检索结果-内蒙古大学图书馆

Decisioning-Based Approach for Optimising Control engineering Tools Using Digital Twin Capabilities and Other Cyber-Physical Metaverse Manufacturing System Components

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3212-3221页

作者： Mourad, Nahia Alsattar, Hassan A. Qahtan, Sarah Zaidan, Aws Alaa Deveci, Muhammet Sangaiah, Arun Kumar Pedrycz, Witold British University in Dubai Faculty of Engineering and IT Dubai United Arab Emirates University of Mashreq College of Administrative Science Department of Business Administration Baghdad10067 Iraq Middle Technical University College of Health and Medical Technology-Baghdad Department of Computer Center Baghdad10047 Iraq SP Jain School of Global Management SydneyNSW2141 Australia National Defence University Turkish Naval Academy Department of Industrial Engineering Istanbul34040 Turkey Lebanese American University Department of Electrical and Computer Engineering Byblos Lebanon International Graduate Institute of AI National Yunlin University of Science and Technology Yunlin64002 Taiwan University of Alberta Faculty of Engineering Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Istanbul34010 Turkey

The optimisation of control engineering tools based on digital twin capabilities and other cyber-physical metaverse manufacturing system (CPMMS) components are crucial for the successful performance. This study proposes a model for optimising control engineering tools using digital twin capabilities and other CPMMS components to solve the open issues. The main contributions and novelty aspects of the methodological process are outlined as follows: Formulated and developed is a decision matrix based on a utility procedure for 10 control engineering tools with digital twin capabilities and other three CPMMS components (Programmable-Logic-Controller and Human-Machine-Interface, Internet of Things connectivity and cybersecurity features). This matrix accounts for the uncertainty associated with tool assessment and transformation evaluation issue;formulated and develop an integrating fuzzy weighted with zero-inconsistency-interval-valued spherical fuzzy rough sets (IvSFRS-FWZIC) and combined compromise solution (CoCoSo) methods. The IvSFRS-FWZIC method is utilised to assign importance degrees to the digital twin capabilities and other CPMMS components. The applicability and robustness of the proposed approach are validated and evaluated through conducting sensitivity, correlation, and comparative analyses. The proposed approach can assist managers in analysing and selecting the most suitable tool for developing CPMMS. © 1975-2011 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction

Advanced Zero-Shot Text-to-Speech for Background Removal and...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Leying Zhang, Wangyou Chen, Zhengyang Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containing backgrounds. To address these challenges, we propose a Controllable Masked Speech Prediction strategy coupled with a dual-speaker encoder, utilizing a task-related control signal to guide the prediction of dual background removal and preservation targets. Experimental results demonstrate that our approach enables precise control over the removal or preservation of background across various acoustic conditions and exhibits strong generalization capabilities in unseen scenarios. © 2025 IEEE.

关键词： background preservation background removal flow-matching text-to-speech

来源：评论

学校读者我要写书评

暂无评论

Waste Product Identification to assist EPR using Object Detection

Waste Product Identification to assist EPR using Object Dete...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： R Anil Prasad Ayain John Harika Gandiboina Gopika Jayadev Frugal Scientific Pvt Ltd Bengaluru India Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bengaluru India Department of AI & ML School of Engineering Dayananda Sagar University Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

With the increase in population, there has been a large increase in waste production. This has affected the environment and in turn have led to land pollution. To increase the recycling of products and increase the lifespan of raw materials, several countries of the world have implemented EPR policy. EPR requires collection of data related to the amount of non biodegradable waste generated by each company. With the recent technological advancements in machine vision, it has become possible to develop an infrastructure to easily collect such data in realtime using various object detection models like Yolo, SSD, RCNN and so on. This paper provides the details of a complete prototype that can help assist in the identification of non biodegradable waste products into their respective producers which can in turn help to implement the EPR policy and also elaborates on the model selection process for this application. The models that were used and compared in this paper includes CNN, Faster RCNN and Yolo v5

关键词： Waste management Biological system modeling Refining Prototypes Object detection Production Land pollution Raw materials Recycling Object recognition

来源：评论

学校读者我要写书评

暂无评论

A Lightweight ai Model for Anomaly Detection in Wireless Networks 2

A Lightweight AI Model for Anomaly Detection in Wireless Net...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, aiBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Idaho National Laboratory Ai Data & Visualization Idaho FallsID United States

ISBN: (纸本)9798331529529

Detecting network anomalies is critical for wireless network security and reliability. Traditional ai methods often require substantial computational resources, particularly when deployed on cloud servers, leading to increased network load and latency. In contrast, deploying ai models directly on end devices enables real-time data processing at the source, facilitating faster anomaly detection and mitigation. We propose a lightweight hierarchical ai model where initial inferences are made by a simple model and outputs confidence scores. Using a modified TOPSIS-based method, we determine an optimal confidence score threshold. Inferences below this threshold are forwarded to a more complex model for accurate analysis, reducing overall computational demands while maintaining high detection performance. Our approach is tested on a 5 G network dataset, demonstrating competitive performance compared to other anomaly detection models. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Boosting Supply Chain Transparency with Blockchain and Smart Contracts 2

Boosting Supply Chain Transparency with Blockchain and Smart...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Kumar, Rakesh Mangaiyarkarasi, V. Ramesh, Gajula Arvind, Sudha Fallah, Mohammed Hussein Niranjanamurthy, M. GLA University Department of Computer Engineering & Applications Mathura India New Prince Shri Bhavani College of Engineering and Technology Department of ECE Tamilnadu Chennai600073 India GRIET Bachupally Department of CSE Telangana Hyderabad India Department of ECE CMR Technical Campus Telangana Hyderabad India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq BMS Institute of Technology and Management Department of AI and ML Karnataka Bangalore560064 India

ISBN: (纸本)9798350368109

This research has developed the theoretical framework that outlines the application of blockchain and smart contracts for enhancing supply chain transparency. The framework here builds in the concept of decentralization and immutability of the blockchain technology to improve accountability, auditability and responsiveness within supply chains. The framework helps to acquire real-time visibility over different processes, control fraud, increase the accuracy of the data, and optimize several procedures as much as possible by implementing the mentioned smart contacts. When the framework is adopted, the various advantages include the efficiency gain in the processing of different transactions and the increased accuracy in the data handling capacity as well as enhanced compliance to the set standard regulatory compliances. Despite this, questions like scalability of the concept, compatibility issues and synergism of the players in the value web remain problematic. In a broader perspective, this study adds to the current literature on the integration of blockchain technology in managing supply chain and offers all-important pointers to the practising managers. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Aligning diffusion behaviors with Q-functions for efficient continuous control 24

Aligning diffusion behaviors with Q-functions for efficient ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Huayu Chen Kaiwen Zheng Hang Su Jun Zhu Department of Computer Science and Technology Tsinghua University and Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University Department of Computer Science and Technology Tsinghua University and Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University and Pazhou Lab (Huangpu) Guangzhou China

ISBN: (纸本)9798331314385

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95% of performance and still outperforms several baselines given only 1% of Q-labelled data during fine-tuning. Code: https://***/thu-ml/Efficient-Diffusion-Alignment

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convergence of Monte Carlo Exploring Starts with TD-Learning 63

Convergence of Monte Carlo Exploring Starts with TD-Learning

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Winnicki, Anna Srikant, R. University of Illinois at Urbana-Champaign Coordinated Science Laboratory Department of Electrical and Computer Engineering United States Uiuc C3.ai Digital Transformation Institute United States

ISBN: (纸本)9798350316339

The use of TD-learning has been widely employed in reinforcement learning algorithms due to its efficiency and practicality. Herein, we study the convergence of a variant of Monte Carlo Exploring Starts when operatornameTD(λ) is used in policy evaluation and policy improvement, and lookahead is used in the policy improvement step. Our results provide a threshold for the amount of lookahead that ensures convergence of Monte Carlo Exploring Starts with T D(λ) as a function of λ in[0,1]. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Non-intrusive Suppression on Enhancement Distortion for Noise Robust ASR

Advancing Non-intrusive Suppression on Enhancement Distortio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Wei Zhao, Siyi Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

Recent advancements in speech enhancement (SE) techniques have greatly improved speech clarity and intelligibility in challenging acoustic environments. However, integrating SE into automatic speech recognition (ASR) systems often results in performance degradation due to artifacts introduced during the enhancement process. While various methods have enhanced recognition accuracy in SE-ASR systems, they often require fine-tuning or re-training of SE or ASR models, which is impractical in many real-world applications. In this paper, we propose a lightweight distortion suppression (DS) network that addresses these artifacts without modifying the SE or ASR models, treating them as fixed black boxes. The DS module operates on the time-frequency (T-F) bands of the original and enhanced complex spectrograms, efficiently compensating for SE distortions using the original T-F information. We validate our approach through experiments on both Mandarin and English ASR tasks using monaural and multi-channel SE frontends, across various ASR backends. Results show that the DS module significantly improves the performance of SE-ASR systems, even when used with robust commercial ASR backends. © 2025 IEEE.

关键词： non-intrusive robust speech recognition speech distortion speech enhancement

来源：评论

学校读者我要写书评

暂无评论

NLP-Powered Short Video Enrichment System

NLP-Powered Short Video Enrichment System

引用

International Conference on Futuristic Technologies (INCOFT)

作者： Harsh Mali Amit Nara Jaya Gupta Smit Panchal Department of Computer Engineering A.P.Shah Institute of Technology Thane India Department of Computer Science & Engineering (AI&ML) A.P.Shah Institute of Technology Thane India

Recommendation systems have received a lot of attention lately due to their pivotal role in guiding users through the overwhelming volumes of information available online. This paper explores the integration of Natural Language Processing (NLP) techniques into recommendation systems to enhance their performance and user experience. The growth of the users has been increasing daily, to give them the satisfaction they want when scrolling through the feed. We have made a recommendation system using prominent technology. The system connects the user faster with their desired videos. To make a better system we have used React, Firebase, and Flask as the crucial elements of our work. We recommend the top 5 reels using some aspects. The aspects are hashtags, descriptions, and user id.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A survey on model-based reinforcement learning

引用

science China(Information sciences) 2024年第2期67卷 59-84页

作者： Fan-Ming LUO Tian XU Hang Lai Xiong-Hui CHEN Weinan ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir. ai Department of Computer Science and Engineering Shanghai Jiao Tong University

Reinforcement learning(RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning(MBRL) is believed to be a promising direction, as it constructs environment models in which trial-and-errors can occur without incurring actual costs. In this survey, we investigate MBRL with a particular focus on the recent advancements in deep RL. There is a generalization error between the learned model of a non-tabular environment and the actual environment. Consequently, it is crucial to analyze the disparity between policy training in the environment model and that in the actual environment, guiding algorithm design for improved model learning, model utilization, and policy training. In addition, we discuss the recent developments of model-based techniques in other forms of RL, such as offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Furthermore,we discuss the applicability and benefits of MBRL for real-world tasks. Finally, this survey concludes with a discussion of the promising future development prospects for MBRL. We believe that MBRL has great unrealized potential and benefits in real-world applications, and we hope this survey will encourage additional research on MBRL.

关键词： reinforcement learning model-based reinforcement learning planning model learning model learning with reduced error model usage

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：