Search for: All records

Sparse deep neural networks (DNNs) have the potential to deliver compelling performance and energy efficiency without significant accuracy loss. However, their benefits can quickly diminish if their training is oblivious to the target hardware. For example, fewer critical connections can have a significant overhead if they translate into long-distance communication on the target hardware. Therefore, hardware-aware sparse training is needed to leverage the full potential of sparse DNNs. To this end, we propose a novel and comprehensive communication-aware sparse DNN optimization framework for tile-based in-memory computing (IMC) architectures. The proposed technique, CANNON first maps the DNN layers onto the tiles of the target architecture. Then, it replaces the fully connected and convolutional layers with communication-aware sparse connections. After that, CANNON optimizes the communication cost with minimal impact on the DNN accuracy. Extensive experimental evaluations with a wide range of DNNs and datasets show up to 3.0× lower communication energy, 3.1× lower communication latency, and 6.8× lower energy-delay product compared to state-of-the-art pruning approaches with a negligible impact on the classification accuracy on IMC-based machine learning accelerators. 

Millimeter-Wave (mmWave) radar can enable high-resolution human pose estimation with low cost and computational requirements. However, mmWave data point cloud, the primary input to processing algorithms, is highly sparse and carries significantly less information than other alternatives such as video frames. Furthermore, the scarce labeled mmWave data impedes the development of machine learning (ML) models that can generalize to unseen scenarios. We propose a fast and scalable human pose estimation (FUSE) framework that combines multi-frame representation and meta-learning to address these challenges. Experimental evaluations show that FUSE adapts to the unseen scenarios 4× faster than current supervised learning approaches and estimates human joint coordinates with about 7 cm mean absolute error. 

Parkinson’s disease (PD) is a neurological disorder with complicated and disabling motor and non-motor symptoms. The complexity of PD pathology is amplified due to its dependency on patient diaries and the neurologist’s subjective assessment of clinical scales. A significant amount of recent research has explored new cost-effective and subjective assessment methods pertaining to PD symptoms to address this challenge. This article analyzes the application areas and use of mobile and wearable technology in PD research using the PRISMA methodology. Based on the published papers, we identify four significant fields of research: diagnosis, prognosis and monitoring, predicting response to treatment, and rehabilitation. Between January 2008 and December 2021, 31,718 articles were published in four databases: PubMed Central, Science Direct, IEEE Xplore, and MDPI. After removing unrelated articles, duplicate entries, non-English publications, and other articles that did not fulfill the selection criteria, we manually investigated 1559 articles in this review. Most of the articles (45%) were published during a recent four-year stretch (2018–2021), and 19% of the articles were published in 2021 alone. This trend reflects the research community’s growing interest in assessing PD with wearable devices, particularly in the last four years of the period under study. We conclude that there is a substantial and steady growth in the use of mobile technology in the PD contexts. We share our automated script and the detailed results with the public, making the review reproducible for future publications. 

Advances in low-power electronics and machine learning techniques lead to many novel wearable IoT devices. These devices have limited battery capacity and computational power. Thus, energy harvesting from ambient sources is a promising solution to power these low-energy wearable devices. They need to manage the harvested energy optimally to achieve energy-neutral operation, which eliminates recharging requirements. Optimal energy management is a challenging task due to the dynamic nature of the harvested energy and the battery energy constraints of the target device. To address this challenge, we present a reinforcement learning-based energy management framework, tinyMAN, for resource-constrained wearable IoT devices. The framework maximizes the utilization of the target device under dynamic energy harvesting patterns and battery constraints. Moreover, tinyMAN does not rely on forecasts of the harvested energy which makes it a prediction-free approach. We deployed tinyMAN on a wearable device prototype using TensorFlow Lite for Micro thanks to its small memory footprint of less than 100 KB. Our evaluations show that tinyMAN achieves less than 2.36 ms and 27.75 μJ while maintaining up to 45% higher utility compared to prior approaches. 

Rehabilitation is a crucial process for patients suffering from motor disorders. The current practice is performing rehabilitation exercises under clinical expert supervision. New approaches are needed to allow patients to perform prescribed exercises at their homes and alleviate commuting requirements, expert shortages, and healthcare costs. Human joint estimation is a substantial component of these programs since it offers valuable visualization and feedback based on body movements. Camera-based systems have been popular for capturing joint motion. However, they have high-cost, raise serious privacy concerns, and require strict lighting and placement settings. We propose a millimeter-wave (mmWave)-based assistive rehabilitation system (MARS) for motor disorders to address these challenges. MARS provides a low-cost solution with a competitive object localization and detection accuracy. It first maps the 5D time-series point cloud from mmWave to a lower dimension. Then, it uses a convolution neural network (CNN) to estimate the accurate location of human joints. MARS can reconstruct 19 human joints and their skeleton from the point cloud generated by mmWave radar. We evaluate MARS using ten specific rehabilitation movements performed by four human subjects involving all body parts and obtain an average mean absolute error of 5.87 cm for all joint positions. To the best of our knowledge, this is the first rehabilitation movements dataset using mmWave point cloud. MARS is evaluated on the Nvidia Jetson Xavier-NX board. Model inference takes only 64 s and consumes 442 J energy. These results demonstrate the practicality of MARS on low-power edge devices. 

Movement disorders, such as Parkinson’s disease, affect more than 10 million people worldwide. Gait analysis is a critical step in the diagnosis and rehabilitation of these disorders. Specifically, step and stride lengths provide valuable insights into the gait quality and rehabilitation process. However, traditional approaches for estimating step length are not suitable for continuous daily monitoring since they rely on special mats and clinical environments. To address this limitation, this article presents a novel and practical step-length estimation technique using low-power wearable bend and inertial sensors. Experimental results show that the proposed model estimates step length with 5.49% mean absolute percentage error and provides accurate real-time feedback to the user. 

Freezing of gait (FoG), which implies a brief absence or reduction of ability to walk, is one of the most common symptoms of Parkinson's Disease (PD). Predicting FoG episodes in time can prevent their onset by providing specific cues to the patients. This paper presents a deep learning approach to predict FoG episodes using a Long Short-Term Memory network (LSTM). It also identifies key issues and concepts which have not been dwelled upon before in the existing literature, paving the way to a more systematic methodology for future work. We evaluate our approach using a publicly available dataset that includes accelerometer readings from 10 PD patients. We achieve up to 89% prediction accuracy with an average prediction time of 1.42 s using a subject-independent model. 

Neural architecture search (NAS) is a promising technique to design efficient and high-performance deep neural networks (DNNs). As the performance requirements of ML applications grow continuously, the hardware accelerators start playing a central role in DNN design. This trend makes NAS even more complicated and time-consuming for most real applications. This paper proposes FLASH, a very fast NAS methodology that co-optimizes the DNN accuracy and performance on a real hardware platform. As the main theoretical contribution, we first propose the NN-Degree, an analytical metric to quantify the topological characteristics of DNNs with skip connections (e.g., DenseNets, ResNets, Wide-ResNets, and MobileNets). The newly proposed NN-Degree allows us to do training-free NAS within one second and build an accuracy predictor by training as few as 25 samples out of a vast search space with more than 63 billion configurations. Second, by performing inference on the target hardware, we fine-tune and validate our analytical models to estimate the latency, area, and energy consumption of various DNN architectures while executing standard ML datasets. Third, we construct a hierarchical algorithm based on simplicial homology global optimization (SHGO) to optimize the model-architecture co-design process, while considering the area, latency, and energy consumption of the target hardware. We demonstrate that, compared to the state-of-the-art NAS approaches, our proposed hierarchical SHGO-based algorithm enables more than four orders of magnitude speedup (specifically, the execution time of the proposed algorithm is about 0.1 seconds). Finally, our experimental evaluations show that FLASH is easily transferable to different hardware architectures, thus enabling us to do NAS on a Raspberry Pi-3B processor in less than 3 seconds. 

Hyperdimensional computing (HDC) has emerged as a new light-weight learning algorithm with smaller computation and energy requirements compared to conventional techniques. In HDC, data points are represented by high dimensional vectors (hypervectors), which are mapped to high dimensional space (hyperspace). Typically, a large hypervector dimension (≥1000) is required to achieve accuracies comparable to conventional alternatives. However, unnecessarily large hypervectors increase hardware and energy costs, which can undermine their benefits. This paper presents a technique to minimize the hypervector dimension while maintaining the accuracy and improving the robustness of the classifier. To this end, we formulate hypervector design as a multi-objective optimization problem for the first time in the literature. The proposed approach decreases the hypervector dimension by more than 128× while maintaining or increasing the accuracy achieved by conventional HDC. Experiments on a commercial hardware platform show that the proposed approach achieves more than two orders of magnitude reduction in model size, inference time, and energy consumption. We also demonstrate the trade-off between accuracy and robustness to noise and provide Pareto front solutions as a design parameter in our hypervector design.