Search

Breast cancer is one of the common disease in female gender population all over the world. The classical methods of segmentation and classification for malignant cells are not only repetitive but also very time-consuming. Therefore, a computer-aided diagnosis is needed for automatic segmentation and classification of malignant cells in breast cytology images. In this article, a machine learning-based approach is proposed for malignant cell segmentation and classification in breast cytology images. In the proposed approach, the segmentation of cells is performed by a level set algorithm which is used to extract statistical information related to the malignant and benign cells. Similarly, the gray level co-occurrence matrix is computed to exploit the texture information, and support vector machine-based classification is used for the classification of malignant and benign cells. It has been observed through experiments that the proposed approach achieved high accuracy (96.3%) in the classification of malignant and benign cells. [ABSTRACT FROM AUTHOR]

Cancer is a genetic disease that is categorized among the most lethal and belligerent diseases. An early staging of the disease can reduce the high mortality rate associated with cancer. The advancement in high throughput sequencing technology and the implementation of several Machine Learning algorithms have led to significant progress in Oncogenomics over the past few decades. Oncogenomics uses RNA sequencing and gene expression profiling for the identification of cancer-related genes. The high dimensionality of RNA sequencing data makes it a complex and large-scale optimization problem. CDRGI presents a Discrete Filtering technique based on a Binary Artificial Bee Colony coupling Support Vector Machine and a two-stage cascading classifier to identify relevant genes and detect cancer using RNA seq data. The proposed approach has been tested for seven different cancers, including Breast Cancer, Stomach Cancer (STAD), Colon Cancer (COAD), Liver Cancer, Lung Cancer (LUSC), Kidney Cancer (KIRC), and Skin Cancer. The results revealed that the CDRGI performs better for feature reduction while achieving better classification accuracy for STAD, COAD, LUSC and KIRC cancer types. [ABSTRACT FROM AUTHOR]

Cancer is a severe condition of uncontrolled cell division that results in a tumor formation that spreads to other tissues of the body. Therefore, the development of new medication and treatment methods for this is in demand. Classification of microarray data plays a vital role in handling such situations. The relevant gene selection is an important step for the classification of microarray data. This work presents gene encoder, an unsupervised two-stage feature selection technique for the cancer samples' classification. The first stage aggregates three filter methods, namely principal component analysis, correlation, and spectral-based feature selection techniques. Next, the genetic algorithm is used, which evaluates the chromosome utilizing the autoencoder-based clustering. The resultant feature subset is used for the classification task. Three classifiers, namely support vector machine, k-nearest neighbors, and random forest, are used in this work to avoid the dependency on any one classifier. Six benchmark gene expression datasets are used for the performance evaluation, and a comparison is made with four state-of-the-art related algorithms. Three sets of experiments are carried out to evaluate the proposed method. These experiments are for the evaluation of the selected features based on sample-based clustering, adjusting optimal parameters, and for selecting better performing classifier. The comparison is based on accuracy, recall, false positive rate, precision, F-measure, and entropy. The obtained results suggest better performance of the current proposal. [ABSTRACT FROM AUTHOR]

This paper presents a model for predicting the water temperature of the reservoir incorporating with solar radiation to analyze and evaluate the water temperature of large high-altitude reservoirs in western China. Through mutual information inspection, the model shows that the dependent variable has a good correlation with water temperature, and it is added to the sample feature training model. Then, the measured water temperature data in the reservoir for many years are used to establish the support vector regression (SVR) model, and genetic algorithm (GA) is introduced to optimize the parameters, so as to construct an improved support vector machine (M-GASVR). At the same time, root-mean-square error, mean absolute error, mean absolute percentage error, and Nash–Sutcliffe efficiency coefficient are used as the criteria for evaluating the performance of SVR model, ANN model, GA-SVR model, and M-GASVR model. In addition, the M-GASVR model is used to simulate the water temperature of the reservoir under different working conditions. The results show that ANN model is the worst among the four models, while GA-SVR model is better than SVR model in terms of metric, and M-GASVR model is the best. For non-stationary sequences, the prediction model M-GASVR can well predict the vertical water temperature and water temperature structure in the reservoir area. This study provides useful insights into the prediction of vertical water temperature at different depths of reservoirs. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the diseases which lead to death if not detected at an early stage. Computer-aided detection and diagnosis systems are designed for its early diagnosis which may prevent biopsy and use of dermoscopic tools. Numerous researches have considered this problem and achieved good results. In automatic diagnosis of skin cancer through computer-aided system, feature extraction and reduction plays an important role. The purpose of this research is to develop computer-aided detection and diagnosis systems for classifying a lesion into cancer or non-cancer owing to the usage of precise feature extraction technique. This paper proposed the fusion of bag-of-feature method with speeded up robust features for feature extraction and quadratic support vector machine for classification. The proposed method shows the accuracy of 85.7%, sensitivity of 100%, specificity of 60% and training time of 0.8507 s in classifying the lesion. The result and analysis of experiments are done on the PH2 dataset of skin cancer. Our method improves performance accuracy with an increase of 3% than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Classification of respiratory diseases using X-ray and CT scan images of lungs is currently practised and used by many medical practitioners for clinical diagnosis. Respiratory disease classification, using breathing and wheezing sounds, remains scarce in the research field and is slowly upcoming. In this work, robust respiratory disease classification using breathing sounds (RRDCBS) is implemented by extracting multiple features from sounds, creating multiple modelling techniques, and experimental identification of diseases using appropriate testing procedures for multi-class and binary classification of respiratory diseases. Decision level fusion of features for Vector quantisation (VQ) modelling technique has provided 100% accuracy for classifying five respiratory diseases and healthy subjects. Decision level fusion of indices on the features has provided 100% accuracy for VQ, support vector machine (SVM), and K-nearest neighbour (KNN) modelling techniques to perform binary classification of the respiratory disease against healthy data sound. Deep recurrent and convolutional neural networks are also evaluated for multiple/binary classification of respiratory diseases. [ABSTRACT FROM AUTHOR]

The recognition of stomatological disorders and the classification of dental caries are important areas of biomedicine that can hugely benefit from machine learning tools for the construction of relevant mathematical models. This paper explores the possibility of using reflectivity data to distinguish between healthy tissues and caries by deep learning and multilayer convolutional neural networks. The experimental data set includes more than 700 observations recorded in the stomatology laboratory. For rigor, the results obtained from the deep learning systems are compared with those evaluated for selected sets of features estimated for each observation and classified by a decision tree, support vector machine (SVM), k-nearest neighbor, Bayesian methods, and two-layer neural networks. The classification accuracy obtained for the deep learning systems was 98.1% and 94.4% for data in the signal and spectral domains, respectively, in comparison with an accuracy of 97.2% and 87.2% evaluated by the SVM method. The proposed method conclusively demonstrates how the artificial intelligence and deep learning methodology can contribute to improved diagnosis of dental problem in stomatology. [ABSTRACT FROM AUTHOR]

Suspicious volumetric tumor (SVT) segmentation of a CT-image (CT i ) and analysing changes in the volume of tumor is a significantly challenging task for the identification of lung cancer. In this regard, we design a two-step suspicious volumetric tumor segmentation (SVTS) approach based on an adaptive multiple resolution contour (AMRC) models for effective SVT segmentation. First, the high-intensity-pixels edge centroid of SVT (HECS) method is designed to identify the SVT location in CT i , and these outcomes are subsequently conceding threshold values to fix the level set method (LSM). Second, HECS outcomes are recognised using particle swarm optimisation (PSO) which is harmonised twin support vector machines (TSVM) to achieve segmentation accuracy. An open-source tumor cancer imaging archive (TCIA) dataset, 529 abnormal tissues (ATs) of the lung from the lung image database consortium (LIDC), are conceded to assess the performance of the SVT segmentation approach. The average segmentation accuracy of NLTC, TCIA, and LIDC datasets are 73.19%, 76.21% and 75.89%, respectively, compared with standard benchmark approaches. Subsequently, our framework efficiently classified the normal and abnormal CT i based on the SVT segmentation accuracy rate. [ABSTRACT FROM AUTHOR]

Mango leaf diseases have a negative impact on mango quality and yield. It is difficult to make an accurate diagnosis of mango leaf disease diagnosis with the naked eye. A lot of computer-aided and machine learning techniques have recently been used by researchers for the classification of mango leaf diseases. However, it has been reported that these approaches have some limitations to their performance which can be attributed to problems due to higher feature dimensionality, overfitting, computational complexity, and lack of feature qualities. To overcome these issues, we proposed a novel framework for mango leaves disease classification. The images were taken from Andhra Pradesh, the largest mango cultivating land in India. The proposed framework is categorized into four stages: data preparation stage, feature selection stage, learning and classification stage, and the performance evaluation stage. We selected 380 images from the categories of healthy and diseased (Mango Anthracnose, Bacterial black spot, and Sooty mold). Different data augmentation techniques are applied to prevent overfitting and improve generalization. Next, a convolutional neural network with crossover-based levy flight distribution is applied for better feature selection. Further, the pre-trained MobileNetV2 model is used for the learning stage and leaves diseases classification is done via support vector machine at the final stage of the MobileNetV2 model. The experimental results demonstrate superior classification performances over other state-of-art methods. [ABSTRACT FROM AUTHOR]

Solutions in geotechnics have been optimizing with the aid of machine learning methods. The aim of this paper is to apply different machine learning algorithms in order to achieve rock mass classification. It is demonstrated that RMR classification system can be obtained using only variables which are closely related to rock mass quality, instead of all RMR variables, without missing significant accuracy. The different machine learning algorithms used are the naïve Bayes, random forest, artificial neural networks and support vector machines. The variables to calculate RMR, selected by factor analysis, are: rock strength, rock weathering, spacing, persistence and aperture of discontinuities and presence of water. The machine learning models were trained and tested thirty times, with random subsampling, using two-thirds of the total database for training sample. The models presented average accuracy greater than 0.81, which was calculated from the confusion matrix, using the proportion of true positives and true negatives in the test sample. Significant values of efficiency, precision and reproducibility rates were achieved. The study shows the application of machine learning algorithms allows obtaining the RMR classes, even with a small number of variables. In addition, the results of the evaluation metrics of the developed algorithms show that the methodology can be applied to new database, working as a valuable way to achieve rock mass classification. [ABSTRACT FROM AUTHOR]

In the field of e-commerce applications, nowadays the aspect-based sentiment analysis has become vital and every consumer started focusing on various aspects of the product before making the purchase decision through online portals like Amazon, Walmart, Alibaba, Flipkart, etc. Hence, the enhancement of sentiment classification considering every aspect of product and services is in the limelight. In this proposed research, aspect-based sentiment classification model has been developed employing sentiment whale optimized adaptive neural network (SWOANN) for classifying the sentiment of key aspects of products and services. The proposed work uses the key features such as the positive opinion score, negative opinion score and the term frequency-inverse document frequency (TF-IDF) for representing each aspect of products and services, which further improves the overall effectiveness of the classifier. Moreover, the computational speed and accuracy of sentiment classification of the product and services have been improved by the optimal selection of weights of the neurons of proposed model. The promising results are obtained by analysing the mobile phone review dataset when compared with other existing sentiment classification approaches such as support vector machine (SVM) and artificial neural network (ANN). The proposed model can be compatible with any sentiment classification problem of products and services. [ABSTRACT FROM AUTHOR]

As a kind of time series, the export volume of foreign trade has the characteristics of randomness, complexity, strong nonlinearity and noise, so it is difficult to describe it by using the traditional time series model algorithm. Support vector neural network (SVNN) has many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition problems. This paper uses the method of support vector neural network to predict and analyze China's foreign trade export and uses principal component analysis and regression analysis to analyze the contribution rate of different influencing factors to foreign trade export. The results show that:(1) the contribution rate of domestic economic factors to China's foreign trade export is the largest, reaching 59.65%, which also reflects the necessity and correctness of China's insistence on supply-side reform. (2) The nonlinear prediction results of the support vector neural network have a good fitting with the actual value of China's foreign trade export, and the prediction error of the support vector neural network is controlled within 10%, showing a good prediction effect; (3) neural network method has good modeling and generalization ability for nonstationary small sample import and export time series data and can achieve high prediction accuracy and decision judgment accuracy, especially for the prediction of its development trend, and the model has a high degree of fitting. [ABSTRACT FROM AUTHOR]

Fault location methods help to reduce outage time and improve reliability indices and therefore are important in practice. However, the performance of traditional fault location methods which are mainly developed for transmission grid is challenged by the specification and complexities of the distribution grid. Furthermore, the errors in measurement devices compromise the accuracy of the fault localization. This paper addresses these issues through an integrated methodology. In the proposed methodology, current transformer (CT) and potential transformer (PT) errors are first applied to current and voltage data recorded at the starting point of the feeder. Then, the impedance-based fault location method (IBFLM) is used to locate possible fault locations using the recorded voltage and current. Then, at the section of possible points, some locations are selected, the same fault is simulated, and an online databank is generated. After this, using a combination of the wavelet transform, Fourier transform and minimum redundancy maximum relevance (mRMR) algorithm, some features are selected and they can be separated using support vector machine (SVM) classifier. They are utilized to select one point as the final fault location among possible locations. A real feeder is considered as the sample distribution network to assess the performance of the proposed method. Instrument errors are modeled using the Gaussian stochastic process which is added to recorded signals at the starting point of the feeder. The accuracy of the proposed method is investigated under different fault locations, fault resistances, and fault inception angles. Simulation results confirm that the proposed method is highly accurate. The proposed method is tested in a distribution network in a power system simulator in the power system laboratory of Persian Gulf University. The experimental results confirm that the accuracy and precision of the proposed method are high. The method is also compared with other state-of-the-art methods, and the results show a clear improvement. [ABSTRACT FROM AUTHOR]

Due to the threat and increasing trend to diabetes, different approaches to diagnose it have been proposed, so that classification is one of the main techniques. In this article ultimate aim is designing a novel system to diagnose diabetes. To this end, we use an ensemble classifier to apply support vector machine (SVM), k-nearest neighbor (KNN), and whale optimization algorithm (WOA). WOA is responsible for generating weights for each classifier to improve the accuracy of the diabetes classification. For our empirical study, we gathered a dataset of diabetes from medical centers in Iran. The implementation results showed that the designed ensemble classifier achieved the accuracy rate of 83%, which means it improved the accuracy of the best preceding classifier about 5%. Moreover, the designed ensemble classifier based on WOA improved the accuracy about 1% in comparison with PSO that is preceding the WOA in terms of accuracy level. [ABSTRACT FROM AUTHOR]

Terms of Service (ToS) are fundamental factors in the creation of physical as well as online legally relevant relationships. They not only define mutual rights and obligations but also inform users about contract key issues that, in online settings, span from liability limitations to data management and processing conditions. Despite their crucial role, however, ToS are often neglected by users that frequently accept without even reading what they agree upon, representing a critical issue when there exist potentially unfair clauses. To enhance users' awareness and uphold legal safeguards, we first propose a definition of ToS unfairness based on a novel unfairness measure computed counting the unfair clauses contained in a ToS, and therefore, weighted according to their direct impact on the customers concrete interests. Secondly, we introduce a novel machine learning-based approach to classify ToS clauses, represented by using sentence embedding, in different categories classes and fairness levels. Results of a test involving well-known machine learning models show that Support Vector Machine is able to classify clauses into categories with a F1-score of 86% outperforming state-of-the-art methods, while Random Forest is able to classify clauses into fairness levels with a F1-score of 81%. With the final goal of making terms of service more readable and understandable, we embedded this approach into ToSware, a prototype of a Google Chrome extension. An evaluation study was performed to measure ToSware effectiveness, efficiency, and the overall users' satisfaction when interacting with it. [ABSTRACT FROM AUTHOR]

In smartphone-based crowd/participatory sensing systems, it is necessary to identify the actual sensor data provider. In this context, this paper attempts to recognize the users' identity based on their gait patterns (i.e. unique walking patterns). More specifically, a deep convolution neural network (CNN) model is proposed for the user identification with accelerometer data generated from users smartphone sensors. The proposed model is evaluated based on the real-world benchmark dataset (accelerometer biometric competition data) having a total of 387 users accelerometer sensor readings (60 million data samples). The performance of the proposed CNN-based approach is also compared with five baseline methods namely Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), and K-Nearest Neighbours (KNN). It is observed that the proposed model achieves better results (accuracy = 98.8%, precision = 0.94, recall = 0.97, and F1-score = 0.95) as compared to the baseline methods. [ABSTRACT FROM AUTHOR]

This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stability in forward flight. The novelty of the work lies in the application of advanced data-driven machine learning (ML) techniques, such as convolution neural networks (CNN), multi-layer perceptron (MLP), random forests, support vector machines and adaptive Gaussian process (GP) for capturing the nonlinear responses of these complex spatio-temporal models to develop an efficient physics-informed ML framework for stochastic rotor analysis. Thus, the work is of practical significance as (i) it accounts for manufacturing uncertainties, (ii) accurately quantifies their effects on nonlinear response of rotor blade and (iii) makes the computationally expensive simulations viable by the use of ML. A rigorous performance assessment of the aforementioned approaches is presented by demonstrating validation on the training dataset and prediction on the test dataset. The contribution of the study lies in the following findings: (i) The uncertainty in composite material and geometric properties can lead to significant variations in the rotor aeroelastic responses and thereby highlighting that the consideration of manufacturing variability in analyzing helicopter rotors is crucial for assessing their behaviour in real-life scenarios. (ii) Precisely, the substantial effect of uncertainty has been observed on the six vibratory hub loads and the damping with the highest impact on the yawing hub moment. Therefore, sufficient factor of safety should be considered in the design to alleviate the effects of perturbation in the simulation results. (iii) Although advanced ML techniques are harder to train, the optimal model configuration is capable of approximating the nonlinear response trends accurately. GP and CNN followed by MLP achieved satisfactory performance. Excellent accuracy achieved by the above ML techniques demonstrates their potential for application in the optimization of rotors under uncertainty. [ABSTRACT FROM AUTHOR]

Direct multi-task twin support vector machine (DMTSVM) performs well in handling multiple related tasks. But it is sensitive to noise points due to the use of hinge loss. In this paper, we propose a novel multi-task twin support vector machine with pinball loss (Pin-DMTSVM) to enhance the noise insensitivity of DMTSVM. Besides, in order to improve the computational speed of Pin-DMTSVM, we further construct a safe screening rule (SSR) for accelerating Pin-DMTSVM based on the optimality conditions. SSR could identify and pre assign most of the inactive instances before actually solving the optimization problem. So, the computational time will be reduced a lot by solving a smaller problem. More importantly, it can get an exactly same solution as solving the original larger optimization problem, so the classification accuracy will not be affected in theory. Numerical experiments on six benchmark datasets and seven image datasets have demonstrated the effectiveness and robustness of our proposed method. [ABSTRACT FROM AUTHOR]

In medical science, collecting and classifying data from various diseases is a vital task. The confused and large amounts of data are problems that prevent us from achieving acceptable results. One of the major problems for diabetic patients is a failure to properly diagnose the disease. As a result of this mistake in diagnosis or failure in early diagnosis, the patient may suffer from complications such as blindness, kidney failure, and cutting off the toes. Nowadays, doctors diagnose the disease by relying on their experience and knowledge and performing complex and time-consuming tests. One of the problems with current diabetic, diagnostic methods is the lack of appropriate features to diagnose the disease and consequently the weakness in its diagnosis, especially in its early stages. Since diabetes diagnosis relies on large amounts of data with many parameters, it is necessary to use machine learning methods such as support vector machine (SVM) to predict the complications of diabetes. One of the disadvantages of SVM is its parameter adjustment, which can be accomplished using metaheuristic algorithms such as particle swarm optimization algorithm (PSO), genetic algorithm, or grey wolf optimizer (GWO). In this paper, after preprocessing and preparing the dataset for data mining, we use SVM to predict complications of diabetes based on selected parameters of a patient acquired by laboratory test using improved GWO. We improve the selection process of GWO by employing dynamic adaptive middle filter, a nonlinear filter that assigns appropriate weight to each value based on the data value. Comparison of the final results of the proposed algorithm with classification methods such as a multilayer perceptron neural network, decision tree, simple Bayes, and temporal fuzzy min–max neural network (TFMM-PSO) shows the superiority of the proposed method over the comparable ones. [ABSTRACT FROM AUTHOR]

In this work, an effective classification of hyperspectral images is modelled and simulated with the proximal support vector machine (PSVM) by integrating them with the deep learning approach. The modelled new deep proximal support vector machines are designed in a manner to handle the existing complexity, discrepancies and irregularities in the traditional hyperspectral image classifiers. This paper investigates the applicability of the new deep linear and nonlinear proximal support vector machines as applied for hyperspectral image classification. In respect of the new deep PSVM classifier, it is modelled for deep linear PSVM and deep nonlinear PSVM to perform classification of spectral images so as to bring out the best classifier model. To test and validate the proposed deep PSVM classifiers University of Pavia datasets, Indian Pine datasets and Kennedy Space Centre datasets are employed as test beds and results are attained. The developed new deep PSVM classifiers are developed with varied kernel functions to do the classification process. The deep learning technique enhances the linear and nonlinear PSVM classifier models to perform more effectively during the learning process and carry out the classification using auto-encoders and decoders. Results attained during the process infer that the developed new deep PSVM (linear and nonlinear) has come out with better classification accuracy in comparison with that of the other techniques from literature for the same datasets. Statistical analysis validates the randomness that occurs in the proposed deep learning techniques as applied for spectral image classification. [ABSTRACT FROM AUTHOR]

This work presents an efficient hybridized approach for the classification of electrocardiogram (ECG) samples into crucial arrhythmia classes to detect heartbeat abnormalities. The physiological detection using electrocardiogram (ECG) signals has been the most popular means and widely accepted automated detection system to monitor heart health. Additionally, arrhythmia beat classification plays a prominent role in electrocardiogram (ECG) analysis dedicated elucidate cardiac health status while analyzing heart rhythm. The authors aim to classify ECG samples into major arrhythmia classes precisely by removing the inherent noise of ECG signals in preprocessing phase using discrete wavelet transformation (DWT). The QRS complex plays a crucial role in ECG signal identification. Therefore, the position and amplitude of R-peaks are determined to detect the QRS complex. The feature vectors of the QRS complex are further optimized with cuckoo search (CS) optimization algorithm in addition to denoising signals using DWT to select the most relevant set of features. The Support vector machine (SVM)-trained support vector contains the best training information used to train feed-forward back-propagation neural network (FFBPNN) to propose the variant DWT + CS + SVM-FFBPNN to classify signals among five classes. MIT-BIH arrhythmia database is utilized for different types of heartbeats. The classification analysis based on a variant with optimized feature vector using cuckoo search algorithm and SVM-FFBPNN determines heart rate with an accuracy of 98.319%. In contrast, the variant FFBPNN without optimization obtains 97.95% accuracy. The improved performance of the novel combination of classifiers resulted in overall classification accuracy of 98.53% with precision and recall of 98.247% and 95.68%, respectively. The simulation analysis comprising 3600 samples and 1160 heartbeats also outperformed the existing arrhythmia classifications performed based on neural networks. This illustrates the success of the proposed ECG classification model in accurately categorizing ECG signals for arrhythmia classification. [ABSTRACT FROM AUTHOR]

The application of artificial neural networks in mapping the mechanical characteristics of the cement-based materials is underlined in previous investigations. However, this machine learning technique includes several major deficiencies highlighted in the literature, such as the overfitting problem and the inability to explain the decisions. Hence, the present study investigates the applicability of other common machine learning techniques, i.e., support vector machine, random forest (RF), decision tree, AdaBoost and k-nearest neighbors in mapping the behavior of the compressive strength (CS) of cement-based mortars. To this end, a big experimental database has been compiled based on experimental data available in the literature considering, namely the cement grade, which is an important parameter for the modeling of mortar's CS. Other important parameters are namely the age, the water-to-binder ratio, the particle size distribution of the sand and the amount of plasticizer. Many models based on the influential factors affecting machine learning techniques have been developed, and their prediction capacities have been assessed using performance indexes. The present research highlights the potential of AdaBoost and RF models as useful tools which can assist in mortar design and/or optimization. In addition, mapping the development of mortar characteristics can assist in revealing the influence of the different mortar mix parameters on the compressive strength. [ABSTRACT FROM AUTHOR]

A malicious data miner can infer users' private information in online social networks (OSNs) by data mining the users' disclosed information. By exploring the public information about a target user (i.e. an individual or a group of OSN users whose privacy is under attack), attackers can prepare a training data set holding similar information about other users who openly disclosed their data. Using a machine learning classifier, the attacker can input released information about users under attack as non-class attributes and extract the private information as a class attribute. Some techniques offer some privacy protection against specific classifiers;, however, the provided privacy can be under threat if an attacker uses a different classifier (rather than the one used by the privacy protection techniques) to infer sensitive information. In reality, it is difficult to predict the classifiers involved in a privacy attack. In this study, we propose a privacy-preserving technique which first prepares a training data set in a similar way that an attacker can prepare and then takes an approach independent of the classifiers to extract patterns (or logic rules) from the training data set. Based on the extracted rule set, it then suggests the target users to hide some non-class attribute values and/or modify some friendship links for protecting their privacy. We apply our proposed technique on two OSN data sets containing users' attribute values and their friendship links. For evaluating the performance of the proposed technique, we use conventional classifiers such as Na i ¨ ve Bayes, Support Vector Machine and Random Forest on the privacy-protected data sets. The experimental results show that our proposed technique outperforms the existing privacy-preserving algorithms in terms of securing privacy while maintaining the data utility. [ABSTRACT FROM AUTHOR]

A Gaussian based Particle Swarm Optimization Gravitational Search Algorithm (GPSOGSA) is being proposed for extensive feature selection that serves highly in making effective predictions. GPSOGSA helps to overcome the problem of being stuck into the local optima and influences the local searching ability, thus it aims to bridge the gap of exploration and exploitation. The algorithm also limits the usage of too many parameters like acceleration factors, maximum velocity, inertia weight that plays a vital role in PSO, GSA and PSOGSA. The efficacy of the algorithm has been tested upon unimodal and multimodal benchmark functions. We have also evaluated the performance of the algorithm by applying it on various benchmark datasets. The algorithm uses a wrapper-based approach that includes Support Vector Machine as a learner algorithm, and improves both the execution time and the performance accuracy. The findings show that the proposed algorithm could escape from local optimum and converges faster than the PSO, GSA and PSOGSA algorithms. [ABSTRACT FROM AUTHOR]

The quest to improve performance accuracy and prediction speed in machine learning algorithms cannot be overemphasized, as the need for machines to outperform humans continue to grow. Accordingly, several studies have proposed methods to improve prediction performance and speed particularly for spatio-temporal analysis. This study proposes a novel classifier that leverages ensemble techniques to improve prediction performance and speed. The proposed classifier, Ada-AdaSVM uses an AdaBoost feature selection algorithm to select small features of input datasets for a joint support vector machine (SVM)–AdaBoost classifier. The proposition is evaluated against a selection of existing classifiers (SVM, AdaSVM and AdaBoost) using the Jaffe, Yale, Taiwanese facial expression database (TFEID) and CK + 48 datasets with Haar features as the preferred method for feature extraction. The findings indicated that Ada-AdaSVM outperforms SVM, AdaSVM and AdaBoost classifiers in terms of speed and accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, graph-structured data are increasingly used to model complex systems. Meanwhile, detecting anomalies from graph has become a vital research problem of pressing societal concerns. Anomaly detection is an unsupervised learning task of identifying rare data that differ from the majority. As one of the dominant anomaly detection algorithms, one-class support vector machine has been widely used to detect outliers. However, those traditional anomaly detection methods lost their effectiveness in graph data. Since traditional anomaly detection methods are stable, robust and easy to use, it is vitally important to generalize them to graph data. In this work, we propose one-class graph neural network (OCGNN), a one-class classification framework for graph anomaly detection. OCGNN is designed to combine the powerful representation ability of graph neural networks along with the classical one-class objective. Compared with other baselines, OCGNN achieves significant improvements in extensive experiments. [ABSTRACT FROM AUTHOR]

With the exponential growth of the amount of data being generated, stored and processed on a daily basis in the machine learning, data analytics and decision-making systems, the data preprocessing established itself as the key factor for building reliable high-performance machine learning models. One of the roles in preprocessing is variable reduction using feature selection methods; however, the processing time needed for these methods is a major drawback. This study aims at mitigating this problem by migrating the algorithm to a MapReduce implementation suitable for parallelization on a high number of commodity hardware units. The genetic algorithm-based methods were put in the focus of this study. Hadoop, an open-source MapReduce library, was used as a framework for implementing parallel genetic algorithms within our research. The representative machine learning methods, SVM (support vector machine), ANN (artificial neural network), RT (random tree), logistic regression and Naive Bayes, were embedded into implementation for feature selection. The feature selection methods were applied to four NSL-KDD data sets, and the number of features is reduced from cca 40 to cca 10 data sets with the accuracy of 90.45%. These results have both significant practical and theoretical impact. On the one hand, the genetic algorithm has been parallelized in the MapReduce manner, which has been considered unachievable in a strict sense. Furthermore, the genetic algorithm allows randomness-enhanced feature selection and its parallelization reduces overall data preprocessing and allows larger population count which in turn leads to better feature selection. On the practical side, it has been shown that this implementation outperforms the existing feature selection methods. [ABSTRACT FROM AUTHOR]

RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is time-consuming and expensive, so the development of an effective computational approach can provide a strategy to solve this issue. In recent years, most of the computational approaches are constructed on protein sequence information, but the protein structure has not been considered. In this paper, we use a novel computational model of RNA-binding residues prediction, using protein sequence and structure information. Our hybrid features are encoded by local sequence and structure feature extraction models. Our predictor is built by employing the Granular Multiple Kernel Support Vector Machine with Repetitive Under-sampling (GMKSVM-RU). In order to evaluate our method, we use fivefold cross-validation on the RBP129, our method achieves better experimental performance with MCC of 0.3367 and accuracy of 88.84%. In order to further evaluate our model, an independent data set (RBP60) is employed, and our method achieves MCC of 0.3921 and accuracy of 87.52%. Above results demonstrate that integrating sequence and structure information is beneficial to improve the prediction ability of RNA-binding residues. [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) is becoming increasingly popular in the short-term flow. In order to develop high-quality prediction models, it is worth investigating the LSTM potential deeply for traffic flow prediction. This study has two objectives: first, to observe the effect of using different sized training sets in LSTM training for various and numerous databases; second, to develop a clustering model that contributes to adjusting the training set size. For this purpose, 83 datasets were divided into certain sizes and LSTM model performances were examined depending on these training set sizes. As a result, enlargement of the training set size reduced LSTM errors monotonic for certain datasets. This phenomenon was modeled with the state-of-the-art clustering algorithms, such as K-nearest neighbor, support vector machine (SVM), logistic regression and pattern recognition networks (PRNet). In these models, statistical properties of datasets were utilized as input. The best results were obtained by PRNet, and SVM model performance was closest to PRNet. This study indicates that enlarging the training set size in traffic flow prediction increases the LSTM performance monotonically for specific datasets. In addition, a high-precision clustering model is presented to assist researchers in short-term traffic forecasting to adjust the size of the training set. [ABSTRACT FROM AUTHOR]

Software testing process is a crucial part in software development. Generally the errors made by developers get fixed at a later stage of the software development process. This increases the impact of the defect. To prevent this, defects need to be predicted during the initial days of the software development, which in turn helps in efficient utilization of the testing resources. Defect prediction process involves classification of software modules into defect prone and non-defect prone. This paper aims to reduce the impact of two major issues faced during defect prediction, i.e., data imbalance and high dimensionality of the defect datasets. In this research work, various software metrics are evaluated using feature selection techniques such as Recursive Feature Elimination (RFE), Correlation-based feature selection, Lasso, Ridge, ElasticNet and Boruta. Logistic Regression, Decision Trees, K-nearest neighbor, Support Vector Machines and Ensemble Learning are some of the algorithms in machine learning that have been used in combination with the feature extraction and feature selection techniques for classifying the modules in software as defect prone and non-defect prone. The proposed model uses combination of Partial Least Square (PLS) Regression and RFE for dimension reduction which is further combined with Synthetic Minority Oversampling Technique due to the imbalanced nature of the used datasets. It has been observed that XGBoost and Stacking Ensemble technique gave best results for all the datasets with defect prediction accuracy more than 0.9 as compared to algorithms used in the research work. [ABSTRACT FROM AUTHOR]

To enhance the reliability of analog circuits in complex electrical systems, a novel fault diagnosis method is presented in this paper. A denoising autoencoder and a sparse autoencoder are combined, producing a feature extraction model named the denoising sparse deep autoencoder (DSDAE) that can obtain effective information from signals contaminated by noise. Compared with traditional feature extraction methods, the DSDAE model can be used to implement adaptive feature learning. Then, linear discriminant analysis is adopted to perform linear dimensionality reduction, thereby obtaining the maximum clustering features of the signals. Finally, a fault diagnosis model based on a support vector machine (SVM) with high versatility and accuracy is developed to identify the fault classes of analog circuits. In addition, the salp swarm algorithm, which is capable of convergence and strong global optimization, is employed to intelligently optimize the SVM classifier. The method is comprehensively evaluated with three typical analog circuits from the ISCAS'97 circuit set. The experimental results illustrate that the proposed fault diagnosis method can achieve excellent fault identification accuracy and generalization performance even under noise interference conditions. [ABSTRACT FROM AUTHOR]

The semi-supervised support vector machine (S3VM) for classification is introduced for dealing with quantities of unlabeled data in the real world. Labeled data are utilized to train the algorithm and then were adapted to classify the unlabeled data. However, this algorithm has several drawbacks, such as the non-smooth term of semi-supervised objective function negatively affects the classification precision. Moreover, it is required to endure heavy burden in solving two quadratic programming problems with inversion matrix operation. To cope with this problem, this article puts forward a novel class of Bézier smooth semi-supervised support vector machines (BS4VMs), based on the approximation property of Bézier function to the non-smooth term. Because of this approximation, a fast quasi-Newton method for solving BS4VMs can be used to decrease the calculating time scale. This new kind of algorithm enhances the generalization and robustness of S3VM for nonlinear case as well. Further, to show how the BS4VMs can be practically implemented, experiments on synthetic, UCI dataset, USPS dataset, and large-scale NDC database are offered. The theoretical analysis and experiments comparisons clearly confirm the superiority of BS4VMs in both classification accuracy and calculating time. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD), which occurs as a result of the loss of cognitive functions in the brain, causes near-forgetfulness in the case and dementia in subsequent processes. Dataset consists of MR images containing four phases of AD. The dataset was re-enhanced separately with DeepDream, fuzzy color image enhancement, hypercolumn techniques. Visual Geometry Group-16 (VGG-16) deep learning model is used in the enhancing process and deep features are combined. Linear Regression is used for the selection of efficient features. The Support Vector Machine is preferred as a classifier. With the proposed approach, the classification achievement was obtained as 100% in Mild Dementia, 99.94% in Moderate Dementia, 100% in non-Dementia, 99.94% in Very Mild Dementia. The overall accuracy was 99.94%. The proposed approach increased the prediction success in detecting Alzheimer's stages by re-enhancing MR images. Thus, an efficient early diagnosis model was realized at an affordable cost for individuals likely to progress with dementia. [ABSTRACT FROM AUTHOR]

One of the most captivating problems being faced nowadays in Physics are ultra-high energy cosmic rays. They are high-energy radiations coming mainly from outside the Solar System, and when they enter Earth's atmosphere, they produce a cascade of particles. This cascade of particles, named as extensive air shower, can be recorded by means of photomultiplier tubes in surface detectors, obtaining different recordings of the energy signal (since the air shower can hit one or more detectors). Based on these signals, different features can be obtained that might give an insight into which particle has caused the extensive air shower, which is of utmost importance for physicists. Therefore, this work presents a supervised learning algorithm to determine that the particle is a photon or a hadron. Convolutional neural networks and feed forward neural networks are compared in order to analyze the importance of spatial information for the classification. Then, a comparison between using the information of each surface detector separately and integrating the information from them for the classification is studied, showing that the integration improves the results compared to using each surface detector's trace independently. Furthermore, a comparison between manually extracted features from the signal and the automatically extracted features by the convolutional neural network is done, showing the classification potential of the latter. Finally, the addition of particle shower features which are external to the surface detector measurements is assessed, showing that the combination of automatically extracted features and external variables is able to predict the particle that has produced the air shower with an accuracy of 98.87%. [ABSTRACT FROM AUTHOR]

In this work, empirical mode decomposition (EMD)-based optimized added kernel least square support vector machine (OAKLSSVM) hybridized model is proposed for automatic identification of epileptic electroencephalogram (EEG) signals where the kernel parameters are being optimized using water cycle algorithm (WCA). The proposed model with EMD decomposition and WCA optimization together is known as EMD-OAKLSSVM-WCA. Here, two kernel functions i.e., radial basis function and wavelet kernel functions are deployed together to form the added kernel framework. From EMD, intrinsic mode functions (IMFs) are obtained where Hilbert transform (HT) is used to obtain analytic form of IMFs. For classifying seizure and non-seizure EEG signals, the frequency modulation bandwidth and amplitude modulation bandwidth parameters are obtained from the analytical IMFs and are used as features for the OAKLSSVM model. The experimental results validate the efficiency of the proposed model which provides better classification accuracy (99.33%) as compared to different promising classifiers and some state-of-the-art models. [ABSTRACT FROM AUTHOR]

Features subset selection was commonly used in data mining and artificial intelligence techniques to produce a model with a minimal set of features that enhances the performance of the classifier. The essential motive for selecting features is to avoid the problem of a number of dimensions trap. This paper introduces a new technique of selection of features dependent on the modified of binary teaching–learning-based optimization and the suggested method called MBTLBO. This algorithm (teaching learning-based optimization TLBO) is one of the present metaheuristic that is been widely utilized to a several of intractable optimization issues in recent times. Such algorithm has been combined with supervised data mining technique (support vector machine) for the implementation of feature subset selection problem in binary identification. The collection of specific risk features with the rheumatic disease was implemented. The findings revealed that the new approach (MBTLBO) increases the accuracy of classification. [ABSTRACT FROM AUTHOR]

A software defect report is a bug in the software system that developers and users submit to the software defect library during software development and maintenance. Managing a software defect report that is overwhelming is a challenging task. The traditional method is manual identification, which is time-consuming and laborious and delays the repair of important software defects. Based on the above background, the purpose of this paper is to study the software defect prediction (SDP) model based on LASSO–SVM. In this paper, the problem of poor prediction accuracy of most SDP models is proposed. A SDP model combining minimum absolute value compression and selection method and support vector machine algorithm is proposed. Firstly, the feature selection ability of the minimum absolute value compression and selection method is used to reduce the dimension of the original data set, and the data set not related to SDP is removed. Then, the optimal value of SVM is obtained by using the parameter optimization ability of cross-validation algorithm. Finally, the SDP is completed by the nonlinear computing ability of SVM. The accuracy of simulation results is 93.25% and 66.67%, recall rate is 78.04%, and f-metric is 72.72%. The results show that the proposed defect prediction model has higher prediction accuracy than the traditional defect prediction model, and the prediction speed is faster. [ABSTRACT FROM AUTHOR]

Automatic processing and analysis of medical images may provide to doctor valuable assistance for diagnostic and therapeutic practice. In this work, the problem of breast cancer edge detection is addressed. We are faced with a challenging task considering the breast tissue specificities and the inevitable mammogram noise. To meet this challenge, we propose novel approaches involving quantum genetic algorithm and support vector machines. The first method uses the quantum genetic algorithm to solve a multilevel thresholding problem based on Tsallis entropy. In the second method, the support vector machines are trained, in different ways, on a simulated image in order to be able to detect breast cancer edge. The proposed approaches are compared to some standard methods of edge detection on a sample of mammographic images taken from a well-known benchmark databases. The evaluation results obtained by PSNR, SSIM and FSIM metrics demonstrated the effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Unconfined compressive strength (UCS) is a major mechanical parameter of the rock which has an essential role in developing geomechanical models. It can be estimated directly by lab testing of retrieved core samples or from well log data. These methods are very expensive and require huge efforts and time. Therefore, there is a need to develop a new technique for predicting UCS values in real-time. In this study, three artificial intelligence (AI) models were developed using artificial intelligence tools; artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS), and support vector machine (SVM) to predict UCS of the downhole formations while drilling based on real-time recording of the drilling mechanical parameters. These parameters include rate of penetration (ROP), mud pumping rate (GPM), stand-pipe pressure (SPP), rotary speed in revolution per minute (RPM), torque (T), and weight on bit (WOB). A dataset of 1771 points from a Middle Eastern field was used to build the developed models: for training and testing processes. A new UCS correlation was developed based on the optimized AI model. Another set of data (2175 data points unseen by the model) was used to validate the model and the developed UCS correlation. The developed ANN-model outperformed the ANFIS- and SVM-models with a correlation coefficient (R-value) of 0.99 and an average absolute percentage error (AAPE) of 3.48% between the predicted and actual UCS values. The new UCS correlation outperformed the available correlations for UCS prediction and it was able to predict the UCS with AAPE of 4.2% compared to the actual UCS values. [ABSTRACT FROM AUTHOR]

The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (1) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (2) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system. The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without specification of any signal features. The accuracy of discrimination between different motion patterns for the uphill and downhill cycling and recognition of 4 classes associated with different route slopes was 96.6% with the loss criterion of 0.275 for sigmoidal activation functions. These results were compared with those evaluated for selected sets of features estimated for each observation and classified by the support vector machine, Bayesian methods, and the two-layer neural network. The best cross-validation error of 0.361 was achieved for the two-layer neural network model with the sigmoidal and softmax transfer functions. Our methodology suggests that deep learning neural networks are efficient in the assessment of motion activities for automated data processing and have a wide range of applications, including rehabilitation, early diagnosis of neurological problems, and possible use in engineering as well. [ABSTRACT FROM AUTHOR]

Due to continued growth in both cyberattacks and network data size, organizations need to develop advanced ways to keep their networks and data secure the dynamic nature of evolving malicious attacks. Nowadays, large number of security mechanisms are installed in the network but it opens the possibility for adversaries to conduct malicious activity in the computer network. To detect potential attacks, intrusion detection systems are important security tools that can help to increase the security posture of computer network. In order to identify new malicious or anomalous attacks, this study developed an opposition self-adaptive grasshopper optimization algorithm based on mutation and perceptive concept. Moreover, reinforcement learning is utilized in support vector machine, named gain actor critic with support vector machine to increase the detection capabilities by identifying new cyberattacks. Extensive experiments are conducted on standard intrusion detection datasets such as NSL-KDD, AWID and CIC-IDS 2017 to measure the performance of the proposed method. It can more reliably detect and classify modern attacks with high accuracy and low false-positive rate. The comparative simulation results demonstrates that the proposed algorithm is more capable than basic grasshopper optimization algorithm and other used evolutionary techniques in terms of detection rate, false-positive rate and accuracy for solving IDS problems. The proposed model has provided high detection rate of 99.71%, accuracy of 99.23% and low false-positive rate of 0.009 in NSL-KDD with six optimal features; in AWID data, high detection rate of 99.11%, accuracy of 99.15% and low false-positive rate of 0.091 with eight optimal features, and high detection rate of 99.61%, accuracy of 99.35% and low false-positive rate of 0.052 in CIC-IDS 2017 data with eight optimal features. [ABSTRACT FROM AUTHOR]

The performance of support vector machines in nonlinearly separable classification problems strongly relies on the kernel function. Toward an automatic machine learning approach for this technique, many research outputs have been produced dealing with the challenge of automatic learning of good-performing kernels for support vector machines. However, these works have been carried out without a thorough analysis of the set of components that influence the behavior of support vector machines and their interaction with the kernel. These components are related in an intricate way and it is difficult to provide a comprehensible analysis of their joint effect. In this paper, we try to fill this gap introducing the necessary steps in order to understand these interactions and provide clues for the research community to know where to place the emphasis. First of all, we identify all the factors that affect the final performance of support vector machines in relation to the elicitation of kernels. Next, we analyze the factors independently or in pairs and study the influence each component has on the final classification performance, providing recommendations and insights into the kernel setting for support vector machines. [ABSTRACT FROM AUTHOR]

Most existing extraction techniques in audio watermarking use conventional techniques in which some sets of special rules based on reverse embedding rules are used for watermark extraction and have many weaknesses, like very low robustness to destructive attacks. To overcome this problem, the use of machine learning-based methods has increased in recent years in this field. The disadvantage of these methods is the high reliance on a unique classifier and lack of proper efficiency when achieving high capacity, which is a major challenge in audio watermarking. The main purpose of this paper is to present a method that covers the weak points of conventional methods and simple intelligent methods and improves system performance using a synergistic combination of discrete wavelet transform (DWT) and ensemble-intelligent extraction approach by proposed combination of trained machine learning classifiers. For the embedding operation in the proposed method, the DWT and the difference in energy levels obtained through DWT coefficients are used. In the extraction section, three methods are used in parallel: (a) the trained support vector machine (SVM) classifier with RBF kernel, (b) trained SVM classifier with quadratic kernel and (c) the trained K-nearest neighbor classifier; finally, the majority function is used to vote and make a final decision to create an intelligent-based watermark detector. A training set is required to train the classifiers, whose bit sequence is generated by a proposed 5-bit linear-feedback shift register. The results of various experiments indicate that this ensemble method has achieved the appropriate imperceptibility and high capacity, along with higher robustness compared to conventional techniques and individual learning classifiers. [ABSTRACT FROM AUTHOR]

This research aims to identify rice diseases, namely Leaf blast, Brown spot, Healthy and Hispa. The purpose of this research is to utilize deep convolutional neural network (DCNN) with support vector machine (SVM), DCNN with artificial neural network (ANN) and DCNN with long short-term memory (LSTM). To enhance the performance of LSTM further, the research includes particle swarm optimization, artificial fish swarm optimization (AFSO) and efficient artificial fish swarm optimization (EAFSO) to identify optimal weights. This research also compares the proposed technique results with a conventional feature extraction approaches like texture, discrete wavelet transforms and color histogram with SVM, ANN and LSTM. The results exhibit the superiority of proposed DCNN-LSTM (EAFSO) technique over other techniques. The proposed technique EAFSO associates DCNN-LSTM identifies the rice diseases with 97.5% accuracy, which is better than DCNN-SVM and DCNN-ANN. [ABSTRACT FROM AUTHOR]

Phishing websites are on the rise and are hosted on compromised domains such that legitimate behavior is embedded into the designed phishing site to overcome the detection. The traditional heuristic techniques using HTTPS, search engine, Page Ranking and WHOIS information may fail in detecting phishing sites hosted on the compromised domain. Moreover, list-based techniques fail to detect phishing sites when the target website is not in the whitelisted data. In this paper, we propose a novel heuristic technique using TWSVM to detect malicious registered phishing sites and also sites which are hosted on compromised servers, to overcome the aforementioned limitations. Our technique detects the phishing websites hosted on compromised domains by comparing the log-in page and home page of the visiting website. The hyperlink and URL-based features are used to detect phishing sites which are maliciously registered. We have used different versions of support vector machines (SVMs) for the classification of phishing websites. We found that twin support vector machine classifier (TWSVM) outperformed the other versions with a significant accuracy of 98.05% and recall of 98.33%. [ABSTRACT FROM AUTHOR]

A multi-robot-based fault detection system for railway tracks is proposed to eliminate manual human visual inspection. A hardware prototype is designed to implement a master–slave robot mechanism capable of detecting rail surface defects, which include cracks, squats, corrugations, and rust. The system incorporates ultrasonic sensor inputs coupled with image processing using OpenCV and deep learning algorithms to classify the surface faults detected. The proposed Convolutional Neural Network (CNN) model fared better compared to the Artificial Neural Network (ANN), random forest, and Support Vector Machine (SVM) algorithms based on accuracy, R-squared value, F1 score, and Mean-Squared Error (MSE). To eliminate manual inspection, the location and status of the fault can be conveyed to a central location enabling immediate attention by utilizing GSM, GPS, and cloud storage-based technologies. The system is extended to a multi-robot framework designed to optimize energy utilization, increase the lifetime of individual robots, and improve the overall network throughput. Thus, the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is simulated using 100 robot nodes, and the corresponding performance metrics are obtained. [ABSTRACT FROM AUTHOR]

In an object detection system, the main objective during training is to maintain the detection and false positive rates under acceptable levels when the model is run over the test set. However, this typically translates into an unacceptable rate of false alarms when the system is deployed in a real surveillance scenario. To deal with this situation, which often leads to system shutdown, we propose to add a filter step to discard part of the new false positive detections that are typical of the new scenario. This step consists of a deep autoencoder trained with the false alarm detections generated after running the detector over a period of time in the new scenario. Therefore, this step will be in charge of determining whether the detection is a typical false alarm of that scenario or whether it is something anomalous for the autoencoder and, therefore, a true detection. In order to decide whether a detection must be filtered, three different approaches have been tested. The first one uses the autoencoder reconstruction error measured with the mean squared error to make the decision. The other two use the k-NN (k-nearest neighbors) and one-class SVMs (support vector machines) classifiers trained with the autoencoder vector representation. In addition, a synthetic scenario has been generated with Unreal Engine 4 to test the proposed methods in addition to a dataset with real images. The results obtained show a reduction in the number of false positives between 22.5% and 87.2% and an increase in the system's precision of 1.2% - 47 % when the autoencoder is applied. [ABSTRACT FROM AUTHOR]

In order to provide benchmark performance for Urdu text document classification, the contribution of this paper is manifold. First, it provides a publicly available benchmark dataset manually tagged against 6 classes. Second, it investigates the performance impact of traditional machine learning-based Urdu text document classification methodologies by embedding 10 filter-based feature selection algorithms which have been widely used for other languages. Third, for the very first time, it assesses the performance of various deep learning-based methodologies for Urdu text document classification. In this regard, for experimentation, we adapt 10 deep learning classification methodologies which have produced best performance figures for English text classification. Fourth, it also investigates the performance impact of transfer learning by utilizing Bidirectional Encoder Representations from Transformers approach for Urdu language. Fifth, it evaluates the integrity of a hybrid approach which combines traditional machine learning-based feature engineering and deep learning-based automated feature engineering. Experimental results show that feature selection approach named as normalized difference measure along with support vector machine outshines state-of-the-art performance on two closed source benchmark datasets CLE Urdu Digest 1000k, and CLE Urdu Digest 1Million with a significant margin of 32% and 13%, respectively. Across all three datasets, normalized difference measure outperforms other filter-based feature selection algorithms as it significantly uplifts the performance of all adopted machine learning, deep learning, and hybrid approaches. The source code and presented dataset are available at Github repository https://github.com/minixain/Urdu-Text-Classification. [ABSTRACT FROM AUTHOR]

This work proposes a novel method for the detection of Left Ventricular Hypertrophy (LVH) from a multi-lead ECG signal. Left Ventricle walls become thick due to prolonged hypertension which may fail to pump heart effectively. The imaging techniques can be used as an alternative diagnose LVH; however, they are more expensive and time-consuming than proposed LVH. To overcome this issue, an algorithm to the diagnosis of LVH using ECG signal based on machine learning techniques were designed. In LVH detection, the pathological attributes such as R wave, S wave, inversion of QRS complex, changes in ST segment noticed in the ECG signal. This clinical information extracted as a feature by applying continuous wavelet transform. The signals were reconstructed with the frequency between 10 and 50 Hz from the wavelet. This followed by the detection of R wave and S wave peaks to obtain the relevant LVH diagnostic features. The Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Ensemble of Bagged Tree, AdaBoost classifiers were employed and the results are compared with four neural network classifiers including Multilayer Perceptron (MLP), Scaled Conjugate Gradient Backpropagation Neural Network (SCG NN), Levenberg–Marquardt Neural Network (LMNN) and Resilient Backpropagation Neural network (RPROP). The data source includes Left Ventricular Hypertrophy and healthy ECG signal from PTB diagnostic ECG database and St Petersburg INCART 12-Lead Arrhythmia Database. The results revealed that the proposed work can diagnose LVH successfully using neural network classifiers. The accuracy in detecting LVH is 86.6%, 84.4%, 93.3%,75.6%, 95.6%, 97.8%, 97.8%, 88.9% using SVM, KNN, Ensemble of Bagged Tree, AdaBoost, MLP, SCG NN, LMNN and RPROP classifiers, respectively. [ABSTRACT FROM AUTHOR]

Data-driven mathematical models are powerful prediction tools, which are utilized to approximate solution responses obtained using numerical saltwater intrusion simulation models. Employing data-driven prediction models as a replacement of the complex groundwater flow and transport models enables prediction of future scenarios. Most important, it also helps save computational time, effort and requirements when developing optimal coastal aquifer management methodologies using complex and large-scale coupled simulation–optimization models. In this study, a new data-driven mathematical model, namely group method of data handling (GMDH)-based prediction models, is developed and utilized to predict salinity concentration in a coastal aquifer by mimicking the responses of a variable-density flow and solute transport numerical simulation model. For comparison and evaluation purpose, the prediction performances of GMDH models were compared with well-established support vector machine regression and genetic programming based models. In addition, one important characteristic of the GMDH models is explored and evaluated, i.e. the ability to identify a set of most influential input predictor variables (pumping rates) that had the most significant impact on the outcomes (salinity concentration at monitoring locations). To confirm variable importance, 3 tests are conducted in which new GMDH models are constructed using subsets of the original datasets. In TEST 1, new GMDH models are constructed using a set of most influential variables (consisting of pumping rates at selected locations) only. In TEST 2, a subset of 20 variables (10 most and least influential variables) is used to develop new GMDH models. In TEST 3, a subset of the least influential variables is used to develop GMDH models. The performance evaluation results demonstrate that GMDH models developed using the entire dataset had reasonable prediction accuracy and efficiency. The comparison performance evaluation results for the three test scenarios highlighted the importance of the appropriate selection of relevant input pumping rates when developing accurate prediction models. The results suggested that incorporating the least influential variables deteriorate the accuracy of the prediction models; thus, considering the most influential pumping rates it is possible to develop more accurate and efficient salinity prediction models. Overall, the evaluation results from this study establish that the GMDH models and the inherent input variable ranking capability can be utilized as accurate and efficient coastal saltwater intrusion prediction models. Hence, GMDH models are viable saltwater intrusion modelling tools, which can be employed in future regional-scale saltwater intrusion prediction and management investigations. [ABSTRACT FROM AUTHOR]