检索结果-内蒙古大学图书馆

Iranian Conference on Electrical Engineering (ICEE)

作者： Arash Akbari Arman Akbari Mehdi Tale Masouleh Department of Computer Science University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering Tehran Iran

Robot grasping is of paramount importance in industrial and service robotics. In recent years, various data-driven algorithms have been proposed to solve the problem of grasp detection and a part of them are based on reinforcement learning (RL) approaches. In a variety of proposed algorithms, random key points are being employed which will make the learning process inefficient and time-consuming. In this paper, a geometry-based algorithm is presented which can find grasp poses based on the geometry of the unknown object and propose the ones which may lead to successful grasping. For the grasp contacts computation part, the presented algorithm produces a finite number of key points based on the 2D shape of the object from a specific point of view. Afterward, it will narrow down the candidate points and output a finite number of successful grasp poses based on three grasp quality metrics for various unknown objects. Three approaches are proposed in order to achieve center points which can describe different parts of a 2D shape. Then, the obtained points are used as the center of circles which are tangent to the 2D shape contour. Also, a new grasp quality metric is proposed. The time of the grasp and the amount of object disorientation after grasping are considered as a metric to evaluate the successfulness of the grasp. Simulation results demonstrate that the proposed algorithm for unknown object grasping can find a finite number of successful grasp poses for different seen or unseen objects without using any random point,

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOWARD ADVERSARIAL TRAINING ON CONTEXTUALIZED LANGUAGE REPRESENTATION 11

TOWARD ADVERSARIAL TRAINING ON CONTEXTUALIZED LANGUAGE REPRE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Wu, Hongqiu Liu, Yongxiang Shi, Hanwen Zhao, Hai Zhang, Min Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology Soochow University Suzhou China

Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named entity recognition. This paper investigates AT from the perspective of the contextualized language representation outputted by PLM encoders. We find the current AT attacks lean to generate sub-optimal adversarial examples that can fool the decoder part but have a minor effect on the encoder. However, we find it necessary to effectively deviate the latter one to allow AT to gain. Based on the observation, we propose simple yet effective Contextualized representation-Adversarial Training (CreAT), in which the attack is explicitly optimized to deviate the contextualized representation of the encoder. It allows a global optimization of adversarial examples that can fool the entire model. We also find CreAT gives rise to a better direction to optimize the adversarial examples, to let them less sensitive to hyperparameters. Compared to AT, CreAT produces consistent performance gains on a wider range of tasks and is proven to be more effective for language pretraining where only the encoder part is kept for downstream tasks. We achieve the new state-of-the-art performances on a series of challenging benchmarks, e.g. AdvGLUE (59.1 → 61.1), HellaSWAG (93.0 → 94.9), ANLI (68.1 → 69.3). © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Clustering Approaches for Gait Analysis within Neurological Disorders: A Narrative Review

引用

Digital Biomarkers 2024年第1期8卷 93-101页

作者： Hummel, Jonas Schwenk, Michael Seebacher, Daniel Barzyk, Philipp Liepert, Joachim Stein, Manuel Department of Computer and Information Science University of Konstanz Konstanz Germany Human Performance Research Centre University of Konstanz Konstanz Germany Research and Development Subsequent GmbH Konstanz Germany Neurologische Rehabilitation Kliniken Schmieder Allensbach Germany

Background: The prevalence of neurological disorders is increasing, underscoring the importance of objective gait analysis to help clinicians identify specific deficits. Nevertheless, existing technological solutions for gait analysis often suffer from impracticality in daily clinical use, including excessive cost, time constraints, and limited processing capabilities. Summary: This review aims to evaluate existing techniques for clustering patients with the same neurological disorder to assist clinicians in optimizing treatment options. A narrative review of thirteen relevant studies was conducted, characterizing their methods, and evaluating them against seven criteria. Additionally, the results are summarized in two comprehensive tables. Recent approaches show promise;however, our results indicate that, overall, only three approaches display medium or high process maturity, and only two show high clinical applicability. Key Messages: Our findings highlight the necessity for advancements, specifically regarding the use of markerless optical tracking systems, the optimization of experimental plans, and the external validation of results. This narrative review provides a comprehensive overview of existing clustering techniques, bridging the gap between instrumented gait analysis and its real-world clinical utility. We encourage researchers to use our findings and those from other medical fields to enhance clustering techniques for patients with neurological disorders, facilitating the identification of disparities within groups and their extent, ultimately improving patient outcomes. © 2024 The Author(s). Published by S. Karger AG, Basel.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Cloud Resource Scheduling with an Optimized Throttled Load Balancing Approach

引用

computers, Materials & Continua 2023年第11期77卷 2179-2188页

作者： V.Dhilip Kumar J.Praveenchandar Muhammad Arif Adrian Brezulianu Oana Geman Atif Ikram Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai600062India Department of Computer Science and Engineering Karunya Institute of Technology and SciencesCoimbatoreTamil Nadu641114India Department of Computer Science Superior UniversityLahorePakistan Faculty of Electronics Telecommunications and Information Technology Gheorghe Asachi Technical University of IasiIa¸si700050Romania Department of Health and Human Development Stefan cel Mare University of SuceavaSuceava720229Romania Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala NerusMalaysia

Cloud Technology is a new platform that offers on-demand computing Peripheral such as storage,processing power,and other computer system *** is also referred to as a system that will let the consumers utilize computational resources like databases,servers,storage,and intelligence over the *** a cloud network,load balancing is the process of dividing network traffic among a cluster of available servers to increase *** is also known as a server pool or server *** a single node is overwhelmed,balancing the workload is needed to manage unpredictable *** load balancer sends the load to another free node in this *** focus on the Balancing of workflows with the proposed approach,and we present a novel method to balance the load that manages the dynamic scheduling *** of the preexisting load balancing techniques is considered,however it is somewhat modified to fit the scenario at *** on the experimentation’s findings,it is concluded that this suggested approach improves load balancing consistency,response time,and throughput by 6%.

关键词： Load balancing throttled algorithm efficient resource allocation

来源：评论

学校读者我要写书评

暂无评论

What Lies Beneath? Exploring the Impact of Underlying AI Model Updates in AI-Infused Systems

arXiv

引用

arXiv 2023年

作者： Mohanty, Vikram Lim, Jude Luther, Kurt Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Independent Researcher ArlingtonVA United States Department of Computer Science Center for Human-Computer Interaction Virginia Tech AlexandriaVA United States

AI models are constantly evolving, with new versions released frequently. human-AI interaction guidelines encourage notifying users about changes in model capabilities, ideally supported by thorough benchmarking. However, as AI systems integrate into domain-specific workflows, exhaustive benchmarking can become impractical, often resulting in silent or minimally communicated updates. This raises critical questions: Can users notice these updates? What cues do they rely on to distinguish between models? How do such changes affect their behavior and task performance? We address these questions through two studies in the context of facial recognition for historical photo identification: an online experiment examining users’ ability to detect model updates, followed by a diary study exploring perceptions in a real-world deployment. Our findings highlight challenges in noticing AI model updates, their impact on downstream user behavior and performance, and how they lead users to develop divergent folk theories. Drawing on these insights, we discuss strategies for effectively communicating model updates in AI-infused systems. © 2023, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring Assumptions about Sustainability: Towards a Constructive Framework for Action in Sustainable HCI 25

Exploring Assumptions about Sustainability: Towards a Constr...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI 2025

作者： Laurell Thorslund, Minna Leifler, Ola Media Technology and Interaction Design KTH Royal Institute of Technology Stockholm Sweden Department of Computer and Information Science Linköping University Linköping Sweden

ISBN: (纸本)9798400713941

The global environmental crises continue to get worse, fast approaching various irreversible thresholds. While a vast array of approaches to solving sustainability problems are found under the umbrella of Sustainable HCI, their contributions are sometimes hard to compare. In this essay, we describe a set of assumptions that influence what is considered meaningful and important areas of sustainability research, along four dimensions of sustainability: 1) the depth and nature of the sustainability challenges;2) the role of technological innovation in sustainability;3) what gets defined as "externalities"to a design or system;and 4) the time perspective used to consider sustainability. We argue that what one assumes within each of these dimensions directly influences what one means by the term "sustainability", which is then reflected in the questions that are asked, the methods chosen, the proposed solutions and the developed systems. By describing these assumptions and some of their commensurate actions, we offer a framework that may enable members of the SHCI community to reflect on and better position their own work and that of others in the field. Our intention is for the framework to lead to better transparency and more constructive conversations about where we might collectively direct our efforts moving forward. © 2025 Copyright held by the owner/author(s).

关键词： Green development

来源：评论

学校读者我要写书评

暂无评论

Improving the Interpretability Through Maximizing Mutual Information for EEG Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年第2期16卷 744-757页

作者： Yang, Hua Chen, C. L. Philip Chen, Bianna Zhang, Tong North Carolina State University Department of Computer Science RaleighNC27695 United States South China University of Technology Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition The School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou510335 China

Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling emotional connections between EEG channels. However, these GNNs lack interpretability due to the absence of explicit rationale behind their predictions. This paper conducts a comprehensive identification of important EEG channels to enhance the interpretability of EEG emotion recognition from the perspective of mutual information. Specifically, an Adjacency-Explainable Graph Neural Network (AEG) for ante-hoc interpretability is proposed to capture genuine EEG emotional connections, which gives a theoretical guarantee to remove spurious connections. Moreover, a Channel-wise Adaptive Class Activation Mapping Explainer (CACA) for post-hoc interpretability is developed to locate the EEG channels that contribute most to predictions. Experimental results on three datasets, i.e., SEED, SEED-IV, and DREAMER, prove that imbuing training processes with enhanced interpretability ensures significant performance improvements in emotion recognition. Quantitative comparisons of post-hoc interpretability also demonstrate the superiority of CACA. Furthermore, this paper illustrates two potential applications of the proposed methodologies, showing their broader utility and significance. © 2010-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Disclosure in Digital Healthcare: Enhancing User Engagement

Self-Disclosure in Digital Healthcare: Enhancing User Engage...

引用

2023 IEEE International Conference on Agents, ICA 2023

作者： Goh, Michelle Jeong, Harim Yoo, Joo Hun Han, Oakyoung Sungkyunkwan University Department of Interaction Science Seoul Korea Republic of Sungkyunkwan University Department of Artificial Intelligence Suwon Korea Republic of Sungkyunkwan University Department of Computer Education Seoul Korea Republic of

ISBN: (纸本)9798350312782

In the growing digital healthcare field, enhancing user engagement is crucial for the sustained usage of e-intervention treatments. This study focuses on improving user engagement by investigating how users interact with agents in a conversational context. To achieve this, we examined communication techniques for building relationships in counseling and selected self-disclosure (SD) as our approach to assess its effectiveness. We created conversational scripts based on iCBT, a prevalent psychotherapy method in digital mental healthcare, and conducted an empirical study with 40 participants. Participants were randomly assigned to two groups: one that contained SD and one without. Our analysis focused on the user experience and its impact on engagement. The findings indicate that employing SD enhances user engagement, agent perception, and intention to use. Conversely, conversations without SD are perceived as task-focused, resulting in reduced engagement and intention to use. This study serves as a foundation for understanding the potential of SD and underscores the need for further exploration in diverse digital healthcare contexts. © 2023 IEEE.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

TouchPose: Hand Pose Prediction, Depth Estimation, and Touch Classification from Capacitive Images 21

TouchPose: Hand Pose Prediction, Depth Estimation, and Touch...

引用

34th Annual ACM Symposium on User Interface Software and Technology, UIST 2021

作者： Ahuja, Karan Streli, Paul Holz, Christian Human-Computer Interaction Institute Carnegie Mellon University United States Department of Computer Science ETH Zürich Switzerland

ISBN: (纸本)9781450386357

Today's touchscreen devices commonly detect the coordinates of user input through capacitive sensing. Yet, these coordinates are the mere 2D manifestations of the more complex 3D configuration of the whole hand - a sensation that touchscreen devices so far remain oblivious to. In this work, we introduce the problem of reconstructing a 3D hand skeleton from capacitive images, which encode the sparse observations captured by touch sensors. These low-resolution images represent intensity mappings that are proportional to the distance to the user's fingers and hands. We present the first dataset of capacitive images with corresponding depth maps and 3D hand pose coordinates, comprising 65,374 aligned records from 10 participants. We introduce our supervised method TouchPose, which learns a 3D hand model and a corresponding depth map using a cross-modal trained embedding from capacitive images in our dataset. We quantitatively evaluate TouchPose's accuracy in touch classification, depth estimation, and 3D joint reconstruction, showing that our model generalizes to hand poses it has never seen during training and can infer joints that lie outside the touch sensor's volume. Enabled by TouchPose, we demonstrate a series of interactive apps and novel interactions on multitouch devices. These applications show TouchPose's versatile capability to serve as a general-purpose model, operating independent of use-case, and establishing 3D hand pose as an integral part of the input dictionary for application designers and developers. We also release our dataset, code, and model to enable future work in this domain. © 2021 Owner/Author.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

In Time and Space: Towards Usable Adaptive Control for Assistive Robotic Arms

arXiv

引用

arXiv 2023年

作者： Pascher, Max Kronhardt, Kirill Goldau, Felix Ferdinand Frese, Udo Gerken, Jens The Westphalian University of Applied Sciences Human-Computer Interaction Gelsenkirchen45897 Germany The University of Duisburg-Essen Human-Computer Interaction Essen45127 Germany The University of Bremen Mathematics & Computer Science Bremen28359 Germany

Robotic solutions, in particular robotic arms, are becoming more frequently deployed for close collaboration with humans, for example in manufacturing or domestic care environments. These robotic arms require the user to control several Degrees-of-Freedom (DoFs) to perform tasks, primarily involving grasping and manipulating objects. Standard input devices predominantly have two DoFs, requiring time-consuming and cognitively demanding mode switches to select individual DoFs. Contemporary Adaptive DoF Mapping Controls (ADMCs) have shown to decrease the necessary number of mode switches but were up to now not able to significantly reduce the perceived workload. Users still bear the mental workload of incorporating abstract mode switching into their workflow. We address this by providing feed-forward multimodal feedback using updated recommendations of ADMC, allowing users to visually compare the current and the suggested mapping in real-time. We contrast the effectiveness of two new approaches that a) continuously recommend updated DoF combinations or b) use discrete thresholds between current robot movements and new recommendations. Both are compared in a Virtual Reality (VR) in-person study against a classic control method. Significant results for lowered task completion time, fewer mode switches, and reduced perceived workload conclusively establish that in combination with feedforward, ADMC methods can indeed outperform classic mode switching. A lack of apparent quantitative differences between Continuous and Threshold reveals the importance of user-centered customization options. Including these implications in the development process will improve usability, which is essential for successfully implementing robotic technologies with high user acceptance. © 2023, CC BY.

关键词： Mapping

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：