检索结果-内蒙古大学图书馆

9th IEEE International Conference on Cyber Security and Cloud Computing and 8th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2022

作者： Liu, Zekun Yu, Jianyong Liu, Yuqi Zhu, Hangyu Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan China Guangdong Qilian Technology Co. Ltd Guangzhou China

ISBN: (数字)9781665480666

ISBN: (纸本)9781665480666

Various communication methods allow modern people to communicate with each other more frequently, resulting in a more diverse network structure in today's social network due to its own dynamics. Compared with the influence maximization under the static network, which has been carried out a lot of related research, the dynamic network's influence maximization has more practical significance. The dynamic network, which is closer to the evolution of real social network, becomes more challenging for its influence maximization problem due to the variability of its network structure. In this paper, the traditional thresholding model is improved to make it feasible to calculate the threshold at each node and make the model can be used in dynamic networks. By proposing related theorems, we propose a new node seed selection strategy, which can select new nodes that are beneficial to the propagation between nodes by calculating the node influence. Through comparative experiments with five different algorithms, we select two real datasets with large structural differences to generate directed and weighted dynamic networks. The experimental results show that the propagation range caused by our method during the process and at the end of the propagation is much larger than that of other comparison algorithms. © 2022 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Latest Innovations in Intelligent Network-on-Chip Architectures: A Systematic Review

Latest Innovations in Intelligent Network-on-Chip Architectu...

引用

International Workshop on Network on Chip Architectures, NoCArc

作者： Elena Kakoulli Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (数字)9798331506421

ISBN: (纸本)9798331506438

This review investigates the latest advancements in intelligent Network-on-Chip (NoC) architectures, focusing on innovations from 2022 to 2024. The integration of Artificial Intelligence (AI) and Machine Learning (ML) into NoC designs has driven significant improvements in performance, scalability, energy efficiency, and security. Key contributions include AI/ML-driven techniques to optimize routing, reduce latency, manage power consumption, and enhancing security against emerging threats. Despite these advancements, challenges such as computational overhead and integration complexities remain. This review consolidates these findings, addresses existing challenges, and proposes future research directions to further leverage AI and ML for developing robust and adaptable NoC architectures.

关键词： Technological innovation Scalability Power system management computer architecture Network-on-chip Predictive models Routing Energy efficiency Complexity theory Security

来源：评论

学校读者我要写书评

暂无评论

Particle Filter Localization Algorithm Based on LOS Possibility for Smart Vehicle Digital Key 8

Particle Filter Localization Algorithm Based on LOS Possibil...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Zhou, Zihan Hu, Weivi Tian, Yiran Luo, Lei Li, Yun Chen, Lirong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Guangdong Weichen Information Technology Co. Ltd Dongguan China Peng Cheng Laboratory Department of New Networks Shenzhen China

ISBN: (纸本)9798350331035

The new generation of digital key technology for smart vehicles imposes increasingly stringent demands on localization accuracy and security. The conventional trilateration method based on least squares is adversely affected by Non-Line-Of-Sight (NLOS), resulting in inadequate accuracy to meet the requirements. This paper presents a study on a UWB-based digital key localization algorithm for smart vehicles. We propose a localization method based on particle filtering called LOSP-PF, which leverages Line-Of-Sight (LOS) probability to enhance localization accuracy. LOSP-PF utilizes trilateration least squares error to characterize and assign LOS likelihood to Ultra-Wideband (UWB) anchors, incorporating this weighting into the particle weight assignment during posterior derivation in particle filtering. LOSP-PF eliminates the need for pre-calibration and does not rely on additional sensors. It solely relies on UWB ranging measurements for localization. Comparative analysis with the traditional PF localization algorithm demonstrates that LOSP-PF achieves accuracy improvements of 26.269%, 8.095%, and 7.928% for short, middle, and long distances, respectively. © 2023 IEEE.

关键词： LOSP-PF particle filtering UWB localization

来源：评论

学校读者我要写书评

暂无评论

Using a Hybrid Neural Network and a Regularized Extreme Learning Machine for Human Activity Recognition with Smartphone and Smartwatch

引用

Sensors 2023年第6期23卷 3354页

作者： Tan, Tan-Hsu Shih, Jyun-Yu Liu, Shing-Hong Alkhaleefah, Mohammad Chang, Yang-Lang Gochoo, Munkhjargal Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung413310 Taiwan Department of Computer Science and Software Engineering United Arab Emirates University Al-Ain15551 United Arab Emirates

Mobile health (mHealth) utilizes mobile devices, mobile communication techniques, and the Internet of Things (IoT) to improve not only traditional telemedicine and monitoring and alerting systems, but also fitness and medical information awareness in daily life. In the last decade, human activity recognition (HAR) has been extensively studied because of the strong correlation between people’s activities and their physical and mental health. HAR can also be used to care for elderly people in their daily lives. This study proposes an HAR system for classifying 18 types of physical activity using data from sensors embedded in smartphones and smartwatches. The recognition process consists of two parts: feature extraction and HAR. To extract features, a hybrid structure consisting of a convolutional neural network (CNN) and a bidirectional gated recurrent unit GRU (BiGRU) was used. For activity recognition, a single-hidden-layer feedforward neural network (SLFN) with a regularized extreme machine learning (RELM) algorithm was used. The experimental results show an average precision of 98.3%, recall of 98.4%, an F1-score of 98.4%, and accuracy of 98.3%, which results are superior to those of existing schemes. © 2023 by the authors.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Cacomp: A Cloud-assisted Collaborative Deep Learning Compiler Framework for DNN Tasks on Edge

引用

IEEE Transactions on computers 2025年

作者： Lin, Weiwei Lin, Jinhui Zhang, Haotong Wu, Wentai Wu, Weizheng Li, Zhetao Li, Keqin South China University of Technology School of Computer Science and Engineering Guangzhou510641 China Pengcheng Laboratory Shenzhen518066 China South China University of Technology School of Software Engineering Guangzhou510641 China Jinan University Department of Computer Science College of Information Science and Technology Guangzhou510632 China Jinan University College of Information Science and Technology Guangzhou510632 China State University of New York Department of Computer Science New PaltzNY12561 United States

With the development of edge computing, DNN services have been widely deployed on edge devices. The deployment efficiency of deep learning models relies on the optimization of inference and scheduling policy. However, traditional optimization methods on edge devices still suffer from prohibitively long tuning time due to devices’ low computational power. Meanwhile, the widely used scheduling algorithm, the dominant resource fairness algorithm(DRF algorithm), struggles to maximize the efficiency of model execution on edge devices and inevitably increases average waiting time as it is not applicable in the real-time distributed computing environment. In this paper, we propose Cacomp, a distributed cloud-assisted deep learning compiler framework that features accelerating the optimization on edge devices with assistance from the cloud and a novel inference task scheduling algorithm. Our framework utilizes the tuning records from the cloud devices and proposes a two-step distillation strategy to obtain the best tuning record set for the edge device. For the scheduling process, we propose an RD-DRF algorithm to allocate inference tasks to edge devices based on dominant resource matching in real time. Extensive results show that our framework can achieve up to 2.19× improvement in the optimization time compared with other methods on edge devices. Our proposed scheduling algorithm significantly shortens the average waiting time of inference tasks by 30% and improves resource utilization by 20% on edge devices. © 1968-2012 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Improved Residual U-Net for COVID-19 Lung Infection Multi-Class Segmentation in CT Image

Improved Residual U-Net for COVID-19 Lung Infection Multi-Cl...

引用

2022 International Conference of Advanced Technology in Electronic and Electrical engineering, ICATEEE 2022

作者： Khouloud, Sahib Ahlem, Melouah Fadel, Toure Amel, Slim LRI Badji-Mokhtar Annaba University Dept. Computer Science Annaba23000 Algeria Trois-Rivieres Laboratory of Software Engineering Dept. du Quebec Quebec Canada

ISBN: (纸本)9798350346749

COVID-19, the new coronavirus, is a threat to global public health. Today, there is an urgent need for automatic COVID-19 infection detection tools. This work proposes an automatic COVID-19 infection detection system based on CT image segmentation. A deep learning network developed from an improved Residual U-net architecture extracts infected areas from a CT lung image. We tested the system on COVID-19 public CT images. An evaluation using the F1 score, sensitivity, specificity and accuracy proved the effectiveness of the proposed network. Besides, experimental results showed that the proposed network performed well in extracting infection regions so, it can assist experts in COVID-19 infection detection. © 2022 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Exploring the Integration of Educational Robotics and the Internet of Things in Learning Environments

Exploring the Integration of Educational Robotics and the In...

引用

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： Elena Kakoulli Salomi Evripidou Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

This study explores the integration of Educational Robotics (ER) and the Internet of Things (IoT) in learning environments, highlighting their collective impact on educational practices. It assesses ER and IoT’s application, challenges, and opportunities, offering insights into their role in enhancing pedagogy and learning outcomes. Specifically, our exploration uncovers the transformative potential of ER and IoT in fostering critical thinking, problem-solving skills, and digital literacy among students and reveals the pivotal role these technologies play in preparing learners for the demands of the digital age and Industry 4.0, while also highlighting the need for strategic implementation and teacher support. Our findings elucidate the potential of ER and IoT to innovate teaching strategies and curriculum design, serving as a guide for educational stakeholders, such as curriculum developers, educators, researchers, and policymakers, in leveraging these technologies to revolutionize instructional practices.

关键词： Training Information age Fourth Industrial Revolution Internet of Things Stakeholders Problem-solving Distributed computing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Prediction Model for T20 and Test Match Outcomes Using Machine Learning

A Comprehensive Prediction Model for T20 and Test Match Outc...

引用

engineering & Computing Technologies (ICECT), International Conference on

作者： Zoha Ahsan Shahwaiz Ghumman Attique Ur Rehman Sabeen Javaid Tahir Muhammad Ali Azka Mir Department of Software Engineering University of Sialkot Sialkot Pakistan Department of Computer Science Gulf University for Sciences and Technology Mubarak Al-Abdullah Kuwait

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

Cricket is a popular sport worldwide, played with a bat and balls. This paper used classification and regression to predict the T20 and Test matches results and scores because cricket fans and analysts always want to predict which team will win the match and how much score a team will make. We have used a supervised machine learning technique to predict the score and result for T20 and Test matches. Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model. For the prediction of winning and losing, we have used Naïve Bayes, Gradient Boosted Trees, Logistic Regression, Deep learning, Decision Tree, Random Forest, and Generalized Linear Model. For Score Prediction, we have used Decision Trees, Random Forests, Gradient Boosted Trees, Generalized Linear Models, and Deep Learning. We've shown the most accurate model after evaluating the accuracy percentages of the several classifiers listed above. Our introduced model has gained an accuracy rate of 96.15% using the Gradient Boosted Trees classifier for Match Score Prediction and 71.72% accuracy by using the Generalized Linear Model for match result prediction. The Rapid Miner tool has been used to perform machine learning techniques to train models. This paper discusses the effectiveness and use of machine learning methods to develop highly accurate models for Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model.

关键词： Training Deep learning Logistic regression Fans Accuracy Computational modeling Predictive models

来源：评论

学校读者我要写书评

暂无评论

EdgeMob: A Context-Aware Dynamic Service Migration for Wearable IoT in Healthcare

EdgeMob: A Context-Aware Dynamic Service Migration for Weara...

引用

Computing, Internet of Things and Microwave Systems (ICCIMS), International Conference on

作者： Imran Raza Syed Asad Hussain Sana Latif Department of Computer Science COMSATS University Islamabad Lahore Lahore Pakistan Department of Software Engineering University of Central Punjab (UCP) Lahore Pakistan

ISBN: (数字)9798350351736

ISBN: (纸本)9798350351743

Edge Computing (EC) is a distributed network architecture offering computation and storage resources at the network edge, addressing cloud computing limitations by optimizing latency and enhancing data safety and privacy for real-time services. It also supports intelligent solutions for IoT-based smart healthcare systems through Deep Learning (DL). DL aids in resource allocation optimization and disease prediction. However, the surge in wearable device usage introduces challenges in user mobility and migration, leading to increased latency and service inconsistencies. To tackle this, we propose EdgeMob, an intelligent and context-aware scheme deployed as a federation of edge servers. EdgeMob utilizes Q-learning-based reinforcement learning for personalized service migration decisions based on user mobility and Quality of Service (QoS). We evaluate our system against existing solutions, considering parameters such as user-perceived latency, migration cost, and network bandwidth utilization.

关键词： Quality of service Medical services Reinforcement learning Real-time systems Safety Internet of Things Servers Resource management Wearable devices Surges

来源：评论

学校读者我要写书评

暂无评论

Integrating virtual reality technology into architecture education: the case of architectural history courses

引用

Open House International 2021年第4期46卷 498-509页

作者： Ibrahim, Anwar Al-Rababah, Amneh Ibrahim Bani Baker, Qanita Department of Architecture Jordan University of Science and Technology Irbid Jordan Department of Computer Science and Software Engineering Jordan University of Science and Technology Irbid Jordan

Purpose: Virtual reality (VR) technology invaded various domains including architecture practice and education. Despite its high applications in architecture design education, VR has a high potential to be used in architectural history courses as well. This paper aims to examine the effect of using VR technology on the students’ learning abilities of history of architecture. Design/methodology/approach: The experimental approach was used. Two experiments were designed by creating virtual environments for two selected architectural examples from the Modern Architecture course. The participants who were students of Modern Architecture class had to complete two questionnaires, one for each example. The first one was based on Bloom’s taxonomy, and the other was prepared to test the participants’ analytical and critical skills. Besides, participants had to fill out satisfaction and ease-of-use survey on a five-step Likert scale. Findings: Participants in the VR condition achieved better grades in knowledge gain compared to those in the traditional conditions. Their analytical and critical thinking skills were improved in the VR conditions. Gender has a significant impact on analytical and critical thinking skills. Participants recorded a high level of satisfaction;however, male students were more satisfied than female students who reported concerns about the weight of the used tools and nausea symptoms. Research limitations/implications: This study informs architecture education and provides insights into the potentials of using advanced technology in architectural history education. Teaching the various history of architecture courses will be improved, shifted toward a more student-centered curriculum, and may acquire more excitement and conscious curiosity. Originality/value: Using VR in architectural education is rigorous in architectural design courses and students’ design projects’ presentations. This research expands architectural education research by examining ot

关键词： Architectural education Bloom’s taxonomy Built environment tectonics and technologies History of architecture VR technology

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：