检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Anguluri, Rajasekhar University of Maryland Department of Computer Science and Electrical Engineering Baltimore CountyMD85281 United States

ISBN: (纸本)9798350316339

Adversarial actions and a rapid climate change are disrupting operations of infrastructure networks (e.g., energy, water, and transportation systems). Unaddressed disruptions lead to system-wide shutdowns, emphasizing the need for quick and robust identification methods. One significant disruption arises from edge changes (addition or deletion) in networks. We present an 1-norm regularized least-squares framework to identify multiple but sparse edge changes using noisy data. We focus only on networks that obey equilibrium equations, as commonly observed in the above sectors. The presence or lack of edges in these networks is captured by the sparsity pattern of the weighted, symmetric Laplacian matrix, while noisy data are node injections and potentials. Our proposed framework systematically leverages the inherent structure within the Laplacian matrix, effectively avoiding overparameterization. We demonstrate the robustness and efficacy of the proposed approach through a series of representative examples, with a primary emphasis on power networks. © 2024 IEEE.

关键词： Laplace equation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Smart Agriculture: A Comprehensive Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2568-2588页

作者： Mahmood, M. Rezwanul Matin, Mohammad Abdul Goudos, Sotirios K. Karagiannidis, George North South University Department of Electrical and Computer Engineering Dhaka1229 Bangladesh Aristotle University of Thessaloniki ELEDIA@AUTH Department of Physics Thessaloniki54124 Greece Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki54124 Greece Cyber Security Systems and Applied AI Research Center Beirut1102 2801 Lebanon

As communication technologies and equipment evolve, smart assets become smarter. The agricultural industry is also evolving in line with the implementation of modern communication protocols, intelligent sensors, and equipment. This evolution is enabling large-scale agricultural production processes to operate independently, thus, securing the food supply chain for an ever-growing population. Data processing for such a system with multiple heterogeneous sources requires proper management for effective agricultural operations. Recognizing the advantages of machine learning (ML) in performing large-scale data processing, researchers are investigating the implementation of ML to design an effective intelligent agricultural architecture. The aim of this article is to provide a thorough analysis of the state-of-the-art in smart agriculture, open challenges, and guidelines for the development of further enhanced smart agriculture systems. Specifically, we describe how ML is used to create intelligent agricultural systems supported by state-of-the-art technology. © 2020 IEEE.

关键词： Weed control

来源：评论

学校读者我要写书评

暂无评论

Integration of Multiple Sensor-Based Wellness Systems for Supportive Housing Using Bluetooth Low Energy 6

Integration of Multiple Sensor-Based Wellness Systems for Su...

引用

6th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Poomdla, Suseela John, Joel Anil Kandregula, Pavan Kumar Murrieta, Rayleene George, Kiran Panangadan, Anand California State University Fullerton Computer Science Department Fullerton United States California State University Fullerton Electrical and Computer Engineering Department Fullerton United States

ISBN: (纸本)9798350396133

Residents in permanent supportive housing, defined as long-term, community-based housing combined with supportive services, often have health conditions requiring daily medication and monitoring for disabling incidents inside their home. Sensor-based solutions for checking for immobile residents, and automatic pill dispensers to ensure the timely delivery of medications are being developed to support living with health conditions. This work describes how multiple such health monitoring devices can be coordinated from a single user interface with communication over Bluetooth Low Energy (BLE). Individual subsystems, including an automatic pill dispenser and a smart wellness check, are designed for use within a supportive housing apartment unit. An Arduino RP2040 micro controller is used as each subsystem's central processing unit. The foundation of the communication between the different subsystems is the BLE protocol. BLE was chosen for its adaptability to heterogeneous devices and low power consumption. The BLE communication architecture links these devices, facilitating reliable data transfer and device-to-device coordination. An Android application running on a tablet PC acts as the central coordinator of all subsystems and provides a unified user interface. The application scans for BLE devices, connects to discovered subsystems, and displays real-time sensor information in a user-friendly format. Nearby peripheral devices are identified using BLE advertising and scanning. Bidirectional communication channels are created once linked, enabling the central device to communicate with the peripherals and receive data from them. This BLE architecture supports simultaneous communication with multiple peripherals. Different parameters of the BLE protocol are systematically varied;the parameters are the MTU size, time interval for BLE device scans, and the resulting number of GATT connections and disconnections under various time intervals. Fine tuning these parameters e

关键词： Dispensers

来源：评论

学校读者我要写书评

暂无评论

Multiple Major Ocular Disease Classification Using Deep Learning Methods: A Comprehensive Review 3

Multiple Major Ocular Disease Classification Using Deep Lear...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Tazoar, Md. Shafayat Jyoti, Oishi Goni, Md. Omaer Faruq Rahman, Md. Mahabubur Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350388282

Ocular diseases have become an important issue worldwide. Every year, various ocular diseases affect numerous individuals, leading to blindness for many. Despite seeking treatment in hospitals or from doctors, accurately diagnosing the disease remains a challenge. In numerous cases, the correct diagnosis is elusive and time-consuming, leading to unnecessary delays. This is why computer-aided diagnosis is necessary to swiftly diagnose the disease. However, most computer-Aided Diagnoses (CADs) are designed for single diagnoses. Therefore, there is a crucial need to develop CAD technology for detecting multiple ocular diseases. Many researchers are currently investigating this issue and developing various deep-learning models to find a solution. They have developed many techniques and models through which various types of ocular diseases can be diagnosed quickly and accurately. So far, the highest AUC score achieved is 99%. Reading all the literature on these techniques is time-consuming, so a literature review paper on this topic is necessary. In this review paper, the techniques from some important papers on this topic have been summarized. A critical analysis has been provided of all the papers, including their limitations and potential solutions. © 2024 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing-Based Ecosystem Monitoring and Disaster Management in Urban Environments Using Machine Learnings

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 319-327页

作者： Mohan, M. Macharla, Anila Parthasarathi, P. Sharan, Bediga Nageswaran, A. R. M, Balajee Department of Computer Science and Engineering SRM University Delhi-NCR Haryana Sonepat India Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology Telangana Hyderabad India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathy India School of Computer Science & amp Artificial Intelligence SR University Telangana Warangal India Department of CSE Tagore Engineering College Rathinamangalam Vandalur Chennai 600 127 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India

A key component of managing natural resources is the use and cover of the land. Maps of environmental changes are created using it in order to monitor ecosystems. For forestry, urban planning and agriculture, automatic mapping has many benefits. The science of remote sensing has benefited greatly from the development of deep learning techniques, which have yielded impressive results in image classification. This research proposes novel technique in ecosystem monitoring with disaster management in urban environments based on hyperspectral image analysis using a machine learning model. Here the input has been collected as hyperspectral image as well as processed for noise removal, normalisation and smoothening. Ecosystem monitoring is carried out utilizing Gaussian attention linear discriminant logistic regression. Then, the disaster management has been carried out based on the ecosystem monitoring model using cloud-based genetic spatio algorithm. Experimental analysis is carried out in terms of prediction accuracy, precision, F-measure, recall and RMSE for various hyperspectral images: prediction accuracy of 96%, precision of 97%, F-measure of 88%, recall of 95% and RMSE of 60% for proposed technique. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Disaster management Ecosystem monitoring Hyperspectral image analysis Machine learning model Urban environments

来源：评论

学校读者我要写书评

暂无评论

A Study on Partially Homomorphic Encryption 17

A Study on Partially Homomorphic Encryption

引用

17th International Conference on Ubiquitous Information Management and Communication, IMCOM 2023

作者： Ryu, Jihyeon Kim, Keunok Won, Dongho Sungkyunkwan University Department of Computer Science and Engineering Suwon Korea Republic of Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9781665453486

Recently, data experts can obtain a large amount of data with the development of the Internet. When computing such data, cloud services that do not use the personal device's memory are becoming popular. However, storing sensitive data as a source in the cloud carries the risk of hijacking. To compensate for this, homomorphic encryption, which encrypts and stores sensitive data, and can safely operate in an encrypted state, is being studied. In this paper, we analyze four methods of partially homomorphic encryption among homomorphic encryption methods. We compare and analyze the key size and ciphertext size of four partially homomorphic encryptions, Paillier, ElGamal, ASHE, and Symmetria. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Towards Machine Learning Based Fingerprinting of Ultrasonic Sensors

Towards Machine Learning Based Fingerprinting of Ultrasonic ...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Elhanafy, Marim Ravva, Srivaths Solanki, Abhijeet Hasan, Syed Rafay Tennessee Technological University Department of Electrical and Computer Engineering CookevilleTN38505 United States Stony Brook University Department of Computer Science Stony BrookNY United States

ISBN: (纸本)9798331504847

Fingerprinting is now recognized as an approach that identifies or categorizes devices using distinct data characteristics. This paper introduces a sensor fingerprinting model and, through experiments, demonstrates that unique error patterns resulting from manufacturing imperfections can be used to accurately identify sensors. Using various machine learning algorithms such as a random forest classifier, multilayer perceptron, and soft decision tree, accuracies of 87%, 85.5%, and 89.2% respectively were achieved. These results highlight the significant potential for reliable sensor fingerprinting applications. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Extensive analysis of IoT Architecture and Access Control Policies in Fog Enabled Environment 2

Extensive analysis of IoT Architecture and Access Control Po...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Lalit, Mohit Maurya, Sant Kumar Khurana, Shiraz Gupta, Nishant Computer Science and Engineering Department Chandigarh University Punjab Mohali India Computer Science and Engineering Department School of ICT Gautam Buddha University Greater Noida India Computer Science and Engineering Department Sharda University Greater Noida India

ISBN: (纸本)9798331541217

Cloud technology provides solutions to a variety of software platform and data accessibility issues. However, as the industrial revolution 4.0 progresses, innovations such as healthcare 4.0 smart buildings, IoT enabled transportation services, and many other new paradigms necessitate more secure data management solutions. Meanwhile, Fog Computing (FC) arises as a supplement to cloud computing, providing a variety of solutions to issues such as low latency and real-time data transfer. However, security concerns remained, and to address such issues, a regressive access control mechanism approach study was necessary. This article addresses methods to access control mechanisms for preserving privacy and confidentiality during communication in a cloud-fog computing environment. The research goal is to investigate various access control approaches used in the recent past for fog computing enabled environments. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Improved Thyroid Disease Prediction: A Voting Classifier Approach 3

Ensemble Learning for Improved Thyroid Disease Prediction: A...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Jyoti, Oishi Paul, Amit Kumar Nawar, Nuzhat Siddique, Md. Abu Ismail Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350388282

Thyroid disease represents a significant contributor to challenges in both medical diagnosis and the prediction of its onset, making it a complex area of study within medical research. This research thoroughly analyses the effective use of machine-learning approaches for thyroid identification. In our research, we use a Voting Classifier using five machine learning models: Support Vector Machine, Logistic Regression, Random Forest, Decision tree, and Gradient Boosting Classifier to detect negative patients or hyperthyroid and hypothyroid patients. The combined result of multiple machine learning models refers to 99.6% accuracy which surpasses the previous results that are mostly single machine learning models. The findings indicate that when considering both accuracy and computational complexity, machine learning models emerge as a preferable option for detecting thyroid disease. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing NPC Behavior in Video Games Using Unity ML-Agents: A Reinforcement Learning-Based Approach 3

Optimizing NPC Behavior in Video Games Using Unity ML-Agents...

引用

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Maurya, Sudhanshu Kotiyal, Arnav Prusty, Pankaj Shelke, Nilesh Bhattacherjee, Abhishek Sarkar, Tiyas School Of Computer Science and Engineering Nagpur Campus Pune India Graphic Era Deemed to be University Department of Computer Science and Engineering Dehradun India Siksha O Anusandhan Deemed to be University Department of Computer Science and Engineering Bhubaneswar India School of Computer Science and Engineering Lovely Professional University Phagwara India

ISBN: (纸本)9798331519582

The development of video games is now being influenced by machine learning (ML), which is changing the industry with every passing day. The focus of this research is on how video games can be made better through ML in game development, particularly how NPCs behave in the game. Game companies can boost the immerse feeling in video games by utilizing reinforcement learning in developing sophisticated NPCs. Those who play modern video games know that they are more realistic than what they used to be, and this is courtesy of ML. The toolkit Unity ML-Agents enables more straightforward ML implementations in the Unity game engine, giving game makers the ability to create complex AI features without having to have deep knowledge of machine learning. This paper seeks to analyze how ML can transform the experience of humans when playing games by enhancing the NPCs and through interactivity. The future of video games is bright, especially considering new advancements in technology like ML. © 2025 IEEE.

关键词： Reinforcement learning

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：