| 日時(Datetime) | 令和7年6月24日(火)3限 (13:30--15:00), 2025/06/24, Tuesday, 3rd slot |
|---|---|
| 場所(Location) | パナソニックISセミナーホール（L1）, Panasonic IS Seminar Hall （L1） |
| 司会(Chair) | Faisal sensei |
| 講演者(Presenter) | Bagus Tris Atmaja, ヒューマンAIインタラクション研究室 (Human-AI Interaction Research Lab.) |
|---|---|
| 題目(Title) | Make AI Emotionally Intelligent |
| 概要(Abstract) | As artificial intelligence continues to evolve, its integration into everyday human experiences demands more than just logical precision—it requires emotional intelligence. This speech explores the imperative of developing AI systems that can recognize, interpret, and respond appropriately to human emotions. By embedding emotional intelligence into AI, we move toward machines that not only process data but also understand human context, foster empathy, and build trust. The talk delves into the interdisciplinary approaches behind emotionally intelligent AI, drawing from infomation science,speech processing, and affective computing. It highlights current advancements in speech emotion recognition and emotional speech synthesis using multimodal, multitask, and multilingual approach. It also suggests practical applications in fields such as mental health, education, and customer service, and addresses ethical concerns and technical challenges. Ultimately, the goal is to spark a dialogue on how we can design emotionally aware AI that enriches human-AI interaction and contributes positively to society. |
| 講演者(Presenter) | Hiroyoshi Ogishima, 脳･行動モデリング研究室 (Computational Behavioral Neuroscience Research Lab.) |
|---|---|
| 題目(Title) | The Empirical Mechanisms of the New Wave of Cognitive Behavioral Therapy |
| 概要(Abstract) | Although a wide range of treatments are available for depression, many patients continue to show resistance to conventional approaches. Mindfulness-based therapies, which incorporate meditation techniques rooted in Eastern traditions, have recently gained significant attention as a promising “new wave” of cognitive behavioral therapy—especially for individuals with recurrent depression. Despite this interest, the specific mechanisms by which mindfulness alleviates depressive symptoms remain unclear. This talk presents a series of studies demonstrating that mindfulness can improve depression by enhancing interoceptive awareness—that is, the ability to perceive internal bodily sensations. Through a combination of EEG analysis, psychological experiments, and time-series intervention data from 82 participants, these studies indicate that improvements in interoceptive awareness can lead to increased use of adaptive cognitive and emotional coping strategies. Finally, this talk will discuss the potential for developing mathematical models that objectively describe the mechanisms of mindfulness, aiming to deepen the scientific understanding of meditation as an internal process. |
| 講演者(Presenter) | Gu Yi, 生体画像知能研究室 (Biomedical Imaging Intelligence Research Lab.) |
|---|---|
| 題目(Title) | Fine-Grained Musculoskeletal Analysis from a Plain X-ray Image |
| 概要(Abstract) | Musculoskeletal disorders pose a growing challenge worldwide, underscoring the need for accessible and cost-effective diagnostic solutions. While quantitative computed tomography (QCT) and dual-energy X-ray absorptiometry (DXA) provide accurate assessments of bone mineral density (BMD) and muscle metrics, these modalities remain limited in availability and affordability. In this talk, I present our works for musculoskeletal analysis that rely on plain X-ray images--a far more ubiquitous and economical modality. By learning to synthesize 2D metric distribution maps (subsets of CT information), the proposed methods enable fine-grained musculoskeletal analysis, including BMD estimation, muscle mass and volume estimation, and 3D bone reconstruction, in an efficient way. Experimental results on clinical data demonstrate that our methods closely approximate the quantitative information conventionally obtained from QCT or DXA. This outcome paves the way for scalable, opportunistic screening and continued monitoring of musculoskeletal health, significantly reducing both clinical burden and cost while retaining substantial diagnostic value. |