检索结果-内蒙古大学图书馆

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Suryavanshi, Sneha Ramhari Thorat, Sandeep A. Shrimati Kashibai Navale College of Engineering Computer Engineering Department Vadgaon Bk Pune India Government College of and Research Computer Engineering Department Avasari Pune India

ISBN: (纸本)9798350377972

This study explores the application of Natural Language Processing (NLP) for automating the summarization of legal documents, addressing the challenge of managing vast amounts of legal data in India. With over 51 million pending cases across various courts, the accumulation of legal information remains largely inaccessible for public and professional use. Traditional methods rely on manual summarization, which is time-intensive and prone to human error. To tackle this, the study employs keyword extraction, named entity recognition (NER), and rhetorical role labeling techniques for refining content and structure. A novel encoder-decoder BiLSTM-GRU model is proposed, incorporating multi-metric graph-based features and a modified attention mechanism to enhance summarization precision, coherence, and relevance. These innovations improve the generation of concise and accurate summaries, critical for legal applications. Furthermore, the study demonstrates practical implementation through a chatbot designed to process legal judgments and answer user queries, showcasing the real-world applicability of the model. Performance evaluation metrics, such as ROUGE and BLEU, validate the model's effectiveness against state-of-the-art approaches. This research emphasizes the advantages of hybrid summarization methods, combining extractive and abstractive approaches to achieve both accuracy and readability. The findings highlight the potential of NLP-driven tools to revolutionize legal workflows, enhance accessibility, and streamline decision-making processes. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal information enhance graph convolutional networks: A deep learning framework for ride-hailing demand prediction

引用

Mathematical Biosciences and engineering 2024年第2期21卷 2542-2567页

作者： Tang, Zhenglong Chen, Chao College of Computer Science and Engineering Sichuan University of Science and Engineering Zigong643000 China Sichuan Key Provincial Research Base of Intelligent Tourism Zigong643000 China

Ride-hailing demand prediction is essential in fundamental research areas such as optimizing vehicle scheduling, improving service quality, and reducing urban traffic pressure. Therefore, achieving accurate and timely demand prediction is crucial. To solve the problems of inaccurate prediction results and difficulty in capturing the influence of external spatiotemporal factors in demand prediction of previous methods, this paper proposes a demand prediction model named as the spatiotemporal information enhance graph convolution network. Through correlation analysis, the model extracts the primary correlation information between external spatiotemporal factors and demand and encodes them to form feature units of the area. We utilize gated recurrent units and graph convolutional networks to capture the spatiotemporal dependencies between demand and external factors, respectively, thereby enhancing the model’s perceptiveness to external spatiotemporal factors. To verify the model’s validity, we conducted comparative and portability experiments on a relevant dataset of Chengdu City. The experimental results show that the model’s prediction is better than the baseline model when incorporating external factors, and the errors are very close under different experimental areas. This result highlights the importance of external spatiotemporal factors for model performance enhancement. Also, it demonstrates the robustness of the model in different environments, providing excellent performance and broad application potential for ride-hailing prediction studies. © 2024 the Author(s), licensee AIMS Press.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Review of Security and Information Control in Blockchain-Integrated IoT Applications 3

A Review of Security and Information Control in Blockchain-I...

引用

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

作者： Cholke, Abhijeet Mandhare, V.V. Vikhe, P.S. Matoshri College of Engineering & Research Centre Department of Computer Engineering Nashik India Pravara Rural Engineering College Department of Computer Engineering Loni Ahmednagar India Pravara Rural Engineering College Department of Instrumentation and Control Engineering Loni Ahmednagar India

ISBN: (纸本)9798350354348

The convergence of the Internet of Things (IoT) and blockchain technologies has gained substantial traction in recent years, owing to the rapid advancement of communication technologies worldwide. This research introduces a prototype model that seamlessly integrates an IoT platform with blockchain technology to ensure the integrity of data. The prototype establishes a decentralized framework for IoT devices, underpinned by a private blockchain infrastructure capable of replicating device data and validating transactions among devices through a consensus mechanism. Nevertheless, the implementation of this concept necessitates a closer examination of various considerations. One crucial aspect to address is transforming data generated by diverse IoT devices into a format compatible with the blockchain. This research takes a proactive approach to effective data management within the blockchain. Initially, we collect data from IoT devices and systematically store it in a blockchain-compatible manner. The custom blockchain and smart contract components define the data access policies for end-users. Within this model, we categorize IoT appliances responsible for different services into distinct sets of chains. These sets of chains collaboratively exchange data while adhering to a comprehensive access control *** research endeavors to harmonize IoT and blockchain technologies through a prototype that safeguards data integrity. It tackles the challenge of data conversion from various IoT devices into a blockchain-compatible format and outlines a sophisticated data management strategy. By delineating access policies and segmenting IoT appliances into specialized sets of chains, this model aims to facilitate secure and efficient data sharing among decentralized IoT devices. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Design a New Approach to Calculate Calorie Count with Machine Learning (ML) and Augmented Reality (AR) 5

Design a New Approach to Calculate Calorie Count with Machin...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Latke, Vaishali Balivada, Kavita Bhamare, Sumit Bhegade, Neha Patil, Sayli PCET's Pimpri Chinchwad College of Engineering & Research Department of Computer Engineering Pune India

ISBN: (纸本)9798350395235

The global obesity epidemic has persisted for many years, resulting from prevalent dietary disorders that expose individuals to a multitude of health risks. Juggling the demands of a working adult's life while trying to manage one's diet can prove to be quite a challenge. Machine Learning (ML) stands as an incredibly potent and indispensable technology in our contemporary *** system will have a significant emphasis on calorie and nutrient calculation within food items, and it sets itself apart from existing systems by offering full automation, eliminating the need for users to manually input data. Users will find the process incredibly straightforward, merely requiring them to capture an image of their food and provide it as input to the system. The initial phase of the system involves determining an individual's recommended calorie intake based on their Basal Metabolic Rate (BMR). This calculated daily calorie goal is then continually monitored and presented through Augmented Reality (AR). If the individual successfully adheres to their daily calorie target, the system sends an achievement notification to acknowledge their progress. However, should the individual surpass their calorie goal, the system responds by displaying a pop-up AR window suggesting suitable exercises to help offset the excess calorie consumption. This approach combines personalized calorie management with real-time AR feedback to support users in maintaining their desired dietary goals and overall health. © 2024 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Chat-bot Health-Care Application using Artificial Intelligence

Chat-bot Health-Care Application using Artificial Intelligen...

引用

2024 MIT Art, Design and Technology School of Computing International Conference, MITADTSoCiCon 2024

作者： Gharge, Samiksha Dnyaneshwar Musale, Jitendra More, Pranjali Khade, Sharvil Dilip Thakare, Charudatta Sunil Maneri, Aliya Javid ABMSP's Anantrao Pawar College of Engineering and Research Department of Computer Engineering Pune India

ISBN: (纸本)9798350362879

This paper explores the application of AI-driven chat-bots in health-care, aiming to assess their effectiveness in improving patient care and engagement. We develop an AI-powered chat-bot equipped with advanced NLP and machine learning to provide personalized health-care interactions. The AI chat-bot demonstrates a significant positive impact, enhancing patient satisfaction, streamlining health-care processes, and promoting patient engagement. It offers a versatile solution across health-care domains, from appointment scheduling to symptom analysis, making it a promising innovation in the ***-driven health-care chat-bots hold substantial promise for revolutionizing patient-centric care, offering an effective and versatile means of enhancing patient experiences and health-care delivery. This paper offers a deep examination of AI-powered health-care chat-bots, positioning them as a driving force in elevating the quality of patient care while embracing the possibilities and challenges of this transformative technology. © 2024 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Personalized Alzheimer's Disease Progression Prediction with Machine Learning 15

Personalized Alzheimer's Disease Progression Prediction with...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Badole, Madhuri Rane, Siddhesh Bharne, Atharv Kulloli, Vaishali Karpe, Mayur Department of Computer Engineering PCET's Pimpri Chinchwad College of Engineering & Research Pune India

ISBN: (纸本)9798331300579

One of the most prevalent diseases in the world is Alzheimer's (AD). It is a neurological condition that can lead to cognitive decline and memory loss. Both the senior population and the prevalence of diseases affecting them have dramatically increased in recent years. It is critical to categorize the progression of Alzheimer's disease. Alzheimer's disease (AD) is a complicated neurological ailment that progresses in different ways for each individual. In this study, we present a novel approach to personalised Alzheimer's disease progression prediction using machine learning techniques. Our goal is to create a model that can forecast the stage of the condition for specific individuals and classify them into one of four categories: Normal, Mild, Average, or Critical. Our method uses Convolutional Neural Networks (CNN) to extract characteristics from various MRI scans, capturing complex patterns in Alzheimer's progression. The CNN is extensively trained on a diverse dataset. Traditional classifiers such as Support Vector Machines (SVM) and Decision Trees supplement the CNN, improving the classification process. Furthermore, ensemble learning, specifically majority voting, harmonises predictions from CNN, SVM, and Decision Trees, increasing accuracy by using their individual strengths to predict Alzheimer's disease development. © Grenze Scientific Society, 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis on Optimal Routing in Wireless Mesh Network Using Optimization and Machine/Deep Learning Algorithms 3

Comprehensive Analysis on Optimal Routing in Wireless Mesh N...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kumar, Kaata Ranjith Bala, K. Srinivas, Kalyanapu Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Vaagdevi Engineering College Department of Computer Science and Engineering Warangal India

ISBN: (纸本)9798331508456

Wireless Mesh Networks (WMNs) is an important component of wireless communications by enhancing the network coverage. The mesh network topology is interconnecting all nodes in the cluster. However, the existing approaches utilized for optimal routing in WMN face challenges such as increased delays, packet loss, network congestion that lead to inefficient data transmission. WMN has an ability to deliver efficient performance even with a large number of devices. Additionally, WMNs support a wide range of applications, by using its effectiveness in various scenarios. The fundamental architecture of a mesh network integrates multiple wireless nodes interconnected through base stations for efficient routing communication. Mesh networks able to adopt different client-based structures, including infrastructure and hybrid configurations. Optimization, learning techniques and Software defined network methods are utilized for efficient optimal routing to enhance the efficiency of data transmission, while reducing delay. In this study, routing-based optimization and Machine (ML), Deep Learning (DL) algorithms are reviewed along with its advantages and limitations. The performance ML or DL model is utilized for optimal routing in WMN is evaluated based on performance metrics such as Delay, Throughput, Packet Delivery Ratio (PDR) and Connected Client Ration (CCR). © 2025 IEEE.

关键词： Wireless mesh networks (WMN)

来源：评论

学校读者我要写书评

暂无评论

Cyber-Bullying Detection on Social Medial Using Machine Learning 13

Cyber-Bullying Detection on Social Medial Using Machine Lear...

引用

13th International Conference on System Modeling and Advancement in research Trends, SMART 2024

作者： Chavan, Pranav Sandip Musale, Jitendra Thorat, Rahul Rede, Gayatri Santosh Bora, Disha Dnyanmal Dalvi, Siddhi Mahesh ABMSP's Anantrao Pawar College of Engineering and Research Department of Computer Engineering Pune India

ISBN: (纸本)9798350380583

In recent years, the rapid progress of artificial intelligence has captured the interest of numerous researchers in this field. Image captioning this study focuses on using image captioning methods to improve accessibility for those who are blind or visually impaired. Our project intends to automatically generate captions for photographs using deep learning techniques, so that blind people may comprehend visuals with ease. Image captioning is used in many contexts other than only accessibility;it's used in social media, education, and navigation, among others. Furthermore, this paper takes a close look at different ways of describing images, like using CNN-LSTM, scene features, and CNN-attention methods. We measure how well these methods work by checking scores like BLEU and ROUGE. We also talk about why different image collections are helpful for teaching computers how to understand pictures. By doing this, we hope to learn more about how to make images easier for people who can't see well. We also show how this technology can help with things like social media, school, and finding your way around. This paper hopes to help others learn more about making technology that's helpful for everyone, including people who can't see well. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Digital image watermarking based on visual secret sharing scheme 8

Digital image watermarking based on visual secret sharing sc...

引用

8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022

作者： Nakhawa, Tabassum Nadaph, Anisaara Narang, Geetika Maske, Rupali Computer Engineering Trinity College of Engineering and Research Pune India Computer Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9781665408165

Orthodox, VSS, visual secret sharing scheme to conceal hidden images of the spots, or printed out on trans-parencies or are encoded and stored in a digital format, so the audio/video, the lyrics. Stains and spots, what a noise-like pixels or as meaningful images may look like it, but this will cause the time and increase the risk of disruptions in the maintenance and transmission of the process. Therefore, in the traditional system of the visual secret sharing, this will create a problem for the possibility of transmitting the secret to himself and to the members of the group, which is involved in the VSS system. In order to solve this problem, we proposed new techniques in the field of the digital watermark on the images, with the help of a texture image, as well as a system for the visual and the replacement of the natural image, the secrets of the VSS of the hidden, the images with the help of different vehicles in order to protect the confidentiality of communications, and the participants during the transmission phase. We combine a process for the synthesis of a digital image as the textures in order to hide the secret message. Instead of using the existing cover image to hide secret messages, our algorithm conceals the original texture of the image and the codes of the secret message by means of a process of watermark or digital images. Natural resources can be pictures, it can be in any form, in both digital and printed media. We also offer the opportunity to hide in the secret, in order to reduce the risks of transmission of notices of default is AES-advanced encryption algorithm. The results show that the proposed method is an obvious way to solve this problem at the risk of the transmission SCD systems, as well as the concern for the reliability of the system. An alphabetical index of terms, information security, information Security, visual secret in exchange programs, as well as a watermark for digital images. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Computationally Effective SDP Solution for Target Localization Using DTD and DFS Measurements in Multistatic Systems With Unknown Signal Propagation Speed

引用

IEEE Sensors Journal 2025年第12期25卷 22264-22278页

作者： Qi, Qinke Li, Youming Wu, Yonghong Guo, Qiang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China China Research Institute of Radiowave Propagation Qingdao266107 China Harbin Engineering University College of Information and Communication Engineering Harbin150000 China

This paper investigates the moving target localization in multistatic systems for unknown signal propagation speed environments and presents a semi-definite programming (SDP) solution with reduced computational complexity by differential time delay (DTD) and differential frequency shift (DFS) measurements. Existing research on this problem defines numerous auxiliary variables to pseudo-linearize measurement models, proposing high requirement related to the number of transmitters/receivers for effective localization performance of the solution or causing the computationally demanding solution. To address the aforementioned shortcomings, the auxiliary variables introduced when constructing pseudo-linear equations from the measurement models are minimized as much as possible. After that, based on the weighted least squares (WLS) criterion, a constrained WLS formulation of reducing the number of constraints is proposed, as the constraints included are formulated according to the relationships among auxiliary variables. Considering the non-convexity of the formulation, semi-definite relaxation (SDR) is applied to transform the constrained WLS problem into its SDP form for the global optimum. Besides, the mean square error (MSE) and complexity analyses are conducted to validate the performance of the proposed method from two perspectives. Both analyses and simulation results demonstrate that the method has the ability to balance the localization accuracy and computational load. © 2001-2012 IEEE.

关键词： NP-hard

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：