检索结果-内蒙古大学图书馆

2024 IEEE Latin-American Conference on Communications, LATINCOM 2024

作者： Marcelli, Emiliano Nazareno Rojas Blanco, Gabriela Azucena Ayala Duarte, Alex Ruben Stockel Chen, Yi-Hsuan Chin, Tai-Lin Universidad Politécnica Taiwán Paraguay National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798331521110

The emergence of the Internet of Things (IoT) has revolutionized the landscape of wireless communications, with a rapid increase of devices at scales far exceeding previous deployments. Consequently, IEEE Task Group ah (TGah) has undertaken the standardization of a new protocol named IEEE 802.11ah tailored specifically for such large-scale networks. IEEE 802.11ah aims to address one of the primary challenges of IoT networks. Despite the potential of Restricted Access Window (RAW) functions to reduce contention and enhance energy efficiency, the standard does not specify how to manage the scheduling, particularly with respect to the optimal configuration of RAW grouping ***, in this paper, we argue that the performance of grouping strategies is closely tied to the heterogeneous traffic demands of devices. We propose a load-balancing grouping algorithm to improve channel utilization in each group. Our evaluations demonstrate that the proposed load-balancing grouping outperforms traditional greedy grouping, especially in networks connecting many sensors with heterogeneous traffic demands in the IoT context. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

The Smart Early Detection of Addison's Disease Using Time Series Analysis

The Smart Early Detection of Addison's Disease Using Time Se...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Saraswat, Nidhi Agarwal, Mayur Harron, Syed Sanskriti University Department of Computer Science Engineering Uttar Pradesh Mathura India College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

This paper proposes a novel early detection gadget for Addison's sickness (ad) using time series analysis. Specifically, it utilizes electrocardiogram (ECG) and electroencephalogram (EEG) signals to increase a technique for the prognosis of ad. The model leverages long brief-term reminiscence (LSTM) and convolutional neural community (CNN) for sign analysis. The signal is pre-processed to filter out and deny the assets, eliminate powerline interference, and reduce movement artifacts. Then, using feature extraction techniques, the features obtained are fed to the LSTM recurrent neural network model to expect the ad prognosis. The proposed method was evaluated towards a dataset of ad sufferers and a healthfully manipulated dataset composed of a substantial variety of time-collection ECG and EEG indicators. The model executed a promising standard accuracy of 97% at same time as using a low fake-fantastic fee of thirteen.5%. It suggests that the proposed approach can offer a dependable time-collection alert for sufferers with ads. Moreover, our version may be applied in clinical applications and clinical exercises. © 2024 IEEE.

关键词： accuracy Addison's extraction fantastic time-collection

来源：评论

学校读者我要写书评

暂无评论

A Web-Based computerized Adaptive Testing with Rasch Analysis for Identifying VAK Learning Styles 5

A Web-Based Computerized Adaptive Testing with Rasch Analysi...

引用

5th technology Innovation Management and engineering Science International Conference, TIMES-iCON 2024

作者： Soe, Nyan Chondamrongkul, Nacha Temdee, Punnarumol Computer and Communication Engineering for Capacity Building Research Center School of Information Technology Mae Fah Luang University Chiang Rai Thailand

ISBN: (纸本)9798350362602

Understanding learner variability in learning styles is critical for optimizing personalized learning benefits. Learning style, a concept within educational psychology, has been explored through various theoretical frameworks, including VAK (Visual, Auditory, and Kinesthetic) learning modalities. This study utilized a multidisciplinary approach to develop and test a web-based computerized Adaptive Testing (CAT) system, aiming to overcome the limitations of conventional questionnaire-based assessments, such as potential disinterest and unreliable outcomes, in determining VAK learning styles. The study approach involved the recruitment of computer science students from Mae Fah Luang University. It also included developing a web-based CAT system using Django. Furthermore, an item bank based on Revised Bloom's Taxonomy was created. Additionally, the validity of the instruments used was evaluated using the Rasch model. We conducted an analysis of User Experience Questionnaire (UEQ) data to evaluate the overall user experience of both the conventional and CAT tests, and the statistics indicate that the web-based CAT offers a more user-friendly experience. The study also utilized the concordance rate to gauge the similarity of data responses among the conventional, CAT, and self-assessment tests concerning VAK learning styles. The findings indicate that the proposed method exhibits an 87% similarity with self-assessment and shows significant potential. ©2024 IEEE.

关键词： computerized adaptive testing (CAT) personalized learning Rasch analysis VAK learning styles

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Remote-Controlled Raft for Enhanced Water Quality Assessment 20

IoT-Enabled Remote-Controlled Raft for Enhanced Water Qualit...

引用

20th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2024

作者： Surasak, Thattapon Kitchat, Kotcharat Jiteurtragool, Nattagit King Mongkut's University Of Technology North Bangkok Faculty Of Applied Science Dept. Of Computer And Information Science Bangkok Thailand National Central University Dept. Of Computer Science And Information Engineering Taoyuan Taiwan

ISBN: (纸本)9798350382310

Water is vital for all life, serving as the foundation for plants and aquatic creatures and promoting abundance among all living beings. This study introduces an innovative approach by combining the Internet of Things (IoT) with advanced sensing techniques to assess water quality. The IoT-powered water quality testing raft has been developed to significantly enhance the monitoring capabilities. Equipped with sensors measuring key parameters such as turbidity, pH, and temperature, the raft provides a comprehensive understanding of water quality. Its GPS module enables real-time tracking and maintains location history, ensuring precise sampling. The collected data undergoes robust processing by a Raspberry Pi, ensuring integrity before being showcased on the Thingsboard. The system's uniqueness lies in its capacity to promptly issue alerts via LINE Notify upon detecting water quality abnormalities, ensuring timely intervention. This IoT-powered raft represents a paradigm shift in water quality assessment, characterised by its precision, remote capabilities, and user-focused approach. Practical applications have been demonstrated through real-world testing in a private lake in Cha-choengsao province, Thailand. The seamless integration of IoT into environmental monitoring marks a significant advancement in ensuring water quality and ecosystem health. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Clustering Using Genetic Algorithm: A Collaborative Performance Analysis 10

Clustering Using Genetic Algorithm: A Collaborative Performa...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Singh, Varsha Singh, Vijai Tiwary, UMa Shanker Indian Institute of Information Technology Allahabad Information Technology Department U.P. Prayagraj India Inderprastha Engineering College Computer Science and Engineering Department U.P. Ghaziabad India

ISBN: (纸本)9789380544472

Clustering is an essential unsupervised classification technique. When data is unlabeled, K-means, an unsupervised learning technique, is used because of its simplicity. This technique has the problem of getting plunges at values that are not optimal. A genetic algorithm (GA) removes the shortcoming of the K-Mean Algorithm. Genetic algorithms are optimization techniques with a randomized search that follow a natural genetic's nature, with implicit parallelism in a large amount. GA digs into large, multimodal, complex landscapes to provide optimal solutions. The proposed work uses GA with k-means to integrate both advantages. Results show that the proposed algorithm performs significantly superior to the widely used technique, that is K-means algorithm. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Travel Time Prediction Based on Transformer 6

Travel Time Prediction Based on Transformer

引用

6th International Conference on Communications, information System and computer engineering, CISCE 2024

作者： Xiong, Zuyun Liu, Lijuan Wang, Yan Zhu, Shunzhi Chen, Manjin Xiamen University of Technology Computer and Information Engineering Xiamen China Longyan Tobacco Industry Co. Ltd. Longyan China

ISBN: (纸本)9798350353174

With the continuous growth in the number of automobiles, the pressure on road traffic is constantly increasing, and the public's demand for convenient transportation is also steadily rising. However, existing research on travel time prediction has deficiencies in handling both route and global information. To address this issue, the paper proposes a new method for travel time prediction called Travel Time Prediction based on Transformer (TTPT). TTPT utilizes the multi-head attention mechanism of the Transformer model to facilitate information interactions among road segments. Additionally, to capture the temporal information of routes, we introduce Long Short-Term Memory (LSTM) networks. Furthermore, we employ an improved wide and deep neural network to handle global information. Finally, we merge the outputs of these modules to comprehensively consider various information and jointly predict travel time. Through experiments on datasets from Chengdu and Shenzhen, the effectiveness of TTPT is confirmed, which also provides new insights for improving accuracy of travel time prediction. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models 41

RoboMP2: A Robotic Multimodal Perception-Planning Framework ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lv, Qi Li, Hao Deng, Xiang Shao, Rui Wang, Michael Yu Nie, Liqiang School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Engineering Great Bay University China School of Computing and Information Technology Great Bay University China

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with human-selected prompts for embodied agents. However, these methods exhibit limited generalization capabilities on unseen tasks or scenarios, and overlook the multimodal environment information which is critical for robots to make decisions. In this paper, we introduce a novel Robotic Multimodal Perception-Planning (RoboMP2) framework for robotic manipulation which consists of a Goal-Conditioned Multimodal Preceptor (GCMP) and a Retrieval-Augmented Multimodal Planner (RAMP). Specially, GCMP captures environment states by employing a tailored MLLMs for embodied agents with the abilities of semantic reasoning and localization. RAMP utilizes coarse-to-fine retrieval method to find the k most-relevant policies as in-context demonstrations to enhance the planner. Extensive experiments demonstrate the superiority of RoboMP2 on both VIMA benchmark and real-world tasks, with around 10% improvement over the baselines. Copyright 2024 by the author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Technologies for Increasing the Energy Efficiency of Electric Vehicles 5

Technologies for Increasing the Energy Efficiency of Electri...

引用

5th IEEE International Conference on Modern Electrical and Energy System, MEES 2023

作者： Beshta, Oleksandr Stepanovich Beshta, Oleksandr Oleksandrovich Beshta, Dmitry Tkachenko, Serhii Khalaimov, Taras Skliar, Dmytro Dnipro University of Technology Department of Electric Drive Dnipro Ukraine Dnipro University of Technology Department of Information Technology and Computer Engineering Dnipro Ukraine

ISBN: (纸本)9798350359787

the purpose of the work is to determine the factors that affect the consumption of electrical energy for the mechanical operation of electric vehicles during movement. Highlighting the key factors that must be paid attention to when performing mathematical modeling, taking into account the features of electric transport, as well as a complete picture of the forces acting on it. Search for key tools and means to determine the most optimal route of movement from several proposed options. As a result of the work, the most optimal and modern standardized motion tachogram for energy consumption studies was determined. Tools for obtaining data on alternative routes from point A to point B and terrain topology are defined. The criteria for determining the optimal route sampling frequency are described. The degree of influence of the driver's driving style factor on energy consumption is determined. A research model is proposed, which serves to accumulate data from the internal sensors of the electric vehicle, while driving, using the CAN bus. The existing tools used for processing the accumulated array of data based on artificial intelligence and machine learning are described. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

EsECC_SDN:Attack Detection and Classification Model for MANET

引用

computers, Materials & Continua 2023年第3期74卷 6665-6688页

作者： Veera Ankalu Vuyyuru Youseef Alotaibi Neenavath Veeraiah Saleh Alghamdi Korimilli Sirisha Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaram522502A.PIndia Department of Computer Science College of Computers and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Electronics and Communications DVR&DHS MIC Engineering CollegeKanchikacharla521180A.PIndia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Electronics and Communications BVC Institute of Technology&ScienceAmalapuram533221A.PIndia

Mobile Ad Hoc Networks(MANET)is the framework for social networking with a realistic *** theMANETenvironment,based on the query,information is transmitted between the sender and *** the MANET network,the nodes within the communication range are involved in data *** the nodes that lie outside of the communication range are involved in the transmission of relay ***,due to the openness and frequent mobility of nodes,they are subjected to the vast range of security threats ***,it is necessary to develop an appropriate security mechanism for the dataMANET environment for data *** paper proposed a security framework for the MANET network signature escrow *** proposed framework uses the centralised Software Defined Network(SDN)with an ECC cryptographic *** developed security framework is stated as Escrow Elliptical Curve Cryptography SDN(EsECC_SDN)for attack detection and *** developed EsECC-SDN was adopted in two stages for attack classification and detection:(1)to perform secure data transmission between nodes SDN performs encryption and decryption of the data;and(2)to detect and classifies the attack in theMANET hyper alert based HiddenMarkovModel Transductive Deep ***,the EsECC_SDN is involved in the assignment of labels in the transmitted data in the database(DB).The escrow handles these processes,and attacks are evaluated using the hyper *** labels are assigned based on the k-medoids attack clustering through label assignment through a transductive deep learning *** proposed model uses the CICIDS dataset for attack detection and *** developed framework EsECC_SDN’s performance is compared to that of other classifiers such as AdaBoost,Regression,and Decision *** performance of the proposed EsECC_SDN exhibits∼3%improved performance compared with conventional techniques.

关键词： MANET security classifier cryptography attack escrow ECC

来源：评论

学校读者我要写书评

暂无评论

Bookbuddy: A Mood Based Book Recommendation System 7

Bookbuddy: A Mood Based Book Recommendation System

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Negandhi, Tisha Dhumale, Purval Vachhani, Mishika Gawande, Kiran Sardar Patel Institute of Technology Information Technology Department Mumbai India Sardar Patel Institute of Technology Computer Engineering Department Mumbai India

ISBN: (纸本)9798350304268

Nowadays, with the abundance of books available, readers often struggle to find books that align with their personal interests and moods. This paper proposes a personalized reading system that leverages machine learning techniques to provide book recommendations based on users' individual preferences and emotional states. The system integrates popularity-based, collaborative, and mood-based filtering approaches to generate highly personalized recommendations that cater to users' unique reading interests and mood. To facilitate user engagement and interaction, the system incorporates a database of books, reviews, and ratings, and allows users to access E-Books for free and purchase hard copies if desired. The paper outlines the system's design and implementation, highlighting its potential to improve users' reading experience and encourage exploration of new books and authors. The proposed system represents a significant contribution to the field of personalized recommendation systems and demonstrates the effectiveness of machine learning techniques in generating tailored recommendations. © 2023 IEEE.

关键词： Book database Book recommendation Collaborative filtering E-Books Emotional state Machine learning Mood-based filtering Popularity-based filtering User preferences

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：