检索结果-内蒙古大学图书馆

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Gokila, S. Rajeswari, S. Helen, D. Lakshna, A. Hindustan Institute of Technology And Science Department of Computer Applications Chennai India Shrimathi Devkunvar Nanalal Bhatt Vaishnav College For Women Pg Department of Computer Science Chennai India Srm Institute of Science And Technology Department of Computer Applications Chennai Kattankulathur India Jeppiaar Engineering Collge Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350365092

Objective: The objective is to develop a generalized deep learning system for sentiment analysis in a feedback system. This implies an intention to create a model that can effectively analyze sentiment across different domains or datasets. Methodology: It is proven that the deep learning systems are playing a major role in NLP, but still there is a need of enhancement to make the prediction system a perfect one. The Convolution Neural Network (CNN) could emphasize its ability to capture spatial dependencies in textual data and the Deep Neural Network(DNN) fetches the feature in text with varying semantics. In this context the proposed work Embed the Deep Neural Network with Convolution Neural Network in a three-layered ID architecture(EDNN with CNN-ID.) The model is enhanced in generalizing input-shape, kernel, channel, and filter parameters of the convolution layer. It produces remarkable results in sentimental analysis. The work is experimented with a feedback system from three different domains like Movie Review, Doctor Treatment Review, Product Review. Result: The EDNN with CNN-ID produces accuracy 93%, 91% and 91% for the three datasets © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Field Employee Productivity and Performance with Android Software Solution and Machine Learning-based Predictive Analytic Model 5

Enhancing Field Employee Productivity and Performance with A...

引用

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

作者： Chilamkurthi, Vijayakumar Deka, Bhupesh Nikitha, Jajala Marapatla, Ajay Dilipkumar Kishore Babu, D. Hyderabad India Department of Computer Science and Engineering Guntur India

ISBN: (纸本)9798350395235

Organizations with field employees face the challenge of maintaining high-quality standards while optimizing costs. Analyzing, Classifying, Predicting, and Monitoring the Field Employee's Regular Activities, Work Productivity and Performance is the challenging objective for Management in any Organization. Research study suggests using Android Application and machine learning predictive analytic model by using decision tree algorithm to analyze and classify field employee work productivity and performance. This aims to achieve a higher accuracy rate and better insights into employee performance. To track field employees, a GPS tracking app is used on mobile devices. As part of Mobile Computing implementation, Android Mobile device transfers the data in the form of text, voice and images to the web server and vice-versa. It generates location data with secured communication through cryptography techniques and stores captured data in a database server for further analysis. Furthermore, a web-based application is proposed for monitoring and generating reports for individuals and groups of field employees, including route maps and time sheets. This proposed solution is going to be a complete one-point automated software solution for any business organization for managing their field employees. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Method for Optimal Route Calculation

Machine Learning Method for Optimal Route Calculation

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Singh, Nongmeikapam Thoiba Satwik, Vishwaroju Mani Wadhwa, Manoj Tirukala, Gowtham Pandey, Shradha Saxena, Smriti Srivastava, Hitanya Chandigarh University Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350388534

This study unveils an innovative approach to optimizing routes by merging the capabilities of the BellmanFord algorithm with the adaptive nature of Q-Learning, addressing the dynamic obstacles encountered in route planning. By integrating the Bellman-Ford algorithm, renowned for its shortest path calculation even with negative weights, with the dynamic adaptability offered by Q-Learning, we introduce a method that surpasses the limitations of traditional routing strategies. Through a series of simulations, our proposed methodology showcases enhanced adaptability, efficiency, and precision in navigating dynamic environments, outperforming both conventional routing strategies and standalone machine learning approaches. The collaboration between Bellman-Ford and Q-Learning yields a robust solution for real-time routing challenges, making it indispensable for applications in logistics, autonomous vehicle navigation, and efficient traffic management. This contribution signifies a groundbreaking step in the domain of route optimization, offering a model that proficiently adjusts to evolving conditions, thus leading the way for future research and applications in this field. © 2024 IEEE.

关键词： Dynamic routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Team IndiDataMiner at IndoNLP 2025: Hindi Back Transliteration - Roman to Devanagari using LLaMa 1

Team IndiDataMiner at IndoNLP 2025: Hindi Back Transliterati...

引用

1st Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages, IndoNLP 2025

作者： Kumar, Saurabh Kakadiya, Dhruvkumar Babubhai Singh, Sanasam Ranbir Department of Computer Science and Engineering Indian Institute of Technology Guwahati India

ISBN: (纸本)9798891762145

The increasing use of Romanized typing for Indo-Aryan languages on social media poses challenges due to its lack of standardization and loss of linguistic richness. To address this, we propose a sentence-level back-transliteration approach using the LLaMa 3.1 model for Hindi. Leveraging fine-tuning with the Dakshina dataset, our approach effectively resolves ambiguities in Romanized Hindi text, offering a robust solution for converting it into the native Devanagari script. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

引用

computers, Materials & Continua 2023年第1期74卷 1871-1886页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Saqib Raza Ahmad Salman Khan Yasir Mahmood Nazri Kama Azri Azmi Assad Alzayed Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala NerusMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Advanced Informatics Department Razak Faculty of Technology and InformaticsUniversiti Teknologi Malaysia54100Kuala LumpurMalaysia Computer Science and Information Systems Department College of Business Studies Public Authority for Applied Education and Training(PAAET)AdailiyahKuwait Department of Computer Science Sharif College of Engineering&TechnologyLahore54000Pakistan

Software maintenance is the process of fixing,modifying,and improving software deliverables after they are delivered to the *** can benefit from offshore software maintenance outsourcing(OSMO)in different ways,including time savings,cost savings,and improving the software quality and *** of the hardest challenges for the OSMO vendor is to choose a suitable project among several clients’*** goal of the current study is to recommend a machine learning-based decision support system that OSMO vendors can utilize to forecast or assess the project of OSMO *** projects belong to OSMO vendors,having offices in developing countries while providing services to developed *** the current study,Extreme Learning Machine’s(ELM’s)variant called Deep Extreme Learning Machines(DELMs)is used.A novel dataset consisting of 195 projects data is proposed to train the model and to evaluate the overall efficiency of the proposed *** proposed DELM’s based model evaluations achieved 90.017%training accuracy having a value with 1.412×10^(-3) Root Mean Square Error(RMSE)and 85.772%testing accuracy with 1.569×10^(-3) RMSE with five DELMs hidden *** results express that the suggested model has gained a notable recognition rate in comparison to any previous *** current study also concludes DELMs as the most applicable and useful technique for OSMO client’s project assessment.

关键词： Software outsourcing deep extreme learning machine(DELM) machine learning(ML) extreme learning machine assessment

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Congestion Control Techniques for WSNs

Comprehensive Analysis of Congestion Control Techniques for ...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Jakhar, Isha Vijarania, Meenu Singh, Hitesh Kumar, Vivek K R Mangalam University Computer Science Department Gurugram India Noida Institute Of Engineering & Technology Computer Science Department Noida India

ISBN: (纸本)9798350366846

Since Wireless Sensor Networks (WSNs) have limited resources for data processing, data storage, transmission capacity, and most crucially energy supply, congestion is one of the pervasive problems for WSNs. Over the past fifteen years, numerous survey operations have been conducted to look into and remedy a variety of congestion-related concerns and challenges. The majority of review articles that were published in the literature focused on traditional methods of congestion area management, such as resource-based, traffic-based, and hybrid methods. In this survey article, an effort has been made to provide a systematic evaluation of recent initiatives that have helped to improve the congestion control methodology in WSNs by taking into consideration traditional procedures, machine learning based approaches and nature inspired techniques. A comparative analysis of these techniques with other approaches has also been done to provide a clarity regarding the performance of the algorithms. In this paper, we have tried to highlight the key areas of the application of the algorithms along with their advantages and limitations. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Networking: A Comprehensive Overview of Intent-Based Networking

Revolutionizing Networking: A Comprehensive Overview of Inte...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Minhas, Sahil Jaswal, Ritik Sharma, Ankita Singla, Sanjay Chandigarh University Department of Computer Science Engineering Mohali India

ISBN: (纸本)9798350376470

This review paper researches Intent-Based Networking (IBN), a novel way to deal with network management that automates configuration and smoothes out tasks. IBN interprets high level business objectives into network configuration, dispensing with manual cycles and lessening errors. The paper investigates the essential ideas of IBN, its architecture components, and the key innovations that empower its usefulness. Besides this, the paper investigates the advantages of IBN, including upgraded network proficiency, further developed agility, proactive health management, and customizable network services. Be that as it may, difficulties like coordination with inheritance frameworks, absence of standardization, and security concerns are additionally talked about. In the last segment, the paper investigates different use cases and utilizations of IBN, featuring its capability to alter network management in modern industrial settings, Software Defined Networking (SDN) environments, and data centers. At last, the paper looks at the future extent of IBN, incorporating its possible joining with arising innovations like 5G and IoT, the job of cutting edge simulated intelligence models, and the significance of cross-layer advancement and standardization. © 2024 IEEE.

关键词： Automation Configuration Intent-Based Networking (IBN) Network Management Software Defined Networking (SDN)

来源：评论

学校读者我要写书评

暂无评论

Trade Ease with Machine Learning and AWS

引用

IEEE Access 2023年 11卷 25893-25905页

作者： Teja, Kamurthi Ravi Liu, Chuan-Ming National Taipei University of Technology International Program of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan

Global trading is undergoing significant changes, necessitating modifications to the trading strategies. This study presents a newly developed cloud-based trading strategy that uses Amazon Web Services (AWS), machine learning (ML), and data science to automate trading tasks. The study begins by creating a machine learning trading strategy using a customized deep neural network (DNN). The strategy was then tested using a trading station before deployment on a cloud machine. The execution of the strategy resulted in a total profit of 42.74526 USD, with a test accuracy score of 87.45% and a training accuracy score of 89.15% over 6047 epochs. The roadmap provides a step-by-step overview of the entire process from strategy development to execution. In addition, this study offers insights into related issues and solutions that can enhance the effectiveness of trading strategies. Overall, this study contributes significantly to the field of cloud-based trading strategies and opens avenues for future research. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Risk Assessment of Human Health Through Gated Dual-Path RNN and Gravitational Search Algorithm 3rd

Enhanced Risk Assessment of Human Health Through Gated Dual-...

引用

3rd International Conference on Emerging Trends in Expert Applications and Security, ICE-TEAS 2024

作者： Shanthi, M.A. Karthik, S. Sabitha, R. Kavitha, M.S. Department of Computer Science and Engineering SNS College of Engineering Tamilnadu Coimbatore641107 India Department of Computer Science and Engineering SNS College of Technology Tamilnadu Coimbatore641035 India

ISBN: (纸本)9789819739905

The need for precise risk assessment of human health in the healthcare industry has resulted in the integration of advanced technology. This study introduces a unique strategy that combines the Gravitational Search Algorithm (GSA) with Gated Dual-Path Recurrent Neural Networks (RNN) to address the present constraints in risk assessment methodologies. Conventional methods are challenged by the complexity of health-related data and the requirement for real-time risk assessment. The goal of this project is to integrate cutting-edge artificial intelligence and optimization techniques to transform the assessment of risks to human health. Predictions produced by current risk assessment algorithms are frequently inadequate due to their inability to identify complex patterns in health data. Moreover, the accuracy and resilience of these models are hampered by the absence of effective optimization tools. For health risk assessment, there is a noticeable lack of integration between advanced neural network topologies and cutting-edge optimization methods. To close this gap and improve risk prediction accuracy, Gated Dual-Path RNN and Gravitational Search Algorithm are combined. The proposed approach uses the Gravitational Search Algorithm to optimize the model parameters and Gated Dual-Path RNN to take advantage of the temporal relationships found in health data. The model capacity to capture both short- and long-term interdependence is improved by the dual-path architecture, and the gravitational search method effectively adjusts the network parameters. Experiments reveal encouraging outcomes, with increased precision and dependability above conventional risk assessment algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Delay Tolerant Routing Protocol for Opportunistic Networks 9

A Novel Delay Tolerant Routing Protocol for Opportunistic Ne...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Shah, Idris Afzal Ahmed, Mushtaq Yadav, Amit Mnit Jaipur Department of Computer Science And Engineering Rajasthan India

ISBN: (纸本)9798350394474

Delay Tolerant networks (DTNs) belong to a class of wireless networks which are designed specifically for environments where high latency, frequent disruptions and intermittent connectivity is seen. Such type of networks rely on a store-forward-carry mechanism in contrast to a store and forward mechanism as seen in MANETs and adhoc networks. In this paper we have attempted to propose a variant of Spray and Wait protocol based on the Catalan series. The Catalan spray and wait protocol converges faster than its binary counterpart and hence can find its applicability in applications with a higher packet delivery ratio at minimal cost. Simulation of real life scenario of cars and pedestrians moving on a map is used to show the working and efficacy of our proposed routing model. The Catalan algorithm outperforms the Binary Spray and Wait in term of metrics viz. delivery ratio, overhead ratio and average buffer time. It showcases a reduced overhead ratio of 21% when compared to the binary version of 24% for no of copies L = 18. The average buffer size and the number of copies used for 100, 500, 1000, and 2000 nodes are analyzed and the Catalan routing protocol exhibits a decrease of 0.1%, 1.5%,1.35%,1.38% (for last values) in average buffer occupancy as compared to the binary version. Moreover, it shows an overall average increase of 3% over Hexago and Pentago protocol in terms of delivery ratio. © 2024 IEEE.

关键词： Delay tolerant 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：