Search

Kinect, with its intrinsic and accessible human motion capture capabilities, found widespread application in real-world scenarios such as rehabilitation therapy and robot control. Consequently, a thorough analysis of its previously under-examined motion capture accuracy is of paramount importance to mitigate the risks potentially arising from recognition errors in practical applications. This study employs a high-precision, marker-based motion capture system to generate ground truth human pose data, enabling an evaluation of Azure Kinect's performance across a spectrum of tasks, which include both static postures and dynamic movement behaviors. Specifically, the cosine similarity for skeletal representation is employed to assess pose estimation accuracy from an application-centric perspective. Experimental results reveal that factors such as the subject's distance and orientation relative to the Kinect, as well as self-occlusion, exert a significant influence on the fidelity of Azure Kinect's human posture recognition. Optimal testing recommendations are derived based on the observed trends. Furthermore, a linear fitting analysis between the ground truth data and Azure Kinect's output suggests the potential for performance optimization under specific conditions. This research provides valuable insights for the informed deployment of Kinect in applications demanding high-precision motion recognition. [ABSTRACT FROM AUTHOR]

Human facial emotion recognition (FER) system has become an active research area and it has attracted various research communities for its wide ranging and promising applications especially in the cybersecurity field. Recognizing various facial expressions corresponding to the emotional forms is considered as a significant task in the system of FER. Typically, the automated system of FER consists of two major and important steps like feature extraction, and facial emotion recognition. In this work, initially the input data is acquired and the features are extracted from the input facial image with the use of Fuzzy Eigen Weighted based feature extraction model (FEW‐FE). Among the extracted features, an optimal and best features are selected by means of feature selection technique, which employs Chaotic Spider Monkey Optimization algorithm (CSMO) so as to find best fitness function solution. The use of this optimization technique for the feature subset selection aids the enhancement of classifier performance. Then, the recognition process is carried using Dual‐attention residual U‐Net classifier framework. The performance evaluation of this proposed model is carried over three input datasets considered such as CK+, FER2013, and JAFFE in terms of recognition accuracy, precision, recall, and F‐measure. The comparison is made for the feature extraction and classifier model with that of various existing methodologies which shows the effectiveness of proposed system over other traditional schemes. This proposed design is applicable in the cybersecurity system to detect a person's emotional state from their expression. [ABSTRACT FROM AUTHOR]

Handwritten text recognition (HTR) technology has brought about a revolution in the way handwritten data is converted and analyzed. This proposed work focuses on developing a HTR system using deep learning through advanced deep learning architecture and techniques. The aim is to create a model for real-time analysis and detection of handwritten texts. The proposed deep learning architecture that is convolutional neural networks (CNNs), is investigated and implemented with tools like OpenCV and TensorFlow. The model is trained on large handwritten datasets to enhance recognition accuracy. The system’s performance is evaluated based on accuracy, precision, real-time capabilities, and potential for deployment on platforms like Raspberry Pi. The actual outcome is a robust HTR system that can convert handwritten text to digital formats accurately. The developed system has achieved a high accuracy rate of 91.58% in recognizing English alphabets and digits and outperformed other models with 81.77% mAP, 78.85% precision, 79.32% recall, 79.46% F1-Score, and 82.4% receiver operating characteristic (ROC). This research contributes to the advancement of HTR technology by enhancing its precision and utility. [ABSTRACT FROM AUTHOR]

A customer information system (CIS) is a crucial component of a customer relationship management (CRM) system. The CIS collects, stores, and manages customer data to enhance the customer experience and sales. Deep learning technology has been used to develop facial expression recognition systems that can accurately identify and analyze facial expressions. By integrating facial expression recognition deep learning into a CIS for CRM, businesses can gain a deeper understanding of the emotions and behavior of the customers, allowing them to provide more personalized experiences. The data collected by the CIS can then be used to personalize marketing campaigns, tailor product recommendations, and improve customer service interactions. The integration of facial expression recognition deep learning into a CIS for CRM has the potential to revolutionize the way businesses interact with their customers. This paper constructed a Feature Fusion Deep Multi-Layer Classification (FFDMLC) model for facial expression recognition for the CIS system. With FFDMLC model comprises the feature-fusion model in face recognition. The propsoed FFDMLC approach fuses various features and estimates the feature fusion model. The FFDMLC model employs deep learning for feature computation and expression classification in individuals. The hyperparameters of this proposed method are optimized using the COOT optimization method. This process optimizes reaction conditions, leading to increased yields, minimized by-products, and improved overall efficiency. The CIS model uses the facial expression recognition system for the computation of facial features in the video sequences. The proposed FFDMLC model is evaluated based on the consideration of two datasets such asCK + and the FER2013 dataset, which also exhibits a higher recognition rate of 99.93% for the understanding opinion of the customers. [ABSTRACT FROM AUTHOR]

This article proposes a new algorithm aimed at improving accuracy when identifying communication signals using artificial intelligence applications. The proposed research algorithm focuses on analog and digitally modulated signals commonly used in communication systems. The proposed algorithm includes two main steps: Step one is used to extract signal features using the analytic Wavelet transform. A deep learning artificial network is designed in step 2 to identify the above signals. The effectiveness of the proposed algorithm is evaluated on simulated signals in MATLAB and compared with common feature extraction methods: short-time Fourier transform, Wigner-Ville distribution, and other networks such as SqueezeNet, AlexNet. The simulation results show that the proposed algorithm achieves 92% recognition accuracy, which is higher than STFT and WVD methods. In comparison with current networks, the proposed method has a 1.5 time-reduced training time and equivalent performance. [ABSTRACT FROM AUTHOR]

The doubly-fed induction generators (DFIG) are critical devices in the field of wind energy generation, Ensuring the stable operation of it is of paramount importance. Aiming at the multi-level classification problem of DFIG bearing faults, a parameter-optimized variational mode decomposition- convolutional neural network- bidirectional long short-term memory (VMD-CNN-BiLSTM) fault diagnosis model was proposed. Firstly, an improved variant of the sparrow search algorithm (SSA), known as the osprey-Cauchy-sparrow search algorithm (OCSSA), was used to optimize the penalty factor and mode components of the variational mode decomposition (VMD). The OCSSA algorithm combined the strengths of the osprey algorithm, the Cauchy mutation strategy and the sparrow algorithm, providing powerful parameter search capabilities to obtain more accurate frequency features. Then, convolutional neural network (CNN) was used to extract temporal and spectral features from the signals, which were fused together. Finally, a bidirectional long short-term memory (BiLSTM) network was used to learn the sequential fault patterns and perform the multi-level fault classification task. The research results show that the OCSSA-optimized VMD-CNN-BiLSTM model shows significant advantages in identifying multi-level bearing faults, achieving an average accuracy rate of 98. 36%. Comparing with other models such as CNN-LSTM, CNN-BiLSTM and VMD-BiLSTM, the proposed model shows superior fault diagnosis performance, excellent generalization ability and fast computation speed. This result confirms the effectiveness of the proposed model in multi-level classification and identification of bearing faults in doubly-fed induction generators. In addition, it is found to be suitable for online monitoring and intelligent diagnosis, which is of great practical value in achieving efficient and reliable wind power generation. [ABSTRACT FROM AUTHOR]

Currently, multi-layer deep convolutional networks are mostly used for field weed recognition to extract and identify target features. However, in practical application scenarios, they still face challenges such as insufficient recognition accuracy, a large number of model parameters, and slow detection speed. In response to the above problems, using chickweed as the identification object, a weed identification model based on improved YOLOv5s was proposed. Firstly, the Squeeze-and-Excitation Module (SE) and Convolutional Block Attention Module (CBAM) were added to the model's feature extraction network to improve the model's recognition accuracy; secondly, the Ghost convolution lightweight feature fusion network was introduced to effectively identify the volume, parameter amount, and calculation amount of the model, and make the model lightweight; finally, we replaced the loss function in the original target bounding box with the Efficient Intersection over Union (EloU) loss function to further improve the detection performance of the improved YOLOv5s model. After testing, the accuracy of the improved YOLOv5s model was 96.80%, the recall rate was 94.00%, the average precision was 93.20%, and the frame rate was 14.01 fps, which were improved by 6.6%, 4.4%, 1.0%, and 6.1%, respectively, compared to the original YOLOv5s model. The model volume was 9.6 MB, the calculation amount was 13.6 GB, and the parameter amount was 5.9 MB, which decreased by 29.4%, 14.5%, and 13.2% compared with the original YOLOv5s model, respectively. This model can effectively distinguish chickweed between crops. This research can provide theoretical and technical support for efficient identification of weeds in complex field environments. [ABSTRACT FROM AUTHOR]

With the construction and development of rural roads, the timely identification and treatment of rural road pavement diseases has become an important task. Traditional methods have certain limitations in accuracy and efficiency, so it is necessary to explore new technical means to improve the identification of rural road pavement diseases. This paper mainly focuses on the research of automatic detection technology for road surface diseases on rural roads. The results indicate that using computer vision technology for the diagnosis of rural road diseases is an efficient and accurate diagnostic method. The results show that the recognition rate of the machine vision recognition system is 94.1%, which is 89% higher than traditional recognition methods. On this basis, a new detection algorithm was proposed, which achieved a detection efficiency of 89.6%, much higher than traditional detection algorithms. [ABSTRACT FROM AUTHOR]

The smooth operation of graph convolution network leads to the problem that it can not capture deep information through deep network stacking. In order to solve this problem, a multi-layer graph convolution attention fusion network (MGCAN) suitable for semi-supervised learning classification of rolling bearing fault diagnosis was proposed. Firstly, the frequency domain graphing method was adopted to transform data into a graph model, the inherent structural information within the data was captured. The constructed graph data was inputted into the network, and feature information was extracted layer by layer, progressively deepening the network's understanding of data features from shallow to deep layers. Then, each layer of graph convolution information was orderly concatenated. Meanwhile, the graph attention mechanism was incorporated, the network was enabled to automatically focus on the important information for classification tasks. As a result, the performance and robustness of the network were enhanced. Finally, through iterative learning, the model parameters were continuously optimized, fault information was accurately identified by the networks, and multiple experiments on rolling bearings under different working conditions was conducted. This method was compared with traditional deep learning methods. The research results indicate that even with only 10% of labeled data, the network can still achieve an accuracy of over 88%, and it is applicable to various conditions such as uniform speed and variable speed. The results confirm that, after employing an appropriate method to retain useful information in multi-layer graph convolutions, deep graph convolutional networks can be a powerful tool for diagnosing faults in rolling bearings. [ABSTRACT FROM AUTHOR]

The accurate detection of ancient artifacts is very crucial in recognizing and tracking the origin of these relics. The methodologies used in engraving characters onto these objects are different from the ones used in the modern era, prompting the need to develop tools that are accurately tailored to detect these characters. The challenge encountered in developing an object character recognition model for this purpose is the lack of sufficient data needed to train these models. In this work, we propose Styleformer-ART to augment the ancient artifact character images. To show the performance of Styleformer-ART, we compared Styleformer-ART with different state-of-the-art data augmentation techniques. To make a conclusion on the best augmentation method for this special dataset, we evaluated all the augmentation methods employed in this work using the Frétchet inception distance (FID) score between the reference images and the generated images. The methods were also evaluated on the recognition accuracy of a CNN model. The Styleformer-ART model achieved the best FID score of 210.72, and Styleformer-ART-generated images achieved a recognition accuracy with the CNN model of 84%, which is better than all the other reviewed image-generation models. [ABSTRACT FROM AUTHOR]

Nested named entity recognition has been widely used in natural language processing, information extraction and other fields. However, the multiple boundaries of nested named entities make the recognition of single entity face great challenges. This article used the information in the knowledge graph to extract and annotate entities in the Chinese nested named entity recognition algorithm, and built a new named entity recognition model based on this. Experimental results showed that this article applied the knowledge graph to the Chinese nested named entity recognition task, and its accuracy could reach up to 95.3%, which has obvious advantages in complex structure processing, relationship extraction and entity links. [ABSTRACT FROM AUTHOR]

This research proposes a novel approach for Tamil Handwritten Character Recognition (THCR) that combines feature selection and ensemble learning techniques. The Tamil script is complex and highly variable, requiring a robust and accurate recognition system. Feature selection is used to reduce dimensionality while preserving discriminative features, improving classification performance and reducing computational complexity. Several feature selection methods are compared, and individual classifiers (support vector machines, neural networks, and decision trees) are evaluated through extensive experiments. Ensemble learning techniques such as bagging, and boosting are employed to leverage the strengths of multiple classifiers and enhance recognition accuracy. The proposed approach is evaluated on the HP Labs Dataset, achieving an impressive 95.56% accuracy using an ensemble learning framework based on support vector machines. The dataset consists of 82,928 samples with 247 distinct classes, contributed by 500 participants from Tamil Nadu. It includes 40,000 characters with 500 user variations. The results surpass or rival existing methods, demonstrating the effectiveness of the approach. The research also offers insights for developing advanced recognition systems for other complex scripts. Future investigations could explore the integration of deep learning techniques and the extension of the proposed approach to other Indic scripts and languages, advancing the field of handwritten character recognition. [ABSTRACT FROM AUTHOR]

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%. [ABSTRACT FROM AUTHOR]

In repeated-event paradigms where participants are asked to recall details of a sequence of similar instances they viewed/experienced previously, more accurate details are typically recalled from the first and final instances (i.e., long-term primacy and recency effects). Participants likely encode distinct attributes of details of the boundary instances that subsequently facilitate source monitoring. To date, most repeated event research has measured memory performance via free-/cued-recall paradigms; we examined delayed memory for repeated events using the recognition paradigm. In two preregistered experiments, participants viewed four videos, and after a delay completed a recognition task. In Experiment 1 (N = 168, between-subjects), participants decided whether an item was old (i.e., presented in any video) or new, or whether an item was presented in video 1/2/3/4 or was new. In Experiment 2 (N = 160, within-subjects), the old/new decision was followed by an instance attribution decision. Old items were recognised faster in the old/new task compared to the instance-attribution task. In the instance-attribution task, items from the boundary instances were accurately attributed faster compared to items from the middle instances. We found further evidence for primacy (and recency) effects in measures of confidence, memory judgments, recognition accuracy and discriminability, and confidence-accuracy calibration. [ABSTRACT FROM AUTHOR]

This study analyzes in detail the recognition accuracy of various gestures using a neural network built on TensorFlow to control a bionic prosthesis. By conducting a series of experiments using data sets and model parameters, it is investigated how effectively the neural network recognizes various gestures in the context of prosthesis control. The results of the exper)iments will allow us to understand the potential limitations and opportunities of this technology for practical application in real conditions. The neural network model and architecture, activation functions and parameters used for training are described. Learning parameters that affect the effectiveness of model learning are also considered. To evaluate the effectiveness of the model, results such as model evaluation metrics, model performance graphs, and confusion matrix are used to evaluate the level of reliability and performance of the trained neural network. Method of collecting electromyography (EMG) data is proposed, which consists in the use of electrical signals arising in muscles during their contraction. This process involves placing electrodes on the surface of the skin over the muscles being analyzed to record the electrical signals that occur at the moment of muscle activity. This approach allows collecting objective data on muscle activity and their movements, which can then be used to train a neural network and further use it in controlling a bionic prosthesis. A series of experiments was conducted to assess the accuracy of recognition of various movements using the trained model. Analyzing the results of the experiments, it is possible to understand how efficiently and reliably the trained model works in real conditions and how suitable it is for practical use in control systems of bionic prostheses. [ABSTRACT FROM AUTHOR]

Microphone array-based beamforming algorithms are widely used in sound source identification, fault diagnosis, and radar communication because of their excellent performance. However, their limited spatial resolution and high dynamic side flap level seriously affect the recognition accuracy. To explore a high-performance beamforming sound source identification algorithm, the microphone array compressed beamforming underdetermined equation is solved by extending the iterative threshold. A sound source identification model is established, and a new compressed beamforming (CSB-II) algorithm is proposed. Numerical simulations show that the CSB-II algorithm can effectively reduce the starting frequency of sound source identification and has high sound source identification accuracy. The effects of signal-to-noise ratio, sound source distance, and array number on sound source identification accuracy are analyzed separately. The laws affecting sound source identification accuracy are derived from guiding actual sound source measurements. [ABSTRACT FROM AUTHOR]

With the fast development of artificial intelligence and emerging technologies, automatic recognition of students’ facial expressions has received increased attention. Facial expressions are a kind of external manifestation of emotional states. It is important for teachers to assess students’ emotional states and adjust teaching activities accordingly. However, existing methods for automatic facial expression recognition have the limitations of low accuracy of recognition and poor feature extraction. To address the problem, this study proposed a novel deep learning model called DenseNetX-CBAM to improve facial expression recognition by utilizing a variant of densely connected convolutional networks (DenseNet) to reduce unnecessary parameters and strengthen the reuse of expression features between networks; moreover, convolutional block attention module (CBAM) was integrated to allow the networks to focus on important special regions and important channels when representing features. The proposed model was tested using 217 video clips of 33 students in an online course. The results demonstrated promising effects of the method in improving the accuracy of facial expression recognition, which can help teachers to accurately recognize students’ emotions and provide real-time adjustment in online learning environments.

Automatic modulation recognition (AMR) is an essential topic of cognitive radio, which is of great significance for the analysis of wireless signals and is one of the current research hotspots. Traditional AMR approaches predominantly utilize raw in-phase/quadrature symbols (I/Q), amplitude/phase (A/P), or pre-processed data (e.g., high-order cumulates, spectrum images, or constellation diagrams) as inputs for the recognition model. However, it is difficult to achieve superior performance with only a single type of data as input. This paper proposes a novel multi-channel hybrid learning framework that integrates convolutional layers, Long Short-Term Memory (LSTM) layers, fully connected layers and classification layers. The model is built for modeling spatial-temporal correlations from four signal cues (including I/Q signals, A/P signals, I, and Q signals), which aims to explore various differences and leverage the complements from multiple data-form. Two functions employed during the data conversion process further enhance the non-linear representational capacity of the model, thereby boosting the recognition accuracy of the model. Experimental results demonstrate that the proposed framework effectively addresses the classification challenges of QAM16 and QAM64. For the RAML2016A dataset, our model achieves an impressive recognition accuracy of 95% at an SNR of 0 dB. Extensive experiments indicate that the proposed framework outperforms other current networks in terms of recognition accuracy.

Gesture recognition has emerged as a significant research domain in computer vision and human-computer interaction. One of the key challenges in gesture recognition is how to select the most useful channels that can effectively represent gesture movements. In this study, we have developed a channel selection algorithm that determines the number and placement of sensors that are critical to gesture classification. To validate this algorithm, we constructed a Force Myography (FMG)-based signal acquisition system. The algorithm considers each sensor as a distinct channel, with the most effective channel combinations and recognition accuracy determined through assessing the correlation between each channel and the target gesture, as well as the redundant correlation between different channels. The database was created by collecting experimental data from 10 healthy individuals who wore 16 sensors to perform 13 unique hand gestures. The results indicate that the average number of channels across the 10 participants was 3, corresponding to an 75% decrease in the initial channel count, with an average recognition accuracy of 94.46%. This outperforms four widely adopted feature selection algorithms, including Relief-F, mRMR, CFS, and ILFS. Moreover, we have established a universal model for the position of gesture measurement points and verified it with an additional five participants, resulting in an average recognition accuracy of 96.3%. This study provides a sound basis for identifying the optimal and minimum number and location of channels on the forearm and designing specialized arm rings with unique shapes.

We developed an optical neural network (ONN) for efficient processing and recognition of 2-dimensional (2D) images, employing a conventional liquid crystal display panel as optical neurons and synapses. This configuration allowed for optical signal outputs proportional to matrix-vector multiplication for 2D image inputs. However, our experimental results revealed a 26.6% decrease in the optical classification accuracy, despite utilizing digitally pre-trained parameters with 100% accuracy for 500 handwritten digits. This decline can be attributed to system imperfections associated with non-ideal functions of optical components and optical alignment. Rather than pursuing an elusive, imperfection-free ONN or attempting to calibrate these defects individually, we addressed these challenges by introducing a self-correction mechanism that utilizes a machine learning algorithm. This approach effectively restored the recognition accuracy and minimized loss of our ONN to levels comparable to the digitally pre-trained model. This study underscores the potential of constructing defect-tolerant hardware in ONNs through the application of machine learning techniques.

Researchers have been developing Hand Gesture Recognition (HGR) systems to enhance natural, efficient, and authentic human-computer interaction, especially benefiting those who rely solely on hand gestures for communication. Despite significant progress, automatic and precise identification of hand gestures remains a considerable challenge in computer vision. Recent studies have focused on specific modalities like RGB images, skeleton data, and spatiotemporal interest points. This paper comprehensively reviews HGR techniques and data modalities from 2014 to 2024, exploring advancements in sensor technology and computer vision. We highlight accomplishments using various modalities, including RGB, Skeleton, Depth, Audio, Electromyography (EMG), Electroencephalography (EEG), and Multimodal approaches and identify areas needing further research. We reviewed over 250 articles from prominent databases, focusing on data collection, data settings, and gesture representation. Our review assesses the efficacy of HGR systems through their recognition accuracy and identifies a gap in research on continuous gesture recognition, indicating the need for improved vision-based gesture systems. The field has experienced steady research progress, including advancements in hand-crafted features and deep learning (DL) techniques. Additionally, we report on the promising developments in HGR methods and the area of multimodal approaches. We hope this survey will serve as a potential guideline for diverse data modality-based HGR research.

Abstract The problems of insufficient recognition accuracy, poor real‐time performance and lack of consideration of actual working conditions in the process of intelligent construction of coal mines make this technology still in the research stage and not applied in practical engineering. The purpose of this paper is to establish an accurate and real‐time recognition model, which can quickly distinguish the vibration acceleration signals of coal and gangue under the influence of external factors such as impact position, velocity, and direction by using the different physical properties of coal and gangue particles. Therefore, the accuracy and real‐time of coal gangue recognition model established by different convolutional neural networks (CNN) structures and different position signal input are studied. First, to meet the real‐time requirements, an original CNN recognition model composed of single convolution layer and single pooling layer is established, and the data collected by seven sensors are input in the form of two‐dimensional matrix. However, the stability of the training and test results is insufficient. To solve this problem, once improved CNN (OI‐CNN) recognition model with multiconvolution layers and multipooling layers is built by deepening the network. The experimental results show that the stability and accuracy are improved, but the real‐time performance is poor. Furthermore, through parameter adjustment, the OI‐CNN is changed to the twice improved CNN (TI‐CNN), and the sensor data at different positions are input in the form of one‐dimensional vectors. The results show that the accuracy and real‐time performance of the TI‐CNN coal gangue recognition model are further improved. Finally, according to the research purpose of this paper, the weights of CNN indexes are given, and a multi‐index comprehensive evaluation system (MICES) is established. With the original CNN recognition model as the control, the OI‐CNN recognition model and the TI‐CNN recognition model at different positions are quantitatively compared to obtain the comprehensive evaluation scores of each model. The results show that the MICES of the coal gangue recognition model established based on the TI‐CNN structure and the data input of a single position sensor is the highest, while the sensor position has little effect on the recognition results.

At present, the application of Artificial Intelligence (AI) in industrial control, smart home and other fields has received good response. However, AI technology has certain requirements for computer performance, and also faces problems in network security, data analysis, human-computer interaction, etc. At present, the visual platform of embedded system has achieved remarkable results in practical applications, but its development has been seriously hampered by problems such as low overall development efficiency and unstable system performance. This paper designed an EP Vision System (VS) based on AI technology. The platform combined the embedded hardware design with the Support Vector Machine (SVM) algorithm to realize the intelligent robot interaction and target detection functions. The test results showed that when other conditions were the same, students and experts had 83.5% and 90% positive evaluations of System X, and 16.5% and 10% negative evaluations respectively. However, their positive evaluation of System Y only accounted for 19% and 4%, while the negative evaluation accounted for 81% and 96%. The proportion of positive evaluation of System X was much higher than that of System Y, which indicated that System X can meet the actual application requirements and improve the system recognition efficiency to a certain extent. It showed the positive relationship between AI technology and EP VS.

Copyright of Journal of Nanchang University (Engineering & Technology) is the property of Nanchang University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Speaker-verification-system (SVS) is automated nowadays to improve the authenticity score of digital applications. However, spoofs in the audio signal have reduced the integrity score of the audio signal, which has tended to cause less authentication exactness score. Considering this, spoof recognition objectives emerged in this field to find the different types of spoofs with high exactness scores. Attracting the widest spoof forecasting score is impossible due to harmful and different spoof features. So, the present study built a novel Dove-based Recurrent Spoof Recognition System (DbRSRS) to identify the spoofing behaviour and its types from the trained audio data. The noise features were filtered in the primary stage to mitigate the complexity of spoof recognition. Moreover, the noise features filtered data is taken to the classification phase for feature selection and spoof recognition. Here, the spoof types were classified based on the different class features. Once the Spoof is identified, it is specified under different spoof classes. Here, the optimal dove features are utilized to tune the DbRSRS classification parameters. This process helped to earn the finest spoof recognition score than the recently published associated model. Henceforth, the recorded highest spoof forecasting accuracy was 99.2%, and the reported less error value was 0.05%. Thus, attaining the highest spoof prediction exactness score with less error value might improve the SVS performance. [ABSTRACT FROM AUTHOR]

This study examines the effectiveness of neural network architectures (multilayer perceptron MLP, convolutional neural network CNN, recurrent neural network RNN) for human voice recognition, with an emphasis on the Kazakh language. Problems related to language, the difference between speakers, and the influence of network architecture on recognition accuracy are considered. The methodology includes extensive training and testing, studying the accuracy of recognition in different languages, and different sets of data on speakers. Using a comparative analysis, this study evaluates the performance of three architectures trained exclusively in the Kazakh language. The testing included statements in Kazakhs and other languages, while the number of speakers varied to assess its impact on recognition accuracy. [ABSTRACT FROM AUTHOR]

The Deese-Roediger and McDermott (DRM) paradigm and visually guided saccade tasks are both prominent research tools in their own right. This study introduces a novel DRM-Saccade paradigm, merging both methodologies. We used rule-based saccadic eye movements whereby participants were presented with items at test and were asked to make a saccade to the left or right of the item to denote a recognition or non-recognition decision. We measured old/new recognition decisions and saccadic latencies. Experiment 1 used a pro/anti saccade task to a single target. We found slower saccadic latencies for correct rejection of critical lures, but no latency difference between correct recognition of studied items and false recognition of critical lures. Experiment 2 used a two-target saccade task and also measured corrective saccades. Findings corroborated those from Experiment 1. Participants adjusted their initial decisions to increase accurate recognition of studied items and rejection of unrelated lures but there were no such corrections for critical lures. We argue that rapid saccades indicate cognitive processing driven by familiarity thresholds. These occur before slower source-monitoring is able to process any conflict. The DRM-Saccade task could effectively track real-time cognitive resource use during recognition decisions. [ABSTRACT FROM AUTHOR]

Gesture recognition has emerged as a significant research domain in computer vision and human-computer interaction. One of the key challenges in gesture recognition is how to select the most useful channels that can effectively represent gesture movements. In this study, we have developed a channel selection algorithm that determines the number and placement of sensors that are critical to gesture classification. To validate this algorithm, we constructed a Force Myography (FMG)-based signal acquisition system. The algorithm considers each sensor as a distinct channel, with the most effective channel combinations and recognition accuracy determined through assessing the correlation between each channel and the target gesture, as well as the redundant correlation between different channels. The database was created by collecting experimental data from 10 healthy individuals who wore 16 sensors to perform 13 unique hand gestures. The results indicate that the average number of channels across the 10 participants was 3, corresponding to an 75% decrease in the initial channel count, with an average recognition accuracy of 94.46%. This outperforms four widely adopted feature selection algorithms, including Relief-F, mRMR, CFS, and ILFS. Moreover, we have established a universal model for the position of gesture measurement points and verified it with an additional five participants, resulting in an average recognition accuracy of 96.3%. This study provides a sound basis for identifying the optimal and minimum number and location of channels on the forearm and designing specialized arm rings with unique shapes. [ABSTRACT FROM AUTHOR]

The performance of machine learning-based radar target recognition models is determined by the respective model and data to be analyzed. Currently, radar target recognition performance evaluation is based on accuracy metrics, but this method does not include the evaluation metrics regarding the impact of data quality on recognition performance. Data separability describes the degree of mixture of samples from different categories. Furthermore, the data separability metric is independent of the model recognition process. By incorporating it into the recognition evaluation process, recognition difficulty can be quantified, and a benchmark for recognition results can be provided in advance. Therefore, in this paper, we propose a data separability metric based on the rate-distortion theory. Extensive experiments on multiple simulated datasets demonstrated that the proposed metric can compare the separability of multivariate Gaussian datasets. Furthermore, by combining it with the Gaussian mixture model, the designed metric method could overcome the limitation of the rate-distortion function, capture the data’s local separable characteristics, and improve the evaluation accuracy of the overall data separability. Subsequently, we applied the proposed metric to evaluate the recognition difficulty in real datasets, the results of which validated its strong correlation with average recognition accuracy. In the experiments on evaluating the effectiveness of convolutional neural network modules, we first quantified and analyzed the separability trend of the feature extracted by each module during the testing phase. Further, we incorporated the proposed metric as a feature separability loss during the training phase to participate in the network optimization process, guiding the network to extract a more separable feature. This paper provides a new perspective for evaluating and improving the neural network recognition performance in terms of feature separability.

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The problems of insufficient recognition accuracy, poor real‐time performance and lack of consideration of actual working conditions in the process of intelligent construction of coal mines make this technology still in the research stage and not applied in practical engineering. The purpose of this paper is to establish an accurate and real‐time recognition model, which can quickly distinguish the vibration acceleration signals of coal and gangue under the influence of external factors such as impact position, velocity, and direction by using the different physical properties of coal and gangue particles. Therefore, the accuracy and real‐time of coal gangue recognition model established by different convolutional neural networks (CNN) structures and different position signal input are studied. First, to meet the real‐time requirements, an original CNN recognition model composed of single convolution layer and single pooling layer is established, and the data collected by seven sensors are input in the form of two‐dimensional matrix. However, the stability of the training and test results is insufficient. To solve this problem, once improved CNN (OI‐CNN) recognition model with multiconvolution layers and multipooling layers is built by deepening the network. The experimental results show that the stability and accuracy are improved, but the real‐time performance is poor. Furthermore, through parameter adjustment, the OI‐CNN is changed to the twice improved CNN (TI‐CNN), and the sensor data at different positions are input in the form of one‐dimensional vectors. The results show that the accuracy and real‐time performance of the TI‐CNN coal gangue recognition model are further improved. Finally, according to the research purpose of this paper, the weights of CNN indexes are given, and a multi‐index comprehensive evaluation system (MICES) is established. With the original CNN recognition model as the control, the OI‐CNN recognition model and the TI‐CNN recognition model at different positions are quantitatively compared to obtain the comprehensive evaluation scores of each model. The results show that the MICES of the coal gangue recognition model established based on the TI‐CNN structure and the data input of a single position sensor is the highest, while the sensor position has little effect on the recognition results. [ABSTRACT FROM AUTHOR]

In this paper, we address the challenge of ensuring safe operations and rescue efforts in emergency situations, for the sake of a sustainable marine environment. Our focus is on character recognition, specifically on deciphering characters present on the surface of aged and corroded ships, where the markings may have faded or become unclear over time, in contrast to vessels with clearly visible letters. Imprinted ship characters encompassing engraved, embroidered, and other variants found on ship components serve as vital markers for ship identification, maintenance, and safety in marine technology. The accurate recognition of these characters is essential for ensuring efficient operations and effective decision making. This study presents a machine-learning-based method that markedly improves the recognition accuracy of imprinted ship numbers and characters. This improvement is achieved by enhancing data classification accuracy through data augmentation. The effectiveness of the proposed method was validated by comparing it to State-of-the-Art classification technologies within the imprinted ship character dataset. We started with the originally sourced dataset and then systematically increased the dataset size, using the most suitable generative adversarial networks for our dataset. We compared the effectiveness of classic and convolutional neural network (CNN)-based classifiers to our classifier, a CNN-based classifier for imprinted ship characters (CNN-ISC). Notably, on the augmented dataset, our CNN-ISC model achieved impressive maximum recognition accuracy of 99.85% and 99.7% on alphabet and digit recognition, respectively. Overall, data augmentation markedly improved the recognition accuracy of ship digits and alphabets, with the proposed classification model outperforming other methods. [ABSTRACT FROM AUTHOR]

Classification is a crucial stage in identification systems, most specifically in biometric identification systems. A weak and inaccurate classification system may produce false identity, which in turn impacts negatively on delicate decisions. Decision making in biometric systems is done at the classification stage. Due to the importance of this stage, many classifiers have been developed and modified by researchers. However, most of the existing classifiers are limited in accuracy due to false representation of image features, improper training of classifier models for newly emerging data (over-fitting or under-fitting problem) and lack of an efficient mode of generating model parameters (scalability problem). The Negative Selection Algorithm (NSA) is one of the major algorithms of the Artificial Immune System, inspired by the operation of the mammalian immune system for solving classification problems. However, it is still prone to the inability to consider the whole self-space during the detectors/features generation process. Hence, this work developed an Optimized Negative Selection Algorithm (ONSA) for image classification in biometric systems. The ONSA is characterized by the ability to consider whole feature spaces (feature selection balance), having good training capability and low scalability problems. The performance of the ONSA was compared with that of the standard NSA (SNSA), and it was discovered that the ONSA has greater recognition accuracy by producing 98.33% accuracy compared with that of the SNSA which is 96.33%. The ONSA produced TP and TN values of 146% and 149%, respectively, while the SNSA produced 143% and 146% for TP and TN, respectively. Also, the ONSA generated a lower FN and FP rate of 4.00% and 1.00%, respectively, compared to the SNSA, which generated FN and FP values of 7.00% and 4.00%, respectively. Therefore, it was discovered in this work that global feature selection improves recognition accuracy in biometric systems. The developed biometric system can be adapted by any organization that requires an ultra-secure identification system.

Coal gangue recognition of top coal caving is one of the important links in the process of intelligent coal mine construction. However, the recognition accuracy of this technology in practical application is still challenging, because the recognition model is not perfect in the following aspects: 1) the filtering scale is not suitable for signal noise reduction;, 2) the selected features have no obvious difference in vibration signals of coal and gangue; and 3) the overall relevance of the model input data to the target classification is insufficient. The purpose of this paper is to establish a coal gangue recognition model with effective filtering, feature extraction and classification capabilities, which can adaptively carry out purposive feature extraction while retaining relevant information to improve the recognition accuracy. Firstly, hierarchical filtering (HF) method was proposed. Secondly, an effective information correlation fusion based coal gangue recognition model (EICF-coal gangue recognition model) was established by coupling wrapper feature selection method and recognition algorithm. Then, 2223 groups of vibration impact tests were carried out on the coal gangue mixture with gangue content of 0 to 50%, and two kinds of coal gangue recognition sample sets of “caving category” and “shutdown category” were established. Finally, coal gangue recognition experiments were carried out on 9 hierarchical filter sample sets by coupling wrapper and 5 recognition algorithms. Under the combined effect of the HF method, wrapper feature selection method and Stacking, coal gangue recognition accuracy reaches 99%. This paper demonstrates the effectiveness of the EICF-coal gangue recognition model.

An abstract painting's hanging orientation directly affects how audiences judge its artistic value. Choosing the optimal hanging orientation can preserve the artist's primary intention, preserving the original aesthetic value to a greater extent. Aesthetic value is frequently influenced by human subjective consciousness. Previous approaches improved direction recognition accuracy only by improving the feature extraction method and deep learning network. For this paper, the key factors that can influence recognition accuracy (such as painting content, image features and learning models) were investigated in conjunction with painting skills to find an experimental setting method that can enhance recognition accuracy. Experiment results show that the content of the painting has the greatest impact on classification accuracy. Furthermore, the average accuracy can be increased to more than 90% by reducing the number of painting categories in a dataset and the number of directions to be classified. While the outcome is superior to the state of the art, it is one-sided to rely solely on the information in the abstract painting. A combination of eye tracker data and questionnaires will be used in the future to examine the effect of audience subjective feelings on orientation classification. [ABSTRACT FROM AUTHOR]

Gesture recognition nowadays has grabbed the attention of researchers as they represent human behaviour in multiple practical ways. Amongst a variety of gestures available, hand gestures play an essential role in the field of human‐computer interaction when recognised efficiently in complex and dynamic environments. In this paper, we propose a dynamic hand gesture recognition system to recognise hand gestures appearing in different indoor and outdoor environments. Hand detection and tracking uses a two‐level system resulting in the formation of gesture trajectory in challenging conditions in which existing detection and tracking algorithms could not do so. A set of 45 features is provided as input to the various classification techniques. The redundancy problem has been reduced by selecting a set of optimum features using the analysis of variance method, which ranks the list of features. An incremental feature selection technique calculates recognition accuracy by selecting features according to rankings. This system provides an accuracy of 96.32% when used with machine learning and 97.5% when used with deep learning techniques. Recognition accuracy is calculated for various environments, including an extra hand, multiple persons in the video frame, and outdoor environment. All machine‐learning classifiers are combined using classifier combination to calculate the accuracy according to the majority‐voting rule. Based on the experimental results, it has been observed that deep learning provides better results compared to machine learning. [ABSTRACT FROM AUTHOR]

A fault diagnosis method for the rotating machinery based on improved Convolutional Neural Network (CNN) with Gray-Level Transformation (GLT) is proposed to increase the accuracy of the recognition adopting the multiple sensors. The Symmetrized Dot Pattern (SDP) in this method is applied to fuse the data of the multiple sensors, and the multi-color value method is adopted to increase the feature dimension. The grayscale and GLT are used to reduce the dimension of the SDP image. The SDP grayscale image is finally input to the CNN network for training recognition. The research results show that the diagnosis accuracy of the rolling bearing system based on the novel method is up to 98.6 %. Compared with the method without the multi-color value and GLT, the recognition accuracy of the proposed method is improved by 22.3 %, and the training time is reduced by about one third. The research work reveals that the developed method has the potential application value under the multi-sensor working conditions for the fault diagnosis. [ABSTRACT FROM AUTHOR]

A highly reliable and versatile resistive memory device that demonstrates threshold and non-volatile memory (NVM) switching behaviour depending on the compliance current (CC) modulation was utilised by doping a semiconducting (Si) material into a high- k (HfO x) film with highly linear synaptic behaviour. The device shifted towards volatile switching at a CC less than 1 µ A and exhibited NVM behaviour at a CC limit above 10 µ A. A 3-bit/cell data storage capability on RESET voltage modulation was implemented for high-density memory application. The device exhibited excellent programming linearity of potentiation/depression responses up to 10 000 pulses compatible with fast pulse (100 ns) with good I ON/ I OFF ratio (>103), stable data retention capability (105 s) at 85 °C and high WRITE endurance (∼107 cycles) with a pulse width of 200 ns. The neuromorphic applications were successfully emulated through neural network simulations using the experimentally calibrated data of the Si-doped HfO x resistive cross-point devices. Simulation results revealed a low nonlinearity of 0.03 with 98.08% pattern recognition accuracy. The estimated results revealed the potential of the device as a low-power selector and high-density NVM storage in large-scale crossbar array in future neuromorphic computing applications. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) has attracted much attention lately. However, the current methods are concerned primarily with recognition accuracy, while ignoring efficiency. Efficient-CapsNet, which employs deep separable convolution operations based on CapsNet, has low network parameters and high network training efficiency while ensuring recognition accuracy. Using three public datasets, JAFFE, CK+, and FER2013, we comprehensively compared the recognition accuracy and training efficiency of Efficient-CapsNet and CapsNet. Results showed that the Efficient-CapsNet's recognition accuracy reached 99.13%, 93.07%, and 72.94%, respectively, which is superior to most of the latest methods. In terms of training efficiency, the training time of a single image of Efficient-CapsNet under 64x64 size input and 48x48 size input is only 0.125ms and 0.033ms, respectively, which is 1454.28 times and 2730.03 times faster than CapsNet, respectively. Results also suggest that the training efficiency of Efficient-CapsNet is affected by the sample size. When the sample size grows, the training efficiency gradually slows down until it stabilizes. [ABSTRACT FROM AUTHOR]

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%.