2022 15th International Conference on Human System Interaction (HSI)最新文献

Evaluating the Adversarial Robustness of Text Classifiers in Hyperdimensional Computing 评估超维计算中文本分类器的对抗鲁棒性

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869459

Harsha Moraliyage, Sachin Kahawala, Daswin De Silva, D. Alahakoon

{"title":"Evaluating the Adversarial Robustness of Text Classifiers in Hyperdimensional Computing","authors":"Harsha Moraliyage, Sachin Kahawala, Daswin De Silva, D. Alahakoon","doi":"10.1109/HSI55341.2022.9869459","DOIUrl":"https://doi.org/10.1109/HSI55341.2022.9869459","url":null,"abstract":"Hyperdimensional (HD) Computing leverages random high dimensional vectors (>10000 dimensions) known as hypervectors for data representation. This high dimensional feature representation is inherently redundant which results in increased robustness against noise and it also enables the use of a computationally simple operations for all vector functions. These two properties of hypervectors have led to energy efficient and fast learning capabilities in numerous Artificial Intelligence (AI) applications. Despite the increasing number of such AI HD applications, their susceptibility to adversarial attacks has not been explored, specifically in the text domain. To the best of our knowledge, this is the first research endeavour to evaluate the adversarial robustness of HD text classifiers and report on their vulnerability to such attacks. In this paper, we designed and developed n-grams based HD computing text classifiers for two primary applications of HD computing; language recognition and text classification, and then performed a set of character level and word level grey-box adversarial attacks, where an attacker’s goal is to mislead the target HD computing classifier to produce false prediction labels while keeping added perturbation noise as low as possible. Our results show that adversarial examples generated by the attacks can mislead the HD computing classifiers to produce incorrect prediction labels. However, HD computing classifiers show a higher degree of adversarial robustness in language recognition compared to text classification tasks. The robustness of HD computing classifiers against character-level attacks is significantly higher compared to word-level attacks and has the highest accuracy compared to deep learning-based classifiers. Finally, we evaluate the effectiveness of adversarial training as a possible defense strategy against adversarial attacks in HD computing text classifiers.","PeriodicalId":282607,"journal":{"name":"2022 15th International Conference on Human System Interaction (HSI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133002087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Physical Human-Robot Interaction (pHRI) through Admittance Control of Dynamic Movement Primitives in Sit-to-Stand Assistance Robot 基于动态运动基元导纳控制的坐立辅助机器人人机物理交互

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869510

Bibhu Sharma, Branesh M. Pillai, J. Suthakorn

{"title":"Physical Human-Robot Interaction (pHRI) through Admittance Control of Dynamic Movement Primitives in Sit-to-Stand Assistance Robot","authors":"Bibhu Sharma, Branesh M. Pillai, J. Suthakorn","doi":"10.1109/HSI55341.2022.9869510","DOIUrl":"https://doi.org/10.1109/HSI55341.2022.9869510","url":null,"abstract":"Physically assistance robots have been conceptualized to compensate or augment the human musculoskeletal function. However, due to the concerns of safety and effectiveness for physical human-robot interaction (pHRI) in such robots, compliant joints are preferred over the rigid joints. This paper illustrates the implementation of admittance control in a sit-to-stand (STS) assistance robot. The 3-degrees of freedom (dof) robot comprises of ball screw-based linear actuators that are arranged in a parallel configuration. While the actuation system is preferable for strength and performance, the non-backdrivable characteristic corroborates the rigidity of the joint, making it unfavorable for human-robot interaction operation. To enhance compliance, force sensor-based admittance control system is implemented. Regarding motion planning, the trajectory were modeled as Dynamic Movement Primitives (DMP), which facilitates the implementation of admittance control. The proposed model is implemented in the robot prototype and validated by illustrating the force input and the motion output.","PeriodicalId":282607,"journal":{"name":"2022 15th International Conference on Human System Interaction (HSI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115023390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Motion-Copying System Based on Modeling of Finger Force Characteristics Using Upper Limb-EMG 基于上肢肌电图的手指力特性建模的运动复制系统

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869479

Daiki Sodenaga, K. Egawa, S. Katsura

引用次数: 0

Computer Aided Telediagnostics System for Stoma Patients 造口病人计算机辅助远程诊断系统

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869492

Rafał Zawiślak, M. Szwoch, Grzegorz Granosik, A. Miarka, Joanna Mik-Wojtczak, M. Mik

引用次数: 0

A BERT-based Idiom Detection Model 基于bert的习语检测模型

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869485

Gihan Gamage, Daswin De Silva, A. Adikari, D. Alahakoon

引用次数: 0

Analysis of the influence of external conditions on temperature readings in thermograms and adaptive adjustment of the measured temperature value 分析外部条件对热像图温度读数的影响及测量温度值的自适应调整

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869458

P. Filipowicz, Mateusz Kowalewski, K. Slominska, M. Kaczmarek

引用次数: 0

A Virtual Reality Study Investigating the Effect of Cybersickness on the Relationship Between Vection and Presence Across Environments with Varying Levels of Ecological Relevance 一项虚拟现实研究调查了在不同生态相关水平的环境中晕机对向量和存在之间关系的影响

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869507

L. Kooijman, Houshyar Asadi, Shady M. K. Mohamed, S. Nahavandi

{"title":"A Virtual Reality Study Investigating the Effect of Cybersickness on the Relationship Between Vection and Presence Across Environments with Varying Levels of Ecological Relevance","authors":"L. Kooijman, Houshyar Asadi, Shady M. K. Mohamed, S. Nahavandi","doi":"10.1109/HSI55341.2022.9869507","DOIUrl":"https://doi.org/10.1109/HSI55341.2022.9869507","url":null,"abstract":"In the absence of physical motion, people sometimes experience the illusory sensation of self-motion which is known as vection. Vection research could contribute to the improvement of the fidelity of simulators as vection and presence appear to be positively related. However, when utilizing virtual reality technology for simulators, visually-induced motion sickness (VIMS) in the form of Cybersickness (CS) sometimes co-occurs with the experience of vection. Nonetheless, the relationship between vection and CS is not evident. Past research mainly investigated the relationship between the vection and CS using environments with a certain level of ecological relevance. Herein we investigated whether CS negatively affects the relationship between vection and presence across different virtual environments with varying levels of ecological relevance. We immersed twenty-nine participants visually and audibly in virtual environments and after each trial participants reported their vection intensity, CS, and presence. Our results showed that the relationship between vection intensity and presence was unaffected by CS. We conclude that the relationship between vection and presence is unaffected by CS with low levels of discomfort.","PeriodicalId":282607,"journal":{"name":"2022 15th International Conference on Human System Interaction (HSI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124758790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Microtransactions in VR. A qualitative comparison between voice user interface and graphical user interface VR中的微交易。语音用户界面与图形用户界面的定性比较

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869475

Karolina Buchta, Piotr Wójcik, Konrad Nakonieczny, Justyna Janicka, Damian Galuszka, Radoslaw Sterna, Magdalena Igras-Cybulska

引用次数: 0

Large monitors reduce tracking error in robot-assisted visual-motor tasks 大型显示器减少了机器人辅助视觉运动任务中的跟踪误差

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869488

F. Stroppa, F. Amirabdollahian, A. Frisoli

引用次数: 0

Attention-based Interactions Network for Breast Tumor Classification with Multi-modality Images 基于关注的多模态图像乳腺肿瘤分类交互网络

2022 15th International Conference on Human System Interaction (HSI) Pub Date : 2022-07-28 DOI: 10.1109/HSI55341.2022.9869477

Xiao Yang, Xiaoming Xi, Chuanzhen Xu, Liangyun Sun, Lingzhao Meng, Xiushan Nie

{"title":"Attention-based Interactions Network for Breast Tumor Classification with Multi-modality Images","authors":"Xiao Yang, Xiaoming Xi, Chuanzhen Xu, Liangyun Sun, Lingzhao Meng, Xiushan Nie","doi":"10.1109/HSI55341.2022.9869477","DOIUrl":"https://doi.org/10.1109/HSI55341.2022.9869477","url":null,"abstract":"Benefiting from the development of medical imaging, the automatic breast image classification has been extensively studied in a variety of breast cancer diagnosis tasks recently. The multi-modality image fusion was helpful to further improve classification performance. However, existing multi-modality fusion methods focused on the fusion of modalities, ignoring the interactions between modalities, which caused the inefficient performance. To address the above issues, we proposed a novel attention-based interactions network for breast tumor classification by using diffusion-weighted imaging (DWI) and apparent dispersion coefficient (ADC) images. Specifically, we proposed a multi-modality interaction mechanism, including relational interaction, channel interaction, and discriminative interaction, to design an attention-based interaction module, which enhanced the abilities of inter-modal interactions. Extensive ablation studies have been carried out, which provably affirmed the advantages of each component. The area under the receiver operating characteristic curve (AUC), accuracy (ACC), specificity (SPC), and sensitivity (SEN) were 87.0%, 87.0%, 88.0%, and 86.0%, respectively, also verifying its effectiveness.","PeriodicalId":282607,"journal":{"name":"2022 15th International Conference on Human System Interaction (HSI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131755597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0