Pub Date : 2025-02-22DOI: 10.1016/j.rcim.2025.102988
Haiming Zhang , Jianzhong Yang , Song Gao , Xiumei Gong , Wanqiang Zhu
Hybrid machine tools (HMTs), known for their fast response speed, high stiffness, and accuracy, have found wide applications in aerospace and other industries. However, maintaining stability and durability during high-speed machining necessitates careful feedrate scheduling. This study introduces a novel feedrate scheduling method for 3-prismatic-revolute-spherical (3-PRS) HMTs, ensuring that the velocities and accelerations of the drive axes remain within predefined ranges. Initially, the velocity and acceleration dynamics of the 3-PRS mechanism were scrutinized using the screw theory. Subsequently, a virtual axis programming method was introduced, transforming the HMT into a virtual double-pendulum five-axis serial machine tool. In addition, the space of the master–slave movement (SMM) concept is proposed to define the toolpath. Moreover, a strategy for constraining the tool center point rate and acceleration was devised based on the kinematic relationships between the drive axes, virtual axes, and tool center points. Simulation and experiment validated the efficacy of the feedrate scheduling method, demonstrating compliance with the kinematic constraints of the drive axes and enhanced machining efficiency.
{"title":"Feedrate scheduling method for 3-PRS hybrid machine tools considering kinematic constraints","authors":"Haiming Zhang , Jianzhong Yang , Song Gao , Xiumei Gong , Wanqiang Zhu","doi":"10.1016/j.rcim.2025.102988","DOIUrl":"10.1016/j.rcim.2025.102988","url":null,"abstract":"<div><div>Hybrid machine tools (HMTs), known for their fast response speed, high stiffness, and accuracy, have found wide applications in aerospace and other industries. However, maintaining stability and durability during high-speed machining necessitates careful feedrate scheduling. This study introduces a novel feedrate scheduling method for 3-prismatic-revolute-spherical (3-PRS) HMTs, ensuring that the velocities and accelerations of the drive axes remain within predefined ranges. Initially, the velocity and acceleration dynamics of the 3-PRS mechanism were scrutinized using the screw theory. Subsequently, a virtual axis programming method was introduced, transforming the HMT into a virtual double-pendulum five-axis serial machine tool. In addition, the space of the master–slave movement (SMM) concept is proposed to define the toolpath. Moreover, a strategy for constraining the tool center point rate and acceleration was devised based on the kinematic relationships between the drive axes, virtual axes, and tool center points. Simulation and experiment validated the efficacy of the feedrate scheduling method, demonstrating compliance with the kinematic constraints of the drive axes and enhanced machining efficiency.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102988"},"PeriodicalIF":9.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.engappai.2025.110314
Chengyan Du, Fu Liu, Bing Kang, Tao Hou
There is an urgent need to determine emotions automatically through speech signals to promote the progress of intelligent technology. However, the low accuracy problem isn't solved so far as, this hinders potential applications of Speech Emotion Recognition (SER). One of the most critical reasons for this low accuracy is that subjective emotions are random and generate weak pulse signals; moreover, they are often hidden in audio, video, and text feature which are extracted from speech. Hence, the features may not be discriminative enough to depict subjective emotions. Therefore, a dual-path SER framework is designed in this paper. Added to the traditional Convolutional Neural Network (CNN)-based SER scheme to handle speech emotion features, the Spiking Neural Network (SNN) framework is added to identify the dynamic pulse emotion features and improve the accuracy of SER. At the same time, a Perceptual Neuron Encoding Layer (PNEL) is proposed to enhance the ability to process speech signals. Overall, the experimental results on the interactive emotional dyadic motion capture database (IEMOCAP) databases show that the proposed approach can achieve 65.3% accuracy and excellent performance in solving the SER issues compared to other existing approaches.
{"title":"Speech emotion recognition based on spiking neural network and convolutional neural network","authors":"Chengyan Du, Fu Liu, Bing Kang, Tao Hou","doi":"10.1016/j.engappai.2025.110314","DOIUrl":"10.1016/j.engappai.2025.110314","url":null,"abstract":"<div><div>There is an urgent need to determine emotions automatically through speech signals to promote the progress of intelligent technology. However, the low accuracy problem isn't solved so far as, this hinders potential applications of Speech Emotion Recognition (SER). One of the most critical reasons for this low accuracy is that subjective emotions are random and generate weak pulse signals; moreover, they are often hidden in audio, video, and text feature which are extracted from speech. Hence, the features may not be discriminative enough to depict subjective emotions. Therefore, a dual-path SER framework is designed in this paper. Added to the traditional Convolutional Neural Network (CNN)-based SER scheme to handle speech emotion features, the Spiking Neural Network (SNN) framework is added to identify the dynamic pulse emotion features and improve the accuracy of SER. At the same time, a Perceptual Neuron Encoding Layer (PNEL) is proposed to enhance the ability to process speech signals. Overall, the experimental results on the interactive emotional dyadic motion capture database (IEMOCAP) databases show that the proposed approach can achieve 65.3% accuracy and excellent performance in solving the SER issues compared to other existing approaches.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"147 ","pages":"Article 110314"},"PeriodicalIF":7.5,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computing betweenness centrality (BC) in large graphs is crucial for various applications, including telecommunications, social, and biological networks. However, the huge size of the data presents significant challenges. In this paper, we introduce a novel approximate approach for efficiently extracting top k BC nodes by combining the Louvain community detection algorithm with Brandes' algorithm. Our method significantly enhances the runtime efficiency of the traditional Brandes' algorithm while preserving accuracy across both synthetic and real-world datasets. Additionally, our approach is suitable for parallelization, further improving its efficiency. Experimental results confirm the effectiveness of our method for large and sparse graphs.
{"title":"Efficient Parallel Algorithm for Approximating Betweenness Centrality Values of Top k Nodes in Large Graphs","authors":"Ismail H. Toroslu, Gadir Suleymanli","doi":"10.1002/cpe.70022","DOIUrl":"https://doi.org/10.1002/cpe.70022","url":null,"abstract":"<div>\u0000 \u0000 <p>Computing betweenness centrality (BC) in large graphs is crucial for various applications, including telecommunications, social, and biological networks. However, the huge size of the data presents significant challenges. In this paper, we introduce a novel approximate approach for efficiently extracting top <i>k</i> BC nodes by combining the Louvain community detection algorithm with Brandes' algorithm. Our method significantly enhances the runtime efficiency of the traditional Brandes' algorithm while preserving accuracy across both synthetic and real-world datasets. Additionally, our approach is suitable for parallelization, further improving its efficiency. Experimental results confirm the effectiveness of our method for large and sparse graphs.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143466145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.conengprac.2025.106269
Maria Khodaverdian , Yeva Gabrielyan , Aleksandr Hakobyan , Salaman Ijaz , Paolo Castaldi
This work introduces a novel predictor-based integral sliding mode control scheme, designed for spacecraft attitude control. By leveraging Taylor series expansion, we develop predictor dynamics for the sliding surface and its integral, along with the corresponding reaching laws. Subsequently, we formulate a constrained quadratic optimization problem to derive the optimal control input. A notable aspect of the proposed method is the integration of the sliding surface’s integral into the control design, which significantly enhances robustness. Additionally, the proposed approach ensures optimality, fault tolerance capability, fixed-time convergence, computational efficiency, and effective constraint management. In this work, we perform a closed-loop stability analysis to confirm system stability in the presence of external perturbations, and constraints. Comparison results with existing method demonstrate that the proposed approach enhances performance while maintaining satisfactory precision. To validate the practical applicability of our algorithm, we conduct hardware-in-the-loop simulations, demonstrating the proposed method’s seamless integration with real-world hardware.
{"title":"A novel predictor based optimal integral sliding-mode-based attitude tracking control of spacecraft under actuator’s uncertainties and constraints","authors":"Maria Khodaverdian , Yeva Gabrielyan , Aleksandr Hakobyan , Salaman Ijaz , Paolo Castaldi","doi":"10.1016/j.conengprac.2025.106269","DOIUrl":"10.1016/j.conengprac.2025.106269","url":null,"abstract":"<div><div>This work introduces a novel predictor-based integral sliding mode control scheme, designed for spacecraft attitude control. By leveraging Taylor series expansion, we develop predictor dynamics for the sliding surface and its integral, along with the corresponding reaching laws. Subsequently, we formulate a constrained quadratic optimization problem to derive the optimal control input. A notable aspect of the proposed method is the integration of the sliding surface’s integral into the control design, which significantly enhances robustness. Additionally, the proposed approach ensures optimality, fault tolerance capability, fixed-time convergence, computational efficiency, and effective constraint management. In this work, we perform a closed-loop stability analysis to confirm system stability in the presence of external perturbations, and constraints. Comparison results with existing method demonstrate that the proposed approach enhances performance while maintaining satisfactory precision. To validate the practical applicability of our algorithm, we conduct hardware-in-the-loop simulations, demonstrating the proposed method’s seamless integration with real-world hardware.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"158 ","pages":"Article 106269"},"PeriodicalIF":5.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1007/s10489-025-06342-3
Tong Sun, Yipeng Ding, Yuxin Chen, Lv Ping
Radar-based human motion recognition (HMR) technology has gained substantial importance across diverse domains such as security surveillance, post-disaster search and rescue operations, and the development of smart home environments. The intricate nature of human movements generates radar echo signals with pronounced non-stationary attributes, which encapsulate a wealth of target feature data. However, striking a balance between the precision of motion recognition and the requirement for real-time processing, especially in the context of extracting meaningful features from radar signals, remains a formidable challenge. This research paper introduces a novel approach to tackle this challenge. Firstly,we apply the multi-order fractional Fourier transform (m-FRFT) to radar echo signals, facilitating the extraction of micro-Doppler (m-D) frequency information. Secondly, we have developed an optimized feature selection model named MPG, which stands for m-D parameter screening based on genetic algorithm (GA) and adaptive weight particle swarm optimization (AWPSO). Thirdly, we apply the MPG model to the recursive feature elimination (RFE) algorithm to refine the representation of m-D frequency information, allowing for adaptive parameter adjustment and effective feature dimensionality reduction. The proposed method has been tested using human motion echo data collected from a Doppler radar prototype. The experimental outcomes demonstrate that our approach outperforms traditional feature extraction methods in terms of reducing feature dimensionality, computational efficiency, and classification accuracy.
{"title":"Feature optimization based on multi-order fusion and adaptive recursive elimination for motion classification in doppler radar","authors":"Tong Sun, Yipeng Ding, Yuxin Chen, Lv Ping","doi":"10.1007/s10489-025-06342-3","DOIUrl":"10.1007/s10489-025-06342-3","url":null,"abstract":"<div><p>Radar-based human motion recognition (HMR) technology has gained substantial importance across diverse domains such as security surveillance, post-disaster search and rescue operations, and the development of smart home environments. The intricate nature of human movements generates radar echo signals with pronounced non-stationary attributes, which encapsulate a wealth of target feature data. However, striking a balance between the precision of motion recognition and the requirement for real-time processing, especially in the context of extracting meaningful features from radar signals, remains a formidable challenge. This research paper introduces a novel approach to tackle this challenge. Firstly,we apply the multi-order fractional Fourier transform (m-FRFT) to radar echo signals, facilitating the extraction of micro-Doppler (m-D) frequency information. Secondly, we have developed an optimized feature selection model named MPG, which stands for m-D parameter screening based on genetic algorithm (GA) and adaptive weight particle swarm optimization (AWPSO). Thirdly, we apply the MPG model to the recursive feature elimination (RFE) algorithm to refine the representation of m-D frequency information, allowing for adaptive parameter adjustment and effective feature dimensionality reduction. The proposed method has been tested using human motion echo data collected from a Doppler radar prototype. The experimental outcomes demonstrate that our approach outperforms traditional feature extraction methods in terms of reducing feature dimensionality, computational efficiency, and classification accuracy.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.engappai.2025.110361
Ren Li , Luyi Zhang , Qiao Xiao , Jianxi Yang , Yu Chen , Shixin Jiang , Di Wang
With the wide application of information technologies in the field of bridge engineering, many electronic bridge inspection reports have been generated. However, due to insufficient research on machine reading comprehension (MRC) in this field, a lot of bridge inspection information, e.g., structural basic data, inspected defects, and maintenance suggestions, has not been fully used. Especially, it is time-consuming and labor-intensive to pre-train a domain-specific language model from scratch or annotate large-scale question answering corpora, which also brings challenges to the MRC research in this field. To tackle the problems, this paper proposes a novel few-shot MRC approach for bridge inspection based on the idea of data augmentation. The proposed model uses a pre-trained model as backbone, along with introducing a pre-tuning stage to bridge the gaps between general-purpose pre-training and domain-specific MRC tasks. In order to reduce the workload of manual annotation, we present a novel pre-tuning data generation algorithm which is based on the domain-specific question classification and answer prediction neural models. After pre-tuning and fine-tuning, the proposed model achieves efficient bridge inspection MRC. The experimental results show that the proposed model outperforms the mainstream fine-tuning-based approaches and few-shot MRC baseline models in various settings. With 1024 fine-tuning samples, the F1 value and Exact Match (EM) value are 86.42%, 74.65%, respectively. Our research work can serve as a foundation for the construction of automatic question answering systems for intelligent bridge management and maintenance.
{"title":"Few-shot machine reading comprehension for bridge inspection via domain-specific and task-aware pre-tuning approach","authors":"Ren Li , Luyi Zhang , Qiao Xiao , Jianxi Yang , Yu Chen , Shixin Jiang , Di Wang","doi":"10.1016/j.engappai.2025.110361","DOIUrl":"10.1016/j.engappai.2025.110361","url":null,"abstract":"<div><div>With the wide application of information technologies in the field of bridge engineering, many electronic bridge inspection reports have been generated. However, due to insufficient research on machine reading comprehension (MRC) in this field, a lot of bridge inspection information, e.g., structural basic data, inspected defects, and maintenance suggestions, has not been fully used. Especially, it is time-consuming and labor-intensive to pre-train a domain-specific language model from scratch or annotate large-scale question answering corpora, which also brings challenges to the MRC research in this field. To tackle the problems, this paper proposes a novel few-shot MRC approach for bridge inspection based on the idea of data augmentation. The proposed model uses a pre-trained model as backbone, along with introducing a pre-tuning stage to bridge the gaps between general-purpose pre-training and domain-specific MRC tasks. In order to reduce the workload of manual annotation, we present a novel pre-tuning data generation algorithm which is based on the domain-specific question classification and answer prediction neural models. After pre-tuning and fine-tuning, the proposed model achieves efficient bridge inspection MRC. The experimental results show that the proposed model outperforms the mainstream fine-tuning-based approaches and few-shot MRC baseline models in various settings. With 1024 fine-tuning samples, the F1 value and Exact Match (EM) value are 86.42%, 74.65%, respectively. Our research work can serve as a foundation for the construction of automatic question answering systems for intelligent bridge management and maintenance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"147 ","pages":"Article 110361"},"PeriodicalIF":7.5,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.softx.2025.102095
Çağla Sarvan Cibil , Nalan Özkurt
Wavelet theory (WT) is essential for analyzing non-stationary signals, particularly in real-world applications requiring time-frequency analysis. A key challenge is to identify the optimal wavelet function that matches signal characteristics, enabling efficient and precise analysis. This study presents WaveConstLib, an open-source Java library for wavelet analysis and construction. It provides tools to create wavelet functions tailored to specific signals while adhering to WT conditions. Unlike traditional methods, WaveConstLib employs multi-objective evolutionary algorithms (MOEAs) optimization to construct signal-specific wavelet functions, ensuring superior adaptability and performance. The library includes numerical implementations of first-generation wavelet construction techniques, along with signal processing tools, wavelet operations, and transformations applicable to diverse tasks. WaveConstLib simplifies the construction of wavelet functions that extract distinctive signal information and supports integration into external systems, making it a valuable resource for research and practical applications.
{"title":"WaveConstLib: A java library for signal analysis and wavelet construction","authors":"Çağla Sarvan Cibil , Nalan Özkurt","doi":"10.1016/j.softx.2025.102095","DOIUrl":"10.1016/j.softx.2025.102095","url":null,"abstract":"<div><div>Wavelet theory (WT) is essential for analyzing non-stationary signals, particularly in real-world applications requiring time-frequency analysis. A key challenge is to identify the optimal wavelet function that matches signal characteristics, enabling efficient and precise analysis. This study presents WaveConstLib, an open-source Java library for wavelet analysis and construction. It provides tools to create wavelet functions tailored to specific signals while adhering to WT conditions. Unlike traditional methods, WaveConstLib employs multi-objective evolutionary algorithms (MOEAs) optimization to construct signal-specific wavelet functions, ensuring superior adaptability and performance. The library includes numerical implementations of first-generation wavelet construction techniques, along with signal processing tools, wavelet operations, and transformations applicable to diverse tasks. WaveConstLib simplifies the construction of wavelet functions that extract distinctive signal information and supports integration into external systems, making it a valuable resource for research and practical applications.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"30 ","pages":"Article 102095"},"PeriodicalIF":2.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A Sagnac ring with parity-time (PT) symmetry design is included to the L-band EDF ring laser to achieve single-longitudinal-mode (SLM) operation. The PT symmetry configuration can cause two opposite lightwave propagation direction to induce the gain and loss effect, when the polarization states of two lightwaves are adjusted by two polarization controllers (PCs) accurately. Once the gain and loss coefficient are greater than coupling coefficient, the SLM output can be reached. Furthermore, the wavelength tunability range, power output, linewidth, optical signal to noise ratio (OSNR) and stability of the EDF Sagnac ring laser presented are experimentally performed.
{"title":"Stable L-band single-frequency erbium fiber laser by applying parity-time symmetric sagnac ring design","authors":"Chi-Chin Wu, Wen-Hao Hung, Kuan-Ming Cheng, Lan-Yin Chen, Yu-Ting Lai, Chun-Yen Lin, Tsu-Hsin Wu, Teng-Yao Yang, Chien-Hung Yeh","doi":"10.1016/j.yofte.2025.104180","DOIUrl":"10.1016/j.yofte.2025.104180","url":null,"abstract":"<div><div>A Sagnac ring with parity-time (PT) symmetry design is included to the L-band EDF ring laser to achieve single-longitudinal-mode (SLM) operation. The PT symmetry configuration can cause two opposite lightwave propagation direction to induce the gain and loss effect, when the polarization states of two lightwaves are adjusted by two polarization controllers (PCs) accurately. Once the gain and loss coefficient are greater than coupling coefficient, the SLM output can be reached. Furthermore, the wavelength tunability range, power output, linewidth, optical signal to noise ratio (OSNR) and stability of the EDF Sagnac ring laser presented are experimentally performed.</div></div>","PeriodicalId":19663,"journal":{"name":"Optical Fiber Technology","volume":"91 ","pages":"Article 104180"},"PeriodicalIF":2.6,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We introduce an adaptive dynamic surface control (ADSC) method tailored for high-order strict-feedback systems (SFSs) with input saturation, utilizing the fully actuated system (FAS) approach. We simplify the steps in designing the controller by combining the FAS approach with ADSC method to directly control each high-order subsystem as a complete entity, without the need to transform it into first-order systems. Smooth functions and Nussbaum functions are applied to solve the problem of input saturation. We use a sequence of low-pass filters to calculate the higher-order derivatives of the virtual control law. Lyapunov stability theory is used to demonstrate that all signals within the closed-loop system become uniformly bounded, with the tracking error ultimately converging to a small vicinity around zero. We validated the efficiency of the proposed method of control through simulations on a flexible joint manipulator system. In contrast to the traditional first-order system method, which requires four virtual control laws, the proposed method in this paper necessitates only two, resulting in a smaller initial value of the control input.
{"title":"Adaptive Dynamic Surface Control for High-Order Strict-Feedback Systems With Input Saturation: A Fully Actuated System Approach","authors":"Yongqiang Xiao, Guangbin Cai, Mingrui Hao","doi":"10.1049/cth2.70010","DOIUrl":"https://doi.org/10.1049/cth2.70010","url":null,"abstract":"<p>We introduce an adaptive dynamic surface control (ADSC) method tailored for high-order strict-feedback systems (SFSs) with input saturation, utilizing the fully actuated system (FAS) approach. We simplify the steps in designing the controller by combining the FAS approach with ADSC method to directly control each high-order subsystem as a complete entity, without the need to transform it into first-order systems. Smooth functions and Nussbaum functions are applied to solve the problem of input saturation. We use a sequence of low-pass filters to calculate the higher-order derivatives of the virtual control law. Lyapunov stability theory is used to demonstrate that all signals within the closed-loop system become uniformly bounded, with the tracking error ultimately converging to a small vicinity around zero. We validated the efficiency of the proposed method of control through simulations on a flexible joint manipulator system. In contrast to the traditional first-order system method, which requires four virtual control laws, the proposed method in this paper necessitates only two, resulting in a smaller initial value of the control input.</p>","PeriodicalId":50382,"journal":{"name":"IET Control Theory and Applications","volume":"19 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cth2.70010","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.engappai.2025.110239
Zhiqin Zhu , Yan Ding , Guanqiu Qi , Baisen Cong , Yuanyuan Li , Litao Bai , Xinbo Gao
Drug–target affinity (DTA) prediction has been widely used in pharmaceutical research as a novel and effective method to explore the interaction strength between drugs and targets. However, existing DTA prediction models mainly rely on graphical representations of drug molecules, overlooking the intricate interactions between individual substructures. This limitation impacts both the predictive accuracy and the informational richness within the model nodes. To address these challenges, this paper proposes the Rotary Retention Graph Drug–Target Affinity (RRGDTA) network with rotation and retention mechanisms. The RRGDTA integrates an information interaction module into the extraction of drug and target features across multiple scale levels. This approach enhances the correlation within the graph representation, leading to an optimal feature representation. Furthermore, to tackle the issue of limited relationship between molecular structure and context, a Multi-Scale Interaction module (MSI) is proposed to enhance important features related to both. Additionally, to address inaccuracies in the structural features of drugs and targets, a Rotary Encoding Module (ROE) is proposed, which focuses on nearby contextual information and effectively captures the correlation between them. In order to solve the problem of insufficient information representation, an Association Prediction Module (APM) and an Intra-Mask Retention Module (IMR) are proposed to maximize the retention of drug–target information. The efficacy of the proposed RRGDTA in DTA prediction was validated on the Davis, kinase inhibitors biochemical assays (KIBA) and binding database (BindingDB) datasets. Compared with current baseline models, the proposed model achieved better results across various metrics, demonstrating its superior performance in accurate DTA prediction.
{"title":"Drug–target affinity prediction using rotary encoding and information retention mechanisms","authors":"Zhiqin Zhu , Yan Ding , Guanqiu Qi , Baisen Cong , Yuanyuan Li , Litao Bai , Xinbo Gao","doi":"10.1016/j.engappai.2025.110239","DOIUrl":"10.1016/j.engappai.2025.110239","url":null,"abstract":"<div><div>Drug–target affinity (DTA) prediction has been widely used in pharmaceutical research as a novel and effective method to explore the interaction strength between drugs and targets. However, existing DTA prediction models mainly rely on graphical representations of drug molecules, overlooking the intricate interactions between individual substructures. This limitation impacts both the predictive accuracy and the informational richness within the model nodes. To address these challenges, this paper proposes the Rotary Retention Graph Drug–Target Affinity (RRGDTA) network with rotation and retention mechanisms. The RRGDTA integrates an information interaction module into the extraction of drug and target features across multiple scale levels. This approach enhances the correlation within the graph representation, leading to an optimal feature representation. Furthermore, to tackle the issue of limited relationship between molecular structure and context, a Multi-Scale Interaction module (MSI) is proposed to enhance important features related to both. Additionally, to address inaccuracies in the structural features of drugs and targets, a Rotary Encoding Module (ROE) is proposed, which focuses on nearby contextual information and effectively captures the correlation between them. In order to solve the problem of insufficient information representation, an Association Prediction Module (APM) and an Intra-Mask Retention Module (IMR) are proposed to maximize the retention of drug–target information. The efficacy of the proposed RRGDTA in DTA prediction was validated on the Davis, kinase inhibitors biochemical assays (KIBA) and binding database (BindingDB) datasets. Compared with current baseline models, the proposed model achieved better results across various metrics, demonstrating its superior performance in accurate DTA prediction.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"147 ","pages":"Article 110239"},"PeriodicalIF":7.5,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号