检索结果-内蒙古大学图书馆

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

作者： Yadav, Krrish Roy, Sritama School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Electronics Engineering Vellore Institute of Technology Chennai600127 India

ISBN: (纸本)9798331527549

Smart parking systems leverage advanced technologies to optimize parking space utilization and enhance user experience. This research paper explores the design, implementation, and evaluation of a smart parking system aimed at improving accessibility and security in urban parking facilities. It utilizes real-time sensor data to provide accurate parking availability information and empowers users to book slots through a secure mobile web app. The app integrates user-friendly navigation to guide drivers to their booked spots. OTP generation bolsters security, preventing unauthorized parking occupancy. One of the most significant and difficult problems in image-based sequence recognition is scene text recognition, which is the focus of this study's investigation. A brand-new neural network architecture is put forth that unifies transcription, sequence modelling, and feature extraction into a single framework. It performs admirably in both lexicon-free and lexicon-based scene text recognition tasks and is not restricted to any predefined lexicon. It produces a much more manageable and effective model, making it more suitable for real-world application scenarios. © 2025 IEEE.

关键词： App development Neural network OTP generation Smart parking text recognition

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Insights: Leveraging Analytics for Predictive Modeling in Finance 4

Data-Driven Insights: Leveraging Analytics for Predictive Mo...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Purwar, Mitali Deka, Upasana Raj, Himadri Ritu Upes Department of Computer Science & Engineering Dehradun India Noida Institute of Engineering & Technology Department of Computer Science & Engineering Greater Noida India Chandigarh College of Engineering Chandigarh Group of Colleges Department of Computer Science & Engineering Jhanjeri140307 India

ISBN: (纸本)9798350387490

A distinct gap in the most recent business intelligence literature is addressed by this research, which discusses the possibility of radical changes in the market based on the application of predictive analytics. The key goal is to evaluate the impact of the prediction models on ethics, expansiveness, precision and reliability. The evaluation is of a qualitative nature, and topic analysis along with case histories is used to acquire specific, contextualised data. Basic findings indicate that employment of market forecasting skills is enhanced through the use of predictive models since decisions are made much more deliberately. The analysis reveals that these models remain prone to change in a variety of contexts and demonstrates their capacity to deal with large data efficiently. Ethical issues is stressed out, which leads to the conclusion that there should be stricter rules for personal data protection and more openness for procedures to gain the compliance and trust. The conclusions underline the major competitive advantages that, if applied line by line, predictive analytics can offer, calling for more adaptability and sensitivity to the market trends. This report which proposes a 50-50 mix of value creation and integrity does, nonetheless;provide notice of potential ethical issues and data privacy. The guidelines for enhancing the accuracy of the prediction, which complies with the ethical standard are strengthening the information management system and developing novel predictive model technologies. Future research must continue to analyze shifts in predictive analytics understanding new technologies and possible changes in the market. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

HRSR-SVM: Hybrid Reptile Search Remora-based Support Vector Machine for forecasting stock price movement

引用

International Journal of Information technology (Singapore) 2023年第6期15卷 3127-3134页

作者： Shanthini, P. Matilda Parthasarathy, S. Venkatesan, P. Nandhini, S. Department of Mathematics SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai 600089 India Research and Statistics Sri Ramachandra Medical College & RI Sri Ramachandra University Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

The prediction of stock movements remains an arduous process because of the dynamic and volatile nature of the stock market. In recent times, numerous stock prediction approaches are developed to forecast future stock movements. However, they have not achieved satisfactory results in predicting future stock prices. The objective of the paper is to enhance the performance of stock prediction by the Support Vector Machine-based Hybrid Reptile Search Remora (SVM-HRSR) approach. The data gathered from the stock market are utilized to examine the performance of the proposed prediction model which is collected from the National Association of Securities Dealers Automated Quotations (NASDAQ). The unstructured stock market data is structured to increase the prediction performance using the preprocessing steps namely data minimization and min–max normalization. The proposed SVM-HRSR approach accurately determines stock market movements based on the predicted patterns. The performance influencing factors of the Support Vector Machine (SVM) such as kernel parameter and penalty parameter is tuned mechanically using the Hybrid Reptile Search Remora (HRSR) algorithm to improve the prediction accuracy. Some of the indicators such as Mean Absolute Percentage Error (MAPE), Correlation Coefficient (C_c) , Root Mean Square Error (RMSE), Hit Rate (HR) and Symmetric Mean Absolute Percentage Error (SMAPE) estimated the performance of the SVM-HRSR method. The experimental results inherit that the proposed method achieved less error rates as compared to existing methods. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Hybrid Reptile Search Remora algorithm NASDAQ Stock prediction Stock price movement Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning based Model for Predicting the future prices of Bitcoin 2

A Deep Learning based Model for Predicting the future prices...

引用

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Singathala, Harshith Malla, Jyotsna Jayashree, J. Vijayashree, J. School of Computer Science and Engineering Vellore Institute of Technology Vellore India Vellore Institute of Technology Department of Computer Science Vellore India

ISBN: (纸本)9798350347982

Bitcoin was introduced in 2009 and is the earliest cryp- tocurrency in the world. It has gained immense popularity and has attracted a huge consumer base owing to its ever-increasing market capitalization. This has led to many traders and investors being interested in knowing the future prices of these cryptocurrencies to gain profits. Researchers have contributed several works in the field of predicting the future cryptocurrency but with very low accuracy. The aim of this paper is to propose a bitcoin price prediction model which will help predict the future prices of bitcoin. Different deep-learning models are involved in the proposed prediction model namely Gated Recurrent Unit(GRU), Long Short-Term Memory(LSTM), Bidirectional GRU (BiGRU) and Bidirectional LSTM (BiLSTM). The performance analysis of the different models shows that BiGRU is able to predict the future bitcoin prices with the lowest Mean Absolute Error Percentage(MAPE) score of 3.41 © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled Semantic Web 2

AI-Enabled Semantic Web

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Saeed, Abdullah Dhanda, Namrata Rao, Ansh Samuel Verma, Rajat Amity University Uttar Pradesh Department of Computer Science and Engineering Lucknow India Pranveer Singh Institute of Technology Department of Computer Science and Engineering Kanpur India

ISBN: (纸本)9798350371055

The paper presents a comprehensive study on the development of an AI-enabled Semantic Search application using a Full Stack approach. The project integrates cutting-edge technologies, such as ***, Langchain, Pinecone, and ChatGPT, to create a robust and efficient information retrieval system. The methodology begins by setting up the essential imports and utility functions for Langchain and Pinecone. Diverse data types are then loaded seamlessly using specialized loaders. The project's core involves the creation of a Pinecone index and successfully uploading documents, which establishesa powerful and accessible database. The application's user interface can be enriched with advanced UI features. These features enhance the aesthetic appeal and interactivity of the platform, facilitating user navigation and query formulation. The implemented technique discusses the challenges of developing an AI-enabled Semantic Search application, such as the need to deal with large volumes of data and the complexity of natural language processing, and suggests solutions to these challenges, such as using distributed computing and machine learning techniques. The culmination of these efforts is a comprehensive Semantic Search application that leverages the capabilities of AI and modern web technologies to deliver an immersive, efficient, and personalized information retrieval experience. This research contributes to the advancement of full-stack development practices and demonstrates the potential of integrating AI technologies to enhance user interactions with data-rich platforms. © 2024 IEEE.

关键词： LangChain LLMs Semantic Search Text Embedding Web

来源：评论

学校读者我要写书评

暂无评论

Enhancing the mechanical performance of recycled aggregate concrete: the synergistic effects of micro titanium dioxide and steel fibres

引用

Journal of Building Pathology and Rehabilitation 2025年第1期10卷 1-12页

作者： Pushpa, K. Jayakumar, S. Pannirselvam, N. Department of Civil Engineering Sri Manakula Vinayagar Engineering College Madagadipet Puducherry 605 107 India Department of Civil Engineering College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India

Rapid urbanization, population growth, and frequent natural and man-made disasters have significantly increased the production of construction and demolition waste (CDW), exacerbating ecological and environmental issues. Titanium dioxide (TD), commonly used in cosmetics, paints, and disinfectants, is being increasingly utilized in cement and concrete due to its self-cleansing, antibacterial, depolluting and photocatalytic properties. An extensive study on nano-scale TD has been conducted, while relatively limited research has been done on micro-scale TD, despite its economic and safety advantages. This observation has been reported in previous studies on micro-TD. Furthermore, the combination of micro-TD with steel fibres and recycled aggregate has received limited attention. This study examines the impact of partially replacing cement with micro-TD on the fresh and mechanical properties of recycled aggregate concrete (RAC) reinforced with 1% steel fibres. Nine concrete mixes were prepared by replacing natural coarse aggregate (NA) with recycled coarse aggregate (RA) derived from CDW at ratios of 25%, 50% and 100%. Additionally, cement was partially replaced with micro-TD at 5%, 10% and 15% by weight. To enhance crack resistance and ductility, 1% of hooked-end steel fibres (SF) were added to all mixes. Throughout this study, the Two Stage Mixing Approach (TSMA) method of mixing was used and RA was utilized without any pre-treatment. Tests for workability, compressive strength, splitting tensile strength, and flexural strength were conducted and compared with control concrete made using NA. The results indicated that workability decreased with increasing replacement ratios of RA and micro-TD. The mix with 25% RA replacement and 10% micro-TD showed the highest improvements, with increases of 12.54%, 63.81%, and 35.93% in compressive strength, splitting tensile strength, and flexural strength respectively. Utilizing recycled coarse aggregates in concrete reduces the de

关键词： Construction and demolition waste Micro-Titanium dioxide Recycled aggregate concrete Steel fibres Two stage mixing methods

来源：评论

学校读者我要写书评

暂无评论

Hybrid Blockchain and IoT Driven Framework for Supply Chain Optimization by Enhancing Transparency, Efficiency and Cost Reduction 3

Hybrid Blockchain and IoT Driven Framework for Supply Chain ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Pradeep Kumar, S. Basha, C.H. Hussaian Prasath, C. Arun Amirthayogam, G. Lathif, Syed Ismail Abdul Leelavathi, R. Rajalakshmi Engineering College Computer Science Design Department Thandalam Chennai602105 India Sr University Department of Electrical and Electronics Engineering Warangal506371 India Mahendra Engineering College Department of Ece Namakkal637503 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600062 India Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai603203 India Velalar College of Engineering and Technology Department of Biomedical Engineering Erode638012 India

ISBN: (纸本)9798331509675

Blockchain technology represents a modern supply chain management revolution which fixes operational challenges while providing enhanced transparency at reduced costs. The research develops HB-SCOF (Hybrid Blockchain-Enabled Supply Chain Optimization Framework) which combines blockchain self-verification databases with automatic smart contracts to maintain continuous supply chain observation and evaluate data credibility. The framework integrates tamper-proof transaction tracking mechanisms with unified supply chain network connectivity for securing data transmission as a trust delivery method through unbreakable shared databases. The retail-industry case study demonstrated a 25% decrease in expenses stemming from agency elimination alongside enhanced flow management and better stock distribution. The system demonstrates its effectiveness through assessments of key performance indicators including transaction speed and data accuracy together with business cost efficiency. This part looks at implementation methods through training stakeholders in addition to transforming organizational policies which produce successful outcomes. Blockchain technology labs verify its capability to enhance supply chain management efficiency while showing realistic deployment methods. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Gemstone Classification Using Deep Convolutional Neural Network

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 773-785页

作者： Chakraborty, Bidesh Mukherjee, Rajesh Das, Sayan Haldia Institute of Technology West Bengal Haldia Purba Midnapur721657 India Department of Computer science and Engineering Haldia Institute of Technology West Bengal Haldia Purba Midnapur721657 India

Gemstones are precious minerals or rocks that can be cut, faceted, and polished to be used in jewelery. Gemstones are valuable commodities in today’s market. For thousands of years, gemstones have been prized for their beauty, metaphysical properties, and commercial applications. The task of classifying a gemstone is very complicated because of its nature, which is associated with various aspects. This paper proposes a convolutional neural network (CNN) based model to automatically classify gemstones. In addition, the data augmentation (DA) technique is employed to expand the quantity of data by incorporating slightly altered replicas of available data. Image cropping has been introduced to remove unwanted elements from the image. For the experiment, we have used the DenseNet169 pre-trained transfer learning (TL) model, and the experiment was conducted on a dataset that contains 87 different categories of gemstones. Our model has been evaluated against all existing models on the following metrics: accuracy, loss function, recall, precision, and F1 score. The proposed model has 79% accuracy (ACC), which shows significant improvement over existing models. © The Institution of Engineers (India) 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Developing Lexicons for Enhanced Sentiment Analysis in Software engineering:An Innovative Multilingual Approach for Social Media Reviews

引用

computers, Materials & Continua 2024年第5期79卷 2771-2793页

作者： Zohaib Ahmad Khan Yuanqing Xia Ahmed Khan Muhammad Sadiq Mahmood Alam Fuad AAwwad Emad A.A.Ismail School of Automation Beijing Institute of TechnologyBeijing100081China Department of Computer Science and Technology University of Science and Technology BannuKPKBannu28100Pakistan School of Computer Science and Engineering Central South UniversityChangsha410083China Department of Quantitative Analysis College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh11587Saudi Arabia

Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.

关键词： Emotional assessment regional dialects SentiWordNet naive bayesian technique lexicons software engineering user feedback

来源：评论

学校读者我要写书评

暂无评论

Improving Automated Diagnosis of Diabetic Retinopathy: Exploring the Influence of Segmented Retinal Blood Vessel Images Through Deep Learning 3rd

Improving Automated Diagnosis of Diabetic Retinopathy: Explo...

引用

3rd International Conference on Advanced Computing and Intelligent Technologies, ICACIT 2023

作者： Tayal, Mahima Singh, Jagendra Kumar, Vinish School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science Engineering Raj Kumar Goel Institute of Technology AKTU Lucknow Ghaziabad India

ISBN: (纸本)9789819719600

The present investigation focuses on using original and segmented retinal images to apply deep learning models, particularly DenseNet 121 and Inception V3, for the detection of diabetic retinopathy. According to the experimental results, DenseNet 121 achieved 97.7% accuracy for original images and 95.5% accuracy for segmented images, while Inception V3 demonstrated 96.6% accuracy for original images and 92.2% accuracy for segmented images. Precision, recall, and F1 score values support the models’ strong diagnostic capabilities. DenseNet 121 consistently demonstrated excellent precision and recall in its results, while Inception V3 exhibited commendable performance. The confusion matrices underscored the models’ effectiveness in minimizing false positives and false negatives, reinforcing their reliability in clinical settings. These results imply that deep learning models show significant potential for enhancing the diagnosis of diabetic retinopathy, providing medical professionals with precise tools for early detection and management. This study contributes to the expanding body of research on the application of deep learning in medical diagnostics, holding implications for improved patient care and outcomes not only in ophthalmology but also in various other medical fields. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image enhancement

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：