Designing an Empathy Training for Depression Prevention Using Virtual Reality and a Preliminary Study

As virtual reality (VR) is labeled by many as 'an ultimate empathy machine,' immersive VR applications have the potential to assist in empathy training for mental healthcare such as depression [21]. In responding to the increasing numbers of diagnosed depression throughout COVID-19, a first-person VR adventure game called 'Schwer' was designed and prototyped by the authors' research team to provide a social support environment for depression treatment. To continue the study and assess the training effectiveness for an appropriate level of empathy, this current article includes a brief survey on data analytics models and features to accumulate evidence for the next phase of the study, an interactive game-level design for the 'Reconstruction' stage, and a preliminary study with data collection. The preliminary study was conducted with a post-game interview to evaluate the design of the levels and their effectiveness in empathy training. Results showed that the game was rated as immersive by all participants. Feedback on the avatar design indicated that two out of three of the non-player characters (NPCs) have made the intended effect. Participants showed mostly positive opinion towards their experienced empathy and provided feedback on innovative teleport mechanism and game interaction. The findings from the literature review and the results of the preliminary study will be used to further improve the existing system and add the data analytics model training. The long-term research goal is to contribute to the healthcare field by developing a dynamic AI-based biofeedback immersive VR system in assisting depression prevention. © 2023 IEEE.

Medical Image Classification based on an Adaptive Size Deep Learning Model

With the rapid development of Artificial Intelligence (AI), deep learning has increasingly become a research hotspot in various fields, such as medical image classification. Traditional deep learning models use Bilinear Interpolation when processing classification tasks of multi-size medical image dataset, which will cause the loss of information of the image, and then affect the classification effect. In response to this problem, this work proposes a solution for an adaptive size deep learning model. First, according to the characteristics of the multi-size medical image dataset, the optimal size set module is proposed in combination with the unpooling process. Next, an adaptive deep learning model module is proposed based on the existing deep learning model. Then, the model is fused with the size fine-tuning module used to process multi-size medical images to obtain a solution of the adaptive size deep learning model. Finally, the proposed solution model is applied to the pneumonia CT medical image dataset. Through experiments, it can be seen that the model has strong robustness, and the classification effect is improved by about 4% compared with traditional algorithms.