检索结果-内蒙古大学图书馆

4th International Conference on Expert Clouds and applications, ICOECA 2024

作者： Hebri, Dheeraj Kirubakaran, S. Jasmine, R. Rajitha Poosamooper, Anitha Devi, S. Rukmani Joseph, D Raja Srinivas Institute of Technology Department of Master of Computer Applications Karnataka Valachil Mangalore574143 India CMR College of Engineering and Technology Department of Computer Science Engineering Telangana Hyderabad501401 India R.M.K. Engineering College Department of Information Technology Tamil Nadu Kavaraipettai Thiruvallur601206 India Vel Tech Ranga Sanku Arts College Department of Computer Applications Tamil Nadu Chennai600062 India Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Department of Computer Science Tamil Nadu Chennai600124 India School of Aeronautical Sciences Hindustan Institute of Technology and Science Padur Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350385793

Remote sensing is concerned with high-resolution geographical data. Its applications include farming, water resources, ecology, forests, deserts, marine applications, soil types, disaster alerts, and management. To extract the necessary information from satellite images, considerable image processing is required. Image segmentation and categorization into land cover categories is an important stage in satellite image processing. This article describes a method for categorizing and detecting different forms of land cover from satellite data. In this study, we examine satellite images for historical map classification using machine learning algorithms. We acquire Landsat images to complete this tedious task. The images are carefully labeled using the ArcMap software. We categorize areas into five types: forest, building, water, barren, and agricultural land. The images are then sent to the Convolutional Neural Network (CNN) Model for feature extraction. The retrieved features were then exposed to three Machine Learning (ML) models: Support Vector Machine (SVM), Naive Bayes (NB), and Decision Tree (DT). Standard classification measures are used to analyze the outcomes of all three models. When compared to the other two models in satellite image classification, CNN feature extraction with SVM classifier achieves the greatest accuracy of 95%. © 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

State of the Art Review: Revolution in Farming with Assistance from Smart Internet of Things Based System 5

State of the Art Review: Revolution in Farming with Assistan...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Dubey, Nilesh Jayswal, Hardik Patel, Atul Goyal, Dinesh Department of Computer Science and Engineering Devang Patel Institute of Advance Technology and Research FTE CHARUSAT University India IT Department Devang Patel Institute of Advance Technology and Research FTE CHARUSAT University India Faculty of Computer Science and Applications Charusat University Changa Gujarat Anand India Computer Science and Engineering Poornima Institute of Engineering and Technology Rajasthan Jaipur India

ISBN: (纸本)9798400709418

Nowadays, IoT is impacting day-to-day lifestyles by making everything smart. Agriculture is the backbone of the economy of every country. In the past, farmers used to examine soil, weather, and crops using traditional methods, but with the smart innovative sensors and the help of IoT, this type of work can be easily done without any human efforts. The IoT-based smart agriculture system can be operated from anywhere by using networking technologies. This paper presents a survey of IoT technologies and applications in the agriculture sector. The survey article presents different research works in this domain, including applications, tools, and technologies, as well as approaches implemented in the field of agriculture using IoT. Furthermore, it discusses the major obstacles and challenges faced in the field of agriculture. Lastly, open challenges have been presented to assist researchers with possible solutions. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Approaches to Securing Multi-Cloud Architectures: Best Practices and Emerging Solutions 7

Comprehensive Approaches to Securing Multi-Cloud Architectur...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Nair, Raveena R Sreevidya, D. Mohan, Chinnem Rama Banerjee, Joydeep Chouhan, Kuldeep Dharamvir Saveetha School of Law Chennai India and Ai & Ds Hyderabad India Narayana Engineering College Nellore Department of Computer Science and Engineering Andhra Pradesh India Nshm Knowledge Campus Durgapur West Bengal Kolkata India Sharda School of Engineering and Technology Department of Computer Science Applications Uttar Pradesh Greater Noida India The Oxford College of Engineering Department of Mca Bommanahalli Karnataka Bengaluru India

ISBN: (纸本)9798350350067

With an emphasis on multi-cloud networks, this research paper offers a synopsis of cloud computing techniques. It covers the fundamentals of cloud programming, the difficulties that cloud computing faces, and the ways that multi-cloud systems, such as cloud hybridization, federation clouds, cross-clouds, and multi-clouds, might help solve these problems. The opportunity of multi-cloud structures in combination with modern technologies such as Big Data and also Machine Learning (ML) is explored as well in the study, leading to some fascinating breakthroughs. To assist researchers, grasp the difficulties and generate enthusiasm within the community for the upcoming pairing of multi-cloud services with additional cutting-edge technologies, the aim is to present a contemporary perspective on multi-cloud technology and solve outstanding concerns. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

FedEnv-Net: Federated Neural Network for Decentralized Health Risk Prediction in Dynamic Urban Environments

FedEnv-Net: Federated Neural Network for Decentralized Healt...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Priyadharshini, M. Murugesh, V. Chowdhury, Subrata Dash, Bibhuti Bhsan Chandra De, Utpal Patra, Sudhansu Shekhar Department of Computer Science and Engineering Hyderabad501 203 India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India Sreenivasa Institute of Technology and Management Studies Department of Cse Anthra Pradesh Chittoor India Deemed to Be University School of Computer Applications Odisha Bhubaneswar India

ISBN: (纸本)9798331508685

The predictions of health risks in urban settings are constrained by factors such as pollution and temperature which change over time. Centralized models have problems with privacy and scalability that often do not allow implementing solutions in real-world large, and distributed systems. To this end, we introduce the FedEnv-Net which is a federated neural network to predict health risk in a decentralized manner. Using federated learning, FedEnv-Net train's models directly on edge devices, where data is trained and only updates are shared. Dynamics of temporal patterns and features are predicted by LSTM branch and Dense branch respectively in the model. A Meta-Learner merges such branches for prediction and a tuned loss function for conservative health risk estimations. Although it ensures privacy of data, FedEnv-Net yields an R2 score of 0.92 and an MAE of 0.14, which determines its predictive capability. Future work includes increasing the efficiency of the communication between the system components, broadening the number of input data sources and improving the level of privacy to make FedEnv-Net a versatile, privacy-preserving solution for real-time health risk assessment. © 2025 IEEE.

关键词： Decentralized Model Federated Learning Health Risk Prediction LSTM Privacy-Preserving Real-Time Monitoring Urban Health

来源：评论

学校读者我要写书评

暂无评论

Evaluating Multi-Platform IoT Solution for Agricultural Monitoring 2

Evaluating Multi-Platform IoT Solution for Agricultural Moni...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Sharma, Sumit Kumar Saraswat, Birendra Kumar Sharma, Kamal Saraswat, Manish Sharma, Tarun Kumar Ajay Kumar Garg Engineering College Department of Information Technology UP Ghaziabad India Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Gla University Department of Mechanical Engineering UP Mathura India Lloyd Institute of Engineering & Technology Department of Mechanical Engineering UP Greater Noida India Abes Engineering College Department of Computer Applications UP Ghaziabad India

ISBN: (纸本)9798350371055

This paper offers a multi-platform Iota answer designed for agricultural tracking. The proposed architecture makes use of three core technologies: low-electricity sensors to acquire environmental data, cloud-based analytics to offer insights into the statistics and a software layer for customers to view and interact with the amassed records. The gadget evaluated the usage of a dataset gathered in real-time from soil moisture and photosynthetic mild distribution sensors. The amassed facts were processed in an actual-time analytics engine, which generated histograms, indicators, and standing messages indicating the situations of the monitored surroundings. The results show that the proposed multi-platform answer finished at a first-class level of accuracy in monitoring the agricultural environment. Additionally, the results reveal that the gadget is able to efficaciously detect early modifications in environmental conditions even using minimum assets. The proposed solution offers an effective and reliable platform for agricultural tracking that can be without difficulty custom-designed and scaled to any size of operation. © 2024 IEEE.

关键词： Accuracy Architecture Conditions Distribution Environmental

来源：评论

学校读者我要写书评

暂无评论

Enhancing Remote Sensing Image Classification using Arithmetic Optimization Algorithm with Deep Learning Approach 2

Enhancing Remote Sensing Image Classification using Arithmet...

引用

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

作者： Shanthi, R. Balasubramaniam, D. Venkatesh, R. Sankari, C. Manimaran, V. Basha, Shaik Hedayath Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Chengalpattu Tamilnadu Kattankulathur603203 India Department of Biomedical Engineering Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Chennai India Ramco Institute of Technology Rajapalayam India Chennai Institute of Technology India Department of Computer Science and Engineering Kongu Engineering College Perundurai Tamilnadu Erode638060 India Department of ECE R.M.K. College of Engineering and Technology India

ISBN: (纸本)9798350383867

The classification of Remote sensing image (RSI)is a vital task in field of geospatial analysis where aerial or satellite images are classified into predefined classes or land cover sorts. It plays a main part in diverse fields namely agriculture, disaster management, environmental surveillance, urban planning, and natural resource management. With the machine learning (ML) and deep learning (DL) models, these images examined and categorized depending on their spatial, spectral and temporal features. The exact detection of remote sensing images simplifies decision-making procedures, aiding governments, environmental agencies, and companies to make knowledgeable decisions and policies. It authorizes experts to observe variations in lands, discover land use trends, and evaluate environmental effects and making it a vital device in addressing present difficult challenges connected to weather change, urban development, and natural resource protection. This study presents an enhanced remote sensing image classification utilizing arithmetic optimization algorithm with DL (ERSC-AODL) Approach. The ERSC-AODL technique concentrates on the accurate recognition of the RSI into dissimilar classes. It begins with the use of an EfficientNet feature extractor, which derives complex spectral and spatial data, and acts as a base of proper representation of the images. Moreover, the recognition process takes place by a bidirectional long short-term memory (BiLSTM). Finally, the hyperparameter optimization procedure is performed by the ERSC-AODL technique. To portray the proficient classification outputs of the ERSC-AODL technique, a range of experiments were utilized. The investigational outputs stated that the ERSC-AODL technique attains improved accomplishment over other models. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning-Based Hand Gesture Recognition Using HCI on IoT Assisted Cloud Platform

引用

computer Systems science & engineering 2023年第8期46卷 2123-2140页

作者： Saurabh Adhikari Tushar Kanti Gangopadhayay Souvik Pal D.Akila Mamoona Humayun Majed Alfayad N.Z.Jhanjhi School of Engineering Swami Vivekananda UniversityIndia Department of Computer Science and Engineering Sister Nivedita University(Techno India Group)KolkataWest BengalIndia Sambalpur University SambalpurIndia Department of Computer Applications Saveetha College of Liberal Arts and SciencesSIMATS Deemed to be UniversityChennaiIndia Department of Information Systems College of Computer and Information SciencesJouf UniversityKSA College of Computer and Information Sciences Jouf UniversitySakaka72341Saudi Arabia School of Computer Science(SCS) Taylor’s UniversitySubang Jaya47500Malaysia

Machine learning is a technique for analyzing data that aids the construction of mathematical *** of the growth of the Internet of Things(IoT)and wearable sensor devices,gesture interfaces are becoming a more natural and expedient human-machine interaction *** type of artificial intelligence that requires minimal or no direct human intervention in decision-making is predicated on the ability of intelligent systems to self-train and detect *** rise of touch-free applications and the number of deaf people have increased the significance of hand gesture *** applications of hand gesture recognition research span from online gaming to surgical *** location of the hands,the alignment of the fingers,and the hand-to-body posture are the fundamental components of hierarchical emotions in *** gestures may be difficult to distinguish from nonsensical motions in the field of gesture *** gestures may be difficult to distinguish from nonsensical motions in the field of gesture *** this scenario,it may be difficult to overcome segmentation uncertainty caused by accidental hand motions or *** a user performs the same dynamic gesture,the hand shapes and speeds of each user,as well as those often generated by the same user,vary.A machine-learning-based Gesture Recognition Framework(ML-GRF)for recognizing the beginning and end of a gesture sequence in a continuous stream of data is suggested to solve the problem of distinguishing between meaningful dynamic gestures and scattered *** have recommended using a similarity matching-based gesture classification approach to reduce the overall computing cost associated with identifying actions,and we have shown how an efficient feature extraction method can be used to reduce the thousands of single gesture information to four binary digit gesture *** findings from the simulation support the accuracy,precision,gesture

关键词： Machine learning gesture recognition framework accuracy rate precision rate gesture recognition rate sensitivity rate efficiency rate

来源：评论

学校读者我要写书评

暂无评论

Novel Audio Mosaic Using LPC-Coefficient and Excitation-Codeword Permutations

引用

IEEE Signal Processing Letters 2024年 31卷 1690-1694页

作者： Tsai, Morris C.-H. Wu, Hsiao-Chun Huang, Scott C.-H. Chang, Shih Yu National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Taoyuan City32003 Taiwan San Jose State University Department of Applied Data Science San JoseCA95192 United States

In this letter, a novel light-weight audio mosaic scheme using permutations of linear predictive coding (LPC) coefficients as LPC has been widely adopted in many audio codecs (coder-encoders) nowadays. We establish the theoretical secrecy analysis with respect to the degree of the original LPC polynomial and the minimum-phase population of permuted LPC polynomials. The mosaic (destructuring) performance in terms of DCT-KLD (Kullback-Leibler divergence of discrete cosine transform) is also evaluated through simulations. In comparison with the existing audio-mosaic method using waveform permutations, our proposed new audio-mosaic scheme using LPC-coefficient permutations can achieve a much better mosaic performance (a much higher DCT-KLD) subject to the same key size. © 1994-2012 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

INTERPRETABLE AUTOMATED LEARNING: EVOLVING FUZZY NETWORKS TO EXPLICIT applications OF AI

INTERPRETABLE AUTOMATED LEARNING: EVOLVING FUZZY NETWORKS TO...

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Rathi, Vikas Vijayalakshmi, V.J. Mahesh, Bhandari Ninoria, Shalini Gupta, Ankur Kumar Premananthan, G. Department of Computer Science & Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Department of Electrical And Electronics Engineering Karpagam Academy of Higher Education Coimbatore641021 India Vishwakarma Institute of Information Technology Pune India CCSIT TMU India School of Computer Science and Applications IIMT University Meerut India Department of Electronics and Communication Engineering Karpagam College of Engineering Coimbatore6410 India

ISBN: (纸本)9798350355338

One of the biggest developments in intelligent machines has been the development of evolving fuzzification. They are flexible system designs created using evolving methods. Fluid simulation now has excellent capabilities to use in a variety of data scientific situations as a result of this combination. The goal with this addition is to create a policy document that provides a thorough study of the evolving hazy ecosystems field of study. In order to comprehend the present setting of this subject and its importance, queries are asked and answered with some of this goal in mind. It will be made clear why evolving neural nets are significant from an explicable perspective, even before they started, how much they are utilized for, and where scholars should devote themselves in this field going forward. People must really be crucial to the developing field of data-driven schooling. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Seg-UResNet: A Deep Hybrid Convolutional Neural Network of Road Scenes for semantic segmentation

Seg-UResNet: A Deep Hybrid Convolutional Neural Network of R...

引用

2024 International Conference on Circuit, Systems and Communication, ICCSC 2024

作者： Faska, Zahra Khrissi, Lahbib Haddouch, Khalid El Akkad, Nabil Sidi Mohamed Ben Abdellah University Laboratory of Engineering Systems and Applications Ensa Fez Morocco Sidi Mohamed Ben Abdellah University Lisac Department of Computer Science Fsdm Fez Morocco

ISBN: (纸本)9798350365306

Comprehending the circumstances is an essential element of every autonomous driving system. computer vision harbors the task of semantic segmentation as one of its core components wherein each pixel in an image is labeled with precise labels. The task has found significant applications in areas like autonomous driving plus analysis of images and videos, not to mention medical imaging and scene understanding. The progress made in semantic segmentation through the utilization of deep learning techniques has been truly extraordinary. Our study introduces a groundbreaking approach known as hybrid evolutionary weighted ensemble, which combines the strengths of two deep models. Two distinct segmentation models will be developed using U-Net and ResNet34 as the decoder and the encoder respectively for the first model using transfer learning technique, we are able to create individual segmentation models. Additionally, we consider SegNet another highly regarded convolutional neural network for image segmentation as our second deep model. With the goal of enhancing the accuracy of the deep learning model, we propose an evolutionary leap towards the convergence of the DL model accuracy will be achieved through the introduction of a hybrid weighted ensemble model. This shall be done by combining ResNet34, an individual U-Net-based DTL model, with SegNet model and then executing fine-tuning. To assess the effectiveness of the hybrid network, we conducted an evaluation using the widely recognized and demanding CamVid dataset. Through our experiments, we were able to showcase that the hybrid network outperforms other popular semantic segmentation algorithms by a significant margin, solidifying its position as a cutting-edge solution. © 2024 IEEE.

关键词： Semantic Segmentation

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：