检索结果-内蒙古大学图书馆

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Priyadharshini, S. Revathi, K. Sowndharya, S. Saranya, S. Prathiksha, R. Thayalini, K. SNS College of Engineering Department of Artificial Intelligence and Data Science Tamil Nadu CoimbatoreIndia India SNS College of Engineering Department of Information Technology Tamil Nadu Coimbatore India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385793

Bus location tracking systems are sophisticated technological systems that have revolutionized public transportation. These systems use advanced technologies, such as Global Positioning System (GPS) and wireless communication, to monitor and manage bus fleets in real-time. GPS receivers installed on buses provide precise location data, while communication networks facilitate data transmission to a central server. This data is then processed, analyzed, and made accessible through various platforms, including mobile applications and web interfaces. These systems have found wide-ranging applications in both developed and developing urban environments. Transit agencies utilize these systems to optimize routes, manage schedules, and proactively respond to incidents and disruptions. Bus location tracking systems have become a powerful toolset for transit agencies to refine bus routes, optimize schedules, and elevate the overall operational efficiency of public transit networks. The core components of bus location tracking systems include GPS devices installed on buses, a central server or cloud-based platform for data processing, and user interfaces accessible through mobile apps, websites, and display screens at bus stations. These user interfaces provide passengers with a user-friendly experience to track buses, estimate arrival times, and plan their journeys seamlessly. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Research on Tensor Multi-Clustering Distributed Incremental Updating Method for Big data

引用

Computers, Materials & Continua 2024年第10期81卷 1409-1432页

作者： Hongjun Zhang Zeyu Zhang Yilong Ruan Hao Ye Peng Li Desheng Shi School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing210023China Ministry of Science and Technology Innovation China Communications Services Corporation LimitedBeijing100071China School of Artificial Intelligence The University of ManchesterManchesterM139PLUK Ministry of Technology Innovation China Telecom Artificial Intelligence Technology(Beijing)Corporation LimitedBeijing100032China Ministry of Science and Technology Innovation Zhongbo Information Technology Research Institute Corporation LimitedNanjing210012China Jiangsu Postal Big Data Technology and Application Engineering Research Center Nanjing University of Posts and TelecommunicationsNanjing210003China

The scale and complexity of big data are growing continuously,posing severe challenges to traditional data processing methods,especially in the field of clustering *** address this issue,this paper introduces a new method named Big data Tensor Multi-Cluster Distributed Incremental Update(BDTMCDIncreUpdate),which combines distributed computing,storage technology,and incremental update techniques to provide an efficient and effective means for clustering ***,the original dataset is divided into multiple subblocks,and distributed computing resources are utilized to process the sub-blocks in parallel,enhancing ***,initial clustering is performed on each sub-block using tensor-based multi-clustering techniques to obtain preliminary *** new data arrives,incremental update technology is employed to update the core tensor and factor matrix,ensuring that the clustering model can adapt to changes in ***,by combining the updated core tensor and factor matrix with historical computational results,refined clustering results are obtained,achieving real-time adaptation to dynamic *** experimental simulation on the Aminer dataset,the BDTMCDIncreUpdate method has demonstrated outstanding performance in terms of accuracy(ACC)and normalized mutual information(NMI)metrics,achieving an accuracy rate of 90%and an NMI score of 0.85,which outperforms existing methods such as TClusInitUpdate and TKLClusUpdate in most ***,the BDTMCDIncreUpdate method offers an innovative solution to the field of big data analysis,integrating distributed computing,incremental updates,and tensor-based multi-clustering *** not only improves the efficiency and scalability in processing large-scale high-dimensional datasets but also has been validated for its effectiveness and accuracy through *** method shows great potential in real-world applications where dynamic data growth is common,and it is of significant imp

关键词： Tensor incremental update distributed clustering processing big data

来源：评论

学校读者我要写书评

暂无评论

AI-Empowered Intruder Alert System for Enhanced Security Surveillance 2

AI-Empowered Intruder Alert System for Enhanced Security Sur...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Shirin Saleem, P. Sushanand, Anagha Renji, Joshua Abraham Aman, M.K. James, Divya Lakshmi, K.S. Department of Information Technology Rajagiri School of Engineering & Technology Kerala Kakkanad India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kerala Kakkanad India

ISBN: (纸本)9798350340235

In today's contemporary society, ensuring security and safety is of paramount importance. For a nation to maintain a robust economy, it must prioritize the establishment of a secure environment. Surveillance cameras are widely employed to monitor and detect illicit actions. However, the current approach often relies on human intervention and monitoring, primarily after an intrusion has occurred. To address this issue, an automated system capable of identifying illegal activities without constant human supervision is necessary. This will help local security. Current local retailers of CCTV systems in Kerala lack AI-enabled intruder alert systems. The proposed project focuses on developing a software to integrate with the current software of the CCTV companies, which provides customizable intruder detection solutions. This will help the local security companies sustain themselves against international competitors by applying machine learning algorithms that take real-time video as input and detect the presence of intruders on the premises and alerts the user/admin. A machine learning model will be built using Convolutional Neural Networks and trained using a large dataset of real life CCTV footage as inputs. The model will be trained to recognize humans with or without weapons, animals, and unidentified moving objects separately and specify the same in the alert provided and also specify familiar faces or not . Users can specify a certain alert time during which the intruder detection system will be activated. This model will be cross-platform integratable, i.e, can be integrated with a mobile/desktop/web application as per the requirement of the client. Accuracy, Precision, Recall and F-measure has been computed for the proposed model. © 2023 IEEE.

关键词： Alert Detection Intruder Security Surveillance

来源：评论

学校读者我要写书评

暂无评论

CollabCodeX: An Effective Platform for Enhancing the Teaching-Learning Experience 3

CollabCodeX: An Effective Platform for Enhancing the Teachin...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Bhagwat, Suvarna Buchade, Amar Burhanpurwala, Adnan Singh, Himanshu Patil, Atul Kumar, Ankit Mit Art Design and Technology University Department of Electronics & Communication Engineering Pune India Viit Department of Artificial Intelligence and Data Science Kondhwa-BK Pune India

ISBN: (纸本)9798350354348

As coding becomes a crucial skillset in the curriculum of any software stream, there is a need for a dedicated tool in the classroom. Educators and students need access to a collaborative coding environment where both can code and interact in real time. This project aims to create a comprehensive collaborative coding platform tailored to meet the needs of teachers and students. We aim to overcome the limitations of existing collaborative coding solutions that lack dedicated features for education purposes. The platform will feature a suite of robust tools and functionalities designed to enhance the collaborative coding experience. Real-time collaboration capabilities will allow multiple users to work simultaneously on multiple programming languages, facilitating seamless coordination. Apart from this, the platform will also feature tools to allow for immediate review and grading of codes and tools for code analysis and interaction between student and teacher. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Comparison of Delay Estimation Techniques for Advanced Traffic Management 6th

Comparison of Delay Estimation Techniques for Advanced Tra...

引用

6th International Conference of Transportation Research Group of India, CTRG 2021

作者： Renju, P.B. Navali, Nitin Vanajakshi, Lelitha Department of Civil Engineering Indian Institute of Technology Madras Chennai India Department of Civil Engineering and Faculty Robert Bosch Centre for Data Science and Artificial Intelligence IIT Madras Chennai India

ISBN: (纸本)9789811942037

Estimating delays at different road segments and intersections is a primary step in any traffic management system. Delay along a path can be estimated using sensors such as Global Positioning System (GPS) sensors, Camera sensors, Wi-Fi sensors and On-Board Diagnostics (OBD) data of the vehicle. The former three techniques have been used for some time now, but the latter one has not been explored much, especially for estimating delay. The accuracy of methodologies using OBD, Wi-Fi and Camera was calculated using data from GPS as ground truth. Results obtained showed the performance of all these methods to be comparable. Choice of the right sensor may depend on various other factors such as cost, weather factors, accuracy, range, etc. Sometimes more than one sensor needs to be used for the desired results. This paper explores three techniques in more detail and summarizes the advantages and disadvantages of each one of them in various scenarios. © 2023, Transportation Research Group of India.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning Algorithms for Broad Learning System with Node and Input Addition

Incremental Learning Algorithms for Broad Learning System wi...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chen, Guang-Ze Jin, Junwei Sun, Hai-Wei Philip Chen, C.L. Faculty of Science and Technology University of Macau Department of Mathematics 99999 China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou510641 510335 China

ISBN: (纸本)9781665410205

The Broad Learning System (BLS) has been established as an effective flat network alternative to Deep Neural Networks (DNNs), delivering high efficiency while achieving competitive accuracy. Despite its advantages, the incremental learning methods of BLS face challenges in stability and computation when expanding with new nodes or input. We introduce two novel incremental learning algorithms based on factorization updates for BLS that optimize node and input additions to overcome these limitations. Our node addition algorithm utilizes QR decomposition and Cholesky factorization, using the update of the Cholesky factor instead of pseudo-inverse computations. For input addition, we propose an iterative Cholesky factor update algorithm. Our algorithms demonstrate not only faster computation compared to the existing BLS but also improved testing accuracy on the MNIST or Fashion-MNIST dataset. This work presents a significant step forward in the practical application and scalability of BLS in various data-dense environments. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Accuracy: Iris Flower Classification with Ensemble Models 1

Enhancing Accuracy: Iris Flower Classification with Ensemble...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Mani, Nishanthini Murugiah, Premkumar Veeraraghavan, Vethavarna Razia, Nuzha Ramesh, Shashank Kpr Institute of Engineering and Technology Department of Artificial Intelligence and Data Science TamilNadu Coimbatore India NextLabs Pte. Ltd. Software Engineer 2 Singapore

ISBN: (纸本)9798350372748

This research study investigates the classification of Iris flowers based on their morphological structures, addressing the challenges posed by variations in attributes like size, shape, and color. This study explores various classification techniques and their practical implementations by conducting a comparative analysis using the IRIS dataset. With 21 attributes and three species (Setosa, Versicolor, and Virginica), each comprising 400 samples, this research aims to leverage machine learning algorithms to achieve precise classification. Key steps include data preprocessing, model selection, and hyperparameter tuning, with evaluation metrics to enhance the model performance. Furthermore, this study also explores ensemble-based learning to improve the prediction accuracy. Comparative analysis reveals the accuracy of each model, demonstrating effective predictions with accuracy rates of 95.5% and 97%. In summary, this research study offers a comprehensive overview of Iris flower species classification and prediction using machine learning techniques, contributing to advancements in this domain. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

DialectMoE: An End-to-End Multi-dialect Speech Recognition Model with Mixture-of-Experts 23rd

DialectMoE: An End-to-End Multi-dialect Speech Recognition M...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhou, Jie Gao, Shengxiang Yu, Zhengtao Dong, Ling Wang, Wenjun Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9789819783663

Dialect speech recognition has always been one of the challenges in Automatic Speech Recognition (ASR) systems. While lots of ASR systems perform well in Mandarin, their performance significantly drops when handling dialect speech. This is mainly due to the obvious differences between dialects and Mandarin in pronunciation and the data scarcity of dialect speech. In this paper, we propose DialectMoE, a Chinese multi-dialects speech recognition model based on Mixture-of-Experts (MoE) in a low-resource conditions. Specifically, DialectMoE assigns input sequences to a set of experts using a dynamic routing algorithm, with each expert potentially trained for a specific dialect. Subsequently, the outputs of these experts are combined to derive the final output. Due to the similarities among dialects, distinct experts may offer assistance in recognizing other dialects as well. Experimental results on the datatang dialect public dataset show that, compared with the baseline model, DialectMoE reduces Character Error Rate (CER) for Sichuan, Yunnan, Hubei and Henan dialects by 23.6%, 32.6%, 39.2% and 35.09% respectively. The proposed DialectMoE model demonstrates outstanding performance in multi-dialects speech recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Dynamic routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-features Enhanced Multi-task Learning for Vietnamese Treebank Conversion 23rd

Multi-features Enhanced Multi-task Learning for Vietnamese ...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhang, Zhenguo Liu, Jianjian Li, Ying Yunnan Key Laboratory of Artificial Intelligence Kunming Kunming650500 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9789819783663

Pre-trained language representation-based dependency parsing models have achieved obvious improvements in rich-resource languages. However, these model performances depend on the quality and scale of training data significantly. Compared with Chinese and English, the scale of Vietnamese Dependency treebank is scarcity. Considering human annotation is labor-intensive and time-consuming, we propose a multi-features enhanced multi-task learning framework to convert all heterogeneous Vietnamese Treebanks to a unified one. On the one hand, we exploit Tree BiLSTM and pattern embedding to extract global and local dependency tree features from the source Treebank. On the other hand, we propose to integrate these features into a multi-task learning framework to use the source dependency parsing to assist the conversion processing. Experiments on the benchmark datasets show that our proposed model can effectively convert heterogeneous treebanks, thus further improving the Vietnamese dependency parsing accuracy by about 7.12 points in LAS. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

StrideSense: Enriching Lower Extremity and Kinetics in ACLR Patients via Sonic Insights

引用

IEEE Internet of Things Journal 2025年第12期12卷 19549-19560页

作者： Ahmed, Awais Yang, Panlong Butt, Abdul Haleem Rizwan, Muhammad Angin, Pelin Khan, Taha Nanjing University of Information Science and Technology University of Science and Technology of China China University of Bologna Department of Biomedical and Neuromotor Sciences Italy Air University Islamabad Department of Creative Technologies Faculty of Computing and Artificial Intelligence Pakistan University of Science and Technology of China School of Computer Science and Technology China Middle East Technical University Department of Computer Engineering Turkey Detectivio AB Sweden

Tearing the anterior cruciate ligament requires repair and rehabilitation to restore lower limb functionality fully. This study outlines a method for monitoring rehabilitation after knee surgery by analyzing footstep sounds and applying deep learning techniques. The process involves examining gait sounds during the initial four weeks of rehabilitation. The suggested system, StrideSense, recognizes walking sounds, enabling seamless and ongoing monitoring of patients' gait rehabilitation. The research proposes a novel method for event detection by analyzing walking patterns using dynamic time-warping and sequential footstep duration. It leverages physiological data like gait sound and energy descriptors to develop a deep-learning model for gait improvement assessment, evaluated by a physiotherapist through lower extremity functional scores. The suggested model, AtdNet, which utilizes Densenet169 and attention mechanisms, achieves 96% accuracy in classifying walking on various post-surgical days. It also predicts lower extremity functional scores with a mean absolute error of 4.63%. A deeper analysis of bone-conducted footstep sounds enriched the acoustic sensing method. We assessed the suggested acoustic model alongside existing methods, showing that rehabilitation monitoring driven by acoustics outperforms traditional clinic-based approach assessments. Future efforts will focus on validating the model with a larger dataset and integrating it into smart homes. © 2014 IEEE.

关键词： Physiological models

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：