检索结果-内蒙古大学图书馆

24th International Conference on control systems and computer science, CSCS 2023

作者： Petrica, Silvian-Marian Fagarasan, Ioana Arghira, Nicoleta Stamatescu, Iulia Neculoiu, Giorgian Flangea, Oana University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania Technical University of Civil Engineering of Bucharest Faculty of Hidrotechnics Romania

ISBN: (纸本)9798350313390

Air pollution is one of the major environmental issues discussed lately due to its influence on human health. Particular attention is paid to air quality monitoring today and most developed societies have implemented weather and air quality monitoring stations in various locations inside or outside cities to monitor and reduce the effects of poor air quality. Modern standards and sensors have started to be used in recent years to monitor air quality. Conventional air quality monitoring systems, on the other hand, are not able to provide real-time air quality data with acceptable spatial and temporal resolutions at a low cost, so the challenge is to achieve low-cost and energy-independent solutions. Using modern technologies, e.g. Internet of-things (IoT), an original approach is proposed for building an air quality monitoring system considering low cost equipment and efficient energy autonomous approach. Smart cities have successfully implemented air quality monitoring systems that combine both hardware and software. The results presented in the paper show the viability of the proposed solution, exposing the designed solution and different ways of presenting air quality monitoring. © 2023 IEEE.

关键词： Energy efficiency

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

Densifying the sparse cloud simsaas: The need of a synergy among agent-directed simulation, SimSaaS and HLA 5

Densifying the sparse cloud simsaas: The need of a synergy a...

引用

5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, SIMULTECH 2015

作者： Azevedo, Tiago Rossetti, Rosaldo J. F. Barbosa, Jorge G. Artificial Intelligence and Computer Science Lab. Department of Informatics Engineering Faculty of Engineering University of Porto Porto Portugal

ISBN: (纸本)9789897581205

Modelling & Simulation (M&S) is broadly used in real scenarios where making physical modifications could be highly expensive. With the so-called Simulation Software-as-a-Service (SimSaaS), researchers could take advantage of the huge amount of resource that cloud computing provides. Even so, studying and analysing a problem through simulation may need several simulation tools, hence raising interoperability issues. Having this in mind, IEEE developed a standard for interoperability among simulators named High Level Architecture (HLA). Moreover, the multi-agent system approach has become recognised as a convenient approach for modelling and simulating complex systems. Despite all the recent works and acceptance of these technologies, there is still a great lack of work regarding synergies among them. This paper shows by means of a literature review this lack of work or, in other words, the sparse Cloud SimSaaS. The literature review and the resulting taxonomy are the main contributions of this paper, as they provide a research agenda illustrating future research opportunities and trends.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Finite-Time Formation control for Unmanned Surface Vehicles with Output Constraints and Time-Varying Disturbance 5th

Event-Triggered Finite-Time Formation Control for Unmanned S...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Wang, Yuanhui Liu, Chong Zhao, Yize College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150000 China Department of Computer Science University of California Irvine92612 United States

ISBN: (纸本)9789811939976

This paper investigates the formation tracking control of unmanned surface vehicles (USVs) swarm based on prescribed performance control and the event-triggered mechanism. A prescribed performance controller is designed to keep the formation tracking errors in pre-set boundary. Considering the environmental disturbance, the finite-time sliding mode observer is constructed such that the disturbance can be accurately estimated in finite-time. Furthermore, the event-triggered scheme is introduced to reduce the occupancy of the communication network while encountering the effect of communication bandwidth restrictions on the performance of USVs formation control system. The finite-time prescribed performance controller and the event-triggered strategy has been combined, which guarantees that the actuator updated aperiodically only when the pre-designed event-triggered threshold is satisfied. Finally, the derived closed-loop system stability is proved by Lyapunov theory and the effectiveness of the proposed control scheme is demonstrated by the simulation results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Intrinsically patterned corrals in monolayer Ag_(5)Se_(2) and selective molecular co-adsorption

引用

Nano Research 2022年第7期15卷 6730-6735页

作者： Jianchen Lu Shiru Song Shuai Zhang Yang Song Yun Cao Zhenyu Wang Li Huang Hongliang Lu Yu-Yang Zhang Sokrates T.Pantelides Shixuan Du Xiao Lin Hong-Jun Gao Institute of Physics&University of Chinese Academy of Sciences Chinese Academy of SciencesBeijing 100190China Department of Physics and Astronomy and Department of Electrical Engineering and Computer Science Vanderbilt UniversityNashvilleTN 37235USA CAS Center for Excellence in Topological Quantum Computation Chinese Academy of SciencesBeijing 100190China Faculty of Materials Science and Engineering Kunming University of Science and TechnologyKunmingYunnan 650093China

Functionalized two-dimensional(2D)materials play an important role in both fundamental sciences and practical *** construction and precise control of patterns at the atomic-scale are necessary for selective and multiple *** we report the fabrication of monolayer pentasilver diselenide(Ag_(5)Se_(2)),a new type of intrinsically patterned 2D material,by direct selenization of a Ag(111)*** atomic arrangement is determined by a combination of scanning tunneling microscopy(STM),low-energy electron diffraction(LEED),and density-functional-theory(DFT)***-scale STM images exhibit a quasi-periodic pattern of stoichiometric triangular domains with a side length of~15 nm and apical *** boundaries between triangular domains are *** of different molecules on the patterned Ag_(5)Se_(2) exhibits selective adsorption *** molecules preferentially adsorb on the boundaries,while tetracyanoquinodimethane(TCNQ)molecules adsorb both on the boundaries and the triangular *** co-depositing pentacene and TCNQ molecules,we successfully construct molecular corrals with pentacene on the boundaries encircling TCNQ molecules on the triangular *** realization of epitaxial large-scale and high-quality,monolayer Ag_(5)Se_(2) extends the family of intrinsically patterned 2D materials and provides a paradigm for dual functionalization of 2D materials.

关键词： two-dimensional materials dual functionalization scanning tunneling microscope epitaxial growth Ag_(5)Se_(2)monolayer

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Epileptic Seizure Diagnosis: Utilizing GRU-CNN Architectures in EEG Signal Analysis 20

A Robust Framework for Epileptic Seizure Diagnosis: Utilizin...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Nikoupour, Maryam Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran Iranian Research Organization for Science and Technology Department of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350383942

Seizures that take place repeatedly and without provocation are referred to as epilepsy. Epilepsy can be diagnosed with electroencephalography (EEG). One of the most influential challenges of the past few years has been the use of deep learning algorithms to replace manual inspection of medical signals by specialists, such as epilepsy signal classification. This paper presents a multi-label classification approach for epileptic seizures using deep learning. UCI machine learning repository's epileptic seizure dataset has been used to classify epileptic seizure patients. 178 features are present in each of the 11500 samples in the dataset. Based on a variety of criteria, the proposed method may have a positive impact on epilepsy diagnosis, in most cases by approximately 6% compared with existing methods utilizing long short-term memory (LSTM) and autoencoder. It is possible thus to develop and apply gated recurrent unit-based methods with good potential for categorizing EEG signals for epilepsy diagnosis based on gated recurrent unit (GRU)-CNN based methods. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Service Recovery in NFV-Enabled Networks: Algorithm Design and Analysis

引用

IEEE Transactions on Cloud Computing 2024年第2期12卷 800-813页

作者： Nguyen, Dung H. P. Lin, Chih-Chieh Nguyen, Tu N. Chu, Shao-I Liu, Bing-Hong Pham Van Dong University Faculty of Engineering and Technology Quang Ngai570000 Viet Nam National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung80778 Taiwan Kennesaw State University Department of Computer Science MariettaGA30060 United States

Network function virtualization (NFV), a novel network architecture, promises to offer a lot of convenience in network design, deployment, and management. This paradigm, although flexible, suffers from many risks engendering interruption of services, such as node and link failures. Thus, resiliency is one of the requirements in NFV-enabled network design for recovering network services once occurring failures. Therefore, in addition to a primary chain of virtual network functions (VNFs) for a service, one typically allocates the corresponding backup VNFs to satisfy the resiliency requirement. Nevertheless, this approach consumes network resources that can be inherently employed to deploy more services. Moreover, one can hardly recover all interrupted services due to the limitation of network backup resources. In this context, the importance of the services is one of the factors employed to judge the recovery priority. In this article, we first assign each service a weight expressing its importance, then seek to retrieve interrupted services such that the total weight of the recovered services is maximum. Hence, we also call this issue the VNF restoration for recovering weighted services (VRRWS) problem. We next demonstrate the difficulty of the VRRWS problem is NP-hard and propose an effective technique, termed online recovery algorithm (ORA), to address the problem without necessitating the backup resources. Eventually, we conduct extensive simulations to evaluate the performance of the proposed algorithm as well as the factors affecting the recovery. The experiment shows that the available VNFs should be migrated to appropriate nodes during the recovery process to achieve better results. © 2013 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Designing effective web mining-based techniques for OOV translation

Designing effective web mining-based techniques for OOV tran...

引用

International Conference on Natural Language Processing and Knowledge engineering

作者： Yu, Haitao Ren, Fuji Huang, Degen Li, Lishuang Faculty of Engineering University of Tokushima Tokushima Japan Department of Computer Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9781424468966

Due to a limited coverage of the existing bilingual dictionary, it is often difficult to translate the Out-Of-Vocabulary terms (OOV) in many natural language processing tasks. In this paper, we propose a general cascade mining technique of three steps, it leverages OOV category to optimize the effectiveness of each step. OOV category based expansion policy is suggested to get more relevant mixed-language documents. OOV category based hybrid extraction approach is suggested to perform a robust extraction. A more flexible model combination based on OOV category is also suggested. Moreover, we conducted experiments to evaluate the effectiveness of each step and the overall performance of the mining technique. The experimental results show significantly performance improvement than the existing methods. ©2010 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Eye Blink Detection for Drowsy Drivers

Eye Blink Detection for Drowsy Drivers

引用

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing, COM-IT-CON 2022

作者： Sharma, Yanshee Bohra, Vanshika Khurana, Ananya Kmuar, Suresh Sindhu, Savita Sharma, Kamlesh Monica Manav Rachna International Institute of Research and Studies Faculty of Engineering and Technology Department of Computer Science and Engineering Faridabad India

ISBN: (数字)9781665496025

ISBN: (纸本)9781665496025

In recent times, road causalities caused by driving cars have increased gradually. These accidents result in severe injuries and deaths, evolving as a serious social and traffic issue. As a matter of fact, fatigue and drowsiness amongst drivers has been detected as the primary reason behind such causalities. Therefore, it is essential to design and implement a system that can fix this issue using known techniques. In this paper, a computer-based process that uses camera to detect the driver's facial expressions and his eye blink rate to detect if the driver is under fatigue or drowsy. Once a drowsy driver is detected, IoT is used to issue warning message for the driver, thereby alerting him using an inbuilt voice speaker. © 2022 IEEE.

关键词： Sleep Roads Machine learning Parallel processing Fatigue Cameras Video recording

来源：评论

学校读者我要写书评

暂无评论

Data Classification using Active Learning based Data Modification: An Application to Churn Prediction 3

Data Classification using Active Learning based Data Modific...

引用

3rd International Conference on Current Trends in computer, Electrical, Electronics and Communication, CTCEEC 2017

作者： Khalid, M.A.R. Farquad, M.A.H. Kamakshi Prasad, V. Department of Computer Science JNTUH College of Engineering Hyderabad Telangana State India Faculty of Computer and Information Systems Madinah Islamic University Madinah Saudi Arabia

ISBN: (纸本)9781538632420

Support Vector Machine (SVM) is on one of its kind of data mining algorithm, tends to always give away the global optimum solution to any given problem because of its convex optimization problem solving approach. SVM learns from the given training data and generates a linear hyperplane classifying the given instances. The training instances which are near this separating hyperplane are called support vectors, using which predictions are obtained. In other words, SVM considers the support vectors as important instances for prediction purposes and ignores other instances which are much away from hyperplane boundary. In this project the ability of SVM i.e. extraction of support vectors is explored further and active learning based synthetic data generation (nearest to the support vectors) is employed. Synthetic data generation near support vectors would provide the classification algorithm (Naïve Bayes algorithm in this project) with some extra and suitable instances to learn from which in-turn expected to result in improving the prediction accuracy of the classifier used. Results have shown that Naïve Bayes classifier yielded superior accuracy using the modified dataset when compared to the accuracy yielded using original data available. © 2017 IEEE.

关键词： Support vector machines

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：