检索结果-内蒙古大学图书馆

Medical Image Classification Using DL-based Feature Extraction in IoMT

Recent Patents on engineering 2024年第9期18卷 e220223213881-e220223213881页

作者： Thimmapuram, Madhuri Salvadi, Shoba Rani Pallati, Narsimhulu Aluvalu, Rajanikanth Department of Information Technology Chaitanya Bharathi Institute of Technology Telangana Hyderabad India Department of Computer Science & Engineering Chaitanya Bharathi Institute of Technology Telangana Hyderabad India

Aim: Recent advances in Artificial Intelligence (AI) and the addition of Deep Learning (DL) have made it possible to analyse both real-time and historical data from the Internet of Things (IoT). Recently, IoT technology has been implemented in healthcare schemes as IoMT to aid in medical diagnoses. Medical image classification is useful for predicting and identifying serious diseases at an early stage, which is crucial in the diagnostic process. Background: When it comes to managing, treating, and preventing illness, medical photographs are an essential element of a patient’s health record. However, it is a difficult issue in computer-based diagnostics to classify images using efficient characteristics. Objective: The patent study aimed to develop a deep learning-based classification model for feature extraction. Methods: Levy flight optimization is employed to pick the weight for the classification model optimally. At the end of the day, the optimal weight led to a better classification result and a higher degree of precision when analyzing medical photos for disease. Results: We tested the proposed results in MATLAB and compared them with conventional methods of classification. The suggested model’s best results include 97.71% accuracy on a brain dataset and 97.2% accuracy on an Alzheimer’s disease dataset. Conclusion: The proposed algorithm’s high rate of convergence proves that it can successfully balance the exploration and exploitation phases by avoiding capturing in local optimization and classifying thresholds rapidly. In light of the need for improved accuracy, precision, and computational speed in clinical picture classification, a novel approach based on soft sets has been presented. © 2024 Bentham science Publishers.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

SADAK: Simple, and Automatic Detection of Accidents on roads using Kolmogorov-Arnold Networks

引用

International Journal of Information technology (Singapore) 2025年 1-8页

作者： Dutta, Anurag Kumar, Pijush Kanti Lakshmanan, K. Ghosh, Soubhik Department of Computer Science Government College of Engineering & Textile Technology Calcutta Serampore India Department of Information Technology Government College of Engineering & Textile Technology Calcutta Serampore India Department of Mathematics Kuwait American School of Education Hawalli Salmiya Kuwait Department of Computer Science Bengal College of Engineering and Technology Calcutta Durgapur India

Road accidents are one of the major contributors to mortality in India with nearly 1.68 lakh deaths in 2023 accounting for nearly 19 deaths per hour. While road accidents aren’t always “fatal”, delayed detection leads to the loss of many lives. Deep Learning deliberately showed terrific results for a lot of tasks, but for a long time, the Deep Learning models utilized the standard Multi-Layered Perceptron (MLP) architecture as its’ skeleton. Recently, a state-of-the-art architecture—Kolmogorov Arnold Network (KAN) showed up, with variable activation functions in each edge of the graphical representation of the network. Several works have inherited the KAN architecture and have shown better results in many instances. This research proposes a class of accident detection models, SADAK (Simple, and Automatic Detection of Accidents on roads using Kolmogorov–Arnold Networks) for detection of road accidents inheriting KAN architecture. To benchmark its efficiency, several well-known MLP based architectures have been considered, alongside some state-of-the-art models, which result in accuracies as high as 89% using the MLP (Vision Transformer), and 97% using the KAN architecture (KAN-Convolutional-MLP). © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Deep learning Kolmogorov Arnold network Multi-layered perceptron Road accidents

来源：评论

学校读者我要写书评

暂无评论

Smart Lock Security System 2

Smart Lock Security System

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Ravikumar, Pushpa Arpitha, C.N. Hemanth, N.G. Department of Computer Science and Engineering Adichunchanagiri Institute of Technology Chikkamagaluru India

ISBN: (纸本)9798350383867

With the percentage of single-parent households rising quickly, criminal vulnerability is becoming more of a social issue The main issue is often worry over stranger visiting, especially in the case of single female families. This project focuses on the design strategy for an embedded real-time surveillance system based on a Raspberry Pi for the purpose of detecting intruders. Surveillance technology is reinforced to provide vital security for our daily lives, along with related control and alert functions. Our creative integration of cameras and motion detectors into a web application is the foundation of the suggested security system. Remote sensing cameras and motion detectors are managed and operated by Raspberry Pi. The goal of this research is to create a system that can quickly identify outsiders and respond by taking pictures and sending them to a wireless module that is based on the owner. If owner wish to add the other members to home, then he need to save the person photo in database. © 2024 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

AgriAid: An Intelligent Farmer Companion Using Deep Learning Approach 2

AgriAid: An Intelligent Farmer Companion Using Deep Learning...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Ilakiyaselvan, N. Dhandapani, Aarthi Khadar Nawas, K. Bhattacharya, Abhinov Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350306415

The percentage of farmers in India's enormous population is roughly 54.6%. However, despite having such a large population, they only contribute roughly 13.9% of the nation's total yearly GDP. This severe inequality may be reduced by improving farmers' access to information and expert advice. In order to increase crop output and quality, farmers typically depend on agricultural counselors and professionals to provide correct information for crop decision-making. Frequently, advisors or specialists in agriculture are not always available. A voice-based chatbot has several benefits, such as being real-time, constantly available, requiring little to no training to use, and providing instant access to information rather than requiring users to walk convoluted paths. In this study, we explain my design work for a farmer's helper, named Farmer Companion, to meet the needs of both rural and urban Indian farmers utilizing Supervised ML Algorithms and Deep Neural Networks, of which the best one is selected. A comparison of recent models that have been used in the literature is also included in the paper. © 2024 IEEE.

关键词： Artificial Neural Network Natural Language Processing Neural Networks Voice based Query System Voice-based Chatbot

来源：评论

学校读者我要写书评

暂无评论

Orange Fruit Disease Detection and Classification Using AI-Based Techniques

Orange Fruit Disease Detection and Classification Using AI-B...

引用

2024 International Conference on Information and Communication technology for Development for Africa, ICT4DA 2024

作者： Weldergs, Gebrhans Weldegebriel Adigrat Univesity College of Engineering and Technology Departmnet of Computer Science Ethiopia

ISBN: (纸本)9798331527792

Orange fruit cultivation is a significant economic activity in Ethiopia. However, many diseases pose a major threat to its productivity and production in many areas of our country. Currently, the detection process is done manually, which is inaccurate, inefficient, expensive, time-consuming, and requires special people. Therefore, this research study is AI-Based Orange Fruit Disease Detection and Classification with Python 3.12.3. This has great potential to enhance early disease identification, reduce crop losses, and increased food security in the country. The paper started by collecting 1252 orange fruits from different environmental locations in the Tigray Region using digital camera. These images were collected as disease categories such as orange canker (201 images), orange scabs (206 images), orange melanosis (88 images), orange greening (369 images), as well as healthy (388 images).After that, the dataset is divided into 20% for testing, for validation 10% and 70% for training. Then, image preprocessing technique is applied on the image to removing the noise and then color threshold technique is used to segment. In feature extraction, texture, shape and color features are considered to facilitate disease detection and classification. Subsequently, a deep learning approach using Convolution Neural Networks (CNN) is then implemented, along with three machine learning approaches - Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Machine (SVM), to recognize orange fruit diseases in the early stages of growth. The proposed CNN model achieves an overall accuracy rate of 99%, recall of 99% and precision of 99%, outperforming SVM, RF, and ANN in disease identification. © 2024 IEEE.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

A Systematic Study for Understanding the Security Risks in 5G Core Network 16

A Systematic Study for Understanding the Security Risks in 5...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Dixit, Unnati Vittal, Shwetha Antony Franklin, A. Indian Institute of Technology Hyderabad Department of Computer Science and Engineering India

ISBN: (纸本)9798350383119

The widespread adoption of 5G networks has revolutionized communication, providing great connectivity and services across various verticals. Specifically, on the 5G Core (5GC) this has been made possible by leveraging network slicing and Network Function Virtualization (NFV) where multiple Network Functions (NFs) are involved to serve different user requests on the control plane and a variety of service traffic on the data plane. However, as 5G networks embrace zero trust and multi-tenant architectures, this rapid technological advancement has also exposed the 5GC to various security risks such as Distributed Denial of Service (DDoS), Man in The Middle (MITM), cross-slice disruptions, and side-channel attacks. In this regard, this paper presents a comprehensive approach to enhance the security of 5GC through a systematic study of dependency graphs, Betweenness Centrality (BC), and attack graphs. Potential attack scenarios are carefully analyzed by modeling the 3GPP-defined 5GC, performing vulnerability assessments, building attack graphs, analyzing them, and presenting the key inferences from the study. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Computation Offloading in Edge Computing for Multi-UAV Networks 8

Energy-Efficient Computation Offloading in Edge Computing fo...

引用

8th International Conference on Smart Cities, Internet of Things and Applications, SCIoT 2024

作者： Ghasemi, Kimia Movahedi, Zeinab Iran University of Science and Technology School of Computer Engineering Tehran Iran

ISBN: (纸本)9798350374674

With the pervasive advancement of communication networks, the utilization of IoT permeates various spheres of societal life. To address the inherent limitations of IoT devices concerning computational power and energy, coupled with the imperative of minimizing access delays, computing offloading to edge computing emerges as a pragmatic solution. Moreover, propelled by the advent of 5G networks, drones have gained significant traction in augmenting network coverage across diverse environments. This paper delves into the intricacies of computation offloading and UAV path planning within an edge computing framework, particularly focusing on multi-UAV scenarios. We formulate the problem with the overarching objective of maximizing the energy efficiency across both UAV and IoT device layers, while accounting for the costs associated with locally executed tasks alongside offloaded ones. Given the formidable computational complexity entailed, we propose a solution algorithm predicated on the functional coverage set paradigm, aimed at enhancing the system's energy efficiency holistically. Evaluation results corroborate the efficacy of the proposed algorithm, demonstrating marked enhancements in energy efficiency and consumption by 128/% and 25%, respectively, compared to prior endeavors. © 2024 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

An Important and Successful Multi-image Stereography-Based Secret Communication System for Military Applications 12th

An Important and Successful Multi-image Stereography-Based S...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Ravi, C.N. Suhasini, T.S. Narasimharao, Jonnadula Mahendar, A. Amruthraj, B. Venkateswara Reddy, R. Department of Computer Science and Engineering CMR Engineering College Telangana Hyderabad India CMR Engineering College Telangana Hyderabad India Department of Computer Science and Engineering CMR Technical Campus Telangana Hyderabad India CMR Technical Campus Telangana Hyderabad India Department of Computer Science and Engineering CMR College of Engineering and Technology Telangana Hyderabad India CMR College of Engineering and Technology Telangana Hyderabad India

ISBN: (纸本)9789819601387

A significant factor in data transfer is computer science. Security considerations make it difficult to transmit sensitive data or have conversations via the internet. Typically, cryptography is used to transmit text-based underground messages and conceal in sequence. These days, there are numerous methods for concealing information on any media. A technique like this is steganography. The creation of a covert communication system that uses multi-image steganography will enable safe communication among the dispatcher and the recipient free from hacker intervention. Image steganography is the main technique for information hiding. It involves integrating the cipher text within a picture called the cover picture that is very difficult for strangers to view through an unassisted eye. Within a cover image, the concealed data may take the shape of any kind of text, picture, music, or even video. The secret code is split up into several pieces and etched into several cover images, according to the conceptual notion of multi-image steganography. Thus, in order to make it extremely difficult for the hackers to hide the data, we suggested two image steganography concepts. In order to create a safe and protected system, this learning suggest by means of the Advanced Encryption Standard (AES) approach of cryptography with the Least Significant Bit (LSB) method of steganography. Here, a symmetric key—which is used by both the sender and the recipient to encrypt and decode data—is used by both parties. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Parameter Optimization Design of GA-LADRC Electro-Hydraulic Position Servo Controller 3rd

Parameter Optimization Design of GA-LADRC Electro-Hydraulic ...

引用

3rd International Conference on Information Control, Electrical engineering, and Rail Transit, ICEERT 2023

作者： Zhang, Xinglan Hao, Yuke Ouyang, Qi Department of Computer Science and Engineering Chongqing University of Technology Chongqing400044 China

ISBN: (纸本)9789819788903

To address the problem that the parameters of the self-disturbance rejection control with piston displacement feedback are hardly adjustable and easily fall into local optimum, an improved genetic algorithm is proposed to optimize the parameters of the self-disturbance suppression controller in the electro-hydraulic servo position control system. The method first establishes the second-order closed-loop state space equations based on the valve-controlled electro-hydraulic cylinder mechanism model. The self-disturbance suppression controller is improved by introducing parameter perturbations and external disturbances, and an extended state observer is established by using a combination of linear and nonlinear fast-tracking differentiators as well as an improved sliding mode control law. In the process of optimizing the parameters of the self-disturbance rejection controller, the dynamic characteristics of the controller and the input constraints of the system are taken as the optimization objectives. The simulation experiment results indicate that the proposed method can effectively improve the control accuracy, stability, and anti-interference performance of the displacement feedback-based active disturbance suppression controller. The study provides a reference for further improving the control performance of electro-hydraulic servo systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

CropSmart-A Crop Prediction Application Using Machine Learning 12th

CropSmart-A Crop Prediction Application Using Machine Learni...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Madugula, Vidya Perumandla, Anshu Likhitha, Singari Gupta, Manu Dholvan, Mohan Department of Electronics and Computer Engineering Sreenidhi Institute of Science and Technology Hyderabad India

ISBN: (纸本)9789819601424

India is a country whose primary sources of income are agriculture and farming. Varied soil in the nation enables farmers to grow a wide range of crops all year round. The agricultural industry has been the focus of in-depth investigation in the past several years due to recent technological advances, including machine learning and smart computing. The proposed work aims to develop a web application for crop selection supporting farmers and improving agricultural productivity. Various supervised machine learning classifiers are used for crop prediction based on environmental factors and soil conditions. Performance metrics are included in the evaluation of several machine learning models. The results attained show that the bagging classifier achieved better results for crop prediction with an accuracy of 97%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smart agriculture

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：