检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1203-1216页

作者： Li, Changping Wang, Bingshu Zheng, Jiangbin Zhang, Yongjun Chen, C.L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Frequent road incidents cause significant physical harm and economic losses globally. The key to ensuring road safety lies in accurately perceiving surrounding road incidents. However, the highly dynamic nature of traffic introduces significant challenges, particularly in detecting sudden and temporary incidents. In this article, we propose a novel detection framework, multihead attention ResNet with dynamic bottleneck (DB_RESNET_MHA), to identify physical unsigned road incidents. Our approach introduces three key innovations. First, we develop a tailored data augmentation strategy to create images that closely mimic the complex variations found in real-world road environments. Second, we enhance model expressiveness by employing attention mechanisms to nonlinearly integrate convolutional kernels within the residual network. Furthermore, we refine the prediction head by applying spatially distinct attention weights, enabling the model to capture intricate correlations between different features more effectively. To demonstrate the effectiveness of our method, we create a dataset for unsigned road incidents (UnsignRI), comprising a total of 16 323 images that capture 12 distinct types of incidents. It stands out as the most comprehensive dataset in the field, encompassing a wide range of geographical features and incident categories. Experimental results show that DB_RESNET_MHA achieves an average accuracy of 96.2% and a f1-score of 0.955 across various categories of unsigned incidents, surpassing other models. © 2020 IEEE.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Prediction of Corrosion Inhibition Efficiency of Expired Pharmaceuticals: Model Development and Application

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-12页

作者： Putra, Dzaki Asari Surya Ardyansyah, Nibras Bahy Putranto, Nicholaus Verdhy Trisnapradika, Gustina Alfa Akrom, Muhamad Rustad, Supriadi Dipojono, Hermawan Kresno Maezono, Ryo Faculty of Computer Science Study Program in Informatics Engineering Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Quantum and Nano Technologies Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung40132 Indonesia School of Information Science Japan Advanced Institute of Science and Technology Ishikawa923-1292 Japan

Corrosion poses a significant challenge in industries due to material degradation and high maintenance costs, making effective inhibitors essential. Recent studies suggest expired pharmaceuticals as alternative corrosion inhibitors, but identifying the most efficient compounds can be time-consuming. This study applies machine learning models, particularly Gradient Boosting Regressor (GBR), to predict corrosion inhibition efficiency (CIE). The developed model is integrated into a web-based application, enabling real-time, accurate CIE predictions. Results show GBR as the more precise model for predicting CIE, with low error rates. The streamlit-based web application offers a user-friendly platform, facilitating quick identification of suitable inhibitors. It is flexible, supporting analysis beyond corrosion inhibitors, and significantly enhances the efficiency of the evaluation process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying 31

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Guanghui Liu, Dexi Nie, Jian-Yun Wan, Qizhi Hu, Rong Liu, Xiping Liu, Wanlong Liu, Jiaming School of Information Management Jiangxi University of Finance and Economics China Canada School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Statistics Division of the Physical Sciences The University of Chicago United States

ISBN: (纸本)9798891761964

Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Textual-dominated Multimodal Depression Detection 30

Textual-dominated Multimodal Depression Detection

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Huang, Kuan Lu, Heli Li, Jing Nanchang University School of Information Engineering Nanchang China The Second Affiliated Hospital of Nanchang University Department of Psychosomatic Medecine Nanchang China Tianjin University of Technology School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350391916

Depression poses a major threat to an individual's overall physical and psychological health, as well as their social functioning. Consequently, it is urgent to design an effective automated diagnostic technique for depression. Recent studies have revealed that multimodal approaches produce better detection performance than unimodal methods. To this end, this paper introduces a multimodal depression detection framework using visual and textual data. Initially, separate networks are employed to extract their shallow features, aiming to capture the diversity across various modalities. The visual features are then integrated into the textual features through a newly designed Textual-dominated Cross-modal Fusion module to highlight the information transmitted by the textual features. Finally, the Multilayer Perceptron-based Hybrid Unit is designed to facilitate deep feature interaction, improving the overall detection performance. Our method was assessed on the NCUDID dataset and achieved promising experimental results with a value of 3.41 for the MAE and 4.59 for the RMSE. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Analysis of Image and Video Quality Metrics for Compression Techniques 3

Analysis of Image and Video Quality Metrics for Compression ...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Saraswat, Pankaj David, Roshita Agarwal, Ankita Sanskriti University Department of Computer Science and Engineering Uttar Pradesh Mathura India School of Engineering and Technology Department of Civil Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350354171

The evaluation of picture and video high-quality metrics for compression techniques is a vital study location that offers perception into the effectiveness of different compression algorithms. Best metrics are equipment used to measure the level of degradation of a photo or video because of compression. Those metrics can be divided into objective metrics, which measure the numerical variations between the original and compressed photograph or video, and subjective metrics, which measure the perceived best from a human factor of view. A selection of metrics has been advanced for assessing photograph and video compression strategies in recent years. It includes algorithms such as suggested squared errors, peak signal-to-noise ratio, and structural similarity index. Moreover, compression-specific metrics, which include bit-fee, compression ratio, and other functions, are frequently used to measure the effectiveness of algorithms. By evaluating those metrics to a general or reference, it is possible to degree the pleasantness of a given compression technique. Furthermore, studying the results of excellent metrics can provide treasured feedback for improving compression algorithms. In the end, the analysis of image and video metrics for compression techniques is vital for measuring the effectiveness of algorithms and enhancing their overall performance. © 2024 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Modeling Product's Visual and Functional Characteristics for Recommender systems (Extended Abstract) 39

Modeling Product's Visual and Functional Characteristics for...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Wu, Bin He, Xiangnan Chen, Yu Nie, Liqiang Zheng, Kai Ye, Yangdong Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China University of Science and Technology of China School of Information Science and Technology Hefei230027 China Shandong University School of Computer Science and Technology Shandong266237 China University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan611731 China

ISBN: (纸本)9798350322279

Recommender systems aim at helping users to discover interesting items and assisting business owners to obtain more profits. Nonetheless, traditional recommendations fail to explore the varying importance of product characteristics for different product domains. In light of this, we propose a novel probabilistic model for recommendation, which could learn products' characteristics in a fine-grained manner. Specifically, a user's preference for a given product is modeled as a combination of visual and functional aspects. To make our method practical in large-scale industrial scenarios, we devise a computationally efficient learning algorithm to optimize VFPMF's parameters. Experiments on four real-world datasets demonstrate the effectiveness and efficiency of our solution, compared with several state-of-the-art methods. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Convolutional Neural Networks Based Spinach Classification and Recognition System

引用

computers, Materials & Continua 2022年第10期73卷 343-361页

作者： Sankar Sennan Digvijay Pandey Youseef Alotaibi Saleh Alghamdi Department of Computer Science and Engineering Sona College of TechnologySalem636005India Department of Technical Education Department of Electronics EngineeringInstitute of Engineering and TechnologyDr.A.P.J.Abdul Kalam Technical UniversityLucknowIndia Department of Computer Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

In the present scenario,Deep Learning(DL)is one of the most popular research algorithms to increase the accuracy of data *** to intra-class differences and inter-class variation,image classification is one of the most difficult jobs in image *** or spinach recognition or classification is one of the deep learning applications through its *** is more critical for human skin,bone,and hair,*** provides vitamins,iron,minerals,and *** is beneficial for diet and is readily available in people’s *** researchers have proposed various machine learning and deep learning algorithms to classify plant images more accurately in recent *** paper presents a novel Convolutional Neural Network(CNN)to recognize spinach more *** proposed CNN architecture classifies the spinach category,namely Amaranth leaves,Black nightshade,Curry leaves,and Drumstick *** dataset contains 400 images with four classes,and each type has 100 *** images were captured from the agricultural land located at Thirumanur,Salem district,Tamil *** proposed CNN achieves 97.5%classification *** addition,the performance of the proposed CNN is compared with Support Vector Machine(SVM),Random Forest,Visual Geometry Group 16(VGG16),Visual Geometry Group 19(VGG19)and Residual Network 50(ResNet50).The proposed provides superior performance than other models,namely SVM,Random Forest,VGG16,VGG19 and ResNet50.

关键词： Accuracy convolutional deep learning plant neural networks spinach

来源：评论

学校读者我要写书评

暂无评论

STAR-RIS Aided INAC in Urban Canyon Scenarios

STAR-RIS Aided INAC in Urban Canyon Scenarios

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Hou, Tianwei Guan, Da Sun, Xin Li, Anna Yi, Wenqiang Liu, Yuanwei Nallanathan, Arumugam School of Electronic and Information Engineering Beijing Jiaotong University Beijing China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computing and Communications Lancaster University Lancaster United Kingdom Ku Leuven Department of Electrical Engineering Leuven Belgium School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

ISBN: (纸本)9798350368369

This study investigates the application of a simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided medium-Earth-orbit (MEO) satellite network for providing both global positioning services and communication services in the urban canyons, where the direct satellite-user links are obstructed. Superposition coding (SC) and successive interference cancellation (SIC) techniques are utilized for the integrated navigation and communication (INAC) networks, and the composed navigation and communication signals are reflected or transmitted to ground users or indoor users located in urban canyons. To meet diverse application needs, navigation-oriented (NO)-INAC and communicationoriented (CO)-INAC have been developed, each tailored according to distinct power allocation factors. We then proposed two algorithms, namely navigation-prioritized-algorithm (NPA) and communication-prioritized-algorithm (CPA), to improve the navigation or communication performance by selecting the satellite with the optimized position dilution of precision (PDoP) or with the best channel gain. © 2025 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Business Scenario Driven Reinforcement Learning Testing Method 26

Business Scenario Driven Reinforcement Learning Testing Meth...

引用

26th ACIS International Winter Conference on Software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2023

作者： Cai, Lizhi Wang, Jin School of Information Science and Engineering East China University of Science and Technology Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai China

ISBN: (纸本)9798350345865

Reinforcement learning has been successfully applied in software testing, but the existing testing methods cannot perform effective testing according to the characteristics of applications, and using outdated interactive experience during training, resulting in inefficient testing. In this paper, we propose BSDRTesting. Firstly, the demonstration experience of human users is collected according to the functional scenarios and business logic of each application, and combining reinforcement learning and imitation learning to maximize rewards while imitating user behavior, experience replay aims to sample experiences from the agent's self-exploration and expert demonstrations to improve sampling efficiency. At the same time, according to the input rules, the black-box testing method is used to fully test the input events, and finally an experience filtering mechanism is proposed, and the reward value and TD-Error are used as the basis for priority sampling. The experimental results on 10 open source applications show BSDRTesting has achieved significant improvements in code coverage and branch coverage compared with existing methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on appliance recognition system based on improved transformer

Research on appliance recognition system based on improved t...

引用

2024 International Conference on Automation Control, Algorithm, and Intelligent Bionics, ACAIB 2024

作者： Wang, Man Jian, Chenchen Xiong, Yong Cheng, Cunliang School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai201209 China Shanghai Institute of Microsystems and Information Technology Chinese Academy of Science Shanghai200050 China

ISBN: (纸本)9781510682597

In response to the need for controlling unauthorized electrical appliances, we have developed a deep learning-based smart appliance recognition system. This paper proposes an innovative approach that effectively extracts features of appliance usage current, such as instantaneous fluctuations, peak currents, and transient changes caused by the starting or shutting down of appliances, using the Transformer's encoding layer. We refined the multi-head attention mechanism and removed the decoding module to simplify the model and focus on feature extraction. After the feature extraction phase, we employed ResNet as the feature mapping module, in conjunction with the enhanced Transformer. This model surpasses all previous models in identifying incremental current produced by appliances and is capable of adapting to the recognition of a large scale of appliances. © 2024 SPIE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：