检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Vignesh, Puthucode Ganesh Nithin Kumar, S. Senthil Kumar, T. Jeyakumar, G. Amrita School of Computing Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798331523923

Fall detection systems are critical in elderly care and healthcare monitoring, but traditional camera-based solutions raise significant privacy concerns. This research presents a novel approach utilizing LiDAR (Light Detection and Ranging) sensors for fall detection in indoor environments, addressing privacy issues while maintaining high accuracy. We introduce LiFall, a new dataset captured using a Velodyne VLP 16 Puck LiDAR sensor, comprising 12 scenes and over 500 frames simulating various fall scenarios (including back falls, bed falls, and walking falls), contributing to the scarcity of LiDAR-based fall detection datasets. Our methodology employs two advanced deep learning architectures: Annularly Convolutional Neural Networks (ACNN) and Dynamic Graph Convolutional Neural Networks (DGCNN). Evaluating these models on both the ModelNet40 dataset and our custom LiFall dataset, results show DGCNN outperforms ACNN, achieving an accuracy of 84% on the ModelNet40 dataset with a 70:30 train-test split. On the LiFall dataset, despite challenges with dataset imbalance and achieving lower detection accuracy even after data augmentation, our approach demonstrates the potential of LiDAR-based fall detection systems. Compared to other fall detection methods, our LiDAR-based system offers significant advantages beyond privacy preservation, such as robust performance in low-light conditions and the ability to capture detailed 3D spatial information. While our current implementation is limited to laboratory settings, future work will focus on real-world deployments and further addressing dataset imbalance issues to enhance overall system performance. This research contributes to the field by providing a privacy-preserving, high-performance alternative to camera-based fall detection systems, paving the way for more acceptable monitoring solutions in sensitive indoor environments. © 2025 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Real-Time Task Manager: A Python-Based Approach Using Psutil and Tkinter 8

Real-Time Task Manager: A Python-Based Approach Using Psutil...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Sai, P. Charan Karthik, K. Prasad, K. Bhargav Pranav, C. Venkata Sai Divya, K.V. Amrita School of Computing Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331505462

The creation of a Real-Time Task Manager with a user-friendly interface and effective system monitoring is presented in this work utilising Python. The Psutil library was used to retrieve comprehensive system information, and Tkinter was used to develop the graphical user interface (GUI). The task manager's capacity to show parent processes at first, enabling users to expand and examine matching child processes upon request, is one of its primary features. In addition, the system permits the termination of user processes and facilitates the search for running processes. Real-time process data refreshing is another essential feature that makes sure the most recent information is shown. The Process ID, Process Name, Username, Memory Usage Percentage, and CPU Usage Percentage are among the prominent metrics displayed. These indicators are essential for locating operations that use a lot of resources and for efficiently controlling system performance. Iterative development was prioritised in the design process, including user feedback to improve stability and performance. The task manager is a potent tool for users and system administrators, providing real-time updates and responsive monitoring and management features through its modular and scalable architecture. © 2024 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Li-Fi Enabled Gas Detection: A Novel Approach for Navy Ship Safety 3

Li-Fi Enabled Gas Detection: A Novel Approach for Navy Ship ...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Ashwanth, G.P.N. Reddy, Gajjala Venkat Rushith Abhiram, Prayaga Shashank Belwal, Meena Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

The major risk of gas leakages to naval ships and vessels is to both personnel and machinery. Traditional types of gas detectors use fixed wired sensors, which tend to be extremely challenging for maintenance in complex ship contexts. This work addresses applying Li-Fi technology for successful wireless detection of gas leaks. Li-Fi has been employed to measure the gas level in real time, hence enabling fast reaction in case of possible leaks or damage. The foundation of this project is to establish a LiFi-driven communication system in areas where Radio Frequency(RF) communication is restricted and provides safer and more reliable detection system for navy ships. Preliminary results show that in this Li-Fi-based system, accurate real-time gas detection with high speed data transfer in RF challenged environments should be possible. This type of approach not only will increase response times but the need for vast wiring diminishes, hence enhancing effectiveness in maintenance and operational dependability in complex ship spaces. © 2025 IEEE.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Using MRI 4

Brain Tumor Detection Using MRI

引用

4th International Conference on Advances in computing, Communication Control and Networking, ICAC3N 2022

作者： Singh, Nidhi Raj Kishore, Siddhant Senthilvel.p, Gururama Saxena, Elina Galgotias University School of Computing Science and Engineering School of Computing Science & Engineering India

ISBN: (纸本)9781665474368

With the advent of science and technology the field of diagnostics is much easier with the help of various imaging modalities such as MRI or CT scan. These images are becoming increasingly important with increasing demand due to a number of helpful features such as these automatic, accurate, reliable, quick and effective diagnostics in a very short time that can provide a clearer view of the story than human eyes. A brain tumor is considered to be the most serious cancer. The study found that Brain Tumor was the second leading cause of cancer-related deaths in men aged 20 to 39, and the fifth leading cause of cancer in women of the same age group. Brain tissue is painful, and can lead to certain diseases if not treated properly. Diagnosis of a tumor is a very important part of the treatment process as it plays a very important role in its treatment. diagnosis plays an important role in detecting malignant and malignant tissue. The main reason for increasing the number of cancer patients worldwide is ignorance about early detection of the disease. © 2022 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Migraine Diagnosis and Classification with TabNet: A Data-Driven Approach 14

Enhancing Migraine Diagnosis and Classification with TabNet:...

引用

14th International Conference on Cloud computing, Data science and engineering, Confluence 2024

作者： Mudassir, Shaik Nawab Ravichandran, M. Amrita School of Computing Amrita Vishwa Vidyapeetham Computer Science and Engineering Chennai India

ISBN: (纸本)9798350344837

In recent years, significant advancements in health-care analytics have shown immense potential in enhancing patient care and clinical decision-making. This research delves into innovative methods for precise migraine classification using TabNet, a state-of-the-art deep learning model specifically designed for tabular data. Migraine, a debilitating neurological condition, poses challenges in accurate categorization and effective management. Our method utilizes the capabilities of TabNet to establish a robust system for classifying various migraine subtypes. We leverage a rich array of clinical and patient-reported data to enable accurate, automated diagnosis. This research underscores the impact of advanced analytical techniques in healthcare, offering a more personalized, data-centric approach to diagnosing and treating migraines. Our findings reveal an impressive 98% accuracy in overall migraine classification, outperforming other methods, and an exceptional approximate 99% accuracy in identifying specific migraine subtypes. Through TabNet, we aim to advance healthcare analytics, providing healthcare professionals with enhanced tools for patient care and contributing to the broader field of precision medicine. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Development of an Online Collectable Items Marketplace Using Modern Practices of SDLC and Web Technologies 1

引用

5th International Conference on Data and Information sciences, ICDIS 2023

作者： Khulbe, Saransh Gumber, Divyam Pratap Singh, Shailendra School of Computing Science and Engineering Galgotias University Uttar Pradesh Greater Noida India

ISBN: (数字)9789819969067

ISBN: (纸本)9789819969050

This research paper is intended to study and implement the development of a PHP-based system of an online collectable items marketplace which can onboard multiple users and sellers while keeping a singular admin account. The research intensely focuses on adapting modern techniques of the software development lifecycle (SDLC), Pattern matching algorithms to optimize search times, secure multilayer encryption techniques for login and purchase modules, overall security from XSS attacks in the input fields while documenting the work and meanwhile proposing a system with a rich feature set to satisfy user requirements. The development cycle one has been intensely studied with usability testing and a tabular representation of the results. Furthermore, the analysis of these results has been captured graphically and conclusively a complete Web application is developed compliant to the essential benchmarks of today’s time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Hyper-personalized employment in urban hubs: multimodal fusion architectures for personality-based job matching

引用

Neural computing and Applications 2024年 1-16页

作者： Jain, Dipika Sangwan, Saurabh Raj Kumar, Akshi Department of Computer Science and Engineering Delhi Technological University New Delhi India School of Computer Science and Engineering Galgotias University Greater Noida India Department of Computing Goldsmiths University of London London United Kingdom

In the evolving landscape of smart cities, employment strategies have been steering towards a more personalized approach, aiming to enhance job satisfaction and boost economic efficiency. This paper explores an advanced solution by integrating multimodal deep learning to create a hyper-personalized job matching system based on individual personality traits. We employed the First Impressions V2 dataset, a comprehensive collection encompassing various data modalities suitable for extracting personality insights. Among various architectures tested, the fusion of XceptionResNet with BERT emerged as the most promising, delivering unparalleled results. The combined model achieved an accuracy of 92.12%, an R2 score of 54.49%, a mean squared error of 0.0098, and a root mean squared error of 0.0992. These empirical findings demonstrate the effectiveness of the XceptionResNet + BERT in mapping personality traits, paving the way for an innovative, and efficient approach to job matching in urban environments. This work has the potential to revolutionize recruitment strategies in smart cities, ensuring placements that are not only skill-aligned but also personality-congruent, optimizing both individual satisfaction and organizational productivity. A set of theoretical case studies in technology, banking, healthcare, and retail sectors within smart cities illustrate how the model could optimize both individual satisfaction and organizational productivity. © The Author(s) 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Traffic Violation Detection with Tesseract OCR and Computer Vision

Advanced Traffic Violation Detection with Tesseract OCR and ...

引用

2024 International Conference on Circuit, Systems and Communication, ICCSC 2024

作者： Gnanakumar, D. Jairus Ponrabi, S.V. Ravindran, N. Razvi, Ahmed Gokulakannan, K. School of Computing Department of Computer Science Engineering Virudhunagar Dist Tamilnadu Krishnankoil India

ISBN: (纸本)9798350365306

The paper introduces an intelligent system that utilizes machine learning to effectively detect traffic infractions. It incorporates adaptive stop line detection, robust licence plate extraction, and real-time traffic light monitoring. The system's machine learning component accurately recognizes traffic signal colors, facilitating better traffic flow management. Adaptive stop line detection adjusts to various traffic situations, enhancing system flexibility. Licence plates are accurately extracted using Optical Character Recognition (OCR), which is powered by image processing and Haar Cascade classifiers. The system's effectiveness in identifying traffic violations, especially during red lights, is demonstrated through video data testing. Additionally, the integration of a MySQL database enables comprehensive logging and tracking of penalized licence plates, providing a detailed overview of traffic infractions and keeping track of all the violating vehicles. This technological integration promises significant improvements in traffic enforcement and road safety. The combination of adaptive stop line detection, real-time traffic light analysis, and licence plate identification makes this system an invaluable tool for traffic control authorities. By improving enforcement and monitoring, the system has the potential to revolutionize traffic management and enhance safety measures. This proposed work suggests that such an intelligent system can be a sophisticated asset in addressing traffic-related challenges and ensuring safer road conditions. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

The Crucial Function that Clouds Access Security Brokers Play in Ensuring the Safety of Cloud computing 16

The Crucial Function that Clouds Access Security Brokers Pla...

引用

16th International Conference on Security of Information and Networks, SIN 2023

作者： Bs, Vidhyasagar Arvindhan, M. Kalimuthu, Sivakumar Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computing Science and Engineering Galgotias University Delhi India Malaysia

ISBN: (纸本)9798350343212

The cloud is a vast network of interconnected servers and other devices that provide computing, communication, and storage services. The cloud market is dynamic, with ever-changing user needs and resource demands. Resource availability may be impacted by changes in the market, such as the addition or removal of service providers. When it comes to policies, standards, and preferences, cloud service providers and new line users are worlds apart. Even though several CSPs provide the same services, new line Access to and pricing for these services can seem different from one provider to the next. There are many advantages to using cloud computing, such as reduced overhead due to centralization, the ability to work remotely from anywhere with an Internet connection, and increased productiv-ity. More research is needed into the cloud's privacy and security risks. To manage the degree of dimensionality, heterogeneity, and ambiguity associated with cloud services, a Cloud Access Security Broker (CASB) can be deployed between consumers of cloud services and cloud applications in a cloud computing (CC) environment. They allow the company to expand its security measures beyond its structure, into third-party software and data storage. To better understand how service users deploy CASBs to provide acceptable security solutions for cloud systems, and to figure out the elements that support or hinder the adoption of CASBs by organizations using remote computing technologies, an analysis based on themes was performed. This paper will provide an in-depth analysis of the security challenges experienced by various stakeholders in cloud computing, including cloud service providers, data owners, and cloud environments. © 2023 IEEE.

关键词： 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：