Adolescents and their parents hesitate to acknowledge mental health issues until symptoms severely worsen, making timely treatment challenging. Moreover, infrequent psychiatric consultations often fail to adjust treatments to the dynamic nature of mental health states. To address these issues, our paper proposes an AI-based mental health assessment framework for adolescent mental health through non-invasively collected data from daily digital activities on their mobile devices, including tablets and smartphones. For this, we collect fifteen different types of passive sensor data across three primary categories of activities: studying, smartphone using, and metaverse gaming. Additionally, each adolescent completes self-survey reports on eight different disorders which are used as labels. Then, feature extraction is conducted based on this dataset, which yields 1,523 features that could function as potential digital biomarkers of mental health conditions in adolescents. Utilizing these features, our algorithm named CAMP: Customizable Automated Machine learning Process incorporates simulated annealing for feature selection. This approach enables the construction of AI models for mental health assessment that are finely tuned to domain specific strategies. Our experiments show that our proposed framework can significantly improve models' performance.

As the activity of flying drones becomes increasingly widespread, drone accidents are also increasing. Many of these accidents are related to operational issues and, therefore, it is urgent to improve drone controls. The purpose of this study was to evaluate the usability of a drone controller interface supporting an external pilot's egocentric perspective. The interface tried to solve the problem of misaligned perspectives that arise from controllers constructed from a drone-centric or allocentric perspective. To achieve this, two experiments were performed to identify the differences in control performance depending on embodied mental rotation. The results of the experiments revealed that the controller designed from the pilot's egocentric point of view had a stronger performance regardless of the direction of drone flight. Based on the results, implications are discussed.

Remote pointing devices like the Wii remote have a wide range of applications and are becoming more important for the manipulation of and interactions with information on a distant display such as smart TVs. Because remote pointing devices are used without external support, however, muscular tremors and motional disparity between the display and motor space can result in usability problems of mouse jitters and instability. In this research, a solution is proposed to those problems using feedforward technology, where a user is provided with predictive information in multisensory modalities while approaching a target. Also, gender effect on the user experience of remote pointing devices is examined. By conducting two experiments and a survey, it was found that the feedforward signal plays a role of precue and is more effective than the typical feedback. It was also found that the modality variations in feedforward were impacted by the gender of the user. The findings can be used to improve user interfaces for remote pointing controllers.

The second devices like tablet PCs give additional contextual information to the user while watching TV in a home network environment. With the growing number of smart devices produced in the last few years, we also need to provide users good user experiences when they use individual second device. In this paper, we propose a framework for context-awarable user interfaces of the second screen devices to serve users more adaptive additional contents in a home network environment. We have described the architecture of the framework and also developed prototype system to provider adaptive user interfaces for second devices with real IPTV service.

One of Autism Spectrum Disorder (ASD)' major characteristics is the lack of social communication and interaction with other people. Recently, some research studies have examined robot-based interventions for children with ASD. In line with those studies, the present paper introduces our ongoing research on robot-mediated imitation training for children with ASD. In this paper, we focus on designing human-robot interaction for autism intervention whereas previous studies largely focused on developing robots for intervention. Several human-robot interaction scenarios for robot-mediated imitation training were developed with emphasis on facilitating communication between a child and a therapist. Two main concepts (triadic interaction and reciprocal imitation training) were adopted and modified to increase the efficacy of the intervention. The developed interaction scenarios described how a robot can be integrated into the clinical sessions and the requirements for a robot. The field trials for examining the efficacy of robot-mediated imitation training will be carried out.

As empathy is important for the emotional interaction between a human and a robot, the design factors which induce human empathy toward robots need to be explored. Human empathy toward a robot can be affected by the presence of a robot. Thus, we focused on the levels of agency and the physical embodiment of a robot, which are influential factors pertaining to social presence, by executing two experiments. In the first experiment, in a 2 (levels of agency: mediated vs. simulated) between-participants experiment, participants interacted with either a mediated robot which delivers the emotional state of a remote user or a simulated robot which expresses its own emotion. Participants empathized more with the mediated robot than with the simulated robot, demonstrating that the proper form of an emotional robot is as a mediator during emotional interaction between people. In the second study, in a 2 (physical embodiment: physically embodied vs. physically disembodied) between-participants experiment design, participants interacted with either a physically embodied robot or a physically disembodied robot. The results showed that participants empathized more with a physically embodied robot than with a physically disembodied robot, indicating the impact of physical embodiment on human empathy. Implications for the design of human-robot interactions are discussed.

This paper presents a preliminary study on a new vibrotactile rendering method which can make smoother directional vibrotactile flows on a thin plate. Both by actuating two piezoelectric actuators sequentially from one side to the opposite side and by controlling amplitude-modulated input excitation frequency from zero to the 1stmode of the resonant frequency of a thin plate, a user can feel a smoother directional vibrotactile flows on his/her palm as he/she touches the surface of the thin plate. Experimental results and a user study show that the proposed vibrotactile flow is smoother than the vibrotactile flow that can be generated by the traditional apparent tactile movement and phantom sensation generation methods. The smooth directional vibrotactile flow may be useful for identifying callers or give directional information in navigation maps in mobile devices.

In this paper, we explore the possibility of using animal robot for teaching social behaviors, especially caregiving behavior to children with Autistic Spectrum Disorders (ASD) and Pervasive Development Disorder (PDD).

This paper describes a Web-based reciprocal peer review system called scaffolded writing and rewriting in the discipline (SWoRD), addressing its approaches to writing and rewriting as a sound function of peer reviews. It also provides an empirical evaluation showing that reciprocal peer reviews through SWoRD are very effective in improving writing quality in content classes.