检索结果-内蒙古大学图书馆

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Infrastructure and city ontologies

引用

Proceedings of the Institution of Civil Engineers: Smart Infrastructure and Construction 2022年第2期176卷 43-52页

作者： Varga, Liz McMillan, Lauren Hallett, Stephen Russell, Tom Smith, Luke Truckell, Ian Postnikov, Andrey Rodger, Sunil Vizcaino, Noel Perkins, Bethan Matthews, Brian Lomax, Nik Department of Civil Environmental and Geomatic Engineering Infrastructure Systems Institute University College London London United Kingdom School of Water Energy and Environment Cranfield University Cranfield United Kingdom Environmental Change Institute Oxford University Oxford United Kingdom Software Engineering Department De la Rue Team Valley Trading Estate Gateshead United Kingdom Lincoln Agri-Robotics University of Lincoln Lincoln United Kingdom Zentrum Klinische Studien Universitätsklinikum Freiburg Freiburg Germany Scientific Computing Department Science and Technology Facilities Council Uk Research and Innovation Rutherford Appleton Laboratory Harwell Campus Didcot United Kingdom School of Geography University of Leeds Leeds United Kingdom

The creation and use of ontologies has become increasingly relevant for complex systems in recent years. This is because of the growing number of use of cases that rely on real-world integration of disparate systems, the need for semantic congruence across boundaries and the expectations of users for conceptual clarity within evolving domains or systems of interest. These needs are evident in most spheres of research involving complex systems, but they are particularly apparent in infrastructure and cities where traditionally siloed and sectoral approaches have dominated, undermining the potential for integration to solve societal challenges such as net zero, resilience to climate change, equity and affordability. This paper reports on findings of a literature review on infrastructure and city ontologies and puts forward some hypotheses inferred from the literature findings. The hypotheses are discussed with reference to the literature and provide avenues for further research on (a) belief systems that underpin non-top-level ontologies and the potential for interference from them, (b) the need for a small number of top-level ontologies and translation mechanisms between them and (c) clarity on the role of standards and information systems in the adaptability and quality of data sets using ontologies. A gap is also identified in the extent that ontologies can support more complex automated coupling and data transformation when dealing with different scales. © 2023 ICE Publishing: All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

UX Definitions: The Missing Components and the Need for the Context and Time of Use 13

UX Definitions: The Missing Components and the Need for the ...

引用

13th International Conference on computing Communication and Networking Technologies, ICCCNT 2022

作者： Mkpojiogu, Emmanuel O.C. Okeke-Uzodike, Obianuju E. Emmanuel, Emelda I. Eze, Chika Universiti Utara Malaysia School of Computing Sintok06010 UUM Malaysia Veritas University Department of Software Engineering Abuja Nigeria Durban University of Technology Faculty of Management Sciences Department of Applied Management KwaZulu-Natal Pietermaritzburg South Africa Ibrahim Badamasi Babangida University Faculty of Management and Social Science Department of Sociology Niger State Lapai Nigeria Veritas University Abuja Faculty of Education Department of Educational Foundations Guidance and Counselling Unit Abuja Nigeria

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

There are several definitions for user experience (UX). However, this study unveiled that there are missing components in those definitions. An analysis of user experience definitions shows that the definitions had the elements of time of use and context of use absent in them. These missing components limit and obscure the understanding of user experience. Nevertheless, the inclusion of these components improves the specificity, robustness, uniqueness, and meaningfulness of UX and will provide illumination for the conceptualization, design, evaluation, and modeling of UX. As UX is understood the way it is defined, an all-encompassing definition that comprises the components of time and context of use will therefore be worthwhile. This study reviewed extant related literature and unraveled these gaps and suggested their inclusion in user experience definitions. © 2022 IEEE.

关键词： User experience

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Human Activity Recognition Using Locality Constrained Linear Coding Combined With Machine Learning (NG-HAR-LCML)

引用

Healthcare Technology Letters 2025年第1期12卷

作者： Shabbir, Maryam Ahmad, Fahad Alanazi, Saad Awadh Khan, Muhammad Hassan Li, Jianqiang Mahmood, Tariq Naseem, Shahid Anwar, Muhammad Department of Computer Sciences Bahria University Punjab Lahore Pakistan Department of Computer Science Faculty of Computing & Information Technology University of the Punjab Lahore Pakistan School of Computing Faculty of Technology University of Portsmouth Portsmouth United Kingdom University of Portsmouth Portsmouth United Kingdom Department of Computer Science College of Computer and Information Sciences Jouf University Aljouf Sakaka Saudi Arabia The School of Software Engineering Beijing University of Technology Beijing China Lab CCIS Prince Sultan University Riyadh Saudi Arabia Department of Information Sciences University of Education Vehari Pakistan Faculty of Information Sciences Division Science &Technology University of Education Lahore Pakistan

Accurate Human Activity Recognition (HAR) is a critical challenge with wide-ranging applications in healthcare, assistive technologies, and human-computer interaction. Traditional feature extraction methods often struggle to capture the complex spatial and temporal dynamics of human movements, leading to suboptimal classification performance. To address this limitation, this study introduces a novel encoding approach using Locality-Constrained Linear Coding (LLC) to enhance the discriminative power of hand-crafted features extracted from low-cost wearable sensors—an accelerometer and a gyroscope. The proposed LLC-based encoding scheme enables robust feature representation, improving the accuracy of HAR models. The encoded features are classified using a diverse set of Machine Learning (ML) and Deep Learning (DL) algorithms, including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbours (KNN), AdaBoost, Gradient Boosting Machine (GBM), and Deep Belief Network (DBN). Extensive quantitative evaluations demonstrate that LLC significantly outperforms conventional feature encoding techniques, leading to improved classification accuracy. Among the tested models, DBN achieves a state-of-the-art accuracy of 99%, highlighting its superiority for HAR tasks. The contributions of this research are threefold: (1) it establishes the necessity of an advanced encoding scheme (LLC) for feature enhancement in HAR, (2) it provides a rigorous comparative analysis of multiple ML and DL classifiers, and (3) it introduces a scalable and cost-effective HAR framework suitable for real-world applications. Performance is comprehensively assessed using robust evaluation metrics such as Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The findings of this study offer new insights into feature encoding for HAR, setting a foundation for future advancements in sensor-based act

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Co-Evolution Algorithm with Variable-Importance Grouping for Large-Scale Optimization

A Cooperative Co-Evolution Algorithm with Variable-Importanc...

引用

Congress on Evolutionary Computation

作者： Yongfeng Li Yuze Zhang Lijia Ma Junkai Ji Dugang Liu Victor C. M. Leung Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Cooperative co-evolution (CC) is a promising direction in solving large-scale multiobjective optimization problems (LMOPs). However, most existing methods of grouping decision variables face some difficulties when searching in the huge search space. Specifically, the methods of grouping decision variables can be classified into two types, i.e., high-consumption grouping methods and non-consumption grouping methods. On the one hand, the former ones divide the decision variables into different groups based on the correlation analysis between variables, which consume much evaluation. This way may lead to premature convergence within limited computational resources. On the other hand, the later ones allocate the decision variables into sub-groups based on some metrics, e.g., order and size, which consume no evaluation while may cause the search fall into local optima. To alleviate the above issues, this paper proposes a CC-based algorithm with a variable-importance grouping (VIG) method, called VICCA. Firstly, the decision variables are classified into several subgroups according to their importance quantified by a meta-gene construction method. Secondly, a CC strategy is designed to simultaneously optimize all subgroups of decision variables formed by VIG using the differential evolution operator, which aims to accelerate the convergence speed. Thirdly, a global evolutionary strategy is proposed to optimize original decision variable space by the competitive swarm optimizer, aiming to maintain the diversity. Finally, the experiments demonstrate that our proposed VICCA has the significant advantage in solving LMOPs when compared with state-of-the-art evolutionary algorithms.

关键词： Measurement Correlation Sociology Evolutionary computation Reinforcement learning Germanium Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Offsite Evaluation of Localization Systems: Criteria, Systems, and Results From IPIN 2021 and 2022 Competitions

IEEE Journal on Indoor and Seamless Positioning and Navigati...

引用

IEEE Journal on Indoor and Seamless Positioning and Navigation 2024年 2卷 92-129页

作者： Potorti, Francesco Crivello, Antonino Lee, Soyeon Vladimirov, Blagovest Park, Sangjoon Chen, Yushi Wang, Long Chen, Runze Zhao, Fang Zhuge, Yue Luo, Haiyong Perez-Navarro, Antoni Jimenez, Antonio R. Wang, Han Liang, Hengyi De Cock, Cedric Plets, David Cui, Yan Xiong, Zhi Li, Xiaodong Ding, Yiming Franco, Fernando Javier Alvarez Polo, Fernando Jesus Aranda Rodriguez, Felipe Parralejo Moreira, Adriano Pendao, Cristiano Silva, Ivo Ortiz, Miguel Zhu, Ni Li, Ziyou Renaudin, Valerie Wei, Dongyan Ji, Xinchun Zhang, Wenchao Wang, Yan Ding, Longyang Kuang, Jian Zhang, Xiaobing Dou, Zhi Yang, Chaoqun Kram, Sebastian Stahlke, Maximilian Mutschler, Christopher Coene, Sander Li, Chenglong Venus, Alexander Leitinger, Erik Tertinek, Stefan Witrisal, Klaus Wang, Yi Wang, Shaobo Jin, Beihong Zhang, Fusang Su, Chang Wang, Zhi Li, Siheng Li, Xiaodong Li, Shitao Pan, Mengguan Zheng, Wang Luo, Kai Ma, Ziyao Gao, Yanbiao Chang, Jiaxing Ren, Hailong Guo, Wenfang Torres-Sospedra, Joaquin Pisa56124 Italy Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Beijing University of Posts and Telecommunications School of Computer Science National Pilot Software Engineering School Beijing100876 China Chinese Academy of Sciences Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Beijing100190 China Universitat Oberta de Catalunya Faculty of Computer Sciences Multimedia and Telecommunication Barcelona08035 Spain Arganda del Rey28500 Spain Huawei Technologies Company Ltd. Shenzhen100015 China IMEC-WAVES/Ghent University Department of Information Technology Gent9052 Belgium Nanjing University of Aeronautics and Astronautics College of Automation Nanjing210016 China University of Extremadura Badajoz06006 Spain University of Trás-os-Montes and Alto Douro Department of Engineering School of Sciences and Technology Vila Real5000-801 Portugal Universidade Do Minho Centro Algoritmi Guimarães4800-058 Portugal Ame Department of the University Gustave Eiffel Geoloc Laboratory Bouguenais44344 France Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China Wuhan University Gnss Research Center Wuhan430072 China AutoNavi Software Company Ltd. China Fraunhofer Institute for Integrated Circuits Iis Fraunhofer Iis Nuremberg90411 Germany Erlangen91058 Germany Graz University of Technology Christian Doppler Laboratory for Location-Aware Electronic Systems Graz8010 Austria Institute of Software Chinese Academy of Sciences Beijing100190 China Purple Mountain Laboratories Pervasive Communication Research Center Nanjing210000 China Beijing University of Posts and Telecommunications Beijing100876 China

Indoor positioning is a thriving research area, which is slowly gaining market momentum. Its applications are mostly customized, ad hoc installations;ubiquitous applications analogous to Global Navigation Satellite System for outdoors are not available because of the lack of generic platforms, widely accepted standards and interoperability protocols. In this context, the indoor positioning and indoor navigation (IPIN) competition is the only long-term, technically sound initiative to monitor the state of the art of real systems by measuring their performance in a realistic environment. Most competing systems are pedestrian-oriented and based on the use of smartphones, but several competing tracks were set up, enabling comparison of an array of technologies. The two IPIN competitions described here include only off-site tracks. In contrast with on-site tracks where competitors bring their systems on-site - which were impossible to organize during 2021 and 2022 - in off-site tracks competitors download prerecorded data from multiple sensors and process them using the EvaalAPI, a real-time, web-based emulation interface. As usual with IPIN competitions, tracks were compliant with the EvAAL framework, ensuring consistency of the measurement procedure and reliability of results. The main contribution of this work is to show a compilation of possible indoor positioning scenarios and different indoor positioning solutions to the same problem. © 2023 CCBY.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Network Intrusion Detection System for Supervisory Control and Data Acquisition System

Generative Adversarial Network-Based Network Intrusion Detec...

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Hong Nhung Nguyen Thi Lan-Phan Chai-Jong Song Department of AI and Software Engineering School of Computing Gachon University Seongnam-si Gyeonggi-do Republic of Korea Division of Information Technology Viet Nam - Korea Institute of Science and Technology Thach That Ha Noi Vietnam Information Media Research Center Korea Electronics Technology Institute Seoul Korea

ISBN: (数字)9798331530839

ISBN: (纸本)9798331530846

In the context of burgeoning cyber threats targeting Supervisory Control and Data Acquisition (SCADA) systems, this paper presents a pioneering Intrusion Detection System (IDS) grounded in Generative Adversarial Networks (GANs). The ubiquity of information technology in critical industrial processes necessitates heightened security measures, and the proposed model addresses this imperative through the fusion of GANs and IDS tailored for SCADA environments. The study delves into the evolutionary trajectory of Intrusion Detection Systems, tracing their progression from conventional signature-based methods to the adaptive capabilities afforded by artificial intelligence, particularly deep learning. Against this backdrop, the paper investigates the vulnerabilities of SCADA systems, elucidating the sophisticated attack vectors identified in recent studies. The distributed nature of SCADA systems, deployed across extensive industrial landscapes, accentuates the need for robust intrusion detection mechanisms. This research's core innovation lies in applying a GAN model to SCADA systems, leveraging the distributed network protocol version 3 (DNP3) for data access authorization. The model is trained on a dataset comprising 12 meticulously selected features from DNP3 packets, attuning it to the nuances of SCADA network traffic. Notably, the proposed GAN-based IDS demonstrates exceptional efficacy, achieving impressive accuracy. Beyond the empirical contributions, the paper envisions future directions for integrating explainable AI techniques and enhancing the interpretability of IDS models specific to SCADA environments. Moreover, collaboration between academia and industry is advocated to foster the development of comprehensive datasets that represent SCADA network traffic.

关键词： Deep learning Protocols Accuracy SCADA systems Network intrusion detection Telecommunication traffic Generative adversarial networks Vectors Trajectory Security

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Using EfficientNet and XceptionNet

Deepfake Detection Using EfficientNet and XceptionNet

引用

IEEE International Conference on Intelligent computing and Information Systems (ICICIS)

作者： Basma Yasser Jumana Hani Salma El-Gayar Omar Amgad Nourhan Ahmed Hala M. Ebied Habiba Amr Mohamed Salah Software Engineering Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Computer Science Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Scientific Computing Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

The increasing prevalence of manipulated media, particularly deepfake videos, poses significant challenges in distinguishing real from fake content. This paper addresses the issue of detecting deepfake videos using advanced CNN architectures such as EfficientNet-B4 and XceptionNet. The FF++ and Celeb-DF (v2) datasets are used to compare real and fake videos. The methodology involves preprocessing the Celeb- DF dataset by extracting frames and isolating faces, training the models, and evaluating their performance using log loss and Area Under the Curve (AUC) metrics. The study shows that both models are effective in accurately classifying real and fake videos and highlights the importance of continuously updating deepfake detection algorithms in response to evolving deepfake generation techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protocol for biomodel engineering of unilevel to multilevel biological models using colored Petri nets

引用

STAR Protocols 2023年第4期4卷 102651页

作者： Liu, Fei Heiner, Monika Gilbert, David School of Software Engineering South China University of Technology Guangdong Guangzhou 510006 China Department of Computing Science Brandenburg University of Technology Cottbus-Senftenberg Cottbus D03013 Germany Department of Computing Science Brunel University London London UB8 3PH United Kingdom

Biological systems inherently span multiple levels, which can pose challenges in spatial representation for modelers. We present a protocol that utilizes colored Petri nets to construct and analyze biological models of systems, encompassing both unilevel and multilevel scenarios. We detail a modeling workflow exploiting the PetriNuts platform comprising a set of tools linked together via common file formats. We describe steps for modeling preparation, component-level modeling and analysis, followed by system-level modeling and analysis, and model use. © 2023 The Author(s)

关键词： Bioinformatics Computer sciences Systems biology

来源：评论

学校读者我要写书评

暂无评论

TA-ASF: Attention-Sensitive Token Sampling and Fusing for Visual Transformer Models on the Edge

TA-ASF: Attention-Sensitive Token Sampling and Fusing for Vi...

引用

IEEE/ACM Symposium on Edge computing (SEC)

作者： Junquan Chen Xingzhou Zhang Wei Zhou Weisong Shi Engineering Research Center of Cyberspace Yunnan University Kunming China School of Software Yunnan University Kunming China Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer and Information Sciences University of Delaware Newark DE USA

ISBN: (数字)9798350378283

ISBN: (纸本)9798350378290

Vision Transformers ( $V$ iTs) have made significant progress in achieving performance comparable to traditional convolutional neural networks in computer vision tasks. However, high computational complexity restricts their application to resource-constrained edge devices. Previous methods for pruning redundant tokens have shown that it is possible to balance performance and computational cost by reducing the number of tokens. Unfortunately, simply removing redundant tokens often leads to the loss of crucial information. To address this issue, we propose a novel token compression scheme called TA-ASF. This scheme considers both the global role of low-importance tokens and the redundancy among similar tokens. TA-ASF employs novel approaches for token sampling and fusion, which are directly applicable to $V$ iTs without introducing additional trainable parameters. A comprehensive evaluation against several edge devices demonstrates our method effectively reduces model complexity while preserving Top-1 accuracy. Experimental results show that on the ImageNet dataset, the proposed method reduces FLOPs by 37% and increases throughput by 1.48 times on the DeiT-S model, with only a 0.1% decrease in accuracy. Specifically, on the DeiT-B model, the proposed method decreases FLOPs by 35% and increases throughput by 1.52 times while maintaining the same accuracy.

关键词： Performance evaluation Training Computer vision Visualization Accuracy Computational modeling Image edge detection Termination of employment Transformers Throughput

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：