Haiyang Chi , Yuhuan Lu , Can Xie , Wei Ke , Bidong Chen
{"title":"Spatio-temporal attention based collaborative local–global learning for traffic flow prediction","authors":"Haiyang Chi , Yuhuan Lu , Can Xie , Wei Ke , Bidong Chen","doi":"10.1016/j.engappai.2024.109575","DOIUrl":"10.1016/j.engappai.2024.109575","url":null,"abstract":"<div><div>Traffic flow prediction is crucial for intelligent transportation systems (ITS), providing valuable insights for traffic control, route planning, and operation management. Existing work often separately models the spatial and temporal dependencies and primarily relies on predefined graphs to represent spatio-temporal dependencies, neglecting the traffic dynamics caused by unexpected events and the global relationships among road segments. Unlike previous models that primarily focus on local feature extraction, we propose a novel collaborative local–global learning model (LOGO) that employs spatio-temporal attention (STA) and graph convolutional networks (GCN). Specifically, LOGO simultaneously extracts hidden traffic features from both local and global perspectives. In local feature extraction, a novel STA is devised to directly attend to spatio-temporal coupling interdependencies instead of separately modeling temporal and spatial dependencies, and to capture in-depth spatio-temporal traffic context with an adaptive graph focusing on the dynamics in traffic flow. In global feature extraction, a global correlation matrix is constructed and GCNs are utilized to propagate messages on the obtained matrix to achieve interactions between both adjacent and similar road segments. Finally, the obtained local and global features are concatenated and fed into a gated aggregation to forecast future traffic flow. Extensive experiments on four real-world traffic datasets sourced from the Caltrans Performance Measurement System (PEMS03, PEMS04, PEMS07, and PEMS08) demonstrate the effectiveness of our proposed model. LOGO achieves the best performance over 18 state-of-the-art baselines and the best prediction performance with the highest improvement of 6.06% on the PEMS07 dataset. Additionally, two real-world case studies further substantiate the robustness and interpretability of LOGO.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109575"},"PeriodicalIF":7.5,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659277","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}
Haohao Duan , Xiaoling Li , Guanghui Zhang , Yanxiang Feng , Qingchang Lu
{"title":"Elite-based multi-objective improved iterative local search algorithm for time-dependent vehicle-drone collaborative routing problem with simultaneous pickup and delivery","authors":"Haohao Duan , Xiaoling Li , Guanghui Zhang , Yanxiang Feng , Qingchang Lu","doi":"10.1016/j.engappai.2024.109608","DOIUrl":"10.1016/j.engappai.2024.109608","url":null,"abstract":"<div><div>This paper focuses on solving a time-dependent multi-objective vehicle-drone collaborative routing problem with simultaneous pickup and delivery, in which multiple visits per drone trip, simultaneous pickup and delivery, soft time windows, and time-dependent road network are considered. With the maximum completion time and total violation time as the optimization objectives, we first formulate the mathematical model of the problem. Then, in order to effectively solve the problem, an Elite-based multi-objective improved iterative local search algorithm developed within a collaborative optimization framework is proposed. Specifically, the multi-objective problem is decomposed into two subproblems, each of which is solved by minimizing a single objective. Meanwhile, the algorithm uses an elite set to record non-dominated solutions, guide the search, and achieve information exchange between subproblems. In the proposed algorithm, an individual is encoded as a vector consisting of two parts, a customer sequence and a sequence recording the customers' visiting modes, and can be decoded into subroutes for the vehicle and drone. To guarantee the feasibility of the solution, an adjustment method is proposed to repair the individual. In addition, based on individual representation and problem characteristics, six neighborhood structures are designed, through which new individuals can be generated. Then, by using the neighborhood structures, a problem-specific local search strategy and an iterative local search strategy are proposed to improve the search capability of the algorithm. Experimental tests and analyses demonstrate the correctness of the established mathematical model and the effectiveness of the proposed algorithm in solving this complex vehicle-drone collaborative routing problem.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109608"},"PeriodicalIF":7.5,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652642","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}
Xingwang Lv , Jinrui Wang , Ranran Qin , Jihua Bao , Xue Jiang , Zongzhen Zhang , Baokun Han , Xingxing Jiang
{"title":"Self-learning guided residual shrinkage network for intelligent fault diagnosis of planetary gearbox","authors":"Xingwang Lv , Jinrui Wang , Ranran Qin , Jihua Bao , Xue Jiang , Zongzhen Zhang , Baokun Han , Xingxing Jiang","doi":"10.1016/j.engappai.2024.109603","DOIUrl":"10.1016/j.engappai.2024.109603","url":null,"abstract":"<div><div>The original vibration signals of the fault gear under different working conditions have a large distribution difference, and there will be insufficient feature extraction during fault diagnosis, which leads to the problem of low diagnostic accuracy. Therefore, a self-learning model based on residual shrinkage network (SLRSN) is proposed. The model constructs a deep residual shrinkage network as the main network for feature extraction of the original vibration signal to enhance the robustness of the model. Then self-believing loss and self-doubting loss are proposed to achieve self-confidence and suspicion of health status prediction. The first is self-confidence loss, which adopts sub-domain distribution adaptation to actively align learned cross-domain features. The second is self-doubt loss, which provides SLRSN with the ability to extricate from wrong experience. Finally, to mitigate the effects of negative transfer, a novel adaptative weight allocation mechanism is designed to recalibrate the weighting of each source domain sample. Through the experiment of two gearboxes, it is verified that the proposed SLRSN method has good diagnostic reliability under the condition of gear speed and load change.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109603"},"PeriodicalIF":7.5,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652712","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}
Zhenjie Yao , Ziyi Hu , Panpan Lai , Fengling Qin , Wenrui Wang , Zhicheng Wu , Lingfei Wang , Hua Shao , Yongfu Li , Zhiqiang Li , Zhongming Liu , Junjie Li , Rui Chen , Ling Li
{"title":"Etching process prediction based on cascade recurrent neural network","authors":"Zhenjie Yao , Ziyi Hu , Panpan Lai , Fengling Qin , Wenrui Wang , Zhicheng Wu , Lingfei Wang , Hua Shao , Yongfu Li , Zhiqiang Li , Zhongming Liu , Junjie Li , Rui Chen , Ling Li","doi":"10.1016/j.engappai.2024.109590","DOIUrl":"10.1016/j.engappai.2024.109590","url":null,"abstract":"<div><div>Etching is one of the most critical processes in semiconductor manufacturing. Etch models have been developed to reveal the underlying etch mechanisms, which employs rigorous physical and chemical process simulation. Traditional simulation is very time consuming. The data-driven artificial intelligence model provides an alternative modeling approach. In this paper, a Cascade Recurrent Neural Networks (CRNN) is proposed to model and predict etching profiles. The etching profile is represented by polar coordinates and modeled by the recurrent neural networks, the corresponding etching parameters (e.g., pressure, power, temperature, and voltage) are integrated into the network through cascade combination layers. Experimental results on a dataset of 10,000 simulated etching profiles demonstrated the effectiveness of our method: compared with traditional etching simulation methods, CRNN can speedup 21,000<span><math><mo>×</mo></math></span> with an average error of less than 0.7 nm for 1 step prediction. Furthermore, compared to simple deep neural networks, the Mean Absolute Errors (MAE) could be reduced from 1.7329 nm to 1.3845 nm for 10 steps prediction. Finally, the effectiveness and accuracy of CRNN etching predictor is validated through fine-tuning on experimental data.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109590"},"PeriodicalIF":7.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652709","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}
{"title":"Attention-based hand pose estimation with voting and dual modalities","authors":"Dinh-Cuong Hoang , Anh-Nhat Nguyen , Thu-Uyen Nguyen , Ngoc-Anh Hoang , Van-Duc Vu , Duy-Quang Vu , Phuc-Quan Ngo , Khanh-Toan Phan , Duc-Thanh Tran , Van-Thiep Nguyen , Quang-Tri Duong , Ngoc-Trung Ho , Cong-Trinh Tran , Van-Hiep Duong , Anh-Truong Mai","doi":"10.1016/j.engappai.2024.109526","DOIUrl":"10.1016/j.engappai.2024.109526","url":null,"abstract":"<div><div>Hand pose estimation has recently emerged as a compelling topic in the robotic research community, because of its usefulness in learning from human demonstration or safe human–robot interaction. Although deep learning-based methods have been introduced for this task and have shown promise, it remains a challenging problem. To address this, we propose a novel end-to-end architecture for hand pose estimation using red-green-blue (RGB) and depth (D) data (RGB-D). Our approach processes the two data sources separately and utilizes a dense fusion network with an attention module to extract discriminative features. The features extracted include both spatial information and geometric constraints, which are fused to vote for the hand pose. We demonstrate that our voting mechanism in conjunction with the attention mechanism is particularly useful for solving the problem, especially when hands are heavily occluded by objects or are self-occluded. Our experimental results on benchmark datasets demonstrate that our approach outperforms state-of-the-art methods by a significant margin.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109526"},"PeriodicalIF":7.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659041","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}
Yanzhen Xiong , Jinjia Peng , Zeze Tao , Huibing Wang
{"title":"Region-guided spatial feature aggregation network for vehicle re-identification","authors":"Yanzhen Xiong , Jinjia Peng , Zeze Tao , Huibing Wang","doi":"10.1016/j.engappai.2024.109568","DOIUrl":"10.1016/j.engappai.2024.109568","url":null,"abstract":"<div><div>In the context of the advancement of smart city management, re-identification technology has emerged as an area of particular interest and research in the field of artificial intelligence, especially vehicle re-identification (re-ID), which aims to identify target vehicles in multiple non-overlapping fields of view. Most existing methods rely on fine-grained cues in the salient regions. Although impressive results have been achieved, these methods typically require additional auxiliary networks to localize the salient regions containing fine-grained cues. Meanwhile, changes in state such as illumination, viewpoint and occlusion can affect the position of the salient regions. To solve the above problems, this paper proposes a Region-guided Spatial Feature Aggregation Network (RSFAN) for vehicle re-ID, which forces the model to learn the latent information in the minor salient regions. Firstly, a Regional Localization (RL) module is proposed to automatically locate the salient regions without additional auxiliary networks. In addition, to mitigate the misguidance caused by the inaccurate salient regions, a Spatial Feature Aggregation (SFA) module is designed to weaken and enhance the expression of the salient and minor salient regions, respectively. Meanwhile, to enhance the diversity of the minor salient region-related information, a Cross-level Channel Attention (CCA) module is designed to implement cross-level interactions through the channel attention mechanism across different levels. Finally, to constrain the distributional differences between the salient regions and minor salient regions feature, a Distributional Variance (DV) loss is proposed. The extensive experiments show that the RSFAN has a good performance on VeRi-776, VehicleID, VeRi-Wild and Market1501 datasets.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109568"},"PeriodicalIF":7.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652711","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}
{"title":"A fault diagnosis framework using unlabeled data based on automatic clustering with meta-learning","authors":"Zhiqian Zhao , Yinghou Jiao , Yeyin Xu , Zhaobo Chen , Enrico Zio","doi":"10.1016/j.engappai.2024.109584","DOIUrl":"10.1016/j.engappai.2024.109584","url":null,"abstract":"<div><div>With the growth of the industrial internet of things, the poor performance of conventional deep learning models hinders the application of intelligent diagnosis methods in industrial situations such as lack of fault samples and difficulties in data labeling. To solve the above problems, we propose a fault diagnosis framework based on unsupervised meta-learning and contrastive learning, which is called automatic clustering with meta-learning (ACML). First, the amount of data is expanded through data augmentation approaches, and a feature generator is constructed to extract highly discriminative features from the unlabeled dataset using contrastive learning. Then, a cluster generator is used to automatically divide cluster partitions and add pseudo-labels for these. Finally, the classification tasks are derived through taking original samples in the partitions, which are embedded in the meta-learner for fault diagnosis. In the meta-learning stage, we split out two subsets from task and feed them into the inner and outer loops to maintain the class consistency of the real labels. After training, ACML transfers its prior expertise to the unseen task to efficiently complete the categorization of new faults. ACML is applied to two cases concerning a public dataset and a self-constructed dataset, demonstrate that ACML achieves good diagnostic performance, outperforming popular unsupervised methods.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109584"},"PeriodicalIF":7.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652636","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}
Changtong Zan , Liang Ding , Li Shen , Yu Cao , Weifeng Liu
{"title":"Code-switching finetuning: Bridging multilingual pretrained language models for enhanced cross-lingual performance","authors":"Changtong Zan , Liang Ding , Li Shen , Yu Cao , Weifeng Liu","doi":"10.1016/j.engappai.2024.109532","DOIUrl":"10.1016/j.engappai.2024.109532","url":null,"abstract":"<div><div>In recent years, the development of pre-trained models has significantly propelled advancements in natural language processing. However, multilingual sequence-to-sequence pretrained language models (Seq2Seq PLMs) are pretrained on a wide range of languages (e.g., 25 languages), yet often finetuned for specific bilingual tasks (e.g., English–German), leading to domain and task discrepancies between pretraining and finetuning stages, which may lead to sub-optimal downstream performance. In this study, we first illustratively reveal such domain and task discrepancies, and then conduct an in-depth investigation into the side effects that these discrepancies may have on both training dynamic and downstream performance. To alleviate those side effects, we introduce a simple and effective code-switching restoration task (namely <strong>code-switching finetuning</strong>) into the standard pretrain-finetune pipeline. Specifically, in the first stage, we recast the downstream data as the self-supervised format used for pretraining, in which the denoising signal is the code-switched cross-lingual phrase. Then, the model is finetuned on downstream task as usual in the second stage. Experiments spanning both natural language generation (12 supervised translations, 30 zero-shot translations, and 2 cross-lingual summarization tasks) and understanding (7 cross-lingual natural language inference tasks) tasks demonstrate that our model consistently and significantly surpasses the standard finetuning strategy. Analyses show that our method introduces negligible computational cost and reduces cross-lingual representation gaps. We have made the code publicly available at: <span><span>https://github.com/zanchangtong/CSR4mBART</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109532"},"PeriodicalIF":7.5,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659040","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}
{"title":"Adaptive masked network for ultra-short-term photovoltaic forecast","authors":"Qiaoyu Ma , Xueqian Fu , Qiang Yang , Dawei Qiu","doi":"10.1016/j.engappai.2024.109555","DOIUrl":"10.1016/j.engappai.2024.109555","url":null,"abstract":"<div><div>In recent years, power grid companies have faced increasingly stringent requirements for accurate prediction of photovoltaic (PV) power generation with the rapid development of PV technologies. In ultra-short-term forecasting, PV power generation exhibits strong temporal correlations, leading to high data redundancy. To address this issue, we propose an adaptive masked network (ASMNet) to enhance the accuracy of ultra-short-term PV forecasting. Specifically, this method improves the feature extraction of short-term fluctuations within historical time periods by down-weighting less significant temporal segments during the learning process. It captures the uncertain effects of environmental changes and provides a better understanding of the impacts of ultra-short-term fluctuations. We test our model on three public PV power generation datasets, and it achieves the best performance with a root mean square error of 21.42, 0.2824 and 23.36 for the Belgian, American National Renewable Energy Laboratory, and Desert Knowledge Australia Solar Center datasets, respectively. Additionally, the proposed model demonstrates a 0.01%–0.50% improvement in coefficient of determination compared to baseline models across all datasets, highlighting its superior performance and effectiveness in ultra-short-term PV forecasting.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109555"},"PeriodicalIF":7.5,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659039","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}
{"title":"Simulation-based genetic algorithm for optimizing a municipal cooperative waste supply chain in a pandemic","authors":"Peiman Ghasemi , Alireza Goli , Fariba Goodarzian , Jan Fabian Ehmke","doi":"10.1016/j.engappai.2024.109478","DOIUrl":"10.1016/j.engappai.2024.109478","url":null,"abstract":"<div><div>The quantity of medical waste produced by municipalities is on the rise, potentially presenting significant hazards to both the environment and human health. Developing a robust supply chain network for managing municipal medical waste is important for society, especially during a pandemic like COVID-19. In supply chain network design, factors such as the collection of non-infectious waste, transporting infectious waste from hospitals to disposal facilities, revenue generation from waste-to-energy initiatives, and the potential for pandemic outbreaks are often overlooked. Hence, in this study, we design a model incorporating COVID-19 parameters to mitigate the spread of the virus while designing an effective municipal medical waste supply chain network during a pandemic. The proposed model is multi-objective, multi-echelon, multi-commodity and involves coalition-based cooperation. The first objective function aims to minimize total costs, while the second objective pertains to minimizing the risk of a COVID-19 outbreak. We identify optimal collaboration among municipal medical waste collection centers to maximize cost savings. The COVID-19 prevalence risk level by the waste in each zone is calculated pursuant to their inhabitants. Additionally, we analyze a system dynamic simulation framework to forecast waste generation levels amid COVID-19 conditions. A metaheuristic based on the Non-dominated Sorting Genetic Algorithm II is used to solve the problem and is benchmarked against exact solutions. To illustrate our approach, we present a case study focused on Tehran, Iran. The results show that an increase in the amount of generated waste leads to an increase in the total costs of the supply chain.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109478"},"PeriodicalIF":7.5,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652710","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}