检索结果-内蒙古大学图书馆

bSafe: A Framework for Hazardous Situation Monitoring in Industries 1

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

作者： Kashyap, Nikhil Rajora, Nikhil Sharma, Shanu Department of Computer Science and Engineering ABES Engineering College Ghaziabad India

ISBN: (数字)9789819969067

ISBN: (纸本)9789819969050

Industrial accidents such as chemical spills, fires, and explosions. Can have serious consequences, including injuries and fatalities, environmental damage, and economic losses. To prevent industrial accidents, it is important for industries to implement safety measures such as proper training for employees, regular maintenance of equipment, etc. Furthermore, the installation of emergency response systems is the need of the era to minimize the impact of any accidents that do occur. In this paper, an IoT-based hazardous situation monitoring framework is presented to monitor and detect toxic releases from chemical companies. The proposed system actively records, processes, and analyses the ambient temperature in areas where molten metal is handled and manufacturing is done. Additionally, it keeps an eye out for two dangerous gases i.e., LPG and natural gas. Every time a parameter is breached, a set of predetermined lists of users are immediately alerted, and the system continuously collects the data for further suggestions to modify the industry’s safety rules. The sensors used in this prototype model can be altered as needed to accommodate industrial requirements. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Losses

来源：评论

学校读者我要写书评

暂无评论

Automated Attendance Management System Using Face Recognition and Real-Time Biometric Authentication 4

Automated Attendance Management System Using Face Recognitio...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Ida Christy, J. Abisha, D. Mithunkumar, C. Navedha Evanjalin, R. Ajith, S. Dharun Ram, K. National Engineering College Department of Computer Science and Engineering Kovilpatti India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

Tracking attendance in educational institutions is an extremely time-consuming and labor-intensive process, and the task seems to be plagued by inaccuracies and inefficiencies at all times. Techniques such as manual roll calls or traditional paper-based attendance systems often face problems like proxy attendance and human error, coupled with delays due to the processing of a large volume of data. The more the number of students, especially with an increasing need to operate with fewer numbers of people, there is a growing need for more efficient, reliable, and secure attendance tracking. Also, the growing administrative and academic interests of accurate attendance records affirms that current techniques of recording attendance lack the necessary level of efficiency. Attendance management systems in the conventional sense faced problems and constraints, and this paper specifically on the pressures toward discovering a solution that can automate the process yet has validity, security, and scalability issues. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Improved Music Genre Classification and Visualization using Conventional Neural Network 2

Improved Music Genre Classification and Visualization using ...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Denslin Brabin, D.R. Swarna Lakshmi, P. Princy, V. DMI College of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331534950

A genre in music is a style or kind of music. To make it easier to recognize favorite songs, music genres group related tracks together. Dissimilar machine learning approaches, for example Decision Tree, K-means Clustering, Support Vector etc., can be used to categorize diverse genres of music. This research proposes a genre classification system based on Conventional Neural Networks (CNNs). The acoustic signal is reformed into a spectrogram in the CNN model. Next, every audio file in a dataset has its Mel-Frequency Cepstral Coefficient (MFCC) retrieved, which is utilized to train the model. Any audio will be classified and its genre will be predicted by the developed model. Additionally, the suggested system is utilized to show the genres using various visualization techniques, including as stacked-bar charts, tables, pie charts, and stacked area charts. The audio is categorized using this system as Pop, Rock, Reggae, Hip-hop, Jazz, Blues, Country, Classical, and Disco. Using visualization techniques, the probability of each genre in an audio file are also displayed. Python is used to implement the suggested approach, and the model is educated by means of the GTZAN dataset. Pandas and matplotlib are used in the implementation of the visuals. On the GTZAN dataset, the precision of the suggested model is 0.875. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Based Diagnosis of Multiple Neurodegenerative Disorders 6

Deep Transfer Learning Based Diagnosis of Multiple Neurodege...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Mahendran, Rakesh Kumar Aishwarya, R. Abinayapriya, R. Kumar, P. Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350306613

Neurodegenerative disorders challenge healthcare systems globally, impacting millions of lives and diminishing quality of life. Machine learning, particularly deep learning, offers promise in improving disease classification. Using a two-step methodology, This study looks into classifying three distinct neurodegenerative diseases using transfer learning: cerebral ataxia, Alzheimer's disease, and Parkinson's disease. First, we use neural network architectures that have already been trained, including VGG16 and ResNet101, which were first trained on large image datasets. This enables us to extract high-level features that capture important disease patterns and characteristics from medical images. By adapting these pre-Trained networks to the unique attributes of each disease, we enhance the model's ability to discriminate between them effectively. We use optimization techniques like SGD, Rmsprop, and Adam algorithm to get the optimized results, we employ a range of evaluation metrics, including accuracy and loss. These metrics provide a comprehensive understanding of the model's competence in accurately classifying patients with diverse neurodegenerative diseases. To make our model more accessible and user-friendly, we deploy it through the Flask web framework. Our research findings conclusively demonstrate that the amalgamation of transfer learning, Flask deployment, and stringent evaluation metrics substantially enhances the accuracy of neurodegenerative disease classification when compared to traditional diagnostic methods. This novel strategy promises to transform the identification and management of neurodegenerative illnesses, resulting in more prompt and efficient patient interventions. © 2024 IEEE.

关键词： biomedical MRI CNN Deep learning Inception v3 ResNet101 transfer learning VGG16

来源：评论

学校读者我要写书评

暂无评论

Enhancing Goal Achievement through Collaborative Goal Tracking: A Recommender System Approach 13

Enhancing Goal Achievement through Collaborative Goal Tracki...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Shaik, Kousar Reddy, Kaki Manoj Vardhan, B Sai Reddy, H. Venkateswara Hariharan, Shanmugasundaram Kukreja, Vinay Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350305463

An innovative goal tracking application that encourages cooperation among users with similar goals is presented in this research. The app uses a strong recommender system to link users based on goal keywords, forming a helpful community, going beyond tracking each user's progress individually. The goal of the study is to assess how well collaborative features increase user engagement and goal achievement rates by examining the shortcomings of current goal tracking apps. The outcomes demonstrate how effective teamwork can be and pave the way for a revolutionary method of goal monitoring. Setting the stage for future improvements that promise a more inclusive and flexible goal tracking experience, such as machine learning-based personalized recommendations, this research lays the groundwork. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

FSACE: finite state automata-based client-side encryption for secure data deduplication in cloud computing

引用

International Journal of Cloud Computing 2023年第6期12卷 531-555页

作者： Kodada, Basappa B. Mello, Demian Antony D. Canara Engineering College VTU Belagavi Mangalore India Department of Computer Science and Engineering Canara Engineering College VTU Belagavi KA Mangalore India

Digital data is growing vastly and is generated from different sources in a structured manner, and the management of this high volume of data is critical, forcing clients to use storage services. The cloud storage server (CSS) has accumulated massive duplicate data. In reality, the computation overhead is increased on the storage server to manage these data with security aspects. Data deduplication is a widely used technique to reduce overhead on CSS. Several approaches have been proposed to address the issues of secure data deduplication (SDD). The convergent encryption (CE) is widely used for SDD to reduce computational overhead and improve storage efficiency, but CE algorithm faces threats from inner and outer adversaries. This paper proposes finite-state automata-based client-side encryption (FSACE) protocol to accomplish SDD to provide confidentiality, integrity and access control on data. The security analysis indicates, FSACE is secure enough to protect data from adversaries. We also evaluate the performance of protocol through experimentation and results that show decrease in computation overhead. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Access Point Management Using Java Based Microservice 8

Access Point Management Using Java Based Microservice

引用

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

作者： Bhat, Manoj Vishalakshi Prabhu, H. Rv College of Engineering Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

This research paper explores the design and implementation of an event-driven monitoring system for Wi-Fi6 Access Points (APs) using Java-based microservices architecture. WiFi 6's primary advantage over other standards is that it provides maximum speed and accessibility in congested networks. The system aims to enhance network management capabilities by leveraging real-time event processing and Kafka messaging infrastructure. Key components include event listeners for capturing Quality of Experience (QoE) and Trap events via Kafka topics from APs, microservices for event processing, and Kafka topics for inter-service communication. The paper discusses the architecture, functionality, and integration of each component, as well as the system's ability to identify and handle various event types, such as ap-info and user reports. Additionally, the paper addresses error handling mechanisms and debugging practices for events with undefined syntax. Overall, the research contributes to the advancement of network monitoring solutions through the utilization of microservices and events-driven architectures. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

News Recommendation Systems 10

News Recommendation Systems

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Mahalakshmi, A. Dharani, P. DivyaPriya, S. Gayathri, M. Sri Eshwar College of Engineering Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

News Data is structured as well as unstructured formatted data, which carries attributes like source, date, location, author, headline text, and detailed data. To extract features from the textual data, which deals with all of the language and text-related aspects. News articles are basic structured as well as unstructured and text-formatted data, which leads it to become the point of interest to the researchers. Various research like classification of news articles according to domain depending on the region or the area of interest of people using various machine learning techniques, sentiment analysis over the news articles using the emotional dictionary, and text summarization on the news data so as to reduce the bulkiness of data, Special Character Recognition. © 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

Computational Approaches for Identifying Potato Plant Pathogens 5

Computational Approaches for Identifying Potato Plant Pathog...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Julian, Anitha Vignesh, S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Potato cultivation is a vital component of global agriculture, providing a significant source of nutrition and income. However, the threat of diseases affecting potato crops remains a persistent challenge for farmers. In our study, we present a novel approach to automatically classify diseases in potato plants using advanced deep learning methods. The proposed approach makes use of Convolutional Neural Networks (CNNs), that perform efficiently for image processing applications. The dataset utilized in our research comprises high-resolution Images depicting diverse disease symptoms in potato plants, including late blight, early blight, and the oomycete pathogen Phytophthora infestans, a destructive ailment that impacts potato crops. To automatically discern between healthy and diseased plants, we implement a multi-layered CNN architecture that learns discriminative characteristics of images. This research significantly contributes to precision agriculture by providing an automated and efficient solution for identifying potato diseases. The proposed method in disease classification not only facilitates prompt disease management but also enables precise treatments, thereby reducing reliance on chemical interventions. The practical implications of these findings extend to farmers, agronomists, and researchers involved in sustainable and resilient potato cultivation. © 2024 IEEE.

关键词： disease identification early blight late blight potato disease

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Lymphoblastic Leukemia Diagnosis Through Dual Deep Learning Approaches 6

Enhancing Acute Lymphoblastic Leukemia Diagnosis Through Dua...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Muhammad Shameem, P. Jemsheer Ahmed, P. Nisa Parvin, K.P. Safa, M.T. Sahana, V.P. Hima Musthafa, T.H. Mea Engineering College Department of Computer Science & Engineering Malappuram India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381689

Leukemia, a life-threatening blood cancer, de-mands early and accurate diagnosis for effective treatment. This project aims to bring out the potential of dual deep learning techniques to enhance acute lymphoblastic leukemia detection. Our approach combines the capabilities of Convolutional Neural Networks (CNNs). We also propose a mobile application that integrates these dual deep learning models to provide a user-friendly and accessible solution for acute lymphoblastic leukemia detection. High-resolution medical images, such as peripheral blood smears undergo thorough examination using advanced CNN architectures. Sequential data, encompassing temporal information like cell morphology evolution, genetic markers, and patient histories, are systematically analyzed. The dual deep learning model is trained on an extensive and diverse leukemia dataset, encompassing various subtypes and disease stages. Fine-tuning and transfer learning techniques are employed to optimize model performance. Once trained, the system is assured to efficiently evaluate new patient data,providing rapid and highly accurate leukemia diagnosis. The app is trained by using a comprehensive dataset of annotated blood cell images. The app will be designed with a user-friendly interface, enabling medical professionals to easily upload and analyze blood samples. The system's output will provide rapid and accurate leukemia detection, reducing the time and subjectivity associated with manual diagnosis. In summary our project aims to advance acute lymphoblastic leukemia detection by combining two or more powerful deep learning methods to work together effectively. This system holds the promise of assisting healthcare practitioners in making more informed decisions, ultimately leading to improved patient outcomes and more effective management of this life-threatening disease © 2024 IEEE.

关键词： Diseases

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：