检索结果-内蒙古大学图书馆

IEEE World Forum on Internet of Things (WF-IoT)

作者： Rodrigo Munoz-Lara Sandra Céspedes Marcos Diaz Dept.of Electrical Engineering University of Chile Santiago Chile Dept. of Computer Science & Software Eng. Concordia University Montreal QC Canada

ISBN: (数字)9798350373011

ISBN: (纸本)9798350373028

Static Context Header Compression and Fragmentation (SCHC) is a standard defined as an adaptation layer for supporting IPv6, UDP, and CoAP protocols in low power wide area network (LPWAN) technologies. SCHC has fragmentation modes that use confirmation mechanisms to deliver reliable communications. Direct-to-satellite Internet of Things (DtS-IoT) directly communicates between end devices and the satellite in an IoT environment. If SCHC is implemented in a DtSIoT environment, applications using IPv6 could have global coverage through the Internet of Things (IoT). Unfortunately, it is not known whether SCHC can operate with the current acknowledgement mechanisms in a DtS-IoT environment, and if so, it is not known which one performs better. This work evaluates SCHC acknowledgement modes for ACK-on-Error fragmentation mode, including the new SCHC Compound ACK mode. It determines which mode has the lowest transfer delay for different LoRa data rates and frame error rates in a DtS-IoT environment with LEO satellites.

关键词： Satellites Protocols Low earth orbit satellites Delays Internet of Things Compounds Reliability IP networks Standards Low-power wide area networks

来源：评论

学校读者我要写书评

暂无评论

Issues with Input-Space Representation in Nonlinear Data-Based Dissipativity Estimation

arXiv

引用

arXiv 2024年

作者： LoCicero, Ethan J. Penne, Alexander Bridgeman, Leila Dept. of Mechancial Eng. and Materials Science Duke Univeristy DurhamNC27708 United States Dept. of Electrical and Computer Engineering Duke Univeristy United States

In data-based control, dissipativity can be a powerful tool for attaining stability guarantees for nonlinear systems if that dissipativity can be inferred from data. This work provides a tutorial on several existing methods for data-based dissipativity estimation of nonlinear systems. The interplay between the underlying assumptions of these methods and their sample complexity is investigated. It is shown that methods based on δ-covering result in an intractable trade-off between sample complexity and robustness. A new method is proposed to quantify the robustness of machine learning-based dissipativity estimation. It is shown that this method achieves a more tractable trade-off between robustness and sample complexity. Several numerical case studies demonstrate the results. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Applications in Market Basket Analysis: A Case Study on elec.ric Vehicle Sales in India

Machine Learning Applications in Market Basket Analysis: A C...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Rachna Rathore Ashish Singh Chauhan Kailash Aseri J. Balaji Praveen Gaurav Sethi Ankur Mishra Dept. of Mathematics Jiwaji University Gwalior India Dept. of Pharmaceutical Sciences Uttaranchal University Dehradun India Dept. of Computer Science D.A.V. College Sri Ganganagar Rajasthan Dept. Civil Eng. Dhanalakshmi Srinivasan College of Eng. Coimbator India Dept. of Electronics and Electrical Eng. Lovely Professional University Punjab India Dept. of CSE (AIML) CSE-APEX Chandigarh University Chandigarh India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

This study explores the potential of Market Basket Analysis (MBA) to enhance elec.ric vehicle (EV) recommendations in India. By analyzing transactional data and identifying common item sets and association rules, MBA can provide valuable insights into customer preferences and purchasing behavior. This information can be utilized to develop personalized recommendation systems that effectively guide customers toward EV solutions tailored to their specific needs and preferences. These include discussions on key drivers of EV purchases in India, steps for implementing MBA, and challeng.s/concerns about the application of MBA. Specific factors in buying decisions can be traced through the analysis of unique characteristics in the Indian EV market. Finally, potential benefits are presented with the implementation of an MBA-driven recommendation system to both the manufacturer and the consumers of elec.ric vehicles in India. The study will delve deep into the application of MBA in the Indian EV market and contribute toward more effective and customized recommendation systems for the industry at large.

关键词： elec.ric potential Time series analysis Predictive models elec.ric vehicles Market research Data models Association rule learning Vehicle dynamics Usability Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Population Diversity Based Dandelion Optimizer for Solving Global Optimization Problems

Enhancing Population Diversity Based Dandelion Optimizer for...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Reham R. Mostafa Ahmed M. Khedr Research Institute of Sci. and Eng. (RISE) Sharjah University Sharjah UAE Dept. of Computer Science University of Sharjah Sharjah UAE

ISBN: (数字)9798350364316

ISBN: (纸本)9798350364323

The Dandelion Optimizer (DO) is a pioneering swarm intelligence optimization algorithm inspired by dandelion seed flight patterns. It simulates seed dispersal with rising, descending, and landing phases, exhibiting global ascent in sunlight and local dispersion in rain. While DO has shown promise across domains, it grapples with challeng.s, particularly rapid convergence in early stages and difficulty escaping local optima. This paper introduces an improved version, IDO, addressing these issues by enhancing the initial population generation method. Performance comparisons on CEC'22 test functions and eng.neering-constrained design problems demonstrate that IDO outperforms other algorithms, showcasing superior robustness.

关键词： Rain Smart cities Metaheuristics Robustness Seeds (agriculture) Particle swarm optimization Dispersion Convergence

来源：评论

学校读者我要写书评

暂无评论

Performance Monitoring and Controlling of Multicore Shared-Memory Parallel Processing Systems 3

Performance Monitoring and Controlling of Multicore Shared-M...

引用

3rd Information Technology to Enhance e-Learning and Other Application, IT-ELA 2022

作者： Haji, Lailan M Zeebaree, Subhi R. M. Ageed, Zainab Salih Ahmed, Omar M. Sadeeq, Mohammed A. M. Shukur, Hanan M. University of Zakho Faculty of Science Computer Science Dep. Duhok Iraq Technical College of Engineering Duhok Polytechnic University Energy Eng. Dept. Duhok Iraq College of Science Nawroz University Computer Science Dept. Duhok Iraq Zakho Technical Institute Duhok Polytechnic University Information Technology Dept. Duhok Iraq Technical College of Administration Duhok Polytechnic University ITM Dept. Duhok Iraq Al-Kitab University Computer Engineering Dept. Kirkuk Iraq

ISBN: (纸本)9798350334968

The field of research known as 'parallel processing' examines architectural and algorithmic methods for increasing the efficiency and other desirable qualities (such as cost-effectiveness and reliability) of computers by exploiting many forms of concurrency. The development of multi-core CPUs has opened the door to novel strategies for boosting system performance via parallelism. Increasing the number of concurrent threads greatly affects the time cost. While increased parallelism might reduce calculation time, the associated synchronization costs would likely be prohibitive for most applications. In this article, we'll go through the first half of the process, which involves gathering requirements and designing a prototype;the second half, which involves monitoring and managing a program that can run on a wide range of multicore system architectures, including those with (2, 4, and 8 CPUs). A shared-memory parallel processing method was proposed and built to show off the system's full potential. The implications of multi-core systems on overall program execution time and parallel processing in shared-memory systems provide the backbone of this investigation. © 2022 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Mixed Energy and Production Scheduling in an Eco-Industrial Park

Mixed Energy and Production Scheduling in an Eco-Industrial ...

引用

Simulation Winter Conference

作者： Shufang Xie Tao Zhang Oliver Rose Tobias Uhlig Björn Vollack Dept. of Computer Science University of the Bundeswehr Munich Munich GERMANY Chair of Logistics Eng. TUD Dresden University of Technology Dresden GERMANY

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

In recent times, eco-industrial parks (EIP) have taken on a significant role in addressing environmental challeng.s and supporting sustainable practices. To enhance the efficient utilization of energy within the park and ensure the achievement of production targets among its members, the implementation of energy and production scheduling is imperative. This paper addresses this optimization challeng. by formulating it into a constraint programming (CP) model. The optimized scheduling solutions generated by the CP model will be directly used to guide the operations within the simulation environment of the EIP. The paper compares the CP results with the results of another method which we developed in our previous research stage. The outcomes of CP solver demonstrate its effectiveness in optimizing energy utilization and meeting production targets. This research contributes to developing a practical decision support system for resolving real-life scheduling problems in industry parks.

关键词： Constraint handling Industries Job shop scheduling Green products Production Search problems Problem-solving Optimization Faces eng.nes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Emotional Support Chatbots Using Deep Learning & NLP: A Study on Personalization and Effectiveness

Enhancing Emotional Support Chatbots Using Deep Learning & N...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Priyanka Kaushik Renuka Sanjay Parihar Md. Saifullah Khalid Umesh Chandra Sharma J. Josphin Mary Dept. of Computer Science Chandigarh University Chandigarh India Dept. of Humanities & S.Science Madhav University Pindwara India Dept. of Bus. Management & Commerce Usha Martin University Jharkhand India Dept. of Computer Eng. & Applications Mangalayatan University Aligarh India Dept. of Computer Science Meenakshi A.H.E.R Chennai India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

This research focuses on utilizing deep learning and natural language processing (NLP) to design an AI-powered chatbot for emotional support. The primary objective is to establish a supportive platform for individuals dealing with emotional challeng.s. By leveraging NLP, the chatbot will identify and interpret users’ emotional states, generating tailored and empathetic responses. Deep learning techniques will enable the system to learn from past interactions, adapting its responses to meet the unique needs of each user. The platform aims to deliver personalized, scalable support while incorporating features like sharing uplifting content, such as cute cat images. This study emphasizes the potential of AI-driven solutions in enhancing mental well-being through empathetic and meaningful interactions.

关键词： Deep learning Emotion recognition Accuracy Virtual assistants Telemedicine Customer services Mental health Chatbots Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Proposal of Speed Sensorless Control Based on IRM-ILQ Control for SPMSM Drive with Active LC Filter

A Proposal of Speed Sensorless Control Based on IRM-ILQ Cont...

引用

International Conference on Renewable Energy Research and Applications (ICRERA)

作者： Ryoki Mikami Kazuki Abe Hiroshi Takami Fuminori Ishibashi Graduate School of Electrical Eng. And Computer Science Shibaura Institute of Technology Koto-ku Tokyo Japan Dept. of Electrical Eng. and Robotics Course College of Engineering Shibaura Institute of Technology Koto-ku Tokyo Japan Dept. of Electrical Eng. Faculty of Eng. Shibaura Institute of Technology Koto-ku Tokyo Japan

ISBN: (数字)9798350375589

ISBN: (纸本)9798350375596

Generally, a position detector has been used to drive the Surface Permanent Magnet Synchronous Motor (SPMSM), because the current and voltage must be controlled according to the magnetic pole position of the rotor. However, using a position detector causes problems such as more expensive and lower reliability due to position detector failure. Therefore, the speed sensor-less control, which estimates the magnetic pole position from voltage and current without using a position detector, is required. Harmonic components in the output voltage waveform of the PWM inverter used to drive the SPMSM can cause problems such as elec.romagnetic Interference (EMI). Harmonic components can be suppressed by using an LC filter. In addition, IRM-ILQ control, which combines modern control theory's Inverse Linear Quadratic (ILQ) control and Inverse Reference Model (IRM), can achieve stable and robust SPMSM drive despite with LC filter. In this paper, robustness of speed sensorless control based on IRM-ILQ current control for SPMSM with active LC filter is described. In simulation, the proposed method allows stable control even when there are parameter errors.

关键词： Maximum likelihood detection Magnetic separation elec.romagnetic interference Sensorless control Detectors Nonlinear filters Drives Harmonic analysis Voltage control Power harmonic filters

来源：评论

学校读者我要写书评

暂无评论

Towards on-device face recognition in body-worn cameras

arXiv

引用

arXiv 2021年

作者： Almadan, Ali Rattani, Ajita Dept. of Elec. Eng. and Computer Science Wichita State University Wichita United States

Face recognition technology related to recognizing identities is widely adopted in intelligence gathering, law enforcement, surveillance, and consumer applications. Recently, this technology has been ported to smartphones and body-worn cameras (BWC). Face recognition technology in body-worn cameras is used for surveillance, situational awareness, and keeping the officer safe. Only a handful of academic studies exist in face recognition using the body-worn camera. A recent study has assembled BWCFace facial image dataset acquired using a body-worn camera and evaluated the ResNet-50 model for face identification. However, for real-time inference in resource constraint body-worn cameras and privacy concerns involving facial images, on-device face recognition is required. To this end, this study evaluates lightweight MobileNet-V2, EfficientNetB0, LightCNN-9 and LightCNN-29 models for face identification using body-worn camera. Experiments are performed on a publicly available BWCface dataset. The real-time inference is evaluated on three mobile devices. The comparative analysis is done with heavy-weight VGG-16 and ResNet-50 models along with six hand-crafted features to evaluate the trade-off between the performance and model size. Experimental results suggest the difference in maximum rank-1 accuracy of lightweight LightCNN-29 over best-performing ResNet-50 is 1.85% and the reduction in model parameters is 23.49M. Most of the deep models obtained similar performances at rank-5 and rank-10. The inference time of LightCNNs is 2.1x faster than other models on mobile devices. The least performance difference of 14% is noted between LightCNN-29 and Local Phase Quantization (LPQ) descriptor at rank-1. In most of the experimental settings, lightweight LightCNN models offered the best trade-off between accuracy and the model size in comparison to most of the models. © 2021, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Spatial Reasoning via Deep Vision Models for Robotic Sequential Manipulation

Spatial Reasoning via Deep Vision Models for Robotic Sequent...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hongyou Zhou Ingmar Schubert Marc Toussaint Ozgur S. Oguz Technical University of Berlin Science of Intelligence Cluster of Excellence TUB Computer Eng. Dept. Bilkent University

In this paper, we propose using deep neural architectures (i.e., vision transformers and ResNet) as heuristics for sequential decision-making in robotic manipulation problems. This formulation enables predicting the subset of objects that are relevant for completing a task. Such problems are often addressed by task and motion planning (TAMP) formulations combining symbolic reasoning and continuous motion planning. In essence, the action-object relationships are resolved for discrete, symbolic decisions that are used to solve manipulation motions (e.g., via nonlinear trajectory optimization). However, solving long-horizon tasks requires consideration of all possible action-object combinations which limits the scalability of TAMP approaches. To overcome this combinatorial complexity, we introduce a visual perception module integrated with a TAMP-solver. Given a task and an initial image of the scene, the learned model outputs the relevancy of objects to accomplish the task. By incorporating the predictions of the model into a TAMP formulation as a heuristic, the size of the search space is significantly reduced. Results show that our framework finds feasible solutions more efficiently when compared to a state-of-the-art TAMP solver.

关键词：

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：