CNN Lithology Prediction (Undergrad Thesis Jeremy Adi Padma Nagara - Universi...Jeremy Adi
This presentation will shows you that you can apply Machine Learning / Deep Learning in many fields. For this time, I use Deep Learning technique, which is Convolutional Neural Network, to tackle the problem in Geophysics Field (Gas Exploration - Oil and Gas Industry).
For the full resources, you can check it out here
https://github.com/Jeremy-Adi/CNN-Lithology-Classification
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Rapid Prediction of Extractives and Polyphenolic Contents in Pinus caribaea B...Waqas Tariq
The potential of near infrared reflectance spectroscopy (NIRS) for rapidly and accurately determining the extractives and polyphenol contents in Pinus caribaea bark extracts was assessed. Pinus caribaea bark samples were obtained from 110 trees in plantation stands at different locations of Ghana and were then scanned by NIRS. Their extractives and polyphenol contents reference values were obtained by TAPPI T204 om-88 and Folin-Ciocalteu methods respectively. These reference values were regressed against different spectral transformations using partial least square (PLS) regression. First derivative transformation equation of the raw spectral data, resulted in a coefficient of determination r2 in the external validation of 0.91 and 0.97 respectively for extractives content and polyphenol content. The calibration samples covered a wide range of extractives content from 34 – 45% and polyphenolic content from 16 – 23.5%. The standard deviation to root mean square error of cross validation ratio (SD/RMSECV), root mean square error of calibration to standard deviation ratio (RMSEC/SD), RMSECV/RMSEC and r2 for both extractives and polyphenol models were indicative of good prediction equations. The predicted values were thus highly correlated with time-consuming wet chemical measured values of extractives content and polyphenol content. The use of NIRS for the determination of the extractives and polyphenol contents in Pinus caribaea bark thus provides an advantage of time saving and cost of analysis.
IRJET- A Novel Hybrid Image Denoising Technique based on Trilateral Filtering...IRJET Journal
The document proposes a novel hybrid image denoising technique based on trilateral filtering and Gaussian conditional random field modeling. It combines trilateral filtering, which is an edge-preserving Gaussian filter, with Gaussian conditional random fields to deal with different noise levels in images. The technique involves first applying trilateral filtering to smooth the image, then using Gaussian conditional random fields on the smoothed image. Experimental results on test images show the proposed technique achieves better denoising performance than traditional trilateral filtering alone, as measured by higher peak signal-to-noise ratios and lower mean squared errors.
Efficacy of Use of A-Si EPID as Imaging Device in IMRT QAIOSR Journals
The document summarizes research into using an amorphous silicon electronic portal imaging device (EPID) for intensity modulated radiation therapy (IMRT) quality assurance. It describes calibrating the EPID to correctly relate pixel values to dose. Measurements were made with the EPID and with film in a phantom to verify that the EPID provides accurate dose distributions for an IMRT plan compared to the treatment planning system and film measurements. The study shows the EPID can accurately verify IMRT field doses in a homogeneous phantom and replace film for pretreatment dose verification when used with the appropriate calibration and correction procedures.
A Simple, Rapid Analysis, Portable, Low-cost, and Arduino-based Spectrophotom...TELKOMNIKA JOURNAL
The purpose of this study was to demonstrate a simple, rapid analysis, portable, and inexpensive spectrophotometer. Different from other spectrophotometers, the present instrument consisted of a single white light-emmiting-diode (LED) as a light source, a light sensor, and arduino electronic card as an acquisition system. To maintain a constant light intensity, a common white-color LED emitting a 450-620 nm continous spectrum was employed. Software was written in C++ to control photometer through a USB interface and for data acquistion to the computer. The instrument is designed to be simple and compacted with sizes of 200 x 130 x 150 mm for length, width, and height, respectively. The analysis of the total cost isabout less than 500 USD, while commercially available offers price of more than 10,000 USD. Thus, this makes the present instrument feasible for teaching support media in developing countries. The effectiveness of the present spectrophotometer for analyzing solution concentration (i.e. curcumin) was also demonstrated. Interestingly, the present spectrophotometer is able to measure the concentration of curcumin precisely with an accuracy of more than 90%. Different from commercially available standard UV-visible spectrophotometers that have limitations in the analysis of concentration of less than 50 ppm, the present system can measure the concentration with no limitation since the measurement is based on the LED light being penetrated.
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...iosrjce
IOSR Journal of Applied Physics (IOSR-JAP) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of physics and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in applied physics. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detect...civej
Most people believe that detector actuation time increases with the age of a device, but the current test
results suggest otherwise. According to government requirements, the standard actuation time limit for
photoelectric smoke detectors is 60 seconds or less in the zoned detection system; however, this experiment
discovered that new detectors all exhibited actuation times between 10 and 15 seconds. The actuation time
of the detectors decreased with the age of the devices. The current study also determined that if the
actuation time was 4 seconds or less, then the detector should be replaced because of the high chance of
false alarms. In short, detectors with actuation times between 4 and 15 seconds are ideal and should be
viewed as the standard for fire safety equipment. In addition, replacing detectors every 6 years in a zoned
system is suggested by this research, which found a greater chance of false alarms after 6 years of detector
use.
CNN Lithology Prediction (Undergrad Thesis Jeremy Adi Padma Nagara - Universi...Jeremy Adi
This presentation will shows you that you can apply Machine Learning / Deep Learning in many fields. For this time, I use Deep Learning technique, which is Convolutional Neural Network, to tackle the problem in Geophysics Field (Gas Exploration - Oil and Gas Industry).
For the full resources, you can check it out here
https://github.com/Jeremy-Adi/CNN-Lithology-Classification
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Rapid Prediction of Extractives and Polyphenolic Contents in Pinus caribaea B...Waqas Tariq
The potential of near infrared reflectance spectroscopy (NIRS) for rapidly and accurately determining the extractives and polyphenol contents in Pinus caribaea bark extracts was assessed. Pinus caribaea bark samples were obtained from 110 trees in plantation stands at different locations of Ghana and were then scanned by NIRS. Their extractives and polyphenol contents reference values were obtained by TAPPI T204 om-88 and Folin-Ciocalteu methods respectively. These reference values were regressed against different spectral transformations using partial least square (PLS) regression. First derivative transformation equation of the raw spectral data, resulted in a coefficient of determination r2 in the external validation of 0.91 and 0.97 respectively for extractives content and polyphenol content. The calibration samples covered a wide range of extractives content from 34 – 45% and polyphenolic content from 16 – 23.5%. The standard deviation to root mean square error of cross validation ratio (SD/RMSECV), root mean square error of calibration to standard deviation ratio (RMSEC/SD), RMSECV/RMSEC and r2 for both extractives and polyphenol models were indicative of good prediction equations. The predicted values were thus highly correlated with time-consuming wet chemical measured values of extractives content and polyphenol content. The use of NIRS for the determination of the extractives and polyphenol contents in Pinus caribaea bark thus provides an advantage of time saving and cost of analysis.
IRJET- A Novel Hybrid Image Denoising Technique based on Trilateral Filtering...IRJET Journal
The document proposes a novel hybrid image denoising technique based on trilateral filtering and Gaussian conditional random field modeling. It combines trilateral filtering, which is an edge-preserving Gaussian filter, with Gaussian conditional random fields to deal with different noise levels in images. The technique involves first applying trilateral filtering to smooth the image, then using Gaussian conditional random fields on the smoothed image. Experimental results on test images show the proposed technique achieves better denoising performance than traditional trilateral filtering alone, as measured by higher peak signal-to-noise ratios and lower mean squared errors.
Efficacy of Use of A-Si EPID as Imaging Device in IMRT QAIOSR Journals
The document summarizes research into using an amorphous silicon electronic portal imaging device (EPID) for intensity modulated radiation therapy (IMRT) quality assurance. It describes calibrating the EPID to correctly relate pixel values to dose. Measurements were made with the EPID and with film in a phantom to verify that the EPID provides accurate dose distributions for an IMRT plan compared to the treatment planning system and film measurements. The study shows the EPID can accurately verify IMRT field doses in a homogeneous phantom and replace film for pretreatment dose verification when used with the appropriate calibration and correction procedures.
A Simple, Rapid Analysis, Portable, Low-cost, and Arduino-based Spectrophotom...TELKOMNIKA JOURNAL
The purpose of this study was to demonstrate a simple, rapid analysis, portable, and inexpensive spectrophotometer. Different from other spectrophotometers, the present instrument consisted of a single white light-emmiting-diode (LED) as a light source, a light sensor, and arduino electronic card as an acquisition system. To maintain a constant light intensity, a common white-color LED emitting a 450-620 nm continous spectrum was employed. Software was written in C++ to control photometer through a USB interface and for data acquistion to the computer. The instrument is designed to be simple and compacted with sizes of 200 x 130 x 150 mm for length, width, and height, respectively. The analysis of the total cost isabout less than 500 USD, while commercially available offers price of more than 10,000 USD. Thus, this makes the present instrument feasible for teaching support media in developing countries. The effectiveness of the present spectrophotometer for analyzing solution concentration (i.e. curcumin) was also demonstrated. Interestingly, the present spectrophotometer is able to measure the concentration of curcumin precisely with an accuracy of more than 90%. Different from commercially available standard UV-visible spectrophotometers that have limitations in the analysis of concentration of less than 50 ppm, the present system can measure the concentration with no limitation since the measurement is based on the LED light being penetrated.
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...iosrjce
IOSR Journal of Applied Physics (IOSR-JAP) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of physics and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in applied physics. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detect...civej
Most people believe that detector actuation time increases with the age of a device, but the current test
results suggest otherwise. According to government requirements, the standard actuation time limit for
photoelectric smoke detectors is 60 seconds or less in the zoned detection system; however, this experiment
discovered that new detectors all exhibited actuation times between 10 and 15 seconds. The actuation time
of the detectors decreased with the age of the devices. The current study also determined that if the
actuation time was 4 seconds or less, then the detector should be replaced because of the high chance of
false alarms. In short, detectors with actuation times between 4 and 15 seconds are ideal and should be
viewed as the standard for fire safety equipment. In addition, replacing detectors every 6 years in a zoned
system is suggested by this research, which found a greater chance of false alarms after 6 years of detector
use.
Machine Learning Based Prediction Model to Estimate Calorific Value of DieselIRJET Journal
This document presents research on developing machine learning models to predict the calorific value of diesel fuel using other measurable properties as inputs. 179 diesel samples were collected from various companies in Maharashtra, India and their pH, viscosity, density, refractive index, flash point, and fire point were measured. These properties were used as inputs for artificial neural network, support vector regression, and multivariate linear regression models to predict calorific value. The models were evaluated based on accuracy, robustness, and reliability. Previous studies that used similar machine learning approaches to predict fuel properties are also discussed.
Computational Intelligence Approach for Predicting the Hardness Performances ...Waqas Tariq
This paper presents a computational approach on predicting of hardness performances for Titanium Aluminium Nitride (TiA1N) coating process. A new application in predicting the hardness performances of TiA1N coatings using a method called Support Vector Machine (SVM) and Artificial Neural Network (ANN) is implemented. TiAlN coatings are usually used in high-speed machining due to its excellent properties in surface hardness and wear resistance. Physical Vapor Deposition (PVD) magnetron sputtering process has been used to produce the TiA1N coatings. Based on the experimental dataset of previous work, the SVM and ANN model is used in predicting the hardness of TiA1N coatings. The influential factors of three coating process parameter namely substrate sputtering power, substrate bias voltage and substrate temperature were selected as input while the output parameter is the hardness. The results of proposed SVM and ANN models are compared to the experimental result and the hybrid RSM-Fuzzy model from previous work. The comparisons of SVM and ANN models against hybrid RSM-Fuzzy were based on predictive performances in order to obtain the most accurate model for prediction of hardness in TiA1N coating. In terms of predictive performance evaluation, four performances matrix were applied that are percentage error, mean square error (MSE), co-efficient determination (R 2) and model accuracy. The result has proved that the proposed SVM model shows the better result compared to the ANN and hybrid RSM-fuzzy model. The good performances of the results obtained by the SVM method shows that this method can be applied for prediction of hardness performances in TiA1N coating process with better predictive performances compared to ANN and hybrid RSM-Fuzzy.
PerkinElmer: Nano-Composites Characterization by Differential Scanning Calori...PerkinElmer, Inc.
This document summarizes a study that used an improved HyperDSC method to measure the specific heat capacity of nanocomposites up to high temperatures without degradation. The method involves rapidly heating and cooling samples at 400°C/min to obtain Cp data without dwelling at high temperatures. Testing on sapphire standards showed the new method achieves accuracy within 1-1.5% compared to literature values. The method was used to analyze thermoplastic polyurethane and epoxy nanocomposites, with the epoxy data possibly showing evidence of devitrification through multiple glass transition temperatures. The improved HyperDSC method extends the temperature range for accurate Cp measurements and could help identify devitrification in
This study aims to classify lithology in the Poseidon gas field using convolutional neural networks (CNN). The study uses well logs from 3 wells, including gamma ray, density, and neutron porosity logs. The CNN model is trained on lithology data from one well and tested on a second well. Several approaches are taken to improve the accuracy of lithology prediction, including simplifying the lithology classes, adding derived well log inputs, and removing thin layers from the data. The best prediction accuracy achieved is 57.7%. The CNN method is found to be less accurate for thin layers and more training data may be needed. Additional preprocessing and increasing the model complexity could further improve prediction.
1) The authors validate the performance of a neural network-based 13C NMR prediction algorithm using the publicly available NMRShiftDB database containing over 214,000 chemical shifts.
2) They find that the mean error between predicted and experimental shifts for the entire database is 1.59 ppm, with 50% of shifts predicted within 1 ppm error.
3) The database was divided based on whether shifts were present or absent from the training set used to develop the prediction algorithm. Slightly better accuracy was seen for shifts present in the training set.
The document describes a study that used artificial neural networks (ANN) to predict chemical oxygen demand (COD) levels in wastewater from an anaerobic reactor. Four different backpropagation algorithms - Levenberg-Marquardt, gradient descent with adaptive learning rate, gradient descent with momentum, and resilient backpropagation - were used to train a three-layer feedforward ANN model. The model trained with the Levenberg-Marquardt algorithm performed best with a mean squared error of 0.533 and regression coefficient of 0.991, accurately predicting COD levels. The Levenberg-Marquardt algorithm provided the most accurate ANN model for predicting COD in effluent from the ana
This document provides an overview of benchmarking experiments for criticality safety and reactor physics applications. It discusses the benchmarking process used by the International Criticality Safety Benchmark Evaluation Project (ICSBEP) and the International Reactor Physics Experiment Evaluation Project (IRPhEP). The tutorial aims to demonstrate the databases used to access benchmark experiments - the International Criticality Safety Benchmark Experiment Data (DICE) and the International Data Bank for Reactor Physics Experiments (IDAT). It outlines the typical contents of a benchmark report, including experimental data, evaluation, benchmark model specifications, sample calculations and measurements. Participation in ICSBEP and IRPhEP is highlighted as a collaborative international effort.
The document summarizes a study that used artificial neural networks (ANN) to predict chemical oxygen demand (COD) levels in an anaerobic wastewater treatment system. Four ANN backpropagation training algorithms - Levenberg-Marquardt, gradient descent with adaptive learning, gradient descent with momentum, and resilient backpropagation - were tested on a model using COD input data. The Levenberg-Marquardt algorithm produced the best results with the lowest mean squared error of 0.533 and highest regression value of 0.991, accurately predicting COD levels. The study demonstrates ANNs can effectively model and predict values in nonlinear wastewater treatment processes.
Fast and accurate primary user detection with machine learning techniques for...nooriasukmaningtyas
Spectrum decision is an important and crucial task for the secondary user to avail the unlicensed spectrum for transmission. Managing the spectrum is an efficient one for spectrum sensing. Determining the primary user presence in the spectrum is an essential work for using the licensed spectrum of primary user. The information which lacks in managing the spectrum are the information about the primary user presence, accuracy in determining the existence of user in the spectrum, the cost for computation and difficult in finding the user in low signal-to noise ratio (SNR) values. The proposed system overcomes the above limitations. In the proposed system, the various techniques of machine learning like decision tree, support vector machines, naive bayes, ensemble based trees, nearest neighbour’s and logistic regression are used for testing the algorithm. As a first step, the spectrum sensing is done in two stages with orthogonal frequency division multiplexing and energy detection algorithm at the various values of SNR. The results generated from the above algorithm is used for database generation. Next, the different machine learning techniques are trained and compared for the results produced by different algorithms with the characteristics like speed, time taken for training and accuracy in prediction. The accuracy and finding the presence of the user in the spectrum at low SNR values are achieved by all the algorithms. The computation cost of the algorithm differs from each other. Among the tested techniques, k-nearest neighbour (KNN) algorithm produces the better performance in a minimized time.
This document summarizes a research paper that proposes a hybrid genetic algorithm-particle swarm optimization (GA-PSO) approach for feature selection to design effective small interfering RNAs (siRNAs). The study uses a plant siRNA dataset containing 1,100 sequences and considers five properties (presence/absence of motifs, presence of specific nucleotides, thermodynamic characteristics) represented by 70 original features. A wrapper method evaluates feature subsets selected by the hybrid GA-PSO approach using an artificial neural network classifier. Results show the hybrid model improves predictive accuracy for siRNA design over general PSO alone. The hybrid approach aims to optimize feature selection performance by combining the exploration of GA with the exploitation of PSO.
siRNA has become an indispensible tool for silencing gene expression. It can act as an antiviral agent in RNAi pathway against plant diseases caused by plant viruses. However, identification of appropriate features for effective siRNA design has become a pressing issue for researchers which need to be resolved. Feature selection is a vital pre-processing technique involved in bioinformatics data set to find the most discriminative information not only for dimensionality reduction and detection of relevance features but also for minimizing the cost associated with features to design an accurate learning system. In this paper, we propose an ANN based feature selection approach using hybrid GA-PSO for selecting feature subset by discarding the irrelevant features and evaluating the cost of the model training. The results showed that the performance of proposed hybrid GA-PSO model outperformed the results of general PSO.a
Prediction of mango firmness by near infrared spectroscopy tandem with machin...CSITiaesprime
The firmness of the mango fruit is one of the internal physical properties that can show its quality. Unfortunately, non-destructive methods to measure this are not yet available. In the current study, we develop a calibration model using near infrared spectroscopy to predict the physical properties (firmness) of the mango cultivar Arumanis (Mangifera indica cv. Arumanis) via machine learning. Spectral data were acquired using the fourier transform near-infrared (FTNIR) benchtop with a wavelength range of 1000 to 2500 nm. Multivariate spectra analysis based on machine learning, including principal component regression (PCR), partial least squares regression (PLSR), and support vector machine regression (SVMR), was utilized and compared to estimate the firmness of fresh mangos. The results obtained show that the prediction of machine learning by PLSR is better than that of SVMR and PCR for the prediction of mango firmness. The coefficient correlation of calibration (rc) and validation (rcv), the root means square error of calibration (RMSE-C) and validation (RMSE-CV), and the ratio of prediction to deviation (RPD) were 0.941, 0.382 kgf, 0.920, 0.472 kgf, and 2.556, respectively. The general results satisfactorily indicate that near infrared spectroscopy technology integrated with an appropriate machine learning algorithm has optimistic results in determining the firmness of mango non-destructively.
Wide-band spectrum sensing with convolution neural network using spectral cor...IJECEIAES
Recognition of signals is a spectrum sensing challenge requiring simultaneous detection, temporal and spectral localization, and classification. In this approach, we present the convolution neural network (CNN) architecture, a powerful portrayal of the cyclo-stationarity trademark, for remote range detection and sign acknowledgment. Spectral correlation function is used along with CNN. In two scenarios, method-1 and method-2, the suggested approach is used to categorize wireless signals without any previous knowledge. Signals are detected and classified simultaneously in method-1. In method-2, the sensing and classification procedures take place sequentially. In contrast to conventional spectrum sensing techniques, the proposed CNN technique need not bother with a factual judgment process or past information on the signs’ separating qualities. The method beats both conventional sensing methods and signal-classifying deep learning networks when used to analyze real-world, over-the-air data in cellular bands. Despite the implementation’s emphasis on cellular signals, any signal having cyclo-stationary properties may be detected and classified using the provided approach. The proposed model has achieved more than 90% of testing accuracy at 15 dB.
Neural Network Model Development with Soft Computing Techniques for Membrane ...IJECEIAES
Membrane bioreactor employs an efficient filtration technology for solid and liquid separation in wastewater treatment process. Development of membrane filtration model is significant as this model can be used to predict filtration dynamic which is later utilized in control development. Most of the available models only suitable for monitoring purpose, which are too complex, required many variables and not suitable for control system design. This work focusing on the simple time seris model for membrane filtration process using neural network technique. In this paper, submerged membrane filtration model developed using recurrent neural network (RNN) train using genetic algorithm (GA), inertia weight particle swarm optimization (IWPSO) and gravitational search algorithm (GSA). These optimization algorithms are compared in term of its accuracy and convergent speed in updating the weights and biases of the RNN for optimal filtration model. The evaluation of the models is measured using three performance evaluations, which are mean square error (MSE), mean absolute deviation (MAD) and coefficient of determination (R2). From the results obtained, all methods yield satisfactory result for the model, with the best results given by IW-PSO.
This chapter provides conclusions and summaries from a dissertation on artificial intelligence techniques for power transformer fault diagnosis. The key conclusions are that rule-based and neural network approaches each have limitations that a hybrid model addresses better, and a specific hybrid system called ANNEPS was developed that integrates rule-based diagnosis with a multi-layer perceptron neural network. The chapter also outlines contributions, such as developing the ANNEPS system, and proposes areas for future work such as integrating additional fault diagnosis functions.
RAMYA SAVITHRI K SELECTION OF AN ANALYTICAL METHOD.pptxRamyasavithri
This document discusses factors to consider when selecting an analytical chemistry method. It outlines accuracy, precision, sensitivity, selectivity, robustness, ruggedness, scale of operation, equipment/time/cost as key criteria. Accuracy is emphasized as the most important - it measures how close experimental values are to true values. Other factors like precision, sensitivity and selectivity ensure a method can reliably distinguish between samples. Robustness and ruggedness refer to a method's reliability across different conditions. Scale of operation and equipment/time/cost considerations ensure a method is suitable for the analysis needs and resources. The document provides definitions and examples to explain how to evaluate methods based on these important selection criteria.
Algorithm for Modeling Unconventional Machine Tool Machining Parameters using...IDES Editor
Unconventional machining process finds a lot of
application in aerospace and precision industries. It is
preferred over other conventional methods because of the
advent of composite and high strength to weight ratio
materials, complex parts and also because of its high accuracy
and precision. Usually in unconventional machine tools, trial
and error method is used to fix the values of process
parameters. In the proposed work an algorithm which is
developed using Artificial Neural Network (ANN) is proposed
to create mathematical model functionally relating process
parameters and operating parameters of any unconventional
machine tool. This is accomplished by training a feed forward
network with back propagation learning algorithm. The
required data which are used for training and testing the ANN
in the case study is obtained by conducting trial runs in EBW
machine. By adopting the proposed algorithm there will be a
reduction in production time and set-up time along with
reduction in manufacturing cost in unconventional machining
processes. This in general increases the overall productivity.
The programs for training and testing the neural network are
developed, using MATLAB package
A novel application of artificial neural network for classifying agarwood es...IJECEIAES
This study uses artificial neural networks (ANN) to classify agarwood essential oil samples as either high or low quality. Stepwise regression is first used to select the most important compounds from a set of seven, reducing them to four key compounds. Two ANN models are then trained and tested: one using all seven original compounds and one using the four compounds selected by stepwise regression. Both networks achieve over 90% accuracy. The ANN using all seven compounds performs slightly better with 100% accuracy on the training, validation, and testing datasets and a lower mean squared error value. This full seven-compound ANN is selected as the best model for agarwood oil quality classification.
This is the MS thesis defend presented in Spring'13. The topic was to present an cloud connected embedded system performing water quality analysis using portable UV spectrometer. Artificial neural network based technique was developed to classify pure vs. dirty water based on COD (Chemical Oxygen Demand) parameter.
This document provides an overview of CT scanning technology. It begins with a brief history of x-rays and their discovery in 1895. It then discusses the evolution of CT scanning technology, from the first generation CT scanners created in the 1970s to advances like helical scanning, multi-detector arrays, and dual source scanning. The document also covers basic physics concepts in CT like attenuation, reconstruction, Hounsfield units, and improvements in detector technology that have allowed for wider coverage and faster scanning times. Overall, the document traces the development of CT scanning from its origins to modern multi-detector systems.
This document provides an overview of CT scanning technology. It begins with a brief history of x-rays and their discovery in 1895. It then discusses the evolution of CT scanning technology, from early generation scanners in the 1970s to advances like helical scanning, multi-detector arrays, and dual source scanning. The document covers basic physics concepts behind CT like attenuation, reconstruction, and Hounsfield units. It also compares single-slice CT to multi-slice CT and discusses detector technologies. Overall, the document provides a high-level introduction to CT scanning systems and their development over time.
Machine Learning Based Prediction Model to Estimate Calorific Value of DieselIRJET Journal
This document presents research on developing machine learning models to predict the calorific value of diesel fuel using other measurable properties as inputs. 179 diesel samples were collected from various companies in Maharashtra, India and their pH, viscosity, density, refractive index, flash point, and fire point were measured. These properties were used as inputs for artificial neural network, support vector regression, and multivariate linear regression models to predict calorific value. The models were evaluated based on accuracy, robustness, and reliability. Previous studies that used similar machine learning approaches to predict fuel properties are also discussed.
Computational Intelligence Approach for Predicting the Hardness Performances ...Waqas Tariq
This paper presents a computational approach on predicting of hardness performances for Titanium Aluminium Nitride (TiA1N) coating process. A new application in predicting the hardness performances of TiA1N coatings using a method called Support Vector Machine (SVM) and Artificial Neural Network (ANN) is implemented. TiAlN coatings are usually used in high-speed machining due to its excellent properties in surface hardness and wear resistance. Physical Vapor Deposition (PVD) magnetron sputtering process has been used to produce the TiA1N coatings. Based on the experimental dataset of previous work, the SVM and ANN model is used in predicting the hardness of TiA1N coatings. The influential factors of three coating process parameter namely substrate sputtering power, substrate bias voltage and substrate temperature were selected as input while the output parameter is the hardness. The results of proposed SVM and ANN models are compared to the experimental result and the hybrid RSM-Fuzzy model from previous work. The comparisons of SVM and ANN models against hybrid RSM-Fuzzy were based on predictive performances in order to obtain the most accurate model for prediction of hardness in TiA1N coating. In terms of predictive performance evaluation, four performances matrix were applied that are percentage error, mean square error (MSE), co-efficient determination (R 2) and model accuracy. The result has proved that the proposed SVM model shows the better result compared to the ANN and hybrid RSM-fuzzy model. The good performances of the results obtained by the SVM method shows that this method can be applied for prediction of hardness performances in TiA1N coating process with better predictive performances compared to ANN and hybrid RSM-Fuzzy.
PerkinElmer: Nano-Composites Characterization by Differential Scanning Calori...PerkinElmer, Inc.
This document summarizes a study that used an improved HyperDSC method to measure the specific heat capacity of nanocomposites up to high temperatures without degradation. The method involves rapidly heating and cooling samples at 400°C/min to obtain Cp data without dwelling at high temperatures. Testing on sapphire standards showed the new method achieves accuracy within 1-1.5% compared to literature values. The method was used to analyze thermoplastic polyurethane and epoxy nanocomposites, with the epoxy data possibly showing evidence of devitrification through multiple glass transition temperatures. The improved HyperDSC method extends the temperature range for accurate Cp measurements and could help identify devitrification in
This study aims to classify lithology in the Poseidon gas field using convolutional neural networks (CNN). The study uses well logs from 3 wells, including gamma ray, density, and neutron porosity logs. The CNN model is trained on lithology data from one well and tested on a second well. Several approaches are taken to improve the accuracy of lithology prediction, including simplifying the lithology classes, adding derived well log inputs, and removing thin layers from the data. The best prediction accuracy achieved is 57.7%. The CNN method is found to be less accurate for thin layers and more training data may be needed. Additional preprocessing and increasing the model complexity could further improve prediction.
1) The authors validate the performance of a neural network-based 13C NMR prediction algorithm using the publicly available NMRShiftDB database containing over 214,000 chemical shifts.
2) They find that the mean error between predicted and experimental shifts for the entire database is 1.59 ppm, with 50% of shifts predicted within 1 ppm error.
3) The database was divided based on whether shifts were present or absent from the training set used to develop the prediction algorithm. Slightly better accuracy was seen for shifts present in the training set.
The document describes a study that used artificial neural networks (ANN) to predict chemical oxygen demand (COD) levels in wastewater from an anaerobic reactor. Four different backpropagation algorithms - Levenberg-Marquardt, gradient descent with adaptive learning rate, gradient descent with momentum, and resilient backpropagation - were used to train a three-layer feedforward ANN model. The model trained with the Levenberg-Marquardt algorithm performed best with a mean squared error of 0.533 and regression coefficient of 0.991, accurately predicting COD levels. The Levenberg-Marquardt algorithm provided the most accurate ANN model for predicting COD in effluent from the ana
This document provides an overview of benchmarking experiments for criticality safety and reactor physics applications. It discusses the benchmarking process used by the International Criticality Safety Benchmark Evaluation Project (ICSBEP) and the International Reactor Physics Experiment Evaluation Project (IRPhEP). The tutorial aims to demonstrate the databases used to access benchmark experiments - the International Criticality Safety Benchmark Experiment Data (DICE) and the International Data Bank for Reactor Physics Experiments (IDAT). It outlines the typical contents of a benchmark report, including experimental data, evaluation, benchmark model specifications, sample calculations and measurements. Participation in ICSBEP and IRPhEP is highlighted as a collaborative international effort.
The document summarizes a study that used artificial neural networks (ANN) to predict chemical oxygen demand (COD) levels in an anaerobic wastewater treatment system. Four ANN backpropagation training algorithms - Levenberg-Marquardt, gradient descent with adaptive learning, gradient descent with momentum, and resilient backpropagation - were tested on a model using COD input data. The Levenberg-Marquardt algorithm produced the best results with the lowest mean squared error of 0.533 and highest regression value of 0.991, accurately predicting COD levels. The study demonstrates ANNs can effectively model and predict values in nonlinear wastewater treatment processes.
Fast and accurate primary user detection with machine learning techniques for...nooriasukmaningtyas
Spectrum decision is an important and crucial task for the secondary user to avail the unlicensed spectrum for transmission. Managing the spectrum is an efficient one for spectrum sensing. Determining the primary user presence in the spectrum is an essential work for using the licensed spectrum of primary user. The information which lacks in managing the spectrum are the information about the primary user presence, accuracy in determining the existence of user in the spectrum, the cost for computation and difficult in finding the user in low signal-to noise ratio (SNR) values. The proposed system overcomes the above limitations. In the proposed system, the various techniques of machine learning like decision tree, support vector machines, naive bayes, ensemble based trees, nearest neighbour’s and logistic regression are used for testing the algorithm. As a first step, the spectrum sensing is done in two stages with orthogonal frequency division multiplexing and energy detection algorithm at the various values of SNR. The results generated from the above algorithm is used for database generation. Next, the different machine learning techniques are trained and compared for the results produced by different algorithms with the characteristics like speed, time taken for training and accuracy in prediction. The accuracy and finding the presence of the user in the spectrum at low SNR values are achieved by all the algorithms. The computation cost of the algorithm differs from each other. Among the tested techniques, k-nearest neighbour (KNN) algorithm produces the better performance in a minimized time.
This document summarizes a research paper that proposes a hybrid genetic algorithm-particle swarm optimization (GA-PSO) approach for feature selection to design effective small interfering RNAs (siRNAs). The study uses a plant siRNA dataset containing 1,100 sequences and considers five properties (presence/absence of motifs, presence of specific nucleotides, thermodynamic characteristics) represented by 70 original features. A wrapper method evaluates feature subsets selected by the hybrid GA-PSO approach using an artificial neural network classifier. Results show the hybrid model improves predictive accuracy for siRNA design over general PSO alone. The hybrid approach aims to optimize feature selection performance by combining the exploration of GA with the exploitation of PSO.
siRNA has become an indispensible tool for silencing gene expression. It can act as an antiviral agent in RNAi pathway against plant diseases caused by plant viruses. However, identification of appropriate features for effective siRNA design has become a pressing issue for researchers which need to be resolved. Feature selection is a vital pre-processing technique involved in bioinformatics data set to find the most discriminative information not only for dimensionality reduction and detection of relevance features but also for minimizing the cost associated with features to design an accurate learning system. In this paper, we propose an ANN based feature selection approach using hybrid GA-PSO for selecting feature subset by discarding the irrelevant features and evaluating the cost of the model training. The results showed that the performance of proposed hybrid GA-PSO model outperformed the results of general PSO.a
Prediction of mango firmness by near infrared spectroscopy tandem with machin...CSITiaesprime
The firmness of the mango fruit is one of the internal physical properties that can show its quality. Unfortunately, non-destructive methods to measure this are not yet available. In the current study, we develop a calibration model using near infrared spectroscopy to predict the physical properties (firmness) of the mango cultivar Arumanis (Mangifera indica cv. Arumanis) via machine learning. Spectral data were acquired using the fourier transform near-infrared (FTNIR) benchtop with a wavelength range of 1000 to 2500 nm. Multivariate spectra analysis based on machine learning, including principal component regression (PCR), partial least squares regression (PLSR), and support vector machine regression (SVMR), was utilized and compared to estimate the firmness of fresh mangos. The results obtained show that the prediction of machine learning by PLSR is better than that of SVMR and PCR for the prediction of mango firmness. The coefficient correlation of calibration (rc) and validation (rcv), the root means square error of calibration (RMSE-C) and validation (RMSE-CV), and the ratio of prediction to deviation (RPD) were 0.941, 0.382 kgf, 0.920, 0.472 kgf, and 2.556, respectively. The general results satisfactorily indicate that near infrared spectroscopy technology integrated with an appropriate machine learning algorithm has optimistic results in determining the firmness of mango non-destructively.
Wide-band spectrum sensing with convolution neural network using spectral cor...IJECEIAES
Recognition of signals is a spectrum sensing challenge requiring simultaneous detection, temporal and spectral localization, and classification. In this approach, we present the convolution neural network (CNN) architecture, a powerful portrayal of the cyclo-stationarity trademark, for remote range detection and sign acknowledgment. Spectral correlation function is used along with CNN. In two scenarios, method-1 and method-2, the suggested approach is used to categorize wireless signals without any previous knowledge. Signals are detected and classified simultaneously in method-1. In method-2, the sensing and classification procedures take place sequentially. In contrast to conventional spectrum sensing techniques, the proposed CNN technique need not bother with a factual judgment process or past information on the signs’ separating qualities. The method beats both conventional sensing methods and signal-classifying deep learning networks when used to analyze real-world, over-the-air data in cellular bands. Despite the implementation’s emphasis on cellular signals, any signal having cyclo-stationary properties may be detected and classified using the provided approach. The proposed model has achieved more than 90% of testing accuracy at 15 dB.
Neural Network Model Development with Soft Computing Techniques for Membrane ...IJECEIAES
Membrane bioreactor employs an efficient filtration technology for solid and liquid separation in wastewater treatment process. Development of membrane filtration model is significant as this model can be used to predict filtration dynamic which is later utilized in control development. Most of the available models only suitable for monitoring purpose, which are too complex, required many variables and not suitable for control system design. This work focusing on the simple time seris model for membrane filtration process using neural network technique. In this paper, submerged membrane filtration model developed using recurrent neural network (RNN) train using genetic algorithm (GA), inertia weight particle swarm optimization (IWPSO) and gravitational search algorithm (GSA). These optimization algorithms are compared in term of its accuracy and convergent speed in updating the weights and biases of the RNN for optimal filtration model. The evaluation of the models is measured using three performance evaluations, which are mean square error (MSE), mean absolute deviation (MAD) and coefficient of determination (R2). From the results obtained, all methods yield satisfactory result for the model, with the best results given by IW-PSO.
This chapter provides conclusions and summaries from a dissertation on artificial intelligence techniques for power transformer fault diagnosis. The key conclusions are that rule-based and neural network approaches each have limitations that a hybrid model addresses better, and a specific hybrid system called ANNEPS was developed that integrates rule-based diagnosis with a multi-layer perceptron neural network. The chapter also outlines contributions, such as developing the ANNEPS system, and proposes areas for future work such as integrating additional fault diagnosis functions.
RAMYA SAVITHRI K SELECTION OF AN ANALYTICAL METHOD.pptxRamyasavithri
This document discusses factors to consider when selecting an analytical chemistry method. It outlines accuracy, precision, sensitivity, selectivity, robustness, ruggedness, scale of operation, equipment/time/cost as key criteria. Accuracy is emphasized as the most important - it measures how close experimental values are to true values. Other factors like precision, sensitivity and selectivity ensure a method can reliably distinguish between samples. Robustness and ruggedness refer to a method's reliability across different conditions. Scale of operation and equipment/time/cost considerations ensure a method is suitable for the analysis needs and resources. The document provides definitions and examples to explain how to evaluate methods based on these important selection criteria.
Algorithm for Modeling Unconventional Machine Tool Machining Parameters using...IDES Editor
Unconventional machining process finds a lot of
application in aerospace and precision industries. It is
preferred over other conventional methods because of the
advent of composite and high strength to weight ratio
materials, complex parts and also because of its high accuracy
and precision. Usually in unconventional machine tools, trial
and error method is used to fix the values of process
parameters. In the proposed work an algorithm which is
developed using Artificial Neural Network (ANN) is proposed
to create mathematical model functionally relating process
parameters and operating parameters of any unconventional
machine tool. This is accomplished by training a feed forward
network with back propagation learning algorithm. The
required data which are used for training and testing the ANN
in the case study is obtained by conducting trial runs in EBW
machine. By adopting the proposed algorithm there will be a
reduction in production time and set-up time along with
reduction in manufacturing cost in unconventional machining
processes. This in general increases the overall productivity.
The programs for training and testing the neural network are
developed, using MATLAB package
A novel application of artificial neural network for classifying agarwood es...IJECEIAES
This study uses artificial neural networks (ANN) to classify agarwood essential oil samples as either high or low quality. Stepwise regression is first used to select the most important compounds from a set of seven, reducing them to four key compounds. Two ANN models are then trained and tested: one using all seven original compounds and one using the four compounds selected by stepwise regression. Both networks achieve over 90% accuracy. The ANN using all seven compounds performs slightly better with 100% accuracy on the training, validation, and testing datasets and a lower mean squared error value. This full seven-compound ANN is selected as the best model for agarwood oil quality classification.
This is the MS thesis defend presented in Spring'13. The topic was to present an cloud connected embedded system performing water quality analysis using portable UV spectrometer. Artificial neural network based technique was developed to classify pure vs. dirty water based on COD (Chemical Oxygen Demand) parameter.
This document provides an overview of CT scanning technology. It begins with a brief history of x-rays and their discovery in 1895. It then discusses the evolution of CT scanning technology, from the first generation CT scanners created in the 1970s to advances like helical scanning, multi-detector arrays, and dual source scanning. The document also covers basic physics concepts in CT like attenuation, reconstruction, Hounsfield units, and improvements in detector technology that have allowed for wider coverage and faster scanning times. Overall, the document traces the development of CT scanning from its origins to modern multi-detector systems.
This document provides an overview of CT scanning technology. It begins with a brief history of x-rays and their discovery in 1895. It then discusses the evolution of CT scanning technology, from early generation scanners in the 1970s to advances like helical scanning, multi-detector arrays, and dual source scanning. The document covers basic physics concepts behind CT like attenuation, reconstruction, and Hounsfield units. It also compares single-slice CT to multi-slice CT and discusses detector technologies. Overall, the document provides a high-level introduction to CT scanning systems and their development over time.
Dokumen tersebut membahas tentang konsep dasar dalam fisika radiasi untuk mahasiswa radiografi, meliputi definisi dan satuan-satuan dosimetri seperti paparan, dosis serap, dosis ekivalen, dan dosis efektif serta faktor-faktor yang mempengaruhinya. Dokumen ini juga menjelaskan konsep radioaktivitas dan dosis eksternal.
Dokumen tersebut membahas interaksi sinar X dengan materi. Ada beberapa jenis interaksi yang dijelaskan seperti hamburan klasik, hamburan Compton, penyerapan fotolistrik, pembentukan pasangan, dan disintegrasi fotonuklir. Interaksi tersebut bergantung pada tingkat energi sinar X yang digunakan.
Dokumen tersebut merupakan template untuk penulisan artikel dalam jurnal Sanitas tentang Teknologi dan Seni Kesehatan. Template ini memberikan pedoman penulisan mulai dari format penulisan judul, nama penulis, abstrak, kata kunci, bagian-bagian artikel (pendahuluan, metode, hasil dan pembahasan, simpulan, ucapan terima kasih, daftar pustaka) beserta contoh-contoh penulisannya.
The document provides guidelines for writing journal articles for a training program on publishing departmental journals in Radiodiagnostics and Radiotherapy. It outlines the structure and formatting requirements, including sections for the title, authors' names and affiliations, English and Indonesian abstracts under 200 words each, 5 English and Indonesian keywords, introduction, methods, results and discussion, conclusion, and references in APA style. Details are given on formatting text, tables, figures, references, and ethical guidelines.
1. Ringkasan dokumen UAS mata kuliah Matematika Dasar tentang penyelesaian persamaan linier dengan eliminasi matriks Gauss Jourdan dan buktikan identitas aljabar.
2. Metode eliminasi matriks Gauss Jourdan digunakan untuk menentukan nilai a, b, c, dan d dari sistem persamaan linier. Identitas aljabar -2A + B = -1 terbukti benar dengan A = 1 dan B = -1.
3. Soal integral
Dokumen ini berisi jawaban soal ujian akhir semester mata kuliah Matematika Dasar untuk program studi Radiodiagnostik dan Radioterapi. Terdapat empat soal yang dibahas, yaitu: 1) membuktikan suatu persamaan himpunan menggunakan hukum himpunan dan tabel logika himpunan, 2) menentukan nilai dari suatu ekspresi, 3) membuktikan suatu pernyataan, dan 4) menyelesaikan persamaan diferensial parsial.
The skin is the largest organ and its health plays a vital role among the other sense organs. The skin concerns like acne breakout, psoriasis, or anything similar along the lines, finding a qualified and experienced dermatologist becomes paramount.
Adhd Medication Shortage Uk - trinexpharmacy.comreignlana06
The UK is currently facing a Adhd Medication Shortage Uk, which has left many patients and their families grappling with uncertainty and frustration. ADHD, or Attention Deficit Hyperactivity Disorder, is a chronic condition that requires consistent medication to manage effectively. This shortage has highlighted the critical role these medications play in the daily lives of those affected by ADHD. Contact : +1 (747) 209 – 3649 E-mail : sales@trinexpharmacy.com
Kosmoderma Academy, a leading institution in the field of dermatology and aesthetics, offers comprehensive courses in cosmetology and trichology. Our specialized courses on PRP (Hair), DR+Growth Factor, GFC, and Qr678 are designed to equip practitioners with advanced skills and knowledge to excel in hair restoration and growth treatments.
DECLARATION OF HELSINKI - History and principlesanaghabharat01
This SlideShare presentation provides a comprehensive overview of the Declaration of Helsinki, a foundational document outlining ethical guidelines for conducting medical research involving human subjects.
Promoting Wellbeing - Applied Social Psychology - Psychology SuperNotesPsychoTech Services
A proprietary approach developed by bringing together the best of learning theories from Psychology, design principles from the world of visualization, and pedagogical methods from over a decade of training experience, that enables you to: Learn better, faster!
share - Lions, tigers, AI and health misinformation, oh my!.pptxTina Purnat
• Pitfalls and pivots needed to use AI effectively in public health
• Evidence-based strategies to address health misinformation effectively
• Building trust with communities online and offline
• Equipping health professionals to address questions, concerns and health misinformation
• Assessing risk and mitigating harm from adverse health narratives in communities, health workforce and health system
Travel Clinic Cardiff: Health Advice for International TravelersNX Healthcare
Travel Clinic Cardiff offers comprehensive travel health services, including vaccinations, travel advice, and preventive care for international travelers. Our expert team ensures you are well-prepared and protected for your journey, providing personalized consultations tailored to your destination. Conveniently located in Cardiff, we help you travel with confidence and peace of mind. Visit us: www.nxhealthcare.co.uk
8 Surprising Reasons To Meditate 40 Minutes A Day That Can Change Your Life.pptxHolistified Wellness
We’re talking about Vedic Meditation, a form of meditation that has been around for at least 5,000 years. Back then, the people who lived in the Indus Valley, now known as India and Pakistan, practised meditation as a fundamental part of daily life. This knowledge that has given us yoga and Ayurveda, was known as Veda, hence the name Vedic. And though there are some written records, the practice has been passed down verbally from generation to generation.