Search

Multi-class classification is one of the major challenges in real world application. Classification algorithms are generally binary in nature and must be extended for multi-class problems. Therefore, in this paper, we proposed an enhanced Genetically Optimized Neural Network (GONN) algorithm, for solving multi-class classification problems. We used a multi-tree GONN representation which integrates multiple GONN trees; each individual is a single GONN classifier. Thus enhanced classifier is an integrated version of individual GONN classifiers for all classes. The integrated version of classifiers is evolved genetically to optimize its architecture for multi-class classification. To demonstrate our results, we had taken seven datasets from UCI Machine Learning repository and compared the classification accuracy and training time of enhanced GONN with classical Koza’s model and classical Back propagation model. Our algorithm gives better classification accuracy of almost 5% and 8% than Koza’s model and Back propagation model respectively even for complex and real multi-class data in lesser amount of time. This enhanced GONN algorithm produces better results than popular classification algorithms like Genetic Algorithm, Support Vector Machine and Neural Network which makes it a good alternative to the well-known machine learning methods for solving multi-class classification problems. Even for datasets containing noise and complex features, the results produced by enhanced GONN is much better than other machine learning algorithms. The proposed enhanced GONN can be applied to expert and intelligent systems for effectively classifying large, complex and noisy real time multi-class data. [ABSTRACT FROM AUTHOR]

The human brain is a delicate mix of neurons (brain cells), electrical impulses and chemicals, known as neurotransmitters. Any damage has the potential to disrupt the workings of the brain and cause seizures. These epileptic seizures are the manifestations of epilepsy. The electroencephalograph (EEG) signals register average neuronal activity from the cerebral cortex and label changes in activity over large areas. A detailed analysis of these electroencephalograph (EEG) signals provides valuable insights into the mechanisms instigating epileptic disorders. Moreover, the detection of interictal spikes and epileptic seizures in an EEG signal plays an important role in the diagnosis of epilepsy. Automatic seizure detection methods are required, as these epileptic seizures are volatile and unpredictable. This paper deals with an automated detection of epileptic seizures in EEG signals using empirical mode decomposition (EMD) for feature extraction and proposes a novel genetic programming (GP) approach for classifying the EEG signals. Improvements in the standard GP approach are made using a Constructive Genetic Programming (CGP) in which constructive crossover and constructive subtree mutation operators are introduced. A hill climbing search is integrated in crossover and mutation operators to remove the destructive nature of these operators. A new concept of selecting the Globally Prime offspring is also presented to select the best fitness offspring generated during crossover. To decrease the time complexity of GP, a new dynamic fitness value computation (DFVC) is employed to increase the computational speed. We conducted five different sets of experiments to evaluate the performance of the proposed model in the classification of different mixtures of normal, interictal and ictal signals, and the accuracies achieved are outstandingly high. The experimental results are compared with the existing methods on same datasets, and these results affirm the potential use of our method for accurately detecting epileptic seizures in an EEG signal. [ABSTRACT FROM AUTHOR]

One in every eight women is susceptible to breast cancer, at some point of time in her life. Early detection and effective treatment is the only rescue to reduce breast cancer mortality. Accurate classification of a breast cancer tumor is an important task in medical diagnosis. Machine learning techniques are gaining importance in medical diagnosis because of their classification capability. In this paper, we propose a new, Genetically Optimized Neural Network (GONN) algorithm, for solving classification problems. We evolve a neural network genetically to optimize its architecture (structure and weight) for classification. We introduce new crossover and mutation operators which differ from standard crossover and mutation operators to reduce the destructive nature of these operators. We use the GONN algorithm to classify breast cancer tumors as benign or malignant. To demonstrate our results, we had taken the WBCD database from UCI Machine Learning repository and compared the classification accuracy, sensitivity, specificity, confusion matrix, ROC curves and AUC under ROC curves of GONN with classical model and classical back propagation model. Our algorithm gives classification accuracy of 98.24%, 99.63% and 100% for 50–50, 60–40, 70–30 training–testing partition respectively and 100% for 10 fold cross validation. The results show that our approach works well with the breast cancer database and can be a good alternative to the well-known machine learning methods. [ABSTRACT FROM AUTHOR]

Abstract The paper deals with an experimental series with the new biaxial cruciform X0-specimen to study the stress state and loading path dependence of ductile damage and fracture. The ongoing material deterioration is studied experimentally to develop and validate corresponding phenomenological damage and fracture models.In this context the new cruciform X0-specimen has been proposed which is characterized by four independent notched regions where inelastic deformations as well as damage and fracture are localized. The specimen allows investigation of a wide range of stress states and can be applied for different loading paths. A series of biaxial experiments with proportional and corresponding non-proportional loading paths has been performed and the experimental technique with different loading histories is presented in detail. The experiments have been monitored by a special six camera DIC setting allowing even the analysis of the specimen behavior in thickness direction. Furthermore, the fracture surfaces have been analyzed by scanning electron microscopy (SEM). The results based on proportional and non-proportional loading paths clearly show that damage and fracture processes are load-path-dependent. [ABSTRACT FROM AUTHOR]

• To propose novel techniques to predict greenhouse gas emissions and minimize energy consumption in renewable sources based on a sustainable environment. • The deep neural network has improved energy efficiency to predict greenhouse gas emissions using a statistic regression neural network. • This research proposed a novel technique in predicting greenhouse gas emission and minimization of energy consumption in renewable sources based on a sustainable environment. • Here, the greenhouse gas emission has been predicted using statistic regression neural network. The long-term viability of energy resources as a main input is essential to achieve long-term economic growth of a country and the energy efficiency significantly reduces energy consumption and greenhouse gas emissions, supporting environmental sustainability. As a result, a number of governments, led by those in the developed world, are making an effort to enact laws governing energy efficiency. This study suggests cutting-edge methods for forecasting greenhouse gas emissions and reducing energy demand from renewable sources based on a sustainable environment. Utilizing the statistical regression neural network (SRNN), greenhouse gas emissions have been predicted, and the deep neural network's (DNN) energy efficiency has increased. The SRNN_DNN intensity method out predicts evaluated MLR (multiple linear regression) and second- and third-order non-linear MPR (multiple polynomial regression) techniques according to MAPE (mean absolute percentage error) results. Furthermore, presented methods are considered suitable for computing GHG emissions due to the high accuracy of the SRNN DNN model. The anticipated greenhouse gas emissions related to energy were remarkably similar to the actual emissions of EU (European Union) nations. [ABSTRACT FROM AUTHOR]

Land surface data is one of the entry points for a enormous resource management and human activity such as to monitor farming, ecology, urban management, and territories. This research aimed to improve the performance of the multispectral image processing technique using a novel deep learning based classification approaches used in classifying the surfaces in multispectral satellite images. The monitoring of Internet of Things (IoT) based wireless communication using secure locations sensor network protocol (SLSNP). The multispectral satellite images are collected based on developing and developed countries. Upon the collection of multispectral image data using deep convolution neural network (DCNN) deep learning system landmarks of the multispectral images are estimated. This will be effective for the identification of resources in a particular location. The simulation results show classification accuracy, precision, recall and the network lifetime, efficiency, throughput based on data transmission from satellite for secure location based wireless sensor networks (WSNs). [ABSTRACT FROM AUTHOR]

• This research proposed novel technique in agricultural farm monitoring and crop disease prediction using deep learning architectures. • Here the monitored data has been collected based on IoT module along with the historical data of cultivation farm image data. • This data has been processed for removal of noise removal and image resizing. • The obtained data and anticipate when a plant will (or will not) get a disease with a high degree of precision, with the ultimate goal of making agriculture more sustainable. Agriculture is necessary for all human activities to survive. Overpopulation and resource competitiveness are major challenges that threaten the planet's food security. Smart farming as well as precision agriculture advancements provide critical tools for addressing agricultural sustainability concerns and addressing the ever-increasing complexity of difficulties in agricultural production systems. This research proposed novel technique in agricultural farm monitoring and crop disease prediction using deep learning architectures. Here the monitored data has been collected based on IoT module along with the historical data of cultivation farm image data. This data has been processed for removal of noise removal and image resizing. The features of processed data has been extracted using deep attention layer based convolutional learning (DAL_CL) in which the features of data has been extracted. This extracted data has been classified using recursive architecture based on neural networks (RNN). The suggested system may use data categorization and deep learning to exploit obtained data and anticipate when a plant will (or will not) get a disease with a high degree of precision, with ultimate goal of making agriculture more sustainable.Experimental results shows the accuracy of 96%, precision of 89%, specificity of 89%, F-1 score of 75% and AUC of 66%. [ABSTRACT FROM AUTHOR]

• A novel LSTM based method is implemented for emotion recognition using EEG signals. • Comparative Analysis of LSTM model. • A new EEG signal dataset for stimuli is created using portable 4-channel MUSE2. • A human behaviour analysis is performed for age and gender based responsiveness. Positive and Negative emotions are experienced by the majority of individuals in their day-to-day life. It is important to control access of negative emotions because it may lead to several chronic health issues like depression and anxiety. The purpose of this research work is to develop a portable brainwave driven system for recognizing positive, negative, and neutral emotions. This research considers the classification of four negative class of emotions using genres sadness, disgust, angry, and surprise along with the classification of three basic class of emotions i.e., positive, negative, and neutral. This paper introduces a long short term memory deep learning (LSTM) network to recognize emotions using EEG signals. The primary goal of this approach is to assess the classification performance of the LSTM model. The secondary goal is to assess the human behavior of different age groups and gender. We have compared the performance of Multilayer Perceptron (MLP), K-nearest neighbors (KNN), Support Vector Machine (SVM), LIB-Support Vector Machine (LIB-SVM), and LSTM based deep learning model for classification. The analysis shows that, for four class of emotions LSTM based deep learning model provides classification accuracy as 83.12%, 86.94%, 91.67%, and 94.12% for 50–50, 60–40, 70–30, and 10-fold cross-validations. For three class of emotions LSTM based deep learning model provides classification accuracy as 81.33%, 85.41%, 89.44%, and 92.66% for 50–50, 60–40, 70–30, and 10-fold cross-validation. The generalizability and reliability of this approach are evaluated by applying our approach to publicly available EEG datasets DEAP and SEED. In compliance with the self-reported feelings, brain signals of 18–25 years of age group provided the highest emotional identification. The results show that among genders, females are more emotionally active as compared to males. These results affirmed the potential use of our method for recognizing positive, negative, and neutral emotions. [ABSTRACT FROM AUTHOR]

• An enhanced distance score (eD-score) fitness function is proposed to handle unbalanced dataset classification. • A new EEG signal dataset for emotional clips is created with a portable, computer-efficient single-channel EEG headset. • A novel eDGP framework is proposed for the classification of unbalanced emotion recognition data. • Analysis of human behavior for age, genre, gender, and attention level is performed. In cognitive science and human-computer interaction, automatic human emotion recognition using physiological stimuli is a key technology. This research considers two-class (positive and negative) of emotions recognition using electroencephalogram (EEG) signals in response to an emotional clip from the genres happy, amusement, sad, and horror. This paper introduces an enhanced fitness function named as eD-score to recognize emotions using EEG signals. The primary goal of this research is to assess how genres affect human emotions. We also analyzed human behaviour based on age and gender responsiveness. We have compared the performance of Multilayer Perceptron (MLP), K-nearest neighbors (KNN), Support Vector Machine (SVM), D-score Genetic Programming (DGP), and enhanced D-score Genetic Programming (eDGP) for classification of emotions. The analysis shows that for two class of emotion eDGP provides classification accuracy as 83.33%, 84.69%, 85.88%, and 87.61% for 50-50, 60-40, 70-30, and 10-fold cross-validations. Generalizability and reliability of this approach is evaluated by applying the proposed approach to publicly available EEG datasets DEAP and SEED. When participants in this research are exposed to amusement genre, their reaction is positive emotion. In compliance with the self-reported feelings, brain signals of 26–35 years of age group provided the highest emotional identification. Among genders, females are more emotionally active as compared to males. These results affirmed the potential use of our method for recognizing emotions. [ABSTRACT FROM AUTHOR]

In cognitive science, the real-time recognition of human's emotional state is pertinent for machine emotional intelligence and human-machine interaction. Conventional emotion recognition systems use subjective feedback questionnaires, analysis of facial features from videos, and online sentiment analysis. This research proposes a system for real-time detection of emotions in response to emotional movie clips. These movie clips elicitate emotions in humans, and during that time, we have recorded their brain signals using Electroencephalogram (EEG) device and analyze their emotional state. This research work considered four class of emotions (happy, calm, fear, and sadness). This method leverages Fast Fourier Transform (FFT) for feature extraction and Genetic Programming (GP) for classification of EEG data. Experiments were conducted on EEG data acquired with a single dry electrode device NeuroSky Mind Wave 2. To collect data, a standardized database of 23 emotional Hindi film clips were used. All clips individually induce different emotions, and data collection was done based on these emotions elicited as the clips contain emotionally inductive scenes. Twenty participants took part in this study and volunteered for data collection. This system classifies four discrete emotions which are: happy, calm, fear, and sadness with an average of 89.14% accuracy. These results demonstrated improvements in state-of-the-art methods and affirmed the potential use of our method for recognizing these emotions. [ABSTRACT FROM AUTHOR]

• Novel fitness functions F2 score and D score is proposed. • Proposed fitness functions tackle the problem of unbalanced breast cancer data classification. • F2 score gives more weight age to minority classes. Breast Cancer is a common disease and to prevent it, the disease must be identified at earlier stages. Available breast cancer datasets are unbalanced in nature, i.e. there are more instances of benign (non-cancerous) cases then malignant (cancerous) ones. Therefore, it is a challenging task for most machine learning (ML) models to classify between benign and malignant cases properly, even though they have high accuracy. Accuracy is not a good metric to assess the results of ML models on breast cancer dataset because of biased results. To address this issue, we use Genetic Programming (GP) and propose two fitness functions. First one is F2 score which focuses on learning more about the minority class, which contains more relevant information, the second one is a novel fitness function known as Distance score (D score) which learns about both the classes by giving them equal importance and being unbiased. The GP framework in which we implemented D score is named as D-score GP (DGP) and the framework implemented with F2 score is named as F2GP. The proposed F2GP achieved a maximum accuracy of 99.63%, 99.51% and 100% for 60-40, 70-30 partition schemes and 10 fold cross validation scheme respectively and DGP achieves a maximum accuracy of 99.63%, 98.5% and 100% in 60-40, 70-30 partition schemes and 10 fold cross validation scheme respectively. The proposed models also achieves a recall of 100% for all the test cases. This shows that using a new fitness function for unbalanced data classification improves the performance of a classifier. [ABSTRACT FROM AUTHOR]