Diet plays a crucial role in preventing chronic diseases such as type 2 diabetes and heart disease. Most existing diet monitoring systems require manual input or raise privacy concerns by continuously recording video data that often captures the user's face or the surrounding environment. In this paper, we present a chest-mounted wearable device that preserves user privacy while passively tracking dietary intake using a Time-of-Flight (ToF) sensor. Captured RGB images are masked using ToF depth data to isolate food items and eliminate background elements. A FOMO-based food detection model achieved an F1 score of 96% and a mean Average Precision (mAP) of 74% on masked images, outperforming its performance on unmasked RGB inputs. Also, ToF depth frames were used to build an eating gesture recognition model that achieved 88% accuracy, indicating reliable identification of eating gestures. All models and image processing steps were executed on-device, demonstrating the feasibility of the system. This work presents a novel approach for real-time dietary monitoring that addresses both user privacy and food detection accuracy in a wearable health system.

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.

Skin cancer, particularly melanoma, is a major health concern due to rising incidence rates, largely driven by ultraviolet (UV) radiation overexposure, making it essential to monitor and manage sun exposure effectively. While existing wearable UV sensors track exposure, they often rely on external power sources, limiting their battery lifetime. This study presents a self-sustaining wearable UV sensor that integrates solar energy harvesting, enabling continuous monitoring without need for frequent recharging. The device uses low-power components to measure UVA and UVB radiation with high accuracy. It is powered by a solar panel made from Ethylene Tetrafluoroethylene (ETFE), which provides continuous energy to recharge a LiPo battery. It transmits data via BLE for real-time feedback and can be used for personalized sun protection recommendations. A usability study with 10 participants demonstrated the sensor's effectiveness in raising UV awareness and encouraging sun protection habits.

Researchers have been leveraging wearable cameras to both visually confirm and automatically detect individuals' eating habits. However, energy-intensive tasks such as continuously collecting and storing RGB images in memory, or running algorithms in real-time to automate detection of eating, greatly impacts battery life. Since eating moments are spread sparsely throughout the day, battery life can be mitigated by recording and processing data only when there is a high likelihood of eating. We present a framework comprising a golf-ball sized wearable device using a low-powered thermal sensor array and real-time activation algorithm that activates high-energy tasks when a hand-to-mouth gesture is confirmed by the thermal sensor array. The high-energy tasks tested are turning on the RGB camera (Trigger RGB mode) and running inference on an on-device machine learning model (Trigger ML mode). Our experimental setup involved the design of a wearable camera, 6 participants collecting 18 hours of data with and without eating, the implementation of a feeding gesture detection algorithm on-device, and measures of power saving using our activation method. Our activation algorithm demonstrates an average of at-least 31.5% increase in battery life time, with minimal drop of recall (5%) and without impacting the accuracy of detecting eating (a slight 4.1% increase in F1-Score).

Differential evolution (DE) is an effective population-based metaheuristic algorithm for solving complex optimisation problems. However, the performance of DE is sensitive to the mutation operator. In this paper, we propose a novel DE algorithm, Clu-DE, that improves the efficacy of DE using a novel clustering-based mutation operator. First, we find, using a clustering algorithm, a winner cluster in search space and select the best candidate solution in this cluster as the base vector in the mutation operator. Then, an updating scheme is introduced to include new candidate solutions in the current population. Experimental results on CEC-2017 benchmark functions with dimensionalities of 30, 50 and 100 confirm that Clu-DE yields improved performance compared to DE.

Wearables are poised to transform health and wellness through automation of cost-effective, objective, and real-time health monitoring. However, machine learning models for these systems are designed based on labeled data collected, and feature representations engineered, in controlled environments. This approach has limited scalability of wearables because (i) collecting and labeling sufficiently large amounts of sensor data is a labor-intensive and expensive process; and (ii) wearables are deployed in highly dynamic environments of the end-users whose context undergoes consistent changes. We introduce TransNet , a deep learning framework that minimizes the costly process of data labeling, feature engineering, and algorithm retraining by constructing a scalable computational approach. TransNet learns general and reusable features in lower layers of the framework and quickly reconfigures the underlying models from a small number of labeled instances in a new domain, such as when the system is adopted by a new user or when a previously unseen event is to be added to event vocabulary of the system. Utilizing TransNet on four activity datasets, TransNet achieves an average accuracy of 88.1% in cross-subject learning scenarios using only one labeled instance for each activity class. This performance improves to an accuracy of 92.7% with five labeled instances.

Advances in embedded systems have enabled integration of many lightweight sensory devices within our daily life. In particular, this trend has given rise to continuous expansion of wearable sensors in a broad range of applications from health and fitness monitoring to social networking and military surveillance. Wearables leverage machine learning techniques to profile behavioral routine of their end-users through activity recognition algorithms. Current research assumes that such machine learning algorithms are trained offline. In reality, however, wearables demand continuous reconfiguration of their computational algorithms due to their highly dynamic operation. Developing a personalized and adaptive machine learning model requires real-time reconfiguration of the model. Due to stringent computation and memory constraints of these embedded sensors, the training/re-training of the computational algorithms need to be memory- and computation-efficient. In this paper, we propose a framework, based on the notion of online learning, for real-time and on-device machine learning training. We propose to transform the activity recognition problem from a multi-class classification problem to a hierarchical model of binary decisions using cascading online binary classifiers. Our results, based on Pegasos online learning, demonstrate that the proposed approach achieves 97% accuracy in detecting activities of varying intensities using a limited memory while power usages of the system is reduced by more than 40%.

We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the probability distribution of output classes occurrences. Also, we propose a memory optimization technique based on SVM parameters, which results in storing fewer support vectors and as a result requiring less memory. To demonstrate the efficiency of our proposed techniques, we performed an activity recognition experiment and were able to save up to 35% and 56% in memory storage when classifying 14 and 6 different activities, respectively. In addition, we demonstrated that there is a trade-off between accuracy of classification and memory savings, which can be controlled based on application requirements.

Activity recognition, as an important component of behavioral monitoring and intervention, has attracted enormous attention, especially in Mobile Cloud Computing (MCC) and Remote Health Monitoring (RHM) paradigms. While recently resource constrained wearable devices have been gaining popularity, their battery life is limited and constrained by the frequent wireless transmission of data to more computationally powerful back-ends. This paper proposes an ultra-low power activity recognition system using a novel adaptive compressed sensing technique that aims to minimize transmission costs. Coarse-grained on-body sensor localization and unsupervised clustering modules are devised to autonomously reconfigure the compressed sensing module for further power saving. We perform a thorough heuristic optimization using Grammatical Evolution (GE) to ensure minimal computation overhead of the proposed methodology. Our evaluation on a real-world dataset and a low power wearable sensing node demonstrates that our approach can reduce the energy consumption of the wireless data transmission up to 81.2 and 61.5 percent, with up to 60.6 and 35.0 percent overall power savings in comparison with baseline and a naive state-of-the-art approaches, respectively. These solutions lead to an average activity recognition accuracy of 89.0 percent-only 4.8 percent less than the baseline accuracy-while having a negligible energy overhead of on-node computation.

We present a novel approach for monitoring beverage intake. Our system is composed of an ultrasonic sensor, an RGB color sensor, and machine learning algorithms. The system not only measures beverage volume but also detects beverage types. The sensor unit is lightweight that can be mounted on the lid of any drinking bottle. Our experimental results demonstrate that the proposed approach achieves more than 97% accuracy in beverage type classification. Furthermore, our regression-based volume measurement has a nominal error of 3%.