检索结果-内蒙古大学图书馆

2023 IEEE National Aerospace and Electronics Conference, NAECON 2023

作者： Kasongo, Muana Ytterdal, Trond Lee, John Rizkalla, Maher Kumar, Mukesh Iupui Electrical and Computer Engineering Department Indianapolis United States Norwegian Institute of Technology Electronic Systems Department Trondheim Norway Indian Institute of Technology Indore Electrical Engineering Department Indore India

ISBN: (纸本)9798350338782

Memristors are novel electronic devices. Memristor-based crossbar arrays have gained a lot of attention for potential applications in nonvolatile memory, in-memory computing, logic design, neuromorphic computing systems, and neural networks. In this paper, we demonstrate the sneaky path current issue within a 3×3 crossbar array. 1T1M scheme has been used to reduce the leakage current. Integrating nMOS and pMOS devices in series with memristors in the crossbar array has optimized the leakage currents. The results show that nMOS devices reduce the leakage currents by 97.35%, whereas pMOS devices reduce the leakage currents by 92.20%. Thus, nMOS outperform pMOS devices in leakage currents optimization. © 2023 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Skin Cancer Detection Using Fusion of Textural Features Based CAD Tool

引用

computers, Materials & Continua 2024年第12期81卷 4217-4263页

作者： Khushmeen Kaur Brar Bhawna Goyal Ayush Dogra Sampangi Rama Reddy Ahmed Alkhayyat Rajesh Singh Manob Jyoti Saikia Department of Electronics and Communication Engineering Chandigarh UniversityMohali140413India Chitkara University Institute of Engineering and Technology Chitkara UniversityChandigarh140401India Department of Physics&Electronics School of SciencesJAIN(Deemed to be University)Bangalore560001India College of Technical Engineering The Islamic UniversityNajaf54001Iraq Department of Electronics and Communication Engineering Uttaranchal Institute of TechnologyUttaranchal UniversityDehradun248007India Electrical and Computer Engineering Department University of MemphisMemphisTN 38152USA Biomedical Sensors&Systems Lab University of MemphisMemphisTN 38152USA

Skin cancer has been recognized as one of the most lethal and complex types of cancer for over a *** diagnosis of skin cancer is of paramount importance,yet the process is intricate and *** analysis and modeling of human skin pose significant difficulties due to its asymmetrical nature,the visibility of dense hair,and the presence of various substitute *** texture of the epidermis is notably different from that of normal skin,and these differences are often evident in cases of unhealthy *** a consequence,the development of an effective method for monitoring skin cancer has seen little ***,the task of diagnosing skin cancer from dermoscopic images is particularly *** is crucial to diagnose skin cancer at an early stage,despite the high cost associated with the procedure,as it is an expensive ***,the advancement of diagnostic techniques for skin cancer has been *** address this issue,there is a need for a more accurate and efficient method for identifying and categorizing skin cancer *** involves the evaluation of specific characteristics to distinguish between benign and malignant skin cancer *** present and evaluate several techniques for segmentation,categorized into three main types:thresholding,edge-based,and *** techniques are applied to a dataset of 200 benign and melanoma lesions from the Hospital Pedro Hispano(PH2)*** evaluation is based on twelve distinct metrics,which are designed to measure various types of errors with particular clinical ***,we assess the effectiveness of these techniques independently for three different types of lesions:melanocytic nevi,atypical nevi,and *** first technique is capable of classifying lesions into two categories:atypical nevi and melanoma,achieving the highest accuracy score of 90.00%with the Otsu(3-level)*** second technique also classifies lesions int

关键词： Melanoma computer-aided diagnosis segmentation PH2 ISIC(International Skin Imaging Collaboration) dermoscopy non-melanoma

来源：评论

学校读者我要写书评

暂无评论

Enhanced Adaptive Brain-computer Interface Approach for Intelligent Assistance to Disabled Peoples

引用

computer systems Science & engineering 2023年第8期46卷 1355-1369页

作者： Ali Usman Javed Ferzund Ahmad Shaf Muhammad Aamir Samar Alqhtani Khlood M.Mehdar Hanan Talal Halawani Hassan A.Alshamrani Abdullah A.Asiri Muhammad Irfan Department of Computer Science COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Anatomy Department Medicine CollegeNajran UniversityNajran61441Saudi Arabia Computer Science Department College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Radiological Sciences Department College of Applied Medical Sciences and Information SystemsNajran UniversityNajran61441Kingdom of Saudi Arabia Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia

Assistive devices for disabled people with the help of Brain-computer Interaction(BCI)technology are becoming vital bio-medical *** with physical disabilities need some assistive devices to perform their daily *** these devices,higher latency factors need to be addressed ***,the main goal of this research is to implement a real-time BCI architecture with minimum latency for command *** proposed architecture is capable to communicate between different modules of the system by adopting an automotive,intelligent data processing and classification ***-sky mind wave device has been used to transfer the data to our implemented server for command ***-Net Convolutional Neural Network(TN-CNN)architecture has been proposed to recognize the brain signals and classify them into six primary mental states for data *** collection and processing are the responsibility of the central integrated server for system load *** of implemented architecture and deep learning model shows excellent *** proposed system integrity level was the minimum data loss and the accurate commands processing *** training and testing results are 99%and 93%for custom model implementation based on *** proposed real-time architecture is capable of intelligent data processing unit with fewer errors,and it will benefit assistive devices working on the local server and cloud server.

关键词： Disable person electroencephalogram convolutional neural network brain signal classification

来源：评论

学校读者我要写书评

暂无评论

Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

Power System Transient Security Assessment using Unsupervise...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Afrasiabi, Shahabodin Allahmoradi, Sarah Liang, Xiaodong Afrasiabi, Mousa Aghaei, Jamshid Chung, C.Y. University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada Lappeenranta University of Technology School of Energy Systems Department of Electrical Engineering Lappeenranta Finland Central Queensland University School of Engineering and Technology Department of Electrical Engineering Rockhampton Australia The Hing Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9781665471640

This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)). © 2023 IEEE.

关键词： Bayesian network imbalanced dataset noise-model free normalizing flow transient security assessment unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based unknown reference tracking control of HMASs with nonidentical communication delays

引用

Science China(Information Sciences) 2023年第7期66卷 46-57页

作者： Yong XU Zheng-Guang WU Wei-Wei CHE Deyuan MENG School of Automation Beijing Institute of Technology Institute of Cyber-Systems and Control Zhejiang University College of Mathematics and Computer Science Zhejiang Normal University Department of Automation Qingdao University School of Automation Science and Electrical Engineering Beihang University(BUAA)

This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies assuming that the precise model of the leader is globally or distributively accessible to all or some of the followers, the leader's precise dynamical model is entirely inaccessible to all the followers in this paper. A data-based learning algorithm is first proposed to reconstruct the leader's unknown system matrix online. A distributed predictor subject to communication delays is further devised to estimate the leader's state, where interaction delays are allowed to be nonidentical. Then, a learning-based local controller, together with a discounted performance function, is projected to reach the optimal output synchronization. Bellman equations and game algebraic Riccati equations are constructed to learn the optimal solution by developing a model-based reinforcement learning(RL) algorithm online without solving regulator equations, which is followed by a model-free off-policy RL algorithm to relax the requirement of all agents' dynamics faced by the model-based RL algorithm. The optimal tracking control of HMASs subject to unknown leader dynamics and communication delays is shown to be solvable under the proposed RL algorithms. Finally, the effectiveness of theoretical analysis is verified by numerical simulations.

关键词： heterogeneous multiagent systems HMAS reinforcement learning RL optimal output synchronization communication delays

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Heart Disease Detection Using Different Machine Learning Approaches 6

Performance Analysis of Heart Disease Detection Using Differ...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Tousif, Md. Noumil Rabbi Ushan, Md. Nahian Akhter, Rumana Mahmud, Sadia Rashid, Sakera Mohammad, Sakib University of Dhaka Department of Biomedical Physics and Technology Dhaka Bangladesh Ahsanullah University of Science and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh European University of Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Southern Illinois University Carbondale Department of Electrical Computer and Biomedical Engineering CarbondaleIL United States

ISBN: (纸本)9798350385779

The leading cause of illness and mortality globally, heart disease is a serious global health problem. For successful prevention and intervention, timely and precise cardiac disease prediction is essential. Using the well-known Cleveland dataset from the UCI repository, we underwent an extensive performance examination of several ML approaches in the context of heart disease prediction in this study. The 303 cases and 14 features in this collection include essential clinical factors. The KNN, Random Forest, Naive Bayes, AdaBoost, Decision Tree, and Logistic Regression machine learning algorithms are among those being examined. Each is being assessed for its predictive efficacy. Our work reveals fascinating insights into algorithm performance through substantial data preparation, robust model training, and a thorough assessment utilizing measures like accuracy, sensitivity, specificity, and PPV, NPV. Notably, our results show that the KNN algorithm is the most effective at predicting heart disease by 93%. This finding has implications for improving clinical decision support systems and early heart disease detection, thereby lowering the prevalence of the condition and its negative effects on public health. This research highlights the crucial contribution of ML to the development of cardiovascular medicine and the significance of algorithm choice for predicting accuracy. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Stochastic physics-Informed Deep Generative Network Scenario Generation: Application on Responsive Residential Load Management

Stochastic Physics-Informed Deep Generative Network Scenario...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Afrasiabi, Mousa Afrasiabi, Shahabodin Allahmoradi, Sarah Aghaei, Jamshid Chung, C.Y. University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada Lappeenranta University of Technology School of Energy Systems Department of Electrical Engineering Lappeenranta Finland Central Queensland University School of Engineering and Technology Department of Electrical Engineering Rockhampton Australia The Hing Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9781665471640

This paper introduces a stochastic model for the optimal residential responsive loads power scheduling considering participants' satisfaction. In this context, firstly, a physical-informed based generative adversarial network (PI-GAN) network is designed for scenario generation with a high correlation with the actual data. In this network, conventional GANs are improved to learn spatial-temporal features of the residential loads and physics-informed concepts. To realize the spatial feature of the complex and highly nonlinear time series like residential loads, a residual convolutional neural network (Res-CNN) is considered to learn the spatial features, while the fully temporal features are realized by gated recurrent neural networks (GNN). Then, generated scenarios are used to cover the uncertainty associated with residential loads and provide the optimal results for responsive loads, including shiftable and curtailable loads. The numerical results on actual data in London, England, verify the effectiveness of the proposed stochastic framework and superiority by comparison with conditional GAN and improved version of GAN in scenario generations impact of stochastic demand response program. © 2023 IEEE.

关键词： Demand response gated recurrent neural network physics-informed based generative adversarial network residual convolutional neural network scenario-generation

来源：评论

学校读者我要写书评

暂无评论

Using Combined Knapsack and Shortest Path Problems for Planning Optimal Navigation Paths for Robotic Deliveries 10

Using Combined Knapsack and Shortest Path Problems for Plann...

引用

10th International Conference on Automation, Robotics, and Applications, ICARA 2024

作者： Voloch, Nadav Zadok, Yair Voloch-Bloch, Noa Hajaj, Maor Meir Ruppin Academic Center Computer Engineering department Emek Hefer Israel Achva Academic College Information Systems department Shikmim Israel Ruppin Academic Center Electrical Engineering department Emek Hefer Israel University of Haifa Information Systems department Haifa Israel

ISBN: (纸本)9798350394245

Today., the use of robotic navigational tools is widely used both in academical research and the technological industry., there is a growing need for planning paths of navigation to autonomous machines., robots and transportation vehicles. In this paper we relate to a specific problem in which the robot has to navigate between several points of delivery., every point contains several items that all have different weights and different values. There are two widely researched problems in computer science algorithms., namely the knapsack problem and the shortest paths on weighted graphs problem. Typically., dynamic programming solutions for the knapsack problem involve using the shortest path problem and creating a knapsack graph. However., this approach only considers the weight and value of each item or vertex. In our case., we introduce a different problem where we consider three properties: item weight., item value., and edge weight (which connects two items but is not dependent on its vertices). Each vertex in this particular graph represents a set of knapsack items. This scenario is applicable to real-life situations where a path has a non-dependent attribute (such as physical distance or travel time) and various types of items need to be selected at different locations along this path. The problem we address here is finding the most efficient path between two vertices (source and target) based on three aspects: minimal edge weight., maximum knapsack value., or a combination of both properties. We present an algorithm for finding these optimal paths., along with detailed explanations of its decision-making process and implementation. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Experimental measurement and numerical modeling of deformation behavior of breast cancer cells passing through constricted microfluidic channels

引用

Microsystems & Nanoengineering 2024年第1期10卷 129-147页

作者： Pouyan Keshavarz Motamed Hesam Abouali Mahla Poudineh Nima Maftoon Department of Systems Design Engineering University of WaterlooWaterlooON N2L 3G1Canada Center for Bioengineering and Biotechnology University of WaterlooWaterlooON N2L 3G1Canada Department of Electrical and Computer Engineering University of WaterlooWaterlooON N2L 3G1Canada

During the multistep process of metastasis,cancer cells encounter various mechanical forces which make them deform *** accurate in-silico models,capable of simulating the interactions between the mechanical forces and highly deformable cancer cells,can pave the way for the development of novel diagnostic and predictive methods for metastatic ***-network models of cancer cell,empowered by our recently proposed identification approach,promises a versatile numerical tool for developing experimentally validated models that can simulate complex interactions at cellular *** this numerical tool,we presented spring-network models of breast cancer cells that can accurately replicate the experimental data of deformation behavior of the cells flowing in a fluidic domain and passing narrow constrictions comparable to ***,using high-speed imaging,we experimentally studied the deformability of breast cancer cell lines with varying metastatic potential(MCF-7(less invasive),SKBR-3(medium-high invasive),and MDA-MB-231(highly invasive)in terms of their entry time to a constricted microfluidic *** observed that MDA-MB-231,that has the highest metastatic potential,is the most deformable cell among the ***,by focusing on this cell line,experimental measurements were expanded to two more constricted microchannel *** experimental deformability data in three constricted microchannel sizes for various cell sizes,enabled accurate identification of the unknown parameters of the spring-network model of the breast cancer cell line(MDA-MB-231).Our results show that the identifed parameters depend on the cell size,suggesting the need for a systematic procedure for identifying the size-dependent parameters of spring-network models of *** the numerical results show,the presented cell models can simulate the entry process of the cell into constricted channels with very good agreements with the measured experimen

关键词： strict passing numerical

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Analysis of Cyber-Attacks Targeting Smart Grid Infrastructure 2nd

Machine Learning Based Analysis of Cyber-Attacks Targeting S...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Nijim, Mais Kanumuri, Viswas Al Aqqad, Waseem Albataineh, Hisham Department of Electrical Engineering and Computer Science Texas A&M University-Kingsville KingsvilleTX United States Department of Electrical and Computer Engineering West Virginia Tech BeckleyWV United States Department of Physics and Geosciences Texas A&M University-Kingsville KingsvilleTX United States

ISBN: (纸本)9783031569494

The transformation of traditional electric power systems into smart grids has allowed for improved monitoring and control capabilities. However, this evolution has also brought about new challenges in the form of malware and vulnerabilities, creating significant security concerns. To address this issue, sensors are being deployed to the grid, leading to a large influx of data that needs to be analyzed for accurate results. Machine learning algorithms are being utilized to process this data and extract important information. This paper explores the application of various machine learning algorithms in smart grids, with a specific focus on their use in cybersecurity. We identify different types of cyber threats affecting smart grids and examine defense strategies to counter these threats. Through this study, we provide insights into the potential of machine learning in addressing the cybersecurity challenges in smart grids. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cybersecurity

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：