检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Syu, Jia-Hao Chun-Wei Lin, Jerry Yu, Philip S. Department of Computer Science and Information Engineering National Taiwan University Taiwan Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Computer Science University of Illinois Chicago United States

As more and more automatic vehicles, power consumption prediction becomes a vital issue for task scheduling and energy management. Most research focuses on automatic vehicles in transportation, but few focus on automatic ground vehicles (AGVs) in smart factories, which face complex environments and generate large amounts of data. There is an inevitable tradeoff between feature diversity and interference. In this paper, we propose Distributed Multi-Head learning (DMH) systems for power consumption prediction in smart factories. Multi-head learning mechanisms are proposed in DMH to reduce noise interference and improve accuracy. Additionally, DMH systems are designed as distributed and split learning, reducing the client-to-server transmission cost, sharing knowledge without sharing local data and models, and enhancing the privacy and security levels. Experimental results show that the proposed DMH systems rank in the top-2 on most datasets and scenarios. DMH-E system reduces the error of the state-of-the-art systems by 14.5% to 24.0%. Effectiveness studies demonstrate the effectiveness of Pearson correlation-based feature engineering, and feature grouping with the proposed multi-head learning further enhances prediction performance. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Recognizing Daily Human Activities Using Smart Home Sensors 8

Deep Learning Approaches for Recognizing Daily Human Activit...

引用

Joint 8th International Conference on Digital Arts, Media and Technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Sanpote, Worrakit Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit Mekruksavanich, Sakorn School of Information and Communication Technology Department of Computer Science University of Phayao Phayao Thailand School of Information and Communication Technology Department of Computer Engineering University of Phayao Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Faculty of Engineering Department of Computer Engineering Nakorn Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350396546

Nowadays, one of the most important objectives in health-related research is the improvement of the living condition and well-being of people. Smart home systems can provide health protection for residents based on the results of daily activity recognition. Recent advances and developments in sensor technology have increased the need for sensor-compatible goods and services in smart homes. Consequently, the ever-increasing volume of data requires the field of deep learning (DL) for auto-matic human motion recognition. Recent research has modeled spatiotemporal sequences gathered by smart home sensors using long short-term memory networks. In this work, ResNeXt-based models that learn to classify human activities in smart homes were proposed to improve recognition performance. Experiments conducted on Center for Advanced Studies in Adaptive Systems (CASAS) data, a publicly available benchmark dataset, shows that the proposed ResNeXt-based techniques are significantly superior to the existing DL methods and provide better results compared to the existing literature. The ResNeXt model achieved the averaged accuracy over the benchmark method to 84.81%, 93.57%, and 90.38% for the CASAS-Cairo, CASAS-Milan and CASAS-Kyoto3 datasets, respectively. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Cooling Yb-Doped Silica Fibers and Fiber Lasers with Anti-Stokes Pumping 5

Cooling Yb-Doped Silica Fibers and Fiber Lasers with Anti-St...

引用

Photonic Heat Engines: science and Applications V 2023

作者： Frey, Benjamin N. Balliu, Enkeleda Vigneron, Pierre-Baptiste Knall, Jenny Hawkins, Thomas W. Meehan, Bailey Cahoon, Mary Ann Ballato, John Engholm, Magnus Dragic, Peter D. Yu, Nanjie Boilard, Tommy Bernier, Martin Digonnet, Michel J.F. Applied Physics Department Stanford University CA United States Department of Engineering Mathematics and Science Education Mid Sweden University Sundsvall Sweden Department of Materials Science and Engineering Clemson University South Carolina United States Department of Electrical Computer Engineering U. of Illinois at Urbana-Champaign IL United States Université Laval Québec Canada

ISBN: (纸本)9781510659797

Optical cooling in Yb-doped silica fibers using anti-Stokes fluorescence has become a subject of great interest in the fiber laser community. This paper provides an update on the development of silica fibers designed specifically to enhance their cooling properties. This growing list includes a new, nearly single-mode fiber with a borophosphosilicate core that produced –65 mK of cooling with only 260 mW of 1040-nm pump power. The silica compositions that have now been successfully cooled at atmospheric pressure by anti-Stokes fluorescence by our team include aluminosilicate, aluminofluorosilicate, borophosphosilicate, and aluminosilicate doped with one of three different alkali-earth nanoparticles (Ba, Sr, and Ca). By fitting the measured temperature dependence of the cooled fiber on pump power, two key parameters that control the degree of cooling are inferred, namely the critical quenching concentration and the absorptive loss due to impurities. The inferred values compiled for the fibers that cooled indicate that the extracted heat is highest when the Yb concentration is 2 wt.% or more (to maximize heat extraction), the Al concentration is ~0.8 wt.% or greater (to reduce quenching), and the absorptive loss is below approximately 15 dB/km, and ideally below 5 dB/km (to minimize heating due to pump absorption). Only two of the reported fibers, an LaF3-doped and an LuF3-doped nanoparticle fiber, did not cool, because their Yb and Al concentrations were not sufficiently high. This analysis shows that through careful composition control (especially the Al and Yb concentrations) and minimization of the OH contamination, a new generation of Yb-doped silica fibers is emerging with higher Yb concentrations, greater resistance to quenching, and lower residual loss than commercial Yb-doped fibers. They can be expected to have a significant impact not only on optically cooled devices but also on a much broader range of fiber lasers and amplifiers. © 2023 SPIE.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Inverse Document Frequency & KNN Machine Learning Approach based Novel Text Semantic Analysis 2

Inverse Document Frequency & KNN Machine Learning Approach b...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Aljohani, Abeer A. Jaroli, Priyanka Chitkara, Rajat Applied College Taibah University Computer Science Department Saudi Arabia Banasthali University Department of Computer Science Newai India University Institute of Engineering & Technology Chitkara University Punjab India

ISBN: (纸本)9781665437899

In the modern era each and every thing is digital. E- commerce takes the place of the physical market. People buy anything not going physically anywhere and they are used the E-commerce platform. When The people buy, initially read the reviews provided by the previous customer regarding the product and decide they buy or not. So, the reviews are most essential part of the customer as well as for the customer. This paper delineates the sentiment analysis (SEAN) of the cell amazon real data values initially, use the NLTK, Porter Stemmer and various processing for pre-process the data and get the clean and desired data. Secondly, use the term frequency inverse document frequency (TFIDF) method for extracting the feature and divide the data using the train and test split and last apply the K-nearest neighbor method to train the machine. The artificial model predicts the positive and negative reviews. The experiment outcome result shows the model accuracy, precision, recall of the novel developed algorithm on the real text set. © 2022 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design Towards Sum-Rate Maximization for Holographic Active RIS-Aided Uplink Near-Field Communications

引用

IEEE Internet of Things Journal 2025年第12期12卷 18582-18595页

作者： Singh, Sandeep Singh, Keshav Singh, Sandeep Kumar Shin, Hyundong Duong, Trung Q. Kaohsiung80424 Taiwan National Sun Yat-sen University Institute of Communications Engineering Kaohsiung80424 Taiwan Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of Motilal Nehru National Institute of Technology Allahabad Department of Electronics and Communication Engineering Prayagraj India Kyung Hee University Department of Electronics and Information Convergence Engineering Deogyeong-daero Gyeonggi-do Yongin-si1732 Korea Republic of Memorial University Faculty of Engineering and Applied Science St. John'sNLA1C 5S7 Canada Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom

Holographically-driven active reconfigurable intelligent surface (HARIS), leveraging densely packed sub-wavelength elements, overcomes the limitations of conventional RIS in signal processing, unlocking advanced capabilities for next-generation networks. Thus, to exploit its full potential, this work proposes the integration of HARIS into an Internet of Things (IoT) multi-user uplink near-field-driven wireless communication system. A sum-rate maximization problem is formulated to provide efficient resource utilization by jointly optimizing the equalizer design, power allocation at each IoT user, and the HARIS phase shift, while satisfying strict constraints of quality of service (QoS) requirement and limited power budget at each IoT user and HARIS. Due to the non-convex nature of the problem, we propose an alternating optimization (AO)-based algorithm, incorporating techniques such as minimum mean square error (MMSE), convex upper bound approximation, and semidefinite relaxation (SDR). Then, extensive simulations validate the algorithm's efficacy and convergence, demonstrating up to 63% higher performance with HARIS than passive RIS. Additionally, we highlight that near-field communication yields up to 90% higher sum-rate than hybrid 76% and far-field model 73%. Moreover, we demonstrate the impact of imperfect channel state information (iCSI) on the system performance. © 2014 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Interpretable Arabic Hate Speech Detection using Large Language Model 2

Interpretable Arabic Hate Speech Detection using Large Langu...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Alwateer, Majed Gad, Ibrahim Elmarhomy, Mahmoud Elmarhomy, Ghada Hashim, Hasan Almaliki, Malik Atlam, El-Sayed College of Computer Science and Engineering Taibah University Department of Computer Science Saudi Arabia Tanta University Faculty of Science Computer Science Department Tanta31527 Egypt College of Applied Taibah University Computer Science and Information Saudi Arabia College of Computer Science and Engineering Taibah University Department of Information Systems Saudi Arabia

ISBN: (纸本)9798331506995

Social media platforms serve as significant spaces for users to have conversations, discussions and express their opinions. However, anonymity provided to users on these platforms allows the spread of hate speech and other offensive material. Due to the wide-ranging nature of these platforms, there is a critical need to automatically detect and report occurrences of hate speech. There are various detection methods, but many of them operate as black boxes, lacking interpretability and explainability by design. To address the lack of interpretability, this study explores the development of an interpretable framework to detect hate speech in Arabic using large language models (LLMs). The proposed approach combines advanced natural language processing techniques with interpretable machine learning methods to enhance understanding of model decisions. The experimental results demonstrate that the model achieves high accuracy while maintaining interpretability, enabling users to understand the reasoning behind the detections. The proposed method achieves an accuracy of 0.846%, with a precision of 0.843% and a recall of 0.846%, outperforming existing Arabic hate speech detection models. These results show the effectiveness of combining LLM with interpretability for this critical task, providing a reliable and transparent solution for automated moderation of harmful content. © 2025 IEEE.

关键词： Arabic Hate Speech Detection Large Language Mode XAI

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Novel Routing Protocols for Ubiquitous Network 7

Design and Development of Novel Routing Protocols for Ubiqui...

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Chavan, Chandrashekhar Pomu Talabattula, Srinivas Pes University Department of Computer Science and Engineering Bangalore India Electrical Communication Engineering Indian Institute of Science Applied Photonics Lab Bangalore India

ISBN: (纸本)9781665421683

In this paper, we designed and developed ECA (Event Condition Action) scheme based novel Improved AODV Position and Speed Aware Routing (ECA-IAODV-PSAR) and Improved AODV Edge Connectivity (ECA-IAODV-EC) routing protocols. In specific, these two routing protocols use the speed and position information of the node received from the Global Positioning System (GPS) to deal with routing control packet overhead during inflated mobility. The primary routing protocol ECA-IAODV-PSAR is an alteration of the PSAR routing protocol. The ECA-IAODV-PSAR protocol set limits flooding of the route query packet to the tiny zone of the ubiquitous network to select the optimal route towards the ultimate destination. The results produced in the simulation demonstrate the feasibility of the scheme proposed. © 2022 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and AI based Robotic System for Archaeological Research 6

Machine Learning and AI based Robotic System for Archaeologi...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Singh, Manmohan Rai, Ashutosh Kumar Vamsi Krishna, G. Dileep Kumar, Y. Mishra, Rashmi Kothandaraman, D. Department of Computer Science and Engineering IES College of Technology Bhopal India VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India Department of Electronics and Instrumentation Engineering Sree Vidyanikethan Engineering College Mohan Babu University Andhra Pradesh Tirupati India Department of Applied Science & Humanities G L Bajaj Institute of Technology & Management Greater Noida India School of Computer Science and Artificial Intelligence SR University Telangana Warangal India

ISBN: (纸本)9798350398496

The use of artificial intelligence (AI) in archaeology and its prospective use in the discipline are the primary focuses of this research study. Even if this issue may not fall under the major interests of certain people, the consequences of being ignorant of the most important aspects of the subject might be catastrophic. As AI is used in many different methods by archaeologists, including the creation of 3D representations of historical sites and the scanning of lands with a laser radar in order to identify old burials. In addition, freshly developed strategies have been put through rigorous testing, and they are almost ready to be put into action. This article provides insight into a branch of research that examines how the recent past and the established present interact. One last thing to mention is that AI is assisting archaeologists in their digs, which in turn makes artifacts and cultural treasures more accessible to the general public. Researchers believe that in the not-too-distant future, they will be able to appease members of the public by virtually demonstrating the significance of ancient sites. © 2023 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Real-Time Scheduling for Energy Optimization: Smart Grid Integration with Renewable Energy 7

Real-Time Scheduling for Energy Optimization: Smart Grid Int...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gopalakrushna, A. Raj, Vijilius Helena Vani, V. Divya Singh, Navdeep Jethabhai, Patel Yogeshkumar Chakravarthi, M. Kalyan Vignana Bharathi Institute of technology Telangana Hyderabad India New Horizon College of Engineering Department of Applied Sciences Karnataka Bangalore India Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Sankalchand Patel University Faculty of Computer Science Shri C.J. Patel College of Computer Studies Gujarat Visnagar India University of Technology and Applied Sciences Department of Electronics and Communication Engineering Muscat Oman

ISBN: (纸本)9798350350067

Reliable power system operations, cost reduction, demand and supply balance maintenance, and efficient load scheduling all depend on real-time energy optimisation. Nevertheless, the unpredictability of electric loads and renewable energy sources (RES) makes real-time energy optimization difficult. As a result, the Energy Management Controller (EMC) was developed, which can automatically react to DR signals and resolve energy-related issues. In light of this, EDGE, a hybrid algorithm combining elements of genetic algorithm (GA) and enhanced differential evolution (EDE), is devised in this work. The EDGE algorithm is used to train the EMC to automatically react to DR signals and schedule the 3 classes of household loads - hybrid, non-interruptible, and interruptible - to handle energy management issues. The results show that in terms of power cost reduction, minimizing carbon release, PAR relief, and client discomfort maximization, the suggested EDGE algorithm performs better than benchmark methods. © 2024 IEEE.

关键词： energy optimization renewable energy Smart grid

来源：评论

学校读者我要写书评

暂无评论

The GraphTempo Framework for Exploring the Evolution of a Graph through Pattern Aggregation

arXiv

引用

arXiv 2024年

作者： Tsoukanara, Evangelia Koloniari, Georgia Pitoura, Evaggelia Triantafillou, Peter Department of Applied Informatics University of Macedonia Greece Department of Computer Science & Engineering University of Ioannina Greece Department of Computer Science University of Warwick Coventry United Kingdom

When the focus is on the relationships or interactions between entities, graphs offer an intuitive model for many real-world data. Such graphs are usually large and change over time, thus, requiring models and strategies that explore their evolution. We study the evolution of aggregated graphs and introduce the GraphTempo model that allows temporal and attribute aggregation not only on node level by grouping individual nodes, but on a pattern level as well, where subgraphs are grouped together. Furthermore, We propose an efficient strategy for exploring the evolution of the graph based on identifying time intervals of significant growth, shrinkage or stability. Finally, we evaluate the efficiency and effectiveness of the proposed approach using three real graphs. © 2024, CC BY.

关键词： Graphic methods

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：