检索结果-内蒙古大学图书馆

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Daniel, E. Akilan, L.H. Infant, P. Alwin Jainish, G.R. Panimalar Engineering College Department of Computer Science & Engineering Chennai City Campus Chennai India Loyola Icam College of Engineering and Technology Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350376425

The alarming rise in motorcycle accidents worldwide necessitates the development of effective safety measures. This research introduces a novel helmet identification system utilizing Single Shot Detection (SSD) algorithm and Convolutional Neural Network (CNN) technology. The proposed system combines feature extraction and object identification techniques to accurately determine whether riders are wearing helmets in real-time. By integrating helmet detection with ignition control, this system actively prevents motorcycles from starting without a helmet, ensuring enhanced rider safety. Experimental results demonstrate the effectiveness of the CNN-SSD based helmet detection system, achieving minimal false positives and high detection accuracy, making it suitable for real-world deployment. This innovative approach contributes to road safety and reduces the risk of injuries associated with motorcycle accidents. © 2024 IEEE.

关键词： Motorcycles

来源：评论

学校读者我要写书评

暂无评论

Sensors Based Assistive technology for Corona Healthcare Insights 1

Sensors Based Assistive Technology for Corona Healthcare Ins...

引用

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Rajendra Prasad, K. Narasimhulu, K. N Santhosh Kumar, C.H. Hyderabad India Rajeev Gandhi College of Engineering and Technology Department of Computer Science and Engineering Nandyal India Anurag Engineering College Department of Computer Science and Engineering Telengana Kodad India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365405

Nano-assistive technology is essential to scientific study in the medical sciences. It offers more substantial options for examining macro-ailments, such as the coronavirus illness (COVID-19). Nanotechnology can sense intrusive sensing of the macro-molecule size of nano-sensors and analyze antibody systems for COVID-19 patients during a pandemic. Traditional big data clustering methods, such as single-pass k-means (spkm), and mini-batch k-means (mmbk), can classify gene data based on molecule similarity structures. However, they suffered with the initial assessment of gene cluster tendency. This paper presents the novel similarity method, Multiview modeling cosine similarities (MMCS), for a better assessment of cluster tendency, combined with the visual technique of visual assessment of cluster tendency (VAT) for the clustering results. The invasive sensors collect data on the internal gene structure of the patient, and the proposed MMCS-VAT makes it easy to make visual classifications. There was a big change in the area under the curve (AUC) of the performance parameters in the experiment with COVID datasets. MMCS-VAT made the AUC better than mbkm by 22-23% and better than spkm and mbkm by 10-16% for all five performance parameters. It also proved that MMCS-VAT is 8 to 10 times and 10 to 15 times faster than spkm, and mbkm methods respectively for the big COVID 19 datasets. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Long-term solar radiation forecasting in India using EMD, EEMD, and advanced machine learning algorithms

引用

Environmental Monitoring and Assessment 2025年第3期197卷 1-36页

作者： RajasundrapandiyanLeebanon, T. Murugan, N. S. Sakthivel Kumaresan, K. Jeyabose, Andrew Department of Electrical and Electronics Engineering TamilNadu College of Engineering Tamil Nadu Coimbatore India Department of Mechanical Engineering Park College of Engineering & Technology TamilNadu Coimbatore India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Solar radiation plays a critical role in the carbon sequestration processes of terrestrial ecosystems, making it a key factor in environmental sustainability among various renewable energy sources. This study integrates two advanced signal processing techniques—empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD)—with machine learning (ML) algorithms, including multilayer perceptron (MLP), random forest regression (RFR), support vector regression (SVR), and ridge regression, to forecast long-term solar radiation. Meteorological data spanning 13 years (2000–2012) from seven locations across India (Bhubaneswar, Chennai, Delhi, Hyderabad, Nagpur, Patna, and Trivandrum) were used for training and testing. The optimal model was identified based on performance metrics, including the highest linear correlation coefficient (R), and the lowest mean absolute error (MAE) and root mean square error (RMSE). The results indicate that EEMD integrated with ML algorithms consistently outperformed EMD-based approaches. Among the ML models evaluated, EEMD integrated with MLP achieved the best performance across all locations, with RMSE = 0.332, MAE = 0.26, and R2 = 0.99. Furthermore, a comparative analysis with previous studies demonstrated that the proposed approach provides superior accuracy, underscoring its efficacy in solar radiation forecasting. © The Author(s) 2025.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Distributed field mapping for mobile sensor teams using a derivative‐free optimisation algorithm

引用

IET Cyber-Systems and Robotics 2024年第2期6卷 20-34页

作者： Tony X.Lin Jia Guo Said Al-Abri Fumin Zhang School of Electrical&Computer Engineering Georgia Institute of TechnologyAtlantaGeorgiaUSA College of Engineering Sultan Qaboos UniversityMuscatOman Department of Electronic&Computer Engineering Hong Kong University of Science and TechnologyHong KongChina

The authors propose a distributed field mapping algorithm that drives a team of robots to explore and learn an unknown scalar field using a Gaussian Process(GP).The authors’strategy arises by balancing exploration objectives between areas of high error and high *** computing high error regions is impossible since the scalar field is unknown,a bio-inspired approach known as Speeding-Up and Slowing-Down is leveraged to track the gradient of the GP *** approach achieves global field-learning convergence and is shown to be resistant to poor hyperparameter tuning of the *** approach is validated in simulations and experiments using 2D wheeled robots and 2D flying mini-ature autonomous blimps.

关键词： environment sensing multi-robot systems

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics in loT Challenges and Opportunities 9

Big Data Analytics in loT Challenges and Opportunities

引用

9th International Conference on science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Kirubakaran, S. Vidhya, R. Prlya, V. Kalai ShyamPrakash, D. Dhotre, Sunita Balaji, N. Alangudi Cmr College of Engineering And Technology Department of Computer Science And Engineering Telangana Hyderabad501401 India Sri Krishna College of Technology Department of Computer Science And Engineering Tamil Nadu Coimbatore641042 India Rmk College of Engineering And Technology Department of Computer Science And Engineering Puduvoyal601206 India Sri Eshwar College of Engineering Deportmem of Computer Science And Business Systems Tamil Nadu Coimbatore641202 India College of Engineering Department of Computer Engineering Maharashtra Pune411043 India KoneruLakshmaiah Education Foundation Department of Computer Science And Engineering Andhra Pradesh Vaddeswaram522302 India

ISBN: (纸本)9798350365092

The intricate interplay between Big Data analytics and the Internet of effects is explored in this paper. The focus of this exploration is the integration of Big Data analytics into Internet of effects surroundings, probing into the complex geography and examining both the advantages and disadvantages. In the current period, where Internet of effects(loT) bias induce unknown quantities of data, the investigates the challenges associated with the collection and analysis of massive datasets. issues are under consideration, including data security, sequestration, scalability, and real-time processing. Again, openings lie in gaining pivotal perceptivity, enhancing decision- making processes, and fostering invention. This exploration provides a comprehensive understanding of the commerce between Big Data analytics and the Internet of effects(IoT), offering a precious resource for companies, academic institutions, and government officers seeking to navigate and acclimatize to this fleetly expanding confluence of technologies. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Developed a Machine Learning and Deep Learning Model for 5G MIMO Data Based Beam Selection and Intelligent Network Analytics

引用

SN computer science 2025年第3期6卷 1-21页

作者： Ashok, P. Suganya, R. Lekha, P. Pandian, Poornima Subashini, M. Nithya, M. Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Tamilnadu India Department of Computer and Communication Engineering Sri Sai Ram Institute of Technology Tamilnadu India Department of Electronics and Communication Engineering Sri Sairam Engineering College Tamilnadu India Department of Computer Science and Engineering Sri Sairam Engineering College Tamilnadu India

Introduces an innovative application of 5G MIMO data in singular value decomposition (SVD) focusing on deep learning beam-selection and intelligent network analytics. This research explores the potential of leveraging 5G MIMO data to enhance network performance and efficiency through advanced ML techniques. Deep learning algorithms are employed for beam-selection, optimizing the transmission of data in 5G networks to improve throughput and reliability. Intelligent network analytics are applied to extract valuable insights from the vast amount of data generated by 5G MIMO systems, enabling proactive network management and optimization. By harnessing the capabilities of deep learning and intelligent analytics, this research aims to address key challenges in 5G network optimization and management. The integration of SVD techniques with 5G MIMO data offers a novel approach to enhancing network performance, enabling more efficient utilization of resources and improved quality of service for users. The insights gained from intelligent network analytics facilitate informed decision-making and proactive maintenance leading to greater reliability and resilience in 5G networks. This research contributes to the advancement of 5G technology by leveraging ML to unlock the full potential of MIMO data for optimizing network performance and enabling intelligent network management. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： 5G Beam-selection Deep learning Intelligent management MIMO Network analytics Network performance Optimization Proactive maintenance Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Learning Framework for Non-Intrusive Autism Spectrum Disorder Detection 3

Multimodal Deep Learning Framework for Non-Intrusive Autism ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kavitha, G. Rajganesh, N. Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Sri Venkateswara College of Engineering Department of Computer Science and Engineering Sriperumbudur Chennai India

ISBN: (纸本)9798331509675

The non-intrusive detection of Autism Spectrum Disorder (ASD) marks a significant advancement in early diagnosis and intervention. This approach allows users to upload videos to a web interface, where visual and auditory data are processed separately. Visual data is analyzed using a customized VGG19 Convolutional Neural Network (CNN) to identify facial expressions and movements indicative of autism, while auditory data is evaluated by a Recurrent Neural Network (RNN) to detect auditory cues like tone and rhythm. A voting mechanism across 10 frames determines the visual classification, labelling the subject autistic if most frames indicate autistic traits. Audio analysis provides an independent prediction. The subject is classified as autistic if either analysis indicates autistic features. By leveraging deep neural networks to process multimodal data, this method offers an accessible, early ASD detection tool for caregivers and professionals, promoting timely interventions and improved outcomes. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Online Learning: A Comparative Analysis of Machine Learning Models and Data Visualization Techniques for Predicting Learner Flexibility

Enhancing Online Learning: A Comparative Analysis of Machine...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Priya, P. Kanaga Suguna, R.K. Sujitha, S. Devi, G. Nandhini, D. Kalyan, G. Ramesh KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India SNS College of Technology Department of Computer Science and Engineering Coimbatore India SNS College of Engineering Department of Computer Science and Technology Coimbatore India

ISBN: (纸本)9798350319200

The fast growth of online learning has increased the demand for efficient tools and approaches to measure and improve student's capacity to adapt to online learning. This paper gives a thorough comparative comparison of Machine Learning (ML) models and data visualization techniques for predicting the flexibility of learners in the realm of online education. In this study, various data visualization techniques are investigated to learn more about how learners behave, engage with, and perform in online courses. Understanding patterns and trends through data visualization is essential for educators and institutions to make well-informed decisions to enhance learner's learning journeys. To find out how effective different visualization techniques are in revealing useful insights, IBM Cognos and Python are used. The suitability of several ML algorithms for predicting learners' flexibility levels is also examined in this study. The predictive accuracy or mean accuracy score of several ML models, including XGBoost, Random Forests, CatBoost, Logistic Regression, and K Nearest Neighbour, is compared. The dataset used for this investigation contains a variety of learner-related variables, such as demographic data, past academic achievement, and interactions with online courses. For educators and educational institutions looking to use data-driven techniques to improve online learning experiences, the findings of this comparative study offer invaluable advice to them. This study contributes to the ongoing attempts to raise the caliber and efficacy of online education by identifying the most efficient data visualization strategies and ML models for forecasting learners' flexibility. The study's conclusions enable educators to proactively identify learners who are at risk of having difficulty with online learning, enabling prompt interventions and individualized support for academic success. © 2023 IEEE.

关键词： accuracy and flexibility IBM Cognos machine learning online learning visualization

来源：评论

学校读者我要写书评

暂无评论

A Quasi-Newton Neural Network Based Efficient Intrusion Detection System for Wireless Sensor Network

引用

computer Systems science & engineering 2023年第4期45卷 427-443页

作者： A.Gautami J.Shanthini S.Karthik Department of Electronics and Communication Engineering SNS College of TechnologyCoimbatoreTamilnaduIndia Department of Computer Science&Engineering Dr.N.G.P Institute of TechnologyCoimbatoreTamilnaduIndia Department of Computer Science&Engineering SNS College of TechnologyCoimbatoreTamilnaduIndia

In Wireless Sensor Networks(WSN),attacks mostly aim in limiting or eliminating the capability of the network to do its normal *** this misbehaviour is a demanding *** so far the prevailing research methods show poor ***3 centred efficient Intrusion Detection Systems(IDS)is proposed in WSN to ameliorate the *** proposed system encompasses Data Gathering(DG)in WSN as well as Intrusion Detection(ID)*** DG,the Sensor Nodes(SN)is formed as clusters in the WSN and the Distance-based Fruit Fly Fuzzy c-means(DFFF)algorithm chooses the Cluster Head(CH).Then,the data is amassed by the discovered ***,it is tested with the trained *** IDS encompasses‘3’steps:pre-processing,matrix reduction,and *** pre-processing,the data is organized in a clear ***,attributes are presented on the matrix format and the ELDA(entropybased linear discriminant analysis)lessens the matrix ***,the output as of the matrix reduction is inputted to the QN3 classifier,which classifies the denial-of-services(DoS),Remotes to Local(R2L),Users to Root(U2R),and probes into attacked or Normal *** an experimental estimation,the proposed algorithm’s performance is contrasted with the prevailing *** proposed work attains an enhanced outcome than the prevailing methods.

关键词： Distance fruit fly fuzzy c-means(DFFF) entropy-based linear discriminant analysis(ELDA) Quasi-Newton neural network(QN3) remote to local(R2L) denial of service(DoS) user to root(U2R)

来源：评论

学校读者我要写书评

暂无评论

SEEK Mobility Adaptive Protocol Destination Seeker Media Access Control Protocol for Mobile WSNs

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2023年第1期4卷 130-145页

作者： Shaker, Atheel Sabih Youssif, Omar F. Aljanabi, Mohammad Abbood, Zainab Ali Mahdi, Mahdi S. Computer Engineering Techniques Baghdad College of Economic SciencesUniversity Baghdad Iraq Computer Engineering Techniques Ibn Khaldun University College Baghdad Iraq Department of computer science Alsalam university college Baghdad Iraq Department of computer Aliraqia university college of education Baghdad Iraq Computer Technology Engineering dep Al-Esraa University College Baghdad Iraq Department of computer technology engineering Al-Esraa University college Baghdad Baghdad Iraq

The mobile wireless sensor network (WSN) is an emerging field as it widens the scope of applications where sensor networks can be applied. Generally, mobility in wireless communications degrades how well each pair of nodes communicate with one another. In WSN, the effect is higher because nodes have limited communication and computational capabilities. Those limitations create a challenging environment for the operation of sensor node communications. This paper proposes an energy-efficient media access control (MAC) protocol with mobility adaptive throughput based on a carrier-sense multiple access with collision avoidance MAC mechanism called the SEEK-mobility adaptive protocol (SEEK-MADP). SEEK-MADP uses a unique control packet operation to transfer data packets through as many nodes as possible in one duty cycle. The control packets, SYNC and RTS, are merged into one packet (SEEK). SEEK is then transferred to the downstream nodes to establish a connection between a stream of nodes in a duty cycle. This process minimizes the energy consumed by the handshaking process between the connected nodes. To increase throughput, the data period is adaptive to minimize/maximize the data packets according to the movement speed of the sender/receiver nodes. The proposed algorithm is assessed via extensive simulations in mobile scenarios using Network Simulator version 2. The final results show that the SEEK-MADP outperforms MAC protocols, sensor MAC (S-MAC), and SMAC with adaptive listening, which have shown good performance in mobile scenarios. The performance of the proposed algorithm is better than that of IEEE 802.15.4 standard MAC mechanism at mobile scenarios. © 2023 Authors. All rights reserved.

关键词： Medium access control

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：