检索结果-内蒙古大学图书馆

International eConference on computer and Knowledge engineering (ICCKE)

作者： Aliyu Sabo Theophilus Ebuka Odoh Samuel Habu Hossien Shahinzadeh Farshad Ebrahimi Department of Electrical andElectronic Engineering Advanced Lightning Power and EnergyResearch (ALPER) Universiti Putra Malaysia Serdang Malaysia Department of Electrical Engineering Water Resource Institute Kaduna Nigeria Department of Electrical Engineering Amikabir University of Technology Tehran Iran Dept. of Electrical and Computer Engineering University of Houston Houston TX USA

The performance of metaheuristic optimization techniques is system-dependent, it is essential to ascertain the suitability of an algorithm before its application. This study surveys the suitability of AVOA in damping controller design by reviewing the performance of AVOA in used cases of power system optimization problems and damping controller design. Based on the findings, AVOA is recommended as a good optimizer in power system optimization and damping controller design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Diagnosis of Alzheimer’s Disease with the Use of Deep Learning based CNN Model

An Effective Diagnosis of Alzheimer’s Disease with the Use ...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： K C Sharmili G P Suja E. Pandian Md. Abul Ala Walid Sripriya Arunachalam G.Charles Babu Computer Science Stella Maris College 17 Cathedral Road Chennai Computer science Muslim Arts College Thiruvithancode Master of Computer Application Sri Muthukumaran Institute of Technology Mangadu Chennai Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Khulna Computer Applications-PG School of Computing Sciences VELS Institute of Science Technology & Advanced Studies - VISTAS Velan Nagar P.V. Vaithiyalingam Road Pallavaram Chennai Department of Computer Science and Engineering GRIET Hyderabad

In recent years, Alzheimer’s disease has become a major health concern. Over 45 million individuals worldwide suffer from this illness. Alzheimer’s disease is a neurodegenerative illness of unidentified etiology and process that causes cognitive deterioration, and it mostly affects the elderly. Dementia, the gradual and irreversible loss of brain cells, is the leading cause of Alzheimer’s disease. Those with this illness lost the ability to think, read, and do other basic tasks. A machine learning system may aid in this situation by making accurate predictions about the onset of illness. Dementia diagnosis in a broad patient population is the major objective. This research presents the findings and analysis of many Machine Learning models for identifying dementia. To alleviate this obstacle and help in the diagnosis of AD will create a deep-learning architecture that uses stacked auto-encoders and a softmax output layer. The proposed technique can analyze numerous classes in a single setting, unlike earlier procedures, and only needs a small number of labeled training samples and basic domain expertise to get started. In the present studies, a substantial improvement in performance when it came to classifying all diagnostic subgroups. Using the proposed technique can run these time series through a Convolutional Neural Network (CNN) and ResNet50 model to extract the distinguishing patterns across stages. With an F1-score of 0.99 and an accuracy of 99.91 percent, the CNN-based technique outperformed the standard feature-based classifiers by a significant margin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Malicious URL Detection Using Kernel PCA-SVM-GA Model with Feature Analysis

Intelligent Malicious URL Detection Using Kernel PCA-SVM-GA ...

引用

Data Science and Network Security (ICDSNS), International Conference on

作者： Sandy Ariawan Arvind Kumar Chinthala Kumara Swamy V. Divya V Manikandan S. Rukmani Devi IAKN Tarutung Indonesia SCA Manav Rachna International Institute of Research and Studies Faridabad India CSE-DS Mallareddy College of Engineering Hyderabad India Department of Information Technology Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Computer Science and Engineering Jain University Bangalore India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

Dangerous websites, or rogue URLs, pose a serious threat to cybersecurity. Malicious URLs cost businesses and consumers alike billions of dollars annually because the system lure unsuspecting users into scams that steal personal information, cause financial loss, or install malware. Immediate action is required to detect and eliminate these threats. This form of detection has traditionally relied on blacklists. A major drawback of blacklists is that the system are not comprehensive and do not detect newly established harmful URLs. The procedure consists of three stages, which are preprocessing, feature extraction, and training the model. Important parts of data preprocessing when dealing with URLs are standardization and parsing. When it comes to detecting dangerous URLs using machine learning, feature extraction is a major concern. The proposed approach used a Kernal PCA-SVM-GA to train the model. The proposed approach beats both SVM and GA, with an average accuracy of 93.52%.

关键词： Uniform resource locators Training Support vector machines Accuracy Data preprocessing Standardization Machine learning Feature extraction Vectors Blocklists

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Estimation of Tonic Dopamine and Serotonin with High Temporal Resolution In Vitro Using Deep Learning

Simultaneous Estimation of Tonic Dopamine and Serotonin with...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Seongtak Kang Yunho Jeong Ji-Woong Choi Department of Electrical Engineering and Computer Science Daegu Gyeongbuk Institute of Science and Technology (DGIST) Daegu Republic of Korea College of Transdisciplinary Studies DGIST Daegu Republic of Korea Department of Electrical Engineering and Computer Science DGIST Daegu Republic of Korea Brain Engineering Convergence Research Center DGIST Daegu Republic of Korea

Quantitative measurement of the phasic (changes in several seconds) and tonic (changes in minutes to hours) level changes of neurotransmitters is an essential technique for understanding brain functions and brain diseases regulated by the neurotransmitters. However, monitoring phasic and tonic levels of multiple neurotransmitters is still a challenging technology. Microdialysis can measure the tonic levels of multiple neurotransmitters simultaneously but has a low temporal resolution (minute) to analyze precisely. Fast-scan cyclic voltammetry (FSCV) has high temporal resolution and high sensitivity, but it was not able to simultaneously measure the tonic level of multiple neurotransmitters. The recently proposed deep learning-based FSCV method was still only capable of phasic concentration estimation of neurotransmitters. In this study, we estimate the tonic levels of dopamine and serotonin simultaneously by training a deep-learning network with the extracted tonic information from the FSCV. The proposed deep learning model was validated in vitro to simultaneously estimate tonic concentrations of two neurotransmitters with statistically significantly higher accuracy than previously proposed background subtraction-based models (p<0.001). In particular, in the case of serotonin concentration estimation error, the proposed model showed higher prediction performance than the background subtraction-based model (48 nM and 73 nM, respectively). We expect that the proposed technique will help simultaneous measurement of the phasic and tonic levels of numerous neurotransmitters in vivo *** Relevance— This study proposes a method to simultaneously measure tonic dopamine and tonic serotonin with high temporal resolution with a single electrode in the brain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis and Forecasting of COVID-19 Pandemic Using ARIMA Model

Analysis and Forecasting of COVID-19 Pandemic Using ARIMA Mo...

引用

Advances in Computing, Communication, Embedded and Secure Systems (ACCESS), International Conference on

作者： Soni Singh Sonam Mittal Sunaina Singh Department of Computer Science and Engineering School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Chitkara University Institute of Engineering & Technology Chitkara University Punjab India Department of Electrical & Electronics School of Engineering University of Petroleum and Energy Studies (UPES) Bidholi Dehradun India

The global community is now seriously threatened by the COVID-19 pandemic. The government of every nation must pay close attention to the analysis of this disease to take the required actions to lessen the impact of this worldwide epidemic. This research focused on the disease outbreak in the Indian region through July 21st, 2021, and evaluated the incidence and mortality. Machine learning techniques, such as the ARIMA model, are applied to perform the prediction analysis on collected data from the World Health Organization (WHO) official portal for India between January 20, 2020, and July 21, 2021. Mean Square Error (MSE), a measure of model performance, was used to assess performance, and it came in between 2170.636098 and 46.839689. In the four weeks of test data, the Expected instances are estimated to be between 192K and 230K, which is fairly similar to the actual figures. The government and physicians will be able to make future strategies with the aid of this study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Highsimb: A Concrete Blockchain High Simulation with Contract Vulnerability Detection for Ethereum and Hyperledger Fabric 4th

Highsimb: A Concrete Blockchain High Simulation with Contra...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Pengfei Jie, Wanqing Voundi Koe, Arthur Sandor Hou, Ruitao Yan, Hongyang Nouioua, Mourad Thien, Phan Duc Mbous Ikong, Jacques Lancine, Camara Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou510006 China Pazhou Lab Guangzhou510330 China Faculty of Mathematics and Computer Science University of Mohamed Bachir El Ibrahimi Bordj Bou Arreridj34030 Algeria Faculty of Information Technology Nam Dinh University of Technology Education Nam Dinh420000 Viet Nam Department of Electrical and Telecommunications Engineering National Advanced School of Engineering - University of Yaounde I Yaounde337 Cameroon Department of Computer Science University of Social Sciences and Management Bamako2575 Mali

ISBN: (纸本)9783031200984

Blockchain testing plays a critical role in the maturation of blockchain technology by ensuring the quality of implemented functional and non-functional requirements. In the new global economy, rapid time to market has become a central issue: developers fail to scrutinize their blockchain designs prior to deployment and customers undergo negative experiences that hurt the widespread adoption of the blockchain technology. Previous published studies aimed for effective blockchain simulators. However, existing solutions exhibit several drawbacks: they rely on guesswork, conceal low-level implementation details, lack expected realistic outcomes and automated testing, as well as lag in smart contract vulnerability analysis. In this paper, we introduce highsimb: the first concrete blockchain high simulation platform for Ethereum and Hyperledger Fabric that supports smart contract vulnerability detection. Unlike a testnet, the blockchain tester can customize any low-level detail to achieve realistic expected results under automated testing. Theoretical analysis demonstrates our concrete simulator is highly observable, supports realistic feedback, is scalable, detects smart contract vulnerabilities, has strong white-box testing capabilities and automates experiments. Our framework complements existing blockchain simulators and introduces a novel development paradigm for blockchain testing. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

African Vultures Optimization Algorithm for Optimal Damping Controllers Design in the electrical Power Grid System

African Vultures Optimization Algorithm for Optimal Damping ...

引用

International eConference on computer and Knowledge engineering (ICCKE)

作者： Aliyu Sabo Theophilus Ebuka Odoh Samuel Habu Hossien Shahinzadeh Farshad Ebrahimi Department of Electrical and Electronic Engineering Advanced Lightning Power and Energy Research (ALPER) Universiti Putra Malaysia Serdang Malaysia Department of Electrical Engineering Water Resource Institute Kaduna Nigeria Department of Electrical Engineering Amikabir University of Technology Tehran Iran Dept. of Electrical and Computer Engineering University of Houston Houston TX USA

Electromechanical oscillation affects power system stability and hinders the improvement of the generating capacity of the electrical power grid system. This is because if electromechanical oscillation is not controlled, it leads to the loss of synchronism in generators and total power disruption in the power grid system. To solve this problem, this study introduces Power System Stabilizer (PSS) damping controllers in the IEEE standard power test systems of Single Machine Infinite Bus (SMIB), Western System Coordinating Council (WSCC), and the New England Power Test Systems for electromechanical oscillation damping and control. The African Vultures Optimization Algorithm (AVOA) was used to obtain the PSS damping controller parameters to ensure optimal performance. Results showed that the introduced PSS damping controllers can dampen and control electromechanical oscillation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fingerspelling Classification for Robot Control

Fingerspelling Classification for Robot Control

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Kevin McCready Sonya Coleman Dermot Kerr Nazmul Siddique Emmett Kerr Yiannis Aloimonos Cornelia Fermüller School of Computing Engineering and Intelligent Systems Ulster University Londonderry Northern Ireland Department of Electronic and Mechanical Engineering Atlantic Technological University Letterkenny Ireland Institute for Advanced Computer Studies University of Maryland College Park Maryland USA

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Improvements to human-robot interaction methods could increase the ease of use of robots in manufacturing environments. Many of these environments are noisy and therefore preclude the use of audio communication between humans or in human-robot interactions. Therefore, this paper proposes using a gesture based communication system for robot control. To that end, the VGG16 and VGG19 convolutional neural network (CNN) structures are used for gesture classification along with 3 datasets of American Sign Language (ASL) fingerspelling images. The model performance is evaluated, and modifications made to their parameters to improve performance, before applying them to robot control tasks. The results show that with parameter tuning, test accuracies of up to, 100% are achievable.

关键词： Sign language Accuracy Computational modeling Robot control Human-robot interaction Convolutional neural networks Noise measurement Tuning Testing Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

FDD Massive MIMO: How to Optimally Combine UL Pilot and Limited DL CSI Feedback?

FDD Massive MIMO: How to Optimally Combine UL Pilot and Limi...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Jungyeon Kim Jinseok Choi Jeonghun Park Ahmed Alkhateeb Namyoon Lee Department of Electrical Engineering Pohang University of Science and Technology Pohang Republic of Korea School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea School of Electrical and Electronic Engineering Yonsei University Seoul Republic of Korea School of Electrical Computer and Energy Engineering Arizona State University AZ USA School of Electrical Engineering Korea University Seoul Republic of Korea

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In frequency-division duplexing (FDD) multipleinput multiple-output (MIMO) systems, obtaining accurate downlink channel state information (CSI) becomes challenging due to the tremendous feedback overhead that increases with the number of antennas. Using uplink pilots to estimate downlink CSI is a promising approach that can eliminate the need for CSI feedback, but its accuracy decreases significantly as the number of channel paths increases. In this paper, we propose a mean square error (MSE)-optimal downlink channel reconstruction method that jointly utilizes uplink CSI and limited downlink CSI. With the MSE-optimal estimator, we derive the MSE as a function of the number of feedback bits for channel phase quantization and show the optimal feedback bit allocation method to minimize the MSE. Harnessing robust downlink precoding, we demonstrate that the proposed downlink channel reconstruction is sufficient to achieve a sum-spectral efficiency comparable to that with perfect downlink CSI.

关键词： Accuracy Quantization (signal) Spectral efficiency Precoding Bit rate Channel estimation Massive MIMO Reconstruction algorithms Downlink Uplink

来源：评论

学校读者我要写书评

暂无评论

A Novel Tactile Sensing Skin for Surface Perception

引用

IEEE Sensors Journal 2025年

作者： Das, Subham Thiyagarajan, Karthick Kodagoda, Sarath Krishnan, Athul Bhattacharjee, Mitradip Indian Institute of Science Education and Research Bhopal i-Labs Electrical Engineering and Computer Science Department Madhya Pradesh 462066 India Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment PenrithNSW2751 Australia UTS Robotics Institute University of Technology Sydney Australia SydneyNSW2007 Australia

Humans employ a fusion of pressure and temperature signals to perceive tactile stimuli. While replicating the complexity of human tactile sensing poses challenges, advancements in artificial tactile sensing skins play a crucial role in the progress of robotics and prosthetics. Here, we present a novel tactile sensing skin designed for the perception of diverse surfaces. It utilizes a microstructured porous tactile sensor, exhibiting notable sensitivity at 21.5 kPa-1 under low-pressure conditions and 2.5 kPa-1 in high-pressure scenarios. The sensor also boasts an impressively low detection limit of 2.5 Pa, allowing for discernment of subtle pressure variations. Simultaneously, we utilize a flexible temperature sensor exhibiting a sensitivity of 0.58 % ∘C-1 and swift response attributes to facilitate the detection of radiated heat from diverse surfaces. The incorporation of a multilayer perceptron algorithm into the developed glove-like system, equipped with tactile and temperature sensors, achieves 87% accuracy in classifying eleven distinct surfaces. © 2001-2012 IEEE.

关键词： Tactile sensors

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：