检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Subramanian, Ashwini Najafizadeh, Laleh Integrated System and NeuroImaging Laboratory Rutgers University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331520526

Detecting pain is critical for developing adaptive systems in clinical and assistive settings, allowing for timely interventions. This work presents an approach to detect the presence of physical pain during the performance of cognitive tasks from cortical signals. Cortical signals from the motor and prefrontal cortices are acquired using functional near in-frared spectroscopy (fNIRS) during two cognitive tasks, per-formed in the absence and presence of physical pain. Visibil-ity graphs (VGs) of these signals are constructed, and graph metrics of averaged clustering coefficient (C) and edge den-sity (D) are extracted. Statistical analysis reveals differences in these metrics for graphs corresponding to tasks performed under no-pain (NP) versus with-pain (WP) conditions, partic-ularly for signals obtained from the motor cortex. The graph metrics were then used as features to a support vector machine (SVM), achieving an accuracy exceeding 80% in distinguishing between tasks performed with and without pain. Our findings suggest that metrics from VGs of cortical sig-nals may serve as potential biomarkers for pain during cog-nitive tasks. This approach could be especially beneficial for non-verbal patients using assistive brain-computer interfaces. © 2025 IEEE.

关键词： Cognitive tasks fNIRS Pain SVM Visibility graphs

来源：评论

学校读者我要写书评

暂无评论

SSVEP Based BCI Control of an Exoskeleton 18th

SSVEP Based BCI Control of an Exoskeleton

引用

18th International Conference on Interdisciplinarity in engineering, INTER-ENG 2024

作者： Sibișanu, Remus Constantin Olar, Marius Leonard Roșca, Sebastian Daniel Leba, Monica Computer and System Control Engineering Department University of Petrosani 20 Universitatii Petrosani332006 Romania

ISBN: (纸本)9783031816840

This paper explores recent innovation in the field of robotic teleoperation, presenting a state-of-the-art system for a robotic arm, configurable as an exoskeleton or prosthetic limb. Based on noninvasive neural headset technology, the system captures movement intentions directly from the user’s neural activity. By precisely interpreting neural signals and translating them into robotic arm movements, the system bridges the gap between human intention and robotic action. Its uniqueness lies in its ability to interpret the subtleties of human intent through non-invasive means, providing intuitive and fluid control over the robotic arm. The system is distinguished by the efficient use of rich neural activity, thus improving usability and opening up new possibilities for people with mobility impairments. The paper analyzes technical complexities, detailing the functionality of neural headsets, signal decoding algorithms, and the command formation process for the robotic arm. It also presents empirical evidence of the effectiveness of the system and discusses possible applications and future improvements. This research not only contributes to robotic teleoperation, but also paves the way for more human and empathetic interactions with machines in the future. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Privacy and Security Implications of Mobile Apps 8

Evaluating the Privacy and Security Implications of Mobile A...

引用

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Mazumder, Shafiul Islam Shovon, Sazzadul Islam Chowdhury, Md Tanvir Islam, Minhajul Raisa, Habiba Azad Rahman, Habibur Sumon, Monjurul Islam Khan, Md. Khalid Mahbub American International University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System Michigan United States East West University Department of Computer Science and Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331520762

The rapid growth of mobile applications, combined with an increasing reliance on these apps for a variety of purposes, has prompted serious concerns about user privacy and data security. This study aims to assess the privacy practices, data handling methods, and security vulnerabilities of mobile apps in a variety of categories, including social media, e-commerce, health and fitness, and financial management. This study identifies major privacy and security issues by examining privacy policies and terms of service, as well as how these apps handle sensitive data. The study also examines free and premium apps' privacy procedures, taking into account the implications for user data protection. The findings illustrate differences in data handling and security standards across different app categories, highlighting the importance of transparent privacy policies, strong security mechanisms, and limited data sharing to protect user information. The research helps to define standards and best practices for promoting secure app activity, increasing user confidence, and guaranteeing a safer digital environment. © 2025 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Human arm motion capture system 9

Human arm motion capture system

引用

9th International Conference on Mathematics and computers in Sciences and Industry, MCSI 2024

作者： Olar, Marius Leonard Leba, Monica Ionica, Andreea University of Petrosani Department of System Control and Computer Engineering Petrosani Romania University of Petrosani Department of Management and Industrial Engineering Petrosani Romania

ISBN: (纸本)9798350377224

The implementation of robotics and human support technologies has opened up new possibilities for recovering the mobility impaired and increasing human productivity in the last few decades. Exoskeletons have been developed as a major component of this progress in order to capture any form of arm motion be it passive or active. Motion capture systems, employing different sensors like IMU sensors, EMG sensors, motion sensors, fiber optic sensors are used to capture arm movements. These sensors provide information on position, movement, muscle contraction, and movement intent of the arm. The use of multiple sensor types allows for redundancy and accurate outcomes. Potentiometer position sensor can be combined with other types of sensors to measure acceleration, orientation, force exerted and arm bendability. The combinations improve accuracy and adaptability for arm motion capture during rehabilitation. Various combinations of adapted sensors can be used for each joint of the hand depending on the peculiarities of application. Sensors enable precise and natural control over recovery devices or exoskeletons which is especially important in terms of rehabilitation process improvement. © 2024 IEEE.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

Architecture and Operational Control for Resilient Microgrids 60

Architecture and Operational Control for Resilient Microgrid...

引用

60th IEEE/IAS Industrial and Commercial Power systems Technical Conference, I and CPS 2024

作者： Correia, Alexandre F. M. Cavaleiro, Miguel Neves, Miguel Coimbra, A. Paulo Almeida, Tony R. O. Moura, Pedro De Almeida, Aníbal T. University of Coimbra Institute of System and Robotics Department of Electrical and Computer Engineering Coimbra Portugal

ISBN: (纸本)9798350345308

The increasing frequency of natural disasters has led to situations in which small urban centers and critical infrastructures become isolated from the main utility grid. The microgrids' ability to work autonomously from the utility grid presents a viable solution to this problem. Microgrid resiliency is the characteristic related to the capacity of a microgrid to minimize the impact of disruptive events and ensure that the power supply is maintained under a variety of adverse conditions. This is especially important for critical infrastructures such as hospitals, communications, computer networks and military bases. The objective of this paper is to simulate strategies and propose an algorithm for the design and management of electric microgrids with a focus on resiliency towards critical and disaster situations. The proposed solutions were validated, using an experimental microgrid implemented at the University of Coimbra as a pilot. As a result of the work, the study presents an algorithm that efficiently manages loads of a microgrid, including automatic islanding operation, in order to increase its resilience when the microgrid is isolated from the utility grid. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer for Audio-Based Depression Detection on Multi-Lingual Audio Data 24

Vision Transformer for Audio-Based Depression Detection on M...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Pratiwi, Monica Sanjaya, Samuel Ady Department of Computer Engineering Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Department of Information System Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia

ISBN: (纸本)9798400709586

Depression has the potential to impact death rates, particularly when it comes to death by suicide. Inadequate diagnosis may result in a delay or unsuitable therapy, which can worsen symptoms of depression. Unaddressed or insufficiently addressed depression can result in deteriorating mental well-being, which includes a higher risk of experiencing suicidal ideation and engaging in self-destructive actions. Voice analysis can be employed to distinguish between individuals with depression and those without depression. However, the research that has been conducted on voice recognition to distinguish between depressed and non-depressed individuals keeps focusing on the use of a single dataset source as input for the classification model that is being developed. This work utilizes the Vision Transformer model and various pre-trained transformers, such as DeiT (Data-Efficient Image Transformer) and Swin Transformer, to detect depression based on voice. The objective was to create a more generic model not restricted to a specific language. Integrating Mel-spectrogram characteristics with a vision transformer-based model can enhance the efficacy of voice recognition models when dealing with multi-language data. The result shows 21% higher accuracy than the previous study that also implemented a cross-dataset test. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data 41

Two-timescale Derivative Free Optimization for Performative ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Haitong Li, Qiang Wai, Hoi-To Department of Computer Science ETH Zurich Switzerland Department of System Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

This paper studies the performative prediction problem where a learner aims to minimize the expected loss with a decision-dependent data distribution. Such setting is motivated when outcomes can be affected by the prediction model, e.g., strategic classification. We consider a state-dependent setting where the data distribution evolves according to a controlled Markov chain. We focus on stochastic derivative free optimization (DFO) where the learner is given access to a loss function evaluation oracle with the above Markovian data. We propose a two-timescale DFO(λ) algorithm that features (i) a sample accumulation mechanism that utilizes every observed sample to estimate the gradient of performative risk, (ii) a two-timescale diminishing step size that balances the rates of DFO updates and bias reduction. Under a non-convex optimization setting, we show that DFO(λ) requires O(1/Ε3) samples (up to a log factor) to attain a near-stationary solution with expected squared gradient norm less than Ε. Numerical experiments verify our analysis. Copyright 2024 by the author(s)

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2023年第10期42卷 3289-3300页

作者： Nguyen, Thai-Hoang Imran, Muhammad Choi, Jaehyuk Yang, Joon-Sung Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical Engineering School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad44000 Pakistan Department of Semiconductor Systems Engineering Sungkyunkwan University Suwon16419 Korea Republic of School of Electrical and Electronic Engineering Department of System Semiconductor Engineering Yonsei University Seoul03722 Korea Republic of

Deep neural networks (DNNs) have emerged as the most effective programming paradigm for computer vision and natural language processing applications. With the rapid development of DNNs, efficient hardware architectures for deploying DNN-based applications on edge devices have been extensively studied. Emerging nonvolatile memories (NVMs), with their better scalability, nonvolatility, and good read performance, are found to be promising candidates for deploying DNNs. However, despite the promise, emerging NVMs often suffer from reliability issues, such as stuck-at faults, which decrease the chip yield/memory lifetime and severely impact the accuracy of DNNs. A stuck-at cell can be read but not reprogrammed, thus, stuck-at faults in NVMs may or may not result in errors depending on the data to be stored. By reducing the number of errors caused by stuck-at faults, the reliability of a DNN-based system can be enhanced. This article proposes CRAFT, i.e., criticality-aware fault-tolerance enhancement techniques to enhance the reliability of NVM-based DNNs in the presence of stuck-at faults. A data block remapping technique is used to reduce the impact of stuck-at faults on DNNs accuracy. Additionally, by performing bit-level criticality analysis on various DNNs, the critical-bit positions in network parameters that can significantly impact the accuracy are identified. Based on this analysis, we propose an encoding method which effectively swaps the critical bit positions with that of noncritical bits when more errors (due to stuck-at faults) are present in the critical bits. Experiments of CRAFT architecture with various DNN models indicate that the robustness of a DNN against stuck-at faults can be enhanced by up to 105 times on the CIFAR-10 dataset and up to 29 times on ImageNet dataset with only a minimal amount of storage overhead, i.e., 1.17%. Being orthogonal, CRAFT can be integrated with existing fault-tolerance schemes to further enhance the robustness of DNNs aga

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Integration of Reinforcement Learning in Industrial Pick-and-Place Robotics 21

Integration of Reinforcement Learning in Industrial Pick-and...

引用

21st International Bhurban Conference on Applied Sciences and Technology, IBCAST 2024

作者： Ul Ain Mushtaq, Noor Narejo, Sanam Memon, Madeha Korai, Fahad Ahmed Abbas, Azhar Jatoi, Sahil Mehran University of Engineering and Technology Department of Computer System Engineering Jamshoro Pakistan Tampere University Department of Biomedical Sciences and Engineering Tampere Finland Mehran University of Engineering and Technology Department of Biomedical Engineering Jamshoro Pakistan

ISBN: (纸本)9798331516680

Industrial robots have significantly transformed manufacturing processes and are increasingly revolutionizing sectors such as logistics, healthcare, agriculture, and construction by enhancing efficiency, quality, and safety, making them indispensable tools for modern industries. Industrial pick-and-place robotics, while significantly advancing, still faces several challenges like Object variability, Environmental factors, Task complexity, Precision and speed. Reinforcement learning (RL) offers a transformative approach to industrial pick-and-place robotics, addressing the limitations of traditional, pre-programmed methods. In order to overcome these challenges, the present research explores how reinforcement learning (RL) may assist robots to determine optimal picking and placing techniques without requiring explicit programming. We developed a framework that employs deep reinforcement learning (DRL) to create an autonomous pick-and-place system. Using Gazebo and ROS, we designed a simulated environment where the robotic arm is trained with Proximal Policy Optimization (PPO) and Deep Q-Network (DQN) algorithms. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

YOLO-Based Damage Detection with StyleGAN3 Data Augmentation for Parcel Information-Recognition system

引用

computers, Materials & Continua 2024年第7期80卷 195-215页

作者： Seolhee Kim Sang-Duck Lee Department of Electrical and Computer Engineering Sungkyunkwan UniversitySuwon16419Republic of Korea Logistics System Research Division Korea Railroad Research InstituteUiwang16105Republic of Korea

Damage to parcels reduces customer satisfactionwith delivery services and increases return-logistics *** can be prevented by detecting and addressing the damage before the parcels reach the ***,various studies have been conducted on deep learning techniques related to the detection of parcel *** study proposes a deep learning-based damage detectionmethod for various types of *** is intended to be part of a parcel information-recognition systemthat identifies the volume and shipping information of parcels,and determines whether they are damaged;this method is intended for use in the actual parcel-transportation *** this purpose,1)the study acquired image data in an environment simulating the actual parcel-transportation process,and 2)the training dataset was expanded based on StyleGAN3 with adaptive discriminator ***,3)a preliminary distinction was made between the appearance of parcels and their damage status to enhance the performance of the parcel damage detection model and analyze the causes of parcel ***,using the dataset constructed based on the proposed method,a damage type detection model was trained,and its mean average precision was *** model can improve customer satisfaction and reduce return costs for parcel delivery companies.

关键词： Parcel delivery service damage detection damage classification data augmentation generative adversarial network

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：