Blood pressure (BP) is one of the most influential bio-markers for cardiovascular diseases and stroke; therefore, it needs to be regularly monitored to diagnose and prevent any advent of medical complications. Current cuffless approaches to continuous BP monitoring, though non-invasive and unobtrusive, involve explicit feature engineering surrounding fingertip Photoplethysmogram (PPG) signals. To circumvent this, we present an end-to-end deep learning solution, BP-Net, that uses PPG waveform to estimate Systolic BP (SBP), Mean Average Pressure (MAP), and Diastolic BP (DBP) through intermediate continuous Arterial BP (ABP) waveform. Under the terms of the British Hypertension Society (BHS) standard, BP-Net achieves Grade A for DBP and MAP estimation and Grade B for SBP estimation. BP-Net also satisfies Advancement of Medical Instrumentation (AAMI) criteria for DBP and MAP estimation and achieves Mean Absolute Error (MAE) of 5.16 mmHg and 2.89 mmHg for SBP and DBP, respectively. Further, we establish the ubiquitous potential of our approach by deploying BP-Net on a Raspberry Pi 4 device and achieve 4.25 ms inference time for our model to translate the PPG waveform to ABP waveform.
Monitoring behaviour in smart homes using sensors can offer insights into changes in the independent ability and long-term health of residents. Passive Infrared motion sensors (PIRs) are standard, however may not accurately track the full duration of movement. They also require line-of-sight to detect motion which can restrict performance and ensures they must be visible to residents. Channel State Information (CSI) is a low cost, unintrusive form of radio sensing which can monitor movement but also offers opportunities to generate rich data. We have developed a novel, self-calibrating motion detection system which uses CSI data collected and processed on a stock Raspberry Pi 4. This system exploits the correlation between CSI frames, on which we perform variance analysis using our algorithm to accurately measure the full period of a resident's movement. We demonstrate the effectiveness of this approach in several real-world environments. Experiments conducted demonstrate that activity start and end time can be accurately detected for motion examples of different intensities at different locations.
The deployment of artificial neural networks-based optical channel equalizers on edge-computing devices is critically important for the next generation of optical communication systems. However, this is still a highly challenging problem, mainly due to the computational complexity of the artificial neural networks (NNs) required for the efficient equalization of nonlinear optical channels with large dispersion-induced memory. To implement the NN-based optical channel equalizer in hardware, a substantial complexity reduction is needed, while we have to keep an acceptable performance level of the simplified NN model. In this work, we address the complexity reduction problem by applying pruning and quantization techniques to an NN-based optical channel equalizer. We use an exemplary NN architecture, the multi-layer perceptron (MLP), to mitigate the impairments for 30GBd 1000km transmission over a standard single-mode fiber, and demonstrate that it is feasible to reduce the equalizer's memory by up to 87.12%, and its complexity by up to 78.34%, without noticeable performance degradation. In addition to this, we accurately define the computational complexity of a compressed NN-based equalizer in the digital signal processing (DSP) sense. Further, we examine the impact of using different CPU and GPU settings on the power consumption and latency for the compressed equalizer. We also verify the developed technique experimentally, by implementing the reduced NN equalizer on two standard edge-computing hardware units: Raspberry Pi 4 and Nvidia Jetson Nano, which are used to process the data generated via simulating the signal's propagation down the optical-fiber system.
We present Tesla-Rapture, a gesture recognition interface for point clouds generated by mmWave Radars. State of the art gesture recognition models are either too resource consuming or not sufficiently accurate for integration into real-life scenarios using wearable or constrained equipment such as IoT devices (e.g. Raspberry PI), XR hardware (e.g. HoloLens), or smart-phones. To tackle this issue, we developed Tesla, a Message Passing Neural Network (MPNN) graph convolution approach for mmWave radar point clouds. The model outperforms the state of the art on two datasets in terms of accuracy while reducing the computational complexity and, hence, the execution time. In particular, the approach, is able to predict a gesture almost 8 times faster than the most accurate competitor. Our performance evaluation in different scenarios (environments, angles, distances) shows that Tesla generalizes well and improves the accuracy up to 20% in challenging scenarios like a through-wall setting and sensing at extreme angles. Utilizing Tesla, we develop Tesla-Rapture, a real-time implementation using a mmWave Radar on a Raspberry PI 4 and evaluate its accuracy and time-complexity. We also publish the source code, the trained models, and the implementation of the model for embedded devices.
EdgeAI (Edge computing based Artificial Intelligence) has been most actively researched for the last few years to handle variety of massively distributed AI applications to meet up the strict latency requirements. Meanwhile, many companies have released edge devices with smaller form factors (low power consumption and limited resources) like the popular Raspberry Pi and Nvidia's Jetson Nano for acting as compute nodes at the edge computing environments. Although the edge devices are limited in terms of computing power and hardware resources, they are powered by accelerators to enhance their performance behavior. Therefore, it is interesting to see how AI-based Deep Neural Networks perform on such devices with limited resources. In this work, we present and compare the performance in terms of inference time and power consumption of the four Systems on a Chip (SoCs): Asus Tinker Edge R, Raspberry Pi 4, Google Coral Dev Board, Nvidia Jetson Nano, and one microcontroller: Arduino Nano 33 BLE, on different deep learning models and frameworks. We also provide a method for measuring power consumption, inference time and accuracy for the devices, which can be easily extended to other devices. Our results showcase that, for Tensorflow based quantized model, the Google Coral Dev Board delivers the best performance, both for inference time and power consumption. For a low fraction of inference computation time, i.e. less than 29.3% of the time for MobileNetV2, the Jetson Nano performs faster than the other devices.
Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper.
Voice controlled devices and services have become very popular in the consumer IoT. Cloud-based speech analysis services extract information from voice inputs using speech recognition techniques. Services providers can thus build very accurate profiles of users' demographic categories, personal preferences, emotional states, etc., and may therefore significantly compromise their privacy. To address this problem, we have developed a privacy-preserving intermediate layer between users and cloud services to sanitize voice input directly at edge devices. We use CycleGAN-based speech conversion to remove sensitive information from raw voice input signals before regenerating neutralized signals for forwarding. We implement and evaluate our emotion filtering approach using a relatively cheap Raspberry Pi 4, and show that performance accuracy is not compromised at the edge. In fact, signals generated at the edge differ only slightly (~0.16%) from cloud-based approaches for speech recognition. Experimental evaluation of generated signals show that identification of the emotional state of a speaker can be reduced by ~91%.
Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search. We first construct a large design space with $\textit{arbitrary encoder-decoder attention}$ and $\textit{heterogeneous layers}$. Then we train a $\textit{SuperTransformer}$ that covers all candidates in the design space, and efficiently produces many $\textit{SubTransformers}$ with weight sharing. Finally, we perform an evolutionary search with a hardware latency constraint to find a specialized $\textit{SubTransformer}$ dedicated to run fast on the target hardware. Extensive experiments on four machine translation tasks demonstrate that HAT can discover efficient models for different hardware (CPU, GPU, IoT device). When running WMT'14 translation task on Raspberry Pi-4, HAT can achieve $\textbf{3}\times$ speedup, $\textbf{3.7}\times$ smaller size over baseline Transformer; $\textbf{2.7}\times$ speedup, $\textbf{3.6}\times$ smaller size over Evolved Transformer with $\textbf{12,041}\times$ less search cost and no performance loss. HAT code is https://github.com/mit-han-lab/hardware-aware-transformers.git