學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 10 of 60

EEG-based Measures of Auditory Saliency in a Complex Context
(2019-01-01)
Huang, Xun-Yi
;
Cherng, Fu-Yin
;
King, Jung-Tai
;
Lin, Wen-Chieh
;
資訊工程學系
Auditory saliency is an important mechanism that helps humans extract relevant information from environments. Audio notifications of mobile devices with high saliency can increase users' receptivity, yet overly high saliency could cause annoyance. Accurately measuring auditory saliency of a notification is critical for evaluating its usability. Previous studies adopted behavioral methods. However, their results may not accurately reflect auditory saliency as humans' perception of auditory saliency often involves complicated cognitive processes. Thus, we propose an electroencephalography (EEG)-based approach that can complement behavioral studies to provide a more nuanced analysis of auditory saliency. We evaluated our method by conducting an EEG experiment that measured the mismatch negativity and P3a of the sounds in realistic scenarios. We also conducted a behavioral experiment to link the EEG-based method with the behavioral method. The results suggested that EEG can provide detailed information about how human perceive auditory saliency and complement the behavioral measures.
Exploration of User's Mental State Changes during Performing Brain-Computer Interface
(2020-06-01)
Ko, Li-Wei
;
Chikara, Rupesh Kumar
;
Lee, Yi-Chieh
;
Lin, Wen-Chieh
;
交大名義發表
Substantial developments have been established in the past few years for enhancing the performance of brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP). The past SSVEP-BCI studies utilized different target frequencies with flashing stimuli in many different applications. However, it is not easy to recognize user's mental state changes when performing the SSVEP-BCI task. What we could observe was the increasing EEG power of the target frequency from the user's visual area. BCI user's cognitive state changes, especially in mental focus state or lost-in-thought state, will affect the BCI performance in sustained usage of SSVEP. Therefore, how to differentiate BCI users' physiological state through exploring their neural activities changes while performing SSVEP is a key technology for enhancing the BCI performance. In this study, we designed a new BCI experiment which combined working memory task into the flashing targets of SSVEP task using 12 Hz or 30 Hz frequencies. Through exploring the EEG activity changes corresponding to the working memory and SSVEP task performance, we can recognize if the user's cognitive state is in mental focus or lost-in-thought. Experiment results show that the delta (1-4 Hz), theta (4-7 Hz), and beta (13-30 Hz) EEG activities increased more in mental focus than in lost-in-thought state at the frontal lobe. In addition, the powers of the delta (1-4 Hz), alpha (8-12 Hz), and beta (13-30 Hz) bands increased more in mental focus in comparison with the lost-in-thought state at the occipital lobe. In addition, the average classification performance across subjects for the KNN and the Bayesian network classifiers were observed as 77% to 80%. These results show how mental state changes affect the performance of BCI users. In this work, we developed a new scenario to recognize the user's cognitive state during performing BCI tasks. These findings can be used as the novel neural markers in future BCI developments.
A robust real-time facial alignment system with facial landmarks detection and rectification for multimedia applications
(1970-01-01)
Chou, Kuang Pen
;
Prasad, Mukesh
;
Yang, Jie
;
Su, Sheng-Yao
;
Tao, Xian
Face detection often plays the first step in various visual applications. Large variants of facial deformations due to head movements and facial expression make it difficult to identify appropriate face region. In this paper, a robust real-time face alignment system, including facial landmarks detection and face rectification, is proposed. A facial landmarks detection model based on regression tree is utilized in the proposed system. In face rectification framework, 2-D geometrical analysis based on pitch, yaw and roll movements is designed to solve the misalignment problem in face detection. The experiments on the two datasets verify the performance significantly improved by the proposed method in the facial recognition task and outperform than those obtained by other alignment methods. Furthermore, the proposed method can achieve robust recognition results even if the amount of training images is not large.
Comparative Evaluation of the Effects of Motion Control on Cybersickness in Immersive Virtual Environments
(2020-01-01)
Venkatakrishnan, Roshan
;
Venkatakrishnan, Rohith
;
Bhargava, Ayush
;
Lucaites, Kathryn
;
Solini, Hannah
The commercialization and lowering costs of consumer grade Virtual Reality (VR) devices has made the technology increasingly accessible to users around the world. The usage of VR technology is often accompanied by an undesirable side effect called cybersickness. Cybersickness is the feeling of discomfort that occurs during VR experiences, producing symptoms similar to those of motion sickness. It continues to remain one of the biggest hurdles to the widespread adoption of VR, making it increasingly important to explore and understand the factors that influence its onset. In this work, we investigated the influence of the presence/absence of motion control on the onset and severity of cybersickness in an HMD based VR driving simulation employing steering as a travel metaphor. Towards this end, we conducted a between subjects study manipulating the presence of control between three experimental conditions, two of which (Driving condition and Yoked Pair condition) formed a yoked control design where every pair of drivers and their yoked pairs were exposed to identical vehicular motion stimuli created by participants in the driving condition. In the other condition (Autonomous Car condition), participants experienced a program driven autonomous vehicle simulation. Results indicated that participants in the Driving condition experienced higher levels of cybersickness than participants in the Yoked Pair condition. While these results don't conform to findings from previous research which suggests that having control over motion reduces cybersickness, it seems to point towards the importance of the fidelity of the control metaphor's feedback response in alleviating cybersickness. Simply allowing one control their motion may not readily alleviate cybersickness but could instead increase it in such HMD based VR driving simulations. It may hence be important to consider how well the control metaphor and its feedback matches users' expectations if we want to successfully mitigate cybersickness.
Design and Initial Evaluation of a VR based Immersive and Interactive Architectural Design Discussion System
(2020-01-01)
Hsu, Ting-Wei
;
Tsai, Ming-Han
;
Babu, Sabarish, V
;
Hsu, Pei-Hsien
;
Chang, Hsuan-Ming
Design discussion is a very important course in architecture education. In this paper, we developed a VR based architecture design discussion system that allows members to visualize and discuss the architectural models and to modify the models during discussion. Since the system is designed to work on top of Rhinoceros and Grasshopper, the object database is updated right after the object modification. Members communicate via voice, object manipulations, and mid-air sketching as well as on-surface sketching in the virtual environment. Several tools have been designed to enhance the sense of presence and to make the discussion more effective. We also developed a rollback mechanism to help users intuitively and quickly revert to a previous state of discussion to make some changes or to start a new direction of discussion. To evaluate the system, we conducted an initial user study with 14 participants to assess the user experience, user impression and effectiveness of the system. The feedback from participants were positive and suggested that the system could be effective and useful for supporting architecture design discussion.
Virtual Classmates: Embodying Historical Learners' Messages as Learning Companions in a VR Classroom through Comment Mapping
(2019-01-01)
Liao, Meng-Yun
;
Sung, Ching-Ying
;
Wang, Hao-Chuan
;
Lin, Wen-Chieh
;
資訊工程學系
Online learning platforms such as MOOCs have been prevalent sources of self-paced learning to people nowadays. However, the lack of peer accompaniment and social interaction may increase learners' sense of isolation and loneliness. Prior studies have shown the positive effects on visualizing peer students' appearances with virtual avatars or virtualized online learners in VR learning environments. In this work, we propose to build virtual classmates, which were constructed by synthesizing previous learners' messages (timeanchored comments). Configurations of virtual classmates, such as the number of classmates participating in a VR class and the behavioral features of the classmates, can also be adjusted. To build the characteristics of virtual classmates, we propose a technique called comment mapping to aggregate prior online learners' comments to shape virtual classmates' behaviors. We conduct a study with 100 participants to evaluate the effects of the virtual classmates built with and without the comment mapping and the amount of virtual classmates rendered in VR. The findings of our study suggest design implications for developing virtual classmates in VR environments.
Tangible and Visible 3D Object Reconstruction in Augmented Reality
(2019-01-01)
Wu, Yi-Chin
;
Chant, Liwei
;
Lin, Wen-Chieh
;
資訊工程學系
;
Department of Computer Science
Many crucial applications in the fields of filmmaking, game design, education, and cultural preservation - among others - involve the modeling, authoring, or editing of 3D objects and scenes. The two major methods of creating 3D models are 1) modeling, using computer software, and 2) reconstruction, generally using high-quality 3D scanners. Scanners of sufficient quality to support the latter method remain unaffordable to the general public. Since the emergence of consumer-grade RGBD cameras, there has been a growing interest in 3D reconstruction systems using depth cameras. However, most such systems are not user-friendly, and require intense efforts and practice if good reconstruction results are to be obtained. In this paper, we propose to increase the accessibility of depth-camera-based 3D reconstruction by assisting its users with augmented reality (AR) technology. Specifically, the proposed approach will allow users to rotate/move a target object freely with their hands and see the object being overlapped with its reconstructing model during the reconstruction process. As well as being more instinctual than conventional reconstruction systems, our proposed system will provide useful hints on complete 3D reconstruction of an object, including the best capturing range; reminder of moving and rotating the object at a steady speed; and which model regions are complex enough to require zooming-in. We evaluated our system via a user study that compared its performance against those of three other state-of-the-art approaches, and found our system outperforms the other approaches. Specifically, the participants rated it highest in usability, understandability, and model satisfaction.
A self-adaptive artificial bee colony algorithm with local search for TSK-type neuro-fuzzy system training
(2019-01-01)
Chou, Kuang-Pen
;
Lin, Chin-Teng
;
Lin, Wen-Chieh
;
資訊工程學系
;
Department of Computer Science
In this paper, we introduce a self-adaptive artificial bee colony (ABC) algorithm for learning the parameters of a Takagi-Sugeno-Kang-type (TSK-type) neuro-fuzzy system (NFS). The proposed NFS learns fuzzy rules for the premise part of the fuzzy system using an adaptive clustering method according to the input-output data at hand for establishing the network structure. All the free parameters in the NFS, including the premise and the following TSK-type consequent parameters, are optimized by the modified ABC (MABC) algorithm. Experiments involve two parts, including numerical optimization problems and dynamic system identification problems. In the first part of investigations, the proposed MABC compares to the standard ABC on mathematical optimization problems. In the remaining experiments, the performance of the proposed method is verified with other metaheuristic methods, including differential evolution (DE), genetic algorithm (GA), particle swarm optimization (PSO) and standard ABC, to evaluate the effectiveness and feasibility of the system. The simulation results show that the proposed method provides better approximation results than those obtained by competitors methods.
Embodying Historical Learners' Messages as Learning Companions in a VR Classroom
(2019-01-01)
Liao, Meng-Yun
;
Sung, Ching-Ying
;
Wang, Hao-Chuan
;
Lin, Wen-Chieh
;
Cherng, Fu-Yin
Online learning platforms such as MOOCs have been prevalent sources of self-paced learning to people nowadays. However, the lack of peer accompaniment and social interaction may increase learners' sense of isolation. Prior studies have shown the positive effects on visualizing peer students' appearances in VR learning environments. In this work, we propose to build virtual classmates, which were constructed by synthesizing previous learners' time-anchored messages. Configurations of virtual classmates and their behavioral features can be adjusted. To build the characteristics of virtual classmates, we developed a technique called comment mapping to aggregate prior online learners' comments to shape virtual classmates' behaviors. We evaluated the effects of the virtual classmates built with and without the comment mapping and the amount of virtual classmates rendered in VR.
Deep Sparse Representation Classifier for facial recognition and detection system
(2019-07-01)
Cheng, Eric-Juwei
;
Chou, Kuang-Pen
;
Rajora, Shantanu
;
Jin, Bo-Hao
;
Tanveer, M.
This paper proposes a two-layer Convolutional Neural Network (CNN) to learn the high-level features which utilizes to the face identification via sparse representation. Feature extraction plays a vital role in real-world pattern recognition and classification tasks. The details description of the given input face image, significantly improve the performance of the facial recognition system. Sparse Representation Classifier (SRC) is a popular face classifier that sparsely represents the face image by a subset of training data, which is known as insensitive to the choice of feature space. The proposed method shows the performance improvement of SRC via a precisely selected feature exactor. The experimental results show that the proposed method outperforms other methods on given datasets. (C) 2019 Elsevier B.V. All rights reserved.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results