.ics.uci.edu/ml/machine-learning-
databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data.
11. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, January 2015
11
[13] Dr. K. U. Rani, ―Parallel Approach for Diagnosis of Breast Cancer using Neural Network
Technique‖ Int. J. of Computer. Application, vol. 10, no. 3, pp. 0975 – 8887, Nov. 2010.
[14] Abdul Sttar Ismail Wdaa ― Differential evolution for neural networks learning enhancement ‖ J. of
university of anbar for pure science: Vol.5: No.2: 2011.
[15] Jun Zhang MS, Haobo Ma Md MS, ―An Implementation of Guildford Cytological Grading System
to diagnose Breast Cancer Using Naïve Bayesian Classifier‖, MEDINFO, M.Fieschi et al. (Eds),
Amsterdam: IOS Press, 2004.
[16] Kamruzzaman S.M. and Monirul Islam Md, ―Extraction of Symbolic Rules from Artificial Neural
Networks‖ Proceedings of world Academy of science, Engineering and Technology, vol. 10, ISSN
1307-6884, Dec. 2005.
[17] Punitha A., Sumathi C.P. and Santhanam T., ―A Combination of Genetic Algorithm and ART
Neural Network for Breast Cancer Diagnosis‖ Asian Journal of Information Technology 6
(1):112-117, 2007, Medwell Journals, 2007.
[18] Rudy Setiono and Huan Liu, ―Neural-Network Feature Selector‖ IEEE Transactions On Neural
Networks, vol. 8, No. 3, pg 664-662, May 1997.
[19] Wlodzislaw Duch and Rafal Adamczak and Krzysztof Grabczewski, ―A New methodology of
Extraction, Optimization and Application of Crisp and Fuzzy Logic Rules‖ IEEE Transactions On
Neural Networks, vol. 12, No. 2, pp. 227-306, March 2001.
[20] Anupam Shukla, Ritu Tiwari and Prabhdeep Kaur, ―Knowledge Based Approach for Diagnosis of
Breast Cancer‖ IEEE International Advance Computing Conference, Patiala, India, pp. 6-12, March
2009.
[21] Esugasini S, Mohd Yusoff Mashor, Nor Ashidi Mat Isa and Nor Hayati Othman, Performance
Comparison for MLP Networks Using Various Back Propagation Algorithms for Breast Cancer
Diagnosis, Knowledge-Based Intelligent Information and Engineering Systems, Lecture Notes in
Computer Science, 3682, pp. 123-130, 2005.
[22] Paulin F. and Santhakumaran A., ―Extracting Rules from Feed Forward Neural Networks for
Diagnosing Breast Cancer‖ CiiT International Journal of Artificial Intelligent Systems and Machine
Learning, vol. 1, No. 4, pp. 143-146, July 2009.
[23] D. Karaboga and S. Okdem, ―A simple and global optimization algorithm for engineering problems:
Differential evolution algorithm,‖ Turkish J. Elect. Eng. Comput. Sci., vol. 12, no. 1, pp. 53–60, 2004.