计算机科学最新文献

英文中文

IF： -

Adaptive Fixed-Time Prescribed Performance Control of Non-Smooth Systems Subject to Injection/Deception Attacks

IF 5.6 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Automation Science and Engineering

Pub Date : 2025-02-21 DOI: 10.1109/tase.2025.3544459

Ge Guo, Qian Xu, Chen-Liang Zhang

引用次数: 0

Bilevel Evolutionary Multi-objective Algorithm with Multiple Lower-level Search Modes

IF 14.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE Transactions on Evolutionary Computation

Pub Date : 2025-02-21 DOI: 10.1109/tevc.2025.3544821

Ning Yang, Hai-Lin Liu

引用次数: 0

Dynamic Soaring Trajectory Optimization Considering the Path Following Performance

IF 4.4 2区计算机科学 Q1 ENGINEERING, AEROSPACE

IEEE Transactions on Aerospace and Electronic Systems

Pub Date : 2025-02-21 DOI: 10.1109/taes.2025.3544581

Xueqing Nie, Alexander Zwenig, Patrick Piprek, Florian Holzapfel, Haichao Hong

引用次数: 0

A Unified Channel Model for IRS-Aided Underwater OWC with Combined Attenuation Losses

IF 16.4 1区计算机科学 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Journal on Selected Areas in Communications

Pub Date : 2025-02-21 DOI: 10.1109/jsac.2025.3543523

Yalc¸ın Ata, Xiang Yi, Yuxuan Li, Xinyue Tao, Anna Maria Vegni

引用次数: 0

Task recognition integrating worker actions and machine operations: A video-based sensing approach without physical sensors

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2025-02-21 DOI: 10.1016/j.engappai.2025.110232

Shotaro Kataoka , Masashi Oba , Hirofumi Nonaka

Automating work process analysis is crucial in manufacturing to improve efficiency and productivity. However, traditional deep learning methods often fail to capture subtle temporal changes in machine operations, such as varying speeds. We propose a cost-effective approach called pseudo-sensing, which simulates sensor data by measuring machine speeds directly from video using wavelet transformation, a mathematical tool for time-frequency analysis. This approach eliminates the need for physical sensors.

We evaluated pseudo-sensing by integrating it into two task classification models. The first is a convolutional neural network-long short-term memory (CNN-LSTM) model, which extracts spatial features via a CNN and learns temporal patterns using an LSTM. The second is a three-dimensional residual network (3D ResNet, R3D), designed to process spatiotemporal data simultaneously. With pseudo-sensing, the CNN-LSTM’s micro-F1 score—an accuracy metric averaging precision and recall across all classes—improved from 0.712 to 0.736 (+2.4 points), while R3D’s score rose from 0.675 to 0.701 (+2.7 points).

To assess general applicability, we tested pseudo-sensing on another dataset featuring diverse machine motions: unidirectional movements (e.g., conveyor belts), oscillatory movements (e.g., pendulum-like motions), rotational movements (e.g., rotary presses), and intermittent movements (e.g., blinking or toggling mechanisms). The method achieved an 83% success rate in identifying machine dynamics.

By leveraging deep learning, this method integrates video-based machine operation sensing with task recognition, considering both human actions and machine states. Eliminating additional sensors while enhancing accuracy and efficiency, pseudo-sensing offers broad potential for advancing manufacturing process analysis.

{"title":"Task recognition integrating worker actions and machine operations: A video-based sensing approach without physical sensors","authors":"Shotaro Kataoka , Masashi Oba , Hirofumi Nonaka","doi":"10.1016/j.engappai.2025.110232","DOIUrl":"10.1016/j.engappai.2025.110232","url":null,"abstract":"<div><div>Automating work process analysis is crucial in manufacturing to improve efficiency and productivity. However, traditional deep learning methods often fail to capture subtle temporal changes in machine operations, such as varying speeds. We propose a cost-effective approach called pseudo-sensing, which simulates sensor data by measuring machine speeds directly from video using wavelet transformation, a mathematical tool for time-frequency analysis. This approach eliminates the need for physical sensors.</div><div>We evaluated pseudo-sensing by integrating it into two task classification models. The first is a convolutional neural network-long short-term memory (CNN-LSTM) model, which extracts spatial features via a CNN and learns temporal patterns using an LSTM. The second is a three-dimensional residual network (3D ResNet, R3D), designed to process spatiotemporal data simultaneously. With pseudo-sensing, the CNN-LSTM’s micro-F1 score—an accuracy metric averaging precision and recall across all classes—improved from 0.712 to 0.736 (+2.4 points), while R3D’s score rose from 0.675 to 0.701 (+2.7 points).</div><div>To assess general applicability, we tested pseudo-sensing on another dataset featuring diverse machine motions: unidirectional movements (e.g., conveyor belts), oscillatory movements (e.g., pendulum-like motions), rotational movements (e.g., rotary presses), and intermittent movements (e.g., blinking or toggling mechanisms). The method achieved an 83% success rate in identifying machine dynamics.</div><div>By leveraging deep learning, this method integrates video-based machine operation sensing with task recognition, considering both human actions and machine states. Eliminating additional sensors while enhancing accuracy and efficiency, pseudo-sensing offers broad potential for advancing manufacturing process analysis.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"147 ","pages":"Article 110232"},"PeriodicalIF":7.5,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465112","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}

引用次数: 0

Analysis and design of concurrent class-F2 power amplifier based on power-series technique

IF 3 3区计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Aeu-International Journal of Electronics and Communications

Pub Date : 2025-02-21 DOI: 10.1016/j.aeue.2025.155722

Jinting Liu , Weimin Shi , Yufeng Zang , Jun Hua , Gaoming Xu , Chunyu Hu , Ke Liu , Yu Li , Mingyu Li

Though the design procedures of dual-band power amplifiers (PAs) have been thoroughly studied in previous works, these studies have seldom delved into analyze the dual-band PA when it is driven by a concurrent dual-band signal. This paper presents the analysis and design of broadband class-F

_{2}

PA operating in concurrent mode. The class-F

_{2}

PA driven by a concurrent dual-band signal is analyzed using power series technique. It is illustrated that, compared to a concurrent class-B PA, the concurrent class-F

_{2}

PA exhibits an increased output power of 4.8 dB. Furthermore, when excited by a concurrent two-tone signal, the output power decrease of the class-F

_{2}

PA is merely 0.8 dB, as opposed to single-tone signal excitation. A broadband 1.8–2.2 GHz class-F

_{2}

PA supporting concurrent operation is designed and measured in this work. When excited by a single-tone signal, the broadband PA achieves a maximum output power of 41.1–42.4 dBm with a drain efficiency (DE) of 61.8%–67.3%. On the other hand, under the excitation of a concurrent two-tone signal centered at 2.0 GHz, the fabricated PA achieves an output power of 40.0–40.6 dBm with a DE of 60.0%–64.0% across a tone-spacing of 0–400 MHz.

{"title":"Analysis and design of concurrent class-F2 power amplifier based on power-series technique","authors":"Jinting Liu , Weimin Shi , Yufeng Zang , Jun Hua , Gaoming Xu , Chunyu Hu , Ke Liu , Yu Li , Mingyu Li","doi":"10.1016/j.aeue.2025.155722","DOIUrl":"10.1016/j.aeue.2025.155722","url":null,"abstract":"<div><div>Though the design procedures of dual-band power amplifiers (PAs) have been thoroughly studied in previous works, these studies have seldom delved into analyze the dual-band PA when it is driven by a concurrent dual-band signal. This paper presents the analysis and design of broadband class-F<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> PA operating in concurrent mode. The class-F<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> PA driven by a concurrent dual-band signal is analyzed using power series technique. It is illustrated that, compared to a concurrent class-B PA, the concurrent class-F<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> PA exhibits an increased output power of 4.8 dB. Furthermore, when excited by a concurrent two-tone signal, the output power decrease of the class-F<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> PA is merely 0.8 dB, as opposed to single-tone signal excitation. A broadband 1.8–2.2 GHz class-F<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> PA supporting concurrent operation is designed and measured in this work. When excited by a single-tone signal, the broadband PA achieves a maximum output power of 41.1–42.4 dBm with a drain efficiency (DE) of 61.8%–67.3%. On the other hand, under the excitation of a concurrent two-tone signal centered at 2.0 GHz, the fabricated PA achieves an output power of 40.0–40.6 dBm with a DE of 60.0%–64.0% across a tone-spacing of 0–400 MHz.</div></div>","PeriodicalId":50844,"journal":{"name":"Aeu-International Journal of Electronics and Communications","volume":"193 ","pages":"Article 155722"},"PeriodicalIF":3.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464945","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}

引用次数: 0

Efficient safety-critical trajectory planning for any N-trailer system with a general model

IF 5.4 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Control Engineering Practice

Pub Date : 2025-02-21 DOI: 10.1016/j.conengprac.2025.106287

Liang Gao, Bobo Jia, Daiwei Li, Yi Yang, Shanshan Xie

Trajectory planning for tractor–trailer vehicles (TTVs) in a cluttered environment is a highly challenging task owing to complicated kinematic and large-scale collision-avoidance constraints. It has stringent requirements for trajectory feasibility and computational efficiency. Moreover, the varying configurations of TTVs pose challenges to the scalability of the planning method. This article proposes a novel safety-critical trajectory planning method with a general model to address these challenges. Firstly, an algebraic general model is first presented to represent these N-Trailer systems with different hitching types and trailer types uniformly. Secondly, the planning problem is formulated as a nonlinear model predictive control scheme with two key efforts to accelerate calculation speed. One operation is that a novel search-guided optimization-based collision avoidance (SG-OBCA) method is developed to provide a high-quality initial guess. The other operation is that intractable non-convex collision-avoidance constraints are translated into a dual form based on exponential discrete-time control barrier function (DCBF). Finally, both comparative simulations and real-world experiments are conducted to demonstrate the efficiency and applicability of the proposed method in different complicated scenarios and configurations of TTVs.

{"title":"Efficient safety-critical trajectory planning for any N-trailer system with a general model","authors":"Liang Gao, Bobo Jia, Daiwei Li, Yi Yang, Shanshan Xie","doi":"10.1016/j.conengprac.2025.106287","DOIUrl":"10.1016/j.conengprac.2025.106287","url":null,"abstract":"<div><div>Trajectory planning for tractor–trailer vehicles (TTVs) in a cluttered environment is a highly challenging task owing to complicated kinematic and large-scale collision-avoidance constraints. It has stringent requirements for trajectory feasibility and computational efficiency. Moreover, the varying configurations of TTVs pose challenges to the scalability of the planning method. This article proposes a novel safety-critical trajectory planning method with a general model to address these challenges. Firstly, an algebraic general model is first presented to represent these N-Trailer systems with different hitching types and trailer types uniformly. Secondly, the planning problem is formulated as a nonlinear model predictive control scheme with two key efforts to accelerate calculation speed. One operation is that a novel search-guided optimization-based collision avoidance (SG-OBCA) method is developed to provide a high-quality initial guess. The other operation is that intractable non-convex collision-avoidance constraints are translated into a dual form based on exponential discrete-time control barrier function (DCBF). Finally, both comparative simulations and real-world experiments are conducted to demonstrate the efficiency and applicability of the proposed method in different complicated scenarios and configurations of TTVs.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"158 ","pages":"Article 106287"},"PeriodicalIF":5.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464494","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}

引用次数: 0

A numerical approach to model and analyse geometric characteristics of a grey-headed albatross aerofoil in flight.

IF 3.1 3区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

Bioinspiration & Biomimetics

Pub Date : 2025-02-21 DOI: 10.1088/1748-3190/adaff4

Alexander Ernest Winter, Janine Schoombie, Lelanie Smith

Limited research exists on the 3D geometric models and as a consequence the aerodynamic characteristics of the grey-headed albatross (GHA). Despite existing methods for extracting bird wing cross-sections, few studies consider deflections due to aerodynamic pressure. With the GHA known for its exceptional flight speed and purported wing-lock mechanism, it offers a valuable subject for studying fixed-wing aerodynamics in nature. This study aims to develop and validate a numerical approach to estimate the GHA's wing cross-section in flight. The PARSEC method is combined with a scanned 3D point cloud of a dried GHA wing to create a 3D model and analyse an averaged aerofoil section. Using a pseudo-2D computational fluid dynamics model, the study explores passive morphing of bird wings due to aerodynamic pressure. Results show that the aerofoil morphs to achieve maximum potential aerodynamic efficiency at a Reynolds number of2×105, decreasing in camber. The maximum lift-to-drag ratio ((CL/CD)max) increases from 3 to 44, primarily due to pressure drag reduction. However, the lack of comparison to true bird geometry in flight remains a limitation. Future research should compare the predicted morphing with actual bird specimens in flight.

{"title":"A numerical approach to model and analyse geometric characteristics of a grey-headed albatross aerofoil in flight.","authors":"Alexander Ernest Winter, Janine Schoombie, Lelanie Smith","doi":"10.1088/1748-3190/adaff4","DOIUrl":"10.1088/1748-3190/adaff4","url":null,"abstract":"<p><p>Limited research exists on the 3D geometric models and as a consequence the aerodynamic characteristics of the grey-headed albatross (GHA). Despite existing methods for extracting bird wing cross-sections, few studies consider deflections due to aerodynamic pressure. With the GHA known for its exceptional flight speed and purported wing-lock mechanism, it offers a valuable subject for studying fixed-wing aerodynamics in nature. This study aims to develop and validate a numerical approach to estimate the GHA's wing cross-section in flight. The PARSEC method is combined with a scanned 3D point cloud of a dried GHA wing to create a 3D model and analyse an averaged aerofoil section. Using a pseudo-2D computational fluid dynamics model, the study explores passive morphing of bird wings due to aerodynamic pressure. Results show that the aerofoil morphs to achieve maximum potential aerodynamic efficiency at a Reynolds number of2×105, decreasing in camber. The maximum lift-to-drag ratio ((CL/CD)max) increases from 3 to 44, primarily due to pressure drag reduction. However, the lack of comparison to true bird geometry in flight remains a limitation. Future research should compare the predicted morphing with actual bird specimens in flight.</p>","PeriodicalId":55377,"journal":{"name":"Bioinspiration & Biomimetics","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143069776","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}

引用次数: 0

Rapid and Precise Online Surface Reconstruction Method for Digital Modeling of Bulk Material Flow

IF 12.3 1区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Industrial Informatics

Pub Date : 2025-02-21 DOI: 10.1109/tii.2025.3538064

Wei Qiao, Chengcheng Hou, Xiaoyan Xiong, Huijie Dong, Yusong Pang, Junzhi Yu

引用次数: 0

Inverse Reinforcement Learning for Discrete-Time Systems With Data Dropouts

IF 11.8 1区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Cybernetics

Pub Date : 2025-02-21 DOI: 10.1109/tcyb.2025.3539961

Jialu Fan, Pengfei Shi, Wenqian Xue, Bosen Lian, Yunfang Cui, Frank L. Lewis