Search

Well test model identification is a challenging task due to the numerous types of well test interpretation models and the non-uniqueness of pressure responses generated by different reservoir models. An automated framework is crucial to aid in the identification of well test interpretation models. Since the identification of well test interpretation relies primarily on the various flow regimes appeared on different diagnostic plots. A novel approach is proposed for the well test model identification from the pressure transient test data using the syntactic pattern recognition in this study. In this study, the identification process of well test interpretation model is divided into six steps: preprocessing, feature primitive extraction, curve shape tracking, flow regime division, model preliminary inference, and model final validation incorporating TDS technology. The automatic identification framework developed with this method has been able to identify a variety of complex well test interpretation models correctly, and the non-uniqueness of model results can be well resolved by syntactic pattern recognition combined with TDS technology. In general, the findings of this study can help for better understanding of the process by which well test expert completes the task of model identification. [ABSTRACT FROM AUTHOR]

Analyzing point clouds with neural networks is a current research hotspot. In order to analyze the 3D geometric features of point clouds, most neural networks improve the network performance by adding local geometric operators and trainable parameters. However, deep learning usually requires a large amount of computational resources for training and inference, which poses challenges to hardware devices and energy consumption. Therefore, some researches have started to try to use a nonparametric approach to extract features. Point-NN combines nonparametric modules to build a nonparametric network for 3D point cloud analysis, and the nonparametric components include operations such as trigonometric embedding, farthest point sampling (FPS), k-nearest neighbor (k-NN), and pooling. However, Point-NN has some blindness in feature embedding using the trigonometric function during feature extraction. To eliminate this blindness as much as possible, we utilize a nonparametric energy function-based attention mechanism (ResSimAM). The embedded features are enhanced by calculating the energy of the features by the energy function, and then the ResSimAM is used to enhance the weights of the embedded features by the energy to enhance the features without adding any parameters to the original network; Point-NN needs to compute the similarity between each feature at the naive feature similarity matching stage; however, the magnitude difference of the features in vector space during the feature extraction stage may affect the final matching result. We use the Squash operation to squeeze the features. This nonlinear operation can make the features squeeze to a certain range without changing the original direction in the vector space, thus eliminating the effect of feature magnitude, and we can ultimately better complete the naive feature matching in the vector space. We inserted these modules into the network and build a nonparametric network, Point-Sim, which performs well in 3D classification tasks. Based on this, we extend the lightweight neural network Point-SimP by adding some trainable parameters for the point cloud classification task, which requires only 0.8 M parameters for high performance analysis. Experimental results demonstrate the effectiveness of our proposed algorithm in the point cloud shape classification task. The corresponding results on ModelNet40 and ScanObjectNN are 83.9% and 66.3% for 0 M parameters—without any training—and 93.3% and 86.6% for 0.8 M parameters. The Point-SimP reaches a test speed of 962 samples per second on the ModelNet40 dataset. The experimental results show that our proposed method effectively improves the performance on point cloud classification networks. [ABSTRACT FROM AUTHOR]

The decipherment of ancient Chinese scripts, such as oracle bone and bronze inscriptions, holds immense significance for understanding ancient Chinese history, culture, and civilization. Despite substantial progress in recognizing oracle bone script, research on the overall recognition of ancient Chinese characters remains somewhat lacking. To tackle this issue, we pioneered the construction of a large-scale image dataset comprising 9233 distinct ancient Chinese characters sourced from images obtained through archaeological excavations. We propose the first model for recognizing the common ancient Chinese characters. This model consists of four stages with Linear Embedding and Swin-Transformer blocks, each supplemented by a CoT Block to enhance local feature extraction. We also advocate for an enhancement strategy, which involves two steps: firstly, conducting adaptive data enhancement on the original data, and secondly, randomly resampling the data. The experimental results, with a top-one accuracy of 87.25% and a top-five accuracy of 95.81%, demonstrate that our proposed method achieves remarkable performance. Furthermore, through the visualizing of model attention, it can be observed that the proposed model, trained on a large number of images, is able to capture the morphological characteristics of ancient Chinese characters to a certain extent. [ABSTRACT FROM AUTHOR]

This study presents a new solution to address challenges encountered in additive manufacturing, specifically in the context of 3D printing, where failures can occur due to complications associated with the nozzle or filament. The proposed solution in this research involves using a time-domain feature extraction method that leverages sound and vibration patterns. By implementing sensors to capture these signals in a controlled and noise-free environment, and then utilizing a Multi-Layer Perceptron (MLP) model trained accurately to predict upcoming signals and vibrations, proactive anticipation of printing outcomes is facilitated, including potential failures. Simulation results obtained using MATLAB for the MLP showcase the effectiveness of this approach, demonstrating remarkably low error rates. Furthermore, through rigorous data validation, the proposed method's ability to accurately identify sound and vibration signals is confirmed. As a result, the likelihood of failures is significantly reduced, thereby preventing defects in the filament. The implications of this solution hold great promise in substantially enhancing the reliability and efficiency of additive manufacturing processes. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DNNs) have achieved outstanding performance in this field. Meanwhile, handwritten Chinese character recognition (HCCR) is a challenging area of research in the field of computer vision. DNNs require a large number of parameters and high memory consumption. To address these issues, this paper proposes an approach based on an attention mechanism and knowledge distillation. The attention mechanism improves the feature extraction and the knowledge distillation reduces the number of parameters. The experimental results show that ResNet18 achieves a recognition accuracy of 97.63% on the HCCR dataset with 11.25 million parameters. Compared with other methods, this study improves the performance for HCCR. [ABSTRACT FROM AUTHOR]

Rotating machine fault diagnosis plays a vital role in reducing maintenance costs and preventing accidents. Machine learning (ML) methods and Internet of things (IoT) technologies have been recently introduced into machine fault diagnosis and have generated inspiring results. An ML model with more trainable parameters can typically generate a higher fault diagnostic accuracy. However, the IoT nodes have limited computation and storage resources. How to design an ML model with high accuracy and computational efficiency is still a difficulty and challenge. This work develops an enhanced sparse filtering (ESF) method for mining and fusing the features of the machine signals for fault diagnosis. First, a dimension reduction algorithm is utilized for obtaining the principal components of the vibration signals that are hindered by noises. The distinct features of the principal components are then exploited by using sparse filtering (SF). To reduce the overfitting of the SF model, the L 1/2 norm is applied to regularize the objective function. Finally, the obtained features are combined as the inputs of a softmax classifier for machine fault pattern recognition. The effectiveness, superiority, and robustness of the proposed ESF method are validated by the simulated signals and the practical bearing and motor fault signals compared with the other conventional methods. The lightweight and intelligent ESF algorithm is also deployed onto an edge computing node to realize online motor fault diagnosis. The designed model and the proposed method show great potential in highly accurate and efficient rotation machine fault diagnosis. [ABSTRACT FROM AUTHOR]

In the task of upper-limb pattern recognition, effective feature extraction, channel selection, and classification methods are crucial for the construction of an efficient surface electromyography (sEMG) signal classification framework. However, existing deep learning models often face limitations due to improper channel selection methods and overly specific designs, leading to high computational complexity and limited scalability. To address this challenge, this study introduces a deep learning network based on channel feature compression—partial channel selection sEMG net (PCS-EMGNet). This network combines channel feature compression (channel selection) and feature extraction (partial block), aiming to reduce the model's parameter count while maintaining recognition accuracy. PCS-EMGNet extracts high-dimensional feature vectors from sEMG signals through the partial block, decoding spatial and temporal feature information. Subsequently, channel selection compresses and filters these high-dimensional feature vectors, accurately selecting channel features to reduce the model's parameter count, thereby decreasing computational complexity and enhancing the model's processing speed. Moreover, the proposed method ensures the stability of classification, further improving the model's capability of recognizing features in sEMG signal data. Experimental validation was conducted on five benchmark databases, namely the NinaPro DB4, NinaPro DB5, BioPatRec DB1, BioPatRec DB2, and BioPatRec DB3 datasets. Compared to traditional gesture recognition methods, PCS-EMGNet significantly enhanced recognition accuracy and computational efficiency, broadening its application prospects in real-world settings. The experimental results showed that our model achieved the highest average accuracy of 88.34% across these databases, marking a 9.96% increase in average accuracy compared to models with similar parameter counts. Simultaneously, our model's parameter size was reduced by an average of 80% compared to previous gesture recognition models, demonstrating the effectiveness of channel feature compression in maintaining recognition accuracy while significantly reducing the parameter count. [ABSTRACT FROM AUTHOR]

At present, the sorting work of library books heavily relies on manual labour, and the sorting process is time-consuming and laborious. To address the above issues, in the context of digital transformation in the information age, a strategy research of intelligent library service transformation based on convolutional network is proposed to achieve intelligent daily maintenance regarding libraries. In particular, the arrangement of books based on category and order is resolved. First, the Canny operator detection algorithm combined with straight line is used to extract the book spine from the book image. Second, the Faster-RCNN-based target detection algorithm is selected to locate the claim number. The positioning accuracy also reaches 96% in the positioning test, which is also better than other algorithms. The specific detection time is 100s. Then the method is used to segment the characters, and the accuracy is 97%. Finally, in the character recognition of library book request numbers, the feature extraction effect of character images based on convolutional networks is the best. Compared with 95% and 96% of other algorithms, the average recognition rate is 97%, which also improves network performance. The comparative experimental findings suggest that the convolutional network algorithm can effectively achieve the information detection and book order recognition of library common claim numbers, providing a feasible solution for library intelligence. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) 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.)

Automatic Speech Emotion Recognition (ASER) has recently garnered attention across various fields including artificial intelligence, pattern recognition, and human–computer interaction. However, ASER encounters numerous challenges such as a shortage of diverse datasets, appropriate feature selection, and suitable intelligent recognition techniques. To address these challenges, a systematic literature review (SLR) was conducted following established guidelines. A total of 60 primary research papers spanning from 2011 to 2023 were reviewed to investigate, interpret, and analyze the related literature by addressing five key research questions. Despite being an emerging area with applications in real-life scenarios, ASER still grapples with limitations in existing techniques. This SLR provides a comprehensive overview of existing techniques, datasets, and feature extraction tools in the ASER domain, shedding light on the weaknesses of current research studies. Additionally, it outlines a list of limitations for consideration in future work. [ABSTRACT FROM AUTHOR]

Purpose: Atomic force microscope (AFM) is a key component of vibration-assisted tip-based nanomachining equipment. Its tip radius determines the machining accuracy and surface smoothness of nanostructures. During the process, the AFM tip directly contacts and relatively slides to the workpiece surface, and tip wear will be caused by the action between the tip and the cutting chip. Meanwhile, the cutting force, vibration amplitude, and cutting temperature will rise, thus affecting the accuracy and surface quality of the machining pattern. Therefore, the research on the online diagnosis of AFM tip damage is of great significance. Methods: An online diagnosis algorithm framework of the AFM tip damage based on statistical pattern recognition (SPR) technology can be used for real-time monitoring of nanomachining tool status. The voltage signal of lateral force generated in the cutting process was collected, and its feature variables were extracted and mapped into the feature space. Further, two models including Incremental Adaptive Support Vector Machine (IASVM) and Gaussian Mixture Model (GMM) were established, and they were used to process the time series feature data of processing force, to achieve real-time diagnosis of tip states. Results: According to the results obtained, IASVM has a strong robustness and generalization ability. For moving window data with 2000 sample points, its average recognition time in ten experiments is 0.180 s, and the average accuracy is 97.63%. On the other hand, as an unsupervised learning method, GMM's significant feature is its short recognition time, only 0.06 s for 2000 samples recognition. Conclusions: The time series data of nano-processing forces represented by vibration signals provide important clues for AFM tip health monitoring. The SPR method has significant advantages in computational time and accuracy, as well as physical consistency, making it a diagnostic tool for real-time detection of AFM tip states. [ABSTRACT FROM AUTHOR]

The principal component analysis (PCA) is widely used in computational science branches such as computer science, pattern recognition, and machine learning, as it can effectively reduce the dimensionality of high-dimensional data. In particular, it is a popular transformation method used for feature extraction. In this study, we explore PCA's ability for feature selection in regression applications. We introduce a new approach using PCA, called Targeted PCA to analyze a multivariate dataset that includes the dependent variable—it identifies the principal component with a high representation of the dependent variable and then examines the selected principal component to capture and rank the contribution of the non-dependent variables. The study also compares the feature selected with that resulting from a Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, the selected features were tested in two regression models: multiple linear regression (MLR) and artificial neural network (ANN). The results are presented for three socioeconomic, environmental, and computer image processing datasets. Our study found that 2 of 3 random datasets have more than 50% similarity in the selected features by the PCA and LASSO regression methods. In the regression predictions, our PCA-selected features resulted in little difference compared to the LASSO regression-selected features in terms of the MLR prediction accuracy. However, the ANN regression demonstrated a faster convergence and a higher reduction of error. [ABSTRACT FROM AUTHOR]

Writing is an important carrier of cultural inheritance, and the digitization of handwritten texts is an effective means to protect national culture. Compared to Chinese and English handwriting recognition, the research on Mongolian handwriting recognition started relatively late and achieved few results due to the characteristics of the script itself and the lack of corpus. First, according to the characteristics of Mongolian handwritten characters, the random erasing data augmentation algorithm was modified, and a dual data augmentation (DDA) algorithm was proposed by combining the improved algorithm with horizontal wave transformation (HWT) to augment the dataset for training the Mongolian handwriting recognition. Second, the classical CRNN handwriting recognition model was improved. The structure of the encoder and decoder was adjusted according to the characteristics of the Mongolian script, and the attention mechanism was introduced in the feature extraction and decoding stages of the model. An improved handwriting recognition model, named the EGA model, suitable for the features of Mongolian handwriting was suggested. Finally, the effectiveness of the EGA model was verified by a large number of data tests. Experimental results demonstrated that the proposed EGA model improves the recognition accuracy of Mongolian handwriting, and the structural modification of the encoder and coder effectively balances the recognition accuracy and complexity of the model. [ABSTRACT FROM AUTHOR]

As the crucial part of a transmission assembly, the monitoring of the status of the crankshaft is essential for the normal working of a reciprocating machinery system. In consideration of the interaction between crankshaft system components, the fault vibration feature is typically non-stationary and nonlinear, and the single-scale feature extraction method cannot adequately assess the fault features, therefore a novel impact feature extraction method based on genetic algorithms to optimize multi-scale permutation entropy is proposed. Compared with other traditional feature extraction methods, the proposed method illustrates good robustness and high adaptability in the signal processing of crankshaft vibrations. Firstly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method is developed on the signal to obtain several intrinsic mode function (IMF) components, and the IMF components with a large kurtosis are selected for array reorganization. Then, the parameters of multi-scale permutation entropy (MPE) are optimized based on genetic algorithm (GA), the multi-scale permutation entropy is calculated and the feature vector set is constructed. The feature vector set is input into the support vector machine (SVM) and optimized by a particle swarm optimization (PSO) model for training and final pattern recognition, where the Variational Mode Decomposition(VMD)-GA-MPE with a PSO-SVM recognition model and the ICEEMDAN-MPE with PSO-SVM recognition model without GA optimization are constructed for a comparison with the proposed method. The research result illustrates that the proposed method, which inputs the genetic algorithm optimized multi-scale permutation entropy extracted from the ICEEMDAN decomposition into the PSO-SVM, performs well in impact feature extraction and the pattern recognition of crankshaft vibrations. [ABSTRACT FROM AUTHOR]

Although low‐rank representation (LRR)‐based subspace learning has been widely applied for feature extraction in computer vision, how to enhance the discriminability of the low‐dimensional features extracted by LRR based subspace learning methods is still a problem that needs to be further investigated. Therefore, this paper proposes a novel low‐rank preserving embedding regression (LRPER) method by integrating LRR, linear regression, and projection learning into a unified framework. In LRPER, LRR can reveal the underlying structure information to strengthen the robustness of projection learning. The robust metric L2,1‐norm is employed to measure the low‐rank reconstruction error and regression loss for moulding the noise and occlusions. An embedding regression is proposed to make full use of the prior information for improving the discriminability of the learned projection. In addition, an alternative iteration algorithm is designed to optimise the proposed model, and the computational complexity of the optimisation algorithm is briefly analysed. The convergence of the optimisation algorithm is theoretically and numerically studied. At last, extensive experiments on four types of image datasets are carried out to demonstrate the effectiveness of LRPER, and the experimental results demonstrate that LRPER performs better than some state‐of‐the‐art feature extraction methods. [ABSTRACT FROM AUTHOR]

This paper explores the representation of vehicle lights in computer vision and its implications for various pattern recognition tasks in autonomous driving. Different representations for vehicle lights, including bounding boxes, center points, corner points, and segmentation masks, are discussed in terms of their strengths and weaknesses toward a variety of domain tasks, as well as associated data collection and annotation challenges. This leads to the introduction of the LISA Vehicle Lights Dataset, providing light annotations related to position, state, color, and signal, specifically designed for downstream applications in vehicle detection, intent and trajectory prediction, and safe path planning. A comparison of existing vehicle light datasets is provided, highlighting the unique features and limitations of each dataset. Because occlusions from vehicle pose and passing objects can limit camera observation, we introduce a group of Light Visibility neural networks, which take as input a detected vehicle image and return as output whether a corresponding vehicle light is present in the image. This is especially important for the evaluation of light localizations, states, and signals, as systems decisions should account for differences of lights being in unknown states due to occlusion versus model uncertainty. We show that our trained Light Visibility Models achieve over 90% accuracy on each of the four light classes. Our dataset and model are made available at https://cvrr.ucsd.edu/vehicle-lights-dataset. • Discussion of tradeoffs in representations of vehicle lights for data-driven models. • Introduction of the LISA Vehicle Lights Dataset. • Light visibility classification results for downstream tasks in pattern recognition. • Description of pattern recognition tasks which rely on light detection. • Discussion of importance of association of lights to particular vehicle instances. [ABSTRACT FROM AUTHOR]

Infrared image technology has the advantages of high sensitivity and non-contact, which can be used to detect athletes' defects and improve the teaching quality and effect. This paper explores infrared image defect detection method based on data information visualization technology, adopts infrared image technology to obtain athletes image data, and uses data information visualization technology to process and analyze the image data. Firstly, the image data is preprocessed, and then the key features of athletes are extracted and defect detection is carried out by using image processing algorithm and pattern recognition algorithm. Finally, the test results are displayed visually, so that teachers and students can intuitively understand the athletes' defects. The research shows that the infrared image defect detection method based on data information visualization technology has achieved good results in physical education teaching. By processing and analyzing the infrared images of athletes, the defects of athletes can be accurately detected, and effective guidance and feedback can be provided for teachers. [ABSTRACT FROM AUTHOR]

Classification and identification of objects are complex and challenging in pattern recognition and artificial intelligence if a shaky and nonshaky camera captures the videos at different distances during the day and nighttime. This work presents a model for classifying a given video as a static, uniform, or arbitrarily moving videos so that the complexity of the problem can be reduced. To avoid the threat of different distances between the objects and the camera, the proposed work introduces new steps for estimating the depth of the objects in the video frames. We explore locally weighted linear regression for feature extraction from depth information based on the notion that the regression line fits almost all the points for uniformity and does not fit for arbitrary moving. The extracted features are fed to a random forest classifier to classify static, uniform, or arbitrary moving video. The results on a large dataset, which includes videos captured day and night, show that the proposed method successfully classifies static, uniform and arbitrary videos with 0.86, 1.00 and 0.67 F-measures, respectively. Overall, our method obtains 87% accuracy for classification of static, uniform and arbitrary video, which is superior to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Pattern recognition of linear feature sets, such as river networks, road networks, and contour clusters, is essential in cartography and geographic information science. Previous studies have investigated many methods to identify the patterns of linear feature sets; the key to each of these studies is to generate a reasonable and computable representation for each set. However, most existing methods are only designed for a specific task or data type and cannot provide a general solution for formalizing linear feature sets owing to their complex geometric characteristics, spatial relations and distributions. In addition, some methods require human involvement to specify characteristics, choose parameters, and determine the weights of different measures. To reduce human intervention and improve adaptability to various feature types, this paper proposes a novel deep learning architecture for learning the representations of linear feature sets. The presented model accepts vector data directly without extra data conversion and feature extraction. After generating local, neighborhood, and global representations of inputs, the representations are aggregated accordingly to perform pattern recognition tasks, including classification and segmentation. In the experiments, building groups classification and road interchanges segmentation achieved accuracies of 98% and 89%, respectively, indicating the model's effectiveness and adaptability. [ABSTRACT FROM AUTHOR]

In this study, surface roughness is analyzed within a supervised pattern recognition framework using machine learning methods to present a robust technique for the quantitative determination of surface roughness of rocks. To reach this goal, rock surfaces are classified based on statistical, fractal, geostatistical, directional, and spectral features obtained from the surface profiles as well as the results of direct shear tests. In this way, after the calculation of the features in more than 9000 profiles collected from 84 natural rock samples, a representative vector containing representative features of the surface profiles was introduced for each surface, and joint roughness coefficient (JRC) was back-calculated from 84 direct shear tests on the rock samples. Then, principal component analysis and linear discriminant analysis of the representative vectors were performed in order to prepare the inputs for the classification. Multilayer perceptron (MLP) and radial basis function (RBF) artificial neural networks and support vector machine (SVM) were trained for the classification of rock surfaces. On the other hand, convolutional neural network (CNN) in which features are automatically extracted from the image data of representative surface profiles was the other method for the classification of rock surfaces. The comparison of the results shows RBF is a robust and reliable classifier yielding the least classification error among the investigated methods. Furthermore, comparing the results of machine learning methods with those of traditional equations proves that the SVM, MLP, and RBF yield superior performance. [ABSTRACT FROM AUTHOR]

Multivariate data analysis and machine learning classification have become popular tools to extract features without physical models for complex environments recognition. For electronic noses, time sampling over multiple sensing elements must be a fair compromise between a period sufficiently long to output a meaningful information pattern and sufficiently short to minimize training time for practical applications. Particularly when a reactivity's kinetics differ from the thermodynamics in sensitive materials, finding the best compromise to get the most from the data is not obvious. Here, we investigate the influence of data acquisition to improve or alter data clustering for molecular recognition on a conducting polymer electronic nose. We found out that waiting for sensing elements to reach their steady state is not required for classification, and that reducing data acquisition down to the first dynamical information suffices to recognize molecular gases by principal component analysis with the same materials. Especially for online inference, this study shows that a good sensing array is not an array of good sensors, and that new figures of merit should be defined for sensing hardware using machine learning pattern recognition rather than metrology. [ABSTRACT FROM AUTHOR]

Most of the successful person re‐ID models conduct supervised training and need a large number of training data. These models fail to generalise well on unseen unlabelled testing sets. The authors aim to learn a generalisable person re‐identification model. The model uses one labelled source dataset and one unlabelled target dataset during training and generalises well on the target testing set. To this end, after a feature extraction by the ResNext‐50 network, the authors optimise the model by three loss functions. (a) One loss function is designed to learn the features of the target domain by tuning the distances between target images. Therefore, the trained model will be more robust to overcome the intra‐domain variations in the target domain and generalises well on the target testing set. (b) One triplet loss is used which considers both source and target domains and makes the model learn the inter‐domain variations between source and target domain as well as the variations in the target domain. (c) Also, one loss function is for supervised learning on the labelled source domain. Extensive experiments on Market1501 and DukeMTMC re‐ID show that the model achieves a very competitive performance compared with state‐of‐the‐art models and also it requires an acceptable amount of GPU RAM compared to other successful models. [ABSTRACT FROM AUTHOR]

Heatmap‐based regression (HBR) methods have dominated for a long time in the face alignment field while these methods need complex design and post‐processing. In this study, the authors propose an end‐to‐end and simple enough coordinate‐based regression (CBR) method called Dynamic Deformable Transformer (DDT) for face alignment. Unlike general pre‐defined landmark queries, DDT uses Dynamic Landmark Queries (DLQs) to query landmarks' classes and coordinates together. Besides, DDT adopts a deformable attention mechanism rather than a regular attention mechanism which has a faster convergence speed and lower computational complexity. Experiment results on three mainstream datasets 300W, WFLW, and COFW demonstrate DDT exceeds the state‐of‐the‐art CBR methods by a large margin and is comparable to the current state‐of‐the‐art HBR methods with much less computational complexity. [ABSTRACT FROM AUTHOR]

Efficient measurement of labor input is a critical aspect of on-site control and management in construction projects, as labor input serves as the primary and direct determinant of project outcomes. However, conventional manual inspection methods are off-line, tedious, and fail to capture their effectiveness. To address this issue, this research presents a novel method that leverages Inertial Measurement Unit (IMU) sensors attached to hand tools during construction activities to measure labor input in a timely and precise manner. This approach encompasses three steps: temporal–spatial feature extraction, self-similarity matrix calculation, and local specific structure identification. The underlying principle is based on the hypothesis that repetitive use data from hand tools can be systematically collected, analyzed, and converted into quantitative measures of labor input by the automatic recognition of repetition patterns. To validate this concept and assess its feasibility for general construction activities, we developed a preliminary prototype and conducted a pilot study focusing on rotation counting for a screw-connection task. A comparative analysis between the ground truth and the predicted results obtained from the experiments demonstrates the effectiveness and efficiency of measuring labor input using IMU sensors on hand tools, with a relative error of less than 5%. To minimize the measurement error, further work is currently underway for accurate activity segmentation and fast feature extraction, enabling deeper insights into on-site construction behaviors. [ABSTRACT FROM AUTHOR]

Botnet is a cyber-attack that aims to compromise the security of internet of things (IoT) networks by exploiting infected devices to launch attacks and gain unauthorized access to private information. Intrusion detection system (IDS) emerges as critical countermeasures for tackling the risks posed by botnet attacks, playing a crucial role in ensuring the integrity and confidentiality of data in IoT environments. Developing an effective botnet detection system depends on efficient contextual understanding and accurate attack pattern characterization. Recently, deep learning and machine learning based IDS have demonstrated promising results in traffic pattern recognition and identification as normal or malicious from raw data. However, these approaches fail to detect simultaneous botnet attacks as it ignores its distributed nature. In this paper, we propose an efficient hybrid deep learning model for simultaneous botnet attack detection over IoT networks. The twostage hybrid model analyzes the network traffic data captured from three parallel sensors and extracts simultaneous characteristics of attack traffic. The use of parallel detection enables more comprehensive coverage of the network, thereby increasing the detection accuracy of malicious activities that could be missed by a single sensor. Features are extracted using a long-short-term memory base autoencoder (LSTM-AE) over the NCC-2 Simultaneous Botnet Dataset. The LSTM-AE is trained using data from multiple sensors to model temporal characteristics and results in reduced latent representation. Attack type identification is achieved through a multi-class classification using the Extreme Gradient Boosting (XGBoost) ensemble learning algorithm. The recently released NCC-2 dataset is the first dataset to provide data representing sequential and simultaneous botnet activities detected concurrently by multiple sensors. Performance exploration indicates that for parallel botnet detection, the proposed LSTM-AE-XGB model achieves high accuracy while reducing false or missing detection. Moreover, to demonstrate model efficiency, we conducted a 10-fold cross-validation and a comparative performance analysis with the state-of-the-art ML and DL-based techniques for feature extraction and simultaneous botnet detection. [ABSTRACT FROM AUTHOR]

Dynamic human activity recognition (HAR) is a domain of study that is currently receiving considerable attention within the fields of computer vision and pattern recognition. The growing need for artificial-intelligence (AI)-driven systems to evaluate human behaviour and bolster security underscores the timeliness of this research. Despite the strides made by numerous researchers in developing dynamic HAR frameworks utilizing diverse pre-trained architectures for feature extraction and classification, persisting challenges include suboptimal performance accuracy and the computational intricacies inherent in existing systems. These challenges arise due to the vast video-based datasets and the inherent similarity in the data. To address these challenges, we propose an innovative, dynamic HAR technique employing a deep-learning-based, deep bidirectional long short-term memory (Deep BiLSTM) model facilitated by a pre-trained transfer-learning-based feature-extraction approach. Our approach begins with the utilization of Convolutional Neural Network (CNN) models, specifically MobileNetV2, for extracting deep-level features from video frames. Subsequently, these features are fed into an optimized deep bidirectional long short-term memory (Deep BiLSTM) network to discern dependencies and process data, enabling optimal predictions. During the testing phase, an iterative fine-tuning procedure is introduced to update the high parameters of the trained model, ensuring adaptability to varying scenarios. The proposed model's efficacy was rigorously evaluated using three benchmark datasets, namely UCF11, UCF Sport, and JHMDB, achieving notable accuracies of 99.20%, 93.3%, and 76.30%, respectively. This high-performance accuracy substantiates the superiority of our proposed model, signaling a promising advancement in the domain of activity recognition. [ABSTRACT FROM AUTHOR]

In human and other organisms' perception, olfaction plays a vital role, and biomimetic olfaction models offer a pathway for studying olfaction. The most optimal existing biomimetic olfaction model is the KIII model proposed by Professor Freeman; however, it still exhibits certain limitations. This study aims to address these limitations: In the feature extraction stage, it introduces adaptive histogram equalization, Gaussian filtering, and discrete cosine transform methods, effectively enhancing and extracting high-quality image features, thereby bolstering the model's recognition capabilities. To tackle the computational cost issue associated with solving the numerical solutions of neuronal dynamics equations in the KIII model, it replaces the original method with the faster Euler method, reducing time expenses while maintaining good recognition results. In the decision-making stage, several different dissimilarity metrics are compared, and the results indicate that the Spearman correlation coefficient performs best in this context. The improved KIII model is applied to a new domain of traffic sign recognition, demonstrating that it outperforms the baseline KIII model and exhibits certain advantages compared to other models. [ABSTRACT FROM AUTHOR]

This study offers a concise overview of classifying hand movements based on their kinetic and myoelectric characteristics. In this work, we propose utilizing Electromyography (EMG) signals to distinguish these movements, especially for applications like wheelchair guidance and prosthetic control. Unlike prior research on forearmderived EMG signals, this study employs a multi-channel surface Electromyography (sEMG) signal to effectively categorize distinct movements, crucial for prosthetic control. To extract informative signal features, a two-step process is deployed, beginning with the transformation of raw EMG data using Discrete Wavelet Transform (DWT) for feature extraction. The ensuing classification task employs an Artificial Neural Network (ANN), overseen by the generation of corresponding confusion matrices (CMs) based on input features. The efficacy of our approach is validated using a human hand EMG signal dataset sourced from the UCI Machine Learning Repository. This dataset encompasses recordings from 36 subjects across 8 channels (sensors), spanning multiple days. The suggested algorithm utilizes unprocessed bipolar EMG data for both training and evaluating the performance of the neural network-based classifier. Significantly, when assessing the algorithm's performance offline, it becomes evident that the use of Frequency Domain (FD) features in sequential signal processing outperforms Standard Linear Discriminant Analysis (LDA) algorithms. The combination of the DWT and ANN results in significantly improved performance and sustained robustness of the classification algorithm. Empirical findings prove the effectiveness of this approach, achieving an accuracy of 89.9%in classifying seven distinct hand movement categories accurately. Additionally, the analysis shows an increasing classification accuracy as the dataset size increases. [ABSTRACT FROM AUTHOR]

The combination of feature extraction and classification methods is an often used approach for wafer map failure pattern recognition. Recently, the convolutional neural network (CNN) method is used to raw wafer map data without feature extraction. CNN can improve the accuracy, but the drawback is the expensive computation cost. In our study, we have extracted local property analysis based features and used them with the traditional classification methods, ensemble methods, and CNN for wafer map failure pattern recognition. The decision tree showed better performance than the other methods when evaluating single traditional classification methods. Therefore, we used the decision tree as the base classifier of the proposed ensemble learning. We built a constituent model on a single type of feature set first and then made an ensemble of models to produce the final decision. We found that it is better than directly building a model on total features. Also, we have tested and compared CNN on extracted feature sets and raw wafer map image data. The results showed that raw image based CNN outperforms extracted features under the same number of epochs. However, the training cost of the raw image is much expensive. Furthermore, the performance of extracted features becomes closer to the raw image when increasing the number of epochs with a much lower training cost. [ABSTRACT FROM AUTHOR]

Amputation of the upper limb significantly hinders the ability of patients to perform activities of daily living. To address this challenge, this paper introduces a novel approach that combines non-invasive methods, specifically electroencephalography (EEG) and electromyography (EMG) signals, with advanced machine learning techniques to recognize upper limb movements. The objective is to improve the control and functionality of prosthetic upper limbs through effective pattern recognition. The proposed methodology involves the fusion of EMG and EEG signals, which are processed using time-frequency domain feature extraction techniques. This enables the classification of seven distinct hand and wrist movements. The experiments conducted in this study utilized the binary grey wolf optimization algorithm to select optimal features for the proposed classification model. The results demonstrate promising outcomes, with an average classification accuracy of 93.6% for three amputees and five individuals with intact limbs. The accuracy achieved in classifying the seven types of hand and wrist movements further validates the effectiveness of the proposed approach. By offering a non-invasive and reliable means of recognizing upper limb movements, this research represents a significant step forward in biotechnical engineering for upper limb amputees. The findings hold considerable potential for enhancing the control and usability of prosthetic devices, ultimately contributing to the overall quality of life for individuals with upper limb amputations. [ABSTRACT FROM AUTHOR]

Purpose: Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics. Design/methodology/approach: The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value. Findings: Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared. Originality/value: To the best of the author's knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression. [ABSTRACT FROM AUTHOR]

Text detection and recognition are widely used in daily life. Although it is a very rich market, it has very difficult challenges in practical application. The complex and changeable natural scenes lead to the complex background of the text in the image, which also reflects the research value of text information recognition and extraction in natural scenes. To solve the many problems faced by the recognition of Chinese characters, such as complex shapes and diverse structures, this paper uses VGG16 to extract features and introduces a two-layer bidirectional LSTM network. It improves Faster R-CNN by using a RPN to extract candidate boxes and adjust the position of candidate regions. In this paper, the improved model Faster BLSTM-CNN is tested, and the effectiveness experiment of feature extraction, the difference comparison before and after the improvement of the algorithm, and the comparison experiment with the traditional recognition algorithm are carried out respectively. And it finally carried out an experimental comparison of the combination of text recognition and positioning, and obtained the results. The algorithm Faster BLSTM-CNN in this paper is better in the localization and recognition of Chinese characters in the dataset. In the natural scene, the recognition rate of Faster BLSTM-CNN in this paper is 81.54%, the positioning accuracy is 88.14%, and the detection speed is 86 ms, which has improved performance. Therefore, the improvement of Faster R-CNN is effective. It can effectively locate and recognize Chinese characters in natural scenes. [ABSTRACT FROM AUTHOR]

Automatic facial expression recognition plays a crucial role in computer vision, and pattern recognition. However, most existing deep learning-based facial expression classifiers usually obtain high average accuracy but have poor recognition accuracy for difficult expressions, like fear and disgust. In this paper, we propose a novel end-to-end architecture termed two-stream inter-class variation enhancement network, which learns the high-level semantic features and subtle inter-class variations in a joint fashion. More precisely, the global feature extraction network is used to extract spatial-channel semantic features, and the variations between different expressions are modeled by a distinction-reinforced network. The outputs of these two streams are weighted integrated in the expression classification network. In addition, a class balanced-weighted cross-entropy loss is designed to further improve feature discrimination. Experiment results indicate that the proposed network can significantly improve the recognition of difficult expressions and achieve a satisfactory average recognition accuracy of 73.67% on FER2013, 86.17% on RAFDB, 98.19% on CK+, and 98.85% on Oulu-CASIA, which outperforms the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the exponential growth of video data, action recognition has become an increasingly important area of study. Despite various advancements, achieving a balance between detection accuracy and lightness remains a formidable challenge, primarily due to the complexity of existing action recognition models. To address this issue, DenseGCN is developed, a lightweight network designed to optimize accuracy and efficiency. The aim was to create a detection model that has high accuracy while remaining lightweight for real‐world applications. DenseGCN operates via a unique three‐level feature fusion system. The initial stage involves the Multi‐level Fusion Network (MlFN), which contains dense connections and a Spatial‐Temporal Fusion Attention module (STF‐Att), designed to eliminate bias in feature extraction caused by deep networks. In the next stage, RefineBone tackles optimization issues in low‐dimensional feature layers by leveraging high‐dimensional feature layers, thus avoiding gradient stacking. Finally, the Multi‐temporal Fusion Feature Pyramid Network (MF‐FPN) generates a discriminative classification feature map by repetitively combining data from multiple dimensions. This strategy has proven successful in refining the extracted feature, allowing for discriminative feature extraction even with a reduced number of channels. This efficient design not only contributes to further research in developing lightweight networks but also offers enhanced possibilities for real‐world implementations. In two large‐scale datasets, NTU RGB+D 60 and 120, DenseGCN outperformed other state‐of‐the‐art methods, achieving an accuracy of 92.7% on the X‐View benchmark of the NTU RGB+D 60 dataset. The DenseGCN is 10.2 × faster and 10 × smaller than the spatial temporal graph attention network (STGAT) proposed in 2022 while retaining very competitive accuracy. The findings suggest that this model significantly improves the quality of feature extraction. As a result, DenseGCN presents a remarkable balance between accuracy and lightness. [ABSTRACT FROM AUTHOR]

The performance assessment of insulation materials within the components of a high voltage power system depends upon effective condition monitoring techniques of the insulation. One of the important phenomena to be considered in the diagnostics and performance assessment of high voltage insulation materials is the Partial Discharge (PD) measurement. The improved Deep learning techniques help in the effective identification and classification of various sources of PD mechanism. In this work, Deep Convolution Neural Network (DCNN) technique is proposed for the fusion of several features that are extracted from the PD signals. Three-dimensional Phase Resolved patterns of PD images can be used for training the DNN. For the classification of PD patterns, linear and non-linear type of multi-class support vector machine has been proposed. The results obtained are compared with linear SVM and non-linear SVMs with the polynomial kernel, Radial Basis Function (RBF) kernel, and Sigmoidal kernel. The SVM type with a higher pattern recognition rate is identified to be effective in PD pattern recognition and classification. The results of the proposed work show that the fusion approach of PD patterns supports applying huge PD data sets as input, generated by multiple faults, for effective PD pattern recognition. [ABSTRACT FROM AUTHOR]

Image texture is an important part of many types of images, for example medical images. Texture Analysis is the technique that uses measurable features to categorize complex textures. The main goal is to extract discriminative features that are used in different pattern recognition applications and texture categorization. This paper investigates the extraction of most discriminative features for different texture images from the “Colored Brodatz” dataset using two types of image contrast measures, as well as using the statistical moments on five bands (red, green, blue, grey, and black). The Euclidean distance measure is used in the matching step to check the similarity degree. The proposed method was tested on 112 classes of textures. The achieved results showed that the proposed method is accurate and fast concerning classification accuracy with low computational complexity. The achieved Recognition Rate (RR) was 100%. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate the damage pattern recognition in carbon/epoxy composite laminates by Acoustic Emission technique. Three specimens with layup of [90/0/90/0]s were fabricated and subjected to three-point bending test. The dataset was clustered and analyzed by three unsupervised algorithms, namely, k -means, Self-Organizing Map, and Fuzzy C-Means. The results show that the signals can be divided into four clusters, which correspond to matrix cracking, delamination, fiber/matrix debonding, and fiber breakage, respectively. A method of energy feature extraction based on wavelet packet decomposition was used to analyze the clustering center to obtain the frequency band with relatively high energy corresponding each damage mode further determined the actual damage pattern of these signals with disputed classification results. The results of k -means illustrated that little difference in the determination of matrix cracking, preferring to assign more signal to inter-laminar damage and higher peak frequency to fiber breakage compared to the other two algorithms. It can verify the clustering results well and k -means algorithm performs better in damage pattern recognition of composites. [ABSTRACT FROM AUTHOR]

Huanglongbing (HLB) is highly contagious and cannot be cured, resulting in a decrease in the commercial value of citrus. Timely detection and removal of diseased trees is an effective way to reduce losses. Complex symptoms of HLB, such as nutrient deficiencies often accompany HLB; as a result effective and accurate identification of HLB remains a challenge. In this study, 175 volatile organic compounds (VOCs) were detected in three categories (healthy, HLB, and Zn‐deficiency) of samples using headspace solid‐phase microextraction gas chromatography–mass spectrometry (HS‐SPME‐GC/MS), highlighting the variability of VOCs present in different categories of samples. In order to simplify the testing steps and reduce the cost in practical agricultural production, a method based on electronic nose technology to collect VOCs from citrus leaves for HLB detection was proposed. Among them, limiting value features and linear discriminant analysis were identified as the best combination of feature extraction and pattern recognition methods. Multiple sets of comparison experiments were set up and the collection conditions of VOCs were optimized. The results showed that the best classification performance was achieved for a 0.2 g sample at a collection time of 20 min when the collection temperature was 40°C and the headspace volume was 200 mL. Four types of samples (healthy, HLB‐positive, Zn‐deficiency, Zn‐deficiency and HLB‐positive) were used for model reliability validation, with an accuracy of 97.79% for HLB samples for multiple symptoms (including HLB‐positive and Zn‐deficiency and HLB‐positive) identification. In addition, the accuracy of samples with a combined effect of Zn‐deficiency and HLB was 96.43%. The results show that the E‐nose‐based HLB detection method is conducive to suppressing the spread of HLB, which can ensure the quality of citrus products and reduce the economic loss to horticulturists, and has good practical value. [ABSTRACT FROM AUTHOR]

Handwriting recognition is an important application in pattern recognition. Because handwritten Tai Le has similar characters and the proportion of characters with similar shapes is relatively high, this paper proposes a wavelet deep convolution (WDC) feature combined with an ensemble deep variational sparse Gaussian process (EDVSGP) offline handwritten Tai Le recognition method. A Tai Le recognition sample database is constructed, 2 and 3 levels of wavelet decomposition prior features are extracted, and then, the wavelet a priori feature is transformed into a WDC feature. To avoid the dimensional disaster caused by feature fusion, a dimensionality reduction method combining LDA and PCA is used to reducing the dimensionality of the fused features without reducing the accuracy rate. Moreover, to better recognize handwritten Tai Le characters, 6 deep variationally sparse Gaussian process (DVSGP) models are integrated as an EDVSGP classification model. Using the handwritten Tai Le character database, the proposed method is superior to the existing methods, with an accuracy, recall and F1-score of 94.15%, 94.15%, and 94.15%, respectively. The universality of the method is verified on a dataset of handwritten Chinese characters with similar shapes (HCFC2021.4) and the Devanagari dataset. [ABSTRACT FROM AUTHOR]

The world is growing with the new technologies for machine learning. Day by day there are incredible developments in the area of pattern recognition for the applications such as institutional record keeping, ancient documents preservation, postal address sorting, signature verification, etc. Handwritten character recognition is one such application grabbing lot of attention for the machines to learn. Handwritten Devanagari script is used in the proposed work which is very difficult to understand by the machines due to many similar shapes incorporated with it. So, pre-processing before extracting the features from the character plays very important role in increasing the accuracy. By keeping this in mind, a new framework for handwritten Devanagari character recognition is proposed where entropy -based skew correction is used to correct the skew of the characters and Mask-based approach is used which efficiently removes the header line and returns the header free character. The histograms of oriented gradients (HOG) features are extracted from the header free characters and provided for non-parametric dimensionality reduction. These features are further classified using AdaBoost ensemble boosting method and achieved a very good recognition accuracy of 98.43% and 98.68% on V2DMDCHAR and ISIDCHAR databases respectively. [ABSTRACT FROM AUTHOR]

Introduction: The electroencephalographic (EEG) based on the motor imagery task is derived from the physiological electrical signal caused by the autonomous activity of the brain. Its weak potential difference changes make it easy to be overwhelmed by noise, and the EEG acquisition method has a natural limitation of low spatial resolution. These have brought significant obstacles to high-precision recognition, especially the recognition of the motion intention of the same upper limb. Methods: This research proposes a method that combines signal traceability and Riemannian geometric features to identify six motor intentions of the same upper limb, including grasping/holding of the palm, flexion/extension of the elbow, and abduction/adduction of the shoulder. First, the EEG data of electrodes irrelevant to the task were screened out by low-resolution brain electromagnetic tomography. Subsequently, tangential spatial features are extracted by the Riemannian geometry framework in the covariance matrix estimated from the reconstructed EEG signals. The learned Riemannian geometric features are used for pattern recognition by a support vector machine with a linear kernel function. Results: The average accuracy of the six classifications on the data set of 15 participants is 22.47%, the accuracy is 19.34% without signal traceability, the accuracy is 18.07% when the features are the filter bank common spatial pattern (FBCSP), and the accuracy is 16.7% without signal traceability and characterized by FBCSP. Discussion: The results show that the proposed method can significantly improve the accuracy of intent recognition. In addressing the issue of temporal variability in EEG data for active Brain-Machine Interfaces, our method achieved an average standard deviation of 2.98 through model transfer on different days' data. [ABSTRACT FROM AUTHOR]

Potato malformation seriously affects commercial value, and its removal has become one of the core steps in the post-harvest and pre-sales process of potatoes. At present, this work mainly relies on manual visual inspection, which requires a lot of labor and incurs high investment costs. Therefore, precise and efficient automatic detection technology urgently needs to be developed. Due to the efficiency of deep learning based on image information in the field of complex object feature extraction and pattern recognition, this study proposes the use of the YOLOv3 algorithm to undertake potato malformation classification. However, the target box regression loss function MSE of this algorithm is prone to small errors being ignored, and the model code is relatively large, which limits its performance due to the high demand for computing hardware performance and storage space. Accordingly, in this study, CIOU loss is introduced to replace MSE, and thus the shortcoming of the inconsistent optimization direction of the original algorithm's loss function is overcome, which also significantly reduces the storage space and computational complexity of the network model. Furthermore, deep separable convolution is used instead of traditional convolution. Deep separable convolution first convolves each channel, and then combines different channels point by point. With the introduction of an inverted residual structure and the use of the h-swish activation function, deep separable convolution based on the MobileNetv3 structure can learn more comprehensive feature representations, which can significantly reduce the computational load of the model while improving its accuracy. The test results showed that the model capacity was reduced by 66%, mAP was increased by 4.68%, and training time was shortened by 6.1 h. Specifically, the correctness rates of malformation recognition induced by local protrusion, local depression, proportional imbalance, and mechanical injury within the test set range were 94.13%, 91.00%, 95.52%, and 91.79%, respectively. Misjudgment mainly stemmed from the limitation of training samples and the original accuracy of the human judgment in type labeling. This study lays a solid foundation for the final establishment of an intelligent recognition and classification picking system for malformed potatoes in the next step. [ABSTRACT FROM AUTHOR]

Wafer characters are used to record the transfer of important information in industrial production and inspection. Wafer character recognition is usually used in the traditional template matching method. However, the accuracy and robustness of the template matching method for detecting complex images are low, which affects production efficiency. An improved model based on YOLO v7-Tiny is proposed for wafer character recognition in complex backgrounds to enhance detection accuracy. In order to improve the robustness of the detection system, the images required for model training and testing are augmented by brightness, rotation, blurring, and cropping. Several improvements were adopted in the improved YOLO model, including an optimized spatial channel attention model (CBAM-L) for better feature extraction capability, improved neck structure based on BiFPN to enhance the feature fusion capability, and the addition of angle parameter to adapt to tilted character detection. The experimental results showed that the model had a value of 99.44% for mAP@0.5 and an F1 score of 0.97. In addition, the proposed model with very few parameters was suitable for embedded industrial devices with small memory, which was crucial for reducing the hardware cost. The results showed that the comprehensive performance of the improved model was better than several existing state-of-the-art detection models. [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]

Radar high-resolution range profile (HRRP) provides geometric and structural information of target, which is important for radar automatic target recognition (RATR). However, due to the limited information dimension of HRRP, achieving accurate target recognition is challenging in applications. In recent years, with the rapid development of radar components and signal processing technology, the acquisition and use of target multi-frequency and polarization scattering information has become a significant way to improve target recognition performance. Meanwhile, deep learning inspired by the human brain has shown great promise in pattern recognition applications. In this paper, a Multi-channel Fusion Feature Extraction Network (MFFE-Net) inspired by the human brain is proposed for dual-band polarimetric HRRP, aiming at addressing the challenges faced in HRRP target recognition. In the proposed network, inspired by the human brain's multi-dimensional information interaction, the similarity and difference features of dual-frequency HRRP are first extracted to realize the interactive fusion of frequency features. Then, inspired by the human brain's selective attention mechanism, the interactive weights are obtained for multi- polarization features and multi-scale representation, enabling feature aggregation and multi-scale fusion. Finally, inspired by the human brain's hierarchical learning mechanism, the layer-by-layer feature extraction and fusion with residual connections are designed to enhance the separability of features. Experiments on simulated and measured datasets verify the accurate recognition capability of MFFE-Net, and ablative studies are conducted to confirm the effectiveness of components of network for recognition. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) has several applications, such as e-learning, human-computer interaction, customer service, and healthcare systems. Although researchers have investigated lots of techniques to improve the accuracy of SER, it has been challenging with feature extraction, classifier schemes, and computational costs. To address the aforementioned problems, we propose a new set of 1D features extracted by using an overlapping sliding window (OSW) technique for SER in this study. In addition, a deep neural network-based classifier scheme called the deep Pattern Recognition Network (PRN) is designed to categorize emotional states from the new set of 1D features. We evaluate the proposed method on the Emo-DB and the AESSD datasets that contain several different emotional states. The experimental results show that the proposed method achieves an accuracy of 98.5% and 87.1% on the Emo-DB and AESSD datasets, respectively. It is also more comparable with accuracy to and better than the state-of-the-art and current approaches that use 1D features on the same datasets for SER. Furthermore, the SHAP (SHapley Additive exPlanations) analysis is employed for interpreting the prediction model to assist system developers in selecting the optimal features to integrate into the desired system. [ABSTRACT FROM AUTHOR]