Overeating is a key contributor to obesity, yet identifying and characterizing its underlying causes remains challenging. While prior research has leveraged Ecological Momentary Assessment (EMA) to capture psychological and contextual factors in real-time, few studies have integrated EMA with passive sensing to uncover fine-grained, individualized consumption behaviors. In this work, we present a multimodal framework combining psychological and contextual data from a custom-built EMA app with validated camera-derived meal microstructure features from a neck-worn activity-oriented wearable camera. Across 41 participants, the camera captured 6,343 hours of footage over 312 days, yielding annotated bites, chews, meal start/end times, and dietitian-confirmed caloric intake. Using supervised contrastive learning, we generated meal-level representations, projected them using UMAP, and applied k-means clustering to identify behavioral phenotypes. We then conducted a z-score analysis to highlight features most distinctive to each cluster. Among the eight discovered groups, three consistently showed high purity for overeating meals (average purity$=0.99$), revealing nuanced, data-driven overeating phenotypes that may inform targeted intervention strategies.

The future Internet of Things (IoT) will enable Internet connectivity for a vast amount of battery-powered devices, which usually need to communicate with each other or to some remote gateways through multihop communications. Although ZigBee has become a widely used communication technology in IoT, Wi-Fi, on the other hand, has its unique advantages such as high throughput and native IP compatibility, despite its potentially higher energy consumption. With the development of IoT, more and more IoT devices are equipped with multiple radio interfaces, such as both Wi-Fi and ZigBee. Inspired by this, we propose a dual-interface dual-pipeline scheduling (DIPS) scheme, which leverages an activation pipeline mainly constructed by low-power ZigBee interfaces to wake up a data pipeline constructed by high-power Wi-Fi interfaces on demand, toward enabling multihop data delivery in IoT. The objective is to minimize network energy consumption while satisfying certain end-to-end delay requirements. Extensive simulations and prototype-based experiments have been conducted. The results show that the energy consumption of DIPS is 96.5% and 92.8% lower than that of the IEEE 802.11's standard power saving scheme and a state-of-the-art pipeline-based scheme in moderate traffic scenarios, respectively.

As the healthcare industry becomes more reliant upon electronic records, the amount of medical data available for analysis increases exponentially. While this information contains valuable statistics, the sheer volume makes it difficult to analyze without efficient algorithms. By using machine learning to classify medical data, diagnoses can become more efficient, accurate, and accessible for the public. After choosing k-Nearest Neighbors for its simplicity, we applied it to datasets compiled by the University of California, Irvine Machine Learning Repository to diagnose two conditions - chronic kidney failure and heart disease - with an accuracy of approximately 90%. In the future, similar methods can be used on a larger scale to bring ease of use to the field of medical diagnostics.