检索结果-内蒙古大学图书馆

International Conference on Computing and Networking Technology (ICCNT)

作者： Sisira C S Princy Ann Thomas Department of Computer Science & Engineering MTech in Computer Science & Engineering Government Engineering College Thrissur Department of Computer Science & Engineering Government Engineering College Thrissur

High dynamic range (HDR) images are the one’s which includes all the objects from the original scene with correct exposure. The HDR content can be very helpful in analysis purposes as it possess all features of the scene as it is. Although it is useful the creation of HDR is very much expensive. Low dynamic range (LDR) images are less expensive but may include saturation regions leads to the absence of some content. For this reason there is a necessity to think of an alternative. The reconstruction of HDR from LDR content can be the alternative solution for the problem. This process can be done using different *** studies mainly represents different kinds of machine learning techniques. The methods include machine learning , deep learning , different kinds of CNN architectures specially designed for particular purposes , GAN models , reverse tone mapping operators etc. This survey also analyses evaluation techniques for assessing quality of images and techniques like image declipping, tone mapping operator etc. Some of the analyzed methods also deals with reconstruction of HDR videos from LDR videos rather than from raw *** in the survey reveals accuracy of different methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Plant Leaf Disease Detection Approach using Hybrid Deep Learning Strategy 5

Novel Plant Leaf Disease Detection Approach using Hybrid Dee...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Vamshi, Jalla Tanwar, Shashi Thatipudi, Jayendra Gopal Ponsangeetha, A. Mukherjee, Saptarshi Mandhare, Jagdish B. School of Agriculture Sr University Telangana Warangal India G D Goenka University Department- Computer Science and Engineering Haryana Gurugram India University of North Texas Dept. of Computer Science United States Velammal Institute of Technology Department of Computer Science and Engineering Panchetti India Goldsmith Institute of Advanced Research Department-Mtech Bioinformatics Giar West Bengal Kolkata India Bharati Vidyapeeth College of Engineering Department of Instrumentation Navi Mumbai India

ISBN: (纸本)9798350385649

The early detection and identification of plant diseases are pivotal for precision agriculture, aiming to mitigate crop losses and optimize yields. This study presents a novel approach to plant disease identification, leveraging Deep Learning (DL) techniques with a focus on transfer learning. Traditional methods often rely on complex image enhancement, disease region segmentation, and feature extraction, whereas our approach employs Convolutional Neural Networks (CNNs) for efficient and accurate disease detection. To enhance accessibility and diagnostic capabilities, we implement Hybrid DL Strategy, which consists of EfficientNetB0 and MobileNetV2 model, tailored for lightweight applications suitable for smartphone implementation. Efficient NetB0 model, which considers depth, width, and resolution during convolution, enhancing the model's capacity to capture intricate features critical for accurate disease diagnosis. The overall accuracy of proposed method is 98.44%, surpassing CNN, ResNet, and AlexNet. This high accuracy underscores the effectiveness of the proposed model in correctly classifying both diseased and healthy plant leaves. © 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

Predicting Malware Classification and Family using Machine Learning: A Cuckoo Environment Approach with Automated Feature Selection 2

Predicting Malware Classification and Family using Machine L...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Niveditha, S. Prianka, R.R. Sathya, K. Shreyanth, S. Subramani, Nandhagopal Deivasigamani, Balakrishnan Karthikeyan, S. Department of Biotechnology Rajalakshmi Engineering College Thandalam Tamil Nadu Chennai602105 India Department of AIML New Horizon College of Engineering Karnataka Bengaluru560103 India School of Computer Science and Engineering VIT Tamilnadu Vellore632014 India MTech in Data Science and Engineering Birla Institute of Technology and Science Rajasthan Pilani333031 India KPR Institute of Engineering and Technology Tamil Nadu Coimbatore641407 India Department of Information Technology KSR Institute for Engineering and Technology India

Malware's increasing menace in the digital realm needs the development of powerful detection and classification systems. This study presents a unique method for predicting malware category and family using machine learning, leveraging the Cuckoo environment and automated feature selection. To undertake an exhaustive examination of malware activity, we combined the Cuckoo environment with cutting-edge machine learning methods, such as the k-Nearest Neighbors (KNN) technique. The dynamic analysis of malware samples within the Cuckoo environment, which captured their interactions with the execution environment, provided remarkable insights into their malicious behaviors. The Boruta method aided automated feature selection, improving the feature set and optimizing model performance. A comparison with existing models yielded striking findings. Notably, Test Case 3 surpassed earlier cases by incorporating Automated Feature Selection + Cross-Validation. In identifying phishing attempts, it displayed outstanding specificity (90%), precision (93%), recall (96%), and an impressive F1-Score (92%), indicating its proficiency in reliably recognizing this frequent threat. Test Case 3 showed considerable increases as well, with a surprising 7.0% increase in precision and a notable 14.6% increase in recall when compared to Test Case 1. Furthermore, in the field of ransomware detection, Test Case 4, which solely focused on Automated Feature Selection, obtained excellent results, with 91% specificity, 92% accuracy, and a recall rate of 93%. These developments highlight the importance of the Boruta algorithm in optimizing the model's performance. © 2024 Elsevier B.V.. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Internet of Things Enabled Gas Leakage Detection Over Industrial Areas using Powerful MQ Series Sensor and Controller 7

Internet of Things Enabled Gas Leakage Detection Over Indust...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Jalinder Jadhav, Rahul Radhakrishnan, P. Arun Jadhav, Dattatraya Ashreetha, B. Divya, J. Mukherjee, Saptarshi Yashwantrao Mohite Institute of Management Karad India Tagore Engineering College Electronics & Communication Engineering India Keystone School of Engineering Electronic And Telecommunication Department Pune India Mohan Babu University School of Engineering Department of Electronics And Communication Engineering Andhra Pradesh Tirupati India R.M.K.Enginnering College Dept of Computer Science And Design India GIAR Goldsmith Institute of Advanced Research Department of Mtech Bioinformatics West Bengal Kolkata India

ISBN: (纸本)9798350359299

This work presents a comprehensive overview of an Internet of Things (IoT)-enabled gas leakage detection system deployed in industrial areas using powerful MQ series gas sensors and controllers. The primary objective is to enhance safety measures by providing real-time monitoring and rapid response capabilities to potential gas leaks. The system incorporates MQ2, MQ7, and MQ135 gas sensors strategically placed in different zones within the industrial facility, capable of detecting a wide range of gases. These sensors continuously collect data, which is then transmitted to a centralized controller for analysis and decision-making. The system's architecture allows for remote accessibility, enabling authorized personnel to monitor sensor readings and take timely actions from anywhere with an internet connection. The MQ series gas sensors provide accurate and dynamic measurements of gas concentrations, including flammable hydrocarbons, toxic substances, and other hazardous gases. The system's integration with existing safety systems ensures a holistic approach to hazard prevention, allowing for coordinated responses with alarms, emergency shutdown systems, and ventilation controls. Key features of the system include scalability, cost-efficiency, and seamless integration with industrial processes. The scalability allows for the expansion of sensor networks to adapt to evolving industrial environments. The cost-efficiency is realized through the prevention of potential damage and operational downtime. Furthermore, the system integrates seamlessly with existing safety and automation systems, creating a unified safety infrastructure. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

MED-LENS — Al-based tool for preliminary diagnosis of Dermatological manifestations

MED-LENS — Al-based tool for preliminary diagnosis of Derma...

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： E. Priya Lohith Kamal T M Nithya Vishnu V Aakash A Ruthi Shankari S Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India Department of MTech Integrated Computer Science Engineering Sri Sairam Engineering College Chennai India

Access to healthcare for skin diseases is challenging, particularly in rural areas, due to limited specialized services, long waiting times, and low awareness. The Med Lens project aims to address these disparities with user-friendly skin disease detection, diagnosis, and consultation services. It leverages technology, including Raspberry Pi 4 Model B and CNNs, to enhance disease detection and provide information The hardware uses Raspberry Pi 4 Model B with a camera module and LCD screen for image capture and display. The software employs CNNs to identify skin diseases accurately, generating detailed medical reports. Database management and cloud technologies ensure data integrity and accessibility. A user-friendly GUI simplifies interactions, allowing input of patient data and delivering rapid, accurate results. This research yielded a positive result achieving a test accuracy of 92.78% and a very low-test loss of 1.11% Med Lens aims to reduce healthcare disparities and improve dermatology care in underserved areas, enhancing patient outcomes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Triple Diseases Prediction System using Deep Learning Techniques

Triple Diseases Prediction System using Deep Learning Techni...

引用

Emerging Trends in Information Technology and engineering (ic-ETITE), Conference on

作者： R. Vijayan V. Mareeswari A. B. Jaswanth Department of Information Technology School of Computer Science Engineering and Information Systems (SCORE) Vellore Institute of Technology (VIT) Vellore Tamilnadu Department of Software and Systems School of Computer Science Engineering and Information Systems (SCORE) Vellore Institute of Technology (VIT) Vellore Tamilnadu MTech (Software Engineering) School of Computer Science Engineering and Information Systems (SCORE) Vellore Institute of Technology (VIT) Vellore Tamilnadu

With the existing deep learning models in predicting multiple diseases primarily focus on analyzing individual diseases in isolation, lacking a unified system for multi-disease prediction. This project presents an approach to predict multiple diseases using Flask API, with a specific focus on brain tumors, COVID-19 and pneumonia. The proposed work represents a significant contribution to the field of disease prediction, harnessing the power of deep learning algorithms and modern web application development. The primary focus is on disease prediction, with a particular emphasis on ensuring accuracy and accessibility for end-users. The initial phase of this research involves data collection, where relevant datasets of various diseases are gathered. These datasets serve as the foundation for training and validating the deep learning models. Two prominent deep learning algorithms, Sequential CNN and VGG16, are employed for this purpose. These algorithms are chosen for their ability to handle complex data and recognize patterns within medical images and other health-related data. The core of the research involves training the deep learning models using the collected datasets. This step is crucial in enabling the models to learn and generalize from the provided data, ultimately enhancing their predictive capabilities. The models are modified to elevate their performance and accuracy. Following the training phase, the models are rigorously tested to evaluate their predictive accuracy. This assessment is vital in gauging the real-world applicability of the models in medical diagnosis. To make these powerful disease prediction models accessible to a wider audience, a front-end web application is developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyclone Chronicles: A Comprehensive Survey of Advancements in Cyclone Prediction Techniques

Cyclone Chronicles: A Comprehensive Survey of Advancements i...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： Abhineet Raj Tanmay Tiwari Ayush Madurwar Sandosh S Integrated Mtech in CSE specialization In Business Analytics Vellore Institute of Technology Chennai India School Of Computer Science and Engineering Vellore Institute of Technology Chennai India

Tropical cyclones represent formidable natural phenomena, demanding constant progress in prediction methodologies. The survey paper amalgamates diverse insights from recent research, offering an extensive overview of the state of tropical cyclone prediction. This study analyzes the stat-of-the-art approaches, such as Support Vector Machine and polynomial regression models to achieve precise cyclone tracking. Additionally, this study examines the critical role of satellite imagery in automation, shedding light on the automated techniques employed. Furthermore, this study explores the emerging applications of Generative Adversarial Networks (GANs) for learning physical characteristics within cyclone data distribution, enhancing predictive capabilities. It also addresses challenges like rapid intensification, presenting prototype visualization tools and bias correction techniques as innovative solutions. The survey underscores the significance of machine learning models and ensemble forecasting in elevating the precision of cyclone predictions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Proficient Approach in Crop Recommendation System using Gradient Boosting Machine Technique

A Proficient Approach in Crop Recommendation System using Gr...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Kandukuri Joseph Kumar N Praneeth Kumar Reddy Andhavarapu Vasu S Sandosh Integrated Mtech in CSE Specialization Business Analytics Vellore Institute of Technology Chennai India School of Computer science and Engineering Vellore Institute of Technology Chennai India

The Crop Recommendation System (CRS), a powerful data-driven tool, has revolutionized farming practices by delivering precise crop recommendations. Decision Trees and Logistic Regression are employed as initial models to assess crop choices and further enhance accuracy with Gradient Boosting Machine (GBM), which consistently outperforms other methods. CRS meticulously processes essential factors, including Nitrogen (N), Phosphorus (P), Potassium (K), Temperature, Humidity, Rainfall, and pH levels. These inputs lead to highly personalized recommendations, tailored to specific farming contexts. CRS significantly boosts agricultural productivity, providing farmers with insights for optimal crop selection, increased yields, and efficient resource allocation. It promotes sustainability by encouraging environmentally responsible farming practices. In modern agriculture, CRS emerges as a pivotal asset, contributing to productivity and global food security. Its ability to guide farmers toward sustainable practices positions it as a driving force for positive change in the agricultural sector, offering a path toward a more sustainable and food-secure future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Plant Leaf Disease Detection Approach using Hybrid Deep Learning Strategy

Novel Plant Leaf Disease Detection Approach using Hybrid Dee...

引用

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： Jalla Vamshi Shashi Tanwar Jayendra Gopal Thatipudi Ponsangeetha. A Saptarshi Mukherjee Jagdish B Mandhare School of Agriculture SR University Warangal Telangana India Department- Computer Science and Engineering G D Goenka University Gurugram Haryana Dept. of Computer Science University of North Texas Department of Computer Science and Engineering Velammal Institute of Technology Panchetti Department-Mtech bioinformatics GIAR Goldsmith Institute of Advanced Research Kolkata West Bengal Department of Instrumentation Bharati Vidyapeeth College of Engineering Navi Mumbai

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phishing Websites Detection Using Machine Learning

SSRN

引用

SSRN 2022年

作者： Jain, Suhani Choudhary, Naveen Jain, Kalpana MTech Student Computer Science Department College of Technology and Engineering MPUAT Udaipur India HOD of Computer Science Department College of Technology and Engineering MPUAT Udaipur India Computer Science Department College of Technology and Engineering MPUAT Udaipur India

Phishing is an online crime in which a criminal tries to persuade unsuspecting users to reveal sensitive (and valuable) personal information to the miscreant, such as usernames, passwords, financial account details, personal addresses, SSNs, and social contacts, for harmful purposes. Phishing is usually carried out by impersonating a reliable entity in Internet communication, which is accomplished through a combination of social engineering and technical trickery. Attackers regularly employ spoofing emails and deceptive websites to persuade users to provide personal information. Spoofing emails frequently pretend to be from legitimate companies and direct consumers to fake websites where they can enter important information. Phishing is one of the most common forms of online crime in today's world. Checking URLs against blacklists of known phishing websites, which are generally built based on manual verification, is a frequent countermeasure that is inefficient. As the Internet develops in size, automatic URL recognition becomes more necessary to offer end users with timely protection. This thesis explains how to use machine learning to detect dangerous phishing websites, with an emphasis on attributes retrieved just from the URL. It starts with a description of the available data and the feature engineering process, then moves on to choosing acceptable machine learning approaches. It compares algorithm performance and assesses the outcomes obtained. © 2022, The Authors. All rights reserved.

关键词： computer crime

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：