Search

In recent years, with the rapid development of deep learning technology, a large number of excellent convolutional neural networks (CNNs) have been proposed, many of which are based on improvements to classical methods. Based on the Inception family of methods, depthwise separable convolution was applied to Xception to achieve lightweighting, and Inception-ResNet introduces residual connections to accelerate model convergence. However, existing improvements for the Inception module often neglect further enhancement of its receptive field, while increasing the receptive field of CNNs has been widely studied and proven to be effective in improving classification performance. Motivated by this fact, three effective expansion modules are proposed in this paper. The first expansion module, Inception expand (Inception-e) module, is proposed to improve the classification accuracy by concatenating more and deeper convolutional branches. To reduce the number of parameters for Inception e, this paper proposes a second expansion module—Equivalent Inception-e (Eception) module, which is equivalent to Inception-e in terms of feature extraction capability, but which suppresses the growth of the parameter quantity brought by the expansion by effectively reducing the redundant convolutional layers; on the basis of Eception, this paper proposes a third expansion module—Lightweight Eception (Lception) module, which crosses depthwise convolution with ordinary convolution to further effectively reduce the number of parameters. The three proposed modules have been validated on the Cifar10 dataset. The experimental results show that all these extensions are effective in improving the classification accuracy of the models, and the most significant effect is the Lception module, where Lception (rank = 4) on the Cifar10 dataset improves the accuracy by 1.5% compared to the baseline model (Inception module A) by using only 0.15 M more parameters. [ABSTRACT FROM AUTHOR]

Effective feature extraction and selection are crucial for the accurate classification and prediction of hand gestures based on electromyographic signals. In this paper, we systematically compare six filter and wrapper feature evaluation methods and investigate their respective impacts on the accuracy of gesture recognition. The investigation is based on several benchmark datasets and one real hand gesture dataset, including 15 hand force exercises collected from 14 healthy subjects using eight commercial sEMG sensors. A total of 37 time- and frequency-domain features were extracted from each sEMG channel. The benchmark dataset revealed that the minimum Redundancy Maximum Relevance (mRMR) feature evaluation method had the poorest performance, resulting in a decrease in classification accuracy. However, the RFE method demonstrated the potential to enhance classification accuracy across most of the datasets. It selected a feature subset comprising 65 features, which led to an accuracy of 97.14%. The Mutual Information (MI) method selected 200 features to reach an accuracy of 97.38%. The Feature Importance (FI) method reached a higher accuracy of 97.62% but selected 140 features. Further investigations have shown that selecting 65 and 75 features with the RFE methods led to an identical accuracy of 97.14%. A thorough examination of the selected features revealed the potential for three additional features from three specific sensors to enhance the classification accuracy to 97.38%. These results highlight the significance of employing an appropriate feature selection method to significantly reduce the number of necessary features while maintaining classification accuracy. They also underscore the necessity for further analysis and refinement to achieve optimal solutions. [ABSTRACT FROM AUTHOR]

Chemical warfare agents pose a serious threat due to their extreme toxicity, necessitating swift the identification of chemical gases and individual responses to the identified threats. Fourier transform infrared (FTIR) spectroscopy offers a method for remote material analysis, particularly in detecting colorless and odorless chemical agents. In this paper, we propose a deep neural network utilizing a semi-supervised autoencoder (SSAE) for the classification of chemical gases based on FTIR spectra. In contrast to traditional methods, the SSAE concurrently trains an autoencoder and a classifier attached to a latent vector of the autoencoder, enhancing feature extraction for classification. The SSAE was evaluated on laboratory-collected FTIR spectra, demonstrating a superior classification performance compared to existing methods. The efficacy of the SSAE lies in its ability to generate denser cluster distributions in latent vectors, thereby enhancing gas classification. This study established a consistent experimental environment for hyperparameter optimization, offering valuable insights into the influence of latent vectors on classification performance. [ABSTRACT FROM AUTHOR]

Gait, a manifestation of one's walking pattern, intricately reflects the harmonious interplay of various bodily systems, offering valuable insights into an individual's health status. However, the current study has shortcomings in the extraction of temporal and spatial dependencies in joint motion, resulting in inefficiencies in pathological gait classification. In this paper, we propose a Frequency Pyramid Graph Convolutional Network (FP-GCN), advocating to complement temporal analysis and further enhance spatial feature extraction. specifically, a spectral decomposition component is adopted to extract gait data with different time frames, which can enhance the detection of rhythmic patterns and velocity variations in human gait and allow a detailed analysis of the temporal features. Furthermore, a novel pyramidal feature extraction approach is developed to analyze the inter-sensor dependencies, which can integrate features from different pathways, enhancing both temporal and spatial feature extraction. Our experimentation on diverse datasets demonstrates the effectiveness of our approach. Notably, FP-GCN achieves an impressive accuracy of 98.78% on public datasets and 96.54% on proprietary data, surpassing existing methodologies and underscoring its potential for advancing pathological gait classification. In summary, our innovative FP-GCN contributes to advancing feature extraction and pathological gait recognition, which may offer potential advancements in healthcare provisions, especially in regions with limited access to medical resources and in home-care environments. This work lays the foundation for further exploration and underscores the importance of remote health monitoring, diagnosis, and personalized interventions. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) need to replicate feature detectors when modeling spatial information, which reduces their efficiency. The number of replicated feature detectors or labeled training data required for such methods grows exponentially with the dimensionality of the data being used. On the other hand, space-insensitive methods are difficult to encode and express effectively due to the limitation of their rich text structures. In response to the above problems, this paper proposes a capsule network (self-attention capsule network, or SA-CapsNet) with a self-attention mechanism for text classification tasks, wherein the capsule network itself, given the feature with the symmetry hint on two ends, acts as both encoder and decoder. In order to learn long-distance dependent features in sentences and encode text information more efficiently, SA-CapsNet maps the self-attention module to the feature extraction layer of the capsule network, thereby increasing its feature extraction ability and overcoming the limitations of convolutional neural networks. In addition, in this study, in order to improve the accuracy of the model, the capsule was improved by reducing its dimension and an intermediate layer was added, enabling the model to obtain more expressive instantiation features in a given sentence. Finally, experiments were carried out on three general datasets of different sizes, namely the IMDB, MPQA, and MR datasets. The accuracy of the model on these three datasets was 84.72%, 80.31%, and 75.38%, respectively. Furthermore, compared with the benchmark algorithm, the model's performance on these datasets was promising, with an increase in accuracy of 1.08%, 0.39%, and 1.43%, respectively. This study focused on reducing the parameters of the model for various applications, such as edge and mobile applications. The experimental results show that the accuracy is still not apparently decreased by the reduced parameters. The experimental results therefore verify the effective performance of the proposed SA-CapsNet model. [ABSTRACT FROM AUTHOR]

In this paper, we present an unprecedented method based on Kohonen networks that is able to automatically recognize partial discharge (PD) classes from phase-resolved partial discharge (PRPD) diagrams with features of various simultaneous PD patterns. The PRPD diagrams were obtained from the stator windings of a real-world hydro-generator rotating machine. The proposed approach integrates classification probabilities into the Kohonen method, producing self-organizing probability maps (SOPMs). For building SOPMs, a group of PRPD diagrams, each containing a single PD pattern for training the Kohonen networks and single- and multiple-class-featured samples for obtaining final SOPMs, is used to calculate the probabilities of each Kohonen neuron to be associated with the various PD classes considered. At the end of this process, a self-organizing probability map is produced. Probabilities are calculated using distances, obtained in the space of features, between neurons and samples. The so-produced SOPM enables the effective classification of PRPD samples and provides the probability that a given PD sample is associated with a PD class. In this work, amplitude histograms are the features extracted from PRPDs maps. Our results demonstrate an average classification accuracy rate of approximately 90% for test samples. [ABSTRACT FROM AUTHOR]

Automotive radar is one of the key sensors for intelligent driving. Radar image sequences contain abundant spatial and temporal information, enabling target classification. For existing radar spatiotemporal classifiers, multi-view radar images are usually employed to enhance the information of the target and 3D convolution is employed for spatiotemporal feature extraction. These models consume significant hardware resources and are not applicable to real-time applications. In this paper, RadarTCN, a novel lightweight network, is proposed that achieves high-accuracy online target classification using single-view radar image sequences only. In RadarTCN, 2D convolution and 3D-TCN are employed to extract spatiotemporal features sequentially. To reduce data dimensionality and computational complexity, a multi-layer max pooling down-sampling method is designed in a 2D convolution module. Meanwhile, the 3D-TCN module is improved through residual pruning and causal convolution is introduced for leveraging the performance of online target classification. The experimental results demonstrate that RadarTCN can achieve high-precision online target recognition for both range-angle and range-Doppler map sequences. Compared to the reference models on the CARRADA dataset, RadarTCN exhibits better classification performance, with fewer parameters and lower computational complexity. [ABSTRACT FROM AUTHOR]

Medium-voltage (MV) cables often experience a shortened lifespan attributed to insulation breakdown resulting from accelerated aging and anomalous operational and environmental stresses. While partial discharge (PD) measurements serve as valuable tools for assessing the insulation state, complexity arises from the presence of diverse discharge sources, making the evaluation of PD data challenging. The reliability of diagnostics for MV cables hinges on the precise interpretation of PD activity. To streamline the repair and maintenance of cables, it becomes crucial to discern and categorize PD types accurately. This paper presents a comprehensive review encompassing the realms of detection, feature extraction, artificial intelligence, and optimization techniques employed in the classification of PD signals/sources. Its exploration encompasses a variety of sensors utilized for PD detection, data processing methodologies for efficient feature extraction, optimization techniques dedicated to selecting optimal features, and artificial intelligence-based approaches for the classification of PD sources. This synthesized review not only serves as a valuable reference for researchers engaged in the application of methods for PD signal classification but also sheds light on potential avenues for future developments of techniques within the context of MV cables. [ABSTRACT FROM AUTHOR]

As a convenient and natural way of human-computer interaction, gesture recognition technology has broad research and application prospects in many fields, such as intelligent perception and virtual reality. This paper summarized the relevant literature on gesture recognition using Frequency Modulated Continuous Wave (FMCW) millimeter-wave radar from January 2015 to June 2023. In the manuscript, the widely used methods involved in data acquisition, data processing, and classification in gesture recognition were systematically investigated. This paper counts the information related to FMCW millimeter wave radar, gestures, data sets, and the methods and results in feature extraction and classification. Based on the statistical data, we provided analysis and recommendations for other researchers. Key issues in the studies of current gesture recognition, including feature fusion, classification algorithms, and generalization, were summarized and discussed. Finally, this paper discussed the incapability of the current gesture recognition technologies in complex practical scenes and their real-time performance for future development. [ABSTRACT FROM AUTHOR]

Early rice disease detection is vital in preventing damage to agricultural product output and quantity in the agricultural field. Manual observations of rice diseases are tedious, costly, and time-consuming, especially when classifying disease patterns and color while dealing with non- native diseases. Hence, image processing and Machine Learning (ML) techniques are used to detect rice disease early and within a relatively brief time period. This article aims to demonstrate the performance of different ML algorithms in rice disease detection through image processing. We critically examined different techniques, and the outcomes of previous research have been reviewed to compare the performance of rice disease classifications. Performance has been evaluated based on the criteria of feature extraction, clustering, segmentation, noise reduction, and level of accuracy of disease detection techniques. This paper also showcases various algorithms for different datasets in terms of training methods, image preprocessing with clustering and filtering criteria, and testing with reliable outcomes. Through this review, we provide valuable insights into the current state of ML-based approaches for the early detection of rice diseases, and assist future research and improvement. In addition, we discuss several challenges that must be overcome in order to achieve effective identification of rice diseases. [ABSTRACT FROM AUTHOR]

For the multi-label classification task of remote sensing images (RSIs), it is difficult to accurately extract feature information from complex land covers, and it is easy to generate redundant features by ordinary convolution extraction features. This paper proposes a multi-label classification model for multi-source RSIs that combines dense convolution and an attention mechanism. This method adds fusion channel attention and a spatial attention mechanism to each dense block module of the DenseNet, and the sigmoid activation function replaces the softmax activation function in multi-label classification. The improved model retains the main features of RSIs to the greatest extent and enhances the feature extraction of the images. The model can integrate local features, capture global dependencies, and aggregate contextual information to improve the multi-label land cover classification accuracy of RSIs. We conducted comparative experiments on the SEN12-MS and UC-Merced land cover dataset and analyzed the evaluation indicators. The experimental results show that this method effectively improves the multi-label classification accuracy of RSIs. [ABSTRACT FROM AUTHOR]

Determining the types of light curves has been a challenge due to the massive amount of light curves generated by large sky survey programs. In the literature, the light curves classification methods are overly dependent on the imaging quality of the light curves, so the classification results are often poor. In this paper, a new method is proposed to classify the Kepler light curves from Quarter 1, and consists of two parts: feature extraction and classification neural network construction. In the first part, features are extracted from the light curves using three different methods, and then the features are fused (transform domain features, light curve flux statistics features, and Kepler photometry features). In the second part, a classification neural network RLNet, based on Residual Network (ResNet) and Long Short Term Memory (LSTM), is proposed. The experiment involved the classification of approximately 150,000 Kepler light curves into 11 categories. The results show that this new method outperforms seven other methods in all metrics, with an accuracy of 0.987, a minimum recall of 0.968, and a minimum precision of 0.970 under all categories. [ABSTRACT FROM AUTHOR]

Electrical activities of the human brain can be recorded with electroencephalography (EEG). To characterize motor imagery (MI) tasks for brain–computer interface (BCI) implementation is an easy and cost-effective tool. The MI task is represented by a short-time trial of multichannel EEG. In this paper, the signal of each channel of raw EEG is decomposed into a finite set of narrowband signals using a Fourier-transformation-based bandpass filter. Rhythmic components of EEG are represented by each of the narrowband signals that characterize the brain activities related to MI tasks. The subband signals are arranged to extend the dimension of the EEG trial in the spatial domain. The spatial features are extracted from the set of extended trials using a common spatial pattern (CSP). An optimum number of features are employed to classify the motor imagery tasks using an artificial neural network. An integrated approach with full-band and narrowband signals is implemented to derive discriminative features for MI classification. In addition, the subject-dependent parameter optimization scheme enhances the performance of the proposed method. The performance evaluation of the proposed method is obtained using two publicly available benchmark datasets (Dataset I and Dataset II). The experimental results in terms of classification accuracy (93.88% with Dataset I and 91.55% with Dataset II) show that it performs better than the recently developed algorithms. The enhanced MI classification accuracy is very much applicable in BCI implementation. [ABSTRACT FROM AUTHOR]

This paper describes the transformation of a traditional in silico classification network into an optical fully convolutional neural network with high-resolution feature maps and kernels. When using the free-space 4f system to accelerate the inference speed of neural networks, higher resolutions of feature maps and kernels can be used without the loss in frame rate. We present FatNet for the classification of images, which is more compatible with free-space acceleration than standard convolutional classifiers. It neglects the standard combination of convolutional feature extraction and classifier dense layers by performing both in one fully convolutional network. This approach takes full advantage of the parallelism in the 4f free-space system and performs fewer conversions between electronics and optics by reducing the number of channels and increasing the resolution, making this network faster in optics than off-the-shelf networks. To demonstrate the capabilities of FatNet, it was trained with the CIFAR100 dataset on GPU and the simulator of the 4f system. A comparison of the results against ResNet-18 shows 8.2 times fewer convolution operations at the cost of only 6% lower accuracy. This demonstrates that the optical implementation of FatNet results in significantly faster inference than the optical implementation of the original ResNet-18. These are promising results for the approach of training deep learning with high-resolution kernels in the direction toward the upcoming optics era. [ABSTRACT FROM AUTHOR]

Arrhythmias are defined as irregularities in the heartbeat rhythm, which may infrequently occur in a human's life. These arrhythmias may cause potentially fatal complications, which may lead to an immediate risk of life. Thus, the detection and classification of arrhythmias is a pertinent issue for cardiac diagnosis. (1) Background: To capture these sporadic events, an electrocardiogram (ECG), a register containing the heart's electrical function, is considered the gold standard. However, since ECG carries a vast amount of information, it becomes very complex and challenging to extract the relevant information from visual analysis. As a result, designing an efficient (automated) system to analyse the enormous quantity of data possessed by ECG is critical. (2) Method: This paper proposes a hybrid deep learning-based approach to automate the detection and classification process. This paper makes two-fold contributions. First, 1D ECG signals are translated into 2D Scalogram images to automate the noise filtering and feature extraction. Then, based on experimental evidence, by combining two learning models, namely 2D convolutional neural network (CNN) and the Long Short-Term Memory (LSTM) network, a hybrid model called 2D-CNN-LSTM is proposed. (3) Result: To evaluate the efficacy of the proposed 2D-CNN-LSTM approach, we conducted a rigorous experimental study using the widely adopted MIT–BIH arrhythmia database. The obtained results show that the proposed approach provides ≈98.7%, 99%, and 99% accuracy for Cardiac Arrhythmias (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR), respectively. Moreover, it provides an average sensitivity of the proposed model of 98.33% and a specificity value of 98.35%, for all three arrhythmias. (4) Conclusions: For the classification of arrhythmias, a robust approach has been introduced where 2 D scalogram images of ECG signals are trained over the CNN-LSTM model. The results obtained are better as compared to the other existing techniques and will greatly reduce the amount of intervention required by doctors. For future work, the proposed method can be applied over some live ECG signals and Bi-LSTM can be applied instead of LSTM. [ABSTRACT FROM AUTHOR]

Hydraulic rock drills are widely used in drilling, mining, construction, and engineering applications. They typically operate in harsh environments with high humidity, large temperature differences, and vibration. Under the influence of environmental noise and operational patterns, the distributions of data collected by sensors for different operators and equipment differ significantly, which leads to difficulty in fault classification for hydraulic rock drills. Therefore, an intelligent and robust fault classification method is highly desired. In this paper, we propose a fault classification technique for hydraulic rock drills based on deep learning. First, considering the strong robustness of x−vectors to the features extracted from the time series, we employ an end−to−end fault classification model based on x−vectors to realize the joint optimization of feature extraction and classification. Second, the overlapping data clipping method is applied during the training process, which further improves the robustness of our model. Finally, the focal loss is used to focus on difficult samples, which improves their classification accuracy. The proposed method obtains an accuracy of 99.92%, demonstrating its potential for hydraulic rock drill fault classification. [ABSTRACT FROM AUTHOR]

White blood cells (WBCs) constitute an essential part of the human immune system. The correct identification of WBC subtypes is critical in the diagnosis of leukemia, a kind of blood cancer defined by the aberrant proliferation of malignant leukocytes in the bone marrow. The traditional approach of classifying WBCs, which involves the visual analysis of blood smear images, is labor-intensive and error-prone. Modern approaches based on deep convolutional neural networks provide significant results for this type of image categorization, but have high processing and implementation costs owing to very large feature sets. This paper presents an improved hybrid approach for efficient WBC subtype classification. First, optimum deep features are extracted from enhanced and segmented WBC images using transfer learning on pre-trained deep neural networks, i.e., DenseNet201 and Darknet53. The serially fused feature vector is then filtered using an entropy-controlled marine predator algorithm (ECMPA). This nature-inspired meta-heuristic optimization algorithm selects the most dominant features while discarding the weak ones. The reduced feature vector is classified with multiple baseline classifiers with various kernel settings. The proposed methodology is validated on a public dataset of 5000 synthetic images that correspond to five different subtypes of WBCs. The system achieves an overall average accuracy of 99.9 % with more than 95 % reduction in the size of the feature vector. The feature selection algorithm also demonstrates better convergence performance as compared to classical meta-heuristic algorithms. The proposed method also demonstrates a comparable performance with several existing works on WBC classification. [ABSTRACT FROM AUTHOR]

Few-shot hyperspectral classification is a challenging problem that involves obtaining effective spatial–spectral features in an unsupervised or semi-supervised manner. In recent years, as a result of the development of computer vision, deep learning techniques have demonstrated their superiority in tackling the problems of hyperspectral unmixing (HU) and classification. In this paper, we present a new semi-supervised pipeline for few-shot hyperspectral classification, where endmember abundance maps obtained by HU are treated as latent features for classification. A cube-based attention 3D convolutional autoencoder network (CACAE), is applied to extract spectral–spatial features. In addition, an attention approach is used to improve the accuracy of abundance estimation by extracting the diagnostic spectral features associated with the given endmember more effectively. The endmember abundance estimated by the proposed model outperforms other convolutional neural networks (CNNs) with respect to the root mean square error (RMSE) and abundance spectral angle distance (ASAD). Classification experiments are performed on real hyperspectral datasets and compared to several supervised and semi-supervised models. The experimental findings demonstrate that the proposed approach has promising potential for hyperspectral feature extraction and has better performance relative to CNN-based supervised classification under small-sample conditions. [ABSTRACT FROM AUTHOR]

In the process of extracting tailings ponds from large scene remote sensing images, semantic segmentation models usually perform calculations on all small-size remote sensing images segmented by the sliding window method. However, some of these small-size remote sensing images do not have tailings ponds, and their calculations not only affect the model accuracy, but also affect the model speed. For this problem, we proposed a fast tailings pond extraction method (Scene-Classification-Sematic-Segmentation, SC-SS) that couples scene classification and semantic segmentation models. The method can map tailings ponds rapidly and accurately in large scene remote sensing images. There were two parts in the method: a scene classification model, and a semantic segmentation model. Among them, the scene classification model adopted the lightweight network MobileNetv2. With the help of this network, the scenes containing tailings ponds can be quickly screened out from the large scene remote sensing images, and the interference of scenes without tailings ponds can be reduced. The semantic segmentation model used the U-Net model to finely segment objects from the tailings pond scenes. In addition, the encoder of the U-Net model was replaced by the VGG16 network with stronger feature extraction ability, which improves the model's accuracy. In this paper, the Google Earth images of Luanping County were used to create the tailings pond scene classification dataset and tailings pond semantic segmentation dataset, and based on these datasets, the training and testing of models were completed. According to the experimental results, the extraction accuracy (Intersection Over Union, IOU) of the SC-SS model was 93.48%. The extraction accuracy of IOU was 15.12% higher than the U-Net model, while the extraction time was shortened by 35.72%. This research is of great importance to the remote sensing dynamic observation of tailings ponds on a large scale. [ABSTRACT FROM AUTHOR]

Emotion plays a vital role in understanding the affective state of mind of an individual. In recent years, emotion classification using electroencephalogram (EEG) has emerged as a key element of affective computing. Many researchers have prepared datasets, such as DEAP and SEED, containing EEG signals captured by the elicitation of emotion using audio–visual stimuli, and many studies have been conducted to classify emotions using these datasets. However, baseline power removal is still considered one of the trivial aspects of preprocessing in feature extraction. The most common technique that prevails is subtracting the baseline power from the trial EEG power. In this paper, a novel method called InvBase method is proposed for removing baseline power before extracting features that remain invariant irrespective of the subject. The features extracted from the baseline removed EEG data are then used for classification of two classes of emotion, i.e., valence and arousal. The proposed scheme is compared with subtractive and no-baseline-correction methods. In terms of classification accuracy, it outperforms the existing state-of-art methods in both valence and arousal classification. The InvBase method plus multilayer perceptron shows an improvement of 29% over the no-baseline-correction method and 15% over the subtractive method. [ABSTRACT FROM AUTHOR]

In this paper, a new method is proposed to detect traffic regulations at intersections using GPS traces. The knowledge of traffic rules for regulated locations can help various location-based applications in the context of Smart Cities, such as the accurate estimation of travel time and fuel consumption from a starting point to a destination. Traffic regulations as map features, however, are surprisingly still largely absent from maps, although they do affect traffic flow which, in turn, affects vehicle idling time at intersections, fuel consumption, CO 2 emissions, and arrival time. In addition, mapping them using surveying equipment is costly and any update process has severe time constraints. This fact is precisely the motivation for this study. Therefore, its objective is to propose an automatic, fast, scalable, and inexpensive way to identify the type of intersection control (e.g., traffic lights, stop signs). A new method based on summarizing the collective behavior of vehicle crossing intersections is proposed. A modification of a well-known clustering algorithm is used to detect stopping and deceleration episodes. These episodes are then used to categorize vehicle crossing of intersections into four possible traffic categories (p1: free flow, p2: deceleration without stopping events, p3: only one stopping event, p4: more than one stopping event). The percentages of crossings of each class per intersection arm, together with other speed/stop/deceleration features, extracted from trajectories, are then used as features to classify the intersection arms according to their traffic control type (dynamic model). The classification results of the dynamic model are compared with those of the static model, where the classification features are extracted from OpenStreetMap. Finally, a hybrid model is also tested, where a combination of dynamic and static features is used, which outperforms the other two models. For each of the three models, two variants of the feature vector are tested: one where only features associated with a single intersection arm are used (one-arm model) and another where features also from neighboring intersection arms of the same intersection are used to classify an arm (all-arm model). The methodology was tested on three datasets and the results show that all-arm models perform better than single-arm models with an accuracy of 95% to 97%. [ABSTRACT FROM AUTHOR]

This paper explores the feasibility of using low-resolution infrared (LRIR) image streams for human activity recognition (HAR) with potential application in e-healthcare. Two datasets based on synchronized multichannel LRIR sensors systems are considered for a comprehensive study about optimal data acquisition. A novel noise reduction technique is proposed for alleviating the effects of horizontal and vertical periodic noise in the 2D spatiotemporal activity profiles created by vectorizing and concatenating the LRIR frames. Two main analysis strategies are explored for HAR, including (1) manual feature extraction using texture-based and orthogonal-transformation-based techniques, followed by classification using support vector machine (SVM), random forest (RF), k-nearest neighbor (k-NN), and logistic regression (LR), and (2) deep neural network (DNN) strategy based on a convolutional long short-term memory (LSTM). The proposed periodic noise reduction technique showcases an increase of up to 14.15% using different models. In addition, for the first time, the optimum number of sensors, sensor layout, and distance to subjects are studied, indicating the optimum results based on a single side sensor at a close distance. Reasonable accuracies are achieved in the case of sensor displacement and robustness in detection of multiple subjects. Furthermore, the models show suitability for data collected in different environments. [ABSTRACT FROM AUTHOR]

A brain stroke is a life-threatening medical disorder caused by the inadequate blood supply to the brain. After the stroke, the damaged area of the brain will not operate normally. As a result, early detection is crucial for more effective therapy. Computed tomography (CT) images supply a rapid diagnosis of brain stroke. However, while doctors are analyzing each brain CT image, time is running fast. This circumstance may lead to result in a delay in treatment and making errors. Therefore, we targeted the utilization of an efficient artificial intelligence algorithm in stroke detection. In this paper, we designed hybrid algorithms that include a new convolution neural networks (CNN) architecture called OzNet and various machine learning algorithms for binary classification of real brain stroke CT images. When we classified the dataset with OzNet, we acquired successful performance. However, for this target, we combined it with a minimum Redundancy Maximum Relevance (mRMR) method and Decision Tree (DT), k-Nearest Neighbors (kNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), and Support Vector Machines (SVM). In addition, 4096 significant features were obtained from the fully connected layer of OzNet, and we reduced the dimension of features from 4096 to 250 using the mRMR method. Finally, we utilized these machine learning algorithms to classify important features. As a result, OzNet-mRMR-NB was an excellent hybrid algorithm and achieved an accuracy of 98.42% and AUC of 0.99 to detect stroke from brain CT images. [ABSTRACT FROM AUTHOR]

In order to categorize feature classes by capturing subtle differences, hyperspectral images (HSIs) have been extensively used due to the rich spectral-spatial information. The 3D convolution-based neural networks (3DCNNs) have been widely used in HSI classification because of their powerful feature extraction capability. However, the 3DCNN-based HSI classification approach could only extract local features, and the feature maps it produces include a lot of spatial information redundancy, which lowers the classification accuracy. To solve the above problems, we proposed a spatial attention network (SATNet) by combining 3D OctConv and ViT. Firstly, 3D OctConv divided the feature maps into high-frequency maps and low-frequency maps to reduce spatial information redundancy. Secondly, the ViT model was used to obtain global features and effectively combine local-global features for classification. To verify the effectiveness of the method in the paper, a comparison with various mainstream methods on three publicly available datasets was performed, and the results showed the superiority of the proposed method in terms of classification evaluation performance. [ABSTRACT FROM AUTHOR]

Tongue color classification serves as important assistance for traditional Chinese medicine (TCM) doctors to make a precise diagnosis. This paper proposes a novel two-step framework based on deep learning to improve the performance of tongue color classification. First, a semantic-based CNN called SegTongue is applied to segment the tongues from the background. Based on DeepLabv3+, multiple atrous spatial pyramid pooling (ASPP) modules are added, and the number of iterations of fusions of low-level and high-level information is increased. After segmentation, various classical feature extraction networks are trained using softmax and center loss. The experiment results are evaluated using different measures, including overall accuracy, Kappa coefficient, individual sensitivity, etc. The results demonstrate that the proposed framework with SVM achieves up to 97.60% accuracy in the tongue image datasets. [ABSTRACT FROM AUTHOR]

Urban forests maintain the ecological balance of cities and are significant in promoting the sustainable development of cities. Therefore, using advanced remote sensing technology to accurately extract forest green space in the city and monitor its change in real-time is very important. Taking Nanjing as the study area, this research extracted 55 vegetation phenological features from Sentinel-2A time series images and formed a feature set containing 81 parameters together with 26 features, including polarimetric- and texture-related information extracted from dual-polarization Sentinel-1A data. On the basis of the improved ABC (ABC-LIBSVM) feature selection method, the optimal feature subset was selected, and the forest coverage areas in the study area were accurately described. To verify the feasibility of the improved feature selection method and explore the potential for the development of multi-source time series remote sensing for urban forest feature extraction, this paper also used the random forest classification model to classify four different feature sets. The results revealed that the classification accuracy based on the feature set obtained by the ABC-LIBSVM algorithm was the highest, with an overall accuracy of 86.80% and a kappa coefficient of 0.8145. The producer accuracy and user accuracy of the urban forest were 93.21% and 82.45%, respectively. Furthermore, by combining the multi-source time series Sentinel-2A optical images with Sentinel-1A dual-polarization SAR images, urban forests can be distinguished from the perspective of phenology, and polarimetric- and texture-related features can contribute to the accurate identification of forests. [ABSTRACT FROM AUTHOR]

Activity recognition using wearable sensors has become essential for a variety of applications. Tri-axial accelerometers are the most widely used sensor for activity recognition. Although various features have been used to capture patterns and classify the accelerometer signals to recognise activities, there is no consensus on the best features to choose. Reducing the number of features can reduce the computational cost and complexity and enhance the performance of the classifiers. This paper identifies the signal features that have significant discriminative power between different human activities. It also investigates the effect of sensor placement location, the sampling frequency, and activity complexity on the selected features. A comprehensive list of 193 signal features has been extracted from accelerometer signals of four publicly available datasets, including features that have never been used before for activity recognition. Feature significance was measured using the Joint Mutual Information Maximisation (JMIM) method. Common significant features among all the datasets were identified. The results show that the sensor placement location does not significantly affect recognition performance, nor does it affect the significant sub-set of features. The results also showed that with high sampling frequency, features related to signal repeatability and regularity show high discriminative power. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmias pose a significant danger to human life; therefore, it is of utmost importance to be able to efficiently diagnose these arrhythmias promptly. There exist many techniques for the detection of arrhythmias; however, the most widely adopted method is the use of an Electrocardiogram (ECG). The manual analysis of ECGs by medical experts is often inefficient. Therefore, the detection and recognition of ECG characteristics via machine-learning techniques have become prevalent. There are two major drawbacks of existing machine-learning approaches: (a) they require extensive training time; and (b) they require manual feature selection. To address these issues, this paper presents a novel deep-learning framework that integrates various networks by stacking similar layers in each network to produce a single robust model. The proposed framework has been tested on two publicly available datasets for the recognition of five micro-classes of arrhythmias. The overall classification sensitivity, specificity, positive predictive value, and accuracy of the proposed approach are 98.37%, 99.59%, 98.41%, and 99.35%, respectively. The results are compared with state-of-the-art approaches. The proposed approach outperformed the existing approaches in terms of sensitivity, specificity, positive predictive value, accuracy and computational cost. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles have large prospects for organizing territory monitoring. To integrate them into this sphere, it is necessary to improve their high functionality and safety. Computer vision is one of the vital monitoring aspects. In this paper, we developed and validated a methodology for terrain classification. The overall classification procedure consists of the following steps: (1) pre-processing, (2) feature extraction, and (3) classification. For the pre-processing stage, a clustering method based on particle swarm optimization was elaborated, which helps to extract object patterns from the image. Feature extraction is conducted via Gray-Level Co-Occurrence Matrix calculation, and the output of the matrix is turned into the input for a feed-forward neural network classification stage. The developed computer vision system showed 88.7% accuracy on the selected test set. These results can provide high quality territory monitoring; prospectively, we plan to establish a self-positioning system based on computer vision. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) point cloud classification methods based on deep learning have good classification performance; however, they adapt poorly to diverse datasets and their classification accuracy must be improved. Therefore, FSDCNet, a neural network model based on the fusion of static and dynamic convolution, is proposed and applied for multiview 3D point cloud classification in this paper. FSDCNet devises a view selection method with fixed and random viewpoints, which effectively avoids the overfitting caused by the traditional fixed viewpoint. A local feature extraction operator of dynamic and static convolution adaptive weight fusion was designed to improve the model's adaptability to different types of datasets. To address the problems of large parameters and high computational complexity associated with the current methods of dynamic convolution, a lightweight and adaptive dynamic convolution operator was developed. In addition, FSDCNet builds a global attention pooling, integrating the most crucial information on different view features to the greatest extent. Due to these characteristics, FSDCNet is more adaptable, can extract more fine-grained detailed information, and can improve the classification accuracy of point cloud data. The proposed method was applied to the ModelNet40 and Sydney Urban Objects datasets. In these experiments, FSDCNet outperformed its counterparts, achieving state-of-the-art point cloud classification accuracy. For the ModelNet40 dataset, the overall accuracy (OA) and average accuracy (AA) of FSDCNet in a single view reached 93.8% and 91.2%, respectively, which were superior to those values for many other methods using 6 and 12 views. FSDCNet obtained the best results for 6 and 12 views, achieving 94.6%, 93.3%, 95.3%, and 93.6% in OA and AA metrics, respectively. For the Sydney Urban Objects dataset, FSDCNet achieved an OA and F1 score of 81.2% and 80.1% in a single view, respectively, which were higher than most of the compared methods. In 6 and 12 views, FSDCNet reached an OA of 85.3% and 83.6% and an F1 score of 85.5% and 83.7%, respectively. [ABSTRACT FROM AUTHOR]

The hyperspectral feature extraction technique is one of the most popular topics in the remote sensing community. However, most hyperspectral feature extraction methods are based on region-based local information descriptors while neglecting the correlation and dependencies of different homogeneous regions. To alleviate this issue, this paper proposes a multi-view structural feature extraction method to furnish a complete characterization for spectral–spatial structures of different objects, which mainly is made up of the following key steps. First, the spectral number of the original image is reduced with the minimum noise fraction (MNF) method, and a relative total variation is exploited to extract the local structural feature from the dimension reduced data. Then, with the help of a superpixel segmentation technique, the nonlocal structural features from intra-view and inter-view are constructed by considering the intra- and inter-similarities of superpixels. Finally, the local and nonlocal structural features are merged together to form the final image features for classification. Experiments on several real hyperspectral datasets indicate that the proposed method outperforms other state-of-the-art classification methods in terms of visual performance and objective results, especially when the number of training set is limited. [ABSTRACT FROM AUTHOR]

Power quality disturbances (PQD) have a negative impact on power quality-sensitive equipment, often resulting in great financial losses. To prevent these losses, besides detecting a PQD on time, it is important to classify it, so that appropriate recovery procedures are employed. The majority of research employs machine learning model PQD classifiers on manually extracted features from simulated or real-world signals. This paper presents an end-to-end approach that circumvents the manual feature extraction and uses signals generated from mathematical voltage sag type formulas. We developed a configurable voltage sag generator that was used to form training and validation datasets. Based on the synthetic three-phase voltage signals, we trained several end-to-end LSTM classifiers that classify voltage sags according to ABC classification. The best-performing model achieved an accuracy of over 90% in the real-world dataset. [ABSTRACT FROM AUTHOR]

Automating the analysis of digital microscopic images to identify the cell sub-types or the presence of illness has assumed a great importance since it aids the laborious manual process of review and diagnosis. In this paper, we have focused on the analysis of white blood cells. They are the body’s main defence against infections and diseases and, therefore, their reliable classification is very important. Current systems for leukocyte analysis are mainly dedicated to: counting, sub-types classification, disease detection or classification. Although these tasks seem very different, they share many steps in the analysis process, especially those dedicated to the detection of cells in blood smears. A very accurate detection step gives accurate results in the classification of white blood cells. Conversely, when detection is not accurate, it can adversely affect classification performance. However, it is very common in real-world applications that work on inaccurate or non-accurate regions. Many problems can affect detection results. They can be related to the quality of the blood smear images, e.g., colour and lighting conditions, absence of standards, or even density and presence of overlapping cells. To this end, we performed an in-depth investigation of the above scenario, simulating the regions produced by detection-based systems. We exploit various image descriptors combined with different classifiers, including CNNs, in order to evaluate which is the most suitable in such a scenario, when performing two different tasks: Classification of WBC subtypes and Leukaemia detection. Experimental results have shown that Convolutional Neural Networks are very robust in such a scenario, outperforming common machine learning techniques combined with hand-crafted descriptors. However, when exploiting appropriate images for model training, even simpler approaches can lead to accurate results in both tasks. [ABSTRACT FROM AUTHOR]

Change detection (CD) for multitemporal hyperspectral images (HSI) can be approached as classification consisting of two steps, change feature extraction and change identification. This paper is focused on binary classification of the changed and the unchanged samples, which is the essential case of change detection. Meanwhile, it is challenging to extract clean change features from heavily corrupted spectral change vectors (SCV) of multitemporal HSI. The corruptions can be characterized as gross sample-specific errors, i.e., outliers, and small entry-wise noise following Gaussian distribution. To address the issue, this paper proposes a novel Spectrally-Spatially (SS) Regularized Low-Rank and Sparse Decomposition (LRSD) model, denoted by LRSD_SS. It decomposes the SCV into three components, a locally smoothed low-rank matrix for the clean change features, a sparse matrix for the outliers and an error matrix for the small Gaussian noise. The proposed method is effective in change feature extraction and robust to noise corruptions as it exploits the underlying data structures of the SCV, especially local spectral-spatial smoothness. It is also efficient since there is a closed-form solution for the feature component in the optimization problem of LRSD_SS. The experimental results in the paper show that the proposed method outperforms several classic methods which only deal with the spectral domain of image samples, as well as some state-of-the-art methods which use both spectral and spatial information. [ABSTRACT FROM AUTHOR]

Automatic building extraction from satellite images, an open research topic in remote sensing, continues to represent a challenge and has received substantial attention for decades. This paper presents an object-based and machine learning-based approach for automatic house detection from RGB high-resolution images. The images are first segmented by an algorithm combing a thresholding watershed transformation and hierarchical merging, and then shadows and vegetation are eliminated from the initial segmented regions to generate building candidates. Subsequently, the candidate regions are subjected to feature extraction to generate training data. In order to capture the characteristics of house regions well, we propose two kinds of new features, namely edge regularity indices (ERI) and shadow line indices (SLI). Finally, three classifiers, namely AdaBoost, random forests, and Support Vector Machine (SVM), are employed to identify houses from test images and quality assessments are conducted. The experiments show that our method is effective and applicable for house identification. The proposed ERI and SLI features can improve the precision and recall by 5.6% and 11.2%, respectively. [ABSTRACT FROM AUTHOR]

The aim of this research was to enhance the classification accuracy of an electronic nose (E-nose) in different detecting applications. During the learning process of the E-nose to predict the types of different odors, the prediction accuracy was not quite satisfying because the raw features extracted from sensors’ responses were regarded as the input of a classifier without any feature extraction processing. Therefore, in order to obtain more useful information and improve the E-nose’s classification accuracy, in this paper, a Weighted Kernels Fisher Discriminant Analysis (WKFDA) combined with Quantum-behaved Particle Swarm Optimization (QPSO), i.e., QWKFDA, was presented to reprocess the original feature matrix. In addition, we have also compared the proposed method with quite a few previously existing ones including Principal Component Analysis (PCA), Locality Preserving Projections (LPP), Fisher Discriminant Analysis (FDA) and Kernels Fisher Discriminant Analysis (KFDA). Experimental results proved that QWKFDA is an effective feature extraction method for E-nose in predicting the types of wound infection and inflammable gases, which shared much higher classification accuracy than those of the contrast methods. [ABSTRACT FROM AUTHOR]

Digital investigations of the real world through point clouds and derivatives are changing how curators, cultural heritage researchers and archaeologists work and collaborate. To progressively aggregate expertise and enhance the working proficiency of all professionals, virtual reconstructions demand adapted tools to facilitate knowledge dissemination. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. In this paper, we review the state of the art of point cloud integration within archaeological applications, giving an overview of 3D technologies for heritage, digital exploitation and case studies showing the assimilation status within 3D GIS. Identified issues and new perspectives are addressed through a knowledge-based point cloud processing framework for multi-sensory data, and illustrated on mosaics and quasi-planar objects. A new acquisition, pre-processing, segmentation and ontology-based classification method on hybrid point clouds from both terrestrial laser scanning and dense image matching is proposed to enable reasoning for information extraction. Experiments in detection and semantic enrichment show promising results of 94% correct semantization. Then, we integrate the metadata in an archaeological smart point cloud data structure allowing spatio-semantic queries related to CIDOC-CRM. Finally, a WebGL prototype is presented that leads to efficient communication between actors by proposing optimal 3D data visualizations as a basis on which interaction can grow. [ABSTRACT FROM AUTHOR]

This paper describes three coarse image description strategies, which are meant to promote a rough perception of surrounding objects for visually impaired individuals, with application to indoor spaces. The described algorithms operate on images (grabbed by the user, by means of a chest-mounted camera), and provide in output a list of objects that likely exist in his context across the indoor scene. In this regard, first, different colour, texture, and shape-based feature extractors are generated, followed by a feature learning step by means of AutoEncoder (AE) models. Second, the produced features are fused and fed into a multilabel classifier in order to list the potential objects. The conducted experiments point out that fusing a set of AE-learned features scores higher classification rates with respect to using the features individually. Furthermore, with respect to reference works, our method: (i) yields higher classification accuracies, and (ii) runs (at least four times) faster, which enables a potential full real-time application. [ABSTRACT FROM AUTHOR]

Learners in a massive open online course often express feelings, exchange ideas and seek help by posting questions in discussion forums. Due to the very high learner-to-instructor ratios, it is unrealistic to expect instructors to adequately track the forums, find all of the issues that need resolution and understand their urgency and sentiment. In this paper, considering the biases among different courses, we propose a transfer learning framework based on a convolutional neural network and a long short-term memory model, called ConvL, to automatically identify whether a post expresses confusion, determine the urgency and classify the polarity of the sentiment. First, we learn the feature representation for each word by considering the local contextual feature via the convolution operation. Second, we learn the post representation from the features extracted through the convolution operation via the LSTM model, which considers the long-term temporal semantic relationships of features. Third, we investigate the possibility of transferring parameters from a model trained on one course to another course and the subsequent fine-tuning. Experiments on three real-world MOOC courses confirm the effectiveness of our framework. This work suggests that our model can potentially significantly increase the effectiveness of monitoring MOOC forums in real time. [ABSTRACT FROM AUTHOR]

In recent years, due to its powerful feature extraction ability, the deep learning method has been widely used in hyperspectral image classification tasks. However, the features extracted by classical deep learning methods have limited discrimination ability, resulting in unsatisfactory classification performance. In addition, due to the limited data samples of hyperspectral images (HSIs), how to achieve high classification performance under limited samples is also a research hotspot. In order to solve the above problems, this paper proposes a deep learning network framework named the three-dimensional coordination attention mechanism network (3DCAMNet). In this paper, a three-dimensional coordination attention mechanism (3DCAM) is designed. This attention mechanism can not only obtain the long-distance dependence of the spatial position of HSIs in the vertical and horizontal directions, but also obtain the difference of importance between different spectral bands. In order to extract the spectral and spatial information of HSIs more fully, a convolution module based on convolutional neural network (CNN) is adopted in this paper. In addition, the linear module is introduced after the convolution module, which can extract more fine advanced features. In order to verify the effectiveness of 3DCAMNet, a series of experiments were carried out on five datasets, namely, Indian Pines (IP), Pavia University (UP), Kennedy Space Center (KSC), Salinas Valley (SV), and University of Houston (HT). The OAs obtained by the proposed method on the five datasets were 95.81%, 97.01%, 99.01%, 97.48%, and 97.69% respectively, 3.71%, 9.56%, 0.67%, 2.89% and 0.11% higher than the most advanced A2S2K-ResNet. Experimental results show that, compared with some state-of-the-art methods, 3DCAMNet not only has higher classification performance, but also has stronger robustness. [ABSTRACT FROM AUTHOR]

Aerial image classification has become popular and has attracted extensive research efforts in recent decades. The main challenge lies in its very high spatial resolution but relatively insufficient spectral information. To this end, spatial-spectral feature extraction is a popular strategy for classification. However, parameter determination for that feature extraction is usually time-consuming and depends excessively on experience. In this paper, an automatic spatial feature extraction approach based on image raster and segmental vector data cross-analysis is proposed for the classification of very high spatial resolution (VHSR) aerial imagery. First, multi-resolution segmentation is used to generate strongly homogeneous image objects and extract corresponding vectors. Then, to automatically explore the region of a ground target, two rules, which are derived from Tobler’s First Law of Geography (TFL) and a topological relationship of vector data, are integrated to constrain the extension of a region around a central object. Third, the shape and size of the extended region are described. A final classification map is achieved through a supervised classifier using shape, size, and spectral features. Experiments on three real aerial images of VHSR (0.1 to 0.32 m) are done to evaluate effectiveness and robustness of the proposed approach. Comparisons to state-of-the-art methods demonstrate the superiority of the proposed method in VHSR image classification. [ABSTRACT FROM AUTHOR]

This paper proposes a computer-aided cirrhosis diagnosis system to diagnose cirrhosis based on ultrasound images. We first propose a method to extract a liver capsule on an ultrasound image, then, based on the extracted liver capsule, we fine-tune a deep convolutional neural network (CNN) model to extract features from the image patches cropped around the liver capsules. Finally, a trained support vector machine (SVM) classifier is applied to classify the sample into normal or abnormal cases. Experimental results show that the proposed method can effectively extract the liver capsules and accurately classify the ultrasound images. [ABSTRACT FROM AUTHOR]

Muscle fatigue is an established area of research and various types of muscle fatigue have been investigated in order to fully understand the condition. This paper gives an overview of the various non-invasive techniques available for use in automated fatigue detection, such as mechanomyography, electromyography, near-infrared spectroscopy and ultrasound for both isometric and non-isometric contractions. Various signal analysis methods are compared by illustrating their applicability in real-time settings. This paper will be of interest to researchers who wish to select the most appropriate methodology for research on muscle fatigue detection or prediction, or for the development of devices that can be used in, e.g., sports scenarios to improve performance or prevent injury. To date, research on localised muscle fatigue focuses mainly on the clinical side. There is very little research carried out on the implementation of detecting/predicting fatigue using an autonomous system, although recent research on automating the process of localised muscle fatigue detection/prediction shows promising results. [ABSTRACT FROM AUTHOR]

Epilepsy is a neurological disorder of the brain that causes frequent occurrence of seizures. Electroencephalography (EEG) is a tool that assists neurologists in detecting epileptic seizures caused by an unexpected flow of electrical activities in the brain. Automated detection of an epileptic seizure is a crucial task in diagnosing epilepsy which overcomes the drawback of a visual diagnosis. The dataset analyzed in this article, collected from Children's Hospital Boston (CHB) and the Massachusetts Institute of Technology (MIT), contains long-term EEG records from 24 pediatric patients. This review paper focuses on various patient-dependent and patient-independent personalized medicine approaches involved in the computer-aided diagnosis of epileptic seizures in pediatric subjects by analyzing EEG signals, thus summarizing the existing body of knowledge and opening up an enormous research area for biomedical engineers. This review paper focuses on the features of four domains, such as time, frequency, time-frequency, and nonlinear features, extracted from the EEG records, which were fed into several classifiers to classify between seizure and non-seizure EEG signals. Performance metrics such as classification accuracy, sensitivity, and specificity were examined, and challenges in automatic seizure detection using the CHB-MIT database were addressed. [ABSTRACT FROM AUTHOR]

Although wearable accelerometers can successfully recognize activities and detect falls, their adoption in real life is low because users do not want to wear additional devices. A possible solution is an accelerometer inside a wrist device/smartwatch. However, wrist placement might perform poorly in terms of accuracy due to frequent random movements of the hand. In this paper we perform a thorough, large-scale evaluation of methods for activity recognition and fall detection on four datasets. On the first two we showed that the left wrist performs better compared to the dominant right one, and also better compared to the elbow and the chest, but worse compared to the ankle, knee and belt. On the third (Opportunity) dataset, our method outperformed the related work, indicating that our feature-preprocessing creates better input data. And finally, on a real-life unlabeled dataset the recognized activities captured the subject's daily rhythm and activities. Our fall-detection method detected all of the fast falls and minimized the false positives, achieving 85% accuracy on the first dataset. Because the other datasets did not contain fall events, only false positives were evaluated, resulting in 9 for the second, 1 for the third and 15 for the real-life dataset (57 days data). [ABSTRACT FROM AUTHOR]

In the inference process of existing deep learning models, it is usually necessary to process the input data level-wise, and impose a corresponding relational inductive bias on each level. This kind of relational inductive bias determines the theoretical performance upper limit of the deep learning method. In the field of sleep stage classification, only a single relational inductive bias is adopted at the same level in the mainstream methods based on deep learning. This will make the feature extraction method of deep learning incomplete and limit the performance of the method. In view of the above problems, a novel deep learning model based on hybrid relational inductive biases is proposed in this paper. It is called CCRRSleepNet. The model divides the single channel Electroencephalogram (EEG) data into three levels: frame, epoch, and sequence. It applies hybrid relational inductive biases from many aspects based on three levels. Meanwhile, multiscale atrous convolution block (MSACB) is adopted in CCRRSleepNet to learn the features of different attributes. However, in practice, the actual performance of the deep learning model depends on the nonrelational inductive biases, so a variety of matching nonrelational inductive biases are adopted in this paper to optimize CCRRSleepNet. The CCRRSleepNet is tested on the Fpz-Cz and Pz-Oz channel data of the Sleep-EDF dataset. The experimental results show that the method proposed in this paper is superior to many existing methods. [ABSTRACT FROM AUTHOR]

Deep learning-based fusion of spectral-spatial information is increasingly dominant for hyperspectral image (HSI) classification. However, due to insufficient samples, current feature fusion methods often neglect joint interactions. In this paper, to further improve the classification accuracy, we propose a dual-attention-guided interactive multi-scale residual network (DA-IMRN) to explore the joint spectral-spatial information and assign pixel-wise labels for HSIs without information leakage. In DA-IMRN, two branches focusing on spatial and spectral information separately are employed for feature extraction. A bidirectional-attention mechanism is employed to guide the interactive feature learning between two branches and promote refined feature maps. In addition, we extract deep multi-scale features corresponding to multiple receptive fields from limited samples via a multi-scale spectral/spatial residual block, to improve classification performance. Experimental results on three benchmark datasets (i.e., Salinas Valley, Pavia University, and Indian Pines) support that attention-guided multi-scale feature learning can effectively explore the joint spectral-spatial information. The proposed method outperforms state-of-the-art methods with the overall accuracy of 91.26%, 93.33%, and 82.38%, and the average accuracy of 94.22%, 89.61%, and 80.35%, respectively. [ABSTRACT FROM AUTHOR]

Breast cancer has affected many women worldwide. To perform detection and classification of breast cancer many computer-aided diagnosis (CAD) systems have been established because the inspection of the mammogram images by the radiologist is a difficult and time taken task. To early diagnose the disease and provide better treatment lot of CAD systems were established. There is still a need to improve existing CAD systems by incorporating new methods and technologies in order to provide more precise results. This paper aims to investigate ways to prevent the disease as well as to provide new methods of classification in order to reduce the risk of breast cancer in women's lives. The best feature optimization is performed to classify the results accurately. The CAD system's accuracy improved by reducing the false-positive rates.The Modified Entropy Whale Optimization Algorithm (MEWOA) is proposed based on fusion for deep feature extraction and perform the classification. In the proposed method, the fine-tuned MobilenetV2 and Nasnet Mobile are applied for simulation. The features are extracted, and optimization is performed. The optimized features are fused and optimized by using MEWOA. Finally, by using the optimized deep features, the machine learning classifiers are applied to classify the breast cancer images. To extract the features and perform the classification, three publicly available datasets are used: INbreast, MIAS, and CBIS-DDSM. The maximum accuracy achieved in INbreast dataset is 99.7%, MIAS dataset has 99.8% and CBIS-DDSM has 93.8%. Finally, a comparison with other existing methods is performed, demonstrating that the proposed algorithm outperforms the other approaches. [ABSTRACT FROM AUTHOR]

After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them. [ABSTRACT FROM AUTHOR]

Various defects are formed on the workpiece surface during the production process. Workpiece surface defects are classified according to various characteristics, which includes a bumped surface, scratched surface and pit surface. Suppliers analyze the cause of workpiece surface defects through the defect types and thus determines the subsequent processing. Therefore, the correct classification is essential regarding workpiece surface defects. In this paper, a multi-classifier decision-level fusion classification model for workpiece surface defects based on a convolutional neural network (CNN) was proposed. In the proposed model, the histogram of oriented gradient (HOG) was used to extract the features of the second fully connected layer of the CNN, and the features of the HOG were further extracted by using the local binary patterns (LBP), which was called the HOG–LBP feature extraction. Finally, this paper designed a symmetry ensemble classifier, which was used to classify the features of the last fully connected layer of the CNN and the features of the HOG–LBP. The comprehensive decision was made by fusing the classification results of the symmetry structure channels. The experiments were carried out, and the results showed that the proposed model could improve the accuracy of the workpiece surface defect classification. [ABSTRACT FROM AUTHOR]