Wearable internet of things (IoT) devices can enable a variety of biomedical applications, such as gesture recognition, health monitoring, and human activity tracking. Size and weight constraints limit the battery capacity, which leads to frequent charging requirements and user dissatisfaction. Minimizing the energy consumption not only alleviates this problem, but also paves the way for self-powered devices that operate on harvested energy. This paper considers an energy-optimal gesture recognition application that runs on energy-harvesting devices. We first formulate an optimization problem for maximizing the number of recognized gestures when energy budget and accuracy constraints are given. Next, we derive an analytical energy model from the power consumption measurements using a wearable IoT device prototype. Then, we prove that maximizing the number of recognized gestures is equivalent to minimizing the duration of gesture recognition. Finally, we utilize this result to construct an optimization technique that maximizes the number of gestures recognized under the energy budget constraints while satisfying the recognition accuracy requirements. Our extensive evaluations demonstrate that the proposed analytical model is valid for wearable IoT applications, and the optimization approach increases the number of recognized gestures by up to 2.4× compared to a manual optimization.

Wearable Internet of Things (IoT) devices can be used efficiently for gesture recognition applications. The nature of these applications requires high recognition accuracy with low energy consumption, which is not easy to solve at the same time. In this paper, we design a finger gesture recognition system using a wearable IoT device. The proposed recognition system uses a light-weight multi-layer perceptron (MLP) classifier which can be implemented even on a low-end micro controller unit (MCU), with a 2-axes flex sensor. To achieve high recognition accuracy with low energy consumption, we first design a framework for the finger gesture recognition system including its components, followed by system-level performance and energy models. Then, we analyze system-level accuracy and energy optimization issues, and explore the numerous design choices to finally achieve energy–accuracy aware finger gesture recognition, targeting four commonly used low-end MCUs. Our extensive simulation and measurements using prototypes demonstrate that the proposed design achieves up to 95.5% recognition accuracy with energy consumption under 2.74 mJ per gesture on a low-end embedded wearable IoT device. We also provide the Pareto-optimal designs among a total of 159 design choices to achieve energy–accuracy aware design points under given energy or accuracy constraints.

Imbalanced distribution of workloads across a chip multiprocessor (CMP) constitutes wasteful use of resources. Most existing load distribution and balancing techniques employ very limited hardware support and rely predominantly on software for their operation. This paper introduces IsoNet, a hardware-based conflict-free dynamic load distribution and balancing engine. IsoNet is a lightweight job queue manager responsible for administering the list of jobs to be executed, and maintaining load balance among all CMP cores. By exploiting a micro-network of load-balancing modules, the proposed mechanism is shown to effectively reinforce concurrent computation in many-core environments. Detailed evaluation using a full-system simulation framework indicates that IsoNet significantly outperforms existing techniques and scales efficiently to as many as 1024 cores. Furthermore, to assess its feasibility, the IsoNet design is synthesized, placed, and routed in 45-nm VLSI technology. Analysis of the resulting low-level implementation shows that IsoNet's area and power overhead are almost negligible.

Wearable health and activity monitoring devices must minimize the battery charging and replacement requirements to be practical. Numerous design techniques, such as power gating and multiple voltage-frequency (VF) domains, can be used to optimize power consumption. However, circuit-level techniques alone cannot minimize energy consumption unless they exploit domain-specific knowledge. To this end, we propose a system-level framework that minimizes the energy consumption of wearable health and activity monitoring applications by combining domain-specific knowledge with low-power design techniques. The proposed technique finds the energy-optimal VF domain partitioning and the corresponding VF assignments to each partition. We evaluate this framework with experiments on two activity monitoring and one electrocardiogram applications. Our approach decreases the energy consumption by 33–58% when compared to baseline designs. It also achieves 20–46% more savings compared to a state-of-the-art approach.