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： Srinivasa Gupta, N. Valarmathi, B. Hiwanj, Ishaan Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798331527549

Predicting water quality is essential to preserving human health and environmental sustainability. Traditional water quality assessment methods often face scalability and real-time monitoring limitations. With accuracies of 62%, 72%, 83%, 69%, 63%, 66%, 71%, 63%, and 64%, respectively, the current techniques utilized were Logistic Regression, Decision Trees, Random Forest Regressor, Extreme Gradient Boosting, Naive Bayes, K-nearest neighbors, Support Vector Machine, AdaBoost, and Bagging [9]. This study addresses these challenges by leveraging Adaptive Synthetic Sampling (ADASYN) to balance the dataset and evaluating model performance on datasets of 5,000 and 10,000 entries per class. A robust dataset obtained from Kaggle was used, with five models – Long Short-Term Memory (LSTM), Feed Forward Neural Network (FFNN), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Random Forest – evaluated and compared. The proposed methods demonstrate significant improvements in accuracy, with XGBoost achieving the highest accuracy of 95.53%, followed by Random Forest at 93.98%. This work underscores the importance of advanced machine learning techniques in addressing the limitations of traditional methods, enhancing accuracy, scalability, and adaptability in water quality prediction. These findings contribute to advancing environmental monitoring and management practices with reliable, data-driven insights. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective ML models

引用

International Journal of computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

Integration of smart Sensors and Machine Learning Algorithms for Automated Pest Management 1

Integration of smart Sensors and Machine Learning Algorithms...

引用

1st International Conference on Sustainable Energy Technologies and Computational Intelligence, SETCOM 2025

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

ISBN: (纸本)9798331520540

This paper presents a new IoT-based approach for agricultural pest control, incorporating machine learning techniques. Traditional pest monitoring methods are labor-intensive and often result in the overuse of pesticides. The proposed system solves this problem by predicting pest populations using environmental data collected via IoT sensors. We use random forest regression and random search cross-validation to predict pests and identify important factors. The system calculates the amount of pesticides based on forecasts, helping farmers optimize use and reduce environmental impact. The experimental results demonstrate the effectiveness of the system in terms of accurate prediction and optimal pesticide application, and thereby providing a scalable and cost-effective solution for sustainable agriculture. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Smart Parking System using YOLO, ANPR and MQTT with Artificial Intelligence Features 3

Smart Parking System using YOLO, ANPR and MQTT with Artifici...

引用

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

Cohesive Heartbeat Monitoring for Geolocation and Log Correlation in Campus Networks 15

Cohesive Heartbeat Monitoring for Geolocation and Log Correl...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Suganya, R. Shazil Nath, Hiran V. Vellore Institute of Technology Chennai Department of Computer Science and Engineering Chennai India Vellore Institute of Technology Chennai School of Computer Science and Engineering Chennai India National Institute of Technology Department of Computer Science and Engineering Kozhikode Calicut India

ISBN: (纸本)9798350370249

A campus network is made up of a dense interconnection of local area networks within a limited geographical area characterized by a centralized infrastructure that interconnects various facilities within an institution, providing communication and data exchange services to support organizational activities. In a campus network, relevant information about connected clients such as connection status, duration, and relative location has to be maintained and updated in real-time to facilitate availability, log correlation and monitoring capabilities. It is important to establish a multi-pronged system in place to combat security threats and potential data loss. In this paper, we examine several existing standard practices and identify the operational and functional bottlenecks associated with each implementation with respect to the campus network. The study underscores the critical need for robust and adaptive network architectures and practices to safeguard organizational communication and data integrity with emphasis on the dynamic landscape of campus environments. Finally, we propose a novel cohesive heartbeat monitoring system that leverages data from various sources to ensure connection availability and provide advanced logging capabilities. © 2024 IEEE.

关键词： 802.1X campus network heartbeat logging RADIUS SNMP

来源：评论

学校读者我要写书评

暂无评论

Predicting Bitcoin Prices: A Comparative Analysis of SuSi vs. Deep Learning Methods 24

Predicting Bitcoin Prices: A Comparative Analysis of SuSi vs...

引用

2024 5th International Artificial Intelligence and Blockchain Conference, AIBC 2024

作者： Godson, Sam Santhosh, V.V. Dhushyanth, S.B. Anandakumaran, Kirtanaa Prem Sankar, N. School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamil Nadu Vellore India

ISBN: (纸本)9798400710780

Predicting Bitcoin prices remains a challenging task due to the inherent volatility and non-linearity of cryptocurrency markets. This paper investigates the effectiveness of Self-Organizing Maps (SOMs) implemented through the SuSi package for Bitcoin price prediction. We compare SuSi's performance with established deep learning methods, including Long Short-Term Memory (LSTM) networks, Recurrent Neural Networks (RNNs), Deep Neural Networks (DNNs) and N-BEATS. We evaluate these approaches using real-world Bitcoin price data and analyze their performance based on accuracy, interpretability, and training efficiency. Our findings suggest that SuSi offers a competitive alternative to deep learning methods, particularly when considering training efficiency. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Survival Prediction of Cirrhosis Patients Using Polynomial Features and Differential Evolution 10

Survival Prediction of Cirrhosis Patients Using Polynomial F...

引用

10th International Conference on Biosignals, Images and Instrumentation, ICBSII 2024

作者： Patil, Hemprasad Yashwant Bhagwan Patil, Priyanka Shanmugasundaram, Lackesh Balasubramaniam, Anishkaa Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Vellore India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Vellore India

ISBN: (纸本)9798350350951

This research focuses on enhancing the accuracy of the Cirrhosis Patient Survival Prediction dataset from the UCI-MLR. Leveraging novel techniques such as feature engineering and hyperparameter tuning, the study employs a comprehensive dataset with attributes including drug administration, age, sex, bilirubin, cholesterol, and albumin levels, along with labels indicating the stage of liver cirrhosis. The chosen dataset, recognized for its reliability and widespread adoption in research, serves as a valuable benchmark for developing diagnostic models. The comparative analysis involves Gradient Boosting Classifier, Logistic Regression, K Nearest Neighbors Classifier, Decision Tree Classifier, Gaussian Naive Bayes Classifier, Linear Discriminant Analysis, and Support Vector Classifier. Further, hyperparameter tuning through Grid Search and Differential Evolution methods results in substantial accuracy improvements, particularly with the latter yielding a remarkable 9% increase with respect to the control dataset with no alterations. This work showcases the potential of advanced methodologies in optimizing cirrhosis prediction models, emphasizing the importance of feature engineering and hyperparameter tuning in achieving significant performance enhancements. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Prevention of Attacks in Vehicular Adhoc Networks

Prevention of Attacks in Vehicular Adhoc Networks

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Anjali, Thuvva Goyal, Rajeev G.n, Balaji Amity University Computer Science and Engineering Amity School of Engineering and Technology Gwalior India Vellore Institute of Technology Computer Science and Engineering School of Cse Vellore India

ISBN: (纸本)9798350348460

Over the past years, numerous methods have been developed to identify anomalies in traditional VANETs networks. A survey of VANET anomaly detection and mitigation methods is presented in this analysis. This survey looks into a variety of VANET research projects, attack types, anomaly detection methods, and mitigation strategies. VANETs provide wireless communication among vehicles as well as between vehicles and infrastructure. Its major objective is to improve road safety, comfort, and convenience. VANET varies from ad hoc networks due to its specific features. Several methods for identifying anomalies in conventional VANET networks have been developed over time. This work examines VANET anomaly detection and prevention technologies. Various VANET research studies, different types of attacks, anomaly detection, and VANET protection measures. The current investigation seeks to address various sorts of vehicle network assaults as well as existing security methods for coping with these attacks. This work will help academics understand the taxonomy of automotive network security vulnerabilities, which can subsequently be researched further to develop unique solutions. © 2024 IEEE.

关键词： Identity Based Signature Intelligent Transport System Intrusion Detection System Vehicle to Vehicle Vehicular Adhoc Network

来源：评论

学校读者我要写书评

暂无评论

Lung-Retinanet Lung Cancer Detection Using A Retinanet With Multi-Scale Feature Fusion And Context Module 15

Lung-Retinanet Lung Cancer Detection Using A Retinanet With ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Gedela, Dattatreya Krishna, S. Venakata Satya Kumar, Dinesh R. Keerthika, P. CSE Department Siddhartha Institute of Technology & Sciences Hyderabad India School of Computer Science and Engineering Vellore Institute of Technology Vellore632014 India

ISBN: (纸本)9798350370249

Lung cancer identification is troublesome, on the grounds that blood tests and CT filters take time and require human mediation. Lung-RetinaNet, a lung tumour detection arrangement, resolves these issues. The RetinaNet model is increased with multi-scale feature fusion and a setting module. The Lung-RetinaNet model purposes a multi-scale highlight combination module to join neural network layers. This strategy further develops the model's semantic data assortment, which is fundamental for lung tumor identification. Notwithstanding multi-scale feature fusion, Lung-RetinaNet utilizes an enlarged and lightweight setting module approach. This module utilizes context oriented data with each neural network layer to further develop feature extraction and lung imaging little cancer area. The task's lung cancer detection technique is more proficient and precise utilizing these parts. Adding the Xception model boosts lung cancer classification accuracy to almost 100%. Likewise, YOLOv5 and YOLOv8 further develop lung cancer detection in photos. This complex strategy ensures a total lung cancer analysis, coordinating accurate classification and exact object recognition. ©2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Fruit and Vegetable Detection Based on Pytorch Machine Learning Frame Work Model 2

A Fruit and Vegetable Detection Based on Pytorch Machine Lea...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Priyadharshini, U. Vijayan, R. School of Advanced Science Vellore Institute of Information Technology Vellore India School of Computer Science Engineering and Information System Vellore Institute of Information Technology Vellore India

ISBN: (纸本)9798350328202

Today, Agricultures has become a significant element of people's life. Among them fruits and vegetables are a great thing for healthy lives. Classification of fruits and vegetable are difficult for normal person because of some same similarities like shape and color. Also, Fruits and Vegetables classification is an important process in industries applications as well as local market. Lots of similarities available between fruits like apples, pears and peaches, and that kinds of fruits are generally used in daily routine. As well as some vegetables are same in shape, so it will be difficult to differentiate in this type of situation for old persons. The previous research for solution of this type of problem for classification of fruits CNN is used but the problem in this research is when they use the self-made datasets then their accuracy decreases as compare to public datasets accuracy increases. To solve this type of problem, here produce a kind of algorithms in the paper to classify fruits and vegetable, using deep leaning technique such as VGG16 and DenseNet169 model have capability to extract the feature of images very deeply using various small filters so it provide a better result. On this premise, it was used to classify fruit kinds against a complex background and integrated with data improvement technology for future usage. It might be helpful for human for automatic differentiate the both categories. This project is implemented in the python programming language and the dataset used Fruits and Vegetables Image Recognition Dataset for the classification. Which will help to differentiate between Fruits and Vegetables with high accuracy rate. For the implementation of this project used Python programming and this implementation using the tool like Jupiter and Kaggle Notebook and used GPU for highspeed execution. © 2024 IEEE.

关键词： Fruits

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：