I will shamelessly tell you what my bottom line is. It is placing balls into boxes... Gian-Carlo Rota - "Indiscrete Thoughts"

Human Data Sensing and Analysis

  1. Marco Canil, Jacopo Pegoraro, Michele Rossi, milliTRACE-IR: Contact Tracing and Temperature Screening via mmWave and Infrared Sensing, IEEE Journal of Selected Topics in Signal Processing, accepted for publication, 2022.
    Social distancing and temperature screening have been widely employed to counteract the COVID-19 pandemic, sparking great interest from academia, industry and public administrations worldwide. While most solutions have dealt with these aspects separately, their combination would greatly benefit the continuous monitoring of public spaces and help trigger effective countermeasures. This work presents milliTRACE-IR, a joint mmWave radar and infrared imaging sensing system performing unobtrusive and privacy preserving human body temperature screening and contact tracing in indoor spaces. milliTRACE-IR combines, via a robust sensor fusion approach, mmWave radars and infrared thermal cameras. It achieves fully automated measurement of distancing and body temperature, by jointly tracking the subjects's faces in the thermal camera image plane and the human motion in the radar reference system. Moreover, milliTRACE-IR performs contact tracing: a person with high body temperature is reliably detected by the thermal camera sensor and subsequently traced across a large indoor area in a non-invasive way by the radars. When entering a new room, a subject is re-identified among several other individuals by computing gait-related features from the radar reflections through a deep neural network and using a weighted extreme learning machine as the final re-identification tool. Experimental results, obtained from a real implementation of milliTRACE-IR, demonstrate decimeter-level accuracy in distance/trajectory estimation, inter-personal distance estimation (effective for subjects getting as close as 0.2 m), and accurate temperature monitoring (max. errors of 0.5 C). Furthermore, milliTRACE-IR provides contact tracing through highly accurate (95%) person re-identification, in less than 20 seconds.

  2. J. Pegoraro, J. O. Lacruz, M. Rossi, J. Widmer, SPARCS: A Sparse Recovery Approach for Integrated Communication and Human Sensing in mmWave Systems, ACM Information Processing in Sensor Networks (IPSN), Milan, Italy, May 4-6, 2022.

  3. A. Shastri, M. Canil, J. Pegoraro, P. Casari, M. Rossi, mmSCALE: Self-Calibration of mmWave Radar Networks from Human Movement Trajectories, IEEE Radar Conference (RadarConf), March 21-25, New York City, USA, 2022.

  4. Jacopo Pegoraro, Michele Rossi, Real-time People Tracking and Identification from Sparse mm-Wave Radar Point-clouds. IEEE Access, Vol. 9, May 2021.
    Mm-wave radars have recently gathered significant attention as a means to track human movement and identify subjects from their gait characteristics. A widely adopted method to perform the identification is the extraction of the micro-Doppler signature of the targets, which is computationally demanding in case of co-existing multiple targets within the monitored physical space. Such computational complexity is the main problem of state-of-the-art approaches, and makes them inapt for real-time use. In this work, we present an end-to-end, low-complexity but highly accurate method to track and identify multiple subjects in real-time using the sparse point-cloud sequences obtained from a low-cost mm-wave radar. Our proposed system features an extended object tracking Kalman filter, used to estimate the position, shape and extension of the subjects, which is integrated with a novel deep learning classifier, specifically tailored for effective feature extraction and fast inference on radar point-clouds. The proposed method is thoroughly evaluated on an edge-computing platform from NVIDIA (Jetson series), obtaining greatly reduced execution times (reduced complexity) against the best approaches from the literature. Specifically, it achieves identification accuracies as high as 96.76%, operating at 15 frames per seconds, with three subjects freely moving in an unseen indoor environment.

  5. Jacopo Pegoraro, Francesca Meneghello and Michele Rossi, Multi-Person Continuous Tracking and Identification from mm-Wave micro-Doppler Signatures. IEEE Transactions on Geoscience and Remote Sensing. Vol. 59, No. 4, April 2021.
    In this work, we investigate the use of backscattered mm-wave radio signals for the joint tracking and recognition of identities of humans as they move within indoor environments. We build a system that effectively works with multiple persons concurrently sharing and freely moving within the same indoor space. This leads to a complicated setting, which requires one to deal with the randomness and complexity of the resulting (composite) backscattered signal. The proposed system combines several processing steps: at first, the signal is filtered to remove artifacts, reflections and random noise that do not originate from humans. Hence, a density-based classification algorithm is executed to separate the Doppler signatures of different users. The final blocks are trajectory tracking and user identification, respectively based on Kalman filters and deep neural networks. Our results demonstrate that the integration of the last-mentioned processing stages is critical towards achieving robustness and accuracy in multi-user settings. Our technique is tested both on a single-target public dataset, for which it outperforms state-of-the-art methods, and on our own measurements, obtained with a 77GHz radar on multiple subjects simultaneously moving in two different indoor environments. The system works in an online fashion, permitting the continuous identification of multiple subjects with accuracies up to 98%, e.g., with four subjects sharing the same physical space, and with a small accuracy reduction when tested with unseen data from a challenging real-life scenario that was not part of the model learning phase.

  6. J. Pegoraro, D. Solimini, F. Matteo, E. Bashirov, F. Meneghello, M. Rossi, Deep Learning for Accurate Indoor Human Tracking with a mm-Wave Radar, IEEE Radar Conference (RadarConf), Florence, Italy, 21-25 September, 2020.

  7. Matteo Gadaleta, Michele Rossi, Eric J. Topol, Steven R. Steinhubl, Giorgio Quer, On the Effectiveness of Deep Representation Learning: the Atrial Fibrillation Case, IEEE Computer, Vol. 52, No. 11, pp. 18-29, November 2019.
    The automatic and unsupervised analysis of biomedical time series is of primary importance for diagnostic and preventive medicine, enabling fast and reliable data processing to reveal clinical insights without the need for human intervention. Representation learning (RL) methods perform an automatic extraction of meaningful features that can be used, e.g., for a subsequent classification of the measured data. The goal of this study is to explore and quantify the benefits of RL techniques of varying degrees of complexity, focusing on modern deep learning (DL) architectures. We focus on the automatic classification of atrial fibrillation (AF) events from noisy single-lead electrocardiographic signals (ECG) obtained from wireless sensors. This is an important task as it allows the detection of sub-clinical AF which is hard to diagnose with a short in-clinic 12-lead ECG. The effectiveness of the considered DL architectures for the AF detection task is quantified and discussed in terms of classification performance, memory/data efficiency and computational complexity.

  8. Matteo Gadaleta, Giulia Cisotto, Michele Rossi, Rana Zia Ur Rehman, Lynn Rochester, Silvia Del Din, Deep Learning Techniques for Improving Digital Gait Segmentation, Engineering in Medicine and Biology Conference, Berlin, Germany, 23-27 July, 2019.

  9. Matteo Gadaleta, Enrico Grisan, Andrea Facchinetti, Michele Rossi, Prediction of Adverse Glycemic Events from Continuous Glucose Monitoring Signal, IEEE Journal of Biomedical and Health Informatics, Vol. 23, No. 2, pp. 650-659, March 2019.
    The most important objective of any diabetes therapy is to maintain the blood glucose concentration within the euglycemic range, avoiding or at least mitigating critical hypo/hyperglycemic episodes. Modern Continuous Glucose Monitoring (CGM) devices bear the promise of providing the patients with an increased and timely awareness of glycemic conditions as these get dangerously near to hypo/hyperglycemia. The challenge is to detect, with reasonable advance, the patterns leading to risky situations, allowing the patient to make therapeutic decisions on the basis of future (predicted) glucose concentration levels. We underline that a technically sound performance comparison of the approaches that have been proposed in recent years is still missing, and is thus unclear which one is to be preferred. The aim of this study is to fill this gap, by carrying out a comparative analysis among the most common methods for glucose event prediction. Both regression and classification algorithms have been implemented and analyzed, including static and dynamic training approaches. The dataset consists of 89 CGM time series measured in diabetic subjects for 7 subsequent days. Performance metrics, specifically defined to assess and compare the event prediction capabilities of the methods, have been introduced and analyzed. Our numerical results show that a static training approach exhibits better performance, in particular when regression methods are considered. However, classifiers show some improvement when trained for a specific event category, such as hyperglycemia, achieving performance comparable to the regressors, with the advantage of predicting the events sooner.

  10. Matteo Gadaleta, Michele Rossi, IDNet: Smartphone-based Gait Recognition with Convolutional Neural Networks. Elsevier Pattern Recognition, Volume 74, Pages 25–37, February 2018. [arXiv:1606.03238v2]
    Here, we present IDNet, a user authentication framework from smartphone-acquired motion signals. Its goal is to recognize a target user from their way of walking, using the accelerometer and gyroscope (inertial) signals provided by a commercial smartphone worn in the front pocket of the user’s trousers. IDNet features several innovations including: i) a robust and smartphone-orientation-independent walking cycle extrac- tion block, ii) a novel feature extractor based on convolutional neural networks, iii) a one-class support vector machine to classify walking cycles, and the coherent integra- tion of these into iv) a multi-stage authentication technique. IDNet is the first system that exploits a deep learning approach as universal feature extractors for gait recog- nition, and that combines classification results from subsequent walking cycles into a multi-stage decision making framework. Experimental results show the superiority of our approach against state-of-the-art techniques, leading to misclassification rates (either false negatives or positives) smaller than 0.15% with fewer than five walking cycles. Design choices are discussed and motivated throughout, assessing their impact on the user authentication performance.

  11. Mohsen Hooshmand, Davide Zordan, Davide Del Testa, Enrico Grisan, Michele Rossi, Boosting the Battery Life of Wearables for Health Monitoring through the Compression of Biosignals. IEEE IoT Journal, Vol. 4, No. 5, pp. 1647-1662, October 2017.
    Modern wearable IoT devices enable the monitoring of vital parameters such as heart or respiratory rates (RESP), electrocardiography (ECG), photo-plethysmographic (PPG) signals within e-health applications. A common issue of wearable technology is that signal transmission is power-demanding and, as such, devices require frequent battery charges and this poses serious limitations to the continuous monitoring of vitals. To ameliorate this, we advocate the use of lossy signal compression as a means to decrease the data size of the gathered biosignals and, in turn, boost the battery life of wearables and allow for fine-grained and long-term monitoring. Considering one dimensional biosignals such as ECG, RESP and PPG, which are often available from commercial wearable IoT devices, we provide a thorough review of existing biosignal compression algorithms. Besides, we present novel approaches based on online dictionaries, elucidating their operating principles and providing a quantitative assessment of compression, reconstruction and energy consumption performance of all schemes. As we quantify, the most efficient schemes allow reductions in the signal size of up to 100 times, which entail similar reductions in the energy demand, by still keeping the reconstruction error within 4% of the peak-to-peak signal amplitude. Finally, avenues for future research are discussed.

  12. Mohsen Hooshmand, Davide Zordan, Tommaso Melodia, Michele Rossi, SURF: subject-adaptive unsupervised ECG signal compression for wearable fitness monitors. IEEE Access, Vol. 5, pp. 19517 - 19535, 7 September 2017.
    Recent advances in wearable devices allow non-invasive and inexpensive collection of biomedical signals including electrocardiogram (ECG), blood pressure, respiration, among others. Collection and processing of various biomarkers is expected to facilitate preventive healthcare through personalized medical applications. Since wearables are based on size- and resource-constrained hardware, and are battery operated, they need to run lightweight algorithms to efficiently manage energy and memory. To accomplish this goal, this article proposes SURF, a subject-adpative unsupervised signal compressor for wearable fitness monitors. The core idea is to perform a specialized lossy compression algorithm on the ECG signal at the source (wearable device), to decrease the energy consumption required for wireless transmission and thus prolong the battery lifetime. SURF leverages unsupervised learning techniques to build and maintain, at runtime, a {\it subject-adaptive} dictionary without requiring any prior information on the signal. Dictionaries are constructed within a suitable feature space, allowing the addition and removal of codewords according to the signal's dynamics (for given target fidelity and energy consumption objectives). Extensive performance evaluation results, obtained with reference ECG traces and with our own measurements from a commercial wearable wireless monitor, show the superiority of SURF against state-of-the-art techniques, including (i) compression ratios up to 90-times, (ii) reconstruction errors (RMSE) between 2% and 7% of the signal's range (depending on the amount of compression sought), and (iii) reduction in energy consumption of up to two-orders of magnitude with respect to sending the signal uncompressed, while preserving its morphology. SURF, with artifact prone ECG signals, allows for typical compression efficiencies (CE) in the range [40,50], which means that the data rate of 3 kbit/s that would be required to send the uncompressed ECG trace is lowered to 60~bit/s and 75~bit/s for CE=40 and CE=50, respectively.

  13. Valentina Vadori, Enrico Grisan, Michele Rossi, Biomedical Signal Compression with Time- and Subject-adaptive Dictionary for Wearable Devices. IEEE International Workshop on Machine Learning for Signal Processing (MLSP), September 13-16, Vietri sul Mare, Salerno, Italy, 2016.

  14. Matteo Gadaleta, Luca Merelli, Michele Rossi, Human Authentication From Ankle Motion Data Using Convolutional Neural Networks. IEEE Statistical Signal Processing Workshop (SSP), June 26-29, Palma de Mallorca, Spain, 2016.

  15. Davide Del Testa, Michele Rossi, Lightweight Lossy Compression of Biometric Patterns via Denoising Autoencoders. IEEE Signal Processing Letters, Vol. 22, No. 12, September 2015.
    Wearable Internet of Things (IoT) devices permit the massive collection of biosignals (e.g., heart-rate, oxygen level, respiration, blood pressure, photo-plethysmographic signal, etc.) at low cost. These, can be used to help address the individual fitness needs of the users and could be exploited within personalized healthcare plans. In this letter, we are concerned with the design of lightweight and efficient algorithms for the lossy compression of these signals. In fact, we underline that compression is a key functionality to improve the lifetime of IoT devices, which are often energy constrained, allowing the optimization of their internal memory space and the efficient transmission of data over their wireless interface. To this end, we advocate the use of autoencoders as an efficient and computationally lightweight means to compress biometric signals. While the presented techniques can be used with any signal showing a certain degree of periodicity, in this letter we apply them to ECG traces, showing quantitative results in terms of compression ratio, reconstruction error and computational complexity. State of the art solutions are also compared with our approach.

  16. Enrico Grisan, Giorgia Cantisani, Giacomo Tarroni, Seung Keun Yoon, Michele Rossi, A supervised learning approach for robust detection of heart beat in plethysmographic data. IEEE Engineering in Medicine and Biology Society (EMBS), August 25-29, Milan, Italy, 2015.

  17. Roberto Francescon, Mohsen Hooshmand, Matteo Gadaleta, Enrico Grisan, Seung Keun Yoon, Michele Rossi, Toward Lightweight Biometric Signal Processing for Wearable Devices. IEEE Engineering in Medicine and Biology Society (EMBS), August 25-29, Milan, Italy, 2015.

I gratefully acknowledge SAMSUNG SAIT for a GRO AWARD on biometric sensing and the project "IoT-SURF: a unifying abstraction and reasoning framework for connected and unconnected objects" (Grant no. CPDA151221/15, funded by the University of Padova)