检索结果-内蒙古大学图书馆

13th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2024

作者： Pham, Huy Jackson, Clayton B. Armstead, Benjamin Nourse, William R. P. Andrada, Emanuel Quinn, Roger D. Department of Mechanical and Aerospace Engineering Case Western Reserve University ClevelandOH44106 United States Institute of Zoology and Evolutionary Research Friedrich-Schiller University Jena Germany Department of Electrical Computer and Systems Engineering Case Western Reserve University ClevelandOH44106 United States

ISBN: (纸本)9783031725968

This paper presents the design of robotic rat forelimbs, scaled to 2.5 times the size of a female Sprague-Dawley rat. Based on a previous rat hindlimb model, significant enhancements were implemented to facilitate manufacturing, robustness, improve overall performance, and enhance biological accuracy. The two front legs are each equipped with five motors to enable sagittal rotations of the scapula, elbow, and wrist joints, along with scapula abduction and adduction. The leg segment dimensions are based on a scanned rat bones model, but the shapes are modified for 3D printing and assembly. Parts are printed using micro carbon fiber filled nylon, strengthened by various amounts of continuously inlaid carbon fiber. Revolute joints are driven by motors, and a pulley-belt transmission system is incorporated to move wrist and elbow motors higher up in order to reduce the inertia of the leg. Furthermore, the foot structure comprises two segments that are passively controlled by two torsion springs to enhance flexibility and facilitate a more naturalistic movement. Additionally, a new electrical board is integrated to enhance operational smoothness and align with the control scheme. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection using deep learning approach for IoT smart city applications

引用

Multimedia Tools and Applications 2025年第17期84卷 17929-17949页

作者： Shibu, S. Kirubakaran, S. Remamany, Krishna Priya Ahamed, Suhail Chitra, L. Kshirsagar, Pravin R. Tirth, Vineet Department of Electronics and Communication Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering CMR College of Engineering and Technology Telangana Hyderabad501401 India Engineering Department College of Engineereing and Technology University of Technology an Applied Sciences PC Musandam811 Oman Machine Learning Software Engineer Paragon Semvox GmbH Saarland Kirkel Germany Department of Electrical and Electronics Engineering Aarupadai Veedu Institute of Technology Vinayaka Missions Research Foundation Tamil Nadu Chennai603104 India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Maharashtra Nagpur India Department of Mechanical Engineering College of Engineering King Khalid University Asir Abha61421 Saudi Arabia

With the advancements of IoT devices, many smart applications start to rule this era. In particular, smart cities has been adapted and realized by many countries around the world. In smart cities, vas amount of data is generated at every second. This vast data need a transmission medium which could be wireless standard. However, security is the main concern in such applications since the smart transmission always binds with anomalies. The existing anomaly detection systems need improvement in accuracy due to inefficient feature extraction and selection procedure. This paper proposes an accurate anomaly detection technique that built upon deep learning approach. We proposed a Combined Deep Q-Learning (CDQL) algorithm for anomaly detection. Priory, optimal features are selected by using Spider Monkey Optimizer (SMO). With the optimal features, CDQL detects anomalies accurately. In addition, the CDQL algorithm learns the environment in order to monitor the network data continuously. This continuous monitoring and optimum features helps in accuracy improvement up to 98%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automating life science labs at the single-cell level through precise ultrasonic liquid sample ejection:PULSE

引用

Microsystems & Nanoengineering 2024年第6期10卷 173-188页

作者： Peiran Zhang Zhenhua Tian Ke Jin Kaichun Yang Wesley Collyer Joseph Rufo Neil Upreti Xianjun Dong Luke P.Lee Tony Jun Huang Department of Mechanical Engineering and Materials Science Duke UniversityDurhamNC 27708USA Department of Mechanical Engineering Virginia Polytechnic Institute and State UniversityBlacksburgVA 24061USA Genomics and Bioinformatics Hub Department of NeurologyBrigham and Women’s HospitalHarvard Medical SchoolBostonMAUSA Department of Medicine Brigham and Women’s HospitalHarvard Medical SchoolBostonMAUSA Department of Bioengineering Department of Electrical Engineering and Computer ScienceUniversity of California at BerkeleyBerkeleyCAUSA Institute of Quantum Biophysics Department of BiophysicsSungkyunkwan UniversitySuwonKorea Department of Chemistry&Nanoscience Ewha Womans UniversitySeoulKorea

Laboratory automation technologies have revolutionized biomedical ***,the availability of automation solutions at the single-cell level remains scarce,primarily owing to the inherent challenges of handling cells with such small dimensions in a precise,biocompatible ***,we present a single-cell-level laboratory automation solution that configures various experiments onto standardized,microscale test-tube matrices via our precise ultrasonic liquid sample ejection technology,known as *** enables the transformation of titer plates into microdroplet arrays by printing nanodrops and single cells acoustically in a programmable,scalable,and biocompatible *** pipetting robots,PULSE enables researchers to conduct biological experiments using single cells as anchoring points(e.g.,1 cell vs.1000 cells per“tube”),achieving higher resolution and potentially more relevant data for modeling and downstream *** demonstrate the ability of PULSE to perform biofabrication,precision gating,and deterministic array barcoding via preallocated droplet-addressable *** cells can be gently printed at a speed range of 5–20 cell⋅s−1 with an accuracy of 90.5–97.7%,which can then adhere to the substrate and grow for up to 72 h while preserving cell *** the deterministic barcoding experiment,95.6%barcoding accuracy and 2.7%barcode hopping were observed by comparing the phenotypic data with known genotypic data from two types of single *** PULSE platform allows for precise and dynamic analyses by automating experiments at the single-cell level,offering researchers a powerful tool in biomedical research.

关键词： precise liquid offering

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement of Phasor Measurement Units Ensuring Power System Observability 14

Optimal Placement of Phasor Measurement Units Ensuring Power...

引用

14th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2022

作者： Rimal, Bishal Paudel, Nirmal Bhattarai, Aayush Kantipur Engineering College Department of Computer and Electronics Engineering Lalitpur Nepal Pulchowk Campus Department of Electrical Engineering Lalitpur Nepal Pulchowk Campus Department of Mechanical and Aerospace Engineering Lalitpur Nepal

ISBN: (纸本)9781665493345

Optimal Phasor measurement unit (PMU) placement is the strategic placement of a minimum number of PMUs to ensure power system observability. Optimal PMU placement (OPP) is essential to overcome the economic burden during the deployment of PMU on every bus. A strategy integrated with the modified Simulated Annealing (SA) algorithm is proposed in this paper with the consideration of the effect of the radial buses during the OPP problem. To recognize the superior placement set from diverse solutions given by the meta-heuristic algorithm, a placement set with the least number of PMUs and a higher system observability redundancy index (SORI) is used. In addition to modified SA, the strategy of ensuring or restricting the PMU placement on the radial bus has been implemented in MATLAB. In addition to the normal case, cases for single PMU outage and zero injection bus (ZIB) have been implemented in IEEE 14-bus, 30-bus, 57-bus, and 118-bus systems. The algorithm has been also used on the existing 90-bus Integrated Nepal Power System. The result of the proposed strategy on modified SA has improved the result in terms of the optimal number of PMUs, the probability of finding an optimal number of PMUs, and SORI. For normal cases, the number of PMUs required for complete power system observability is found to be in the range of 28-33% of the total number of buses. Similarly, with the consideration of single PMU outages and ZIB, the number of PMUs required is found to be in the range of 57-70% and 21-26% respectively. © 2022 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of SiC MOSFET Performance in a Traction Inverter 20

A Comparative Analysis of SiC MOSFET Performance in a Tracti...

引用

20th IEEE Asia Pacific Conference on Circuits and Systems and IEEE Asia Pacific Conference on Postgraduate Research in Microelectronics Electronics, APCCAS and PrimeAsia 2024

作者： Wu, Chih-Chiang Rout, Uma Sankar Wang, Yu-Long Lin, Yi-Ling Hu, Jwu-Sheng National Yang Ming Chiao Tung University Department of Electrical Engineering & Computer Science Taiwan Industrial Technology Research Institute Mechanical and Mechatronics Systems Research Laboratories Hsinchu Taiwan

ISBN: (纸本)9798350378771

This study rigorously tests and verifies silicon carbide (SiC) power modules within a developed 800 V electric vehicle traction inverter. SiC traction inverters offer high efficiency, power density, and compact size. The developed SiCbased traction inverter is thoroughly evaluated on the established platform with various switching frequency, achieving a peak drive efficiency exceeding 98% at 6 kHz and a power density of 50 kW/L. © 2024 IEEE.

关键词： Power MOSFET

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Shooting Rover via Situation Aware Visual-Perception and Dynamic Action Execution

Towards Autonomous Shooting Rover via Situation Aware Visual...

引用

2024 IEEE/SICE International Symposium on System Integration, SII 2024

作者： Chikoti, Shreenaga Shubham Seelam, Yukkta Jain, Aditya Mehta, Nishi Watsa, Sidhartha Ranjan, Ayush Behera, L. Indian Institute of Technology Kanpur Department of Mathematics and Scientific Computing India Indian Institute of Technology Kanpur Department of Material Science and Engineering India Indian Institute of Technology Kanpur Department of Electrical Engineering India Indian Institute of Technology Kanpur Department of Computer Science and Engineering India Indian Institute of Technology Kanpur Department of Mechanical Engineering India

ISBN: (纸本)9798350312072

In this system paper, we present our approach to the DJI Robomaster AI Challenge, 2022 where our team ERA-IITK was ranked 3rd worldwide among 83 teams. We primarily focus on system hardware design and algorithmic components to achieve full autonomy. We first detail the hardware infrastructure, including intricate details on sensors and communication setup. Then we comprehensively describe our algorithmic pipeline and a state machine based on them to realize an autonomous system. Our major novelty is the high-speed and accurate visual perception module for target detection, and high-speed self-localization to maximize the likelihood of a target being shot. Our research endeavor in this paper can serve as a foundation for more complex systems and holds immense potential for various real-world applications. © 2024 IEEE.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Live Demonstration: A fully embedded adaptive real-time hand gesture classifier leveraging HD-sEMG and deep learning

Live Demonstration: A fully embedded adaptive real-time hand...

引用

2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023

作者： Isabel, Xavier Labbe, Thomas Chamberland, Felix Buteau, Etienne Campbell, Evan Cote-Allard, Ulysse Tam, Simon Fortier, Paul Campeau-Lecours, Alexandre Boukadoum, Mounir Scheme, Erik Gosselin, Benoit Laval University Electrical Engineering and Computer Engineering Department Canada University of New-Brunswick Institute of Biomedical Engineering Canada University of Oslo Department off Technology Systems Norway Laval University Mechanical Engineering Department Canada University of Quebec at Montreal Computer Science Department Canada

ISBN: (纸本)9798350300260

In a fully immersive virtual reality setting, visitors will actively participate in our demonstration, engaging in an interactive videogame utilizing our cutting-edge HD-sEMG Bracelet. Prior to this, they will undergo state-of-the-art training to personalize their machine learning gesture recognition model. The gameplay will be broadcast on a computer monitor, allowing onlookers to observe while the demonstrator explains the core concept of our work. By wearing the bracelet, the player gains control over their limb in a game inspired by Simon Says. Throughout the demonstration, visitors will gain firsthand experience and knowledge about the forthcoming advantages of HD-sEMG for control applications, such as prosthesis control. They will also discover how the EMaGer HD-sEMG Bracelet capitalizes on its uniform and high electrode density to enhance the reliability of hand gesture recognition models utilized in myoelectric prosthesis control. © 2023 IEEE.

关键词： Armband Control Convolution Deep Learning Edge Computing Electromyography Gesture HD-EMG Machine Learning Myoelectric Neural Network

来源：评论

学校读者我要写书评

暂无评论

Development of a Movie AI Question Answering System Based on Knowledge Graph 4

Development of a Movie AI Question Answering System Based on...

引用

4th International Signal Processing, Communications and engineering Management Conference, ISPCEM 2024

作者： Xu, Yihan Xie, Nan Hu, Xinjun Chen, Weimin College of Computer Science and Technology Zhejiang University of Water Resources and Electric Power Zhejiang Hangzhou China College of Mechanical and Electrical Engineering China Jiliang University Zhejiang Hangzhou China

ISBN: (纸本)9798331528676

With the increasing influence of the internet, information retrieval technology needs to be continuously upgraded. The development of the internet drives the transformation of the film industry, with an increase in the number of online movies, a flourishing of professional film websites and forums, and an increasing influence of online comments. There are still shortcomings in the relationship between the internet and film evaluation, and further exploration is needed. The development of this system adopts a front-end and back-end separation mode, with Vue technology architecture used in the front-end and Django framework used in the back-end. The knowledge graph can organize and express movie information, providing data support for intelligent question answering and comment systems. The system constructs a graph by collecting movie data, achieving storage, management, and querying, providing intelligent and personalized services, and designing movie review functions to provide comprehensive information and evaluation references;The question answering function is implemented through natural language processing technology (NLP) and graph database technology, which can recognize the user's query intention and retrieve relevant information, generate accurate and concise answers. Its core module is the movie AI question answering function based on Neo4j. After the user raises a question, the comment system will parse the question and construct a Cypher query statement. After execution, the result will be returned and displayed to the user, achieving intelligent answers and personalized services. In system design, the connection between the movie AI question answering module and the Neo4j database is crucial. This connection enables effective communication and information exchange between user questions and movie knowledge graphs, providing users with convenient and accurate movie related information. Through deep integration with the Neo4j database, the system can bette

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Performance-Barrier Periodic Event-Triggered PDE Control of Traffic Flow 63

Performance-Barrier Periodic Event-Triggered PDE Control of ...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhang, Peihan Rathnayake, Bhathiya Diagne, Mamadou Krstic, Miroslav University of California San Diego Department of Mechanical and Aerospace Engineering 9500 Gilman Dr La Jolla CA9500 United States University of California San Diego Department of Electrical and Computer Engineering 9500 Gilman Dr La Jolla CA92093 United States

ISBN: (纸本)9798350316339

This paper enhances the recently introduced performance-barrier-based continuous-time event-triggered control (P-CETC) by introducing a periodically evaluated triggering function, which leads to the proposed performance-barrier-based periodic event-triggered control (P-PETC). This approach aims to stabilize stop-and-go oscillations in traffic flow through the activation of variable speed limits (VSL) at the downstream boundary of a freeway segment, described by the linearized Aw-Rascle-Zhang (ARZ) traffic model-a 2 × 2 coupled hyperbolic system. P-PETC preserves the flexibility of P-CETC, which allows the Lyapunov function to increase within a performance barrier. This results in fewer control updates than regular continuous-time event-triggered control (R-CETC), where a strict decrease in the Lyapunov function is mandated. Furthermore, P-PETC guarantees exponential convergence to zero in the spatial L2 norm and ensures a Zeno-free behavior. Through comparative simulations, P PETC is shown to match P-CETC in traffic metrics such as driver comfort, total travel time, and fuel consumption. Notably, P-PETC significantly reduces discomfort by nearly 50 % compared to the open-loop scenario and increases the average dwell time by up to 8 times relative to R-CETC. © 2024 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances

arXiv

引用

arXiv 2024年

作者： Xu, Wenting Ila, Viorela Zhou, Luping Jin, Craig T. School of Electrical and Computer Engineering The University of Sydney Australia School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney Australia

The concept of function and affordance is a critical aspect of 3D scene understanding and supports task-oriented objectives. In this work, we develop a model that learns to structure and vary functional affordance across a 3D hierarchical scene graph representing the spatial organization of a scene. The varying functional affordance is designed to integrate with the varying spatial context of the graph. More specifically, we develop an algorithm that learns to construct a 3D hierarchical scene graph (3DHSG) that captures the spatial organization of the scene. Starting from segmented object point clouds and object semantic labels, we develop a 3DHSG with a top node that identifies the room label, child nodes that define local spatial regions inside the room with region-specific affordances, and grand-child nodes indicating object locations and object-specific affordances. To support this work, we create a custom 3DHSG dataset that provides ground truth data for local spatial regions with region-specific affordances and also object-specific affordances for each object. We employ a Transformer Based Hierarchical Scene Understanding model (TB-HSU) to learn the 3DHSG. We use a multi-task learning framework that learns both room classification and learns to define spatial regions within the room with region-specific affordances. Our work improves on the performance of state-of-the-art baseline models and shows one approach for applying transformer models to 3D scene understanding and the generation of 3DHSGs that capture the spatial organization of a room. The code and dataset are publicly available. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task 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：