检索结果-内蒙古大学图书馆

23rd International Conference on Intelligent systems Design and Applications, ISDA 2023

作者： Hosseinabadi, Ali Asghar Rahmani Mirkamali, Seyedsaeid Hajiabadi, Mahdi Rohani Abraham, Ajith Department of Computer Science University of Regina Regina Canada Department of Computer Engineering and IT Payame Noor University Tehran Iran Faculty of Computer and Information Technology Engineering Islamic Azad University Qazvin Qazvin Iran School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India

ISBN: (纸本)9783031647758

Optimal energy consumption in Wireless Sensor Networks (WSNs) is important. Previous research has shown that by organizing network nodes into a number of clusters, one can achieve greater energy efficiency leading to longer network life. The WSN is made up of a very large number of sensor nodes that communicate with each other to perform specific tasks. These nodes have limited energy, processing power, and memory. Because the lifetime of the network depends on the brightness of the nodes, the energy consumption of each node is very important. Therefore, we need to find solutions to reduce the energy consumption of the nodes. One way to reduce energy consumption is clustering, many algorithms have been introduced in this field. In this paper, we optimize Particle Swarm Optimization (PSO) algorithm based on fuzzy logic and PSO algorithm. The fitting criterion will be based on the minimum energy consumed by the nodes of the network during each operation period, It leads to a balance in the energy consumption of the headers and, as a consequence, a lengthening of the life of the network. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Literature Review of Drowsiness Identification and Alert System for Real Time Network 6

Literature Review of Drowsiness Identification and Alert Sys...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Thirumurugan, S. Pradeepan, M.L. Sundhar, K. Dhanapal, R. Faculty of Engineering Department of Computer Science and Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore India

ISBN: (纸本)9798350398496

Road mishaps are more likely to be caused by tired drivers. Driving for extended periods of time, driving while sleep deprived, and driving while under the influence of drugs, alcohol, or medication are just a few of the factors that contribute to driver fatigue. In developing nations, where the death rate from traffic injuries is above 85% and the disability-adjusted life expectancy is above 90%, traffic injuries and fatalities are a major public health concern. One of the safeguards to avoid accidents is drowsiness detection. Based on the parameters each method uses, drowsiness detection techniques created for defence purposes are divided into four groups. These groups are: Subjective-based, Vehicle-based, Behavioral or Visual-based, Mouth Tracking, Physiological or Non visual-based. The remote healthcare monitoring and drowsiness alert system is a network of interconnected vehicles that communicate with each other and with the surrounding environment using advanced communication technologies. It leverages this network to collect and transmit vital health data from drivers to healthcare professionals who can then use the information's to monitor their health status and provide timely medical interventions when necessary. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of generative adversarial networks in denoising medical imaging (CT/MRI images)

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Ramadass, Sudhir Narayanan, Sreekumar Kumar, Rajiv K, Thilagavathi Data Analytics Sterck Systems Private Limited Chennai Nungambakkam India Network and Infrastructure Management Faculty of Engineering and Technology Botho University Gaborone Botswana School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India Department of Electronics and Communication Engineering Kumaraguru College of Technology Coimbatore India

For clinical analysis or medical intrusion, imaging technology is a potent tool for producing visual images of a body's inside. However, several existing methods include restricted access to high-quality and diverse datasets, overfitting, a lack of interpretability, high computational costs, varying medical imaging data, and ethical issues concerning patient privacy, consent, and bias. To overcome these issues, the effectiveness of generative adversarial networks in denoising medical imaging (CT/MRI images) is proposed. The input CT images are first gathered and preprocessed to reduce undesired noise using Altered Phase Preserving Dynamic Range Compression (APPDRC). The General Adversarial Network (GAN) is then given these preprocessed images to cope with the noisy areas of CT/MRI while also complying with maintaining image structures such as boundary details while preventing over-smoothing, and the weight parameters for the GAN are optimized using the Golden Eagle Optimization (GEO) technique. General Adversarial Network (GAN) has piqued the interest of academics studying medical image-denoising mechanisms and developing sophisticated medical image-denoising algorithms based on deep learning. In light of reducing the difficulty in feature learning and improving final diagnosis accuracy, data preprocessing is necessary and crucial in gan-based medical image denoising methods. This work focuses on GAN-based effective denoising approaches in CT/MRI. The potential challenges and research objectives are in the context of data preprocessing in medical image denoising. Because of how CT/MRI images are acquired, it was observed that noise in CT/MRI data follows the distribution. Generative Adversarial Networks (GANs) for denoising medical imaging, mainly CT and MRI images, have yielded promising results of 99% accuracy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Feature selection using modified chaotic satin bowerbird algorithm with deep transfer learning for Multispectral Image Classification

引用

International Journal of Information Technology (Singapore) 2024年 1-13页

作者： Rajakani, M. Kavitha, R.J. Rajesh, S. Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India Department of Electronics and Communication Engineering University College of Engineering Panruti Panruti 607106 India Department of Information Technology Mepco Schlenk Engineering College Sivakasi India

Multispectral image classification has received significant attention among research communities and academicians. Recently, several artificial intelligence (AI) models can be used for the extraction of prominent features. Besides, deep learning (DL) methods become more familiar and gained interest in the remote sensing community for the classification of multispectral and hyperspectral images. With this motivation, this paper presents an optimized feature learning with deep transfer learning enabled multispectral image classification (OFLDTL-MSIC) technique. The proposed OFLDTL-MSIC technique aims to categorize the different class labels of the multispectral images. Besides, the OFLDTL-MSIC technique applies multi-level discrete wavelet transform (DWT) based image decomposition technique. Moreover, the EfficientNet technique is applied as a feature extractor to generate a collection of features. Furthermore, selecting optimal features extracted by a EfficientNet involves identifying and retaining the most relevant and informative features The improved chaotic satin bowerbird optimization (CSBO) algorithm which uses dynamic population size is proposed for feature selection and kernel extreme learning machine (KELM) model is applied for the classification process. In order to ensure the enhanced performance of the OFLTDL-MSIC technique, a wide range of simulations take place using the Madurai LISS IV multispectral images and the results are examined under several aspects. The extensive comparative study highlighted the better performance of the OFLTDL-MSIC technique over the recent methods. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Deep learning Image classification Multispectral images Parameter tuning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Agricultural Water Conservation through AI-Enhanced Solar IoT Networks 3

Agricultural Water Conservation through AI-Enhanced Solar Io...

引用

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

作者： Maniraj, S.P. Monisha, J. Amutha, R. Kavitha, R. Shriidhar, P.J. Srinivasan, C. Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur Tamilnadu Chennai India Tamil Nadu Chennai India Ultra College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vinayaka Missions Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha Universityi Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

With the increasing water shortage and climatic uncertainty, creative strategies for effective water management in agriculture are necessary. This research investigates the integration of Artificial Intelligence (AI), particularly Artificial Neural Networks (ANN), with solar-powered Internet of Things (IoT) networks to enhance water utilization in agricultural activities. The proposed system facilitates accurate irrigation scheduling using real-time data from soil moisture sensors, meteorological stations, and crop health monitoring devices. The ANN model analyses this data to predict ideal irrigation schedules and volumes, minimizing water waste while improving crop yields. The solar-powered IoT framework provides sustainability and reduces dependence on traditional energy sources. Field trials indicate that the AI-enhanced system may promote water saving by as much as 30% relative to traditional irrigation techniques. Moreover, using AI enables adaptive learning, enabling the system to enhance its irrigation tactics using historical and real-time data. This novel method conserves water resources and fosters sustainable agriculture practices, coinciding with global initiatives to address water shortages and assure food security. The findings underscore the potential of technology-based solutions to revolutionize agricultural water management for a sustainable future. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Brain Tumor Detection Scheme using a Hybrid Deep Learning Model 2

An Enhanced Brain Tumor Detection Scheme using a Hybrid Deep...

引用

2nd International Conference on Electronics and Renewable systems, ICEARS 2023

作者： Dharshini, S. Geetha, S. Arya, S. Mekala, N. Reshma, R. Sasirekha, S.P. Karpagam Academy of Higher Education Faculty of Engineering Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350346640

Brain tumor detection using machine learning techniques seems to be a promising approach to improve the accuracy and efficiency of the diagnosis process. This research proposes a hybrid brain tumor detection scheme using convolutional neural networks (CNN) and BAT algorithms. This method involves the use of medical imaging, such as magnetic resonance imaging (MRI) or computed tomography (CT) scans, to detect and classify brain tumors. The removal of the past and its negative repercussions from diverse pixy units causes age extraction. By mapping the contour and c-label of the tumor and its limitations, we can acquire information about the tumor that could aid in diagnosis. This approach may be used to identify the tumor's size, shape, and function. The clinical team and the patient can detect the significance of the tumor by using different color labeling different levels of elevation. The clinical workforce can send data to a graphical user interface for the shape and limitations of the tumor. The CNN is trained to identify patterns and features in the images that are indicative of a tumor, while the bat algorithm is used to optimize the parameters of the CNN for improved performance. This approach has the potential to increase the accuracy and speed of brain tumor diagnosis. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing

引用

computers, Materials & Continua 2023年第6期75卷 5597-5613页

作者： V.Banupriya S.Anusuya Department of Computer Science and Business Systems M.Kumarasamy College of EngineeringKarur639113TamilnaduIndia Department of Information Technology Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSIMATSChennai602117Tamil NaduIndia

In the modern world,one of the most severe eye infections brought on by diabetes is known as diabetic retinopathy(DR),which will result in retinal damage,and,thus,lead to *** retinopathy(DR)can be well treated with early *** fundus images of humans are used to screen for lesions in the ***,detecting DR in the early stages is challenging due to the minimal ***,the occurrence of diseases linked to vascular anomalies brought on by DR aids in diagnosing the ***,the resources required for manually identifying the lesions are ***,training for Convolutional Neural Networks(CNN)is more *** proposed research aims to improve diabetic retinopathy diagnosis by developing an enhanced deep learning model(EDLM)for timely DR identification that is potentially more accurate than existing CNN-based *** proposed model will detect various lesions from retinal images in the early ***,characteristics are retrieved from the retinal fundus picture and put into the EDLM for *** dimensionality reduction,EDLM is ***,the classification and feature extraction processes are optimized using the stochastic gradient descent(SGD)*** EDLM’s effectiveness is assessed on the KAG-GLE dataset with 3459 retinal images,and results are compared over VGG16,VGG19,RESNET18,RESNET34,and *** results show that the EDLM achieves higher average sensitivity by 8.28%for VGG16,by 7.03%for VGG19,by 5.58%for ResNet18,by 4.26%for ResNet 34,and by 2.04%for ResNet 50,respectively.

关键词： Diabetic retinopathy deep learning classification retinal fundus

来源：评论

学校读者我要写书评

暂无评论

Alginate Hydrogel Microbeads With Different Mesh Structures Enable Controlled Release Of Adeno-Associated Virus For Gene Therapy 22

Alginate Hydrogel Microbeads With Different Mesh Structures ...

引用

22nd International Conference on Solid-State Sensors, Actuators and Microsystems, Transducers 2023

作者： Hioki, Aiki Takatsuka, Shuhei Kurashina, Yuta Onoe, Hiroaki Keio University Faculty Of Science And Technology Department Of Mechanical Engineering Kanagawa Japan Tokyo University Of Agriculture And Technology Faculty Of Engineering Department Of Mechanical Systems Engineering Tokyo Japan

ISBN: (纸本)9784886864352

This paper proposes the control of adeno-associated virus (AAV) release from calcium alginate hydrogel (Ca-Alg.) microbeads with different mesh structures. We found that Ca-Alg. with many cross-linking points have smaller mesh structures than those of normal Ca-Alg. This difference enabled the controlled release of AAV from Ca-Alg. according to the mesh size that can physically trap the AAV particles (~20 nm). As the carriers of AAV, Ca-Alg. microbeads using different mesh structures were fabricated and evaluated the release of AAV. In addition, Janus shaped Ca-Alg. microbeads (Janus microbeads) with different mesh structures between hemispheres were demonstrated to design the precisely controlled AAV release. Controlled release of AAV from Ca-Alg. microbeads with optimized mesh structures could be a biocompatible release system for gene therapy. © 2023 IEEJ.

关键词： AAV Ca-Alg. microbeads Gene therapy Janus microbeads M/G-ratio Mesh structures

来源：评论

学校读者我要写书评

暂无评论

A Study on Artificial Intelligence-based Natural Language Processing for Online Shopping Services 6

A Study on Artificial Intelligence-based Natural Language Pr...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Parthipan, N. Ramar, K. Prasath, Ragu S. Santhosh, R. Reshma, R. Department of Computer Science and Engineering Faculty of Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore India

ISBN: (纸本)9798350398496

As a result of the developments in the digital age, communication has become the primary route for modern business. Business discussions, profiles, seminars, transactions, and agreements were all conducted in person in the past, but today practically everything is done digitally. The goal of this work is to investigate how text-object connections made by artificial intelligence help NLP and AI better meet human requirements. Additionally, this work considers how modern applications like NLP and AI integrated with IoT services have altered online shopping environments. Online shopping service providers have created sophisticated NLP systems that take human demands and instantaneously satisfy them through text, phone conversations, smart records, and chatbots as communication takes centerstage in the commercial environment. This work modeled the artificial intelligence-based natural language processing framework for online shopping services and evaluated using support vector machine (SVM) classification algorithm and a hybrid Naive Bayes - Hidden Markov model (NB-HMM) algorithm. The experimental analysis shows the better performance when the model use SVM for classification over NB-HMM with the average accuracy of 94.3% and F-score of 97.5%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach in Garbage Collection and Monitoring with IoT Sensors 6

A Machine Learning Approach in Garbage Collection and Monito...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Dhanushya, S. Chitra, K. Swetha, S. Tharageswari, K. Department of Computer Science and Engineering Faculty of Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore India

ISBN: (纸本)9798350398496

The greatest challenge people face today is garbage management and disposal. As the world is driven by technology, there are still small villages in India where waste is still disposedmanually by humans. As humans remove waste, it is frequently seen spilled in unexpected places, causing health problems and spreading deadly diseases. All of this occurs due to a lack of information about waste management anda lack of communication with those involved in the process. By considering this fact, waste management can be accomplished efficiently by segregating garbage and using it to produce compost. This research study has proposed a smart waste management system by integrating IoT sensors by checking the level of the bin used, sending GPS signals to the municipality and giving alert message to the authority in case if there is any production of poisonous gas from the garbage bin. The proposed method is a sustainable andreliable waste disposal and management methoddeployedin the state. The data collection for the proposed system can be leveraged to further plan the most efficient ways to lower waste mishandling and ensure a clean environment. In order to perform this process, machine learning algorithm is incorporated in the data testing and training process to get higher accuracy. The method adopted can also be used for monitoring and segregating the waste in future. © 2023 IEEE.

关键词： Bins

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：