Search

Since the beginning of the COVID-19 pandemic, many works have been published proposing solutions to the problems that arose in this scenario. In this vein, one of the topics that attracted the most attention is the development of computer-based strategies to detect COVID-19 from thoracic medical imaging, such as chest X-ray (CXR) and computerized tomography scan (CT scan). By searching for works already published on this theme, we can easily find thousands of them. This is partly explained by the fact that the most severe worldwide pandemic emerged amid the technological advances recently achieved, and also considering the technical facilities to deal with the large amount of data produced in this context. Even though several of these works describe important advances, we cannot overlook the fact that others only use well-known methods and techniques without a more relevant and critical contribution. Hence, differentiating the works with the most relevant contributions is not a trivial task. The number of citations obtained by a paper is probably the most straightforward and intuitive way to verify its impact on the research community. Aiming to help researchers in this scenario, we present a review of the top-100 most cited papers in this field of investigation according to the Google Scholar search engine. We evaluate the distribution of the top-100 papers taking into account some important aspects, such as the type of medical imaging explored, learning settings, segmentation strategy, explainable artificial intelligence (XAI), and finally, the dataset and code availability. [ABSTRACT FROM AUTHOR]

Featured Application: This paper proposes a method of monitoring the condition of three-phase asynchronous induction motors running with no load based on computer analysis of the instantaneous active electrical power. This paper experimentally reveals some of the resources offered by the instantaneous active electric power in describing the state of three-phase AC induction asynchronous electric motors (with a squirrel-cage rotor) operating under no-load conditions. A mechanical power is required to rotate the rotor with no load, and this mechanical power is satisfactorily reflected in the constant and variable part of instantaneous active electric power. The variable part of this electrical power should necessarily have a periodic component with the same period as the period of rotation of the rotor. This paper proposes a procedure for extracting this periodic component description (as a pattern by means of a selective averaging of instantaneous active electrical power) and analysis. The time origin of this pattern is defined by the time of a selected first passage through the origin of an angular marker placed on the rotor, detectable by a proximity sensor (e.g., a laser sensor). The usefulness of the pattern in describing the state of the motor rotor has been demonstrated by several simple experiments, which show that a slight change in the no-load running conditions of the motor (e.g., by placing a dynamically unbalanced mass on the rotor) has clear effects in changing the shape of the pattern. [ABSTRACT FROM AUTHOR]

This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the responses of mammalian retinas, this retinal model reproduces both the natural adjustment of contrast and the enhancement of object contours by parvocellular cells. Among other contributions, this paper provides an in-depth exploration of the architecture, advantages, and limitations of the model; investigates the tuning parameters of the model; and evaluates its performance when integrating a convolutional neural network and a spiking neural network into an optical character recognition (OCR) algorithm, using 40 different genuine license plate images as a case study and for testing. The results obtained demonstrate the reduction of error rates in character recognition based on convolutional neural networks (CNNs), spiking neural networks (SNNs), and OCR. It is concluded that this bio-inspired retina model offers a wide spectrum of potential applications to further explore, including motion detection, pattern recognition, and improvement of dynamic range in images, among others. [ABSTRACT FROM AUTHOR]

In this paper, the aim is to classify torque signals that are received from a 3-DOF manipulator using a pattern recognition neural network (PR-NN). The output signals of the proposed PR-NN classifier model are classified into four indicators. The first predicts that no collisions occur. The other three indicators predict collisions on the three links of the manipulator. The input data to train the PR-NN model are the values of torque exerted by the joints. The output of the model predicts and identifies the link on which the collision occurs. In our previous work, the position data for a 3-DOF robot were used to estimate the external collision torques exerted by the joints when applying collisions on each link, based on a recurrent neural network (RNN). The estimated external torques were used to design the current PR-NN model. In this work, the PR-NN model, while training, could successfully classify 56,592 samples out of 56,619 samples. Thus, the model achieved overall effectiveness (accuracy) in classifying collisions on the robot of 99.95%, which is almost 100%. The sensitivity of the model in detecting collisions on the links "Link 1, Link 2, and Link 3" was 97.9%, 99.7%, and 99.9%, respectively. The overall effectiveness of the trained model is presented and compared with other previous entries from the literature. [ABSTRACT FROM AUTHOR]

China is a large consumer of meat and meat products. People's daily diets include a variety of meat, but meat food adulteration problems are common. This paper discusses the research progress of the electronic nose and near-infrared spectroscopy in the field of meat adulteration detection. Through the study of dozens of related papers in recent years, it has been found that the use of the electronic nose and near-infrared spectroscopy for meat detection has the advantages of speed, a nondestructive nature, high sensitivity, strong quantitative analysis, high automation, a wide applicability, an improved product quality, and cost reduction over the traditional detection, but it may be limited in detecting the adulteration of a specific meat, and there are issues with the life and stability of the sensors of the electronic nose in the process of detection, along with the problems of the high requirements for the modeling of the data of near-infrared spectroscopy. This paper takes adulterated meat as the research object and briefly summarizes the detection principles of the electronic nose and near-infrared spectroscopy, as well as the types of sensors applied in the electronic nose. The research progress of the electronic nose and near-infrared detection technology in meat adulteration assessment is reviewed, the advantages and disadvantages of the two in practical application are analyzed, the classification of pattern recognition methods and their applications in meat identification are described, and the feasibility and practical significance of the joint application of the two in meat adulteration detection are envisioned. Meanwhile, the challenges faced by the two in meat detection are pointed out. [ABSTRACT FROM AUTHOR]

Bridges are crucial transportation infrastructures with significant socioeconomic impacts, necessitating continuous assessment to ensure safe operation. However, the vast number of bridges and the technical and financial challenges of maintaining permanent monitoring systems in every single bridge make the implementation of structural health monitoring (SHM) difficult for authorities. Unsupervised transfer learning, which reuses experimental or numerical data from well-known bridges to detect damage on other bridges with limited monitoring response data, has emerged as a promising solution. This solution can reduce SHM costs while ensuring the safety of bridges with similar characteristics. This paper investigates the limitations, challenges, and opportunities of unsupervised transfer learning via domain adaptation across datasets from various prestressed concrete bridges under distinct operational and environmental conditions. A feature-based transfer learning approach is proposed, where the joint distribution adaptation method is used for domain adaptation. As the main advantage, this study leverages the generalization of SHM for damage detection in prestressed concrete bridges with limited long-term monitoring data. [ABSTRACT FROM AUTHOR]

This study introduces a novel mathematical tool for representing imprecise and ambiguous data: the multi-q cubic bipolar fuzzy soft set. Building upon established bipolar fuzzy sets and soft sets, this paper fist defines the concept of multi-q cubic bipolar fuzzy sets and their fundamental properties. Mathematical operations such as complement, union, and intersection are then developed for these sets. The core contribution lies in the introduction of multi-q cubic bipolar fuzzy soft sets. This new tool allows for a more nuanced representation of imprecise data compared to existing approaches. Key operations for manipulating these sets, including complement, restriction, and expansion, are defined. The applicability of multi-q cubic bipolar fuzzy soft sets extends to various domains, including multi-criteria decision making and problem solving. Illustrative examples demonstrate the practical utility of this innovative concept. [ABSTRACT FROM AUTHOR]

Gait recognition, also known as walking pattern recognition, has expressed deep interest in the computer vision and biometrics community due to its potential to identify individuals from a distance. It has attracted increasing attention due to its potential applications and non-invasive nature. Since 2014, deep learning approaches have shown promising results in gait recognition by automatically extracting features. However, recognizing gait accurately is challenging due to the covariate factors, complexity and variability of environments, and human body representations. This paper provides a comprehensive overview of the advancements made in this field along with the challenges and limitations associated with deep learning methods. For that, it initially examines the various gait datasets used in the literature review and analyzes the performance of state-of-the-art techniques. After that, a taxonomy of deep learning methods is presented to characterize and organize the research landscape in this field. Furthermore, the taxonomy highlights the basic limitations of deep learning methods in the context of gait recognition. The paper is concluded by focusing on the present challenges and suggesting several research directions to improve the performance of gait recognition in the future. [ABSTRACT FROM AUTHOR]

Featured Application: This paper mainly applies to the parameter inversion problem in mining subsidence under the condition of lack of empirical values. In this study conducted in the Shendong mining area, this paper tackles the challenge of estimating mining subsidence parameters in the absence of empirical values. The study employs a tailored pattern recognition method specifically designed for mining subsidence in a specific working face. The goal is to determine a globally approximate optimal solution for these parameters. Subsequently, this study utilizes the approximate optimal solution as an initial exploration value and harnesses the modular vector method to obtain stable, accurate, optimal solutions for the parameters. The results of the study demonstrate the effectiveness of the improved modular vector method. In simulation tests involving the subsidence coefficient, the main influence angle tangent value, the propagation angle of mining influence, and the deviation of the inflection point, the relative errors do not exceed 1.2%, 1.9%, 1.7%, and 7.9%, respectively. Furthermore, when subjected to random errors of less than 20 mm, the relative errors for each parameter remain below 2%. Even in conditions with 200 mm gross error, the relative error for each parameter does not exceed 5.1%, indicating high precision. In an engineering example, the root mean square error of the improved modular vector method's fitting result is 64.31 mm, constituting a mere 1.79% of the maximum subsidence value. This performance surpasses that of the genetic algorithm (70.47 mm), particle swarm algorithm (72.82 mm), and simulated annealing algorithm (75.45 mm). Notably, the improved modular vector method exhibits superior stability and reduced reliance on the quantity of measured values compared to the three aforementioned algorithms. The inversion analysis of predicted parameters based on the improved modular vector method, coupled with the probability integral method, holds practical significance for enhancing the accuracy of mining subsidence prediction. [ABSTRACT FROM AUTHOR]

Craters are regarded as significant navigation landmarks during the descent and landing process in small body exploration missions for their universality. Recognizing and matching craters is a crucial prerequisite for visual and LIDAR-based navigation tasks. Compared to traditional algorithms, deep learning-based crater detection algorithms can achieve a higher recognition rate. However, matching crater detection results under various image transformations still poses challenges. To address the problem, a composite feature-matching algorithm that combines geometric descriptors and region descriptors (extracting normalized region pixel gradient features as feature vectors) is proposed. First, the geometric configuration map is constructed based on the crater detection results. Then, geometric descriptors and region descriptors are established within each feature primitive of the map. Subsequently, taking the salience of geometric features into consideration, composite feature descriptors with scale, rotation, and illumination invariance are generated through fusion geometric and region descriptors. Finally, descriptor matching is accomplished by computing the relative distances between descriptors and adhering to the nearest neighbor principle. Experimental results show that the composite feature descriptor proposed in this paper has better matching performance than only using shape descriptors or region descriptors, and can achieve a more than 90% correct matching rate, which can provide technical support for the small body visual navigation task. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) is a crucial and intricate electrical occurrence observed in various types of electrical equipment. Identifying and characterizing PDs is essential for upholding the integrity and reliability of electrical assets. This paper proposes an ensemble methodology aiming to strike a balance between the model complexity and the predictive performance in PD pattern recognition. A simple convolutional neural network (SCNN) was constructed to efficiently decrease the model parameters (quantities). A quadratic support vector machine (QSVM) was established and ensembled with the SCNN model to effectively improve the PD recognition accuracy. The input for QSVM consisted of the circular local binary pattern (CLBP) extracted from the enhanced image. A testing prototype with three types of PD was constructed and 3D phase-resolved pulse sequence (PRPS) spectrograms were measured and recorded by ultra-high frequency (UHF) sensors. The proposed methodology was compared with three existing lightweight CNNs. The experiment results from the collected dataset emphasize the benefits of the proposed method, showcasing its advantages in high recognition accuracy and relatively few mode parameters, thereby rendering it more suitable for PD pattern recognition on resource-constrained devices. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for recognizing, extracting, and processing Phase-Resolved Partial Discharge (PRPD) patterns from two-dimensional plots to identify specific defect types affecting electrical equipment without human intervention while retaining the principals that make PRPD analysis an effective diagnostic technique. The proposed method does not rely on training complex deep learning algorithms which demand substantial computational resources and extensive datasets that can pose significant hurdles for the application of on-line partial discharge monitoring. Instead, the developed Cosine Cluster Net (CCNet) model, which is an image processing pipeline, can extract and process patterns from any two-dimensional PRPD plot before employing the cosine similarity function to measure the likeness of the patterns to predefined templates of known defect types. The PRPD pattern recognition capabilities of the model were tested using several manually classified PRPD images available in the existing literature. The model consistently produced similarity scores that identified the same defect type as the one from the manual classification. The successful defect type reporting from the initial trials of the CCNet model together with the speed of the identification, which typically does not exceed four seconds, indicates potential for real-time applications. [ABSTRACT FROM AUTHOR]

Supervised discretisation is widely considered as far more advantageous than unsupervised transformation of attributes, because it helps to preserve the informative content of a variable, which is useful in classification. After discretisation, based on employed criteria, some attributes can be found irrelevant, and all their values can be represented in a discrete domain by a single interval. In consequence, such attributes are removed from considerations, and no knowledge is mined from them. The paper presents research focused on extended transformations of attribute values, thus combining supervised with unsupervised discretisation strategies. For all variables with single intervals returned from supervised algorithms, the ranges of values were transformed by unsupervised methods with varying numbers of bins. Resulting variants of the data were subjected to selected data mining techniques, and the performance of a group of classifiers was evaluated and compared. The experiments were performed on a stylometric task of authorship attribution. [ABSTRACT FROM AUTHOR]

The q-rung orthopair fuzzy sets (q-ROFSs), a novel concept for processing vague information, offer a more potent and all-encompassing method compared to traditional fuzzy sets, intuitionistic fuzzy sets, and Pythagorean fuzzy sets. The inclusion of the parameter q allows for the q-rung orthopair fuzzy sets to capture a broader range of uncertainty of information. In this paper, we present two novel distance measures for q-ROFSs inspired by the Jensen–Shannon divergence, called D J S _ 2 D and D J S _ 3 D , and we analyze some properties they satisfy, such as non-degeneracy, symmetry, boundedness, and triangular inequality. Then, the normalized distance measures, called D J S _ 2 D ˜ and D J S _ 3 D ˜ , are proposed and we verify their rationality through numerical experiments. Finally, we apply the proposed distance measures to practical scenarios, including pattern recognition and multicriteria decision-making, and the results demonstrate the effectiveness of the proposed distance measures. [ABSTRACT FROM AUTHOR]

Pedestrian Dead Reckoning (PDR) is a promising algorithm for indoor positioning. However, the accuracy of PDR degrades due to the accumulated error, especially in multi-floor buildings. This paper introduces a three-dimensional (3D) positioning method based on terrain feature matching to reduce the influence of accumulated errors in multi-floor scenes. The proposed calibration method involves two steps: motion pattern recognition and position matching-based calibration. The motion pattern recognition aims to detect different motion patterns, i.e., taking the stairs or horizontal walking, from the streaming data. Then, stair entrances and corridor corners are matched with transition points of motion patterns and pedestrian turning points, respectively. After matching, calibration is performed to eliminate the accumulated errors. By carrying out experiments on a two-floor closed-loop path with a walking distance about 145 m, it is shown that this method can effectively reduce the accumulated error of PDR, achieving accurate 3D positioning. The average error is reduced from 6.60 m to 1.37 m. [ABSTRACT FROM AUTHOR]

Non-intrusive load monitoring (NILM) has emerged as a pivotal technology in energy management applications by enabling precise monitoring of individual appliance energy consumption without the requirements of intrusive sensors or smart meters. In this technique, the load disaggregation for the individual device is accrued by the recognition of their current signals by employing machine learning (ML) methods. This research paper conducts a comprehensive comparative analysis of various ML techniques applied to NILM, aiming to identify the most effective methodologies for accurate load disaggregation. The study employs a diverse dataset comprising high-resolution electricity consumption data collected from an Estonian household. The ML algorithms, including deep neural networks based on long short-term memory networks (LSTM), extreme gradient boost (XgBoost), logistic regression (LR), and dynamic time warping with K-nearest neighbor (DTW-KNN) are implemented and evaluated for their performance in load disaggregation. Key evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of each technique in capturing the nuanced energy consumption patterns of diverse appliances. Results indicate that the XgBoost-based model demonstrates superior performance in accurately identifying and disaggregating individual loads from aggregated energy consumption data. Insights derived from this research contribute to the optimization of NILM techniques for real-world applications, facilitating enhanced energy efficiency and informed decision-making in smart grid environments. [ABSTRACT FROM AUTHOR]

Governments and health authorities emphasize the importance of early detection of breast cancer, usually through mammography, to improve prognosis, increase therapeutic options and achieve optimum outcomes. Despite technological advances and the advent of full-field digital mammography (FFDM), diagnosis of breast abnormalities on mammographic images remains a challenge due to qualitative variations in different tissue types and densities. Highly accurate computer-aided diagnosis (CADx) systems could assist in the differentiation between normal and abnormal tissue and the classification of abnormal tissue as benign or malignant. In this paper, classical, advanced fuzzy sets and fusion techniques for image enhancement were combined with three different thresholding methods (Global, Otsu and type-2 fuzzy sets threshold) and three different classifying techniques (K-means, FCM and ANFIS) for the classification of breast masses on FFDM. The aim of this paper is to identify the performance of the advanced fuzzy sets, fuzzy sets type-2 segmentation, decisions based on K-means and FCM, and the ANFIS classifier. Sixty-three combinations were evaluated on ninety-seven digital mammographic masses (sixty-five benign and thirty-two malignant). The performance of the sixty-three combinations was evaluated by estimating the accuracy, the F1 score, and the area under the curve (AUC). LH-XWW enhancement method with Otsu thresholding and FCM classifier outperformed all other combinations with an accuracy of 95.17%, F1 score of 89.42% and AUC of 0.91. This algorithm seems to offer a promising CADx system for breast cancer diagnosis on FFDM. [ABSTRACT FROM AUTHOR]

The phase-sensitive optical time-domain reflectometer (φ-OTDR) is commonly used in various industries such as oil and gas pipelines, power communication networks, safety maintenance, and perimeter security. However, one challenge faced by the φ-OTDR system is low pattern recognition accuracy. To overcome this issue, a Dendrite Net (DD)-based pattern recognition method is proposed to differentiate the vibration signals detected by the φ-OTDR system, and normalize the differential signals with the original signals for feature extraction. These features serve as input for the pattern recognition task. To optimize the DD for the pattern recognition of the feature vectors, the Variable Three-Term Conjugate Gradient (VTTCG) is employed. The experimental results demonstrate the effectiveness of the proposed method. The classification accuracy achieved using this method is 98.6%, which represents a significant improvement compared to other techniques. Specifically, the proposed method outperforms the DD, Support Vector Machine (SVM), and Extreme Learning Machine (ELM) by 7.5%, 8.6%, and 1.5% respectively. The findings of this research paper indicate that the pattern recognition method based on DD and optimized using the VTTCG can greatly enhance the accuracy of the φ-OTDR system. This improvement has important implications for various applications in industries such as pipeline monitoring, power communication networks, safety maintenance, and perimeter security. [ABSTRACT FROM AUTHOR]

In offshore drilling, accidents such as gas invasion, overflow, and kicks are unavoidable, and they can escalate into blowouts and other catastrophic events, resulting in casualties and significant economic losses. Therefore, ensuring drilling safety requires precise monitoring of gas invasion and overflow. Currently, most overflow monitoring methods used at drilling sites are based on threshold criteria. However, the monitoring parameters obtained during actual drilling operations often contain noise signals, which makes it challenging for threshold-based methods to achieve a balance between improving accuracy and minimizing false positives. This paper proposes a novel method called Pattern-Recognition-based Kick Detection (PRKD) for diagnosing overflow in offshore drilling. The PRKD method utilizes the overflow evolution process by integrating multiphase flow calculations, data filtering theory, pattern recognition theory, the Bayesian framework, and other theoretical models. By analyzing the shape and wave characteristics of the curves, PRKD effectively detects and monitors gas intrusion and overflow based on single parameters. Through case analysis, it is demonstrated that the proposed method achieves high precision in monitoring drilling overflow while maintaining a low false positive rate. By combining advanced computational techniques with pattern recognition algorithms, PRKD improves the accuracy and reliability of kick detection, enabling proactive responses to potential risks, protecting the environment and human lives, and optimizing drilling operations. The case analysis shows that by integrating the probabilistic information of pre-drilling kicks and various characteristic parameters, when the noise amplitude is less than 8 L/s, the PRKD model exhibits superior detection performance. Moreover, when the noise amplitude is 16 L/s, the PRKD model detects the continuous overflow approximately 200 s after the actual overflow occurs and predicts a 95.8% probability of overflow occurrence at the specified location, meeting the on-site requirements. The gas invasion monitoring method proposed in this paper provides accurate diagnostic results and a low false positive rate, offering valuable guidance for gas invasion monitoring in drilling operations. [ABSTRACT FROM AUTHOR]

The correct identification of partial discharge types is of great significance to the stable operation of GIS. In order to improve the recognition accuracy and result of partial discharge, and to meet the requirements of real-time monitoring of GIS equipment, this paper proposes a GIS partial discharge defect recognition model based on YOLOv5. First, the GIS partial discharge simulation experiment is established to create the dataset of partial discharge PRPD map. Then, a YOLOv5-based GIS partial discharge defect recognition model is constructed, and different training methods are used to optimize the parameters of the model. By comparing with target detection models based on other deep learning methods, such as Faster-RCNN and YOLOv4, the YOLOv5 model discussed in the paper has significantly improved the recognition efficiency and recognition accuracy, in which mAP value is 95.89% and FPS is 28.89. In addition, the model can realize the distinction and identification of multiple PD types in a single PRPD map. At last, the YOLOv5-based GIS partial discharge defect identification model is applied to the test in a 500 kV substation. The model accurately determines the type of GIS partial discharge, which verifies the accuracy and validity of the model. [ABSTRACT FROM AUTHOR]

Fermatean fuzzy sets (FFSs) serve as a nascent yet potent approach for coping with fuzziness, with their efficacy recently being demonstrated across a spectrum of practical contexts. Nevertheless, the scholarly literature remains limited in exploring the similarity and distance measures tailored for FFSs. The limited existing measures on FFSs sometimes yield counter-intuitive outcomes, which can obfuscate the accurate quantification of similarity and difference among FFSs. This paper introduces a suite of similarity and distance measures tailored for FFSs, drawing inspiration from the Tanimoto measure. We delve into the characteristics of these novel measures and offer some comparative studies with existing FFSs measures, highlighting their superior efficacy in the processing of fuzzy data from FFSs. Our proposed measures effectively rectify the counter-intuitive situations encountered with many existing measures and demonstrate a significant enhancement in differentiating between diverse FFSs. Moreover, we showcase the real-world applicability of our proposed measures through case studies in pattern recognition, medical diagnostics, and multi-attribute decision-making. [ABSTRACT FROM AUTHOR]

Machine vision, an interdisciplinary field that aims to replicate human visual perception in computers, has experienced rapid progress and significant contributions. This paper traces the origins of machine vision, from early image processing algorithms to its convergence with computer science, mathematics, and robotics, resulting in a distinct branch of artificial intelligence. The integration of machine learning techniques, particularly deep learning, has driven its growth and adoption in everyday devices. This study focuses on the objectives of computer vision systems: replicating human visual capabilities including recognition, comprehension, and interpretation. Notably, image classification, object detection, and image segmentation are crucial tasks requiring robust mathematical foundations. Despite the advancements, challenges persist, such as clarifying terminology related to artificial intelligence, machine learning, and deep learning. Precise definitions and interpretations are vital for establishing a solid research foundation. The evolution of machine vision reflects an ambitious journey to emulate human visual perception. Interdisciplinary collaboration and the integration of deep learning techniques have propelled remarkable advancements in emulating human behavior and perception. Through this research, the field of machine vision continues to shape the future of computer systems and artificial intelligence applications. [ABSTRACT FROM AUTHOR]

Illegal archaeological excavations, generally denoted as looting, is one of the most important damage factors to cultural heritage, as it upsets the human occupation stratigraphy of sites of archaeological interest. Looting identification and monitoring are not an easy task. A consolidated instrument used for the detection of archaeological features in general, and more specifically for the study of looting is remote sensing. Nevertheless, passive optical remote sensing is quite ineffective in dense vegetated areas. For these type of areas, in recent decades, LiDAR data and its derivatives have become an essential tool as they provide fundamental information that can be critical not only for the identification of unknown archaeological remains, but also for monitoring issues. Actually, LiDAR can suitably reveal grave robber devastation, even if, surprisingly, up today LiDAR has been generally unused for the identification of looting phenomenon. Consequently, this paper deals with an approach devised ad hoc for LiDAR data to detect looting. With this aim, some spatial visualization techniques and the geomorphon automatic landform extraction were exploited to enhance and extract features linked to the grave robber devastation. For this paper, the Etruscan site of San Giovenale (Northern Lazio, Italy) was selected as a test area as it is densely vegetated and was deeply plundered throughout the 20th century. Exploiting the LiDAR penetration capability, the prediction ability of the devised approach is highly satisfactory with a high rate of success, varying from 85–95%. [ABSTRACT FROM AUTHOR]

High-speed train is a large-scale electromechanical coupling equipment with a complex structure, where the coupling is interlaced between various system components, and the excitation sources are complex and diverse. Therefore, reliability has become the top priority for the safe operation of high-speed trains. As the operating mileage of high-speed trains increases, various key systems experience various degrees of performance degradation and damage failures. Moreover, it is accompanied by the influence of external environmental high interference noise and weak early fault information. Thus, those factors are serious challenges for the condition monitoring and fault diagnosis of high-speed trains. Therefore, this paper summarizes the research progress and theoretical results of the fault detection, fault isolation, and fault diagnosis methods of the key systems of high-speed trains. Finally, the paper summarizes the applicability of the main methods, discusses the challenges and opportunities of condition monitoring and fault diagnosis of high-speed trains, and looks forward to improving its diagnosis level. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for 2D pattern recognition by extracting features with the log-polar transform, the dual-tree complex wavelet transform (DTCWT), and the 2D fast Fourier transform (FFT2). Our new method is invariant to translation, rotation, and scaling of the input 2D pattern images in a multiresolution way, which is very important for invariant pattern recognition. We know that very low-resolution sub-bands lose important features in the pattern images, and very high-resolution sub-bands contain significant amounts of noise. Therefore, intermediate-resolution sub-bands are good for invariant pattern recognition. Experiments on one printed Chinese character dataset and one 2D aircraft dataset show that our new method is better than two existing methods for a combination of rotation angles, scaling factors, and different noise levels in the input pattern images in most testing cases. [ABSTRACT FROM AUTHOR]

As an important topological property for a 3D binary image, the Euler number can be computed by finding specific a voxel block with 2 × 2 × 2 voxels, named the voxel pattern, in the image. In this paper, we introduce three strategies for enhancing the efficiency of a voxel-pattern-based Euler number computing algorithm used for 3D binary images. The first strategy is taking advantage of the voxel information acquired during computation to avoid accessing voxels repeatedly. This can reduce the average number of accessed voxels from 8 to 4 for processing a voxel pattern. Therefore, the efficiency of computation will be improved. The second strategy is scanning every two rows and processing two voxel patterns simultaneously in each scan. In this strategy, only three voxels need to be accessed when a voxel pattern is processed. The last strategy is determining the voxel accessing order in the processing voxel pattern and unifying the processing of the voxel patterns that have identical Euler number increments to one group in the computation. Although this strategy can theoretically reduce the average number of voxels accessed from 8 to 4.25 for processing a voxel pattern, it is more efficient than the above two strategies for moderate- and high-density 3D binary images. Experimental results demonstrated that the three algorithms with each of our proposed three strategies exhibit greater efficiency compared to the conventional Euler number computing algorithm based on finding specific voxel patterns in the image. [ABSTRACT FROM AUTHOR]

Hybrid energy storage systems (HESS) composed of a battery and ultracapacitor (UC) provide a feasible solution to the economy of electric vehicles (EVs). To fully exploit the potential of HESSs, a power distribution strategy that can split power between the battery and UC in HESSs plays an important role. Therefore, a novel power distribution strategy and its online application are proposed in this paper. First, a new and simple power distribution model of HESSs is proposed, and the model parameters are optimized offline through particle swarm optimization (PSO). Then, a driving condition recognizer based on a neural network is introduced, and the online application of the strategy is realized by combining offline global optimization and online recognition. Compared with the traditional rule-based strategy, the strategy proposed reduces the average fluctuation of the battery current by 52.53% and the average amplitude of the battery current by 11.51%. Meanwhile, it can be seen from the results that the strategy proposed is very close to the offline PSO-based strategy proposed and exhibits good performance under all driving cycles. [ABSTRACT FROM AUTHOR]

Human activity recognition and classification are some of the most interesting research fields, especially due to the rising popularity of wearable devices, such as mobile phones and smartwatches, which are present in our daily lives. Determining head motion and activities through wearable devices has applications in different domains, such as medicine, entertainment, health monitoring, and sports training. In addition, understanding head motion is important for modern-day topics, such as metaverse systems, virtual reality, and touchless systems. The wearability and usability of head motion systems are more technologically advanced than those which use information from a sensor connected to other parts of the human body. The current paper presents an overview of the technical literature from the last decade on state-of-the-art head motion monitoring systems based on inertial sensors. This study provides an overview of the existing solutions used to monitor head motion using inertial sensors. The focus of this study was on determining the acquisition methods, prototype structures, preprocessing steps, computational methods, and techniques used to validate these systems. From a preliminary inspection of the technical literature, we observed that this was the first work which looks specifically at head motion systems based on inertial sensors and their techniques. The research was conducted using four internet databases—IEEE Xplore, Elsevier, MDPI, and Springer. According to this survey, most of the studies focused on analyzing general human activity, and less on a specific activity. In addition, this paper provides a thorough overview of the last decade of approaches and machine learning algorithms used to monitor head motion using inertial sensors. For each method, concept, and final solution, this study provides a comprehensive number of references which help prove the advantages and disadvantages of the inertial sensors used to read head motion. The results of this study help to contextualize emerging inertial sensor technology in relation to broader goals to help people suffering from partial or total paralysis of the body. [ABSTRACT FROM AUTHOR]

This paper presents the implementation of an intelligent real-time single-channel electromyography (EMG) signal classifier based on open-source hardware. The article shows the experimental design, analysis, and implementation of a solution to identify four muscle movements from the forearm (extension, pronation, supination, and flexion), for future applications in transradial active prostheses. An EMG signal acquisition instrument was developed, with a 20–450 Hz bandwidth and 2 kHz sampling rate. The signals were stored in a Database, as a multidimensional array, using a desktop application. Numerical and graphic analysis approaches for discriminative capacity were proposed for feature analysis and four feature sets were used to feed the classifier. Artificial Neural Networks (ANN) were implemented for time-domain EMG pattern recognition (PR). The system obtained a classification accuracy of 98.44% and response times per signal of 8.522 ms. Results suggest these methods allow us to understand, intuitively, the behavior of user information. [ABSTRACT FROM AUTHOR]

Computational thinking (CT) has become one of the critical goals of teaching CS programming courses. Computational skills consist of skills taken in a computational form in learning programming and dealing with daily life. More research adopted games to teach CT skills. This paper investigated two games, Little Alchemy 2 and Dr. Sudoku, to promote CS students' CT skills and applied international Bebras tests to measure their CT skills. The results showed that CT skills in problem decomposition and pattern recognition could be improved via digital games. Thus, this study contributes to computing education using available digital games to promote CS college students' CT abilities. [ABSTRACT FROM AUTHOR]

Binary memristor crossbars have great potential for use in brain-inspired neuromorphic computing. The complementary crossbar array has been proposed to perform the Exclusive-NOR function for neuromorphic pattern recognition. The single crossbar obtained by shortening the Exclusive-NOR function has more advantages in terms of power consumption, area occupancy, and fault tolerance. In this paper, we present the impact of data density on the single memristor crossbar architecture for neuromorphic image recognition. The impact of data density on the single memristor architecture is mathematically derived from the reduced formula of the Exclusive-NOR function, and then verified via circuit simulation. The complementary and single crossbar architectures are tested by using ten 32 × 32 images with different data densities of 0.25, 0.5, and 0.75. The simulation results showed that the data density of images has a negative effect on the single memristor crossbar architecture while not affecting the complementary memristor crossbar architecture. The maximum output column current produced by the single memristor crossbar array decreases as data density decreases while the complementary memristor crossbar array architecture provides stable maximum output column currents. When recognizing images with data density as low as 0.25, the maximum output column currents of the single memristor crossbar architecture is reduced four-fold compared with the maximum currents from the complementary memristor crossbar architecture. This reduction causes the Winner-take-all circuit to work incorrectly and will reduce the recognition rate of the single memristor crossbar architecture. These simulation results show that the single memristor crossbar architecture has more advantages compared with the complementary crossbar architecture when the images do have not many different densities, and none of the images have very low densities. This work also indicates that the single crossbar architecture must be improved by adding a constant term to deal with images that have low data densities. These are valuable case studies for archiving the advantages of single memristor crossbar architecture in neuromorphic computing applications. [ABSTRACT FROM AUTHOR]

In this paper, a novel feature generator framework is proposed for handwritten digit classification. The proposed framework includes a two-stage cascaded feature generator. The first stage is based on principal component analysis (PCA), which generates projected data on principal components as features. The second one is constructed by a partially trained neural network (PTNN), which uses projected data as inputs and generates hidden layer outputs as features. The features obtained from the PCA and PTNN-based feature generator are tested on the MNIST and USPS datasets designed for handwritten digit sets. Minimum distance classifier (MDC) and support vector machine (SVM) methods are exploited as classifiers for the obtained features in association with this framework. The performance evaluation results show that the proposed framework outperforms the state-of-the-art techniques and achieves accuracies of 99.9815% and 99.9863% on the MNIST and USPS datasets, respectively. The results also show that the proposed framework achieves almost perfect accuracies, even with significantly small training data sizes. [ABSTRACT FROM AUTHOR]

In this paper, force sensor signals are classified using a pattern recognition neural network (PRNN). The signals are classified to show if there is a collision or not. In our previous work, the joints positions of a 2-DOF robot were used to estimate the external force sensor signal, which was attached at the robot end-effector, and the external joint torques of this robot based on a multilayer feedforward NN (MLFFNN). In the current work, the estimated force sensor signal and the external joints' torques from the previous work are used as the inputs to the proposed designed PRNN, and its output is whether a collision is found or not. The designed PRNN is trained using a scaled conjugate gradient backpropagation algorithm and tested and validated using different data from the training one. The results prove that the PRNN is effective in classifying the force signals. Its effectiveness for classifying the collision cases is 92.8%, and for the non-collisions cases is 99.4%. Therefore, the overall efficiency is 99.2%. The same methodology and work are repeated using a PRNN trained using another algorithm, which is the Levenberg–Marquardt (PRNN-LM). The results using this structure prove that the PRNN-LM is also effective in classifying the force signals, and its overall effectiveness is 99.3%, which is slightly higher than the first PRNN. Finally, a comparison of the effectiveness of the proposed PRNN and PRNN-LM with other previous different classifiers is included. This comparison shows the effectiveness of the proposed PRNN and PRNN-LM. [ABSTRACT FROM AUTHOR]

Human activity recognition has been widely used to monitor users during physical activities. By embedding a pre-trained model into wearable devices with an inertial measurement unit, it is possible to identify the activity being executed, count steps and activity duration time, and even predict when the user should hydrate himself. Despite these interesting applications, these approaches are limited by a set of pre-trained activities, making them unable to learn new human activities. In this paper, we introduce a novel approach for generating runtime models to give the users feedback that helps them to correctly perform repetitive physical activities. To perform a distributed analysis, the methodology focuses on applying the proposed method to each specific body segment. The method adopts the Restricted Boltzmann Machine to learn the patterns of repetitive physical activities and, at the same time, provides suggestions for adjustments if the repetition is not consistent with the model. The learning and the suggestions are both based on inertial measurement data mainly considering movement acceleration and amplitude. The results show that by applying the model's suggestions to the evaluation data, the adjusted output was up to 3.68x more similar to the expected movement than the original data. [ABSTRACT FROM AUTHOR]

With the recent growth of the Internet of Things (IoT) and the demand for faster computation, quantized neural networks (QNNs) or QNN-enabled IoT can offer better performance than conventional convolution neural networks (CNNs). With the aim of reducing memory access costs and increasing the computation efficiency, QNN-enabled devices are expected to transform numerous industrial applications with lower processing latency and power consumption. Another form of QNN is the binarized neural network (BNN), which has 2 bits of quantized levels. In this paper, CNN-, QNN-, and BNN-based pattern recognition techniques are implemented and analyzed on an FPGA. The FPGA hardware acts as an IoT device due to connectivity with the cloud, and QNN and BNN are considered to offer better performance in terms of low power and low resource use on hardware platforms. The CNN and QNN implementation and their comparative analysis are analyzed based on their accuracy, weight bit error, RoC curve, and execution speed. The paper also discusses various approaches that can be deployed for optimizing various CNN and QNN models with additionally available tools. The work is performed on the Xilinx Zynq 7020 series Pynq Z2 board, which serves as our FPGA-based low-power IoT device. The MNIST and CIFAR-10 databases are considered for simulation and experimentation. The work shows that the accuracy is 95.5% and 79.22% for the MNIST and CIFAR-10 databases, respectively, for full precision (32-bit), and the execution time is 5.8 ms and 18 ms for the MNIST and CIFAR-10 databases, respectively, for full precision (32-bit). [ABSTRACT FROM AUTHOR]

Signal recognition accuracy and recognition time are the two most important parameters of pattern recognition in a fiber optic vibration sensing system. To obtain high recognition accuracy and short recognition time, this paper optimized the VGG16 algorithm and carried out VGG16-1D and VGG16-2D recognition on big data signals generated by a Michelson–Sagnac interferometric vibration sensor system. The results indicate that VGG16-1D has a higher accuracy of 98.44% and a shorter recognition time of 0.03 s. The proposed method is a more accurate and faster pattern recognition method for big data signals from optical fiber vibration sensing systems, which is helpful in promoting further applications of optical fiber sensing systems. [ABSTRACT FROM AUTHOR]

Recently, several arbitrary-scale models have been proposed for single-image super-resolution. Furthermore, the importance of arbitrary-scale single image super-resolution is emphasized for applications such as satellite image processing, HR display, and video-based surveillance. However, the baseline integer-scale model must be retrained to fit the existing network, and the learning speed is slow. This paper proposes a network to solve these problems, processing super-resolution by restoring the high-frequency information lost in the remaining arbitrary-scale while maintaining the baseline integer scale. The proposed network extends an integer-scaled image to an arbitrary-scale target in the discrete cosine transform spectral domain. We also modulate the high-frequency restoration weights of the depthwise multi-head attention to use memory efficiently. Finally, we demonstrate the performance through experiments with existing state-of-the-art models and their flexibility through integration with existing integer-scale models in terms of peak signal-to-noise ratio (PSNR) and similarity index measure (SSIM) scores. This means that the proposed network restores high-resolution (HR) images appropriately by improving the image sharpness of low-resolution (LR) images. [ABSTRACT FROM AUTHOR]

Mechanical defects and partial discharge (PD) defects can appear in the indoor switchgear of substations or distribution stations, making the switchgear a safety hazard. However, traditional acoustic methods detect and identify these two types of defects separately, ignoring the general recognition of audio signals. In addition, the process of using testing equipment is complex and costly, which is not conducive to timely testing and widespread application. To assist technicians in making a quick preliminary diagnosis of defect types for switchgear, improve the efficiency of the subsequent overhaul, and reduce the cost of detection, this paper proposes a general audio recognition method for identifying defects in switchgear using a smartphone. Using this method, we can analyze and identify audio and video files recorded with smartphones and synchronously distinguish background noise, mechanical vibration, and PD audio signals, which have good applicability within a certain range. When testing the feasibility of using smartphones to identify three types of audio signal, through characterizing 12 sets of live audio and video files provided by technicians, it was found that there were similarities and differences in these characteristics, such as the autocorrelation, density, and steepness of the waveforms in the time domain, and the band energy and harmonic components of the frequency spectrum, and new combinations of features were proposed as applicable. To compare the recognition performance for features in the time domain, frequency band energy, Mel-frequency cepstral coefficient (MFCC), and this method, feature vectors were input into a support vector machine (SVM) for a recognition test, and the recognition results showed that the the present method had the highest recognition accuracy. Finally, a set of mechanical defects and PD defects were set up for a switchgear, for practical verification, which proved that this method was general and effective. [ABSTRACT FROM AUTHOR]

Some fundamental visual features have been found to be fully extracted before reaching the cerebral cortex. We focus on direction-selective ganglion cells (DSGCs), which exist at the terminal end of the retinal pathway, at the forefront of the visual system. By utilizing a layered pathway composed of various relevant cells in the early stage of the retina, DSGCs can extract multiple motion directions occurring in the visual field. However, despite a considerable amount of comprehensive research (from cells to structures), a definitive conclusion explaining the specific details of the underlying mechanisms has not been reached. In this paper, leveraging some important conclusions from neuroscience research, we propose a complete quantified model for the retinal motion direction selection pathway and elucidate the global motion direction information acquisition mechanism from DSGCs to the cortex using a simple spiking neural mechanism. This mechanism is referred to as the artificial visual system (AVS). We conduct extensive testing, including one million sets of two-dimensional eight-directional binary object motion instances with 10 different object sizes and random object shapes. We also evaluate AVS's noise resistance and generalization performance by introducing random static and dynamic noises. Furthermore, to thoroughly validate AVS's efficiency, we compare its performance with two state-of-the-art deep learning algorithms (LeNet-5 and EfficientNetB0) in all tests. The experimental results demonstrate that due to its highly biomimetic design and characteristics, AVS exhibits outstanding performance in motion direction detection. Additionally, AVS possesses biomimetic computing advantages in terms of hardware implementation, learning difficulty, and parameter quantity. [ABSTRACT FROM AUTHOR]

The magnetic method is one of the very few nondestructive testing (NDT) techniques that provide the possibility to conduct area tests of reinforced concrete (RC) structures in a fast, cheap, and straightforward way. This paper aims to present a new approach to the simultaneous identification of rebars' diameter, alloy class, and thickness of the concrete cover tested with this method. Since rebars from different manufacturers may have different electromagnetic properties (standardization only for mechanical properties), preparing an effective and universal database is impossible. In this work, ACO decomposition is proposed, a new attributes extraction method designed to identify object parameters, even if it is impossible to collect a suitable training database (by pattern recognition and analysis of the deviation). Conducted tests prove that the ACO method enables accurate reflection of the waveform shape and limitation of attributes number to three or fewer (avoiding the curse of dimensionality). These properties, combined with the ability to analyze spatial components of magnetic induction (which only magnetic sensors provide), make the complex task of identification of three parameters more straightforward and the separation between the results received for different classes larger. This article presents the measurement results and the whole identification process. [ABSTRACT FROM AUTHOR]

The tendency towards thin insulation layers in traction battery systems presents new challenges regarding insulation quality and service life. Phase-resolved DC partial discharge diagnostics can help to identify defects. Furthermore, different root causes are characterized by different patterns. However, to industrialize the procedure, there is the need for an automatic pattern recognition system. This paper shows how methods from computer vision can be applied to DC partial discharge diagnostics. The derived system is self-learning, needs no tedious manual calibration, and can identify defects within a matter of seconds. Thus, the combination of computer vision and phase-resolved DC partial discharge diagnostics provides an industrializable system for detecting insulation faults and identifying their root causes. [ABSTRACT FROM AUTHOR]

The recognition of human activities using vision-based techniques has become a crucial research field in video analytics. Over the last decade, there have been numerous advancements in deep learning algorithms aimed at accurately detecting complex human actions in video streams. While these algorithms have demonstrated impressive performance in activity recognition, they often exhibit a bias towards either model performance or computational efficiency. This biased trade-off between robustness and efficiency poses challenges when addressing complex human activity recognition problems. To address this issue, this paper presents a computationally efficient yet robust approach, exploiting saliency-aware spatial and temporal features for human action recognition in videos. To achieve effective representation of human actions, we propose an efficient approach called the dual-attentional Residual 3D Convolutional Neural Network (DA-R3DCNN). Our proposed method utilizes a unified channel-spatial attention mechanism, allowing it to efficiently extract significant human-centric features from video frames. By combining dual channel-spatial attention layers with residual 3D convolution layers, the network becomes more discerning in capturing spatial receptive fields containing objects within the feature maps. To assess the effectiveness and robustness of our proposed method, we have conducted extensive experiments on four well-established benchmark datasets for human action recognition. The quantitative results obtained validate the efficiency of our method, showcasing significant improvements in accuracy of up to 11% as compared to state-of-the-art human action recognition methods. Additionally, our evaluation of inference time reveals that the proposed method achieves up to a 74× improvement in frames per second (FPS) compared to existing approaches, thus showing the suitability and effectiveness of the proposed DA-R3DCNN for real-time human activity recognition. [ABSTRACT FROM AUTHOR]

Pattern recognition of lower-limb movements based on mechanomyography (MMG) signals has a certain application value in the study of wearable rehabilitation-training devices. In this paper, MMG feature selection methods based on a chameleon swarm algorithm (CSA) and a grasshopper optimization algorithm (GOA) are proposed for the pattern recognition of knee and ankle movements in the sitting and standing positions. Wireless multichannel MMG acquisition systems were designed and used to collect MMG movements from four sites on the subjects thighs. The relationship between the threshold values and classification accuracy was analyzed, and comparatively high recognition rates were obtained after redundant information was eliminated. When the threshold value rose, the recognition rates from the CSA fluctuated within a small range: up to 88.17% (sitting position) and 90.07% (standing position). However, the recognition rates from the GOA drop dramatically when increasing the threshold value. The comparison results demonstrated that using a GOA consumes less time and selects fewer features, while a CSA gives higher recognition rates of knee and ankle movements. [ABSTRACT FROM AUTHOR]

A novel instance-based algorithm for pattern classification is presented and evaluated in this paper. This new method is motivated by the challenge of pattern classifications where only limited and/or noisy training data are available. For every classification, the proposed system transforms the query data and the training templates based on their distributions in the feature space. One of the major novelties of the proposed method is the concept of template reconstruction enabling improved performance with limited training data. The technique is compared with similar algorithms and evaluated using both the image and time-series modalities to demonstrate its effectiveness and versatility. Two public image databases, FASHION-MNIST and CIFAR-10, were used to test its effectiveness for the classification of images using small amounts of training samples. An average classification improvement of 2~3% was observed while using a small subset of the training database, compared to the performances achieved by state-of-the-art techniques using the full datasets. To further explore its capability in solving more challenging classification problems such as non-stationary time-series electroencephalography (EEG) signals, a clinical grade 64-electrode EEG database, as well as a low-quality (high-noise level) EEG database, obtained using a low-cost system equipped with a single dry sensor, have also been used to test the algorithm. Adaptive reconstruction of the feature instances has been seen to have substantially improved class separation and matching performance for both still images and time-series signals. In particular, the method is found to be effective for the classification of noisy non-stationary data with limited training data volumes, indicating its potential suitability for a wide range of applications. [ABSTRACT FROM AUTHOR]

Measuring the similarity between two objects and classifying them on the basis of their resemblance level has been a fundamental tool of the human mind. In an intuitionistic fuzzy environment, we find researchers that have attempted to generalize the fuzzy versions of similarity measures between fuzzy sets to their intuitionistic forms for measuring the level of similarity between the intuitionistic fuzzy sets. Though many different forms of intuitionistic fuzzy similarity measures have been introduced so far, a comparative study reveals that among all these measures, it is difficult for one to claim the existence of a single measure that alone has the capability to recognize every single pattern assigned to it. This paper presents a four-parametric family of similarity measures for intuitionistic fuzzy sets employing weighted average cardinality and intuitionistic fuzzy t-norms along with their dual t-co-norms. A combinational variation of the parameters involved in this family resulted in some of the famous similarity measures having an intuitionistic version. These new measures are analyzed for their properties, and they have shown some remarkable results. Moreover, the proposed family has a practical advantage over the other measures in the existing literature because every member not only possesses the capability of successfully recognizing any pattern assigned to it up to a fine accuracy but also a choice of different t-norms and co-norms within a single measure equips it with the capacity to portray different mindsets of a decision-maker who, besides being unbiased, can possess a deep psychology of being an optimist, pessimist, or possessing neutral behavior in general. Lastly, the members of this family are tested for their feasibility in a sensitive medical decision process of detection of COVID-19. [ABSTRACT FROM AUTHOR]

Vision-based human activity recognition (HAR) has emerged as one of the essential research areas in video analytics. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize complex human actions from video streams. These deep learning algorithms have shown impressive performance for the video analytics task. However, these newly introduced methods either exclusively focus on model performance or the effectiveness of these models in terms of computational efficiency, resulting in a biased trade-off between robustness and computational efficiency in their proposed methods to deal with challenging HAR problem. To enhance both the accuracy and computational efficiency, this paper presents a computationally efficient yet generic spatial–temporal cascaded framework that exploits the deep discriminative spatial and temporal features for HAR. For efficient representation of human actions, we propose an efficient dual attentional convolutional neural network (DA-CNN) architecture that leverages a unified channel–spatial attention mechanism to extract human-centric salient features in video frames. The dual channel–spatial attention layers together with the convolutional layers learn to be more selective in the spatial receptive fields having objects within the feature maps. The extracted discriminative salient features are then forwarded to a stacked bi-directional gated recurrent unit (Bi-GRU) for long-term temporal modeling and recognition of human actions using both forward and backward pass gradient learning. Extensive experiments are conducted on three publicly available human action datasets, where the obtained results verify the effectiveness of our proposed framework (DA-CNN+Bi-GRU) over the state-of-the-art methods in terms of model accuracy and inference runtime across each dataset. Experimental results show that the DA-CNN+Bi-GRU framework attains an improvement in execution time up to 167× in terms of frames per second as compared to most of the contemporary action-recognition methods. [ABSTRACT FROM AUTHOR]

Speech is the primary way via which most humans communicate. Computers facilitate this transfer of information, especially when people interact with databases. While some methods to manipulate and interpret speech date back many decades (e.g., Fourier analysis), other processing techniques were developed late last century (e.g., linear predictive coding and hidden Markov models). Nonetheless, the last 25 years have seen major advances leading to the wide acceptance of computer-based speech processing, e.g., cellular telephones and real-time online conversations. This paper reviews older techniques and recent methods that focus largely on artificial neural networks. The major highlights in speech research are examined, without delving into mathematical detail, while giving insight into the research choices that have been made. The focus of this work is to understand how and why the discussed methods function well. [ABSTRACT FROM AUTHOR]

Microphone identification is a crucial challenge in the field of digital audio forensics. The ability to accurately identify the type of microphone used to record a piece of audio can provide important information for forensic analysis and crime investigations. In recent years, transformer-based deep-learning models have been shown to be effective in many different tasks. This paper proposes a system based on a transformer for microphone identification based on recorded audio. Two types of experiments were conducted: one to identify the model of the microphones and another in which identical microphones were identified within the same model. Furthermore, extensive experiments were performed to study the effects of different input types and sub-band frequencies on system accuracy. The proposed system is evaluated on the Audio Forensic Dataset for Digital Multimedia Forensics (AF-DB). The experimental results demonstrate that our model achieves state-of-the-art accuracy for inter-model and intra-model microphone classification with 5-fold cross-validation. [ABSTRACT FROM AUTHOR]

This paper introduces a new spike activation function (SPKAF) or spike membership function for fuzzy adaptive neurons (FAN), developed for decoding spatiotemporal information with spikes, optimizing digital signal processing. A solution with the adaptive network-based fuzzy inference system (ANFIS) method is proposed and compared with that of the FAN-SPKAF model, obtaining very precise simulation results. Stability analysis of systems models is presented. An application to voice recognition using solfeggio syllables in Spanish is performed experimentally, comparing the methods of FAN-step activation function (STEPAF)-SPKAF, Augmented Spiking Neuron Model, and Augmented FAN-STEPAF-SPKAF, achieving very good results. [ABSTRACT FROM AUTHOR]

The process of forming a vector-field model of flat images of group point objects, with various field-forming functions, is considered in this paper. Algorithms for recognizing group point objects in the presence of false and missing point objects are proposed. The quality of the recognition of group point objects by the proposed algorithms is also evaluated. [ABSTRACT FROM AUTHOR]