Engineering Applications of Artificial Intelligence最新文献

英文中文

Cross-domain facial expression recognition: Bi-Directional Fusion of Active and Stable Information

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-12 DOI: 10.1016/j.engappai.2025.110357

Yanan Zhu , Jiaqiu Ai , Weibao Xue , Mingyang Wu , Sen Yang , Wei Jia , Min Hu

Facial expression recognition (FER) algorithms often encounter obstacles in cross-domain scenarios, attributed to variations in collection conditions such as lighting, weather, age, gender, and skin color of subjects. Unlike existing approaches that primarily focus on extracting globally invariant features and aligning domain distributions, we propose a novel framework that fundamentally shifts the approach to cross-domain FER. Our proposed algorithm, termed Bi-Directional Fusion of Active and Stable Information (FER-DAS), uniquely combines three innovative components: the Active Assessment Strategy (AAS), Cross-Domain Dynamic Class Threshold (CD-DCT), and Weighted Cross-Domain Alignment (WCDA). The AAS component selectively identifies and enhances active samples in the target domain, providing precise annotations for improved model robustness. Samples with the highest uncertainty are deemed active, indicating low prediction confidence and high informational value for model training. These are then filtered using a predefined threshold to ensure only the most informative samples are included in training iterations. In contrast to conventional static threshold techniques, our dynamic class threshold strategy (CD-DCT) adaptively filters stable samples across domains, thereby ensuring that only the most reliable information is utilized in training. The WCDA strategy further refines this process by dynamically assessing and weighting the contribution of target domain samples to class centers, effectively mitigating domain distribution discrepancies. Extensive experiments on multiple benchmark datasets confirm that FER-DAS sets a new standard in cross-domain FER, consistently outperforming existing state-of-the-art methods.

{"title":"Cross-domain facial expression recognition: Bi-Directional Fusion of Active and Stable Information","authors":"Yanan Zhu , Jiaqiu Ai , Weibao Xue , Mingyang Wu , Sen Yang , Wei Jia , Min Hu","doi":"10.1016/j.engappai.2025.110357","DOIUrl":"10.1016/j.engappai.2025.110357","url":null,"abstract":"<div><div>Facial expression recognition (FER) algorithms often encounter obstacles in cross-domain scenarios, attributed to variations in collection conditions such as lighting, weather, age, gender, and skin color of subjects. Unlike existing approaches that primarily focus on extracting globally invariant features and aligning domain distributions, we propose a novel framework that fundamentally shifts the approach to cross-domain FER. Our proposed algorithm, termed Bi-Directional Fusion of Active and Stable Information (FER-DAS), uniquely combines three innovative components: the Active Assessment Strategy (AAS), Cross-Domain Dynamic Class Threshold (CD-DCT), and Weighted Cross-Domain Alignment (WCDA). The AAS component selectively identifies and enhances active samples in the target domain, providing precise annotations for improved model robustness. Samples with the highest uncertainty are deemed active, indicating low prediction confidence and high informational value for model training. These are then filtered using a predefined threshold to ensure only the most informative samples are included in training iterations. In contrast to conventional static threshold techniques, our dynamic class threshold strategy (CD-DCT) adaptively filters stable samples across domains, thereby ensuring that only the most reliable information is utilized in training. The WCDA strategy further refines this process by dynamically assessing and weighting the contribution of target domain samples to class centers, effectively mitigating domain distribution discrepancies. Extensive experiments on multiple benchmark datasets confirm that FER-DAS sets a new standard in cross-domain FER, consistently outperforming existing state-of-the-art methods.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110357"},"PeriodicalIF":7.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601573","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

Influence factor-based transformation method for translating mass function to probability in Dempster–Shafer evidence theory

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110385

Haocheng Shao , Lipeng Pan , Jiahui Chen , Xiaozhuan Gao , BingYi Kang

Dempster–Shafer evidence theory provides an effective mathematical tool to represent uncertain information by assigning information into power set. Among its associated studies, a pivotal challenge is the transformation of mass functions into probability distributions which can enhance the robustness and reliability of decision-making. In this paper, influence factor is constructed by considering the impact of transformation between multi-element propositions and single-element propositions. Then based on influence factor, the novel transformation method is proposed. In addition, some numerical examples are used to explain effectiveness of new method by analyzing the probability information capacity of different methods. Finally, this paper applies the novel method to target recognition and validates its effectiveness as well as its enhanced support for decision-making through the utilization of real-world datasets.

引用次数: 0

SlimDL: Deploying ultra-light deep learning model on sweeping robots

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110415

Xudong Sun , Yu Wang , Zhanglin Liu , Shaoxuan Gao , Wenbo He , Chao Tong

Advanced object detection methods have yielded impressive progress in recent years. However, the computational constraints of edge mobile devices present significant deployment challenges for state-of-the-art algorithms. We propose a deep learning deployment framework with two stages: model adaptation and compression. Our method enhance “You Only Look Once version 5” (YOLOv5) with lightweight modules, which improves detection performance while reducing computational load. Additionally, we present a pruning algorithm, employing adaptive batch normalization and iterative pruning. Our evaluation on “Microsoft Common Objects in Context” (MSCOCO) dataset and custom SweepRobot datasets demonstrates that our method consistently outperforms state-of-the-art approaches. On the SweepRobot dataset, our method doubled YOLOv5’s detection speed on the sweeping robot from 15.69 frames per second (FPS) to 30.77 FPS, maintaining 97.3% performance at 20% of the computational cost. Even on Graphics Processing Unit equipped devices, our method achieved 1.8% and 2.8% higher Average Precision compared to direct scaling and pruning with the original pruning algorithm.

{"title":"SlimDL: Deploying ultra-light deep learning model on sweeping robots","authors":"Xudong Sun , Yu Wang , Zhanglin Liu , Shaoxuan Gao , Wenbo He , Chao Tong","doi":"10.1016/j.engappai.2025.110415","DOIUrl":"10.1016/j.engappai.2025.110415","url":null,"abstract":"<div><div>Advanced object detection methods have yielded impressive progress in recent years. However, the computational constraints of edge mobile devices present significant deployment challenges for state-of-the-art algorithms. We propose a deep learning deployment framework with two stages: model adaptation and compression. Our method enhance “You Only Look Once version 5” (YOLOv5) with lightweight modules, which improves detection performance while reducing computational load. Additionally, we present a pruning algorithm, employing adaptive batch normalization and iterative pruning. Our evaluation on “Microsoft Common Objects in Context” (MSCOCO) dataset and custom SweepRobot datasets demonstrates that our method consistently outperforms state-of-the-art approaches. On the SweepRobot dataset, our method doubled YOLOv5’s detection speed on the sweeping robot from 15.69 frames per second (FPS) to 30.77 FPS, maintaining 97.3% performance at 20% of the computational cost. Even on Graphics Processing Unit equipped devices, our method achieved 1.8% and 2.8% higher Average Precision compared to direct scaling and pruning with the original pruning algorithm.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110415"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592770","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

HT-AggNet: Hierarchical temporal aggregation network with near-zero-cost layer stacking for human activity recognition

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110465

Jaegyun Park , Dae-Won Kim , Jaesung Lee

With the steady growth of sensor technology and wearable devices in pervasive computing applications, sensor-based human activity recognition has gained attention in fields such as healthcare monitoring and fitness tracking. This has resulted in an increased need for accurate and real-time systems. Recent studies to satisfy the real-time conditions have attempted to design lightweight neural networks by mainly restricting the number of layers shallowly, which has decreased both inference time and accuracy. To recover the loss of accuracy, we propose an innovative hierarchical temporal aggregation network (HT-AggNet) that allows the network architecture to be deeper, leading to an accuracy gain with only a near-zero increase in computational cost. Furthermore, a temporal glance convolution is presented to model the global context information of the signal patterns. Consequently, the HT-AggNet hierarchically extracts the local and global temporal information and then merges them based on hierarchical temporal aggregation. In our experiments, the HT-AggNet outperformed existing methods on seven publicly available datasets and achieved state-of-the-art performance. The source code for the HT-AggNet is publicly available at https://github.com/jgpark92/HT-AggNet.

{"title":"HT-AggNet: Hierarchical temporal aggregation network with near-zero-cost layer stacking for human activity recognition","authors":"Jaegyun Park , Dae-Won Kim , Jaesung Lee","doi":"10.1016/j.engappai.2025.110465","DOIUrl":"10.1016/j.engappai.2025.110465","url":null,"abstract":"<div><div>With the steady growth of sensor technology and wearable devices in pervasive computing applications, sensor-based human activity recognition has gained attention in fields such as healthcare monitoring and fitness tracking. This has resulted in an increased need for accurate and real-time systems. Recent studies to satisfy the real-time conditions have attempted to design lightweight neural networks by mainly restricting the number of layers shallowly, which has decreased both inference time and accuracy. To recover the loss of accuracy, we propose an innovative hierarchical temporal aggregation network (HT-AggNet) that allows the network architecture to be deeper, leading to an accuracy gain with only a near-zero increase in computational cost. Furthermore, a temporal glance convolution is presented to model the global context information of the signal patterns. Consequently, the HT-AggNet hierarchically extracts the local and global temporal information and then merges them based on hierarchical temporal aggregation. In our experiments, the HT-AggNet outperformed existing methods on seven publicly available datasets and achieved state-of-the-art performance. The source code for the HT-AggNet is publicly available at <span><span>https://github.com/jgpark92/HT-AggNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110465"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592772","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 novel multivariate nonlinear time-delayed grey model for forecasting electricity consumption

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110452

Wen-Ze Wu , Naiming Xie

Accurate and stable annual electricity consumption forecasting play vital role in modern social and economic development, which can provide effective planning and guaranteeing a reliable supply of sustainable electricity. Given that electricity consumption series present nonlinearity, poor information, and time-delayed characteristics, this paper proposes a multivariate nonlinear time-delayed grey model. Three primary efforts have been made as follows. First, we introduce the nonlinear and time-delayed terms into the typical multivariate grey model to identify the relationship between electricity consumption sequence and its driving factor sequence. Second, based on the Monte-Carlo simulation, an intelligent algorithm matching framework is designed to seek for the optimal model parameters of the model, which enhances the model’s applicability and flexibility. Third, we use datasets of China’s and America’s electricity consumption from 2000 to 2021 to validate the effectiveness of the newly-proposed model. Additionally, sensitivity analysis under different time horizons further verifies the model’s robustness. The experiment results indicates the superior prediction accuracy and robustness when comparing with other prevailing benchmarks. Overall, the newly-designed model is an effective technique for forecasting electricity consumption in China and America. Based on this, the forecasts of China’s and America’s electricity consumption in the following years can serve as a valuable reference for formulating related policies.

{"title":"A novel multivariate nonlinear time-delayed grey model for forecasting electricity consumption","authors":"Wen-Ze Wu , Naiming Xie","doi":"10.1016/j.engappai.2025.110452","DOIUrl":"10.1016/j.engappai.2025.110452","url":null,"abstract":"<div><div>Accurate and stable annual electricity consumption forecasting play vital role in modern social and economic development, which can provide effective planning and guaranteeing a reliable supply of sustainable electricity. Given that electricity consumption series present nonlinearity, poor information, and time-delayed characteristics, this paper proposes a multivariate nonlinear time-delayed grey model. Three primary efforts have been made as follows. First, we introduce the nonlinear and time-delayed terms into the typical multivariate grey model to identify the relationship between electricity consumption sequence and its driving factor sequence. Second, based on the Monte-Carlo simulation, an intelligent algorithm matching framework is designed to seek for the optimal model parameters of the model, which enhances the model’s applicability and flexibility. Third, we use datasets of China’s and America’s electricity consumption from 2000 to 2021 to validate the effectiveness of the newly-proposed model. Additionally, sensitivity analysis under different time horizons further verifies the model’s robustness. The experiment results indicates the superior prediction accuracy and robustness when comparing with other prevailing benchmarks. Overall, the newly-designed model is an effective technique for forecasting electricity consumption in China and America. Based on this, the forecasts of China’s and America’s electricity consumption in the following years can serve as a valuable reference for formulating related policies.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110452"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592775","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

Finite time multilayer neural network command filter backstepping controller design for large scale uncertain nonlinear systems

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110474

Qitian Yin, Quanqi Mu, Jianbai Yang

This study presents a novel dynamical multilayer neural network finite time command filter backstepping control scheme. This method realizes the finite time robust tracking control of uncertain nonlinear system. The uncertainty in system varies in large scale around system states. Its boundary is unknown and unavailable before design. The multilayer neural network (MNN) approximater is redesigned into the backstepping controller instead of the common radial basis function (RBF) neural network (NN) and Fuzzy System (FS) to realize the accuracy approximation of the large scale uncertain structure. The introduction of the MNN approximater overcomes the drawback of local identification constraint of RBF NN and Fuzzy System without the structure knowledge and boundary of uncertainty before design. Otherwise, owing to the MNN structure is more complex than common three layer RBF NN, the approximation costs more time to dynamically tune weight parameters online. In order to make up the time consistent between the MNN approximation and the backstepping process, the finite time (FT) command filter (CF) backstepping control strategy balancing the two distinct procedures guarantees the MNN identification of larger scale uncertainty and backstepping control process consistently convergence into a smaller area in uniform finite time interval. Finally, through a practical example, the effectiveness and advantages of are illustrated by comparison between this mechanism and traditional RBF NN method.

{"title":"Finite time multilayer neural network command filter backstepping controller design for large scale uncertain nonlinear systems","authors":"Qitian Yin, Quanqi Mu, Jianbai Yang","doi":"10.1016/j.engappai.2025.110474","DOIUrl":"10.1016/j.engappai.2025.110474","url":null,"abstract":"<div><div>This study presents a novel dynamical multilayer neural network finite time command filter backstepping control scheme. This method realizes the finite time robust tracking control of uncertain nonlinear system. The uncertainty in system varies in large scale around system states. Its boundary is unknown and unavailable before design. The multilayer neural network (MNN) approximater is redesigned into the backstepping controller instead of the common radial basis function (RBF) neural network (NN) and Fuzzy System (FS) to realize the accuracy approximation of the large scale uncertain structure. The introduction of the MNN approximater overcomes the drawback of local identification constraint of RBF NN and Fuzzy System without the structure knowledge and boundary of uncertainty before design. Otherwise, owing to the MNN structure is more complex than common three layer RBF NN, the approximation costs more time to dynamically tune weight parameters online. In order to make up the time consistent between the MNN approximation and the backstepping process, the finite time (FT) command filter (CF) backstepping control strategy balancing the two distinct procedures guarantees the MNN identification of larger scale uncertainty and backstepping control process consistently convergence into a smaller area in uniform finite time interval. Finally, through a practical example, the effectiveness and advantages of are illustrated by comparison between this mechanism and traditional RBF NN method.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110474"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592779","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

Reliability evaluation of solar integrated power distribution systems using an Evolutionary Swarm Algorithm

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110464

P.A.G.M. Amarasinghe , S.K. Abeygunawardane , C. Singh

The reliability of solar-integrated power distribution systems is significantly affected by intermittent solar generation and its impact on feeder voltages. While existing adequacy studies account for intermittency, they frequently overlook feeder voltages due to the computational burden of the Alternating Current Optimal Power Flow (AC-OPF) analysis. Addressing this gap, we propose an efficient framework based on an Evolutionary Swarm Algorithm (ESA) to integrate AC-OPF analysis into the reliability evaluation of power distribution systems. The sampling mechanism of ESA reduces the application of time-consuming AC-OPF and allows the fast estimation of reliability indices. The performance of the proposed framework is compared with Sequential Monte Carlo Simulation (SMCS), classical meta-heuristics, and three state-of-the-art meta-heuristics. Results demonstrate that our proposed framework can estimate the reliability indices approximately 34 times faster than SMCS without sacrificing accuracy. Furthermore, the ESA outperforms classical and state-of-the-art methods by over 23% in event sampling efficiency. Friedman and Nemenyi post-hoc tests conclude that ESA’s results significantly differ from others. We utilize the proposed framework in a case study to analyze the influence of solar photovoltaic integration on distribution system reliability. Another case study investigates the impact of dynamic tap changing of power transformers on the reliability improvement of distribution systems.

{"title":"Reliability evaluation of solar integrated power distribution systems using an Evolutionary Swarm Algorithm","authors":"P.A.G.M. Amarasinghe , S.K. Abeygunawardane , C. Singh","doi":"10.1016/j.engappai.2025.110464","DOIUrl":"10.1016/j.engappai.2025.110464","url":null,"abstract":"<div><div>The reliability of solar-integrated power distribution systems is significantly affected by intermittent solar generation and its impact on feeder voltages. While existing adequacy studies account for intermittency, they frequently overlook feeder voltages due to the computational burden of the Alternating Current Optimal Power Flow (AC-OPF) analysis. Addressing this gap, we propose an efficient framework based on an Evolutionary Swarm Algorithm (ESA) to integrate AC-OPF analysis into the reliability evaluation of power distribution systems. The sampling mechanism of ESA reduces the application of time-consuming AC-OPF and allows the fast estimation of reliability indices. The performance of the proposed framework is compared with Sequential Monte Carlo Simulation (SMCS), classical meta-heuristics, and three state-of-the-art meta-heuristics. Results demonstrate that our proposed framework can estimate the reliability indices approximately 34 times faster than SMCS without sacrificing accuracy. Furthermore, the ESA outperforms classical and state-of-the-art methods by over 23% in event sampling efficiency. Friedman and Nemenyi post-hoc tests conclude that ESA’s results significantly differ from others. We utilize the proposed framework in a case study to analyze the influence of solar photovoltaic integration on distribution system reliability. Another case study investigates the impact of dynamic tap changing of power transformers on the reliability improvement of distribution systems.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110464"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592769","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

Goal-oriented graph generation for transmission expansion planning

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110350

Anna Varbella , Blazhe Gjorgiev , Federico Sartore , Enrico Zio , Giovanni Sansavini

The electrification strategies that are being designed to meet sustainability objectives and rising energy demands pose significant challenges for power systems worldwide and require Transmission Expansion Planning (TEP). This study adopts a risk-informed approach to TEP, formulated as a multi-objective optimization problem that concurrently minimizes systemic risks and expansion costs. Given the intractability of this problem with conventional solvers, we turn to artificial intelligence techniques. In particular, we conceptualize power grids as graphs and introduce a goal-oriented graph generation methodology using deep reinforcement learning. We extend welfare-Q learning, a modified variant of Q-learning tailored to yield high rewards across multiple dimensions, by incorporating geometric deep learning for function approximation. This allows us to account for system security while minimizing grid expansion costs. Notably, system risk is evaluated by incorporating a Graph Neural Network (GNN) cascading failure meta-model into the proposed approach. The TEP method is applied to the IEEE 118-bus system, and the efficacy of this novel technique is compared against the state of the art. We conclude that the deep reinforcement learning method can compete with established methods for multi-objective optimization, identifying expansion strategies that improve system security at reduced costs. Furthermore, we test the robustness of the meta-model against topology changes in the transmission network, demonstrating its applicability to novel grid configurations.

{"title":"Goal-oriented graph generation for transmission expansion planning","authors":"Anna Varbella , Blazhe Gjorgiev , Federico Sartore , Enrico Zio , Giovanni Sansavini","doi":"10.1016/j.engappai.2025.110350","DOIUrl":"10.1016/j.engappai.2025.110350","url":null,"abstract":"<div><div>The electrification strategies that are being designed to meet sustainability objectives and rising energy demands pose significant challenges for power systems worldwide and require Transmission Expansion Planning (TEP). This study adopts a risk-informed approach to TEP, formulated as a multi-objective optimization problem that concurrently minimizes systemic risks and expansion costs. Given the intractability of this problem with conventional solvers, we turn to artificial intelligence techniques. In particular, we conceptualize power grids as graphs and introduce a goal-oriented graph generation methodology using deep reinforcement learning. We extend welfare-Q learning, a modified variant of Q-learning tailored to yield high rewards across multiple dimensions, by incorporating geometric deep learning for function approximation. This allows us to account for system security while minimizing grid expansion costs. Notably, system risk is evaluated by incorporating a Graph Neural Network (GNN) cascading failure meta-model into the proposed approach. The TEP method is applied to the IEEE 118-bus system, and the efficacy of this novel technique is compared against the state of the art. We conclude that the deep reinforcement learning method can compete with established methods for multi-objective optimization, identifying expansion strategies that improve system security at reduced costs. Furthermore, we test the robustness of the meta-model against topology changes in the transmission network, demonstrating its applicability to novel grid configurations.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110350"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110397

Aryan Bhambu , Koushik Bera , Selvaraju Natarajan , Ponnuthurai Nagaratnam Suganthan

High frequency volatility forecasting is essential for timely risk management and informed decision-making in dynamic financial markets. However, accurate forecasting is challenging due to the rapid nature of market movements and the complexity of underlying economic factors. This paper introduces a novel architecture combining Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Multi-layer Perceptron (MLP)-based models for enhanced volatility forecasting and risk assessment, where input variables are processed through GARCH-type models for volatility forecasting. The proposed GARCH-based MLP-Mixer (GaMM) model incorporates the stacking of multi-layer perceptrons, enabling deep representation learning, facilitating the extraction of temporal and feature information through operations along both time and feature dimensions, and addressing the complexity of high-frequency time-series data. The proposed model is evaluated on three high frequency financial times series datasets over three different years. The computational results demonstrate the proposed model’s superior performance over sixteen forecasting methods in three error metrics, Value-at-risk, and statistical tests for high frequency volatility forecasting and risk assessment tasks.

{"title":"High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model","authors":"Aryan Bhambu , Koushik Bera , Selvaraju Natarajan , Ponnuthurai Nagaratnam Suganthan","doi":"10.1016/j.engappai.2025.110397","DOIUrl":"10.1016/j.engappai.2025.110397","url":null,"abstract":"<div><div>High frequency volatility forecasting is essential for timely risk management and informed decision-making in dynamic financial markets. However, accurate forecasting is challenging due to the rapid nature of market movements and the complexity of underlying economic factors. This paper introduces a novel architecture combining Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Multi-layer Perceptron (MLP)-based models for enhanced volatility forecasting and risk assessment, where input variables are processed through GARCH-type models for volatility forecasting. The proposed GARCH-based MLP-Mixer (GaMM) model incorporates the stacking of multi-layer perceptrons, enabling deep representation learning, facilitating the extraction of temporal and feature information through operations along both time and feature dimensions, and addressing the complexity of high-frequency time-series data. The proposed model is evaluated on three high frequency financial times series datasets over three different years. The computational results demonstrate the proposed model’s superior performance over sixteen forecasting methods in three error metrics, Value-at-risk, and statistical tests for high frequency volatility forecasting and risk assessment tasks.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110397"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

An adaptive traffic signal control scheme with Proximal Policy Optimization based on deep reinforcement learning for a single intersection

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

Engineering Applications of Artificial Intelligence

Pub Date : 2025-03-11 DOI: 10.1016/j.engappai.2025.110440

Lijuan Wang , Guoshan Zhang , Qiaoli Yang , Tianyang Han

Adaptive traffic signal control (ATSC) is an important means to alleviate traffic congestion and improve the quality of road traffic. Although deep reinforcement learning (DRL) technology has shown great potential in solving traffic signal control problems, the state representation and reward design, as well as action interval time, still need to be further studied. The advantages of policy learning have not been fully applied in TSC. To address the aforementioned issues, we propose a DRL-based traffic signal control scheme with Poximal Policy Optimization (PPO-TSC). We use the waiting time of vehicles and the queue length of lanes represented the spatiotemporal characteristics of traffic flow to design the simplified traffic states feature vectors, and define the reward function that is consistent with the state. Additionally, we compare and analyze the performance indexes obtained by various methods using action intervals of 5s, 10s, and 15s. The algorithm is implemented based on the Actor-Critic architecture, using the advantage estimation and the clip mechanism to constrain the range of gradient updates. We validate the proposed scheme at a single intersection in Simulation of Urban MObility (SUMO) under two different traffic demand patterns of flat traffic and peak traffic. The experimental results show that the proposed method is significantly better than other compared methods. Specifically, PPO-TSC demonstrates a reduction of 24% in average travel time (ATT), a decrease of 45% in the average time loss (ATL), and an increase of 16% in average speed (AS) compared with the existing methods under peak traffic condition.

{"title":"An adaptive traffic signal control scheme with Proximal Policy Optimization based on deep reinforcement learning for a single intersection","authors":"Lijuan Wang , Guoshan Zhang , Qiaoli Yang , Tianyang Han","doi":"10.1016/j.engappai.2025.110440","DOIUrl":"10.1016/j.engappai.2025.110440","url":null,"abstract":"<div><div>Adaptive traffic signal control (ATSC) is an important means to alleviate traffic congestion and improve the quality of road traffic. Although deep reinforcement learning (DRL) technology has shown great potential in solving traffic signal control problems, the state representation and reward design, as well as action interval time, still need to be further studied. The advantages of policy learning have not been fully applied in TSC. To address the aforementioned issues, we propose a DRL-based traffic signal control scheme with Poximal Policy Optimization (PPO-TSC). We use the waiting time of vehicles and the queue length of lanes represented the spatiotemporal characteristics of traffic flow to design the simplified traffic states feature vectors, and define the reward function that is consistent with the state. Additionally, we compare and analyze the performance indexes obtained by various methods using action intervals of 5s, 10s, and 15s. The algorithm is implemented based on the Actor-Critic architecture, using the advantage estimation and the clip mechanism to constrain the range of gradient updates. We validate the proposed scheme at a single intersection in Simulation of Urban MObility (SUMO) under two different traffic demand patterns of flat traffic and peak traffic. The experimental results show that the proposed method is significantly better than other compared methods. Specifically, PPO-TSC demonstrates a reduction of 24% in average travel time (ATT), a decrease of 45% in the average time loss (ATL), and an increase of 16% in average speed (AS) compared with the existing methods under peak traffic condition.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"149 ","pages":"Article 110440"},"PeriodicalIF":7.5,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592776","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Engineering Applications of Artificial Intelligence

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀