Chen Xie

Chen Xie

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 July 2022 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
FDFrancesco Daghero
Francesco Daghero
ABAlessio Burrello
Alessio Burrello
CXChen Xie
Chen Xie
MCMarco Castellano
Marco Castellano
LGLuca Gandolfi
Luca Gandolfi
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari
Human Activity Recognition (HAR) based on inertial data is an increasingly diffused task on embedded devices, from smartphones to ultra low-power sensors. Due to the high computational complexity of deep learning models, most embedded HAR systems are based on simple and not-so-accurate classic machine learning algorithms. This work bridges the gap between on-device HAR and deep learning, proposing a set of efficient one-dimensional Convolutional Neural Networks (CNNs) that can be deployed on general purpose microcontrollers (MCUs). Our CNNs are obtained combining hyper-parameters optimization with sub-byte and mixed-precision quantization, to find good trade-offs between classification results and memory occupation. Moreover, we also leverage adaptive inference as an orthogonal optimization to tune the inference complexity at runtime based on the processed input, hence producing a more flexible HAR system. With experiments on four datasets, and targeting an ultra-low-power RISC-V MCU, we show that (i) we are able to obtain a rich set of Pareto-optimal CNNs for HAR, spanning more than 1 order of magnitude in terms of memory, latency, and energy consumption; (ii) thanks to adaptive inference, we can derive >20 runtime operating modes starting from a single CNN, differing by up to 10% in classification scores and by more than 3× in inference complexity, with a limited memory overhead; (iii) on three of the four benchmarks, we outperform all previous deep learning methods, while reducing the memory occupation by more than 100×. The few methods that obtain better performance (both shallow and deep) are not compatible with MCU deployment; (iv) all our CNNs are compatible with real-time on-device HAR, achieving an inference latency that ranges between 9 μs and 16 ms. Their memory occupation varies in 0.05–23.17 kB, and their energy consumption in 0.05 and 61.59 μJ, allowing years of continuous operation on a small battery supply.

30 March 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CXChen Xie
Chen Xie
FDFrancesco Daghero
Francesco Daghero
Yukai ChenYukai Chen
Yukai Chen
MCMarco Castellano
Marco Castellano
LGLuca Gandolfi
Luca Gandolfi
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari
Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring and visitor flow analysis in private and public spaces. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. However, the literature was missing an extensive comparative analysis of various efficient DL architectures for IR array-based people counting, that considers not only their accuracy, but also the cost of deploying them on memory-and energy-constrained Internet of Things (IoT) edge nodes. Such analysis is key for system designers, since it helps them select the most appropriate DL model given the constraints of their target hardware. In this work, we address this need by comparing 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array, which we made openly available. With a wide architectural exploration of each model type, we obtain a rich set of Pareto-optimal solutions, spanning cross-validated balanced accuracy scores in the 55.70-82.70% range. When deployed on a commercial Microcontroller (MCU) by STMicroelectronics, the STM32L4A6ZG, these models occupy 0.41-9.28kB of memory, and require 1.10-7.74ms per inference, while consuming 17.18-120.43 of energy. Our models are significantly more accurate than a previous deterministic method (up to +39.9%), while being up to 3.53x faster and more energy efficient. So, our work serves also as a demonstration that DL can not only achieve higher accuracy, but also higher efficiency compared to classic algorithms for this type of task. Further, our models accuracy is comparable to state-of-the-art DL solutions on similar resolution sensors, despite a much lower complexity. All our models enable continuous, real-time inference on a MCU-based IoT node, with years of autonomous operation without battery recharging.

26 July 2021
Verified
Conference Paper
Closed access
CXChen Xie
Chen Xie
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari
ANDREA CALIMERAANDREA CALIMERA
ANDREA CALIMERA
EMEnrico Macii
Enrico Macii
Massimo PoncinoMassimo Poncino
Massimo Poncino
In ultra low power systems with many peripherals, off-chip serial interconnects contribute significantly to the total energy budget. Leveraging the error-resilience characteristics of many embedded applications, the approximate computing paradigm has been applied to serial bus encodings to reduce interconnect consumption. However, the power model considered in previous works was purely capacitive. Accordingly, the objective of these approximate encodings was simply to reduce the transition count. While this works well for most bus standards, one notable exception is represented by I 2 C, whose open-drain physical connection makes the static energy consumed by logic-0 values on the bus extremely relevant. In this work, we propose ACME, the first approximate serial bus encoding targeting specifically I 2 C connections. With a simple encoding/decoding scheme, ACME concurrently reduces both the static and dynamic energy on the bus by maximizing the number of logic-1 values in codewords, while simultaneously reducing transitions. Using an accurate bus model and realistic capacitance and resistance values selected according to the I 2 C standard, we show that our encoding outperforms state-of-the-art solutions and reduces the total energy consumption on the bus by 57% on average, with an error smaller than 0.1%.

12 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
CXChen Xie
Chen Xie
ABAlessio Burrello
Alessio Burrello
FDFrancesco Daghero
Francesco Daghero
LBLuca Benini
Luca Benini
ANDREA CALIMERAANDREA CALIMERA
ANDREA CALIMERA
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari
Hand gesture recognition applications based on surface electromiographic (sEMG) signals can benefit from on-device execution to achieve faster and more predictable response times and higher energy efficiency. However, deploying state-of-the-art deep learning (DL) models for this task on memory-constrained and battery-operated edge devices, such as wearables, requires a careful optimization process, both at design time, with an appropriate tuning of the DL models’ architectures, and at execution time, where the execution of large and computationally complex models should be avoided unless strictly needed. In this work, we pursue both optimization targets, proposing a novel gesture recognition system that improves upon the state-of-the-art models both in terms of accuracy and efficiency. At the level of DL model architecture, we apply for the first time tiny transformer models (which we call bioformers) to sEMG-based gesture recognition. Through an extensive architecture exploration, we show that our most accurate bioformer achieves a higher classification accuracy on the popular Non-Invasive Adaptive hand Prosthetics Database 6 (Ninapro DB6) dataset compared to the state-of-the-art convolutional neural network (CNN) TEMPONet (+3.1%). When deployed on the RISC-V-based low-power system-on-chip (SoC) GAP8, bioformers that outperform TEMPONet in accuracy consume 7.8×–44.5× less energy per inference. At runtime, we propose a three-level dynamic inference approach that combines a shallow classifier, i.e., a random forest (RF) implementing a simple “rest detector” with two bioformers of different accuracy and complexity, which are sequentially applied to each new input, stopping the classification early for “easy” data. With this mechanism, we obtain a flexible inference system, capable of working in many different operating points in terms of accuracy and average energy consumption. On GAP8, we obtain a further 1.03×–1.35× energy reduction compared to static bioformers at iso-accuracy.

22 September 2022
Verified
Book Chapter
Closed access
PDF file
FDFrancesco Daghero
Francesco Daghero
ABAlessio Burrello
Alessio Burrello
CXChen Xie
Chen Xie
LBLuca Benini
Luca Benini
ANDREA CALIMERAANDREA CALIMERA
ANDREA CALIMERA
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari

22 April 2022 in arXiv
Verified
Preprint
Open access
PDF file
CXChen Xie
Chen Xie
FDFrancesco Daghero
Francesco Daghero
Yukai ChenYukai Chen
Yukai Chen
MCM. Castellano
M. Castellano
LGLuca Gandolfi
Luca Gandolfi
DPDaniele Jahier Pagliari
Daniele Jahier Pagliari
Low-resolution infrared (IR) array sensors offer a low-cost, low-power, and privacy-preserving alternative to optical cameras and smartphones/wearables for social distance monitoring in indoor spaces, permitting the recognition of basic shapes, without revealing the personal details of individuals. In this work, we demonstrate that an accurate detection of social distance violations can be achieved processing the raw output of a 8x8 IR array sensor with a small-sized Convolutional Neural Network (CNN). Furthermore, the CNN can be executed directly on a Microcontroller (MCU)-based sensor node. With results on a newly collected open dataset, we show that our best CNN achieves 86.3% balanced accuracy, significantly outperforming the 61% achieved by a state-of-the-art deterministic algorithm. Changing the architectural parameters of the CNN, we obtain a rich Pareto set of models, spanning 70.5-86.3% accuracy and 0.18-75k parameters. Deployed on a STM32L476RG MCU, these models have a latency of 0.73-5.33ms, with an energy consumption per inference of 9.38-68.57{\mu}J.