检索结果-内蒙古大学图书馆

IEEE SENSORS

作者： Manuel Reis Carneiro Luis Rosa Mahmoud Tavakoli Dept. of Electrical and Comp. Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal Dept. of Mechanical Engineering Soft Machines Lab Carnegie Mellon University Pittsburgh Pennsylvania United States

This article presents a low-cost, and scalable method for synthesizing large sheets of functionalized foam for soft resistive pressure sensing that is compatible with any commercially available non-conductive foam. The process is illustrated by soaking Pu (Polyurethane) foam in a carbon-based polymeric mixture resulting in a functional foam with large pressure detection range up to 500 kPa, while retaining its deformability and recoverability after cyclic compression. The foam also shows unprecedentedly fast response time of ~120 ms. The foam was integrated in a wearable respiration sensor and in a large multitouch sensing mat that allows for precise data acquisition on the position and intensity of various simultaneous touches without the occurrence of ghost touches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Processing of Corneal Images with A Cepstral Approach 23

Processing of Corneal Images with A Cepstral Approach

引用

23rd International Conference on Computer Theory and Applications, ICCTA 2013

作者： Tawfik, Nahed El Din, Mahmoud F. Dessouky, Moawad I. Abd Ei-Samie, Fathi E. Electronics Research Institute Computers and Systems Dept. Dokki-Giza Egypt Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Menouf Egypt

ISBN: (纸本)9781479924158

The Mel-Frequency Cepstral Coefficients (MFCCs) feature extraction approach can be used for corneal pattern recognition, and hence in the diagnosis of corneal diseases. In this method, cepstral features are extracted from a group of corneal images. Images are first transformed to 1-D signals by lexicographic ordering, and then MFCCs and polynomial shaping coefficients are extracted to form a database of features, which can be used to train a neural network. With the same method used in the training phase, features are extracted from a new group of images. These features can be tested with the neural network. Different transform domains can be used for this purpose. Experimental results show that the Discrete Cosine Transform (DCT) is the most suitable domain for feature extraction. The method in this paper is limited to feature extraction for pattern recognition and the automatic diagnosis case is left for future work. © 2013 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Localization of Dengue Virus Likelihood Using Image Processing Technique

Localization of Dengue Virus Likelihood Using Image Processi...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Md. Mahbub Hosen Md. Rahatul Islam Faria Tabassum Syeda Thamina Tonni Malik Mohammad Nafiur Noor Shahid Rahman Dept. of Computer Science & Engineering Northern University of Bangladesh Dhaka Bangladesh Dept. of Human Intelligence Systems Kyushu Institute of Technology Wakamatsu Kitakyushu Japan Dept. of Computer Science & Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Human Intelligence Lab Bangladesh Advance Robotics Research Center Dhaka Bangladesh Dept. of Electrical & Electronic Engineering Canadian University of Bangladesh Dhaka Bangladesh

The Aedes mosquito, found in tropical areas, transmits, and causes dengue fever. The spread of the dengue fever virus from an infected Aedes mosquito bite typically takes between three and fifteen days to manifest itself clinically as dengue fever symptoms. Early and automated detection of this illness will reduce the occurrence of outbreaks and facilitate the digitization of the system. Our primary objective is to identify regions at high risk for dengue fever using limited image data through the utilization of sophisticated machine learning and image processing methods. This work showcases the application of transfer learning algorithms for the timely identification of regions at risk for dengue mosquito infestation, particularly in situations where obtaining early data on dengue outbreaks is challenging. The experiments included images of 2150 dengue-positive data sets and 1440 dengue-negative data sets. We used AI and image classifiers Yolo V4 Tin, Tensor Flow, Google Colab, etc. for the training data set, and the system makes predictions with a 99.63% accuracy rate. Our system has some unique attributes; it not only detects the percentage of dengue probability but also the specific dengue-prone location on the submitted image.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VVoIP Quality Improvement Over IMS Network based on background subtraction

VVoIP Quality Improvement Over IMS Network based on backgrou...

引用

Learning and Technology Conference (L&T)

作者： Hanafy M. Ali Aziza I. Hussein Waled M. Ismail Yahia B. Hassan Computers and Systems Engineering Dept. Faculty of Engineering Minia University El Minia Egypt College of Engineering Energy and Technology Research Center Effat University Saudi Arabia Mobile Core Back Office Engineer Telecom Egypt Co. Egypt Electrical Eng. Dept Higher Institute of Engineering Minia Egypt

The dependence on making Voice and Video over Internet Protocol (VVoIP) calls has increased dramatically in recent times. The use of VVoIP applications is not limited to social applications only but extended to business applications. The improvement of VVoIP call quality is one of the most important factors that enhance the spread of VVoIP services. In many cases, the high network traffic prevents the possibility of sending high data rate live video streams as sending high data rate live stream over high-traffic networks causes an increase in the data loss *** this paper, the codec switching techniques used to improve the quality under live networks with high traffic are discussed. In addition, A technique based on background subtraction to improve the quality of VVoIP calls using Python code to detect the moving pixels (foreground) and subtract them from the frame to discard the background is *** proposed technique was tested on large scale live network. The tested parameters impacting the Quality of Service (QoS) were packet loss and delay variation (Jitter). The study based on the comparison of packet loss and Jitter for the three common resolutions 480P, 720P and, 1080P over high traffic network without using background subtraction vs. using background subtraction. The results showed a significant improvement in different rates for each resolution and network condition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving ASTRO's Perception Capability for a more Natural Follow-Me Task

Improving ASTRO's Perception Capability for a more Natural F...

引用

Experiment@ International Conference (exp.at)

作者： Bruno Ferreira Alessandra Sorrentino Paulo Menezes Jorge Batista Jorge Dias Laura Fiorini Filipo Cavallo Dept. of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Coimbra Portugal Dept. of Industrial Engineering University of Florence Florence Italy Khalifa University Center for Autonomous Robotic Systems Khalifa University of Science and Technology Abu Dhabi UAE BioRobotics Institute Scuola Superiore Sant'Anna Pisa Italy

ISBN: (数字)9798350314403

ISBN: (纸本)9798350314410

Social assistive robots usually encompass a great compromise between the advanced perception models that one can use and their computing capabilities. The ideal approaches are always oriented towards low power consumption while maintaining a higher order of responsiveness to the surroundings. Therefore, we present in this paper, an improvement of the follow-me system on ASTRO. In detail, we propose the use of Mediapipe SDK for human detection and tracking, when ASTRO is meant to accompany someone that is walking. A study on the new velocity and distance profiles that the robot keeps from the individuals is presented and we have also evaluated how it affects their perception of being safe. The presented results show that our new approach allows the system to achieve real-time performance by becoming $\approx 9.1\times \mathbf{faster}$ , smoothing, and keeping a more natural distance from the user.

关键词： Legged locomotion Smoothing methods Power demand Computational modeling Robot vision systems Pose estimation Cameras

来源：评论

学校读者我要写书评

暂无评论

Modular Cyber-Physical System for Smart Industry: a case study on energy load disaggregation

Modular Cyber-Physical System for Smart Industry: a case stu...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Jorge Alves Pedro Sousa Bárbara Matos Jérôme Mendes Francisco Souza Tiago Matias Department of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Coimbra Portugal Oncontrol Technologies Coimbra Portugal Dept. Analytical Chemistry & Chemometrics Radboud University Nijmegen AJ Netherlands

Constant changes have marked the industry, and cyber-physical systems have offered great potential in Industry 4.0 on production processes, allowing the integration of computational intelligence and real-time processing. In this context, this paper proposes a modular hardware system for industrial applications according to a plug & play concept. The proposed system comprises a processing module (mPP) and specific expansion modules (mEXs). The mPP is responsible for administrating the network/communication. It collects data from the mEXs, extracts features, processes the features through artificial intelligence, and interacts with the production process. The mEXs comprise sensors, conditioning circuits, and an analog/digital converter. They are responsible for acquiring field signals and their transmission to the mPP. The proposed system is designed for operating with electrical protection, allowing reliable operation of the mPP and mEXs. For evaluating and demonstrating the proposed system in a real scenario, we applied it in a case study for non-intrusive energy load disaggregation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Goal-based Movement via Motivational-based Models in Cognitive Mobile Robots

arXiv

引用

arXiv 2023年

作者： Berto, Letícia Costa, Paula Simões, Alexandre Gudwin, Ricardo Colombini, Esther Laboratory of Robotics and Cognitive Systems Institute of Computing University of Campinas Brazil Dept. of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Brazil Dept. of Control and Automation Engineering Institute of Science and Technology São Paulo State University Sorocaba Brazil University of Campinas Brazil

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action’s perceived pleasure, which is susceptible to changes over time. This makes decision-making more complex, requiring learning to balance needs and preferences according to the context. To understand how this process works and enable the development of robots with a motivational-based learning model, we computationally model a motivation theory proposed by Hull. In this model, the agent (an abstraction of a mobile robot) is motivated to keep itself in a state of homeostasis. We added hedonic dimensions to see how preferences affect decision-making, and we employed reinforcement learning to train our motivated-based agents. We run three agents with energy decay rates representing different metabolisms in two different environments to see the impact on their strategy, movement, and behavior. The results show that the agent learned better strategies in the environment that enables choices more adequate according to its metabolism. The use of pleasure in the motivational mechanism significantly impacted behavior learning, mainly for slow metabolism agents. When survival is at risk, the agent ignores pleasure and equilibrium, hinting at how to behave in harsh scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning Techniques for Predicting False Data Injection Attacks in Smart Grid

Application of Machine Learning Techniques for Predicting Fa...

引用

International Middle-East Power System Conference, MEPCON

作者： Hesham A. Sakr Abdelfattah A. Eladl Hegazi M. Ibrahim Magda I. El-Afifi Faculty of Engineering Technology Elsewedy University of Technology Cairo Egypt Dept. of Elect. and Comm.Eng Nile Higher Institute for Eng. and Technology Mansoura Egypt Electrical Engineering Department Faculty of Engineering Mansoura University El-Mansoura Egypt Faculty of Computers and Information Systems Egyptian Chinese University Cairo Egypt

ISBN: (数字)9798350379648

ISBN: (纸本)9798350379655

Attacks that involve False Data Injection (FDI) provide a substantial risk to the safety and dependability of contemporary power systems. The weaknesses that are present inside the system's infrastructure are exploited by these attacks, which frequently circumvent the conventional measures that detect bad data. Because of the sophistication of these attacks, which are characterized by their ability to circumvent conventional protections and their targeted nature, it is necessary to develop novel techniques to detection and mitigation. For the purpose of identifying, preventing, and predicting FDI threats, this research studies the application of machine learning approaches. In order to improve the security posture of power systems, the strategy that has been developed intends to make use of the potential that data-driven models possess. According to preliminary findings, the approach that was developed demonstrates a high level of accuracy in identifying anomalies within the data of the system, which suggests that it has the potential to be an effective countermeasure against FDI threats. In particular, Extra Trees and XGBClassifier are quite efficient when it comes to identifying attacks that include the injection of bogus data into power systems.

关键词： Accuracy Prevention and mitigation Feature extraction Data models Power systems Smart grids Complexity theory Security Ensemble learning Protection

来源：评论

学校读者我要写书评

暂无评论

“Should I Lead?” Feasibility Study of User Perception on Following-Robot for Gait Assessment

“Should I Lead?” Feasibility Study of User Perception on F...

引用

International Conference on Advanced robotics (ICAR)

作者： Alessandra Sorrentino Bruno Ferreira Paulo Menezes Jorge Batista Jorge Dias Laura Fiorini Pietro Benvenuti Filippo Cavallo Department of Industrial Engineering University of Florence Florence Italy Dept. of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Coimbra Portugal Khalifa University of Science and Technology Khalifa University Center for Autonomous Robotic Systems Abu Dhabi UAE BioRobotics Institute Scuola Superiore Sant'Anna Pisa Italy

Current techniques of gait assessment rely on wearable sensors, pressure-sensitive walkway systems, and optical motion capture systems. A less invasive and more portable solution could be represented by a mobile robot that follows the user during the gait activity. The main idea behind this work relies on finding the best robot configuration for less invasive gait analysis with high acceptability from the end users. To this aim, two follow-me configurations have been designed: human-leader (i.e. the robot follows the person from behind), and robot-leader (i.e. robot follows the person from the front). We asked 27 young participants to test both modalities and to evaluate their perception of the robot in 5 domains: comfort, expected conformity, safety, trust, and unobtrusiveness. Additionally, we extracted quantitative parameters related to the walking experience from the data recorded by the platform and we analyzed them in tandem with the qualitative results. The results reported that robot-leader configuration tended to be more appreciated in terms of comfort, trust, and safety. On the contrary, the human-leader configuration is perceived as less obtrusive, less invasive, and in line with users' expectations. Considering the gait assessment application, we expect the human-leader configuration to return more promising and accurate results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reputation-based resilient consensus with privacy guarantees

引用

IEEE Transactions on Control of Network systems 2025年

作者： Ramos, Guilherme Pequito, Sergio Silvestre, Daniel University of Lisbon Dept. of Computer Science and Engineering Instituto Superior Técnico Portugal Instituto de Telecomunicações Lisbon1049-001 Portugal Universidade de Lisboa Dept. of Electrical and Computer Engineering Instituto Superior Técnico Lisbon1049-001 Portugal University of Lisbon Institute for Systems and Robotics Instituto Superior Técnico Portugal NOVA University of Lisbon FCT/UNL School of Science and Technology Caparica2829-516 Portugal COPELABS Lusófona University Portugal

Reputation-based consensus methods have gained significant attention in distributed systems to mitigate the impact of malicious agents and ensure reliable decision-making. However, privacy concerns arise when sensitive information is shared among participants. In this paper, we propose a reputation-based consensus method that incorporates resilience and privacy guarantees, providing a balance between preserving participants' privacy and maintaining the accuracy of the resilient consensus process. Our approach leverages the notion of privacy to add noise to the agents' states, ensuring that individual contributions are masked while still enabling the detection of malicious behavior. We present a detailed analysis of the privacy-accuracy trade-off and demonstrate the effectiveness of our method through simulations. The results show that our reputation-based consensus method with privacy guarantees offers robustness against attacks while preserving the privacy of participants, making it a promising solution for privacy-conscious resilient distributed systems. © 2014 IEEE.

关键词： Sensitive data

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：