Recognition Precision Research Articles

Frequency and Spatial Domain-Based Approaches for Recognition of Indian Sign Language Gestures

Objectives: The objective of this paper is to introduce and demonstrate an innovative approach for the recognition of Indian sign language gestures, with a focus on bridging communication gap between the deaf and hearing communities. The goal is to contribute to the development of effective tools and technologies that facilitate seamless communication between individuals using sign language and the people with no knowledge about sign language. Methods: The methodology consists of three key steps. First, data pre-processing involves resizing and contours extraction. Next, feature extraction employs Fourier descriptors for frequency domain analysis and gray-level-co-occurrence matrix for spatial domain analysis. Finally, various machine learning models including SVM, Random Forest, Logistic Regression, K-Nearest Neighbor and Naive Bayes are trained on a standard dataset. Findings: In our controlled experimental setup, we applied a diverse set of machine learning classifiers to evaluate the proposed approach for gesture recognition. Among the classifiers tested, K-Nearest Neighbors demonstrated the highest accuracy, achieving 99.82%. To validate the robustness of our approach, we employed k-fold cross-validation with 5 folds. Novelty: This study presents an innovative method for sign language recognition by employing a dual-domain fusion strategy that prominently emphasizes the frequency domain. Through the integration of Fourier descriptors, the research conducts a detailed frequency domain analysis to characterize the contour shapes of sign language gestures. The synergy with gray-level co-occurrence matrix texture features in the spatial domain analysis, contributes to the creation of a comprehensive feature vector. The proposed approach ensures a thorough exploration of gesture features, there by advancing the precision and efficacy of sign language recognition. Keywords: Indian Sign Language (ISL), Sign Language Recognition (SLR), Frequency domain, Spatial domain, Fourier descriptors, Gray level co­occurrence matrix (GLCM), K­ Fold

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system.

A Dual-Branch Spatio-Temporal-Spectral Transformer Feature Fusion Network for EEG-Based Visual Recognition

Recognizing visual objects from single-trial electroencephalograph (EEG) signals is a promising brain-computer interface (BCI) technology. However, due to the redundant features from noisy multi-channel EEG signals, it is still a challenging task to achieve high precision recognition. Recent deep learning approaches commonly extract spatio-temporal features of EEG signals, which neglect important spectral-temporal features and may degrade the EEG recognition performance. To address the deficiency, we propose a novel channel attention weighting and multi-level adaptive spectral aggregation based dual-branch spatio-temporal-spectral Transformer feature fusion network (CAW-MASA-STST) for EEG-based visual recognition. Specially, we first develop a channel attention weighting (CAW) to automatically learn the channel weights of EEG signals. Then, a graph convolution-based multi-level adaptive spectral aggregation (MASA) is employed to aggregate spectral-temporal features of different sub-bands. Finally, a spatio-temporal-spectral Transformer (STST) is designed to fuse spatio-temporal and spectral-temporal features, which enhances the comprehensive learning ability by modeling the temporal dependencies of the fused features. Competitive experimental results on two public datasets demonstrate that the proposed method is able to achieve superior recognition performance compared with the state-of-the-art methods, indicating a feasible solution for visual recognition-based BCI technology. The code of our proposed method will be available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ljbuaa/VisualDecoding</uri> .

Advancing speed limit detection in ADAS: A novel data-driven approach using Pareto-GBDTMO

Recognizing speed limit information is crucial for advanced driver assistance systems (ADAS) as it directly affects the safety planning and decision-making process of intelligent driving systems. However, traditional image recognition-based solutions confront inherent restrictions and precision issues due to uncontrolled external factors. This paper endeavors to present a novel, data-driven solution for speed limit information recognition that leverages the stability and maturity of data-driven technologies, overcoming these challenges. We introduce Pareto-GBDTMO, a cutting-edge method that synergistically blends Gradient Boosting Decision Trees for Multiple Output (GBDT-MO) and Fast Pareto Feature Selection (FPFS). This integration is instrumental in discerning salient features to direct and expedite the learning process of GBDT-MO. When coupled with Bayesian optimization, the feature set undergoes dynamic updates at each boosting iteration, allowing GBDT-MO to concentrate on the most prominent features. This adaptive, relevance-guided feature space regularization mechanism enhances the efficiency and precision of speed limit recognition. Fujian Province highway electronic toll collection (ETC) data is used for further validation, and the experimental results emphasize the effectiveness of our model, with an high accuracy of 97%, a low loss rate of 0.7%, and minimal latency. These findings affirm the feasibility and scientific validity of our data-driven approach, offering a reliable and redundant solution for speed limit information recognition in ADAS. This study not only contributes to the practical application of ADAS but also lays the groundwork for future large-scale lane-level data research

Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion.

To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.

Skin Conductance-Based Acupoint and Non-Acupoint Recognition Using Machine Learning.

Acupoints (APs) prove to have positive effects on disease diagnosis and treatment, while intelligent techniques for the automatic detection of APs are not yet mature, making them more dependent on manual positioning. In this paper, we realize the skin conductance-based APs and non-APs recognition with machine learning, which could assist in APs detection and localization in clinical practice. Firstly, we collect skin conductance of traditional Five-Shu Point and their corresponding non-APs with wearable sensors, establishing a dataset containing over 36000 samples of 12 different AP types. Then, electrical features are extracted from the time domain, frequency domain, and nonlinear perspective respectively, following which typical machine learning algorithms (SVM, RF, KNN, NB, and XGBoost) are demonstrated to recognize APs and non-APs. The results demonstrate XGBoost with the best precision of 66.38%. Moreover, we also quantify the impacts of the differences among AP types and individuals, and propose a pairwise feature generation method to weaken the impacts on recognition precision. By using generated pairwise features, the recognition precision could be improved by 7.17%. The research systematically realizes the automatic recognition of APs and non-APs, and is conducive to pushing forward the intelligent development of APs and Traditional Chinese Medicine theories.

A high precision recognition method for small area fingerprints based on machine vision

A high precision recognition method for small area fingerprints based on machine vision

A High Precision Recognition Method for Small Area Fingerprints Based on Machine Vision

A High Precision Recognition Method for Small Area Fingerprints Based on Machine Vision

Machine learning-enhanced gesture recognition through impedance signal analysis.

Gesture recognition is a crucial aspect in the advancement of virtual reality, healthcare, and human-computer interaction, and requires innovative methodologies to meet the increasing demands for precision. This paper presents a novel approach that combines Impedance Signal Spectrum Analysis (ISSA) with machine learning to improve gesture recognition precision. A diverse dataset that included participants from various demographic backgrounds (five individuals) who were each executing a range of predefined gestures. The predefined gestures were designed to encompass a broad spectrum of hand movements, including intricate and subtle variations, to challenge the robustness of the proposed methodology. The machine learning model using the K-Nearest Neighbors (KNN), Gradient Boosting Machine (GBM), Naive Bayes (NB), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms demonstrated notable precision in performance evaluations. The individual accuracy values for each algorithm are as follows: KNN, 86%; GBM, 86%; NB, 84%; LR, 89%; RF, 87%; and SVM, 87%. These results emphasize the importance of impedance features in the refinement of gesture recognition. The adaptability of the model was confirmed under different conditions, highlighting its broad applicability.

Time to Think the Security of WiFi-Based Behavior Recognition Systems

Behavior recognition plays an essential role in numerous behavior-driven applications ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e</i> . <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">g</i> ., virtual reality and smart home) and even in the security-critical applications ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e</i> . <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">g</i> ., security surveillance and elder healthcare). Recently, WiFi-based behavior recognition (WBR) technique stands out among many behavior recognition techniques due to its advantages of being non-intrusive, device-free, and ubiquitous. However, existing WBR research mainly focuses on improving the recognition precision, while rarely studying the security aspects. In this paper, we reveal that WBR systems are vulnerable to manipulating physical signals. For instance, our observation shows that WiFi signals can be changed by jamming signals. By exploiting the vulnerability, we propose two approaches to generate physically online adversarial samples to perform untargeted attack and targeted attack, respectively. The effectiveness of these attacks are extensively evaluated over four real-world WBR systems. The experiment results show that our attack approaches can achieve 80% and 60% success rates for untargeted attack and targeted attack in physical world, respectively. We also show that our attack approaches can be generalized to other WiFi-based sensing applications, such as user authentication.

A Multimodal Biometric System for Iris and Face Traits Based on Hybrid Approaches and Score Level Fusion

The increasing need for information security on a worldwide scale has led to the widespread adoption of appropriate rules. Multimodal biometric systems have become an effective way to increase recognition precision, strengthen security guarantees, and reduce the drawbacks of unimodal biometric systems. These systems combine several biometric characteristics and sources by using fusion methods. Through score-level fusion, this work integrates facial and iris recognition techniques to present a multimodal biometric recognition methodology. The Histogram of Oriented Gradients (HOG) descriptor is used in the facial recognition system to extract facial characteristics, while the deep Wavelet Scattering Transform Network (WSTN) is applied in the iris recognition system to extract iris features. Then, for customized recognition classification, the feature vectors from every facial and iris recognition system are fed into a multiclass logistic regression. These systems provide scores, which are then combined via score-level fusion to maximize the efficiency of the human recognition process. The realistic multimodal database known as (MULB) is used to assess the suggested system's performance. The suggested technique exhibits improved performance across several measures, such as precision, recall, accuracy, equal error rate, false acceptance rate, and false rejection rate, as demonstrated by the experimental findings. The face and iris biometric systems have individual accuracy rates of 96.45% and 95.31% respectively. The equal error rates for the face and iris are 1.79% and 2.36% respectively. Simultaneously, the proposed multimodal biometric system attains a markedly enhanced accuracy rate of 100% and an equal error rate as little as 0.26%.

Component Recognition and Coordinate Extraction in Two-Dimensional Paper Drawings Using SegFormer

Within the domain of architectural urban informatization, the automated precision recognition of two-dimensional paper schematics emerges as a pivotal technical challenge. Recognition methods traditionally employed frequently encounter limitations due to the fluctuating quality of architectural drawings and the bounds of current image processing methodologies, inhibiting the realization of high accuracy. The research delineates an innovative framework that synthesizes refined semantic segmentation algorithms with image processing techniques and precise coordinate identification methods, with the objective of enhancing the accuracy and operational efficiency in the identification of architectural elements. A meticulously curated data set, featuring 13 principal categories of building and structural components, facilitated the comprehensive training and assessment of two disparate deep learning models. The empirical findings reveal that these algorithms attained mean intersection over union (MIoU) values of 96.44% and 98.01% on the evaluation data set, marking a substantial enhancement in performance relative to traditional approaches. In conjunction, the framework’s integration of the Hough Transform with SQL Server technology has significantly reduced the coordinate detection error rates for linear and circular elements to below 0.1% and 0.15%, respectively. This investigation not only accomplishes the efficacious transition from analog two-dimensional paper drawings to their digital counterparts, but also assures the precise identification and localization of essential architectural components within the digital image coordinate framework. These developments are of considerable importance in furthering the digital transition within the construction industry and establish a robust foundation for the forthcoming extension of data collections and the refinement of algorithmic efficacy.

A novel object recognition method for photovoltaic (PV) panel occlusion based on deep learning

During the long-term operation of the photovoltaic (PV) system, occlusion will reduce the solar radiation energy received by the PV module, as well as the photoelectric conversion efficiency and economy. However, the occlusion detection of the PV power station has the defects of low efficiency, poor accuracy, and untimely detection, which will cause unknown system losses. Based on the deep learning algorithm, this paper conducts research on PV module occlusion detection. In order to accurately obtain the occlusion area and position information of the PV panel, a PV module occlusion detection model based on the Segment-You Only Look Once (Seg-YOLO) algorithm is established. Based on the YOLOv5 algorithm, the loss function is modified, the Segment Head detection module is introduced, and the convolutional block attention module (CBAM) attention mechanism is added to achieve the accurate detection of small targets by the algorithm model and the fast detection of the PV module occlusion area identify. The model performance research is carried out on three types of occlusion datasets: leaf, bird dropping, and shadow. According to the experimental results, the proposed model has better recognition accuracy and speed than SSD, Faster-Rcnn, YOLOv4, and U-Net. The precision rate, recall rate, and recognition speed can reach 90.52%, 92.41%, and 92.3 FPS, respectively. This model can lay a theoretical foundation for the intelligent operation and maintenance of PV systems.

Filter bank second-order underdamped stochastic resonance analysis for implementing a short-term high-speed SSVEP detection

ObjectiveThe progression of brain-computer interfaces (BCIs) has been propelled by breakthroughs in neuroscience, signal processing, and machine learning, marking it as a dynamic field of study over the past few decades. Nevertheless, the nonlinear and non-stationary characteristics of steady-state visual evoked potentials (SSVEPs), coupled with the incongruity between frequently employed linear techniques and nonlinear signal attributes, resulted in the subpar performance of mainstream non-training algorithms like canonical correlation analysis (CCA), multivariate synchronization index (MSI), and filter bank CCA (FBCCA) in short-term SSVEP detection. MethodsTo tackle this problem, the novel fusions of common filter bank analysis, CCA dimensionality reduction methods, USSR models, and MSI recognition models are used in SSVEP signal recognition. ResultsUnlike conventional linear techniques such as CCA, MSI, and FBCCA, the filter bank second-order underdamped stochastic resonance (FBUSSR) analysis demonstrates superior efficacy in the detection of short-term high-speed SSVEPs. ConclusionThis research enlists 32 subjects and uses a public dataset to assess the proposed approach, and the experimental outcomes indicate that the non-training method can attain greater recognition precision and stability. Furthermore, under the conditions of the newly proposed fusion method and light stimulation, the USSR model exhibits the most optimal enhancement effect. SignificanceThe findings of this study underscore the expansive potential for the application of BCI systems in the realm of neuroscience and signal processing.

Landmark Topology Descriptor-Based Place Recognition and Localization under Large View-Point Changes.

Accurate localization between cameras is a prerequisite for a vision-based heterogeneous robot systems task. The core issue is how to accurately perform place recognition from different view-points. Traditional appearance-based methods have a high probability of failure in place recognition and localization under large view-point changes. In recent years, semantic graph matching-based place recognition methods have been proposed to solve the above problem. However, these methods rely on high-precision semantic segmentation results and have a high time complexity in node extraction or graph matching. In addition, methods only utilize the semantic labels of the landmarks themselves to construct graphs and descriptors, making such approaches fail in some challenging scenarios (e.g., scene repetition). In this paper, we propose a graph-matching method based on a novel landmark topology descriptor, which is robust to view-point changes. According to the experiment on real-world data, our algorithm can run in real-time and is approximately four times and three times faster than state-of-the-art algorithms in the graph extraction and matching phases, respectively. In terms of place recognition performance, our algorithm achieves the best place recognition precision at a recall of 0-70% compared with classic appearance-based algorithms and an advanced graph-based algorithm in the scene of significant view-point changes. In terms of positioning accuracy, compared to the traditional appearance-based DBoW2 and NetVLAD algorithms, our method outperforms by 95%, on average, in terms of the mean translation error and 95% in terms of the mean RMSE. Compared to the state-of-the-art SHM algorithm, our method outperforms by 30%, on average, in terms of the mean translation error and 29% in terms of the mean RMSE. In addition, our method outperforms the current state-of-the-art algorithm, even in challenging scenarios where the benchmark algorithms fail.

An Improved YOLOv5-Based Lightweight Submarine Target Detection Algorithm.

Submarine recognition plays a critical role in maritime security and military defense. However, traditional submarine recognition algorithms face limitations in feature representation capability and robustness. Additionally, deploying deep learning methods on embedded and mobile platforms presents a bottleneck. To address these challenges, we propose an innovative and practical approach-an improved YOLOv5-based lightweight submarine automatic recognition detection algorithm. Our method leverages the Feature Pyramid based on MobileNetV3 and the C3_DS module to reduce computation and parameter complexity while ensuring high precision in submarine recognition. The integration of the adaptive neck from the SA-net strategy further mitigates missed detections, significantly enhancing the accuracy of submarine target detection and recognition. We evaluated our improved model on a submarine dataset, and the results demonstrate remarkable advancements in Precision, Recall, and mAP0.5, with respective increases of 8.54%, 6.02%, and 3.36%. Moreover, we achieved a notable reduction of 34.1% in parameter quantity and 67.9% in computational complexity, showcasing its lightweight effects. Overall, our proposed method introduces novel improvements to submarine recognition, addressing existing limitations and offering practical benefits for real-world deployment on embedded and mobile platforms. The enhanced performance in precision and recall metrics, coupled with reduced computational requirements, emphasizes the significance of our approach in enhancing maritime security and military applications.

High precision of sign language recognition based on In2O3 transistors gated by AlLiO solid electrolyte

In recent years, the synaptic properties of transistors have been extensively studied. Compared with liquid or organic material-based transistors, inorganic solid electrolyte-gated transistors have the advantage of better chemical stability. This study uses a simple, low-cost solution technology to prepare In2O3 transistors gated by AlLiO solid electrolyte. The electrochemical performance of the device is achieved by forming a double electric layer and electrochemical doping, which can mimic basic functions of biological synapses, such as excitatory postsynaptic current, paired-pulse promotion, and spiking time-dependent plasticity. Furthermore, complex synaptic behaviors such as Pavlovian classical conditioning is successfully emulated. With a 95% identification accuracy, an artificial neural network based on transistors is built to recognize sign language and enable sign language interpretation. Additionally, the handwriting digit’s identification accuracy is 94%. Even with various levels of Gaussian noise, the recognition rate is still above 84%. The above findings demonstrate the potential of In2O3/AlLiO TFT in shaping the next generation of artificial intelligence.

Changeable moving window-standard normal variable transformation for visible-NIR spectroscopic analyses

Based on the assumption of point-by-point local linearity, the changeable moving window-standard normal variable (CMW-SNV) was proposed as a reasonable improvement of the classical SNV. The three examples of quantitative and qualitative visible-near-infrared (Vis-NIR) analysis, quantifications of soil organic matter and corn meal moisture, and discriminant of rice seeds identification, were used to validate the effects of the CMW-SNV, SNV and equal segmentation SNV (ES-SNV) methods. The ES-SNV is another improvement of the SNV, but its algorithm would cause artificial discontinuities of the corrected spectrum. The SNV, ES-SNV and CMW-SNV corrected spectra were used to establish partial least squares (PLS) or partial least squares-discriminant analysis (PLS-DA) models respectively. For soil and corn meal datasets in modeling, the CMW-SNV-PLS models were both significantly better than the global SNV-PLS models; the root mean square errors of prediction in modeling (SEPM) values had the relative decrease of 26.4% and 6.6% respectively. For rice seeds dataset in modeling, the CMW-SNV-PLS-DA model was significantly better than the global SNV-PLS-DA model; the total recognition-accuracy rates in modeling (RARM) value increased by 2.1%. For all three datasets, the CMW-SNV models were better than (or close to) ones of the ES-SNV models. The equidistant combination (EC) and wavelength step-by-step phase-out (WSP) methods were used to perform wavelength selection on the CMW-SNV corrected spectra, determining the optimal EC-WSP-PLS or EC-WSP-PLS-DA models. In independent validation of three datasets, the high precision and high recognition accuracy rates validation results were all obtained. The CMW-SNV was a localized natural improvement of the classic global SNV method, and its correction maintained continuity of the spectra. The number of wavelengths m of the correction window represented the scale of localized SNV, and the algorithm platform of CMW-SNV also included the optimization of parameter m, making the localized CMW-SNV method more reasonable.

Optimal Deep Learning-Based Recognition Model for EEG Enabled Brain-Computer Interfaces Using Motor-Imagery

Abstract Brain-Computer Interfaces (BCIs) facilitate the translation of brain activity into actionable commands and act as a crucial link between the human brain and the external environment. Electroencephalography (EEG)-based BCIs, which focus on motor imagery, have emerged as an important area of study in this domain. They are used in neurorehabilitation, neuroprosthetics, and gaming, among other applications. Optimal Deep Learning-Based Recognition for EEG Signal Motor Imagery (ODLR-EEGSM) is a novel approach presented in this article that aims to improve the recognition of motor imagery from EEG signals. The proposed method includes several crucial stages to improve the precision and effectiveness of EEG-based motor imagery recognition. The pre-processing phase starts with the Variation Mode Decomposition (VMD) technique, which is used to improve EEG signals. The EEG signals are decomposed into different oscillatory modes by VMD, laying the groundwork for subsequent feature extraction. Feature extraction is a crucial component of the ODLR-EEGSM method. In this study, we use Stacked Sparse Auto Encoder (SSAE) models to identify significant patterns in the pre-processed EEG data. Our approach is based on the classification model using Deep Wavelet Neural Network (DWNN) optimized with Chaotic Dragonfly Algorithm (CDFA). CDFA optimizes the weight and bias values of the DWNN, significantly improving the classification accuracy of motor imagery. To evaluate the efficacy of the ODLR-EEGSM method, we use benchmark datasets to perform rigorous performance validation. The results show that our approach outperforms current methods in the classification of EEG motor imagery, confirming its promising performance. This study has the potential to make brain-computer interface applications in various fields more accurate and efficient, and pave the way for brain-controlled interactions with external systems and devices.

A multimedia art interaction model for motion recognition based on data-driven model

Ergonomics is a relatively important part of user experience in multimedia art design. The study aims to improve human–computer interaction efficiency using a data-driven neural network model combined with video data and wearable devices to achieve high-precision human motion recognition. Firstly, the human motion skeleton information is extracted based on video information through the OpenPose framework, and the motion characteristics of each joint of the human body are calculated. Then, use the inertia data of the wearable bracelet to calculate the exercise intensity. At last, the two kinds of information are sent to recurrent neural networks (RNN) together to achieve high-precision human motion recognition. The innovative contribution of the article is to establish a multimodal fusion model for human activity recognition. The experimental results show that the recognition precision of the proposed method reaches 97.85%, much higher than the backpropagation neural network (BPNN) and K-nearest neighbor (KNN), whose precision is 94.35% and 90.12%, respectively. The method’s superior performance convinces us that the model can provide strong technical support for the interaction design of multimedia art.