检索结果-内蒙古大学图书馆

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Beevi, l Sherin Joe Prathap, P.M. dani, W Vinil Abinaya lakshmi, B.G. Chowdary, GurramRenuka devi, Hema R.M.D. Engineering College Department of Computer Science and Engineering Kavaraipettai India St. Peter's College of Engg. and Tech. Department of Eee Chennai India R.M.D. Engineering College Dept. of Computer Science and Engineering Kavaraipettai India

ISBN: (纸本)9798331540364

Blockchain technology has evolved as a formidable instrument in the financial technology space, providing unrivalled security, transparency, and efficiency. This article presents a groundbreaking approach for safe and transparent client fund collection using blockchain technology. Addressing the flaws of traditional money collecting systems, such as security risks, opacity, and inefficiency, the protocol uses blockchain's inherent properties to revolutionize fund collection. The protocol, initiated by the client, permits fund collection requests through a secure client interface, with the blockchain network authenticating transactions using cryptographic techniques to ensure only authorized transactions are performed and immutably recorded on the blockchain.. Notably, the protocol's openness and security, which are supported by strong encryption algorithms and cryptographic protocols, reduce the danger of fraud and embezzlement while establishing trust in stakeholders. This protocol, which leverages blockchain capabilities, provides a disruptive solution for money collection, increasing responsibility and confidence in the financial industry. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks for SEO: A Comprehensive Framework for Healthcare Information Ranking

引用

Journal of The Institution of Engineers (India): Series B 2025年 1-16页

作者： RR, Prianka M, Vedaraj R, Anto Arockia Rosaline Department of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bangalore India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Kavaraipettai Thiruvallur India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India

Internet’s remarkable surge, ubiquitous accessibility, and serviceability have increased users’ dependency on web services for fast search and recovery of wide sources of information. Search engine optimization (SEO) has become paramount in healthcare industries, which helps patients enhance and understand their health status based on their records. In the context of healthcare, it is more significant to improve search results from specific keywords related to clinical conditions, treatments, and healthcare services. So, this research work proposes a Graph Convolutional Network (GCN)-based Search Engine Optimization (SEO) algorithm for healthcare applications. The algorithm utilizes two distinct datasets: MIMIC-III Clinical database and Consumer Health Search Queries to optimize search engine rankings for health related queries. Following data acquisition, data pre-processing is performed for better enrichment of analysis. The preprocessing steps involve data cleaning, data integration, feature engineering, and knowledge graph construction procedures to remove noisy data, integrate medical data with user search behavior, compute significant features, and construct knowledge graphs, correspondingly. The relation between the data entities is examined within constructed graph through link analysis. The pre-processed data including medical knowledge weights, content relevance scores, and user interaction signals are processed further on GCN model with Adam-tuned weights and bias for ranking healthcare data based on relevance score in response to user query using cosine similarity. The search relevance estimation indicators namely recall, precision, f1-score, and normalized discounted cumulative gain (NdCG) are computed to measure search optimization performance. The proposed GCN-SEO approach benchmarked its effectiveness over existing methods in optimizing web searches related to healthcare with a high performance rate of 95.75% accuracy and 48.25 s dwell time. This sho

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Combining Fuzzy logic and Reinforcement learning for Resource Management in Edge Computing 5

Combining Fuzzy Logic and Reinforcement Learning for Resourc...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Prasath, S. Ram Selvi, M. Krishnan, R. Santhana Nithila, Ezhil E. Malar, P. Stella Rose Sankar, G. Ram Scad College of Engineering and Technology Computer Science and Engineering Cheranmahadevi India Rajarajeswari College of Engineering Computer Science and Engineering Bangalore India Scad College of Engineering and Technology Electronics and Communication Engineering Chranmahadevi India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Electronics and Communication Engineering Chennai Avadi India J.P. College of Engineering Electronics and Communication Engineering Thenkasi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798350379945

With the wide spread of Internet of Things (loT) devices, edge computing plays a decisive part in meeting the computational demands of loT applications. Efficient resource allocation in such networks is essential to ensure optimal utilization of resources and meet the quality of service (QoS) necessities of loT applications. This research addresses the challenge of dynamic resource allocation in edge computing networks for loT applications through a novel hybrid AI approach, 'FledegeRl.' By integrating fuzzy logic and reinforcement learning, FledegeRl aims to optimize resource utilization and enhance system performance. The proposed framework is evaluated through simulation analysis and compared with existing algorithms, including Q-Iearning, Fuzzy logic Control, and Ant Colony Optimization, using metrics such as resource allocation accuracy, average throughput, and network overhead. The results demonstrate that FledegeRl consistently outperforms these algorithms, achieving higher accuracy, greater throughput, and lower network overhead. This highlights the potential of FledegeRl as an effective solution for dynamic resource allocation in edge computing environments. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Studies on Consolidation Characteristics of Marine Clay Using Geodrain

Studies on Consolidation Characteristics of Marine Clay Usin...

引用

Indian Geotechnical Conference, IGC 2021

作者： Mehta, Ashvini R. dave, S.P. Singh, Shalini L.D. Engineering College Gujarat Ahmedabad India

ISBN: (纸本)9789811967269

Many countries have had to reclaim land due to rising population and severe land scarcity. India's largest cities stretch for 7516.6 km along the coast. The Gujarat region contains a significant amount of marine clay along the coastline. The coastal clay is a soil that is difficult to work with. Because of their high consolidation over time, these clays represent a difficulty in terms of bearing capacity and stability. large settlements with a delay in the occurrence of excessive pore pressures are a characteristic of soft soil. Marine clays were collected from two separate places in Gujarat, Una and Bhavnagar, for this study. The goal of the project is to use a large-scale consolidometer with a geo drain to assist disperse excess pore water drainage and expedite settlement in marine clay. The central drain with inward radial flow is used to determine settlement in a large-scale model consolidometer with an aspect ratio of 1:0.564(H:d). The influence of considerable thickness of remolded soil sample on pore water pressure mobility may be better understood by employing a vertical drain and comparing it to a vertical flow of a typical oedometer. The degree of consolidation estimated using Barron's hypothesis shows little variance. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte ltd.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Model Study on Single Pile Subjected to Axial and Inclined load Embedded in Contaminated Soil

Model Study on Single Pile Subjected to Axial and Inclined L...

引用

Indian Geotechnical Conference, IGC 2021

作者： Kalthiya, Rutvik K dave, Jay Shah, Manish V. L.D. Engineering College Gujarat Ahmedabad India

ISBN: (纸本)9789811963582

With substantial increase of industrialization, large quantities of toxic waste remain untreated, which is a serious geo-environmental issue. Pile foundation is being extensively used at many such sites to support weak soils, where the load transfer mechanism is either through skin friction, end bearing, or both. The present research paper focuses on influence of contamination on load–settlement characteristics of RCC model pile foundation for two different slenderness ratios (8 and 10) by carrying out experimental model test on both contaminated and non-contaminated soil subjected to various load inclinations (0°, 30°, 45° and 60°) from vertical axis. Various parameters analyzed and compared in this study are ultimate inclined bearing capacity, deflection, moment, soil resistance (p), engineering properties of soil, mineralogical content of soil and effect of lateral component on inclined bearing capacity. Various theories are used to estimate vertical and lateral capacity of the pile. P–Y curve is also constructed and used to calculate deflection, moment and soil resistance for the applied load. Experimental result of the model test is compared with the inclined capacity calculated using Meyerhof’s interaction equation. This investigation has revealed that contamination of soil leads to reduction in the bearing capacity. Also, there is a direct correlation established between increase in angle of load inclination with reduced bearing capacities, and increase in l/d ratio with increase in bearing capacities of pile. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte ltd.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

American Sign language Recognition using Video Vision Transformers 3

American Sign Language Recognition using Video Vision Transf...

引用

3rd International Conference on Advanced Computing Technologies and Applications, ICACTA 2023

作者： Singh, Nishant Shinde, Vinayak Kanani, Pratik Shree L.R. Tiwari College of Engineering Dept. of Computer Engineering Mumbai India Dwarkadas J. Sanghvi College of Engineering Dept. of Computer Engineering Mumbai India

ISBN: (纸本)9798350348347

Sign language is the most natural and effective way for communication amongst the hearing/vocally challenged and the hearing abled. To bridge the social gap, this paper proposes a system that aids in translating from a video feed of American Sign language signers to a known set of common English words. Current solutions for vision based sign language to English translation is limited to a very small set of target classes and old modeling techniques that do not take into consideration the temporal factor that caters to the sequential nature of signing. We use the WlASl dataset, which is a largescale dataset for Word-level American Sign language and it comprises of 2000 words from over 100 signers and develop models on WlASl100 and WlASl300 each representing the top 100 and 300 most commonly appearing glossaries respectively. For modelling, we make use of video vision transformers (ViViT) to leverage the power of multi head attention in a temporal and spatial setting and experiment with two feature extraction models like Truncated Resnet50 and MoveNet-thunder which act as a precursor to the ViViT. The final model does better than state of the art models like Pose-GRU, Pose-TGCN and VGG-GRU, which were also trained on the WlASl dataset with a top-1 accuracy of 59.44% on the WlASl100 subset and a top-1 accuracy of 48.38% on the WlASl300 subset. © 2023 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Invoice Processing Automation Using UI Path Studio 5

Invoice Processing Automation Using UI Path Studio

引用

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

作者： Ramyadevi, R. Anbuselvan, A. Julian, Anitha Selvi, S. Murali dhar, M.S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Invoices are the fundamental document that play a vital role in encapsulating the details of the products and the business transactions between the seller and the buyer. We cannot check our invoices at any time for emergencies. Substituting the case, by storing the basic details of multiple invoices in an excel sheet might be used for future purposes. This paper provides the advancement of data extraction through automation technologies. We begin this research by the technique Optical Character Recognition (OCR) in automation of data extraction from invoices. This reduces the manual errors during extraction as the entire process works with the automation and provides an accuracy of 95%. The paper discusses the design of the automation that has to be processed for the data extraction including the invoice details, line items and relevant metadata and stored in a structured and accessible format. This storage allows the customer to get through all their product details in a document. Furthermore, the study investigates the integration of extracted data from the invoice to the customer. This integration acts as the strategic role in transforming invoice data into a dynamic asset, enabling customers to glean insights. The paper incorporates real-world examples and case studies to illustrate implementations of scrapping techniques using automation. By addressing challenges such as technological limitations, integration complexities, and data security concerns, the paper provides practical understanding for customers in processing the automation. © 2024 IEEE.

关键词： Accuracy Automation Technologies data Extractions data Storage Invoice Processing Optical Character Recognition (OCR)

来源：评论

学校读者我要写书评

暂无评论

Analysis and Estimation of discounts on Product Prices in E-Commerce Sites 5

Analysis and Estimation of Discounts on Product Prices in E-...

引用

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

作者： Julian, Anitha Maheswar, Challa Ramyadevi, R. Murali dhar, M.S. Selvi, S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Sales on e-commerce platforms are significantly influenced by discounts. When a discount is offered, 80% of buyers who initially show disinterest end up making a purchase, per a Retail Me-not survey. This increases revenue and draws in new clients who might not have otherwise thought about making a purchase. Another survey by Accenture reveals that 75% of consumers are more inclined to choose a brand that provides personalized discounts. To retain customers, e-commerce websites can implement tailored discount strategies based on customers' past purchases or preferences. The decision-making process for discounts involves various factors. Pricing strategies and discounts, as identified in the study, are pivotal in influencing consumer behavior and encouraging purchases, particularly among new customers. This research delves into the complexities of discounting practices and their impact on the online retail ecosystem. Employing a comprehensive methodology that combines quantitative and qualitative techniques, the study investigates the frequency, trends, and effectiveness of discounts across different e-commerce platforms. Through extensive data collection, including details on discount percentages, durations, and consumer feedback, the research aims to reveal insights into the strategic implementation of discounts. The study's main objective is to analyze discounts that are given on a variety of products by gathering information from an online store and using the characteristics, reviews, and ratings of the products as factors to calculate the discount value. © 2024 IEEE.

关键词： data analysis discount analysis EdA estimation techniques feedback and reviews predictive modelling

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection using deep learning approach for IoT smart city applications

引用

Multimedia Tools and Applications 2025年第17期84卷 17929-17949页

作者： Shibu, S. Kirubakaran, S. Remamany, Krishna Priya Ahamed, Suhail Chitra, l. Kshirsagar, Pravin R. Tirth, Vineet Department of Electronics and Communication Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering CMR College of Engineering and Technology Telangana Hyderabad501401 India Engineering Department College of Engineereing and Technology University of Technology an Applied Sciences PC Musandam811 Oman Machine Learning Software Engineer Paragon Semvox GmbH Saarland Kirkel Germany Department of Electrical and Electronics Engineering Aarupadai Veedu Institute of Technology Vinayaka Missions Research Foundation Tamil Nadu Chennai603104 India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Maharashtra Nagpur India Department of Mechanical Engineering College of Engineering King Khalid University Asir Abha61421 Saudi Arabia

With the advancements of IoT devices, many smart applications start to rule this era. In particular, smart cities has been adapted and realized by many countries around the world. In smart cities, vas amount of data is generated at every second. This vast data need a transmission medium which could be wireless standard. However, security is the main concern in such applications since the smart transmission always binds with anomalies. The existing anomaly detection systems need improvement in accuracy due to inefficient feature extraction and selection procedure. This paper proposes an accurate anomaly detection technique that built upon deep learning approach. We proposed a Combined deep Q-learning (CdQl) algorithm for anomaly detection. Priory, optimal features are selected by using Spider Monkey Optimizer (SMO). With the optimal features, CdQl detects anomalies accurately. In addition, the CdQl algorithm learns the environment in order to monitor the network data continuously. This continuous monitoring and optimum features helps in accuracy improvement up to 98%. © The Author(s), under exclusive licence to Springer Science+Business Media, llC, part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time deep learning for dynamic Scene Understanding and Autonomous Robot Navigation

Real-Time Deep Learning for Dynamic Scene Understanding and ...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Muthukrishnan, A. Pushparani, S. Poongavanam, N. Arun, M. Ilangovan, S. Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Avadi Tamil Nadu Chennai India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai600 078 India Saveetha University Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India K.L.N.College of Engineering Department of Information Technology Sivaganga India

ISBN: (纸本)9798331542344

In this paper, a new approach in dynamic scene understanding and robot navigation especially for autonomous robots through the integration of deep learning approach with real time processing is proposed. For object recognition and its localization on the image the system uses convolutional neural networks, also semantic segmentation relies on convolutional neural networks, for autonomous navigation, the deep reinforcement learning is used. The data for the research are gathered from publicly available databases and new data captured with web-cameras and lidAR sensors installed on robots exploring the chosen scenarios. The deep learning models are for real time usage by using TensorFlow lite and the models are run on Jetson Xavier. In order to investigate object detection efficiency, scene segmentation differentiate, success rate of providing navigation and system latency, various experiments were performed inside and outside the building. The outcomes also show a high degree of 'indoor' stability and an interacting environment obstacle avoidance efficiency over real-Time system operation. While these difficulties were noticed in rural outdoor environment, the system managed to navigate in space populated with dynamic obstacles and safely avoid them even if environment conditions changed, for instance, due to wind. deep learning with sensor fusion as a solution offered accurate scene understanding to make sure that autonomous navigation is possible on both indoor and outdoor settings. Thus, the research provides valuable information on the improvement of safety and efficiency in autonomous robots for use in various industries such as self-driving cars, robots for a smart warehouse etc. © 2024 IEEE.

关键词： Convolutional neural networks

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：