2020 13th International Conference on Human System Interaction (HSI)最新文献_第6页

Typical Courseware Versus Assistive Courseware for Low Vision Learners 低视力学习者的典型课件与辅助课件

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142656

Nurulnadwan Aziz, A. A. Mutalib, A. Omar

{"title":"Typical Courseware Versus Assistive Courseware for Low Vision Learners","authors":"Nurulnadwan Aziz, A. A. Mutalib, A. Omar","doi":"10.1109/HSI49210.2020.9142656","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142656","url":null,"abstract":"Studies related to learners with low vision highlights that learning activities is the most challenging and difficult part in low vision learner's life. Interview with experts also emphasizes that learning materials that specifically developed for low vision learners particularly that focus on content development is highly limited. Currently, the school teachers have to struggle to create the best technique of teaching method to the low vision learners in ensuring them could understand the delivered content as much as possible. Therefore, the main aim of this study is to propose a Conceptual Design Model of Assistive Courseware for Low Vision (AC4LV) learners which has been discussed and reported in the previous articles. Prior to test the proposed model, two types of prototypes were developed with the objective (i) to validate the proposed model and (ii) to provide means for testing the proposed model. The prototypes were named as Assistive Courseware for Low Vision (AC4LV) and typical courseware (TC). Two of them were developed by following two different methods. IntView v1 was found appropriate for developing a small scaled courseware such as TC. While, AC4LV make uses three phases of development process which are pre-production, production, and postproduction. To guarantee the design of AC4LV is tailored towards the target users and meet the appropriate learning aim, User Centred Design (UCD) approach was applied throughout the development process of AC4LV. Actual users, teachers from special primary school, academicians from higher learning institution, and a team of developer were engaged and collaborated with. The results of this study reports and discuss both of the developed prototypes. Future works of this study is to conduct user experience testing for both of the developed coursewares.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122455978","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

Enhanced Feature Pyramid Networks by Feature Aggregation Module and Refinement Module 基于特征聚合模块和改进模块的特征金字塔网络

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142674

Xuan-Thuy Vo, K. Jo

{"title":"Enhanced Feature Pyramid Networks by Feature Aggregation Module and Refinement Module","authors":"Xuan-Thuy Vo, K. Jo","doi":"10.1109/HSI49210.2020.9142674","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142674","url":null,"abstract":"Feature pyramids executing refinements on the raw feature maps produced by the backbone (e.g., ResNet, VGG) are universally employed in object detection tasks (e.g., Faster R-CNN, Mask R-CNN, YOLO, SSD, RetinaNet) to mitigate scale variation problem. Although these object detections with feature pyramids accomplish a boost in accuracy without compromising speed, they have some limitations since that they only naturally design the feature pyramid with consecutive scales, the pyramidal architecture of the backbone, which are initially constructed for the classification task. This problem leads to the feature imbalance between high-level features and low-level features in object detection. In this work, the proposed method introduces Feature Aggregation Module (FAM) and Refinement Module (RM) to obtain more powerful feature pyramids for predicting objects of different scales. First, the multi-level feature maps (i.e., multiple layers) extracted by the backbone network are aggregated as the basic feature. Second, the basic feature is enhanced by a refinement module exploiting long-range dependency. Three, to construct a feature pyramid for object detection, the proposed FAM is used by converting the basic feature (after utilizing a refinement module) into multi-level features. Finally, refined multi-level features and raw features generated by the backbone could be enhanced through shortcut connections to capture more representative. To perform the efficiency, the proposed method integrates the FAM and the RAM into the architecture of Faster R-CNN called EFPN Faster R-CNN. Especially on the MS-COCO dataset, EFPN Faster R-CNN achieves 2.2 points higher Average Precision (AP) than FPN Faster R-CNN without bells and whistles.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126334259","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: 2

Electric Wheelchair-Humanoid Robot Collaboration for Clothing Assistance of the Elderly 电动轮椅-人形机器人合作为老年人提供衣物援助

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142645

R. P. Joshi, Jayant Prasad Tarapure, T. Shibata

{"title":"Electric Wheelchair-Humanoid Robot Collaboration for Clothing Assistance of the Elderly","authors":"R. P. Joshi, Jayant Prasad Tarapure, T. Shibata","doi":"10.1109/HSI49210.2020.9142645","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142645","url":null,"abstract":"In rapidly aging societies, robotic solutions for clothing assistance can significantly improve the quality of life of the elderly while coping with the shortage of caregivers. Previously, we proposed a framework for the same by employing imitation learning from a human demonstration to a compliant dual-arm robot. As the robot has a limited workspace, this framework involves a manual movement of the wheeled chair by pushing it while coordinating with the robot to stay within the workspace of the robot [1]. To avoid the manual push and coordination, we facilitate the automatic movement of the chair based on the trajectory of the robot's dual arms. In this paper, we present an approach for the collaboration of an electric wheelchair and a humanoid robot to achieve the clothing assistance task. Our approach incorporates Manifold Relevance Determination (MRD) to learn an offline latent model from the simultaneous observations of the clothing assistance task as well as the movement of the wheelchair. We trained and tested the latent model on different human subjects by dressing a sleeveless T-shirt. Experimental results verify the plausibility of our approach. To the best of our knowledge, this is the first work addressing collaboration between wheelchair and robot to perform clothing assistance.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114304048","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: 2

Classification of Hazardous Chemicals with Raman Spectrum by Convolution Neural Network 基于卷积神经网络的危险化学品拉曼光谱分类

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142632

Liangrui Pan, Pronthep Pipitsunthonsan, M. Chongcheawchamnan

{"title":"Classification of Hazardous Chemicals with Raman Spectrum by Convolution Neural Network","authors":"Liangrui Pan, Pronthep Pipitsunthonsan, M. Chongcheawchamnan","doi":"10.1109/HSI49210.2020.9142632","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142632","url":null,"abstract":"Dangerous chemicals have always been the hidden danger of social security, how to accurately identify chemicals is very important. In this experiment, the Raman scattering instrument will provide us with the Raman spectrum signal of about 190 chemical substances, each of which has its own characteristics. However, the traditional methods of identifying and classifying chemicals are not only inefficient, but also lack of security. This study proved the feasibility of using neural network to classify chemical substances. For one-dimensional signal, the experiment mainly uses the semi-supervised learning method to establish the 1D-DCNN model and simulate the real noise environment. One-dimensional signal is used as input and then the model is trained to get the model. The experimental results show that the accuracy of toxic and toxic, flammable, corrosive, environment hazard, health hazard, safe, expansive, harmful classification is 99% ± 1%. This shows that the 1D-DCNN model has strong anti-interference and robustness for signals in noise environments. This rapid classification method will provide reference value for the identification of chemical substances.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130156800","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: 2

Lightweight Convolutional Neural Network for Real-Time Face Detector on CPU Supporting Interaction of Service Robot 基于CPU的服务机器人实时人脸检测轻量级卷积神经网络

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142636

M. D. Putro, Duy-Linh Nguyen, K. Jo

{"title":"Lightweight Convolutional Neural Network for Real-Time Face Detector on CPU Supporting Interaction of Service Robot","authors":"M. D. Putro, Duy-Linh Nguyen, K. Jo","doi":"10.1109/HSI49210.2020.9142636","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142636","url":null,"abstract":"Face detection plays an essential role in the success of the interaction between service robots and consumers. This method is the initial stage for face-related applications. Practical applications require face detection to work in real-time and can be implemented on low-cost devices such as CPU. Traditional methods have problems when the face is not frontal, blocked, and partially covered, but real-time speed is not an obstacle. On the other hand, deep learning has succeeded in accurately distinguishing facial features and backgrounds. Face sizes that tend to be medium and large when robot interaction with consumers so it can employ Convolutional Neural Networks (CNN) with light weights. In this paper, a real-time face detector is built that can work on the CPU. This detector will be implemented explicitly in service robots to support interactions with consumers. It can overcome the occlusion and not-frontal face. Detector architecture consists of the backbone as rapidly features extractor, transition module as a transformer of prediction map, and the dual-detection layer is head of a network prediction based on scale assignment. As a result, the detector can work at speeds of 301 frames per second on CPU without ignoring the accuracy.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115483578","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: 12

Robotics and HSI in Robotics 机器人和机器人中的HSI

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/hsi49210.2020.9142664

引用次数: 0

Hetero Complementary Networks with Hard-Wired Condensing Binarization for High Frame Rate and Ultra-Low Delay Dual-Hand Tracking 高帧率超低延迟双手跟踪的硬连线压缩二值化异构互补网络

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142660

Peiqi Zhang, Dingli Luo, Songlin Du, T. Ikenaga

{"title":"Hetero Complementary Networks with Hard-Wired Condensing Binarization for High Frame Rate and Ultra-Low Delay Dual-Hand Tracking","authors":"Peiqi Zhang, Dingli Luo, Songlin Du, T. Ikenaga","doi":"10.1109/HSI49210.2020.9142660","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142660","url":null,"abstract":"High frame rate, ultra-low delay yet accurate hand tracking system provides a seamless and intuitive interface for Human Computer Interaction (HCI). Tracking multi-person's dual-hand from monocular RGB camera is challenging for hand's variant image feature. Although many CNN based trackers have been proposed on general hardware, they cannot address this challenge with ultra-high speed. This paper proposes: (A) Hetero complementary networks for ultra-high speed dual-hand tracking, where the quick primary result from an FPGA network is intermittently combined with delayed accurate result from a GPU network. (B) Hard-wired condensing binarization for ultrahigh speed network implementation on FPGA. The network is able to be directly mapped as hardware resource because complex computation is condensed into binary layers. The proposed method achieves 69.8% accuracy on test sequences, which is only 4.7% lower compared with the general method. Meanwhile, the estimated FPGA resource utilization is tremendously reduced to 54.7% on the target platform. This work shows the potential to track multi-person's dual-hand at millisecond-level speed.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122234254","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: 1

Deep learning for recommending subscription-limited documents 深度学习推荐订阅有限的文档

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142663

Grzegorz Chłodziński, Karol Wozniak

引用次数: 0

Investigating Influence of Complexity and Stressors on Human Performance during Remote Navigation of a Robot Plattform in a Virtual 3D Maze 虚拟三维迷宫中机器人平台远程导航过程中复杂性和压力源对人的影响研究

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2020-06-01 DOI: 10.1109/HSI49210.2020.9142671

Jochen Nelles, Matthias G. Arend, Alexander Mertens, Anne Henschel, Christopher Brandl, V. Nitsch

{"title":"Investigating Influence of Complexity and Stressors on Human Performance during Remote Navigation of a Robot Plattform in a Virtual 3D Maze","authors":"Jochen Nelles, Matthias G. Arend, Alexander Mertens, Anne Henschel, Christopher Brandl, V. Nitsch","doi":"10.1109/HSI49210.2020.9142671","DOIUrl":"https://doi.org/10.1109/HSI49210.2020.9142671","url":null,"abstract":"Human-machine systems for identifying and defusing improvised explosive devices need to be designed according to specific user requirements and task-specific affordances. The navigation of mobile robots in unknown environments is, for example, a typical task of emergency response personnel, which occurs during situation assessment and analysis of suspicious objects. This contribution investigates determinants of the efficient performance as well as human behaviour in remote navigation tasks. In an experimental study, participants had to navigate forwards and backwards in a virtual 3D maze, then draw the path they had covered from memory. Task complexity and environmental stressors were varied between levels, to examine their impact on performance (task completion time, route retracing performance) and subjective measures (mental workload, perceived difficulty). In a sample of 50 participants, a negative relationship between complexity and the dependent variables was found. For the stressors, only the addition of an acoustic stressor had an impact on the performance measures. A discussion of the practical implications of these results is provided.","PeriodicalId":371828,"journal":{"name":"2020 13th International Conference on Human System Interaction (HSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121632582","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: 1

Human Computer and Machine Interaction 人机和机器交互

2020 13th International Conference on Human System Interaction (HSI) Pub Date : 2019-06-01 DOI: 10.1109/hsi47298.2019.8942618

引用次数: 0