2025 a2 National Symposium Keynote Speech: Pattie Maes, PhD– Opportunities for AI and Wearables to Support Healthy Aging

  • Post category:Events

As the global population ages, cognitive decline and social isolation pose significant challenges to independent living and well-being. In this keynote, Dr. Pattie Maes presents a series of innovative research initiatives from the MIT Media Lab’s Fluid Interfaces group that explore how artificial intelligence (AI) and wearable technologies can support healthy aging. Through participatory design workshops with older adults (ages 70–94), her team identified key areas of need, including memory support, communication assistance, health monitoring, and social connection. Prototypes such as MemPal, a wearable memory assistant using multimodal AI to track daily activities and locate lost objects, and a voice-based memory augmentation system were developed and tested in real-world settings. Additional systems include real-time speech simplification tools and AI-enhanced social agents designed to reduce loneliness by promoting and supporting human relationships.

Continue Reading2025 a2 National Symposium Keynote Speech: Pattie Maes, PhD– Opportunities for AI and Wearables to Support Healthy Aging

Patent Awarded: AI powered mobility assessment system (No. US 12,343,138 B2)

Abstract: To assess the mobility of a user, a mobility assessment system obtains a video of a user having a plurality of video frames from a camera. The mobility assessment system generates a three-dimensional (3D) skeleton model of the user based on the plurality of video frames, and determines a range of motion of the user based on a change in position of the 3D skeleton model over the plurality of video frames. Then the mobility assessment system provides an indication of the range of motion of the user for display. Also, the mobility assessment system delivers tailored exercises and suggestions to enhance user mobility and reduce the risk of falls. Source: US-12343138-B2

Continue ReadingPatent Awarded: AI powered mobility assessment system (No. US 12,343,138 B2)

Publication: Reinforcement Learning on Dyads to Enhance Medication Adherence

Authors: Ziping Xu, Hinal Jajal, Sung Won Choi, Inbal Nahum-Shani, Guy Shani, Alexandra M. Psihogios, Pei-Yao Hung, Susan A. Murphy Abstract Medication adherence is critical for the recovery of adolescents and young adults (AYAs) who have undergone hematopoietic cell transplantation. However, maintaining adherence is challenging for AYAs after hospital discharge, who experience both individual (e.g. physical and emotional symptoms) and interpersonal barriers (e.g., relational difficulties with their care partner, who is often involved in medication management). To optimize the effectiveness of a three-component digital intervention targeting both members of the dyad as well as their relationship, we propose a novel Multi-Agent Reinforcement Learning (MARL) approach to personalize the delivery of interventions. By incorporating the domain knowledge, the MARL framework, where each agent is responsible for the delivery of one intervention component, allows for faster learning…

Continue ReadingPublication: Reinforcement Learning on Dyads to Enhance Medication Adherence

Publication: Proceedings from SOUPS ’25 – Can You Walk Me Through It? Explainable SMS Phishing Detection using LLM-based Agents

Authors: Yizhu Wang, Haoyu Zhai, Chenkai Wang, Qingying Hao, Nick A Cohen, Roopa Foulger, Jonathan A Handler, and Gang Wang. Abstract SMS phishing poses a significant threat to users, especially older adults. Existing defenses mainly focus on phishing detection, but often cannot explain why the SMS is malicious to lay users. In this paper, we use large language models (LLMs) to detect SMS phishing while generating evidence-based explanations. The key challenge is that SMS is short, lacking the necessary context for security reasoning. We develop a prototype called SmishX which gathers external contexts (e.g., domain and brand information, URL redirection, and web screenshots) to augment the chain-of-thought (CoT) reasoning of LLMs. Then, the reasoning process is converted into a short explanation message to help users with their decision-making. Evaluation using real-world SMS datasets shows SmishX can achieve…

Continue ReadingPublication: Proceedings from SOUPS ’25 – Can You Walk Me Through It? Explainable SMS Phishing Detection using LLM-based Agents

Past Webinar – Technological Advancements in Functional Assessments and Fall Prevention, John Ralston and Hamed Tabkhi

https://www.youtube.com/watch?v=37KcJYSMRHE Overview: This webinar gives an overview of two of the MassAITC pilot projects.  John Ralston, from Neursantys describes their work on bioelectronic restoration of the body’s aging balance system.  In addition, Hamed Tabkhi of ForesightCares discusses their product, AVA, which is an AI-powered, video-based mobile app designed to enable clinically grounded fall risk assessments directly in the home. Abstracts: Wearable diagnostic sensors and personalized bioelectronic therapeutics for the treatment of neurophysiological conditions Bioelectronics has been an important component of modern medicine for more than half a century, because of the ability to provide functional recovery for conditions with limited pharmaceutical treatment options. Bioelectronic devices have now received regulatory approval for a growing range of medical conditions and have been shown to provide effective treatment for a growing range of neurological conditions.In this talk we will review the…

Continue ReadingPast Webinar – Technological Advancements in Functional Assessments and Fall Prevention, John Ralston and Hamed Tabkhi

Publication: Causal Directed Acyclic Graph-informed Reward Design

Authors: Luton Zou, Ziping Xu, Daiqi Gao, Susan Murphy Abstract It is well known that in reinforcement learning (RL) different reward functions may lead to the same optimal policy, while some reward functions can be substantially easier to learn. In this paper, we propose a framework for reward design by constructing surrogate rewards with mediators informed by causal directed acyclic graphs (DAGs), which are often available in real-world applications through domain knowledge. We show that under the surrogacy assumption, the proposed reward is unbiased and has lower variance than the primary reward. Specifically, we use an online reward design agent that adaptively learns the target surrogate reward in an unknown environment. Feeding the surrogate rewards to standard online learning oracles, we show that the regret bound can be improved. Our framework provides a theoretical improvement…

Continue ReadingPublication: Causal Directed Acyclic Graph-informed Reward Design