The main idea of filter methods in feature selection is constructing a feature-assessing criterion and searching for feature subset that optimizes the criterion. The primary principle of designing such criterion is to capture the relevance between feature subset and the class as precisely as possible. It would be difficult to compute the relevance directly due to the computation complexity when the size of feature subset grows. As a result, researchers adopt approximate strategies to measure relevance. Though these strategies worked well in some applications, they suffer from three problems: parameter determination problem, the neglect of feature interaction information and overestimation of some features. We propose a new feature selection algorithm that could compute mutual information between feature subset and the class directly without deteriorating computation complexity based on the computation of partitions. In light of the specific properties of mutual information and partitions, we propose a pruning rule and a stopping criterion to accelerate the searching speed. To evaluate the effectiveness of the proposed algorithm, we compare our algorithm to the other five algorithms in terms of the number of selected features and the classification accuracies on three classifiers. The results on the six synthetic datasets show that our algorithm performs well in capturing interaction information. The results on the thirteen real world datasets show that our algorithm selects less yet better feature subset.

We propose a method for embedding the awareness state and response state in an image-based avatar to smoothly and automatically start an interaction with a user. When both states are not embedded, the image-based avatar can become non-responsive or slow to respond. To consider the beginning of an interaction, we observed the behaviors between a user and receptionist in an information center. Our method replayed the behaviors of the receptionist at appropriate times in each state of the image-based avatar. Experimental results demonstrate that, at the beginning of the interaction, our method for embedding the awareness state and response state increased subjective scores more than not embedding the states.

The Technical Committee on Communication Behavior Engineering addresses the research question “How do we construct a communication network system that includes users?”. The growth in highly functional networks and terminals has brought about greater diversity in users' lifestyles and freed people from the restrictions of time and place. Under this situation, the similarities of human behavior cause traffic aggregation and generate new problems in terms of the stabilization of network service quality. This paper summarizes previous studies relevant to communication behavior from a multidisciplinary perspective and discusses the research approach adopted by the Technical Committee on Communication Behavior Engineering.

Small group detection is still a challenging problem in crowds. Traditional methods use the trajectory information to measure pairwise similarity which is sensitive to the variations of group density and interactive behaviors. In this paper, we propose two types of information by simultaneously incorporating trajectory and interaction information, to detect small groups in crowds. The trajectory information is used to describe the spatial proximity and motion information between trajectories. The interaction information is designed to capture the interactive behaviors from video sequence. To achieve this goal, two classifiers are exploited to discover interpersonal relations. The assumption is that interactive behaviors often occur in group members while there are no interactions between individuals in different groups. The pairwise similarity is enhanced by combining the two types of information. Finally, an efficient clustering approach is used to achieve small group detection. Experiments show that the significant improvement is gained by exploiting the interaction information and the proposed method outperforms the state-of-the-art methods.

This paper discusses the use of a common computer mouse as a pointing interface for tabletop displays. In the use of a common computer mouse for tabletop displays, there might be an angular distance between the screen coordinates and the mouse control coordinates. To align those coordinates, this paper introduces a screen coordinates calibration technique using a shadow cursor. A shadow cursor is the basic idea of manipulating a mouse cursor without any visual feedbacks. The shadow cursor plays an important role in obtaining the angular distance between the two coordinates. It enables the user to perform a simple mouse manipulation so that screen coordinates calibration will be completed in less than a second.

This study focuses on modeling the storytelling performance of the participants in a group conversation. Storytelling performance is one of the fundamental communication techniques for providing information and entertainment effectively to a listener. We present a multimodal analysis of the storytelling performance in a group conversation, as evaluated by external observers. A new multimodal data corpus is collected through this group storytelling task, which includes the participants' performance scores. We extract multimodal (verbal and nonverbal) features regarding storytellers and listeners from a manual description of spoken dialog and from various nonverbal patterns, including each participant's speaking turn, utterance prosody, head gesture, hand gesture, and head direction. We also extract multimodal co-occurrence features, such as head gestures, and interaction features, such as storyteller utterance overlapped with listener's backchannel. In the experiment, we modeled the relationship between the performance indices and the multimodal features using machine-learning techniques. Experimental results show that the highest accuracy (R2) is 0.299 for the total storytelling performance (sum of indices scores) obtained with a combination of verbal and nonverbal features in a regression task.

Adding versatile interactions to imperative programming - C, Java and Android - is an essential task. Unfortunately, existing languages provide only limited constructs for user interaction. These constructs are usually in the form of unbounded quantification. For example, existing languages can take the keyboard input from the user only via the read(x)/scan(x) statement. Note that the value of x is unbounded in the sense that x can have any value. This statement is thus not useful for applications with bounded inputs. To support bounded choices, we propose new bounded-choice statements for user interation. Each input device (keyboard, mouse, touchpad, ...) naturally requires a new bounded-choice statement. To make things simple, however, we focus on a bounded-choice statement for keyboard - kchoose - to allow for more controlled and more guided participation from the user. We illustrate our idea via CBI, an extension of the core C with a new bounded-choice statement for the keyboard.

In recent years, researchers have tried to create unhindered human-computer interaction by giving virtual agents human-like conversational skills. Predicting backchannel feedback for agent listeners has become a novel research hot-spot. The main goal of this paper is to identify appropriate features and methods for backchannel prediction in Mandarin conversations. Firstly, multimodal Mandarin conversations are recorded for the analysis of backchannel behaviors. In order to eliminate individual difference in the original face-to-face conversations, more backchannels from different listeners are gathered together. These data confirm that backchannels occurring in the speakers' pauses form a vast majority in Mandarin conversations. Both prosodic and visual features are used in backchannel prediction. Four types of models based on the speakers' pauses are built by using support vector machine classifiers. An evaluation of the pause-based prediction model has shown relatively high accuracy in consideration of the optional nature of backchannel feedback. Finally, the results of the subjective evaluation validate that the conversations performed between humans and virtual listeners using backchannels predicted by the proposed models is more unhindered compared to other backchannel prediction methods.

To represent interactive objects, we propose a choice-disjunctive declaration statement of the form $S add R$ where S, R are the (procedure or field) declaration statements within a class. This statement has the following semantics: request the user to choose one between S and R when an object of this class is created. This statement is useful for representing interactive objects that require interaction with the user.

With the rapid growth of high performance ICT (Information Communication Technologies) devices such as smart phones and tablet PCs, multitasking has become one of the popular ways of using mobile devices. The reasons users have adopted multitask operation are that it reduces the level of dissatisfaction regarding waiting time and makes effective use of time by switching their attention from the waiting process to other content. This is a good solution to the problem of waiting; however, it may cause another problem, which is the increase in traffic volume due to the multiple applications being worked on simultaneously. Thus, an effective method to control throughput adapted to the multitasking situation is required. This paper proposes a transmission rate control method for web browsing that takes multitasking behavior into account and quantitatively demonstrates the effect of service by two different field experiments. The main contribution of this paper is to present a service design process for a new transmission rate control that takes into account human-network interaction based on the human-centered approach. We show that the degree of satisfaction in relation to waiting time did not degrade even when a field trial using a testbed showed that throughput of the background task was reduced by 40%.

This paper presents an experimental study that analyzes how conversational agents activate human communication in thought-evoking multi-party dialogues between multi-users and multi-agents. A thought-evoking dialogue is a kind of interaction in which agents act to provoke user thinking, and it has the potential to activate multi-party interactions. This paper focuses on quiz-style multi-party dialogues between two users and two agents as an example of thought-evoking multi-party dialogues. The experimental results revealed that the presence of a peer agent significantly improved user satisfaction and increased the number of user utterances in quiz-style multi-party dialogues. We also found that agents' empathic expressions significantly improved user satisfaction, improved user ratings of the peer agent, and increased the number of user utterances. Our findings should be useful for activating multi-party communications in various applications such as pedagogical agents and community facilitators.

This paper presents our project of designing EdgeWrite text entry methods for Japanese language. We are developing a version of EdgeWrite text entry method for Japanese language: Katakana EdgeWrite. Katakana EdgeWrite specifies the line stroke directions and writing order of the Japanese Katakana character. The ideal corner sequence pattern of EdgeWrite for each Katakana character is designed based on its line stroke directions and writing order.

This paper proposes a novel multimodal interactive surgical simulator that incorporates haptic, olfactory, as well as traditional vision feedback. A scent diffuser was developed to produce odors when errors occur. Haptic device was used to provide the sense of touch to the user. The preliminary results show that adding smell as an aid to the simulation enhanced the memory retention that lead to better performance.

Combinatorial interaction testing has been well studied in recent years, and has been widely applied in practice. It generally aims at generating an effective test suite (an interaction test suite) in order to identify faults that are caused by parameter interactions. Due to some constraints in practical applications (e.g. limited testing resources), for example in combinatorial interaction regression testing, prioritized interaction test suites (called interaction test sequences) are often employed. Consequently, many strategies have been proposed to guide the interaction test suite prioritization. It is, therefore, important to be able to evaluate the different interaction test sequences that have been created by different strategies. A well-known metric is the Average Percentage of Combinatorial Coverage (shortly APCCλ), which assesses the rate of interaction coverage of a strength λ (level of interaction among parameters) covered by a given interaction test sequence S. However, APCCλ has two drawbacks: firstly, it has two requirements (that all test cases in S be executed, and that all possible λ-wise parameter value combinations be covered by S); and secondly, it can only use a single strength λ (rather than multiple strengths) to evaluate the interaction test sequence - which means that it is not a comprehensive evaluation. To overcome the first drawback, we propose an enhanced metric Normalized APCCλ (NAPCC) to replace the APCCλ Additionally, to overcome the second drawback, we propose three new metrics: the Average Percentage of Strengths Satisfied (APSS); the Average Percentage of Weighted Multiple Interaction Coverage (APWMIC); and the Normalized APWMIC (NAPWMIC). These metrics comprehensively assess a given interaction test sequence by considering different interaction coverage at different strengths. Empirical studies show that the proposed metrics can be used to distinguish different interaction test sequences, and hence can be used to compare different test prioritization strategies.

Traditional face swapping technologies require that the faces of source images and target images have similar pose and appearance (usually frontal). For overcoming this limit in applications this paper presents a pose-free face swapping method based on personalized 3D face modeling. By using a deformable 3D shape morphable model, a photo-realistic 3D face is reconstructed from a single frontal view image. With the aid of the generated 3D face, a virtual source image of the person with the same pose as the target face can be rendered, which is used as a source image for face swapping. To solve the problem of illumination difference between the target face and the source face, a color transfer merging method is proposed. It outperforms the original color transfer method in dealing with the illumination gap problem. An experiment shows that the proposed face reconstruction method is fast and efficient. In addition, we have conducted experiments of face swapping in a variety of scenarios such as children's story book, role play, and face de-identification stripping facial information used for identification, and promising results have been obtained.

To help student nurses learn to transfer patients from a bed to a wheelchair, this paper proposes a system for automatic skill evaluation in nurses' training for this task. Multiple Kinect sensors were employed, in conjunction with colored markers attached to the trainee's and patient's clothing and to the wheelchair, in order to measure both participants' postures as they interacted closely during the transfer and to assess the correctness of the trainee's movements and use of equipment. The measurement method involved identifying body joints, and features of the wheelchair, via the colors of the attached markers and calculating their 3D positions by combining color and depth data from two sensors. We first developed an automatic segmentation method to convert a continuous recording of the patient transfer process into discrete steps, by extracting from the raw sensor data the defining features of the movements of both participants during each stage of the transfer. Next, a checklist of 20 evaluation items was defined in order to evaluate the trainee nurses' skills in performing the patient transfer. The items were divided into two types, and two corresponding methods were proposed for classifying trainee performance as correct or incorrect. One method was based on whether the participants' relevant body parts were positioned in a predefined spatial range that was considered ‘correct’ in terms of safety and efficacy (e.g., feet placed appropriately for balance). The second method was based on quantitative indexes and thresholds for parameters describing the participants' postures and movements, as determined by a Bayesian minimum-error method. A prototype system was constructed and experiments were performed to assess the proposed approach. The evaluation of nurses' patient transfer skills was performed successfully and automatically. The automatic evaluation results were compared with evaluation by human teachers and achieved an accuracy exceeding 80%.

A macroscopic structure was analyzed for a system comprising multiple elements in which the dynamics is affected by their distribution. First, a nonlinear Boltzmann equation, which has an integration term with respect to the distribution of the elements, was derived. Next, the moment vector equation (MVE) for the Boltzmann equation was derived. The average probability density function (pdf) in a steady state was derived using eigen analysis of the coefficient matrix of the MVE. The macroscopic structure of the system and the mechanism that provides the average pdf and the transient response were then analyzed using eigen analysis. Evaluation of the average pdf and transient response showed that using eigen analysis is effective for analyzing not only the transient and stationary properties of the system but also the macroscopic structure and the mechanism providing the properties.

Recognizing human action in complex scenes is a challenging problem in computer vision. Some action-unrelated concepts, such as camera position features, could significantly affect the appearance of local spatio-temporal features, and therefore the performance of low-level features based methods degrades. In this letter, we define the action-unrelated concept: the position of camera as high-level features. We observe that they can serve as a prior to local spatio-temporal features for human action recognition. We encode this prior by modeling interactions between spatio-temporal features and camera position features. We infer camera position features from local spatio-temporal features via these interactions. The parameters of this model are estimated by a new max-margin algorithm. We evaluate the proposed method on KTH, IXMAS and Youtube actions datasets. Experimental results show the effectiveness of the proposed method.

To understand human emotion, it is necessary to be aware of the surrounding situation and individual personalities. In most previous studies, however, these important aspects were not considered. Emotion recognition has been considered as a classification problem. In this paper, we attempt new approaches to utilize a person's situational information and personality for use in understanding emotion. We propose a method of extracting situational information and building a personalized emotion model for reflecting the personality of each character in the text. To extract and utilize situational information, we propose a situation model using lexical and syntactic information. In addition, to reflect the personality of an individual, we propose a personalized emotion model using KBANN (Knowledge-based Artificial Neural Network). Our proposed system has the advantage of using a traditional keyword-spotting algorithm. In addition, we also reflect the fact that the strength of emotion decreases over time. Experimental results show that the proposed system can more accurately and intelligently recognize a person's emotion than previous methods.

This study investigated the relationship between human use of automation and their sensitivity to changes in automation and manual performance. In the real world, automation and manual performance change dynamically with changes in the environment. However, a few studies investigated whether changes in automation or manual performance have more effect on whether users choose to use automation. We used two types of experimental tracking tasks in which the participants had to select whether to use automation or conduct manual operation while monitoring the variable performance of automation and manual operation. As a result, we found that there is a mutual relationship between human use of automation and their sensitivity to automation and manual performance changes. Also, users do not react equally to both automation and manual performance changes although they use automation adequately.