检索结果-内蒙古大学图书馆

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Singh, Digvijay Yadav, Annu Arora, Rishabh Ravivarman, G. Vijay, S. Arul Antran Sharma, Y.K. School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand India School of Computer Science and Applications IIMT University Meerut India K. R. Mangalam University Department of Civil Engineering Gurugram India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore India Karpagam College of Engineering Department of Computer Science Engineering Coimbatore India Computer Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350304480

Previous studies have shown that Deep Neural Networks'(DNN's) outputs is not consistent and very susceptible to inputs vectors perturbations of any size, and as a result, a number of techniques have been developed for creating effective perturbations on the connections. In this research, we offer a novel divergent transformation method for visually computing very small adversarial perturbations (few-pixel attacks). It works with a wider range of DNN different classifiers and calls for far less adverse data. The findings indicate that, on average, 73.8percent of total of the test photos can be modified to create hostile images by changing just one pixel. Additionally, it is well recognized that analyzing the DNN resilience problem can provide crucial hints for comprehending the geometric characteristics of the DNN decision. a high-dimensional inputs area map. In contrast to earlier research, the outcomes of performing few-pixel attack give quantifiable data and analyses to the geometric knowledge, Genetic algorithm (GA) © 2023 IEEE.

关键词： DNN geometric hostile images Pixel

来源：评论

学校读者我要写书评

暂无评论

A Novel Cluster Analysis-Based Crop Dataset Recommendation Method in Precision Farming

引用

computer Systems science & engineering 2023年第9期46卷 3239-3260页

作者： K.R.Naveen Kumar Husam Lahza B.R.Sreenivasa Tawfeeq Shawly Ahmed A.Alsheikhy H.Arunkumar C.R.Nirmala Department of Computer Science&Engineering Bapuji Institute of Engineering&TechnologyDavangereKarnatakaIndia Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Information Science&Engineering Bapuji Institute of Engineering&TechnologyDavangereKarnatakaIndia Department of Electrical Engineering Faculty of Engineering at RabighKing Abdulaziz UniversityJeddahSaudi Arabia Department of Electrical Engineering College of EngineeringNorthern Border UniversityArarSaudi Arabia

Data mining and analytics involve inspecting and modeling large pre-existing datasets to discover decision-making *** agriculture uses datamining to advance agricultural *** farmers aren’t getting the most out of their land because they don’t use precision *** harvest crops without a well-planned recommendation *** crop production is calculated by combining environmental conditions and management behavior,yielding numerical and categorical *** existing research still needs to address data preprocessing and crop categorization/***,statistical analysis receives less attention,despite producing more accurate and valid *** study was conducted on a dataset about Karnataka state,India,with crops of eight parameters taken into account,namely the minimum amount of fertilizers required,such as nitrogen,phosphorus,potassium,and pH *** research considers rainfall,season,soil type,and temperature parameters to provide precise cultivation recommendations for high *** presented algorithm converts discrete numerals to factors first,then reduces ***,the algorithm generates six datasets,two fromCase-1(dataset withmany numeric variables),two from Case-2(dataset with many categorical variables),and one from Case-3(dataset with reduced factor variables).Finally,the algorithm outputs a class membership allocation based on an extended version of the K-means partitioning method with lambda *** presented work produces mixed-type datasets with precisely categorized crops by organizing data based on environmental conditions,soil nutrients,and ***,the prepared dataset solves the classification problem,leading to a model evaluation that selects the best dataset for precise crop prediction.

关键词： Data mining crop prediction k-prototypes k-means cluster machine learning

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Personalized Health: The Frontier of Wearable Biomolecule Sensors Through 3D Printing Innovation

引用

Biomedical Materials and Devices 2025年第2期3卷 818-834页

作者： Rajendran, Jerome Esfandyarpour, Rahim Department of Electrical Engineering and Computer Science University of California Irvine 92697 CA United States Laboratory for Integrated Nano BioElectronics Innovation The Henry Samueli School of Engineering University of California Irvine 92697 CA United States

This review article delves into the innovative intersection of 3D-printed technologies and wearable chemical sensors, highlighting a forward-thinking approach to biomarker monitoring. It emphasizes the transformative role of additive manufacturing in the development of wearable devices tailored for the precise detection of chemical biomarkers, crucial for proactive disease management and health assessment. By offering a detailed exploration of how 3D printing of nanomaterials contributes to pioneering sensor designs, this review underscores the practicality of sensor wearability, ensuring comfort and efficacy for users. We address the challenges of material resilience, sensor durability, and efficient data communication, while also charting the significant trends and future directions that promise to redefine the landscape of flexible and wearable chemical sensors. Through a comprehensive analysis, this article aims to showcase the pivotal advancements and ongoing innovations in the field, emphasizing the critical impact of 3D printing on enhancing personalized healthcare and wearable diagnostics. Graphical Abstract: (Figure presented.) © The Author(s) 2024.

关键词： 3D printing Biomarker monitoring Chemical sensors Flexible Personalized healthcare Wearable

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Telehealth Ecosystems Using IoT for Virtual Consultations and Support 10

Next-Gen Telehealth Ecosystems Using IoT for Virtual Consult...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Kathija Nasreen, A. Priya, S. Gupta, Nukala Sujata Shoba, L.K. Mohankumar, N. Arunkumar, S. Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Deemed To Be University Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Chaitanya Bharathi Institute of Technology Department of Computer Engineering and Technology Telangana Hyderabad India Srm Institute of Science and Technology Department of Computing Technologies Chenagalpattu Chennai Tamil Nadu Kattankulathur India Symbiosis Institute of Technology Maharashtra Nagpur India Adhiparasakthi Engineering College Department of Computer Applications Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

The research discussed focuses on improving virtual medical consultations and support using Internet of Things (IoT) technologies in telehealth services. It is predicted that IoT devices can assist with creating a new telehealth environment where patients and doctors can communicate easily for remote monitoring, diagnosis, and treatment. The main objective of this unique approach is to expand access to healthcare, especially in poor and rural areas. Connected medical equipment, smart sensors, and wearable technology all play an important role in this system. These IoT components enable gathering real-time and complete patient data, helping doctors make better, more individualized choices and care plans. Data safety, privacy, and system compatibility are some areas where this integration hits a snag. Sensitive patient data and the integrity of the IoT-enabled systems need robust safety measures. These IoT improvements in telemedicine have had a revolutionary effect. Proactive interventions, continuous health monitoring, and individualized care are ways patients might benefit from improved medical care. Virtual consultations are increasingly used in the medical field, and a more connected and data-driven framework for the patient experience is emerging. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Real-Time Implementation of Quadrotor UAV Control System Based on a Deep Reinforcement Learning Approach

引用

computers, Materials & Continua 2024年第12期81卷 4757-4786页

作者： Taha Yacine Trad Kheireddine Choutri Mohand Lagha Souham Meshoul Fouad Khenfri Raouf Fareh Hadil Shaiba Aeronautical Sciences Laboratory Aeronautical and Spatial Studies InstituteBlida 1 UniversityBlida0900Algeria Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Energy and Embedded Systems for Transportation Research Department ESTACA-LABMontigny-Le-Bretonneux78066France Department of Electrical Engineering University of SharjahSharjah27272United Arab Emirates Department of Computer Science College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

The popularity of quadrotor Unmanned Aerial Vehicles(UAVs)stems from their simple propulsion systems and structural ***,their complex and nonlinear dynamic behavior presents a significant challenge for control,necessitating sophisticated algorithms to ensure stability and accuracy in *** strategies have been explored by researchers and control engineers,with learning-based methods like reinforcement learning,deep learning,and neural networks showing promise in enhancing the robustness and adaptability of quadrotor control *** paper investigates a Reinforcement Learning(RL)approach for both high and low-level quadrotor control systems,focusing on attitude stabilization and position tracking tasks.A novel reward function and actor-critic network structures are designed to stimulate high-order observable states,improving the agent’s understanding of the quadrotor’s dynamics and environmental *** address the challenge of RL hyper-parameter tuning,a new framework is introduced that combines Simulated Annealing(SA)with a reinforcement learning algorithm,specifically Simulated Annealing-Twin Delayed Deep Deterministic Policy Gradient(SA-TD3).This approach is evaluated for path-following and stabilization tasks through comparative assessments with two commonly used control methods:Backstepping and Sliding Mode Control(SMC).While the implementation of the well-trained agents exhibited unexpected behavior during real-world testing,a reduced neural network used for altitude control was successfully implemented on a Parrot Mambo mini *** results showcase the potential of the proposed SA-TD3 framework for real-world applications,demonstrating improved stability and precision across various test scenarios and highlighting its feasibility for practical deployment.

关键词： Deep reinforcement learning hyper-parameters optimization path following quadrotor twin delayed deep deterministic policy gradient and simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Scheduling of Electric Vehicle Charging in a Solar-Wind Powered Microgrid Using Machine Learning

Scheduling of Electric Vehicle Charging in a Solar-Wind Powe...

引用

2024 IEEE International Women in engineering (WIE) Conference on electrical and computer engineering, WIECON-ECE 2024

作者： Rahman, Motinur Saha, Subrata Hasan, Mahmudul Alam, Mahbub Dadon, Saikot Hossain Suki, Tahmid Tamrin College of Ecs Arkansas State University Department of Electrical Engineering JonesboroAR United States Institute of Electronics Bangladesh Atomic Energy Commission Dhaka Bangladesh Institute of Computer Science Bangladesh Atomic Energy Commission Dhaka Bangladesh Bangladesh University of Professionals Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331535476

The future of power generation lies in renewable energy, and solar and wind power are major contributors to meeting the ever-increasing energy demand brought on by the development of new technologies like electric vehicles (EVs). To address the rising energy demand, a machine learning-based approach has been explored in this research, which predicts the most practical hour for EV charging using renewable energy sources. Power generation throughout the year has been predicted using wind-solar power generation datasets. The research was conducted in two stages: applying machine learning algorithms and time series analysis. We have compared the R-squared value, correlation, and various types of errors using five machine-learning algorithms. With an R-squared value of 0.9574, the XGB Regressor model outperformed the other four machine learning algorithms in predicting solar wind power generation for EV charging demand management. On the other hand, our time series study reveals that when the sum of these two powers (solar, wind) reaches its peak between 8 AM and 8 PM over 24 hours, EV charging demand stays at its peak, suggesting the demand handling capacity of EVs by renewable energy sources. © 2024 IEEE.

关键词： demand flexibility electric vehicle machine learning microgrid regression renewable energy solar power wind power

来源：评论

学校读者我要写书评

暂无评论

Formal verification of observers supervising a cyber-physical system implemented using IEC 61499 32

Formal verification of observers supervising a cyber-physica...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Ovsiannikova, Polina Priol, Etienne Le Perret, Vincent Jhunjhunwala, Pranay Xavier, Midhun Vyatkin, Valeriy Aalto University Department of Electrical Engineering and Automation Espoo Finland École Normale Supérieure Paris-Saclay Department of Mechanical Engineering Gif-sur-Yvette France Luleå Tekniska Universitet Computer and Space Engineering Department of Computer Science Sweden

ISBN: (纸本)9798350399714

A rigorous check is a significant phase in the design process of control programs of safety-critical cyber-physical systems. Here, we consider such programs to be implemented using IEC 61499 standard for industrial automation. After the check is performed (for example, using formal verification), the engineer needs to ensure that even in unexpected situations, the system will not fail during the runtime, and for this online verification methods can be utilized. In this work, we consider attaching monitors implemented as basic function blocks to the interface of the controller, thus having a property being monitored represented in the form of a state machine. Now, monitors make the system safer only if their quality is also ensured. Since their complexity is far lower than the complexity of the controller, they can be model checked, however, in the case of IEC 61499 function blocks, open-loop model checking will produce spurious counterexamples as it will allow combinations that are not possible according to the IEC 61499 function blocks semantics (e.g., data transferred without firing the event). The current work addresses this issue and proposes a method for close-loop model checking of monitors, using the non-deterministic twin of a controller under supervision. We present our approach using the system of two orthogonal pneumatic cylinders. © 2023 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Biomedical Osteosarcoma Image Classification Using Elephant Herd Optimization and Deep Learning

引用

computers, Materials & Continua 2022年第12期73卷 6443-6459页

作者： Areej A.Malibari Jaber S.Alzahrani Marwa Obayya Noha Negm Mohammed Abdullah Al-Hagery Ahmed S.Salama Anwer Mustafa Hilal Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Faculty of Science Mathematics and Computer Science DepartmentMenoufia UniversityEgypt Department of Computer Science College of ComputerQassim UniversitySaudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia

Osteosarcoma is a type of malignant bone tumor that is reported across the *** advancements in Machine Learning(ML)and Deep Learning(DL)models enable the detection and classification of malignancies in biomedical *** this regard,the current study introduces a new Biomedical Osteosarcoma Image Classification using Elephant Herd Optimization and Deep Transfer Learning(BOIC-EHODTL)*** presented BOIC-EHODTL model examines the biomedical images to diagnose distinct kinds of *** the initial stage,Gabor Filter(GF)is applied as a pre-processing technique to get rid of the noise from *** addition,Adam optimizer with MixNet model is also employed as a feature extraction technique to generate feature ***,EHOalgorithm is utilized along with Adaptive Neuro-Fuzzy Classifier(ANFC)model for recognition and categorization of *** algorithm is utilized to fine-tune the parameters involved in ANFC model which in turn helps in accomplishing improved classification *** design of EHO with ANFC model for classification of osteosarcoma is the novelty of current *** order to demonstrate the improved performance of BOIC-EHODTL model,a comprehensive comparison was conducted between the proposed and existing models upon benchmark dataset and the results confirmed the better performance of BOIC-EHODTL model over recent methodologies.

关键词： Biomedical imaging osteosarcoma classification deep transfer learning parameter tuning fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Human Stress Detection through Sleep Patterns 5

Machine Learning based Human Stress Detection through Sleep ...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Santhosh Krishna, B.V. Mai, Kiran Aswini, S. Biju, J. Mohanraj, S. Kaliappan, S. New Horizon College of Engineering Department of Computer Science and Engineering Bangalore India Bangalore Technological Institute Department of Computer Science and Engineering Bangalore India Bannari Amman Institute of Technology Information Science and Engineering Erode Tamilnadu Sathyamangalam India KGiSL institute of Technology Artificial Intelligence and Data Science Tamilnadu Coimbatore India Lovely Professional University Division of Research and Development Punjab India

ISBN: (纸本)9798331504403

Stress is a critical factor in overall wellbeing, and understanding its patterns during sleep can provide valuable insights into improving sleep quality and managing stress-related health issues. Stress has become an increasingly prevalent issue in modern society, impacting both mental and physical well-being. The ability to accurately detect stress levels in individuals is crucial for timely intervention and management. Sleep patterns serve as a valuable indicator of stress, as disruptions in sleep quality and duration often correlate with heightened stress levels. Leveraging advancements in machine learning techniques, this study proposes a novel linaer regression based approach to detect human stress by analyzing sleep patterns extracted from wearable devices. The proposed system consists of several key components. Firstly, data collection involves the continuous monitoring of sleep parameters such as sleep stages, heart rate variability, and movement using wearable sensors. Next, feature extraction techniques are applied to transform raw sleep data into informative features that capture relevant aspects of sleep patterns indicative of stress. © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

LEAF + AIO: Edge-Assisted Energy-Aware Object Detection for Mobile Augmented Reality

引用

IEEE Transactions on Mobile Computing 2023年第10期22卷 5933-5948页

作者： Wang, Haoxin Kim, BaekGyu Xie, Jiang Han, Zhu R and D InfoTech Labs Mountain ViewCA94043 United States University of North Carolina at Charlotte CharlotteNC28223 United States University of Houston Department of Electrical Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science Engineering Seoul446-701 Korea Republic of

Today very few deep learning-based mobile augmented reality (MAR) applications are applied in mobile devices because they are significantly energy-guzzling. In this paper, we design an edge-based energy-aware MAR system that enables MAR devices to dynamically change their configurations, such as CPU frequency, computation model size, and image offloading frequency based on user preferences, camera sampling rates, and available radio resources. Our proposed dynamic MAR configuration adaptations can minimize the per frame energy consumption of multiple MAR clients without degrading their preferred MAR performance metrics, such as latency and detection accuracy. To thoroughly analyze the interactions among MAR configurations, user preferences, camera sampling rate, and energy consumption, we propose, to the best of our knowledge, the first comprehensive analytical energy model for MAR devices. Based on the proposed analytical model, we design a LEAF optimization algorithm to guide the MAR configuration adaptation and server radio resource allocation. An image offloading frequency orchestrator, coordinating with the LEAF, is developed to adaptively regulate the edge-based object detection invocations and to further improve the energy efficiency of MAR devices. Extensive evaluations are conducted to validate the performance of the proposed analytical model and algorithms. © 2002-2012 IEEE.

关键词： Energy utilization

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：