检索结果-内蒙古大学图书馆

6th international Conference on Energy, Power and Environment, iCEPE 2024

作者： Varadarajan, Mageshkumar Naarayanasamy Vinya, Viyyapu Lokeshwari Prabhu, R. Jenin swathi, G. Mohankumar, N. Velmurugan, s. Capital One Tamil Nadu Chennai India Vardhaman College of Engineering Department of Computer Science and Engineering Telangana Ranga Reddy India Vel Tech Multi Tech Dr. Rangarajan Dr. Sakundhala Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Cmr Technical Campus Department of Computer Science and Engineering Telangana Hyderabad India Maharashtra Nagpur India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350379297

this research introduces an innovative approach to water conservation and personalized consumption management by combining internet of things (iot) sensors with Deep Reinforcement Learning (DRL) methods. the suggested approach aims to give people more control over their water use in response to water shortages and the need for sustainable resource management. it installs i.t.sensors on taps to track water use in real time. A DRL framework is fed data that these sensors have collected. the DRL algorithm develops individual consumption profiles for each user by factoring in past water use, environmental conditions, and personal tastes. Using this unique profile, water efficiency may be improved instantly. Users may easily enter their water conservation choices, budgets, and the system's user interface. Adjusting the water's flow rate by the user profiles learned by the DRL actively regulates water use while keeping people happy. the results of the experiments reveal that our method effectively reduces both water use and waste. integrating i.t.sensors with DRL methods provides a flexible and scalable answer for smart water management that economically benefits the environment and consumers. © 2024 iEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of an efficient deep Learning Model for segmentation and Classification of Psoriasis and Vitiligo skin diseases

Design of an efficient deep Learning Model for Segmentation ...

引用

2023 international Conference on Advances in Computation, Communication and information technology, iCAiCCit 2023

作者： Reddy, Dasari Anantha shambharkar, saroj Chaudhari, Dipti Jyothsna, Kandi somkunwar, Rachna K. srinish Reddy, Amireddy Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Telangana Hyderabad500075 India K.I.T.S. Ramtek Department of Information Technology Nagpur India Pimpri Chichwad College of Engineering and Research Department of Computer Engineering Pune Ravet India Mlrit Department of Computer Science and Engineering Hyderabad Dundigal India Dr. D. Y. Patil Institute of Technology Department of Computer Engineering Pune Pimpri India Cmrit Department of Computer Science and Engineering Hyderabad Telangana Kandlakoya India

ISBN: (纸本)9798350344387

skin diseases such as psoriasis and vitiligo can greatly impact a patient's quality of life. For correct diagnosis and therapy planning, it is crucial to accurately segment and classify various skin disorders. Existing segmentation & classification models for identification of skin diseases either have low efficiency or have higher complexity when used for clinical scenarios. in order to address these problems, we provide a deep learning model in this study that can automatically separate and categorize vitiligo and psoriasis skin lesions from clinical photos. the suggested model is built on a Convolutional Neural Network (CNN) architecture that has been specifically designed for use in medical image processing applications. initially, all the collected images are augmented via scale, rotate, width shift, height shift, shear and zoom operations. in proposed approach, train the model on this augmented dataset of clinical images for psoriasis and vitiligo lesions via transfer Learning based ResNet50 CNN, and evaluate its performance using various metrics such as accuracy, precision, recall, and F1-scores. Proposed approach results show that the proposed model achieves high accuracy in both segmentation and classification tasks. the proposed deep learning model can assist dermatologists and medical professionals in accurately diagnosing and treating skin diseases, potentially leading to better patient outcomes. © 2023 iEEE.

关键词： Classification CNN Disease Learning scenarios ResNet50 segmentation skin transfer

来源：评论

学校读者我要写书评

暂无评论

Novel and Robust Energy Efficient Protocol for Authentication Purpose in iiot

Novel and Robust Energy Efficient Protocol for Authenticatio...

引用

2023 iEEE international Conference on Research Methodologies in Knowledge Management, Artificial intelligence and telecommunication engineering, RMKMAtE 2023

作者： Kirubakaran, D. Velmurugan, s. Rekha, R. sasirekha saravanan, s. Panurangan, Raji Department of Computer Science and Engineering R.M.K. Engineering College Tamil Nadu Chennai India Department of Electronics and Communication Engineering T J S Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Panimalar Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Tamil Nadu Chennai600127 India Department of Artificial Intelligence and Data Science Engineering Jeppiaar Institute of Technology Tamil Nadu Chennai India Saveetha Engineering College Department of Electronics and Communication Engineering Saveetha Nagar Thandalam Tamil Nadu Chennai India

ISBN: (纸本)9798350305708

An developing technology called the internet of things (iot) is anticipated to offer answers for several industrial industries. Wireless sensor networks (WsNs), a foundational iot technology, may be utilized to gather the necessary environmental characteristics for certain applications. security in WsN has grown to be a huge concern as a result of the sensor node's resource limitations and the wireless channel's open nature. to ensure the legitimacy of data access in WsN, authentication may be utilized as a fundamental security function. For various security needs, Chang and Le have presented two authentication techniques for WsN. However, their protocol has significant security and functionality flaws and is unable to provide appropriate mutual authentication. to address the shortcomings of earlier methods, we introduce a three-factor user authentication scheme for WsN. the proposed protocol's security is examined, and its performance, functionality, and security are contrasted with those of other relevant protocols. the comparison and simulation findings by Ns-3 demonstrate how reliable and resource-efficient the suggested protocol is for iot applications. © 2023 iEEE.

关键词： energy efficient internet of things Packet Delivery Ratio Public Key infrastructure Wireless sensor Networks

来源：评论

学校读者我要写书评

暂无评论

Reliability of i.t.systems for Fire Detection 16

Reliability of IoT Systems for Fire Detection

引用

16th international Conference on ENtERprise information systems, CENtERis 2024 - 12th international Conference on Project MANagement, ProjMAN 2024 - 14th international Conference on Health and social Care information systems and technologies, HCist 2024

作者： singh, Khushwant Yadav, Mohit Barak, Dheerdhwaj Moreira, Fernando Department of Computer Science & Engineering U.I.E.T Maharshi Dayanand University Rohtak124001 India Department of Mathematics University Institute of Sciences Chandigarh University Punjab Mohali140413 India Department of Computer Science & Engineering Vaish College of Engineering Rohtak124001 India REMIT IJP Universidade Portucalense Porto & IEETA Universidade de Aveiro Aveiro Portugal

in this paper, a smart i.t.system including the software and hardware aspects of its design, as well as its operation in the context of a city or a building, along with its advantages, disadvantages, and potential applications, all with a focus on fire safety have been analyzed. Based on the results of the aforementioned research, it is clear that an iot-based fire system may be tailored to the specific requirements of each individual situation. the major focus of the study is on the planning and evaluation of a WsN that can detect house fires in their earliest stages. the authors address the crucial issue of giving rapid-fire alerts by including a broad range of sensors in the wireless sensor network. in order to provide precise, real-time fire detection, the wireless sensor network (WsN) is constructed from tiny, low-power sensor devices that have sensors able to sense their surroundings. Using the Global system for Mobile Communications (GsM) to reduce the number of false alarms is one strategy the authors propose for coping with sensor malfunctions. the reliability of iot (internet of things) systems for fire detection has been a topic of interest and continuous improvement. iot-based fire detection systems have the potential to offer numerous benefits, such as real-time monitoring, remote management, and data-driven insights. However, their reliability depends on several factors, including technology, implementation, and maintenance. this research aids in the enhancement of residential community safety by improving the early detection and prevention of house fires. © 2025 the Author(s).

关键词： Fire detectors

来源：评论

学校读者我要写书评

暂无评论

Design of a smart Energy Meter and Monitoring system for industrial and Residential Use Based on the internet of things

Design of a Smart Energy Meter and Monitoring System for Ind...

引用

2023 international Conference on system, Computation, Automation and Networking, iCsCAN 2023

作者： Moorthy, Vijai Meyyappan Muthukumaran Mansingh, Benson Manoj, Britto sateesh Kumar Reddy, C. Elango, Arul Vignan Foundation of Science Research and Technology Department of Advanced Computer Science and Engineering Andhra Pradesh Guntur India M. I. E. T. Engineering College Department of Electrical and Electronics Engineering Tamilnadu Trichy India

ISBN: (纸本)9798350315127

Electronic meters have become increasingly important for efficient energy use, and the proposed research aims to develop an iot-based architecture for metering and monitoring. this smart monitoring and control system (sMACs) for home appliances is suggested to enhance household electricity control. the technology uses a wireless control module with an EsP8266 microcontroller and Wi-Fi channel to monitor current consumption and send measured amounts over Wi-Fi. the system calculates current consumption, counts units, and displays results on the user's website and smartphone. it avoids using traditional analog and digital meter reading techniques and allows remote access to electronic meters. the proposed work offers lower total costs, greater energy savings, and reduced time and labour requirements. © 2023 iEEE.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

3D-MACNet: A Multiscale Asymetric Convolution Network for Feature Extraction and Classification of Hyperspectral images 4

3D-MACNet: A Multiscale Asymetric Convolution Network for Fe...

引用

4th iEEE international Conference on Computing, Communication, and intelligent systems, iCCCis 2023

作者： Kanthi, Murali Ravi Kumar, K.C. seelothu, sammaiah sudha Pavani, K. Bhaskar, Nuthanakanti sarma, t. Hitendra Telangana Hyderabad India Sridevi Women's Engineering College Department of Computer Science & Engineering Telangana Hyderabad India Maulana Azad Nation Urdu University P.G.T-Computer Science Telangana Hyderabad India Vasavi College of Engineering Department of Information Technology Telangana Hyderabad India

ISBN: (纸本)9798350306118

in recent years, deep learning's amazing feature extraction capabilities have led to its widespread adoption in hyperspectral image classification (Hsi) applications. However, traditional deep learning methods frequently produce inferior classification results because of the low discriminatory power of the retrieved features. Furthermore, a notable area of interest in research now involves the difficulty of achieving good classification performance in Hsis with a restricted number of samples. this letter offers a unique 3D multiscale asymmetric convolution network (3D-MACNet) for the extraction of features and Hsis classification to address this issue. By adapting the concept of symmetric convolution to the construction of an asymmetric convolution with three identical branches at distinct scales that can retrieve spatial-spectral characteristics from vertical, horizontal, and all perspectives. run on both the new data sets and the freely accessible standard data sets. the provided model has been proven to exceed the other cutting-edge approaches in regard to classification accuracy, according to empirical evidence. © 2023 iEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Predictions and Classification of Crop Diseases: A systematic Literature Review

SSRN

引用

ssRN 2025年

作者： singh, Mukesh Kumar singh, Natthan sharma, Vishnu Department of Computer Science & Engineering Dr. A.P.J. Abdul Kalam Technical University Lucknow India Department of Computer Science & Engineering I.E.T Lucknow India Department of Computer Science & Engineering I. T. S. Engineering College Greater Noida India

in agriculture, deep learning (DL) has applications in crop diseases detection, yield prediction, and weed identification. this study investigates the current state and future prospects of crop disease detection using deep learning. A systematic Literature Review (sLR) was conducted to gather and analyse the methodologies and features used in crop disease detection using deep learning research. We used an integrated approach to extract 1327 relevant research papers from four electronic databases. Of these, 113 articles were chosen for analysis using inclusion and exclusion criteria. We thoroughly examined these chosen studies, including the crops and diseases they caused, the methodologies, the evaluation parameter, the dataset, and our recommendations for more research. Based on a review of 113 articles including deep learning, our study shows that tomato and rice are the most frequently used crops for research, and that the most widely used deep learning algorithms are ResNet50, inception V3, AlexNet, DenseNet, VGG16, and Convolutional Neural Networks (CNNs). We carried out further work for the dataset and evaluation parameter. this further research indicates that the PlantVillage dataset is the most often used dataset in these experiments, and accuracy is the most commonly used deep learning method evaluation metrics. © 2025, the Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Healthcare Bots for Elderly Assistance Using Cloud-Driven Gradient Boosting Machines 4

Healthcare Bots for Elderly Assistance Using Cloud-Driven Gr...

引用

4th international Conference on innovative Practices in technology and Management, iCiPtM 2024

作者： sudha Juliet, P. sivakumar, s. thinakaran, K. srinivas, Porandla thamizhamuthu, R. Velmurugan, s. Meenakshi College of Engineering Department of Electronics and Instrumentation Engineering Tamil Nadu Chennai India Department of Computer Science Tamil Nadu Perambalur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Malla Reddy Institute of Engineering and Technology Department of Information Technology Telangana Hyderabad India Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350307757

As the world's population ages, there will be a greater need for creative methods to help the elderly maintain their independence and quality of life at home. this study investigates the feasibility of using healthcare bots powered by cloud-based Gradient Boosting Machines (GBM) to provide elderly people with individualized and timely support. the proposed system learns from each user's interactions and improves over time to better meet their specific requirements. Also, the cloud-based design ensures real-time updates and smooth interaction with different devices. Results show that the system is effective in improving the quality of geriatric support, promoting aging in place, and contributing to the creation of patient-centric healthcare solutions via a thorough review that includes user input and performance indicators. the results point to a potential direction for integrating Artificial intelligence (Ai), cloud computing, and healthcare to meet the issues of an aging population. © 2024 iEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Liver Cancer Detection using Neural Network Algorithm and Correlation Algorithm

A Comparative Analysis of Liver Cancer Detection using Neura...

引用

international Conference on Computational and Characterization techniques in engineering & sciences (CCtEs)

作者： Deepak srivastava Vibhor sharma Pramod Kumar Yogesh Kumar sharma Department of Computer Science & Engineering Himalayan School of Science & Technology Swami Rama Himalayan University Dehradun India Computer Science & Engineering I.T.S. Engineering College Graeter Noida India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

the fast development of machine learning and Ai in recent years has made it a widely used method. Because of its widespread use and effective pattern recognition and classification techniques, big institutions have begun funding research in the healthcare sector to boost the precision with which illnesses may be predicted. However, there are a number of difficulties in applying these methods. A significant barrier is the lack of a sufficient medical picture data set. this paper aims to provide a modest introduction to deep learning in medical image processing, including both the theoretical foundations and practical implementations of this technique. this thesis explores various major advances in computer science that contribute to the widespread appeal of deep learning (DL). this sheds light on the causes behind deep learning’s meteoric rise in numerous application fields, including medical image processing. the aim was to deploy new methodologies on existing cancer datasets to see if machine learning and deep learning algorithms might be used for the detection of cancer. the purpose of this study was to classify cancer using many text and picture datasets. Liver BUPA disease database is the dataset that is processed using various machine learning and deep learning models. in this paper, we provide optimization algorithms that outperform the existing strategies in terms of efficiency.

关键词： Deep learning training Liver cancer Machine learning algorithms Correlation Neural networks Liver Medical services Classification algorithms Biomedical image processing

来源：评论

学校读者我要写书评

暂无评论

image cyberbullying detection and recognition using transfer deep machine learning

引用

international Journal of Cognitive Computing in engineering 2024年第1期5卷 14-26页

作者： Almomani, Ammar Nahar, Khalid Alauthman, Mohammad Al-Betar, Mohammed Azmi Yaseen, Qussai Gupta, Brij B. School of Computing Skyline University College University City of Sharjah P.O. Box 1797 Sharjah United Arab Emirates I.T. department Al-Huson University College AlBalqa Applied University Irbid Jordan Computer Science Department Faculty of I.T. Yarmouk University Irbid Jordan Department of Information Security Faculty of Information Technology University of Petra Amman Jordan Ajman University Ajman United Arab Emirates Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Symbiosis International University Pune India Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Dehradun India

Cyberbullying detection on social media platforms is increasingly important, necessitating robust computational methods. Current approaches, while promising, have not fully leveraged the combined strengths of deep learning and traditional machine learning for enhanced performance. Moreover, online content complexity requires models that can capture nuanced contexts beyond text, which many current methods lack. this research proposes a novel hybrid approach using deep learning models as feature extractors and machine learning classifiers to improve cyberbullying detection. Extracting features using pre-trained deep learning models like inceptionV3, ResNet50, and VGG16, then feeding them into classifiers like Logistic Regression and support Vector Machines, enhances understanding of the complex contexts where cyberbullying occurs. Experiments on an image dataset showed that combining deep learning and machine learning achieved higher accuracy than using either approach alone. this novel framework bridges the gap in existing literature and contributes to broader efforts to combat cyberbullying through more nuanced, context-aware detection methods. the hybrid technique demonstrates the potential of blending deep learning's representation learning strengths with machine learning's sample efficiency and interpretability. © 2023

关键词： Learning systems

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：