The document describes a study that used an artificial neural network (ANN) approach to predict heart disease. Researchers analyzed data from 52 patient cases that included physical symptoms and medical metrics. They used a backpropagation algorithm to train a multi-layer perceptron neural network. The network was tested by predicting the coronary angiogram value for each patient case after being trained on data from the previous cases. The ANN achieved reasonably accurate predictions, with the best results obtained after 1000 iterations of training. The study demonstrated that ANN techniques can be effective for medical diagnosis and predicting heart disease based on symptom and test data.
Neural network based identification of multimachine power systemcsandit
In recent years, the golden codes have proven to exhibit a superior performance in a wireless
MIMO (Multiple Input Multiple Output) scenario than any other code. However, a serious
limitation associated with it is its increased decoding complexity. This paper attempts to resolve
this challenge through suitable modification of golden code such that a less complex sphere
decoder could be used without much compromising the error rates. In this paper, a minimum
polynomial equation is introduced to obtain a reduced golden ratio (RGR) number for golden
code which demands only for a low complexity decoding procedure. One of the attractive
approaches used in this paper is that the effective channel matrix has been exploited to perform
a single symbol wise decoding instead of grouped symbols using a sphere decoder with tree
search algorithm. It has been observed that the low decoding complexity of O (q1.5) is obtained
against conventional method of O (q2.5). Simulation analysis envisages that in addition to
reduced decoding, improved error rates is also obtained.
Mobile Network Coverage Determination at 900MHz for Abuja Rural Areas using A...ijtsrd
This study proposes Artificial Neural Network ANN based field strength prediction models for the rural areas of Abuja, the federal capital territory of Nigeria. The ANN based models were created on bases of the Generalized Regression Neural network GRNN and the Multi Layer Perceptron Neural Network MLP NN . These networks were created, trained and tested for field strength prediction using received power data recorded at 900MHz from multiple Base Transceiver Stations BTSs distributed across the rural areas. Results indicate that the GRNN and MLP NN based models with Root Mean Squared Error RMSE values of 4.78dBm and 5.56dBm respectively, offer significant improvement over the empirical Hata Okumura counterpart, which overestimates the signal strength by an RMSE value of 20.17dBm. Deme C. Abraham ""Mobile Network Coverage Determination at 900MHz for Abuja Rural Areas using Artificial Neural Networks"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-2 , February 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30228.pdf
Paper Url : https://www.ijtsrd.com/computer-science/artificial-intelligence/30228/mobile-network-coverage-determination-at-900mhz-for-abuja-rural-areas-using-artificial-neural-networks/deme-c-abraham
This document summarizes a research paper that proposes a new interleaver design called a power rotational interleaver for Interleave Division Multiple Access (IDMA) systems. The power rotational interleaver aims to reduce the bandwidth required compared to conventional interleaver designs like random interleavers, while maintaining similar error rate performance. It works by scrambling user data in a matrix using column and row permutations determined by random sequences. Simulation results showed the power rotational interleaver has similar bit error rate to other interleavers but requires less memory and bandwidth.
LOG MESSAGE ANOMALY DETECTION WITH OVERSAMPLINGijaia
Imbalanced data is a significant challenge in classification with machine learning algorithms. This is particularly important with log message data as negative logs are sparse so this data is typically imbalanced. In this paper, a model to generate text log messages is proposed which employs a SeqGAN network. An Autoencoder is used for feature extraction and anomaly detection is done using a GRU network. The proposed model is evaluated with three imbalanced log data sets, namely BGL, OpenStack, and Thunderbird. Results are presented which show that appropriate oversampling and data balancing
improves anomaly detection accuracy.
Genetic Algorithm Processor for Image Noise Filtering Using Evolvable HardwareCSCJournals
This document describes a genetic algorithm processor for image noise filtering using evolvable hardware. It proposes an evolvable hardware architecture that uses a genetic algorithm and virtual reconfigurable circuit to evolve image filters without prior information. The genetic algorithm is used to generate configuration bits that control the connections and functions of processing elements in the virtual reconfigurable circuit. This allows the filter to adapt its design to different noise types through evolution. Experimental results show the evolved hardware filter more effectively removes Gaussian and salt-and-pepper noise compared to conventional filters. Future work could explore applying this approach to additional noise models and image processing tasks.
Optimal neural network models for wind speed predictionIAEME Publication
The document presents two neural network models - multilayer perceptron (MLP) and radial basis function (RBF) networks - for wind speed prediction. It evaluates these models on real wind speed data collected over one year from wind farms in Coimbatore, India. The experimental results show that the RBF and MLP models can improve wind speed prediction accuracy compared to other approaches, according to statistical metrics like coefficient of determination, mean absolute error, root mean square error, and mean bias error.
Black-box modeling of nonlinear system using evolutionary neural NARX modelIJECEIAES
Nonlinear systems with uncertainty and disturbance are very difficult to model using mathematic approach. Therefore, a black-box modeling approach without any prior knowledge is necessary. There are some modeling approaches have been used to develop a black box model such as fuzzy logic, neural network, and evolution algorithms. In this paper, an evolutionary neural network by combining a neural network and a modified differential evolution algorithm is applied to model a nonlinear system. The feasibility and effectiveness of the proposed modeling are tested on a piezoelectric actuator SISO system and an experimental quadruple tank MIMO system.
Comparison of hybrid pso sa algorithm and genetic algorithm for classificationAlexander Decker
This document compares the performance of a hybrid particle swarm optimization-simulated annealing (PSO-SA) algorithm and a genetic algorithm for training neural networks to perform classification. Both algorithms are compared to traditional backpropagation training. The PSO-SA algorithm combines particle swarm optimization with simulated annealing to avoid local minima. A genetic algorithm uses evolutionary operators like selection, crossover and mutation to perform stochastic parallel search of the solution space. Both algorithms are used to train a neural network with 4 inputs, 3 hidden units and 3 outputs on an iris flower classification task. The neural network trained with the PSO-SA algorithm achieved better classification results than the network trained with the genetic algorithm.
Neural network based identification of multimachine power systemcsandit
In recent years, the golden codes have proven to exhibit a superior performance in a wireless
MIMO (Multiple Input Multiple Output) scenario than any other code. However, a serious
limitation associated with it is its increased decoding complexity. This paper attempts to resolve
this challenge through suitable modification of golden code such that a less complex sphere
decoder could be used without much compromising the error rates. In this paper, a minimum
polynomial equation is introduced to obtain a reduced golden ratio (RGR) number for golden
code which demands only for a low complexity decoding procedure. One of the attractive
approaches used in this paper is that the effective channel matrix has been exploited to perform
a single symbol wise decoding instead of grouped symbols using a sphere decoder with tree
search algorithm. It has been observed that the low decoding complexity of O (q1.5) is obtained
against conventional method of O (q2.5). Simulation analysis envisages that in addition to
reduced decoding, improved error rates is also obtained.
Mobile Network Coverage Determination at 900MHz for Abuja Rural Areas using A...ijtsrd
This study proposes Artificial Neural Network ANN based field strength prediction models for the rural areas of Abuja, the federal capital territory of Nigeria. The ANN based models were created on bases of the Generalized Regression Neural network GRNN and the Multi Layer Perceptron Neural Network MLP NN . These networks were created, trained and tested for field strength prediction using received power data recorded at 900MHz from multiple Base Transceiver Stations BTSs distributed across the rural areas. Results indicate that the GRNN and MLP NN based models with Root Mean Squared Error RMSE values of 4.78dBm and 5.56dBm respectively, offer significant improvement over the empirical Hata Okumura counterpart, which overestimates the signal strength by an RMSE value of 20.17dBm. Deme C. Abraham ""Mobile Network Coverage Determination at 900MHz for Abuja Rural Areas using Artificial Neural Networks"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-2 , February 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30228.pdf
Paper Url : https://www.ijtsrd.com/computer-science/artificial-intelligence/30228/mobile-network-coverage-determination-at-900mhz-for-abuja-rural-areas-using-artificial-neural-networks/deme-c-abraham
This document summarizes a research paper that proposes a new interleaver design called a power rotational interleaver for Interleave Division Multiple Access (IDMA) systems. The power rotational interleaver aims to reduce the bandwidth required compared to conventional interleaver designs like random interleavers, while maintaining similar error rate performance. It works by scrambling user data in a matrix using column and row permutations determined by random sequences. Simulation results showed the power rotational interleaver has similar bit error rate to other interleavers but requires less memory and bandwidth.
LOG MESSAGE ANOMALY DETECTION WITH OVERSAMPLINGijaia
Imbalanced data is a significant challenge in classification with machine learning algorithms. This is particularly important with log message data as negative logs are sparse so this data is typically imbalanced. In this paper, a model to generate text log messages is proposed which employs a SeqGAN network. An Autoencoder is used for feature extraction and anomaly detection is done using a GRU network. The proposed model is evaluated with three imbalanced log data sets, namely BGL, OpenStack, and Thunderbird. Results are presented which show that appropriate oversampling and data balancing
improves anomaly detection accuracy.
Genetic Algorithm Processor for Image Noise Filtering Using Evolvable HardwareCSCJournals
This document describes a genetic algorithm processor for image noise filtering using evolvable hardware. It proposes an evolvable hardware architecture that uses a genetic algorithm and virtual reconfigurable circuit to evolve image filters without prior information. The genetic algorithm is used to generate configuration bits that control the connections and functions of processing elements in the virtual reconfigurable circuit. This allows the filter to adapt its design to different noise types through evolution. Experimental results show the evolved hardware filter more effectively removes Gaussian and salt-and-pepper noise compared to conventional filters. Future work could explore applying this approach to additional noise models and image processing tasks.
Optimal neural network models for wind speed predictionIAEME Publication
The document presents two neural network models - multilayer perceptron (MLP) and radial basis function (RBF) networks - for wind speed prediction. It evaluates these models on real wind speed data collected over one year from wind farms in Coimbatore, India. The experimental results show that the RBF and MLP models can improve wind speed prediction accuracy compared to other approaches, according to statistical metrics like coefficient of determination, mean absolute error, root mean square error, and mean bias error.
Black-box modeling of nonlinear system using evolutionary neural NARX modelIJECEIAES
Nonlinear systems with uncertainty and disturbance are very difficult to model using mathematic approach. Therefore, a black-box modeling approach without any prior knowledge is necessary. There are some modeling approaches have been used to develop a black box model such as fuzzy logic, neural network, and evolution algorithms. In this paper, an evolutionary neural network by combining a neural network and a modified differential evolution algorithm is applied to model a nonlinear system. The feasibility and effectiveness of the proposed modeling are tested on a piezoelectric actuator SISO system and an experimental quadruple tank MIMO system.
Comparison of hybrid pso sa algorithm and genetic algorithm for classificationAlexander Decker
This document compares the performance of a hybrid particle swarm optimization-simulated annealing (PSO-SA) algorithm and a genetic algorithm for training neural networks to perform classification. Both algorithms are compared to traditional backpropagation training. The PSO-SA algorithm combines particle swarm optimization with simulated annealing to avoid local minima. A genetic algorithm uses evolutionary operators like selection, crossover and mutation to perform stochastic parallel search of the solution space. Both algorithms are used to train a neural network with 4 inputs, 3 hidden units and 3 outputs on an iris flower classification task. The neural network trained with the PSO-SA algorithm achieved better classification results than the network trained with the genetic algorithm.
This document discusses using the Levenberg-Marquardt algorithm for forecasting stock exchange share rates on the Karachi Stock Exchange. It provides an overview of artificial neural networks and how they can be used for financial forecasting applications. The Levenberg-Marquardt algorithm is presented as an efficient method for training neural networks to minimize errors through gradient descent. The document applies this method to train a neural network to predict the direction of change in share prices on the Karachi Stock Exchange. The network is trained on historical stock price data and testing shows it can achieve the performance goal of forecasting next day price changes.
11.comparison of hybrid pso sa algorithm and genetic algorithm for classifica...Alexander Decker
This document compares the performance of a hybrid particle swarm optimization-simulated annealing (PSO-SA) algorithm and genetic algorithm for training neural networks to perform classification. It describes the architecture of a neural network used for classification of iris data, with 4 input units, 3 hidden units, and 3 output units. The genetic algorithm and PSO-SA algorithm are used to train the neural network by minimizing an error function, and their ability to classify test data is compared. The neural network trained with the hybrid PSO-SA algorithm achieved better results than the genetic algorithm in tests conducted.
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ...csandit
The document describes an algorithm called X-TREPAN that extracts decision trees from trained neural networks. X-TREPAN is an enhancement of the TREPAN algorithm that allows it to handle both multi-class classification and multi-class regression problems. It can also analyze generalized feed forward networks. The algorithm was tested on several real-world datasets and was found to generate decision trees with good classification accuracy while also maintaining comprehensibility.
The Use of K-NN and Bees Algorithm for Big Data Intrusion Detection SystemIOSRjournaljce
Big data problem in intrusion detection system is mainly due to the large volume of the data. The dimension of the original data is 41. Some of the feature of original data are unnecessary. In this process, the volume of data has expanded into hundreds and thousands of gigabytes(GB) of information. The dimension span of data and volume can be reduced and the system is enhanced by using K-NN and BA. The reduction ratio of KDD datasets and processing speed is very slow so the data has been reduced for extracting features by Bees Algorithm (AB) and use K-nearest neighbors as classification (KNN). So, the KDD99 datasets applied in the experiments with significant features. The results have gave higher detection and accuracy rate as well as reduced false positive rate. Keywords: Big Data; Intru
Performance analysis of neural network models for oxazolines and oxazoles der...ijistjournal
Neural networks have been used successfully to a br
oad range of areas such as business, data mining, d
rug
discovery and biology. In medicine, neural network
s have been applied widely in medical diagnosis,
detection and evaluation of new drugs and treatment
cost estimation. In addition, neural networks have
begin practice in data mining strategies for the a
im of prediction, knowledge discovery. This paper
will
present the application of neural networks for the
prediction and analysis of antitubercular activity
of
Oxazolines and Oxazoles derivatives. This study pre
sents techniques based on the development of Single
hidden layer neural network (SHLFFNN), Gradient Des
cent Back propagation neural network (GDBPNN),
Gradient Descent Back propagation with momentum neu
ral network (GDBPMNN), Back propagation with
Weight decay neural network (BPWDNN) and Quantile r
egression neural network (QRNN) of artificial
neural network (ANN) models Here, we comparatively
evaluate the performance of five neural network
techniques. The evaluation of the efficiency of eac
h model by ways of benchmark experiments is an
accepted application. Cross-validation and resampli
ng techniques are commonly used to derive point
estimates of the performances which are compared to
identify methods with good properties. Predictiv
e
accuracy was evaluated using the root mean squared
error (RMSE), Coefficient determination(
), mean
absolute error(MAE), mean percentage error(MPE) and
relative square error(RSE). We found that all five
neural network models were able to produce feasible
models. QRNN model is outperforms with all
statistical tests amongst other four models.
This document describes a study that developed a neuro-fuzzy system for predicting electricity consumption. The neuro-fuzzy system combines the learning capabilities of neural networks with the linguistic rule interpretation of fuzzy inference systems. It was applied to predict future electricity consumption in Northern Cyprus based on past consumption data. The system was trained using a supervised learning algorithm to determine optimal parameters. Simulation results showed the neuro-fuzzy system achieved more accurate predictions of electricity consumption than a neural network model alone, using fewer training epochs.
ANALYTICAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MININGcsandit
Although opinion mining is in a nascent stage of development but still the ground is set for dense growth of researches in the field. One of the important activities of opinion mining is to extract opinions of people based on characteristics of the object under study. Feature extraction in opinion mining can be done by various ways like that of clustering, support vector machines
etc. This paper is an attempt to appraise the various techniques of feature extraction. The first part discusses various techniques and second part makes a detailed appraisal of the major techniques used for feature extraction
Analytical study of feature extraction techniques in opinion miningcsandit
Although opinion mining is in a nascent stage of development but still the ground is set for
dense growth of researches in the field. One of the important activities of opinion mining is to
extract opinions of people based on characteristics of the object under study. Feature extraction
in opinion mining can be done by various ways like that of clustering, support vector machines
etc. This paper is an attempt to appraise the various techniques of feature extraction. The first
part discusses various techniques and second part makes a detailed appraisal of the major
techniques used for feature extraction
This document summarizes research on neural networks. It discusses the basic structure and components of neural networks, including network topology (feed forward and recurrent), transfer functions, and learning algorithms (supervised, unsupervised, reinforcement). It also overview popular neural network models like multilayer perceptrons, radial basis function networks, Kohonen's self-organizing maps, and Hopfield networks. Finally, it outlines some applications of neural networks such as process control, pattern recognition, and more.
COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN NEURAL NETWORK BASED IDENT...ijcsit
This paper explores the application of artificial neural networks for online identification of a multimachine power system. A recurrent neural network has been proposed as the identifier of the two area, four machine system which is a benchmark system for studying electromechanical oscillations in multimachine power systems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of the paper is on investigating the performance of the variants of the Backpropagation algorithm in training the neural identifier. The paper also compares the performances of the neural identifiers trained using variants of the Backpropagation algorithm over a wide range of operating conditions. The simulation results establish a satisfactory performance of the trained neural identifiers in identification of the test power system.
PERFORMANCE EVALUATION OF FUZZY LOGIC AND BACK PROPAGATION NEURAL NETWORK FOR...ijesajournal
ABSTRACT
Fuzzy c-mean is one of the efficient tools used in character recognition. Back propagation neural network is another powerful that may be used in such field. A comparison between fuzzy c-mean and BP neural network classifiers are presented in this research to obtain the performance of both classifiers. The comparison was based on recognition efficiency; this efficiency was evaluated as the ratio of the number of assigned characters with unknown one to the number of character set related to that character. The fuzzy C-mean and BP neural network algorithms were tested on a set of hand written and machine printed dataset named Chars74K dataset using Matlab (2016 b) programming language and the result was that neural network classifier gave 82% recognition efficiency while fuzzy c –mean gave 78%. Neural network classifier is more superior than fuzzy C-mean in recognition due to the limitations of processing time of fuzzy C-mean that requires smaller image size and eventually this will cause less efficiency.
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...Waqas Tariq
Kalman filter have been used for the estimation of instantaneous states of linear dynamic systems. It is a good tool for inferring of missing information from noisy measurement. The quantum neural network is another approach to the merging of fuzzy logic with the neural network and that by the investment of quantum mechanics theory in building the structure of neural network. The gradient descent algorithm has been used, widely, in training the neural network, but the problem of local minima is one of the disadvantages of this algorithm. This paper presents an algorithm to train the quantum neural network by using the extended kalman filter.
Improving Classifier Accuracy using Unlabeled Data..docbutest
This document describes a method for improving classifier accuracy using unlabeled data in addition to a small set of labeled data. The algorithm builds an initial classifier using just the labeled data, then uses that classifier to label a larger set of unlabeled data. A new classifier is then built using both the original labeled data and the now labeled unlabeled data. Experimental results using three common learning algorithms (neural networks, Naive Bayes, C4.5) on 10 datasets show average accuracy improvements of 5%, 3%, and 8% respectively when incorporating unlabeled data. The results indicate that leveraging unlabeled data can significantly boost classifier performance when labeled data is limited.
This document presents a study that analyzes network traffic data to detect user behavior patterns, including both normal and intrusive patterns. It uses the KDDCUP99 dataset and applies various feature selection and data preprocessing algorithms. A model is developed using evolutionary neural networks and genetic algorithms to identify trends and anomalies in user behavior over time. The model is able to accurately classify behavior patterns in the network with over 92% accuracy based on testing. Future work could involve using deep learning techniques to further improve the algorithm training.
Maria Tornberg is a highly skilled photographer and filmmaker with over 10 years of experience in photography, film and television production, and project management. She has worked with major brands and publications and is proficient in several languages. Her areas of expertise include strong organizational, writing, and visual skills as well as the ability to work efficiently under tight deadlines.
Encuesta realizada por el colectivo ciudadanos los que elegimos en Bogota, se realizo para evitar que los canales de television y periodicos decidan por nosotros
Este documento describe el proceso de acreditación con la Carta Europea de Turismo Sostenible (CETS), un sistema de certificación voluntario para espacios naturales protegidos en Europa. Explica las fases del proceso de candidatura, incluyendo la elaboración del diagnóstico, la estrategia y el plan de acción, así como los beneficios de la acreditación para el espacio natural y las empresas turísticas locales. Finalmente, detalla los pasos a seguir y los costes asociados con la verificación y concesión final de la acreditación por parte
Optimal neural network models for wind speed predictionIAEME Publication
The document describes using artificial neural networks for wind speed prediction. Specifically, it analyzes the performance of multilayer perceptron networks and radial basis function networks for wind speed forecasting using real-time data collected from wind farms in Coimbatore, India over one year. The models are trained on 3000 samples and tested on 1000 samples. Performance is evaluated using statistical metrics like coefficient of determination, mean absolute error, root mean square error, and mean bias error. Results show that the neural network models improve prediction accuracy compared to other approaches and the optimal model depends on factors like the number of hidden neurons and spread value.
This document discusses using the Levenberg-Marquardt algorithm for forecasting stock exchange share rates on the Karachi Stock Exchange. It provides an overview of artificial neural networks and how they can be used for financial forecasting applications. The Levenberg-Marquardt algorithm is presented as an efficient method for training neural networks to minimize errors through gradient descent. The document applies this method to train a neural network to predict the direction of change in share prices on the Karachi Stock Exchange. The network is trained on historical stock price data and testing shows it can achieve the performance goal of forecasting next day price changes.
11.comparison of hybrid pso sa algorithm and genetic algorithm for classifica...Alexander Decker
This document compares the performance of a hybrid particle swarm optimization-simulated annealing (PSO-SA) algorithm and genetic algorithm for training neural networks to perform classification. It describes the architecture of a neural network used for classification of iris data, with 4 input units, 3 hidden units, and 3 output units. The genetic algorithm and PSO-SA algorithm are used to train the neural network by minimizing an error function, and their ability to classify test data is compared. The neural network trained with the hybrid PSO-SA algorithm achieved better results than the genetic algorithm in tests conducted.
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ...csandit
The document describes an algorithm called X-TREPAN that extracts decision trees from trained neural networks. X-TREPAN is an enhancement of the TREPAN algorithm that allows it to handle both multi-class classification and multi-class regression problems. It can also analyze generalized feed forward networks. The algorithm was tested on several real-world datasets and was found to generate decision trees with good classification accuracy while also maintaining comprehensibility.
The Use of K-NN and Bees Algorithm for Big Data Intrusion Detection SystemIOSRjournaljce
Big data problem in intrusion detection system is mainly due to the large volume of the data. The dimension of the original data is 41. Some of the feature of original data are unnecessary. In this process, the volume of data has expanded into hundreds and thousands of gigabytes(GB) of information. The dimension span of data and volume can be reduced and the system is enhanced by using K-NN and BA. The reduction ratio of KDD datasets and processing speed is very slow so the data has been reduced for extracting features by Bees Algorithm (AB) and use K-nearest neighbors as classification (KNN). So, the KDD99 datasets applied in the experiments with significant features. The results have gave higher detection and accuracy rate as well as reduced false positive rate. Keywords: Big Data; Intru
Performance analysis of neural network models for oxazolines and oxazoles der...ijistjournal
Neural networks have been used successfully to a br
oad range of areas such as business, data mining, d
rug
discovery and biology. In medicine, neural network
s have been applied widely in medical diagnosis,
detection and evaluation of new drugs and treatment
cost estimation. In addition, neural networks have
begin practice in data mining strategies for the a
im of prediction, knowledge discovery. This paper
will
present the application of neural networks for the
prediction and analysis of antitubercular activity
of
Oxazolines and Oxazoles derivatives. This study pre
sents techniques based on the development of Single
hidden layer neural network (SHLFFNN), Gradient Des
cent Back propagation neural network (GDBPNN),
Gradient Descent Back propagation with momentum neu
ral network (GDBPMNN), Back propagation with
Weight decay neural network (BPWDNN) and Quantile r
egression neural network (QRNN) of artificial
neural network (ANN) models Here, we comparatively
evaluate the performance of five neural network
techniques. The evaluation of the efficiency of eac
h model by ways of benchmark experiments is an
accepted application. Cross-validation and resampli
ng techniques are commonly used to derive point
estimates of the performances which are compared to
identify methods with good properties. Predictiv
e
accuracy was evaluated using the root mean squared
error (RMSE), Coefficient determination(
), mean
absolute error(MAE), mean percentage error(MPE) and
relative square error(RSE). We found that all five
neural network models were able to produce feasible
models. QRNN model is outperforms with all
statistical tests amongst other four models.
This document describes a study that developed a neuro-fuzzy system for predicting electricity consumption. The neuro-fuzzy system combines the learning capabilities of neural networks with the linguistic rule interpretation of fuzzy inference systems. It was applied to predict future electricity consumption in Northern Cyprus based on past consumption data. The system was trained using a supervised learning algorithm to determine optimal parameters. Simulation results showed the neuro-fuzzy system achieved more accurate predictions of electricity consumption than a neural network model alone, using fewer training epochs.
ANALYTICAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MININGcsandit
Although opinion mining is in a nascent stage of development but still the ground is set for dense growth of researches in the field. One of the important activities of opinion mining is to extract opinions of people based on characteristics of the object under study. Feature extraction in opinion mining can be done by various ways like that of clustering, support vector machines
etc. This paper is an attempt to appraise the various techniques of feature extraction. The first part discusses various techniques and second part makes a detailed appraisal of the major techniques used for feature extraction
Analytical study of feature extraction techniques in opinion miningcsandit
Although opinion mining is in a nascent stage of development but still the ground is set for
dense growth of researches in the field. One of the important activities of opinion mining is to
extract opinions of people based on characteristics of the object under study. Feature extraction
in opinion mining can be done by various ways like that of clustering, support vector machines
etc. This paper is an attempt to appraise the various techniques of feature extraction. The first
part discusses various techniques and second part makes a detailed appraisal of the major
techniques used for feature extraction
This document summarizes research on neural networks. It discusses the basic structure and components of neural networks, including network topology (feed forward and recurrent), transfer functions, and learning algorithms (supervised, unsupervised, reinforcement). It also overview popular neural network models like multilayer perceptrons, radial basis function networks, Kohonen's self-organizing maps, and Hopfield networks. Finally, it outlines some applications of neural networks such as process control, pattern recognition, and more.
COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN NEURAL NETWORK BASED IDENT...ijcsit
This paper explores the application of artificial neural networks for online identification of a multimachine power system. A recurrent neural network has been proposed as the identifier of the two area, four machine system which is a benchmark system for studying electromechanical oscillations in multimachine power systems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of the paper is on investigating the performance of the variants of the Backpropagation algorithm in training the neural identifier. The paper also compares the performances of the neural identifiers trained using variants of the Backpropagation algorithm over a wide range of operating conditions. The simulation results establish a satisfactory performance of the trained neural identifiers in identification of the test power system.
PERFORMANCE EVALUATION OF FUZZY LOGIC AND BACK PROPAGATION NEURAL NETWORK FOR...ijesajournal
ABSTRACT
Fuzzy c-mean is one of the efficient tools used in character recognition. Back propagation neural network is another powerful that may be used in such field. A comparison between fuzzy c-mean and BP neural network classifiers are presented in this research to obtain the performance of both classifiers. The comparison was based on recognition efficiency; this efficiency was evaluated as the ratio of the number of assigned characters with unknown one to the number of character set related to that character. The fuzzy C-mean and BP neural network algorithms were tested on a set of hand written and machine printed dataset named Chars74K dataset using Matlab (2016 b) programming language and the result was that neural network classifier gave 82% recognition efficiency while fuzzy c –mean gave 78%. Neural network classifier is more superior than fuzzy C-mean in recognition due to the limitations of processing time of fuzzy C-mean that requires smaller image size and eventually this will cause less efficiency.
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...Waqas Tariq
Kalman filter have been used for the estimation of instantaneous states of linear dynamic systems. It is a good tool for inferring of missing information from noisy measurement. The quantum neural network is another approach to the merging of fuzzy logic with the neural network and that by the investment of quantum mechanics theory in building the structure of neural network. The gradient descent algorithm has been used, widely, in training the neural network, but the problem of local minima is one of the disadvantages of this algorithm. This paper presents an algorithm to train the quantum neural network by using the extended kalman filter.
Improving Classifier Accuracy using Unlabeled Data..docbutest
This document describes a method for improving classifier accuracy using unlabeled data in addition to a small set of labeled data. The algorithm builds an initial classifier using just the labeled data, then uses that classifier to label a larger set of unlabeled data. A new classifier is then built using both the original labeled data and the now labeled unlabeled data. Experimental results using three common learning algorithms (neural networks, Naive Bayes, C4.5) on 10 datasets show average accuracy improvements of 5%, 3%, and 8% respectively when incorporating unlabeled data. The results indicate that leveraging unlabeled data can significantly boost classifier performance when labeled data is limited.
This document presents a study that analyzes network traffic data to detect user behavior patterns, including both normal and intrusive patterns. It uses the KDDCUP99 dataset and applies various feature selection and data preprocessing algorithms. A model is developed using evolutionary neural networks and genetic algorithms to identify trends and anomalies in user behavior over time. The model is able to accurately classify behavior patterns in the network with over 92% accuracy based on testing. Future work could involve using deep learning techniques to further improve the algorithm training.
Maria Tornberg is a highly skilled photographer and filmmaker with over 10 years of experience in photography, film and television production, and project management. She has worked with major brands and publications and is proficient in several languages. Her areas of expertise include strong organizational, writing, and visual skills as well as the ability to work efficiently under tight deadlines.
Encuesta realizada por el colectivo ciudadanos los que elegimos en Bogota, se realizo para evitar que los canales de television y periodicos decidan por nosotros
Este documento describe el proceso de acreditación con la Carta Europea de Turismo Sostenible (CETS), un sistema de certificación voluntario para espacios naturales protegidos en Europa. Explica las fases del proceso de candidatura, incluyendo la elaboración del diagnóstico, la estrategia y el plan de acción, así como los beneficios de la acreditación para el espacio natural y las empresas turísticas locales. Finalmente, detalla los pasos a seguir y los costes asociados con la verificación y concesión final de la acreditación por parte
Optimal neural network models for wind speed predictionIAEME Publication
The document describes using artificial neural networks for wind speed prediction. Specifically, it analyzes the performance of multilayer perceptron networks and radial basis function networks for wind speed forecasting using real-time data collected from wind farms in Coimbatore, India over one year. The models are trained on 3000 samples and tested on 1000 samples. Performance is evaluated using statistical metrics like coefficient of determination, mean absolute error, root mean square error, and mean bias error. Results show that the neural network models improve prediction accuracy compared to other approaches and the optimal model depends on factors like the number of hidden neurons and spread value.
Optimal neural network models for wind speed predictionIAEME Publication
The document presents two neural network models - multilayer perceptron (MLP) and radial basis function (RBF) networks - for wind speed prediction. It evaluates these models on real-time wind speed data collected from wind farms in Coimbatore, India over one year. The experimental results show that RBF and MLP networks can improve wind speed prediction accuracy compared to other approaches, according to statistical metrics like coefficient of determination, mean absolute error, root mean square error and mean bias error. The RBF and MLP models are able to handle the non-linear patterns in wind speed data, which conventional models struggle with, increasing prediction precision.
This document discusses using a fuzzy-neural network to forecast electricity demand. It proposes combining a neural network with fuzzy logic to overcome some limitations of only using artificial neural networks (ANNs). Specifically, it implements a fuzzy logic front-end processor to handle both numeric and fuzzy inputs before feeding them to a three-layer backpropagation neural network. This allows the neural network to capture unknown relationships between input variables like temperature, rain forecast, season and day type with the target output of electricity load. The strengths of this hybrid technique are its ability to incorporate both quantitative and qualitative knowledge and to produce more accurate forecasts.
Expert system design for elastic scattering neutrons optical model using bpnnijcsa
In present paper, a proposed expert system is designed to obtain a trained formulae for the optical model
parameters used in elastic scattering neutrons of light nuclei for (7Li), at energy range between [(1) to
(20)] MeV. A simple algorithm has used to design this expert system, while a multi-layer backwardpropagation
neural network (BPNN) is applied for training and testing the data used in this model. This
group of formulae may get a simple expert system occurring from governing formulae model, and predicts
the critical parameters usually resulted from the complicated computer coding methods. This expert system
may use in nuclear reactions yields in both fission and fusion nature who gives more closely results to the
real model.
This document discusses using an artificial neural network to forecast electricity demand. It describes preprocessing data, creating a feed-forward neural network model with input, hidden and output layers, and training the model using backpropagation and incremental training. The model is trained on 80% of the data and tested on the remaining 20%. Mean square error is used to evaluate accuracy on both the training and test sets, with a lower error on the test set indicating better generalization of the model to new data. The goal is to accurately forecast future electricity demand based on input variables like population, GDP, price indexes, and past consumption data.
X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D...cscpconf
In this work, the TREPAN algorithm is enhanced and extended for extracting decision trees from neural networks. We empirically evaluated the performance of the algorithm on a set of databases from real world events. This benchmark enhancement was achieved by adapting Single-test TREPAN and C4.5 decision tree induction algorithms to analyze the datasets. The models are then compared with X-TREPAN for comprehensibility and classification accuracy. Furthermore, we validate the experimentations by applying statistical methods. Finally, the modified algorithm is extended to work with multi-class regression problems and the ability to comprehend generalized feed forward networks is achieved.
NEURAL NETWORK BASED IDENTIFICATION OF MULTIMACHINE POWER SYSTEMcscpconf
This paper demonstrates an effective application of artificial neural networks for online identification of a multimachine power system. The paper presents a recurrent neural network as the identifier of the benchmark two area, four machine system. This neural identifier is trained using the static Backpropagation algorithm. The trained neural identifier is then tested using datasets generated by simulating the system under consideration at different operating
points and a different loading condition. The test results clearly establish a satisfactory performance of the trained neural identifier in identification of the power system considered.
Disease Classification using ECG Signal Based on PCA Feature along with GA & ...IRJET Journal
This document describes a method for classifying ECG signals to detect cardiovascular diseases using principal component analysis (PCA), genetic algorithms, and artificial neural networks. PCA is used to extract features from ECG signals. A genetic algorithm is then used to select optimal features and train an artificial neural network classifier. The method is tested on datasets from Physionet.org to classify ECG signals as normal or indicating conditions like bradycardia or tachycardia with high accuracy. The goal is to develop an automated system for ECG analysis and heart disease diagnosis.
This work is proposed the feed forward neural network with symmetric table addition method to design the
neuron synapses algorithm of the sine function approximations, and according to the Taylor series
expansion. Matlab code and LabVIEW are used to build and create the neural network, which has been
designed and trained database set to improve its performance, and gets the best a global convergence with
small value of MSE errors and 97.22% accuracy.
Towards neuralprocessingofgeneralpurposeapproximateprogramsParidha Saxena
Did validation of one of the machine learning algorithms of neural networks,and compared the results for its implementation on hardware (FPGA) using xilinx, with that of a sequential code execution(using FANN).
The document discusses using neural networks to accelerate general purpose programs through approximate computing. It describes generating training data from programs, using this data to train neural networks, and then running the neural networks at runtime instead of the original programs. Experimental results show the neural network implementations provided speedups of 10-900% compared to the original programs with minimal loss of accuracy. An FPGA implementation of the neural networks was also able to achieve further acceleration, running a network 4x faster than software.
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesIJCSES Journal
ANN is a computational model that is composed of several processing elements (neurons) that tries to solve a specific problem. Like the human brain, it provides the ability to learn
from experiences without being explicitly programmed. This article is based on the implementation of artificial neural networks for logic gates. At first, the 3 layers Artificial Neural Network is
designed with 2 input neurons, 2 hidden neurons & 1 output neuron. after that model is trained
by using a backpropagation algorithm until the model satisfies the predefined error criteria (e)
which set 0.01 in this experiment. The learning rate (α) used for this experiment was 0.01. The
NN model produces correct output at iteration (p)= 20000 for AND, NAND & NOR gate. For
OR & XOR the correct output is predicted at iteration (p)=15000 & 80000 respectively
New Approach of Preprocessing For Numeral RecognitionIJERA Editor
The present paper proposes a new approach of preprocessing for handwritten, printed and isolated numeral
characters. The new approach reduces the size of the input image of each numeral by discarding the redundant
information. This method reduces also the number of features of the attribute vector provided by the extraction
features method. Numeral recognition is carried out in this work through k nearest neighbors and multilayer
perceptron techniques. The simulations have obtained a good rate of recognition in fewer running time.
Application of Hybrid Genetic Algorithm Using Artificial Neural Network in Da...IOSRjournaljce
The main purpose of data mining is to extract knowledge from large amount of data. Artificial Neural network (ANN) has already been applied in a variety of domains with remarkable success. This paper presents the application of hybrid model for stroke disease that integrates Genetic algorithm and back propagation algorithm. Selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In addition the hybrid model that leads to further improvised categorization, accuracy compared to the result produced by genetic algorithm alone. In this study, a new hybrid model of Neural Networks and Genetic Algorithm (GA) to initialize and optimize the connection weights of ANN so as to improve the performance of the ANN and the same has been applied in a medical problem of predicting stroke disease for verification of the results.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Design of c slotted microstrip antenna using artificial neural network modeleSAT Journals
Abstract In this paper, neural network model has been used to estimation of resonance frequency of a coaxial feed C-slotted Microstrip Antenna. The Multi-Layer Perceptron Feed forward back Propagation (MLPFFBP) and Radial basis function Artificial Neural Network (RBFANN) have been used to implement the neural network model. A relative performance analysis of the proposed neural network for different training algorithms. Number of neurons and number of hidden layer is also carried out for estimating the resonance frequency. The method of moment (MOM) based IE3D software was used to generate data dictionary for training and validation set of ANN. The results obtain using ANN are compared with simulation feeding and found quite satisfactory and also it is concluded that RBFANN network is more accurate and fast compared to MLPFFBP network algorithm. Index Terms: Artificial Neural Network, C slot, Microstrip Antenna, Multilayer Feed Forward Networks, Radial basis function Artificial Neural Network, Resonance frequency.
Adaptive modified backpropagation algorithm based on differential errorsIJCSEA Journal
A new efficient modified back propagation algorithm with adaptive learning rate is proposed to increase the convergence speed and to minimize the error. The method eliminates initial fixing of learning rate through trial and error and replaces by adaptive learning rate. In each iteration, adaptive learning rate for output and hidden layer are determined by calculating differential linear and nonlinear errors of output layer and hidden layer separately. In this method, each layer has different learning rate in each iteration. The performance of the proposed algorithm is verified by the simulation results.
This document summarizes a research paper that uses an artificial neural network approach to forecast stock market prices in India. The paper trains a feedforward neural network using a backpropagation algorithm on data from 5 Indian companies between 2004 and 2013. The network is tested in MATLAB to predict stock prices and calculate an error rate for accuracy. The neural network model is found to provide a computational method for predicting stock market movements based on historical price and volume data.
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...IAEME Publication
This paper presents an approach based on applying an aggregated predictor formed by multiple versions of a multilayer neural network with a back-propagation optimization algorithm for helping the engineer to get a list of the most appropriate well-test interpretation models for a given set of pressure/ production data. The proposed method consists of three stages: (1) data decorrelation through principal component analysis to reduce the covariance between the variables and the dimension of the input layer in the artificial neural network, (2) bootstrap replicates of the learning set where the data is repeatedly sampled with a random split of the data into train sets and using these as new learning sets, and (3) automatic reservoir model identification through aggregated predictor formed by a plurality vote when predicting a new class. This method is described in detail to ensure successful replication of results. The required training and test dataset were generated by using analytical solution models. In our case, there were used 600 samples: 300 for training, 100 for cross-validation, and 200 for testing. Different network structures were tested during this study to arrive at optimum network design. We notice that the single net methodology always brings about confusion in selecting the correct model even though the training results for the constructed networks are close to 1. We notice also that the principal component analysis is an effective strategy in reducing the number of input features, simplifying the network structure, and lowering the training time of the ANN. The results obtained show that the proposed model provides better performance when predicting new data with a coefficient of correlation approximately equal to 95% Compared to a previous approach 80%, the combination of the PCA and ANN is more stable and determine the more accurate results with lesser computational complexity than was feasible previously. Clearly, the aggregated predictor is more stable and shows less bad classes compared to the previous approach.
This document summarizes research on improving image classification results using neural networks. It compares common image classification methods like support vector machines (SVM) and K-nearest neighbors (KNN). It then evaluates the performance of multilayer perceptron (MLP) neural networks and radial basis function (RBF) neural networks on image classification. The document tests various configurations of MLP and RBF networks on a dataset containing 2310 images across 7 classes. It finds that a MLP network with two hidden layers of 10 neurons each achieves the best results, with an average accuracy of 98.84%. This is significantly higher than the 84.47% average accuracy of RBF networks and outperforms KNN classification as well. The research concludes that neural
The Department of Veteran Affairs (VA) invited Taylor Paschal, Knowledge & Information Management Consultant at Enterprise Knowledge, to speak at a Knowledge Management Lunch and Learn hosted on June 12, 2024. All Office of Administration staff were invited to attend and received professional development credit for participating in the voluntary event.
The objectives of the Lunch and Learn presentation were to:
- Review what KM ‘is’ and ‘isn’t’
- Understand the value of KM and the benefits of engaging
- Define and reflect on your “what’s in it for me?”
- Share actionable ways you can participate in Knowledge - - Capture & Transfer
"Choosing proper type of scaling", Olena SyrotaFwdays
Imagine an IoT processing system that is already quite mature and production-ready and for which client coverage is growing and scaling and performance aspects are life and death questions. The system has Redis, MongoDB, and stream processing based on ksqldb. In this talk, firstly, we will analyze scaling approaches and then select the proper ones for our system.
"NATO Hackathon Winner: AI-Powered Drug Search", Taras KlobaFwdays
This is a session that details how PostgreSQL's features and Azure AI Services can be effectively used to significantly enhance the search functionality in any application.
In this session, we'll share insights on how we used PostgreSQL to facilitate precise searches across multiple fields in our mobile application. The techniques include using LIKE and ILIKE operators and integrating a trigram-based search to handle potential misspellings, thereby increasing the search accuracy.
We'll also discuss how the azure_ai extension on PostgreSQL databases in Azure and Azure AI Services were utilized to create vectors from user input, a feature beneficial when users wish to find specific items based on text prompts. While our application's case study involves a drug search, the techniques and principles shared in this session can be adapted to improve search functionality in a wide range of applications. Join us to learn how PostgreSQL and Azure AI can be harnessed to enhance your application's search capability.
Main news related to the CCS TSI 2023 (2023/1695)Jakub Marek
An English 🇬🇧 translation of a presentation to the speech I gave about the main changes brought by CCS TSI 2023 at the biggest Czech conference on Communications and signalling systems on Railways, which was held in Clarion Hotel Olomouc from 7th to 9th November 2023 (konferenceszt.cz). Attended by around 500 participants and 200 on-line followers.
The original Czech 🇨🇿 version of the presentation can be found here: https://www.slideshare.net/slideshow/hlavni-novinky-souvisejici-s-ccs-tsi-2023-2023-1695/269688092 .
The videorecording (in Czech) from the presentation is available here: https://youtu.be/WzjJWm4IyPk?si=SImb06tuXGb30BEH .
High performance Serverless Java on AWS- GoTo Amsterdam 2024Vadym Kazulkin
Java is for many years one of the most popular programming languages, but it used to have hard times in the Serverless community. Java is known for its high cold start times and high memory footprint, comparing to other programming languages like Node.js and Python. In this talk I'll look at the general best practices and techniques we can use to decrease memory consumption, cold start times for Java Serverless development on AWS including GraalVM (Native Image) and AWS own offering SnapStart based on Firecracker microVM snapshot and restore and CRaC (Coordinated Restore at Checkpoint) runtime hooks. I'll also provide a lot of benchmarking on Lambda functions trying out various deployment package sizes, Lambda memory settings, Java compilation options and HTTP (a)synchronous clients and measure their impact on cold and warm start times.
Discover top-tier mobile app development services, offering innovative solutions for iOS and Android. Enhance your business with custom, user-friendly mobile applications.
ScyllaDB is making a major architecture shift. We’re moving from vNode replication to tablets – fragments of tables that are distributed independently, enabling dynamic data distribution and extreme elasticity. In this keynote, ScyllaDB co-founder and CTO Avi Kivity explains the reason for this shift, provides a look at the implementation and roadmap, and shares how this shift benefits ScyllaDB users.
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...Alex Pruden
Folding is a recent technique for building efficient recursive SNARKs. Several elegant folding protocols have been proposed, such as Nova, Supernova, Hypernova, Protostar, and others. However, all of them rely on an additively homomorphic commitment scheme based on discrete log, and are therefore not post-quantum secure. In this work we present LatticeFold, the first lattice-based folding protocol based on the Module SIS problem. This folding protocol naturally leads to an efficient recursive lattice-based SNARK and an efficient PCD scheme. LatticeFold supports folding low-degree relations, such as R1CS, as well as high-degree relations, such as CCS. The key challenge is to construct a secure folding protocol that works with the Ajtai commitment scheme. The difficulty, is ensuring that extracted witnesses are low norm through many rounds of folding. We present a novel technique using the sumcheck protocol to ensure that extracted witnesses are always low norm no matter how many rounds of folding are used. Our evaluation of the final proof system suggests that it is as performant as Hypernova, while providing post-quantum security.
Paper Link: https://eprint.iacr.org/2024/257
QA or the Highway - Component Testing: Bridging the gap between frontend appl...zjhamm304
These are the slides for the presentation, "Component Testing: Bridging the gap between frontend applications" that was presented at QA or the Highway 2024 in Columbus, OH by Zachary Hamm.
In the realm of cybersecurity, offensive security practices act as a critical shield. By simulating real-world attacks in a controlled environment, these techniques expose vulnerabilities before malicious actors can exploit them. This proactive approach allows manufacturers to identify and fix weaknesses, significantly enhancing system security.
This presentation delves into the development of a system designed to mimic Galileo's Open Service signal using software-defined radio (SDR) technology. We'll begin with a foundational overview of both Global Navigation Satellite Systems (GNSS) and the intricacies of digital signal processing.
The presentation culminates in a live demonstration. We'll showcase the manipulation of Galileo's Open Service pilot signal, simulating an attack on various software and hardware systems. This practical demonstration serves to highlight the potential consequences of unaddressed vulnerabilities, emphasizing the importance of offensive security practices in safeguarding critical infrastructure.
From Natural Language to Structured Solr Queries using LLMsSease
This talk draws on experimentation to enable AI applications with Solr. One important use case is to use AI for better accessibility and discoverability of the data: while User eXperience techniques, lexical search improvements, and data harmonization can take organizations to a good level of accessibility, a structural (or “cognitive” gap) remains between the data user needs and the data producer constraints.
That is where AI – and most importantly, Natural Language Processing and Large Language Model techniques – could make a difference. This natural language, conversational engine could facilitate access and usage of the data leveraging the semantics of any data source.
The objective of the presentation is to propose a technical approach and a way forward to achieve this goal.
The key concept is to enable users to express their search queries in natural language, which the LLM then enriches, interprets, and translates into structured queries based on the Solr index’s metadata.
This approach leverages the LLM’s ability to understand the nuances of natural language and the structure of documents within Apache Solr.
The LLM acts as an intermediary agent, offering a transparent experience to users automatically and potentially uncovering relevant documents that conventional search methods might overlook. The presentation will include the results of this experimental work, lessons learned, best practices, and the scope of future work that should improve the approach and make it production-ready.
Session 1 - Intro to Robotic Process Automation.pdfUiPathCommunity
👉 Check out our full 'Africa Series - Automation Student Developers (EN)' page to register for the full program:
https://bit.ly/Automation_Student_Kickstart
In this session, we shall introduce you to the world of automation, the UiPath Platform, and guide you on how to install and setup UiPath Studio on your Windows PC.
📕 Detailed agenda:
What is RPA? Benefits of RPA?
RPA Applications
The UiPath End-to-End Automation Platform
UiPath Studio CE Installation and Setup
💻 Extra training through UiPath Academy:
Introduction to Automation
UiPath Business Automation Platform
Explore automation development with UiPath Studio
👉 Register here for our upcoming Session 2 on June 20: Introduction to UiPath Studio Fundamentals: https://community.uipath.com/events/details/uipath-lagos-presents-session-2-introduction-to-uipath-studio-fundamentals/
[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...Jason Yip
The typical problem in product engineering is not bad strategy, so much as “no strategy”. This leads to confusion, lack of motivation, and incoherent action. The next time you look for a strategy and find an empty space, instead of waiting for it to be filled, I will show you how to fill it in yourself. If you’re wrong, it forces a correction. If you’re right, it helps create focus. I’ll share how I’ve approached this in the past, both what works and lessons for what didn’t work so well.
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor IvaniukFwdays
At this talk we will discuss DDoS protection tools and best practices, discuss network architectures and what AWS has to offer. Also, we will look into one of the largest DDoS attacks on Ukrainian infrastructure that happened in February 2022. We'll see, what techniques helped to keep the web resources available for Ukrainians and how AWS improved DDoS protection for all customers based on Ukraine experience
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-EfficiencyScyllaDB
Freshworks creates AI-boosted business software that helps employees work more efficiently and effectively. Managing data across multiple RDBMS and NoSQL databases was already a challenge at their current scale. To prepare for 10X growth, they knew it was time to rethink their database strategy. Learn how they architected a solution that would simplify scaling while keeping costs under control.
Conversational agents, or chatbots, are increasingly used to access all sorts of services using natural language. While open-domain chatbots - like ChatGPT - can converse on any topic, task-oriented chatbots - the focus of this paper - are designed for specific tasks, like booking a flight, obtaining customer support, or setting an appointment. Like any other software, task-oriented chatbots need to be properly tested, usually by defining and executing test scenarios (i.e., sequences of user-chatbot interactions). However, there is currently a lack of methods to quantify the completeness and strength of such test scenarios, which can lead to low-quality tests, and hence to buggy chatbots.
To fill this gap, we propose adapting mutation testing (MuT) for task-oriented chatbots. To this end, we introduce a set of mutation operators that emulate faults in chatbot designs, an architecture that enables MuT on chatbots built using heterogeneous technologies, and a practical realisation as an Eclipse plugin. Moreover, we evaluate the applicability, effectiveness and efficiency of our approach on open-source chatbots, with promising results.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/temporal-event-neural-networks-a-more-efficient-alternative-to-the-transformer-a-presentation-from-brainchip/
Chris Jones, Director of Product Management at BrainChip , presents the “Temporal Event Neural Networks: A More Efficient Alternative to the Transformer” tutorial at the May 2024 Embedded Vision Summit.
The expansion of AI services necessitates enhanced computational capabilities on edge devices. Temporal Event Neural Networks (TENNs), developed by BrainChip, represent a novel and highly efficient state-space network. TENNs demonstrate exceptional proficiency in handling multi-dimensional streaming data, facilitating advancements in object detection, action recognition, speech enhancement and language model/sequence generation. Through the utilization of polynomial-based continuous convolutions, TENNs streamline models, expedite training processes and significantly diminish memory requirements, achieving notable reductions of up to 50x in parameters and 5,000x in energy consumption compared to prevailing methodologies like transformers.
Integration with BrainChip’s Akida neuromorphic hardware IP further enhances TENNs’ capabilities, enabling the realization of highly capable, portable and passively cooled edge devices. This presentation delves into the technical innovations underlying TENNs, presents real-world benchmarks, and elucidates how this cutting-edge approach is positioned to revolutionize edge AI across diverse applications.
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
Hs3613611366
1. R. K. Srivastava et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1361-1366
www.ijera.com
RESEARCH ARTICLE
OPEN ACCESS
A Neural Network Approach For Heart Disease Prediction
Tanu Verma1, R. K. Srivastava2
1
2
Mewar University
Dept. of Computer Science, Bareilly College Bareilly, UP, India
Abstract
Artificial Neural Network for intelligent medical diagnoses has been shown to be an interesting topic. In this
paper we have used a neural network technique to predict a system, which can detect heart disease from their
physical symptoms. We have used a prediction method with the help of the back propagation algorithm to train
the networks. The actual procedure of medical diagnosis that usually is employed by physicians was analyzed
and converted to a computer program implemented format. After selecting some symptoms a data set contains
the information of fifty two cases was configured and applied to a M L P neural network.
Keywords: artificial neural network, back propagation algorithm
I. Introduction
Neural Network have been used in the field of
artificial intelligence, preferred as these use the
relation of dependency, a generation of function. The
model and language of neural networks are more
mathematically formulated hence most of the doctors
avoid to use neural networks for prediction of disease.
A prediction of heart disease system usually starts with
patients complaints and the physician learn more about
the patients situations interactively during the
diagnosis as well as by measuring some metrics such
as blood pressure, hemoglobin, s. urea, s. creating,
FBS(mg/d), PPb(mg/d),RBS etc.
The quantity of
examples is playing an important role for training
purpose but examples need to be selected carefully for
the reliability and efficient system. I have considered
the indirect relation of various parameters for data and
presume that their relations are time invariant in view
of the patient pathological test reports. The proposed
method is more efficient and provide better forecast.
The forecasted values obtained through the back
propagation algorithm process have been compared
with the observed productivity and their robustness has
been examined.
II. Artificial Neural Network
Back Propagation through time is a powerful
tool of artificial neural network with application to
many areas as pattern recognition, dynamic modeling
and
nonlinear
systems.
Back
propagation
algorithm(BPA) provides an efficient way to calculate
the gradient of the error function using chain rule of
differentiation. The error after initial computation in
the forward pass is propagated backward from the
output units, layer by layer. BPA, a generalized Delta
rule is commonly used algorithm for supervised
training of multi layer feed forward artificial neural
network. In supervised learning, we try to adapt an
artificial network so that the actual outputs ( Y ) come
www.ijera.com
close to some target outputs(Y) for a training set,
which contains T patterns. The goal is to adapt the
parameters of network so that it performs well for
pattern from outside the training set.
2.1 Back propagation Algorithm :
We have
proposed a neural network that will combine the
features of multi perceptron concept of both feed
forward part of back propagation algorithm and Let
N
the training set be {x(k),d(k)} k 1 ,Where x(k) is the
input pattern vector to the network and d(k) is the
desired output vector for the input pattern x(k).The
output of the jth output unit is denoted by yj ,
connections weights from the ith unit in one layer to
the jth unit in the layer above are denoted by wij. If m
be the no. of output units and dj(k) is the desired
output from the jth output unit whose actual output in
response to the kth input exemplar x(k) is yj ,for
j=1,2,3,……..,m. The sum of squares of the error over
all the output unit for this kth exemplar by
m
j 1
E(k)=(1/2)
[yj(k)-dj(k)]2
Error E(k) is affected by the output from unit j at the
output layer and is determined by
E (k )
yj dj
yj
The net input to output layer is of the form
yi
(1)
Sj=
y i(1)
i
wij-
j
is
Where
the output from the ith unit in the first
layer below the output layer, wij is connection weight
y (1)
multiplying i
j is the threshold of unit j. The
negative of threshold is defined to be the bias.
1361 | P a g e
2. R. K. Srivastava et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1361-1366
2.2 Computer code in C Language to trained the
Network: Let us consider the components x[0][0] to
x[ntmax][ni] so that there are “ntmax * ni” inputs to
the network and y[0] to y[ntmax] outputs. The value
“ntmax *ni“ decides how many neurons in the
network, “net” represents the total level of existing a
neuron and y[nt][k] represents the intensity of resulting
output from the neuron or activation level. We assume
the full range of allowed connections, simply for the
sake of generality.
#include<stdio.h>
#include<math.h>
#include<conio.h>
void main()
{
double
x[52][13],h[13][13],y[13],yd[13],dy[13],dh[13][13],ne
t,whi[13][13],woh[13];
double
xmax[700],xmin[700],ydmax[13],ydmin[13],e,dnet,dw
hi[13][13],dwoh[13],diff;
int ni=13,ntmax=52,ncmax,nh,i,j,k,nt,nc;
float eta;
FILE *f,*ee,*o;
clrscr();
printf("type no of iterations");
scanf("%d",&ncmax);
printf("type no. of hidden neurons");
scanf("%d",&nh);
printf("type value of learning rate");
scanf("%f",&eta);
for(i=0;i<=ni;++i)
for(j=0;j<=nh;++j)
whi[i][j]=0;
for(i=0;i<=ni;++i)
woh[i]=0;
f=fopen("data1","r");
o=fopen("out","w");
ee=fopen("error","w");
for(nt=0;nt<=ntmax;++nt)
fscanf(f,"%ld",&yd[nt]);
for(nt=0;nt<=ntmax;++nt)
for(i=0;i<=ni;++i)
fscanf(f,"%ld",&x[nt][i]);
for(nc=0;nc<=ncmax;++nc)
{
for(nt=0;nt<=ntmax;++nt)
{
for(j=0;j<=nh;++j)
{
net=0.0;
for(i=0;i<=ni;++i)
net+=whi[j][i]*x[nt][i];
h[nt][j]=1.0/(1.0+exp(-net));
}
}for(nt=0;nt<=ntmax;++nt)
{net=0;
for(j=1;j<=nh;++j)
net+=woh[j]*h[nt][j];
www.ijera.com
www.ijera.com
y[nt]=1.0/(1.0+exp(-net));
}
e=0.0;
for(nt=0;nt<=ntmax;++nt)
{
dnet=y[nt]-yd[nt];
e+=0.5*pow(dnet,2);
dy[nt]=dnet*y[nt]*(1.0-y[nt]);
}
printf("nc=%d,e=......%f",nc,e);
fprintf(ee,"%d%fn",nc,e);
for(nt=0;nt<=ntmax;++nt)
for(j=0;j<=nh;++j)
{
dnet=0.0;
dnet+=dy[nt]*woh[j];
dh[nt][j]=dnet*h[nt][j]*(1.0-h[nt][j]);
}
for(i=0;i<=nh;++i)
for(j=0;j<=ni;++j)
{
dwhi[i][j]=0.0;
for(nt=0;nt<=ntmax;++nt)
dwhi[i][j]+=x[nt][j]*dh[nt][i];
}
for(j=0;j<=nh;++j)
{
dwoh[j]=0.0;
for(nt=0;nt<=ntmax;++nt)
dwoh[j]+=h[nt][j]*dy[nt];
}
for(i=0;i<=ni;i++)
for(j=0;j<=nh;j++)
whi[j][i]-=eta*dwhi[j][i];
for(j=0;j<=nh;++j)
woh[j]-=eta*dwoh[j];
}
printf("n observed value t calculated value t
difference");
fprintf(o,"n observed value t calculated value t
difference");
for(nt=0;nt<=ntmax;++nt)
{
diff=0.0;
diff=yd[nt]-y[nt];
printf("n%ft%ft%f",yd[nt],y[nt],diff);
fprintf(o,"n %ft %ft %f",yd[nt],y[nt],diff);
}fclose(f);
getch();
}
III. Computation of ANN forecasted value
Considering the patient pathological and other
test reports related to heart disease as input x(k) and
particular S. No. of patient data set to be predicted as
desired output d(k) after applying the BPA, the
calculated output is treated as predicted value of cor.
Angio. The steps adapted for calculation of predicted
cor. Angio. value i.e. output through BPA is as
follows:
1362 | P a g e
3. R. K. Srivastava et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1361-1366
www.ijera.com
Step 1: Data set of patient S. No. 1 to 46 as input set
Step 6: Data set of patient S. No. 1 to 51 as input set
and Coronary Angiogram value of patient S. No. 46 as
and Coronary Angiogram value of patient S. No. 51 as
desired output.
desired output.
Step 2: Data set of patient S. No. 1 to 47 as input set
Step 7: Data set of patient S. No. 1 to 52 as input set
and Coronary Angiogram value of patient S. No. 47 as
and Coronary Angiogram value of patient S. No. 52 as
desired output.
desired output.
Step 3: Data set of patient S. No. 1 to 48 as input set
The algorithm has been implemented through C
and Coronary Angiogram value of patient S. No. 48 as
programming language, considering two hidden layers
desired output.
and computations have been made by various iterations
Step 4: Data set of patient S. No. 1 to 49 as input set
levels like: 100, 200, 500 & 1000. Out of these, the
and Coronary Angiogram value of patient S. No. 49 as
best suitable forecasted values have been obtained by
desired output.
model with 1000 iterations. The result so obtained has
Step 5: Data set of patient S. No. 1 to 50 as input set
been illustrated in Table 1 as follows:
and Coronary Angiogram value of patient S. No. 50 as
desired output.
Table: 1
S
NAME
sNo
.
AGE Hb
S.UR S.CR FBS
(Yrs) (gm% EA
EATI (mg/
)
(mg/ NIN dl)
dl)
E
(mg/
dl)
PPBS
(mg/dl
)
RBS
(mg/
dl)
TG
S.CHOLE
S
LDL
VLDL
HDL
FAST
ING
INSU
LIN
I.R.
ANN
COR. Foreca
ANG sted
I O. COR.
ANGI
O
value
1 H.C.YADAV
63
12.1
33
1.2 93.85
134.5
158
122
206
130
26
50
7.34
1
3
2 B.M PANDEY
65
12
20
1.07 72.28
118.6
132
117.14
145.5
83.23
23.43
38.9
12.2
2.18
0
3 K.P YADAV
LALMANI
4 SAROJ
KAVITA
5 PURVAR
54
13
24
1.12
76.4
114.8
148
114.6
138
84
22
32
10.2
1.92
3
55
12
24
1.23
70.2
116.8
98
117
136
76
24
36
8.13
1.4
3
38
12
20
0.98 74.81
136.1
124
115.75
124.97
71.03
23.15 30.79
10.1
1.86
0
6 KALI PRASAD
62
13.7
23
1.27 92.25
124.6
118
121.34
124.41
76.42
24.27 23.72
16
3.64
0
7 RAJPAT
60
11.4
24
1.1 68.69
94.7
96
105.45
103.5
48.21
21.09
34.2
2.07
0.35
3
8
60
8.9
33.6
1.37
69.4
126.1
103
73.76
89.76
23.51
14.75
51.5
2.12
0.36
3
45
13.9
41.3
1.13 78.87
114.2
134
152.1
163.2
82.58
30.42
50.2
13.9
2.7
1
10 V.D.SINGH
65
12.4
25.4
1.48 88.03
116.7
128
95.68
155.6
34.56
19.14
51.9
22.2
4.8
3
11 C.B.SINGH
MAKKHAN
12 LAL
57
13
27.7
80.2
136.6
150
96
248.5
180.2
19.26
49
39.3
7.78
2
61
10.4
31.1
1.24 98.86
126.7
142
86.65
118.26
49.63
17.33
51.3
14.2
3.46
0
13 CHAMPA DEVI
50
11.5
29
1
78
97.85
132
114
160
104
16
40
2
0.38
0
14 RAM DEV
50
15
30.5
1.37
84.6
116.6
102
115.9
261.2
191.1
23.18
46.9
13.9
2.9
1
15 HARISHANKER
CHHOTAK
16 SINGH
BANKEYLAL
17 YADAV
57
13.1
28.4
1.23 88.68
121.4
90
125.7
138
73
25
40
4.5
0.98
0
65
13.9
42.5
1.9
72.2
120.7
157
132.3
182.6
112.8
26.46
43.4
10.4
1.85
0
61
7.6
44.9
1.11
76.6
114.9
72.6
80.6
116.7
54.38
16.12
46.2
11.6
2.19
0
40
12
27
89
79.8
119.8
82
167.9
175.8
117
31
46
13.8
2.6
1
64
8.9
31.4
0.93
80.6
134.1
81.9
150.95
138.75
59.59
30.19
42.2
8.6
1.71
1
65
6.8
21.9
0.9
74.8
125.8
84.6
99.65
119.87
63.14
19.03 36.14
10.4
1.92
3
SI KANDEV
9 RAJDEV
18
B.M PANDEY
19 K.P YADAV
LALMANI
20 SAROJ
www.ijera.com
1.4
1363 | P a g e
5. R. K. Srivastava et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1361-1366
www.ijera.com
51 RAM RAJ
54
8.4
34.9
1.41 84.65
143.9
128
64
157
97
13
47
14.7
3.07
1
1.0925
52 KAZIM
36
12
28.4
1.6 75.98
153.6
133
148
190
112
29
48
8.4
1.57
2
1.9742
IV. Result & Conclusion
The proposed artificial neural network
technique has been implemented to have diagnosis of
heart disease. We have considered the indirect
relation of various parameters for time series data and
presume that their relations are time invariant. The
motivation of the study is to diagnose the heart
disease, data are collected through various sampling
techniques and obtained the diagnostic result through
ANN using back propagation algorithm. A network
requires information only on the input variable for
diagnostic system. As values on test data are
comparatively less the diagnostic model is reliable.
The availability of data have tremendous amount of
imprecision and uncertainty due to test reports of the
patients are based on
involvement of different
electronic and mechanical equipments. Network
performance could have been further improved by
providing more training data. Moreover the
considered connectionist models are robust, capable
of handling the approximate data and therefore
should be more reliable in worse situation. Optimal
result will depend on the selection of parameters
which is based on test results and symptoms of the
patients. It is evident through the study that neural
network model is even suitable over human
diagnostic system
Heart disease prediction is of much use to
the heart patient having pathological test data tending
towards expected position of heart to avoid the heart
attack. The motivation of the study is that the
pathological test data are collected through various
sampling and based on the reading of electronic
machines, involving vagueness. Comparison of
forecasted coronary angiogram test value of the
patient obtained through ANN using back
propagation algorithm with actual coronary
angiogram value of the patients are listed in table-2.
Table-2
S
No.
1
2
3
4
5
6
7
Name
COR.
ANGIO.
GUDDU
YADAV
SAUGAR
LAL
NISHATH
FATIMA
ABDUL
SALAAM
RAM
SUMAN
RAM RAJ
KAZIM
ANN
Forecasted
COR.
ANGIO.
1
0.9865
2
2.2376
0
0.0083
0
0.0063
1
1
2
1.1765
1.0925
1.9742
2.5
Cor.Angio. Values
2
1.5
COR. ANGIO.
1
ANN Forecasted COR.
ANGIO.
0.5
0
1
2
3
4
5
6
7
Patient’s S. No.
Fig.- Actual Cor.Angio. Vs Forecasted Cor.Angio. Values
www.ijera.com
1365 | P a g e
6. R. K. Srivastava et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1361-1366
www.ijera.com
In the study the target patient S.NO. 46 to 52 for
the prediction of coronary angiogram value
computed through the ANN method are quite
impressive by comparison with actual value.
Further, the computations shows that the predicted
data through ANN method provides much better,
suitable and reliable forecast for the heart disease
patients.
References
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9]
Chou-An Chen[2007], Neuro –Fuzzy
Technology as a Predictor of Parathyroid
Harmonse
Level
in
Hemodialysis
Patients,Tohku J,Exp.Med.,211,81-87
Ferdous Ahemad Sohel, A new Neural
Network with Fuzzy Technique, Disease
diagnosis, A Case study,Dept. of
Computer Science & Engg.,International
Islamic University-Dhaka
Holmstr,M. L. Koinstinen P, [1992],using
Additive
Noise in Backpropagation
Training,IEEE Transaction on Neural
Networks,pp 24-38,vol 3No. 1
K.K.Shukla,Raghunath,[1999],An
Efficient Global Algorithm for Supervised
Training of Neural Networks,International
Journal
of
Computers
and
EE,PERGAMON Press,25,pp 195-218
R. Brause, F Friedrich[2000],A Neuro
Fuzzy Approach as Medical Diagnostic
Interface,pp 201-206
S Moein,a Monadjemi[2006],A Novel
Fuzzy-Neural Based Medical Diagnosis
System,volume 1, Number 3
V.S. Kodogiannis,MBoulougoura[2007],
An Adaptive NeuroFuzzy Approach for
the Diagnosis in Wireless Capsule
endoscopy Imaging,International Journal
of Information Technology,Vol. 13 No. 1
Werbos Paul J. [1990], Back propagation
through time: what it does and how to do
it,Proceeding of the IEEE,78,1550-1559.
Yang CC[1998],The use of back
propagation neural network for the sim. &
analysis of time series data ,Transcations
of the ASAE,41,1181-1187
www.ijera.com
1366 | P a g e