Search

The core premise of cancelable biometrics lies in the creation of a distinct biometric template for every individual, which can be either canceled or regenerated as needed. This process requires the use of a uniquely-defined key during the generation of such template. The generated templates are tailored to be key-specific. This ensures that each distinct key will generate a unique template, while preserving the integrity and security of the original biometric data, ensuring that it remains uncompromised. In this paper, a cancelable biometric system based on electrocardiography (ECG) and photoplethysmography (PPG) signals is introduced. A signal fusion process is implemented for the two traits to generate a single template per user. In order to enhance the security of generated templates, a well-designed permutation stage is implemented according to a user-specific key. The permutation key is obtained through a well-designed look-up table created by the authors. The user verification is conducted on the cancelable template, without the need for any inversion processes. The user verification scheme depends on a two-pronged approach: robust feature extraction followed by the application of a machine learning (ML) classifier. The mel-frequency cepstral coefficients (MFCCs) extraction algorithm is employed for feature extraction due to the low frequency range of the adopted biometric signals and the nonlinearity of the filter bank used for MFCC extraction. Several ML classifiers are adopted to validate the system with cancelable templates without any inversion process. Simulation results with multilayer perceptron (MLP) and logistic regression (LR) classifiers demonstrated superior effectiveness of the proposed authentication framework, with accuracy rates up to 100% and 99.7% on the pulse transit time PPG and BIDMC datasets, respectively. Hence, the proposed system proves effective access control and user verification in the Internet-of-Things (IoT) applications. [ABSTRACT FROM AUTHOR]

With the increased use of social network sites, such as Twitter, attackers exploit these platforms to spread counterfeit content. Such content can be fake advertisements or illegal content. Classifying such content is a challenging task, especially in Arabic. The Arabic language has a complex structure and makes classification tasks more difficult. This paper presents an approach to classifying Arabic tweets using classical machine learning (non-deep machine learning) and deep learning techniques. Tweets corpus were collected through Twitter API and labelled manually to get a reliable dataset. For an efficient classifier, feature extraction is applied to the corpus dataset. Then, two learning techniques are used for each feature extraction technique on the created dataset using N-gram models (uni-gram, bi-gram, and char-gram). The applied classical machine learning algorithms are support vector machines, neural networks, logistics regression, and naïve Bayes. Global vector (GloVe) and fastText learning models are utilised for the deep learning approaches. The Precision, Recall, and F1-score are the suggested performance measures calculated in this paper. Afterwards, the dataset is increased using the synthetic minority oversampling technique class to create a balanced dataset. After applying the classical machine learning models, the experimental results show that the neural network algorithm outperforms the other algorithms. Moreover, the GloVe outperforms the fastText model for the deep learning approach. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) using inertial motion data has gained a lot of momentum in recent years both in research and industrial applications. From the abstract perspective, this has been driven by the rapid dynamics for building intelligent, smart environments, and ubiquitous systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc., which necessitate and subsume activity recognition aiming at recognizing the actions, characteristics, and goals of one or more agent(s) from a temporal series of observations streamed from one or more sensors. From a more concrete and seemingly orthogonal perspective, such momentum has been driven by the ubiquity of inertial motion sensors on-board mobile and wearable devices including smartphones, smartwatches, etc. In this paper we give an introductory and a comprehensive survey to the subject from a given perspective. We focus on a subset of topics, that we think are major, that will have significant and influential impacts on the future research and industrial-scale deployment of HAR systems. These include: (1) a comprehensive and detailed description of the inertial motion benchmark datasets that are publicly available and/or accessible, (2) feature selection and extraction techniques and the corresponding learning methods used to build workable HAR systems; we survey classical handcrafted datasets as well as data-oriented automatic representation learning approach to the subject, (3) transfer learning as a way to overcome many hurdles in actual deployments of HAR systems on a large scale, (4) embedded implementations of HAR systems on mobile and/or wearable devices, and finally (5) we touch on adversarial attacks, a topic that is essentially related to the security and privacy of HAR systems. As the field is very huge and diverse, this article is by no means comprehensive; it is though meant to provide a logically and conceptually rather complete picture to advanced practitioners, as well as to present a readable guided introduction to newcomers. Our logical and conceptual perspectives mimic the typical data science pipeline for state-of-the-art AI-based systems. [ABSTRACT FROM AUTHOR]

Automatic captioning of images contributes to identifying features of multimedia content and helps in the detection of interesting patterns, trends, and occurrences. English image captioning has recently made incredible progress; however, Arabic image captioning is still lagging. In the field of machine learning, Arabic image-caption generation is generally a very difficult problem. This paper presents a more accurate model for Arabic image captioning by using transformer models in both the encoder and decoder phases as feature extractors from images in the encoder phase and a pre-trained word embedding model in the decoder phase. The models are demonstrated, and all of them are implemented, trained, and tested on Arabic Flickr8k datasets. For the image feature extraction subsystem, we compared using three different individual vision models (SWIN, XCIT, and ConvNexT) with concatenation to get among them the most expressive extracted feature vector of the image, and for the caption generation lingual subsystem, which is tested by four different pre-trained language embedding models: (ARABERT, ARAELECTRA, MARBERTv2, and CamelBERT), to select from them the most accurate pre-trained language embedding model. Our experiments showed that building an Arabic image captioning system that uses a concatenation of the three transformer-based models ConvNexT combined with SWIN and XCIT as an image feature extractor, combined with the CamelBERT language embedding model produces the best results among the other combinations, having scores of 0.5980 with BLEU-1 and with ConvNexT combined with SWIN the araelectra language embedding model having a score of 0.1664 with BLEU-4 which are higher than the previously reported values of 0.443 and 0.157. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging is a highly advanced and sophisticated method for capturing images in hundreds of narrow, contiguous spectral bands. However, processing and analyzing such large amounts of data are challenging. Deep learning algorithms, especially those based on convolutional neural networks (CNNs), effectively extract rich feature representations from complex datasets, such as hyperspectral images (HSIs). These representations capture high-level patterns and characteristics that can facilitate accurate classification. The success of this approach has led to its widespread use in various remote sensing applications. However, the standard CNN inputs and outputs are scalars, ignoring the relative position relationships between features. In this paper, we propose a hierarchical capsule network for HSI classification. This network incorporates a multi-level convolutional structure for feature extraction and fusion. It utilizes convolutional feature maps of various depths to generate initial capsules, followed by vector computation using capsule neurons and a weight matrix to encode spatial location relationships among features. Furthermore, the shallow convolution of the hierarchical capsule network is pre-trained based on transfer learning to further improve the performance of HSI classification. According to experimental results, the proposed method for hyperspectral image classification has been found to outperform other state-of-the-art deep learning models on four benchmark datasets. [ABSTRACT FROM AUTHOR]

To improve the effect of landslide feature extraction, this paper improves the remote sensing image recognition algorithm with the support of a machine learning algorithm. Moreover, this paper combines UAV remote sensing images to extract landslide features, classifies and introduces the evaluation criteria for target detection and several representative target detectors. This paper also constructs the functional structure of the system according to the landslide feature extraction requirements and designs a set of optimization schemes for landslide feature data collection and control measurement suitable for field operations. In addition, this paper analyses the system kernel algorithm process and analyses the system function realization through simulation research. Finally, this paper designs an experiment to evaluate the practicability of the system constructed in this paper. From the results of experimental statistics, we can see that the system constructed in this paper has good practicability. [ABSTRACT FROM AUTHOR]

Automatic facial expression recognition (AFER), sometimes referred to as emotional recognition, is important for socializing. Automatic methods in the past two years faced challenges due to Covid-19 and the vital wearing of a mask. Machine learning techniques tremendously increase the amount of data processed and achieved good results in such AFER to detect emotions; however, those techniques are not designed for masked faces and thus achieved poor recognition. This paper introduces a hybrid convolutional neural network aided by a local binary pattern to extract features in an accurate way, especially for masked faces. The basic seven emotions classified into anger, happiness, sadness, surprise, contempt, disgust, and fear are to be recognized. The proposed method is applied on two datasets: the first represents CK and CK +, while the second represents M-LFW-FER. Obtained results show that emotion recognition with a face mask achieved an accuracy of 70.76% on three emotions. Results are compared to existing techniques and show significant improvement. [ABSTRACT FROM AUTHOR]

POI group recommendation is one of the hottest research topics in location-based social networks, which recommends the most agreeable places for a group of users. However, traditional POI group recommendation methods only generate a consensus function to aggregate individual preference into group preference and they do not consider all the factors that can determine the results of POI group recommendation, which leads to a low recommendation accuracy. What's more, these methods have a long running time. Therefore, in this paper, we propose a new POI group recommendation method with an extreme learning machine (ELM) called PGR-ELM. The PGR-ELM method regards POI group recommendation as a binary classification problem. First, three features are extracted from three factors: POI popularity, group members' distance to POI, members' interest preferences combined affinity between group members. These features simultaneously consider all the factors that can determine the results of recommendation and guarantee the effectiveness of POI group recommendation. Then, the extracted features are input to train an ELM classifier because of its fast learning speed, which guarantees the efficiency of POI group recommendation. Finally, extensive experiments verify the accuracy and efficiency of PGR-ELM method. [ABSTRACT FROM AUTHOR]

Stress is now thought to be a major cause to a wide range of human health issues. However, many people may ignore their stress feelings and disregard to take action before serious physiological and mental disorders take place. The heart rate (HR) and blood pressure (BP) are the most physiological markers used in various studies to detect mental stress for a human, and because they are captured non-invasively using wearable sensors, these markers are recommended to provide information on a person's mental state. Most stress assessment studies have been undertaken in a laboratory-based controlled environment. This paper proposes an approach to identify the mental stress of automotive drivers based on selected biosignals, namely, ECG, EMG, GSR, and respiration rate. In this study, six different machine learning models (KNN, SVM, DT, LR, RF, and MLP) have been used to classify between the stressed and relaxation states. Such system can be integrated with a Driver Assistance System (DAS). The proposed stress detection technique (SDT) consists of three main phases: (1) Biosignal Pre-processing, in which the signal is segmented and filtered. (2) Feature Extraction, in which some discriminate features are extracted from each biosignal to describe the mental state of the driver. (3) Classification. The results show that the RF classifier outperforms other techniques with a classification accuracy of 98.2%, sensitivity 97%, and specificity 100% using the drivedb dataset. [ABSTRACT FROM AUTHOR]

In order to improve the diagnosis and classification effect of pituitary tumors, this paper combines the current common machine learning methods and classification prediction methods to improve the traditional machine learning algorithms. Moreover, this paper analyzes the feature algorithm based on the feature extraction requirements of pituitary tumor pictures and compares a variety of commonly used algorithms to select a classification algorithm suitable for the model of this paper through comparison methods. In addition, this paper carries out the calculation of the prediction algorithm and verifies the algorithm according to the actual situation. Finally, based on the neural network algorithm, this paper designs and constructs the algorithm function module and combines the actual needs of pituitary tumors to build the model and verify the performance of the model. The research results show that the model system constructed in this paper meets the expected demand. [ABSTRACT FROM AUTHOR]

Feature extraction, feature clustering, feature selection are suitable to enhance learning performance, reduce computational complexity, create better generalizable models, and reduce required storage. Although there are several feature reduction techniques, still it remains one of the research hot spots in the field of data mining and machine learning groups. Owl search algorithm (OSA) is one of the recent metaheuristic optimization algorithms that mimic the hunting mechanism of owls in dark. However, OSA suffers from the same problem faced by many other optimization algorithms and tends to fall in local optima and premature convergence. To overcome these problems, two improvements for OSA algorithm are proposed in this paper. The first improvement uses a fuzzy system which is responsible to tune a control parameter in the updating phase of OSA. The second improvement includes the fuzzy system along with modifying the updating equation of OSA to enhance the exploration activity. In addition, this paper presents a new feature extraction technique for regression problems based on the improved OSA, called Fuzzy Owl Clustering Dimension Reduction (FOCDR). We apply a method that uses three weighting methods (i.e., soft, hard, and mixed) to extract new features based on the generated clusters. The experiment is divided into two parts. In the first part, the performance of the OSA algorithm and two improvement versions are analyzed with ten benchmark functions. The results show that the proposed versions on average can improve the convergence rate by 6.75% and 14.2% compared to OSA in solving complex problems. The second part is conducted to show FOCDR's ability for feature selection problems. The effectiveness of FOCDR has been evaluated using four benchmark datasets and a real-world case study. [ABSTRACT FROM AUTHOR]

At present, the judgment of the burn depth is mainly based on the experience of doctors, so the accuracy of judgment is low, which will affect the follow-up treatment and nursing. In order to improve the diagnostic effect of clinical burns, based on incremental reinforcement learning algorithms, this paper constructs a classification model of clinical burn thermal images based on machine learning algorithms. Moreover, this paper proposes an adaptive network algorithm and uses the structure of the network to implement a reinforcement learning algorithm. In this algorithm, in order to reduce the computational complexity under the premise of ensuring sample utilization, the parameters are updated in the form of increments. In addition, this paper uses the value function approximator to linearly approximate the value function and TD error. Finally, this paper constructs the basic structure of the model based on the functional requirements and constructs experiments to verify the performance of the model. The research results show that the algorithm has good convergence and the image classification effect is very obvious, so it has certain practical significance. [ABSTRACT FROM AUTHOR]

When the turning tool has worn and failed but the failure is not found, if it continues to be used for processing, it will break, and cause the workpiece to be scrapped, and even damage the machine tool. In order to avoid the loss caused by turning tool wear, the remaining useful life (RUL) prediction of turning tool wear has become a hot research topic in recent years. For RUL prediction in turning tools, the traditional machine is difficult to acquire sufficient degradation data and inconsistent data distribution among different turning tools in engineering, and they cannot provide better prediction accuracy to some extent. To solve the above problems, this paper proposes a multi-granularity feature extraction (MGFE) method based on the gray-level co-occurrence matrix (GLCM) and random forest (RF). Moreover, a health indicator (HI) of turning tools in the source domain was obtained. The common representative features in HI sequence of target domain was transferred to source domain and builds the condition monitoring and life prediction system of turning tools based on extreme learning machine and transfer learning. Finally, extreme vector machine (ELM) is used to construct the RUL prediction model. The research results show that the model constructed in this paper is effective in RUL prediction and can significantly improve the prediction accuracy of remaining useful life. [ABSTRACT FROM AUTHOR]

In recent years, image perception such as enhancement, classification and object detection with deep learning has achieved significant successes. However, in real world under extreme conditions, the training of a deep learning model often yields low accuracy, low efficiency in feature extraction and generalizability, due to the inner uncourteous and uninterpretable characteristics. In this paper, a maximal-entropy-attention-based convolutional neural network (MEA-CNN) framework is proposed. A maximum entropy algorithm is first used for image feature pre-extraction. An attention mechanism is then proposed by combining the extracted features on original images. By applying the mechanism, the key areas of an image are enhanced, and noised area can be ignored. Afterward, the processed images are transferred into region convolutional neural network, which is a well-known pre-trained CNN model, for further feature learning and extraction. Finally, two real-world experiments on traffic sign recognition and road surface condition monitoring are designed. The results show that the proposed framework has high testing accuracy, with improvements of 17% and 2.9%, compared with some other existing methods. In addition, the features extracted by the model are more easily interpretable. [ABSTRACT FROM AUTHOR]

Dummy trajectory is widely used to protect the privacy of mobile users' locations. However, two main challenges remain: (1) Map background information has not been modeled by machine learning methods in existing schemes, and (2) it is difficult to generate a good quality dummy trajectory that is similar to the real one. Focused on these two challenges, in this paper, we propose a dummy trajectory generation scheme with conditional generative adversary network (GAN), where the map features are extracted using convolutional neural network, which is regarded as a prior restriction of conditional GAN. Then, the movement pattern of the real trajectory is deduced by an auto-encoder and is involved in the dummy trajectory generation. Our model is trained and evaluated with two real-world datasets. Experimental results demonstrate that our scheme addresses these challenges well and defends against various attacks effectively. [ABSTRACT FROM AUTHOR]

To date, being benefited from the ability of automated feature extraction and the performance of software vulnerability identification, deep learning techniques have attracted extensive attention in data-driven software vulnerability detection. Many methods based on deep learning have been proposed to speed up and intelligentize the process of vulnerability identification. Although these methods have shown significant advantages over traditional machine learning ones, there is an apparent gap between the deep learning-based detection systems and human experts in understanding potentially vulnerable code semantics. In some real-world vulnerability prediction scenarios, the performance of deep learning-based methods drops by more than 50% compared to these methods' performance in experimental scenarios. We define this phenomenon as the perception gap by examining and reviewing the early software vulnerability detection approaches. Then, from the perspective of the perception gap, this paper profoundly explores the current software vulnerability detection methods and how existing solutions endeavor to narrow the perception gap and push forward the development of the field of interest. Finally, we summarize the challenges of this new field and discuss the possible future. [ABSTRACT FROM AUTHOR]

Deaf people face major challenges during communication with normal people. Employing a human interpreter (a person who converts Sign language (SL) into a language that the normal/hearing community can understand) is not an effective solution to this problem due to the unavailability of professional interpreters. Thus, the Sign Language Recognition System (SLRS) is the most efficient and effective choice because it automatically converts SL into text/speech without an interpreter and reduces the communication barrier between deaf and normal people. This paper reports a work on Indian Sign Language (ISL) word recognition using a vision-based technique. The existing vision-based solutions for ISL word recognition are ineffective due to excessive pre-processing such as extracting features from a large sequence of frames. Therefore, a vision-based SLRS named Hybrid CNN-BiLSTM SLR (HCBSLR) is proposed, which overcomes the drawback of excessive pre-processing. The proposed model uses a Histogram Difference (HD) based key-frame extraction method to improve the accuracy and efficiency of the system by eliminating redundant or useless frames. The HCBSLR system uses VGG-19 for spatial feature extraction and Bidirectional Long Short Term Memory (BiLSTM) for temporal feature extraction. The proposed HCBSLR system has achieved an average accuracy of 87.67%, which is compared with some of the existing SLRS. The experimental results show that the proposed HCBSLR system is more accurate and efficient than the existing SLRS. [ABSTRACT FROM AUTHOR]

Human emotion recognition is an active research area in artificial intelligence and has made substantial progress over the past few years. Many recent works mainly focus on facial regions to infer human affection, while the surrounding context information is not effectively utilized. In this paper, we proposed a new deep network to effectively recognize human emotions using a novel global-local attention mechanism. Our network is designed to extract features from both facial and context regions independently, then learn them together using the attention module. In this way, both the facial and contextual information is used to infer human emotions, therefore enhancing the discrimination of the classifier. The intensive experiments show that our method surpasses the current state-of-the-art methods on recent emotion datasets by a fair margin. Qualitatively, our global-local attention module can extract more meaningful attention maps than previous methods. The source code and trained model of our network are available at https://github.com/minhnhatvt/glamor-net. [ABSTRACT FROM AUTHOR]

Language classification using speeches is a complex issue in machine learning and pattern recognition. Various text and image-based language classification methods have been presented. But there are limited speech-based language classification methods in the literature. Also, the previously presented models classified limited numbers of languages, and few are accents. This work presents an automated handcrafted language classification model. The novel pyramid pattern is presented to extract the features extraction. Also, statistical features and maximum pooling are used to generate the features. We have developed our speech-language classification model using two datasets: (i) created a new big speech dataset containing 14,500 speeches in 29 languages, and (ii) used the VoxForge dataset. The neighborhood component analysis method is used to select the most informative 1000 features from the generated features, and these features are classified using a quadratic support vector machine classifier (QSVM). Our developed method yielded 98.87 ± 0.30% and 97.12 ± 1.27% accuracies for our and VoxForge datasets, respectively. Also, geometric mean, average precision, and F1-score evaluation parameters are calculated, and they are presented in the results section. This paper presents an accurate language classification model developed using two big speech-language datasets. Our results indicate the success of the proposed pyramid pattern-based language classification method in classifying various speech languages accurately. [ABSTRACT FROM AUTHOR]

In the previous works on heat stress detection, various state-of-the-art machine learning techniques had been used to detect stress patterns from electroencephalographic (EEG) signals. Since the handcrafted feature engineering-based approaches pose certain limitations and are sensitive to transform the nonlinearities of EEG, deep learning techniques have drawn attention in the domain of EEG-based applications. Moreover, existing approaches for stress detection consider the whole frequency band (delta to gamma) which conceals the redundant and lossy information that increased the false detection rate. Also, these approaches were implemented only to identify the stress in binary classes and confined their application to identifying the level of stress. Therefore, a multi-scale channel-wise convolution-based multi-level heat stress assessment has been proposed in this paper. The novel contributions of this work are (1) designing a multi-scale convolutional neural network (MS-CNN) for extracting precise information from individual frequency bands of EEG, (2) use of sparse connectivity to reduce the redundant information and increase the performance with less trainable parameters, and (3) multi-level heat stress assessment for precise identification of the severity of stress. The proposed approaches were evaluated on pre-recorded data of 10 rats in a simulated laboratory environment. The high accuracy of approximately 96–97% and 90–92% has been achieved for binary and multi-level stress detection. There is approximately a 6 to 50% reduction in the trainable parameters with a 2% improvement of accuracy achieved on adopting channel-wise convolution over MS-CNN and deep convolutional neural network (DCNN). This demonstrates the effectiveness of the adopted multiscale feature extraction and sparse connectivity to improve the performance with a less complex model. [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]

Images and videos captured in rainy conditions show visual degradation, resulting in poor performance for outdoor computer vision systems. Traditional deraining methods fail to work in moderate and torrential rain removal, while the data-driven learning-based methods are hindered by removing rain streaks in an efficient manner, and lack consideration applied to edge devices with limited resources. So, this paper proposes a software-hardware co-designed image deraining system named MSL-MNN based on the multi-scale lightweight memristive neural network, which combines deep learning and the nanoscale device memristor. Specifically, a novel feature extraction block ReFiSE based on the lightweight residual mode and squeeze-and-excitation operation is designed. Benefiting from this, MSL-MNN is endowed with a lightweight network framework. Then, the multi-scale skip connection design is introduced to encourage the decoder to use low-level semantic information. Besides, a hardware implementation scheme of MSL-MNN is presented by leveraging the memristor crossbar array, which organically combines the deep learning algorithm with the neuro-inspired computing chip to speed the real-time processing of image data. Finally, a series of experimental results prove the effectiveness and superiority of MSL-MNN in rain removal and the recovery of image details. This study is expected to provide an end-to-end algorithm design and hardware acceleration solution for intelligent image processing besides image deraining. [ABSTRACT FROM AUTHOR]

This paper presents several approaches to deal with the problem of identifying muons in a water Cherenkov detector with a reduced water volume and 4 PMTs. Different perspectives of information representation are used, and new features are engineered using the specific domain knowledge. As results show, these new features, in combination with the convolutional layers, are able to achieve a good performance avoiding overfitting and being able to generalise properly for the test set. The results also prove that the combination of state-of-the-art machine learning analysis techniques and water Cherenkov detectors with low water depth can be used to efficiently identify muons, which may lead to huge investment savings due to the reduction of the amount of water needed at high altitudes. This achievement can be used in further research to be able to discriminate between gamma and hadron-induced showers using muons as discriminant. [ABSTRACT FROM AUTHOR]

With the development of science and technology, the classification of polarimetric SAR images has become an important part of the research of target recognition and image interpretation. However, for the research method is relatively simple and the accuracy is low, this paper carries out the work from the two aspects of feature extraction and feature classification of the ground object, and analyzes and studies the application and value of the polarimetric SAR system. The basic algorithm of polarization SAR image classification is proposed. A polarimetric SAR image feature classification method based on polarization target decomposition and support vector machine is proposed. Four kinds of scattering features and Freeman decomposition are obtained by Cloude decomposition. The simulation results show that the accuracy of using combined features is about 6.5% higher than that of single features. A polarization classification model based on polarization target decomposition and limit learning method is proposed. The simulation experiment shows ELM learning. The algorithm is indeed much faster than SVM learning. In this paper, a polarimetric SAR image classification method based on improved scattering mechanism coefficients is proposed, and the effectiveness of the polarimetric SAR image classification method based on improved scattering mechanism coefficients is verified. Experimental results show that after feature selection, the method of combining Freeman decomposition and Wishart classifier can get better classification results. [ABSTRACT FROM AUTHOR]

Feature extraction is one of most important steps in the control of multifunctional prosthesis based on surface electromyography (sEMG) pattern recognition. In this paper, a new sEMG feature extraction method based on muscle active region is proposed. This paper designs an experiment to classify four hand motions using different features. This experiment is used to prove that new features have better classification performance. The experimental results show that the new feature, active muscle regions (AMR), has better classification performance than other traditional features, mean absolute value (MAV), waveform length (WL), zero crossing (ZC) and slope sign changes (SSC). The average classification errors of AMR, MAV, WL, ZC and SSC are 13%, 19%, 26%, 24% and 22%, respectively. The new EMG features are based on the mapping relationship between hand movements and forearm active muscle regions. This mapping relationship has been confirmed in medicine. We obtain the active muscle regions data from the original EMG signal by the new feature extraction algorithm. The results obtained from this algorithm can well represent hand motions. On the other hand, the new feature vector size is much smaller than other features. The new feature can narrow the computational cost. This proves that the AMR can improve sEMG pattern recognition accuracy rate. [ABSTRACT FROM AUTHOR]

At present, there are many methods to realize the matching of specified images with features, and the basic components include image feature point detection, feature description, and image matching. Based on this background, this article has done different research and exploration around these three aspects. The image feature point detection method is firstly studied, which commonly include image edge information-based feature detection method, corner information-based detection method, and various interest operators. However, all of the traditional detection methods are involved in problems of large computation burden and time consumption. In order to solve this problem, a feature detection method based on image grayscale information-FAST operator is used in this paper, which is combined with decision tree theory to effectively improve the speed of extracting image feature points. Then, the feature point description method BRIEF operator is studied, which is a local expression of detected image feature points based on descriptors. Since the descriptor does not have rotation invariance, the detection operator is endowed by a direction that is proposed in this paper, and then the local feature description is conducted on the feature descriptor to generate a binary string array containing direction information. Finally, the feature matching machine learning method is analyzed, and the nearest search method is used to find the nearest feature point pair in Euclidean distance, of which the calculation burden is small. The simulation results show that the proposed nearest neighbor search and matching machine learning algorithm has higher matching accuracy and faster calculation speed compared with the classical feature matching algorithm, which has great advantages in processing a large number of array images captured by the light field camera. [ABSTRACT FROM AUTHOR]

Risk management plays a vital role in tackling cyber threats within the cyber-physical system (CPS). It enables identifying critical assets, vulnerabilities and threats and determining suitable proactive control measures for the risk mitigation. However, due to the increased complexity of the CPS, cyber-attacks nowadays are more sophisticated and less predictable, which makes risk management task more challenging. This paper aims for an effective cybersecurity risk management (CSRM) practice using assets criticality, predication of risk types and evaluating the effectiveness of existing controls. We follow a number of techniques for the proposed unified approach including fuzzy set theory for the asset criticality, machine learning classifiers for the risk predication and comprehensive assessment model (CAM) for evaluating the effectiveness of the existing controls. The proposed approach considers relevant CSRM concepts such as asset, threat actor, attack pattern, tactic, technique and procedure (TTP), and controls and maps these concepts with the VERIS community dataset (VCDB) features for the risk predication. The experimental results reveal that using the fuzzy set theory in assessing assets criticality supports stakeholder for an effective risk management practice. Furthermore, the results have demonstrated the machine learning classifiers exemplary performance to predict different risk types including denial of service, cyber espionage and crimeware. An accurate prediction of risk can help organisations to determine the suitable controls in proactive manner to manage the risk. [ABSTRACT FROM AUTHOR]

Spike trains (STs) induced by external stimuli are complex and challenging to decode the embedded spatiotemporal information. Although various methods have been developed to characterize STs, few applications have been reported in tactile discrimination applications. In this paper, a neurocomputing method based on reference spike train (RST) is proposed to establish a neural computation scheme, on which existing ST metrics could be fed into various traditional models directly. Moreover, existing metrics in the field of statistics and vector measurement are introduced together to extract more discriminative features. With the binning technique and feature selection algorithm applied, the neural computation scheme is aimed at taking advantage of as maximal as possible information contained in tactile signals. Based on our designed artificial fingertip, the effect is validated by improving the recognition accuracy from 77.6% to 83.4% when it is applied to the discrimination of eight roughness surfaces. Furthermore, properties of RST, such as spike intervals and distributions, are evaluated and it is found that RSTs with uniform distribution perform the best for tactile discrimination. [ABSTRACT FROM AUTHOR]

This paper presents a new and mathematical method for online signature validation based on machine learning. In this way, the average values of the factors are taken into account to ensure validity. Here, seven different types of features used are x coordinates, y coordinates, time stamp, pen up and down, azimuth, height and pressure. Three new features are extracted from it, i.e., (displacement, velocity and acceleration) using the correlated extraction process to obtain dynamic feature of signature. These features are extracted from the popular dataset SVC2004. The extracted feature is then passed to various classifiers named as Naive Bayes, random forest, J48, MLP, logistic regression and PART. The result of genuine and forge signatures is obtained in terms of precision, true positive rate, false positive rate, F-score, etc. The obtained result is then compared with the existing method with respect to false acceptance rate and false rejection rate. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) is the current trend in technology expansion as it provides an easy interface between human brain and machine. The demand for BCI-based applications is growing tremendously, and efforts are in progress to deploy BCI devices for real-world applications. One of the widely known applications of BCI technology is rehabilitation in which BCI devices can provide various types of assistance to specially abled persons. In this paper, the effect of hand actions on objects is analyzed for motor-related mental task. The proposed approach analyzes electroencephalogram (EEG)-based brain activity which was captured for images shown with different gripping actions on objects. The EEG recordings are first pre-processed, followed by extraction of epochs and frequency bands using discrete wavelet transform; afterward, feature extraction followed by training and classification steps is performed for classifying the grip action into congruent (correct) and incongruent (incorrect) grip categories. The proposed work makes use of average power and relative wavelet energy as discriminating features which are then fed to train an artificial neural network for automatically classifying the incoming EEG patterns into correct or incorrect object hand grips. The performance evaluation of the proposed system is done on real EEG dataset obtained from 14 subjects. Experimental results have shown an accuracy of 75%. Also, to evaluate the effectiveness of our work, a comparison of our work with other state-of-the-art works reported by different authors is presented at the end. The results show the effectiveness of proposed approach and suggest further that the system can be used to analyze and train subjects having motor-related disabilities for perceiving correct or incorrect hand grips on objects. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases are one of the most fatal diseases across the globe. Clinically, conventional stethoscope is used to check the medical condition of a human heart. Only a trained medical professional can understand and interpret the heart auscultations clinically. This paper presents a machine learning-based automatic classification system based on heart sounds to diagnose cardiac disorders. The proposed framework involves strategic processing and framing of heart sound to extract discriminatory features for machine learning. The most prominent features are selected and used to train a supervised classifier for automatic detection of cardiac diseases. The biological abnormalities disturbing the physical functioning of the heart cause variations in the auscultations, which is strategically used in terms of some discriminatory features for machine learning-based automatic classification. The proposed method achieved 97.78% accuracy with the equal error rate of 2.22% for abnormal and normal heart sound classification. The experimental results exhibit that the performance of the proposed method in proper diagnosis of the cardiac diseases is high in terms of accuracy and has low error rate which makes the proposed algorithm suitable for real-time applications. [ABSTRACT FROM AUTHOR]

Today's human activity recognition is an important part of healthcare and ambient-assisted living where accelerometer and gyroscope sensors provide the raw data about physical activities and functional abilities of an observed person. Previous studies have shown that activity recognition can be seen as a machine learning chain with its particular data preprocessing technique. In recent past, several scientists measured rather high recognition accuracies on public databases or in laboratory environment but their solutions have not been tested in real environment. The goal of this paper is to examine the efficiency of previously used machine learning methods in real time by an Android-based, self-learning, activity recognition application which has been designed especially to this study according to the latest theoretical results (with the most relevant feature extraction and machine learning algorithms). Before real-time tests, we investigated the design considerations and application possibilities of different shallow and deep methods. The final outcome shows recognition rate difference between the "online" and "offline" cases. In the article we present some reasons for the difference and their possible solutions. [ABSTRACT FROM AUTHOR]

Artificial metaplasticity is the machine learning algorithm inspired in the biological metaplasticity of neural synapses. Metaplasticity stands for plasticity of plasticity, and as long as plasticity is related to memory, metaplasticity is related to learning. Implemented in supervised learning assuming input patterns distribution or a related function, it has proved to be very efficient in performance and in training convergence for multidisciplinary applications. Now, for the first time, this kind of artificial metaplasticity is implemented in an unsupervised neural network, achieving also excellent results that are presented in this paper. To compare results, a modified self-organization map is applied to the classification of MIT-BIH cardiac arrhythmias database. [ABSTRACT FROM AUTHOR]

This paper proposes a new two-dimensional manifold learning algorithm called two-dimensional joint local/nonlocal discriminant analysis (2DJLNDA) for 2D image feature extraction, which directly extracts projective vectors from 2D image matrices rather than image vectors. Different from other typical 2D methods, e.g., two-dimensional principal component analysis (2DPCA), two-dimensional linear discriminative analysis (2DLDA), two-dimensional locality-preserving projection (2DLPP), 2DJLNDA preserves not only local/nonlocal intrinsic structure but also local/nonlocal penalization structure of the image data in the high-dimensional space, which can be powerful in extracting intrinsic information of the image data in the low-dimensional space. The experimental results on the ORL, Yale, AR and UMIST face datasets indicate that 2DJLNDA is capable of extracting effective image features and outperforms 2DPCA, 2DLDA and 2DLPP. The 2D image features extracted by 2DJLNDA further improve the performance of deep neural networks (DNNs), e.g., stacked denoising autoencoder, and convolutional neural network (CNN) significantly. These studying results illustrate that the feature face images will provide more discriminant features than the original face images for DNNs. Therefore, 2DJLNDA-based 2D feature image extraction can be used as an effective preprocessing of DNNs (e.g., CNN) for face recognition. [ABSTRACT FROM AUTHOR]

Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79% using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1% accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system. [ABSTRACT FROM AUTHOR]

This paper presents a learning mechanism based on hybridization of static and dynamic learning. Realizing the detection performances offered by the state-of-the-art deep learning techniques and the competitive performances offered by the conventional static learning techniques, we propose the idea of exploitation of the concatenated (parallel) hybridization of the static and dynamic learning-based feature spaces. This is contrary to the cascaded (series) hybridization topology in which the initial feature space (provided by the conventional, static, and handcrafted feature extraction technique) is explored using deep, dynamic, and automated learning technique. Consequently, the characteristics already suppressed by the conventional representation cannot be explored by the dynamic learning technique. Instead, the proposed technique combines the conventional static and deep dynamic representation in concatenated (parallel) topology to generate an information-rich hybrid feature space. Thus, this hybrid feature space may aggregate the good characteristics of both conventional and deep representations, which are then explored using an appropriate classification technique. We also hypothesize that ensemble classification may better exploit this parallel hybrid perspective of the feature spaces. For this purpose, pyramid histogram of oriented gradients-based static learning has been incorporated in conjunction with convolution neural network-based deep learning to produce concatenated hybrid feature space. This hybrid space is then explored with various state-of-the-art ensemble classification techniques. We have considered the publicly available INRIA person and Caltech pedestrian standard image datasets to assess the performance of the proposed hybrid learning system. Furthermore, McNemar's test has been used to statistically validate the outperformance of the proposed technique over various contemporary techniques. The validated experimental results show that the employment of the proposed hybrid representation results in effective detection performance (an AUC of 0.9996 for INRIA person and 0.9985 for Caltech pedestrian datasets) as compared to the individual static and dynamic representations. [ABSTRACT FROM AUTHOR]

Learning results depend on the representation of data, so how to efficiently represent data has been a research hot spot in machine learning and artificial intelligence. With the deepening of the deep learning research, studying how to train the deep networks to express high dimensional data efficiently also has been a research frontier. In order to present data more efficiently and study how to express data through deep networks, we propose a novel stacked denoising sparse autoencoder in this paper. Firstly, we construct denoising sparse autoencoder through introducing both corrupting operation and sparsity constraint into traditional autoencoder. Then, we build stacked denoising sparse autoencoders which has multi-hidden layers by layer-wisely stacking denoising sparse autoencoders. Experiments are designed to explore the influences of corrupting operation and sparsity constraint on different datasets, using the networks with various depth and hidden units. The comparative experiments reveal that test accuracy of stacked denoising sparse autoencoder is much higher than other stacked models, no matter what dataset is used and how many layers the model has. We also find that the deeper the network is, the less activated neurons in every layer will have. More importantly, we find that the strengthening of sparsity constraint is to some extent equal to the increase in corrupted level. [ABSTRACT FROM AUTHOR]

Automated textual analysis of firm-related documents has become an important decision support tool for stock market investors. Previous studies tended to adopt either dictionary-based or machine learning approach. Nevertheless, little is known about their concurrent use. Here we use the combination of financial indicators, readability, sentiment categories, and bag-of-words (BoW) to increase prediction accuracy. This paper aims to extract both sentiment and BoW information from the annual reports of US firms. The sentiment analysis is based on two commonly used dictionaries, namely a general dictionary Diction 7.0 and a finance-specific dictionary proposed by Loughran and McDonald (J Finance 66:35-65, 2011. doi:10.1111/j.1540-6261.2010.01625.x). The BoW are selected according to their tf-idf. We combine these features with financial indicators to predict abnormal stock returns using a multilayer perceptron neural network with dropout regularization and rectified linear units. We show that this method performs similarly as naïve Bayes and outperforms other machine learning algorithms (support vector machine, C4.5 decision tree, and k-nearest neighbour classifier) in predicting positive/negative abnormal stock returns in terms of ROC. We also show that the quality of the prediction significantly increased when using the correlation-based feature selection of BoW. This prediction performance is robust to industry categorization and event window. [ABSTRACT FROM AUTHOR]

Nowadays, millions of people are affected by heart diseases worldwide, whereas a considerable amount of them could be aided through an electrocardiogram (ECG) trace analysis, which involves the study of arrhythmia impacts on electrocardiogram patterns. In this work, we carried out the task of automatic arrhythmia detection in ECG patterns by means of supervised machine learning techniques, being the main contribution of this paper to introduce the optimum-path forest (OPF) classifier to this context. We compared six distance metrics, six feature extraction algorithms and three classifiers in two variations of the same dataset, being the performance of the techniques compared in terms of effectiveness and efficiency. Although OPF revealed a higher skill on generalizing data, the support vector machines (SVM)-based classifier presented the highest accuracy. However, OPF shown to be more efficient than SVM in terms of the computational time for both training and test phases. [ABSTRACT FROM AUTHOR]

This paper presents a modified TLBO (teaching-learning-based optimization) approach for the local linear radial basis function neural network (LLRBFNN) model to classify multiple power signal disturbances. Cumulative sum average filter has been designed for localization and feature extraction of multiple power signal disturbances. The extracted features are fed as inputs to the modified TLBO-based LLRBFNN for classification. The performance of the proposed modified TLBO-based LLRBFNN model is compared with the conventional model in terms of convergence speed and classification accuracy. Also, an extreme learning machine (ELM) approach is used to optimize the performance of the proposed LLRBFNN and is compared with the TLBO method in classifying the multiple power signal disturbances. The classification results reveal that although the TLBO approach produces slightly better accuracy in comparison with the ELM approach, the latter is much faster in implementation, thus making it suitable for processing large quantum of power signal disturbance data. [ABSTRACT FROM AUTHOR]

The shape feature of an object represents the geometrical information which plays an important role in the image understanding and image retrieval. How to get an excellent shape feature that has rotation, scaling and translation (RST) invariance is a problem in this field. This paper proposed a novel local extreme learning machine (LELM) classification algorithm to extract the shape features. LELM finds nearest neighbors of the testing set from the original training set and trains a local classification model. The shape feature is represented by an analytic decision function with a radial basis function (RBF) kernel obtained by LELM. Our method has the following advantages: (1) LELM not only keeps the local structure of the samples, but also solves the imbalance problem between variance and bias. (2) Features obtained by the RBF kernel are RST invariant. (3) LELM is more robust against the noise and fragmentation compared to other methods. We also demonstrate the performance of the proposed method in image retrieval. [ABSTRACT FROM AUTHOR]

Manifold learning aims to map the original data from a high-dimensional space into a low-dimensional feature space with possible better discriminative structure. In this paper, we propose a supervised manifold learning approach called SubManifold Individuality LEarning (SMILE). In SMILE, the linear subspace derived from the principal component analysis based on data with the same label is named as 'the individual subspace', while the linear subspace learned from all data is defined as 'the global subspace'. For each data sample, the aim of SMILE is to enlarge the diversity between its reconstructed data from individual subspace and global subspace, respectively, so that the intrinsic character of each class can be stimulated in the feature space. SMILE also utilizes the Laplacian matrix to restrict the local structure of data in the low-dimensional feature space in order to preserve the locality of the high-dimensional data. The proposed method is validated in appearance-based face recognition problem on some typical facial image databases via extracting discriminative features. Experimental results show that the proposed approach can obtain the discriminative structure of facial manifold and extract better features for face recognition than other counterparts approaches. [ABSTRACT FROM AUTHOR]

In a smart healthcare system, the sensor-embedded wearable devices have the ability to track various vital signs of a patient.However, such devices need to be worn by the patients all the time. These devices have limitations such as their battery lifetime, charging mechanism, and hardware-related cost. Moreover, these devices transmit a huge amount of redundant and inconsistent data. The transmitted data need to be fused to remove any outlier so that only highly- refined data are available for decision-making. In this paper, we use channel state information (CSI) to track the vital signs of a patient and remove any outliers from the gathered data. We monitor the respiration rate of a patient during sleep with minimal hardware-related cost. Our CSI-based approach no longer requires the patients to wear any wearables and can monitor even the minute fluctuations in a WiFi signal.For extracting useful features from the respiratory data, three types of feature extraction techniques are used. In order to select important features from the extracted feature space, three feature selection algorithms, i.e., Relief, mRMR, and Lasso, have been investigated. In addition, for predicting the health conditions of a patient, four machine learning classification algorithms, i.e., KNN, SVM, DT, and RF, are utilized. The use of CSI ensures that highly refined and fused data are available for feature selection, and the selected features are presented to the ML classification algorithms for predicting the health condition of the patient. [ABSTRACT FROM AUTHOR]