HCI Bibliography Home | HCI Conferences | HCII Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
HCII Tables of Contents: 11-111-211-311-411-511-613-113-213-313-413-513-613-714-114-214-314-414-515-115-215-3

HCI International 2013: 15th International Conference on HCI, Part V: Towards Intelligent and Implicit Interaction

Fullname:HCI International 2013: 15th International Conference on Human-Computer Interaction, Part V: Towards Intelligent and Implicit Interaction
Editors:Masaaki Kurosu
Location:Las Vegas, Nevada
Dates:2013-Jul-21 to 2013-Jul-26
Publisher:Springer Berlin Heidelberg
Series:Lecture Notes in Computer Science 8008
Standard No:DOI: 10.1007/978-3-642-39342-6 hcibib: HCII13-5; ISBN: 978-3-642-39341-9 (print), 978-3-642-39342-6 (online)
Links:Online Proceedings | Conference Home Page
  1. HCII 2013-07-21 Volume 5
    1. Adaptive, Personalised and Context-Aware Interaction
    2. Computational Vision in HCI
    3. Emotions in HCI
    4. Biophysiological Aspects of Interaction

HCII 2013-07-21 Volume 5

Adaptive, Personalised and Context-Aware Interaction

Development of a Virtual Keyboard System Using a Bio-signal Interface and Preliminary Usability Test BIBAKFull-Text 3-9
  Kwang-Ok An; Da-Hey Kim; Jongbae Kim
People with severe speech or language problems rely on augmentative and alternative communication (AAC) to supplement existing speech or replace speech that is not functional. However, many people with severely motor disabilities are limited to use AAC, because most of AAC use the mechanical input devices. In this paper, to solve the limitations and offer a practical solution to disabled person, a virtual keyboard system using a bio-signal interface is developed. The developed system consists of bio-signal interface, training and feedback program, connecting module and virtual keyboard. In addition, we evaluate how well do subjects control the system. From results of preliminary usability test, the usefulness of the system is verified.
Keywords: augmentative and alternative communication; bio-signal interface; preliminary usability test; virtual keyboard system
Unifying Conceptual and Spatial Relationships between Objects in HCI BIBAKFull-Text 10-18
  David Blezinger; Ava Fatah gen. Schieck; Christoph Hölscher
To design interfaces which occupy a continuous space of interaction, the conceptual model of an interface needs to be transferred to a spatial model. To find mappings between conceptual and spatial structure which are natural to people, an experiment is undertaken in which participants organize objects in a semi-circle of shelves around their body. It is analyzed how conceptual relationships between objects such as categorial relationships and sequential relationships within task performance are represented in spatial configurations of objects as chosen by the participants. In these configurations, a strong correlation between conceptual and spatial relationships is observed between objects.
Keywords: HCI frameworks; spatial interface; conceptual model; information architecture; navigation; object-based; task-based; spatial configuration; spatial cognition; embodied interaction; categories; visual identity
Context-Aware Multimodal Sharing of Emotions BIBAKFull-Text 19-28
  Maurizio Caon; Leonardo Angelini; Yong Yue; Omar Abou Khaled; Elena Mugellini
Computer mediated interaction often lacks of expressivity, in particular for emotion communication. Therefore, we present a concept for context-aware multimodal sharing of emotions for human-to-computer-to-human interaction in social networks. The multimodal inputs and outputs of this system are distributed in a smart environment in order to grant a more immersive and natural interaction experience. The context information is used to improve the opportuneness and the quality of feedback. We implemented an evaluation scenario and we conducted an observation study during some events with the participants. We reported our considerations at the end of this paper.
Keywords: affective computing; multimodal interaction; computer mediated communication; social sharing of emotions
Supportive User Interfaces for MOCOCO (Mobile, Contextualized and Collaborative) Applications BIBAKFull-Text 29-38
  Bertrand David; René Chalon; Florent Delomier
Enhancing interaction with supplementary Supportive User Interfaces: Meta-UIs, Mega-UIs, Extra-UIs, Supra-UIs, etc. is a relatively new challenge for HCI. In this paper, we describe our view of supportive user Interfaces for AmI applications taking into account Mobility, Collaboration and Contextualization. We describe proposed formalisms and their working conditions: initially created for designers in the design stage; we consider that they can now also be used by final-users for dynamic adjustment of working conditions.
Keywords: Interactive and collaborative model architectures; formalisms; Ambient Intelligence; pervasive and ubiquitous computing; tangible UI
RFID Mesh Network as an Infrastructure for Location Based Services for the Blind BIBAKFull-Text 39-45
  Hugo Fernandes; Jose Faria; Paulo Martins; Hugo Paredes; João Barroso
People with visual impairments face serious challenges while moving from one place to another. This is a difficult challenge that involves obstacle avoidance, staying on street walks, finding doors, knowing the current location and keeping on track through the desired course, until the destination is reached. While assistive technology has contributed to the improvement of the quality of life of people with disabilities, people with visual impairment still face enormous limitations in terms of their mobility. There is still an enormous lack of availability of information that can be used to assist them, as well as a lack of sufficient precision in terms of the estimation of the user's location. This paper proposes an infrastructure to assist the estimation of the user's location with high precision using Radio Frequency Identification, providing seamless availability of location based services for the blind, whether indoor or outdoor.
Keywords: Computer-augmented environments; blind; navigation; rfid
An Ontology-Based Interaction Concept for Social-Aware Applications BIBAKFull-Text 46-55
  Alexandra Funke; Sören Brunk; Romina Kühn; Thomas Schlegel
With the usage of mobile devices becoming more and more ubiquitous, access to social networks such as Facebook and Twitter from those devices is increasing at a fast rate. Many different social networking applications for mobile devices exist but most of them only enable access to one social network. As users are often registered in multiple social networks, they have to use different applications for mobile access. Furthermore, most applications do not consider the users' social context to aid them with their intentions. This paper presents our idea to model the user's social context and intentions in social networks within an ontology. Based on this ontology we describe an interaction concept that allows publishing information in different social networks in a flexible way. We implemented a prototype to show how our findings can be presented. To conclude, we highlight some possibilities for the future of ontology-based social-aware applications.
Keywords: interaction; ontology; semantic modeling; social-aware; social media
Sensor-Based Adaptation of User Interface on Android Phones BIBAKFull-Text 56-61
  Tor-Morten Grønli; Gheorghita Ghine; Jarle Hansen
The notion of context-aware computing is generally the ability for the devices to adapt their behavior to the surrounding environment, ultimately enhancing usability. Sensors are an important source of information input in any real world context and several previous research contributions look into this topic. In our research, we combine sensor-generated context information received both from the phone itself and information retrieved from cloud-based servers. All data is integrated to create a context-aware mobile device, where we implemented a new customized home screen application for Android enabled devices. Thus, we are also able to remotely configure the mobile devices independent of the device types. This creates a new concept of context-awareness and embraces the user in ways previously unavailable.
Keywords: sensor; interface adaptation; Android
Perception and BDI Reasoning Based Agent Model for Human Behavior Simulation in Complex System BIBAKFull-Text 62-71
  Jaekoo Joo
Modeling of human behaviors in systems engineering has been regarded as an extremely complex problem due to the ambiguity and difficulty of representing human decision processes. Unlike modeling of traditional physical systems, from which active humans are assumed to be excluded, HECS has some peculiar characteristics which can be summarized as follows: 1) Environments and human itself are nondeterministic and dynamic that there are many different ways in which they dynamically evolve. 2) Human perceives a set of perceptual information taken locally from surrounding environments and other humans in the environment, which will guide human actions toward his or her goal achievement. In order to overcome the challenges due to the above characteristics, we present an human agent model for mimicking perception-based rational human behaviors in complex systems by combining the ecological concepts of affordance -- and the Belief-Desire-Intention (BDI) theory. Illustrative models of fire evacuation simulation are developed to show how the proposed framework can be applied. The proposed agent model is expected to realize their potential and enhance the simulation fidelity in analyzing and predicting human behaviors in HECS.
Keywords: Human Behavior; Affordance theory; BDI theory; Agent-based Simulation; Social Interaction
Long-Term Study of a Software Keyboard That Places Keys at Positions of Fingers and Their Surroundings BIBAKFull-Text 72-81
  Yuki Kuno; Buntarou Shizuki; Jiro Tanaka
In this paper, we present a software keyboard called Leyboard that enables users to type faster. Leyboard makes typing easier by placing keys at the positions of fingers and their surroundings. To this end, Leyboard automatically adjusts its key positions and sizes to users' hands. This design allows users to type faster and more accurately than using ordinary software keyboards, the keys of which are unperceptive. We have implemented a prototype and have performed a long-term user study. The study has proved the usefulness of Leyboard and its pros and cons.
Keywords: Touch screen; text entry; software keyboard; long-term study
Fast Dynamic Channel Allocation Algorithm for TD-HSPA System BIBAKFull-Text 82-91
  Haidong Li; Hai-Lin Liu; Xueyi Liang
In order to make full use of channel, a new dynamic channel allocation algorithm for TD-HSPA system is proposed. The proposed algorithm gives priority to consider the time slot distribution in uplink channels. This paper uses low order modulation coding in uplink channels, but uses high order modulation coding in downlink channels. The transmission rate of uplink and downlink are asymmetric. In his paper, we propose a criterion sharing channel for each other through main and auxiliary frequency when the voice channel is idle. As a result, the system capacity is increased 50% larger than the past. Simulation results show that the proposed algorithm can decrease the call blocking ratio and dropping packet rate of data service, improve the channel utilization efficiency, and increase the number of data users dramatically.
Keywords: TD-HSPA; asymmetric transmission; frequency sharing; dynamic channel allocation
Evaluating Intelligibility Usage and Usefulness in a Context-Aware Application BIBAKFull-Text 92-101
  Brian Y. Lim; Anind K. Dey
Intelligibility has been proposed to help end-users understand context-aware applications with their complex inference and implicit sensing. Usable explanations can be generated and designed to improve user understanding. However, will users want to use these intelligibility features? How much intelligibility will they use, and will this be sufficient to improve their understanding? We present a quasi-field experiment of how participants used the intelligibility features of a context-aware application. We investigated how many explanations they viewed, how that affected their understanding of the application's behavior, and suggestions they had for improving its behavior. We discuss what constitutes successful intelligibility usage, and provide recommendations for designing intelligibility to promote its effective use.
Keywords: Context-Awareness; Intelligibility; Explanations; User Study
Strangers and Friends BIBAKFull-Text 102-111
  Nikita Mattar; Ipke Wachsmuth
We demonstrate how an artificial agent's conversational style can be adapted to different interlocutors by using a model of Person Memory. While other approaches so far rely on adapting an agent's behavior according to one particular factor like personality or relationship, we show how to enable an agent to take diverse factors into account at once by exploiting social categories. This way, our agent is able to adapt its conversational style individually to reflect interpersonal relationships during conversation.
Keywords: embodied conversational agents; conversational style; social categories; personality; relationships; situational context
suGATALOG: Fashion Coordination System That Supports Users to Choose Everyday Fashion with Clothed Pictures BIBAKFull-Text 112-121
  Ayaka Sato; Keita Watanabe; Michiaki Yasumura; Jun Rekimoto
When deciding what to wear, we normally have to consider several things, such as color and combination of clothes, as well as situations that might change every day, including the weather, what to do, where to go, and whom to meet with. Trying on many possible combinations can be very tedious; thus, computer support would be helpful. Therefore, we propose suGATALOG, a fashion coordination system that allows users to choose and coordinate clothes from their wardrobe. Previous studies have proposed systems using computer images of clothes to allow users to inspect their clothing ensemble. Our system uses pictures of users actually wearing the clothes to give a more realistic impression. suGATALOG compares several combinations by swapping top and bottom images. In this paper, we describe the system architecture and its user interface, as well as an evaluation experiment and a long-term trial test to verify the usefulness of the system.
Keywords: Fashion coordinate; Clothes; Life-log
Interacting with a Context-Aware Personal Information Sharing System BIBAFull-Text 122-131
  Simon Scerri; Andreas Schuller; Ismael Rivera; Judie Attard; Jeremy Debattista; Massimo Valla; Fabian Hermann; Siegfried Handschuh
The di.me userware is a decentralised personal information sharing system with a difference: extracted information and observed personal activities are exploited to automatically recognise personal situations, provide privacy-related warnings, and recommend and/or automate user actions. To enable reasoning, personal information from multiple devices and online sources is integrated and transformed to a machine-interpretable format. Aside from distributed personal information monitoring, an intuitive user interface also enables the i) manual customisation of advanced context-driven services and ii) their semi-automatic adaptation across interactive notifications. In this paper we outline how average users interact with the current user interface, and our plans to improve it.
Design and Evaluation of Eco-feedback Interfaces to Support Location-Based Services for Individual Energy Awareness and Conservation BIBAKFull-Text 132-140
  Yang Ting Shen; Po Chun Chen; Tay Sheng Jeng
The Eco-feedback technology has widely applied to the energy conservation. Eco-feedback technology is usually represented as any kind of interactive device or interface targeted at revealing energy consumption in order to promote users' energy awareness and then trigger more ecologically responsible behaviors. In this paper, the primary goal is to help the individual user understand his comparative energy consumption through the Eco-feedback energy visualization. The energy information we provide is the comparison between the historical average energy consumption and the instant energy consumption. Based on the instant comparative energy consumption, the user can intuitively understand the current energy consumption is higher or lower than usualness. We develop the location-based individual energy consumption feedback system named EME (Energy MEter). Integrated with the concepts of historical comparison and incentives, three kinds of eco-feedback interface prototypes including the Dichotomy type, the Accumulation type, and the Numeral type are designed and deployed in practical fields. The user study both from quantitative and qualitative surveys is conducted in order to find out the potential interface which links user and energy consumption data better.
Keywords: Eco-feedback; Energy awareness; Energy conservation; Comparative energy consumption
Fuzzy Logic Approach for Adaptive Systems Design BIBAKFull-Text 141-150
  Makram Soui; Mourad Abed; Khaled Ghedira
Adaptive system is a field in rapid development. Adaptation is an effective solution for reducing complexity when searching information. This article presents how to personalize user interface (UI) using fuzzy logic. Our approach is based on the definition of relations for selection of appropriate and not appropriate of UI components. These relations are based the degree of certainty about the meaning coincidence of metadata elements and user' preferences. The proposed approach has been validated by applying it in e-learning field.
Keywords: Adaptation; Adaptive Systems; Fuzzy logic; Evaluation; User Interface (UI)

Computational Vision in HCI

Semi-supervised Remote Sensing Image Segmentation Using Dynamic Region Merging BIBAKFull-Text 153-162
  Ning He; Ke Lu; Yixue Wang; Yue Gao
This paper introduces a remote sensing image segmentation approach by using semi-supervised and dynamic region merging. In remote sensing images, the spatial relationship among pixels has been shown to be sparsely represented by a linear combination of a few training samples from a structured dictionary. The sparse vector is recovered by solving a sparsity-constrained optimization problem, and it can directly determine the class label of the test sample. Through a graph-based technique, unlabeled samples are actively selected based on the entropy of the corresponding class label. With an initially segmented image based semi-supervised, in which the many regions to be merged for a meaningful segmentation. By taking the region merging as a labeling problem, image segmentation is performed by iteratively merging the regions according to a statistical test. Experiments on two datasets are used to evaluate the performance of the proposed method. Comparisons with the state-of-the-art methods demonstrate that the proposed method can effectively investigate the spatial relationship among pixels and achieve better remote sensing image segmentation results.
Keywords: Semi-supervised; Remote Sensing Image; Image segmentation; Dynamic region merging
Correcting Distortion of Views into Aquarium BIBAKFull-Text 163-170
  Yukio Ishihara; Makio Ishihara
In this paper, we discuss a way to correct light distortion of views into an aquarium. When we see fish in an aquarium, they appear closer also distorted due to light distortion. In order to correct the distortion, the light rays travelling in the aquarium directly towards an observer should hit him/her after emerging from the aquarium. A basic idea is to capture those light rays by a reference camera, then merge the rays as a single view, which is displayed to the observer. An experiment in a real world environment shows that light distortion of a view into an aquarium can be corrected using the multiple reference camera views.
Keywords: distortion correction; aquarium; light distortion
A Dense Stereo Matching Algorithm with Occlusion and Less or Similar Texture Handling BIBAFull-Text 171-177
  Hehua Ju; Chao Liang
Due to image noise, illumination and occlusion, to get an accurate and dense disparity with stereo matching is still a challenge. In this paper, a new dense stereo matching algorithm is proposed. The proposed algorithm first use cross-based regions to compute an initial disparity map which can deal with regions with less or similar texture. Secondly, the improved hierarchical belief propagation scheme is employed to optimize the initial disparity map. Then the left-right consistency check and mean-shift algorithm are used to handle occlusions. Finally, a local high-confidence strategy is used to refine the disparity map. Experiments with the Middlebury dataset validate the proposed algorithm.
Robust Face Recognition System Using a Reliability Feedback BIBAKFull-Text 178-185
  Shotaro Miwa; Shintaro Watanabe; Makito Seki
In the real world there are a variety of lighting conditions, and there exist many directional lights as well as ambient lights. These directional lights cause partial dark and bright regions on faces. Even if auto exposure mode of cameras is used, those uneven pixel intensities are left, and in some cases saturated pixels and black pixels appear. In this paper we propose robust face recognition system using a reliability feedback. The system evaluates the reliability of the input face image using prior distributions of each recognition feature, and if the reliability of the image is not enough for face recognition, it capture multiple images by changing exposure parameters of cameras based on the analysis of saturated pixels and black pixels. As a result the system can cumulates similarity scores of enough amounts of reliable recognition features from multiple face images. By evaluating the system in an office environment, we can achieve three times better EER than the system only with auto exposure control.
Keywords: Face Recognition; Prior Probability; Probabilistic Model
A Developer-Oriented Visual Model for Upper-Body Gesture Characterization BIBAKFull-Text 186-195
  Simon Ruffieux; Denis Lalanne; Omar Abou Khaled; Elena Mugellini
This paper focuses on a facilitated and intuitive representation of upper-body gestures for developers. The representation is based on the user motion parameters, particularly the rotational and translational components of body segments during a gesture. The developed static representation aims to provide a rapid visualization of the complexity for each body segment involved in the gesture for static representations. The model and algorithms used to produce the representation have been applied to a dataset of 10 representative gestures to illustrate the model.
Keywords: natural interaction; human-computer interaction; multimodality; visualization tools; developer-oriented
Annotate. Train. Evaluate. A Unified Tool for the Analysis and Visualization of Workflows in Machine Learning Applied to Object Detection BIBAKFull-Text 196-205
  Michael Storz; Marc Ritter; Robert Manthey; Holger Lietz; Maximilian Eibl
The development of classifiers for object detection in images is a complex task that comprises the creation of representative and potentially large datasets from a target object by repetitive and time-consuming intellectual annotations, followed by a sequence of methods to train, evaluate and optimize the generated classifier. This is conventionally achieved by the usage and combination of many different tools. Here, we present a holistic approach to this scenario by providing a unified tool that covers the single development stages in one solution to facilitate the development process. We prove this concept by the example of creating a face detection classifier.
Keywords: Model-driven Annotation; Image Processing; Machine Learning; Object Detection; Workflow Analysis
A New Real-Time Visual SLAM Algorithm Based on the Improved FAST Features BIBAFull-Text 206-215
  Liang Wang; Rong Liu; Chao Liang; Fuqing Duan
The visual SLAM is less dependent on hardware, so it attracts growing interests. However, the visual SLAM, especially the Extend Kalman Filter-based monocular SLAM is computational expensive, and is hard to fulfill real-time process. In this paper, we propose an algorithm, which uses the binary robust independent elementary Features descriptor to describe the features from accelerated segment test feature aiming at improving feature points extraction and matching, and combines with the 1-point random sample consensus strategy to speedup the EKF-based visual SLAM. The proposed algorithm can improve the robustness of the EKF-based visual SLAM and make it operate in real-time. Experimental results validate the proposed algorithm.
A Coastline Detection Method Based on Level Set BIBAKFull-Text 216-226
  Qian Wang; Ke Lu; Fuqing Duan; Ning He; Lei Yang
This paper proposes a level set based coastline detection method by using the template initialization and local energy minimization. It can complete the sea-land boundary detection in infrared channel image. This method is an improvement on the traditional level set algorithm by using the information of GSHHS to optimize the initialization procedure, which can reduce the number of iterations and numerical errors. Moreover, this method optimizes regional energy functional, and can achieve the rapid coastline detection. Experiments on the IR image of FY-2 satellite show that the method has fast speed and high accuracy.
Keywords: Edge detection; level set method; IR image processing
Tracking End-Effectors for Marker-Less 3D Human Motion Estimation in Multi-view Image Sequences BIBAKFull-Text 227-235
  Wenzhong Wang; Zhaoqi Wang; Xiaoming Deng; Bin Luo
We propose to track the end-effectors of human body, and use them as kinematic constraints for reliable marker-less 3D human motion tracking. In the presented approach, we track the end-effectors using particle filtering. The tracked results are then combined with image features for 3D full pose tracking. Experimental results verified that the inclusion of end-effectors' constraints improves the tracking performances.
Keywords: end-effectors; motion tracking; particle filtering
Kernel Based Weighted Group Sparse Representation Classifier BIBAKFull-Text 236-245
  Bingxin Xu; Ping Guo; C. L. Philip Chen
Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, SRC can not well classify the data when they are in the overlap feature space. In addition, SRC treats different samples equally and ignores the cooperation among samples belong to the same class. In this paper, a kernel based weighted group sparse classifier (KWGSC) is proposed. Kernel trick is not only used for mapping the original feature space into a high dimensional feature space, but also as a measure to select members of each group. The weight reflects the importance degree of training samples in different group. Substantial experiments on benchmark databases have been conducted to investigate the performance of proposed method in image classification. The experimental results demonstrate that the proposed KWGSC approach has a higher classification accuracy than that of SRC and other modified sparse representation classification.
Keywords: Group sparse representation; kernel method; image classification
Kernel Fuzzy Similarity Measure-Based Spectral Clustering for Image Segmentation BIBAKFull-Text 246-253
  Yifang Yang; Yuping Wang; Yiu-ming Cheung
Spectral clustering has been successfully used in the field of pattern recognition and image processing. The efficiency of spectral clustering, however, depends heavily on the similarity measure adopted. A widely used similarity measure is the Gaussian kernel function where Euclidean distance is used. Unfortunately, the Gaussian kernel function is parameter sensitive and the Euclidean distance is usually not suitable to the complex distribution data. In this paper, a novel similarity measure called kernel fuzzy similarity measure is proposed first, Then this novel measure is integrated into spectral clustering to get a new clustering method: kernel fuzzy similarity based spectral clustering (KFSC). To alleviate the computational complexity of KFSC on image segmentation, Nyström method is used in KFSC. At last, the experiments on three synthetic texture images are made, and the results demonstrate the effectiveness of the proposed algorithm.
Keywords: spectral clustering; kernel fuzzy-clustering; image segmentation; Nyström method
Depth Camera Based Real-Time Fingertip Detection Using Multi-view Projection BIBAKFull-Text 254-261
  Weixin Yang; Zhengyang Zhong; Xin Zhang; Lianwen Jin; Chenlin Xiong; Pengwei Wang
We propose a real-time fingertip detection algorithm based on depth information. It can robustly detect single fingertip regardless of the position and direction of the hand. With the depth information of front view, depth map of top view and side view is generated. Due to the difference between finger thickness and fist thickness, we use thickness histogram to segment the finger from the fist. Among finger points, the farthest point from palm center is the detected fingertip. We collected over 3,000 frames writing-in-the-air sequences to test our algorithm. From our experiments, the proposed algorithm can detect the fingertip with robustness and accuracy.
Keywords: Kinect; depth image; finger detection; fingertip detection; multiview projection
Evaluation of Hip Impingement Kinematics on Range of Motion BIBAKFull-Text 262-269
  Mahshid Yazdifar; Mohammadreza Yazdifar; Pooyan Rahmanivahid; Saba Eshraghi; Ibrahim Esat; Mahmoud Chizari
Femoroacetabulare impingement (FAI) is a mechanical mismatch between femur and acetabulum. It would bring abnormal contact stress and potential joint damage. This problem is more common on people with high level of motion activity such as baler dancer and athletics. FAI causes pain in hip joints and consequently would lead to reduction in range of motion. This study investigates whether changing the kinematics parameters of hip joint with impingement can improve range of motion or not. Hip joint model is created in finite element environment, and then the range of motion was detected. The original boundary conditions are applied in the initial hip impingement model. Then gradually the gap between femur and acetabulum in the model was changed to evaluate the changing kinematics factors on range of motion.
   Mimics (Materialise NV) software was used to generate the surface mesh of three-dimensional (3D) models of the hip joint from computerised tomography (CT) images of the subject patients diagnosed with FAI. The surface mesh models created in Mimics were then exported to Abaqus (Simulia Dassault Systems) to create a finite element (FE) models that will be suitable for mechanical analysis. The surface mesh was converted into a volumetric mesh using Abaqus meshing modules. Material properties of the bones and soft tissues were defined in the FE model. The kinematic values of the joint during a normal sitting stance, which were obtained from motion capture analysis in the gait lab, were used as boundary conditions in the FE model to simulate the motion of the hip joint during a normal sitting stance and find possible contact at the location of the FAI. The centre of rotation for a female hip model with impingement was changed and range of motion was measured in Abaqus. The results were compared to investigate the effect of centre of rotation on range of motion for hip with femoroacetabular impingement. There was a significant change on range of motion with changing the gap between femur and acetabulum. Decreasing the distance between femur and acetabulum decreases the range of motion. When the distance between femur and acetabulum changes the location of impingement shifted. Increasing the distance between femur and acetabulum, there is no noticeable change in the location of impingement. This study concludes that changing the kinematics of hip with impingement changes the range of motion.
Keywords: hip joint; femoroacetabular impingement; finite element; kinematics
Tracking People with Active Cameras BIBAKFull-Text 270-279
  Alparslan Yildiz; Noriko Takemura; Yoshio Iwai; Kosuke Sato
In this paper, we introduce a novel method on tracking multiple people using multiple active cameras. The aim is to capture as many targets as possible at any time using a limited number of active cameras.
   In our context, an active camera is a statically located PTZ (pan-tilt-zoom) camera. Using active cameras for tracking is not researched thoroughly, since it is relatively easier to use increased number of fully static cameras. However, we believe this is costly and a deeper research on the employment of active cameras is necessary.
   Our contributions include the removal of necessity for the detection of each person individually in an efficient way and estimating the future states of the system using a simplified fluid simulation.
Keywords: multiple view; tracking; active cameras
Classification Based on LBP and SVM for Human Embryo Microscope Images BIBAKFull-Text 280-288
  Yabo Yin; Yun Tian; Weizhong Wang; Fuqing Duan; Zhongke Wu; Mingquan Zhou
Embryo transfer is an extremely important step in the process of in-vitro fertilization and embryo transfer (IVF-ET). The identification of the embryo with the greatest potential for producing a child is a very big challenge faced by embryologists. Most current scoring systems of assessing embryo viability are based on doctors' subjective visual analysis of the embryos' morphological features. So it provides only a very rough guide to potential. A classifier as a computer-aided method which is based on Pattern Recognition can help to automatically and accurately select embryos. This paper presents a classifier based on the support vector machine (SVM) algorithm. Key characteristics are formulated by using the local binary pattern (LBP) algorithm, which can eliminate the inter-observer variation, thus adding objectivity to the selection process. The experiment is done with 185 embryo images, including 47 "good" and 138 "bad" embryo images. The result shows our proposed method is robust and accurate, and the accurate rate of classification can reach about 80.42%.
Keywords: embryo microscope images; feature extraction; automatic classifier; local vector pattern; support vector machine
Semantic Annotation Method of Clothing Image BIBAKFull-Text 289-298
  Lu Zhaolao; Mingquan Zhou; Wang Xuesong; Fu Yan; Tan Xiaohui
Semantic annotation is an essential issue for image retrieval. In this paper, we take the online clothing product images as sample. In order to annotate images. we first segment the image into regions, then remove the background and noise information. The illumination and light interference is considered too. Cloth position and region are determined by rules. Images are translated into some features. Visual words are prepared by human and calculate methods. Finally, Image features are mapped to different visual words. Pre-processing and post-processing steps which uses face recognition method and background rule analysis are applied. Finally, some segmentation and annotation results are given to discuss the method.
Keywords: Semantic annotation; Image segmentation; Graph cut

Emotions in HCI

Audio-Based Pre-classification for Semi-automatic Facial Expression Coding BIBAFull-Text 301-309
  Ronald Böck; Kerstin Limbrecht-Ecklundt; Ingo Siegert; Steffen Walter; Andreas Wendemuth
The automatic classification of the users' internal affective and emotional states is nowadays to be considered for many applications, ranging from organisational tasks to health care. Developing suitable automatic technical systems, training material is necessary for an appropriate adaptation towards users. In this paper, we present a framework which reduces the manual effort in annotation of emotional states. Mainly it pre-selects video material containing facial expressions for a detailed coding according to the Facial Action Coding System based on audio features, namely prosodic and mel-frequency features. Further, we present results of first experiments which were conducted to give a proof-of-concept and to define the parameters for the classifier that is based on Hidden Markov Models. The experiments were done on the EmoRec I dataset.
Sentimental Eyes! BIBAKFull-Text 310-318
  Amitava Das; Björn Gambäck
A closer look at how users perform search is needed in order to best design a more efficient next generation sentiment search engine and understand fundamental behaviours involved in online review/opinion search processes. The paper proposes utilizing personalized search, eye tracking and sentiment analysis for better understanding of end-user behavioural characteristics while making a judgement in a Sentiment Search Engine.
Keywords: Sentiment Analysis; Sentiment Search; Eye Tracking
Developing Sophisticated Robot Reactions by Long-Term Human Interaction BIBAFull-Text 319-328
  Hiromi Nagano; Miho Harata; Masataka Tokumaru
In this study, we proposed an emotion generation model for robots that considers mutual effects of desires and emotions. Many researchers are developing partner robots for communicating with people and entertaining them, rather than for performing practical functions. However, people quickly grow tired of these robots owing to their simplistic emotional responses. To solve this issue, we attempted to implement the mutual effects of desires and emotions using internal-states, such as physiological factors. Herein, the simulation results verified that the proposed model expresses complex emotions similar to humans. The results confirmed that the emotions expressed by the proposed model are more complex and realistic than those expressed by a reference model.
An Awareness System for Supporting Remote Communication -- Application to Long-Distance Relationships BIBAKFull-Text 329-338
  Tomoya Ohiro; Tomoko Izumi; Yoshio Nakatani
Recently, the methods of conducting long distance communication have dramatically changed due to improvements in communication technology including TV phones, e-mail, and SNS (Social Networking Services). However, people still have difficulty in enjoying sufficient long distance communication because subtle nuance and atmosphere are difficult to be felt in a distant place. For example, there are many romantic partners with feelings of anxiety about long-distance relationships. This is because an environment that allows the partners to understand each other has not been sufficiently supported. The purpose of this study is to help people separated by a long distance to understand each other by enabling the sensing of a partner's feelings from the partner's behavior. Our target is long-distance romantic partners. When people feel, sense, or are conscious of another person's existence or state, this ability or state is called "awareness.". Awareness is nonverbal communication. Awareness sharing among people is very important for managing relationships successfully, especially for people separated by a long distance. This is because a partner will develop feelings of unease if awareness sharing is not adequate. Our approach is as follows. First, examine what kind of action is useful for representing the feeling of love. Next, monitor these actions in partners. Third, summarize actions to quantitative indications. The prototype system was evaluated through evaluation experiments. Three pairs of partners used the system for two weeks. The result verified the effectiveness of this system as it promoted mutual communication.
Keywords: long distance communication; nonverbal communication; awareness
Emotion Sharing with the Emotional Digital Picture Frame BIBAKFull-Text 339-345
  Kyoung Shin Park; Yongjoo Cho; Minyoung Kim; Ki-Young Seo; Dongkeun Kim
This paper presents the design and implementation of emotional digital picture frame system, which is designed for a group of users to share their emotions via photographs with their own emotional expressions. This system detects user emotions using physiological sensor signals in real-time and changes audio-visual elements of photographs dynamically in response to the user's emotional state. This system allows user emotions to be shared with other users in remote locations. Also, it provides the emotional rule authoring tool to enable users to create their own expression for audio-visual element to fit their emotion. In particular, the rendering elements of a photograph can appear differently when another user's emotion is received.
Keywords: Emotional Digital Picture Frame; Emotional Intelligent Contents; Emotional Rule Authoring Tool
Vision Based Body Dither Measurement for Estimating Human Emotion Parameters BIBAKFull-Text 346-352
  Sangin Park; Deajune Ko; Mincheol Whang; Eui Chul Lee
In this paper, we propose a new body dither analyzing method in order to estimating various kinds of intention and emotion of human. In previous researches for quantitatively measuring human intention and emotion, many kinds of physiological sensors such as ECG, PPG, GSR, SKT, and EEG have been adopted. However, these sensor based methods may supply inconvenience caused by sensor attachment to user. Also, therefrom caused negative emotion can be a noise factor in terms of measuring particular emotion. To solve these problems, we focus on facial dither by analyzing successive image frames captured from conventional webcam. For that, face region is firstly detected from the captured upper body image. Then, the amount of facial movement is calculated by subtracting adjacency two image frames. Since the calculated successive values of facial movement has the form of 1D temporal signal, all of conventional temporal signal processing methods can be used to analysis that. Results of feasibility test by inducing positive and negative emotions showed that more facial movement when inducing positive emotion was occurred compared with the case of negative emotion.
Keywords: Body dither measurement; Emotion recognition; Image subtraction
Evaluating Emotional State during 3DTV Viewing Using Psychophysiological Measurements BIBAKFull-Text 353-361
  Kiyomi Sakamoto; Seiji Sakashita; Kuniko Yamashita; Akira Okada
Using a 50-inch 3DTV, we experimentally estimated the relationship between TV viewers' emotional states and selected physiological indices. Our experiments show complex emotional states to be significantly correlated with these physiological indices, which comprise near-infrared spectroscopy (NIRS), representing central nervous system activity, and the low frequency/high frequency ratio (LF/HF), representing sympathetic nervous system activity. These are useful indices for evaluating emotional states that include "feeling of involvement."
Keywords: emotional states; physiological and psychological measurements; NIRS; HR variability; 3DTV; TV viewing
Affect-Based Retrieval of Landscape Images Using Probabilistic Affective Model BIBAKFull-Text 362-371
  Yunhee Shin; Eun Yi Kim; Tae-Eung Sung
We consider the problem of ranking the web image search using human affects. For this, a Probabilistic Affective Model (PAM) is presented for predicting the affects from color compositions (CCs) of images, then the retrieval system is developed using them. The PAM first segments an image into seed regions, then extracts CCs among seed regions and their neighbors, finally infer the numerical ratings of certain affects by comparing the extracted CCs with pre-defined human-devised color triplets. The performance of the proposed system has been studied at an online demonstration site where 52 users search 16,276 landscape images using affects, then the results demonstrated its effectiveness in affect-based image annotation and retrieval.
Keywords: Affect-based image retrieval; probabilistic affective model; meanshift clustering; color image scale
A Study on Combinative Value Creation in Songs Selection BIBAKFull-Text 372-380
  Hiroko Shoji; Jun Okawa; Ken Kaji; Ogino Akihiro
Recently, advances in information and communications technology have allowed us to easily download our favorite songs from the Internet. A song in general is more often played in sequence with other various ones than listened separately. The evolution of devices, however, has caused an increased number of portable songs and thus frequent difficulties in nicely combining multiple songs from a flood of songs to make a satisfactory playlist. There are many existing research works on songs search and retrieval, such as a songs each system using affective words and a songs recommendation system in consideration for the user's preference. These existing researches, however, are intended for "selecting a single song suited to the user's image", and never takes into consideration a combination of multiple songs. Therefore, it is difficult that existing systems automatically generate a desired playlist.
Keywords: combination value; playlist; recommendation; onomatopoeia
The Influence of Context Knowledge for Multi-modal Affective Annotation BIBAKFull-Text 381-390
  Ingo Siegert; Ronald Böck; Andreas Wendemuth
To provide successful human-computer interaction, automatic emotion recognition from speech experienced greater attention, also increasing the demand for valid data material. Additionally, the difficulty to find appropriate labels is increasing.
   Therefore, labels, which are manageable by evaluators and cover nearly all occurring emotions, have to be found. An important question is how context influences the annotators' decisions. In this paper, we present our investigations of emotional affective labelling on natural multi-modal data investigating different contextual aspects. We will explore different types of contextual information and their influence on the annotation process.
   In this paper we investigate two specific contextual factors, observable channels and knowledge about the interaction course. We discover, that the knowledge about the previous interaction course is needed to assess the affective state, but that the presence of acoustic and video channel can partially replace the lack of discourse knowledge.
Keywords: emotion comparison; affective state; labelling; context influence
Generation of Facial Expression Emphasized with Cartoon Techniques Using a Cellular-Phone-Type Teleoperated Robot with a Mobile Projector BIBAFull-Text 391-400
  Yu Tsuruda; Maiya Hori; Hiroki Yoshimura; Yoshio Iwai
We propose a method for generating facial expressions emphasized with cartoon techniques using a cellular-phone-type teleoperated android with a mobile projector. Elfoid is designed to transmit the speaker's presence to their communication partner using a camera and microphone, and has a soft exterior that provides the look and feel of human skin. To transmit the speaker's presence, Elfoid sends not only the voice of the speaker but also emotional information captured by the camera and microphone. Elfoid cannot, however, display facial expressions because of its compactness and a lack of sufficiently small actuator motors. In this research, facial expressions are generated using Elfoid's head-mounted mobile projector to overcome the problem. Additionally, facial expressions are emphasized using cartoon techniques: movements around the mouth and eyes are emphasized, the silhouette of the face and shapes of the eyes are varied by projection effects, and color stimuli that induce a particular emotion are added. In an experiment, representative face expressions are generated with Elfoid and emotions conveyed to users are investigated by subjective evaluation.

Biophysiological Aspects of Interaction

A Biofeedback Game for Training Arousal Regulation during a Stressful Task: The Space Investor BIBAFull-Text 403-410
  Olle Hilborn; Henrik Cederholm; Jeanette Eriksson; Craig Lindley
Emotion regulation is a topic that has considerable impact in our everyday lives, among others emotional biases that affect our decision making. A serious game that was built in order to be able to train emotion regulation is presented and evaluated here. The evaluation consisted of a usability testing and then an experiment that targeted the difficulty of the game. The results suggested adequate usability and a difficulty that requires the player to engage in managing their emotion in order to have a winning strategy.
Responses Analysis of Visual and Linguistic Information on Digital Signage Using fNIRS BIBAKFull-Text 411-420
  Satoru Iteya; Atsushi Maki; Toshikazu Kato
When customers receive recommended information through digital signage, it is important not only to choose suitable commodities matching each customer's preferences, but also to choose suitable information media to express their features. This paper proposes a method to estimate their preferences on information media by measuring brain activity. First step in order to achieve our final goal, we disclose that there are significant differences in brain activity in case subjects receive recommended information. The result of analysis shows there are significant differences in brain activity, especially visual cortex and language area.
Keywords: fNIRS; Preference on Commodities and Information Parts; Information Recommendation
A Method for Promoting Interaction Awareness by Biological Rhythm in Elementary School Children BIBAKFull-Text 421-430
  Kyoko Ito; Kosuke Ohmori; Shogo Nishida
Recently, in Japan, education about the ability to make decisions as part of a group composed of children with different ways of thinking has become more important. Therefore, discussion activities have been adopted in elementary school education. This study considers a method that supports discussion activities by making children aware of the "state" (i.e., atmosphere, progress) of their group during discussion, and of the ways they are influencing this state themselves. We developed a system which allows us to visualize the entrainment of the biological rhythm to present the group's state. An experiment using this system was conducted to clarify whether the children were aware of the group state during discussion, and how they were affected by this awareness. We found that this system has the potential to support children when considering ways of participating in the discussion. Also, it was found that the system can act as an interface, encouraging children to think about the importance of their listening to others in the group.
Keywords: Education support; Elementary school education; discussion activity; interaction; biological rhythm
Internet Anxiety: Myth or Reality? BIBAKFull-Text 431-440
  Santosh Kumar Kalwar; Kari Heikkinen; Jari Porras
The purpose of this paper is to determine if Internet anxiety is a myth or reality using literature, questionnaires, and analysis of the collected data. Results showed that the Internet anxiety phenomenon is mostly reality. By placing strong emphasis on the existent Internet anxiety phenomenon, the HCI community could constructively build effective tools and techniques to mitigate users' anxiety.
Keywords: Internet; anxiety; concept; qualitative; myth; reality
Brain Function Connectivity Analysis for Recognizing Different Relation of Social Emotion in Virtual Reality BIBAKFull-Text 441-447
  Jonghwa Kim; Dongkeun Kim; Sangmin Ann; Sangin Park; Mincheol Whang
Social emotions are emotion that can be induced from human social relationships when people are interacting with others. In this study, we are aim to analyze a brain function connectivity in terms of different relations of social emotions. The brain function connectivity can be used to observe the neural responses with features of EEG coherences during a cognitive process. In this study, the EEG coherence is measured according to different social emotion evocations. The auditory and visual stimulus for inducing social emotions was presented to participants during 20.5 sec (±3.1 sec). The participants were asked to imagine and explain about similar emotion experience after watching each video clips. The measured EEG coherence was grouped into two different social emotion categories; the information sharing relation and emotion sharing relation, and compared with the results of subjective evaluation and independent T-test. The information sharing relation was related with the brain connectivity of the right temporo-occipital position associated with a language memory. The emotion sharing relation was related with the brain connectivity of the left fronto-right parietal position associated with a visual information processing area.
Keywords: Emotion; Social emotion; Emotion relation; EEG coherence; Brain function connectivity
A Mobile Brain-Computer Interface for Freely Moving Humans BIBAKFull-Text 448-453
  Yuan-Pin Lin; Yijun Wang; Chun-Shu Wei; Tzyy-Ping Jung
Recent advances in mobile electroencephalogram (EEG) systems featuring dry electrodes and wireless telemetry have promoted the applications of brain-computer interfaces (BCIs) in our daily life. In the field of neuroscience, understanding the underlying neural mechanisms of unconstrained human behaviors, i.e. freely moving humans, is accordingly in high demand. The empirical results of this study demonstrated the feasibility of using a mobile BCI system to detect steady-state visual-evoked potential (SSVEP) of the participants during natural human walking. This study considerably facilitates the process of bridging laboratory-oriented BCI demonstrations into mobile EEG-based systems for real-life environments.
Keywords: EEG; BCI; SSVEP; moving humans
The Solid Angle of Light Sources and Its Impact on the Suppression of Melatonin in Humans BIBAKFull-Text 454-463
  Philipp Novotny; Peyton Paulick; Markus J. Schwarz; Herbert Plischke
Our group conducted a preliminary study to examine the influence of different sizes of light sources, and therefore different illuminance levels, at the retina. Six participants were exposed to two lighting scenarios and saliva samples were collected to determine melatonin levels throughout the experiment. Melatonin levels were analyzed to compare the efficacy of each lighting scenario and its ability to suppress melatonin period. Our data is showing a trend that both lighting scenarios are capable of suppressing melatonin. Moreover, the preliminary data show that the lighting scenario with the large solid angle is more effective at suppressing melatonin compared to the lighting scenario with the small solid angle lighting scenario period. Further testing with a larger patient population will need to be done to prove statistical significance of our findings. Our further studies will repeat this experiment with a larger test group and modifying the time frame between different lighting scenarios period.
Keywords: light; health; melatonin; suppression; optimal healing environment; chronodisruption; circadian rhythm; shift work; dementia; light therapy
Facial Electromyogram Activation as Silent Speech Method BIBAKFull-Text 464-473
  Lisa Rebenitsch; Charles B. Owen
A wide variety of alternative speech-free input methods have been developed, including speech recognition, gestural commands, and eye typing. These methods are beneficial not only for the disabled, but for situations where the hands are preoccupied. However, many of these methods are sensitive to noise, tolerate little movement, and require it to be the primary focus of the environment. Morse code offers an alternative when background noise cannot be managed. A Morse code-inspired application was developed employing electromyograms. Several muscles were explored to determine potential electrode sites that possessed good sensitivity and were robust to normal movement. The masseter jaw muscle was selected for later testing. The prototype application demonstrated that the jaw muscle can be used as a Morse "key" while being robust to normal speech.
Keywords: Silent Speech; Human computer interaction; User interfaces
The Impact of Gender and Sexual Hormones on Automated Psychobiological Emotion Classification BIBAKFull-Text 474-482
  Stefanie Rukavina; Sascha Gruss; Jun-Wen Tan; David Hrabal; Steffen Walter; Harald C. Traue; Lucia Jerg-Bretzke
It is a challenge to make cognitive technical systems more empathetic for user emotions and dispositions. Among channels like facial behavior and nonverbal cues, psychobiological patterns of emotional or dispositional behavior contain rich information, which is continuously available and hardly willingly controlled. However, within this area of research, gender differences or even hormonal cycle effects as potential factors in influencing the classification of psychophysiological patterns of emotions have rarely been analyzed so far.
   In our study, emotions were induced with a blocked presentation of pictures from the International Affective Picture System (IAPS) and Ulm pictures. For the automated emotion classification in a first step 5 features from the heart rate signal were calculated and in a second step combined with two features of the facial EMG. The study focused mainly on gender differences in automated emotion classification and to a lesser degree on classification accuracy with Support Vector Machine (SVM) per se. We got diminished classification results for a gender mixed population and also we got diminished results for mixing young females with their hormonal cycle phases. Thus, we could show an improvement of the accuracy rates when subdividing the population according to their gender, which is discussed as a possibility of incrementing automated classification results.
Keywords: emotion classification; gender; hormonal cycle; heart rate; facial EMG
Evaluation of Mono/Binocular Depth Perception Using Virtual Image Display BIBAKFull-Text 483-490
  Shys-Fan Yang-Mao; Yu-Ting Lin; Ming-Hui Lin; Wen-Jun Zeng; Yao-lien Wang
Augmented reality (AR) is a very popular technology in various applications. It allows the user to see the real world, with virtual objects composited with or superimposed upon the real world. The usability of interactive user interface based on AR relies heavily on visibility and depth perception of content, virtual image display particularly. In this paper, we performed several basic evaluations for a commercial see-through head mounted display based on those factors that can change depth perception: binocular or monocular, viewing distance, eye dominance, content changed in shape or size, indicated by hand or reference object. The experiment results reveal many interesting and fascinating features. The features will be user interface design guidelines for every similar see-through near-eye display systems.
Keywords: augmented reality; virtual image display; see-through near-eye display; user interface; depth perception
Visual Image Reconstruction from fMRI Activation Using Multi-scale Support Vector Machine Decoders BIBAKFull-Text 491-497
  Yu Zhan; Jiacai Zhang; Sutao Song; Li Yao
The correspondence between the detailed contents of a person's mental state and human neuroimaging has yet to be fully explored. Previous research reconstructed contrast-defined images using combination of multi-scale local image decoders, where contrast for local image bases was predicted from fMRI activity by sparse logistic regression (SLR). The present study extends this research to probe into accurate and effective reconstruction of images from fMRI. First, support vector machine (SVM) was employed to model the relationship between contrast of local image and fMRI; second, additional 3-pixel image bases were considered. Reconstruction results demonstrated that the time consumption in modeling the local image decoder was reduced to 1% by SVM compared to SLR. Our method also improved the spatial correlation between the stimulus and reconstructed image. This finding indicated that our method could read out what a subject was viewing and reconstruct simple images from brain activity at a high speed.
Keywords: Image Reconstrution; fMRI; Multi-scale; SVM
Alterations in Resting-State after Motor Imagery Training: A Pilot Investigation with Eigenvector Centrality Mapping BIBAKFull-Text 498-504
  Rushao Zhang; Hang Zhang; Lele Xu; Mingqi Hui; Zhiying Long; Yijun Liu; Li Yao
Motor training, including motor execution and motor imagery training, has been indicated to be effective in mental disorders rehabilitation and motor skill learning. In related neuroimaging studies, resting-state has been employed as a new perspective besides task-state to examine the neural mechanism of motor execution training. However, motor imagery training, as another part of motor training, has been few investigated. To address this issue, eigenvector centrality mapping (ECM) was applied to explore resting-state before and after motor imagery training. ECM could assess the computational measurement of eigenvector centrality for capturing intrinsic neural architecture on a voxel-wise level without any prior assumptions. Our results revealed that the significant increases of eigenvector centrality were in the precuneus and medial frontal gyrus (MFG) for the experimental group but not for the control group. These alterations may be associated with the sensorimotor information integration and inner state modulation of motor imagery training.
Keywords: Motor imagery; functional magnetic resonance imaging (fMRI); ECM; precuneus; medial frontal gyrus (MFG)