Enrico Macii's research while affiliated with Politecnico di Torino and other places

Publications (690)

Article
Starting in 2007, EU set energy efficiency improvement targets in sectors with high energy-saving potential such as buildings. ICT allows innovative opportunities for energy consumption forecast to integrate with new control policies such as Demand/Response and Demand Side Management to reduce energy waste. However, such technologies must overcome...
Article
The evolution of industrial digitalisation has accelerated in recent years with the availability of hyperconnectivity, low-cost miniaturised electronic components, edge computing, and Internet of Things (IoT) technologies. More generally, with these key enablers, the concept of a system of systems (SoS) is becoming a reality in the industry domain....
Preprint
Full-text available
Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for different portions of the network, has been shown to provide excellent efficiency gains with limited accuracy...
Preprint
Full-text available
The widespread adoption of Electric Vehicles (EVs) is limited by their reliance on batteries with presently low energy and power densities compared to liquid fuels and are subject to aging and performance deterioration over time. For this reason, monitoring the battery State Of Charge (SOC) and State Of Health (SOH) during the EV lifetime is a very...
Article
Electrical anomalies in residential buildings represent a serious problem that can unpredictably change the power profiles of end-users, causing a sub-optimal energy distribution. In addition, electrical faults can cause unnoticed energy wastages and higher energy bills, or even severe damages for properties and people in the most critical cases. I...
Preprint
Full-text available
Neural Architecture Search (NAS) is increasingly popular to automatically explore the accuracy versus computational complexity trade-off of Deep Learning (DL) architectures. When targeting tiny edge devices, the main challenge for DL deployment is matching the tight memory constraints, hence most NAS algorithms consider model size as the complexity...
Preprint
Full-text available
Random Forests (RFs) are widely used Machine Learning models in low-power embedded devices, due to their hardware friendly operation and high accuracy on practically relevant tasks. The accuracy of a RF often increases with the number of internal weak learners (decision trees), but at the cost of a proportional increase in inference latency and ene...
Preprint
Full-text available
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 dete...
Preprint
Full-text available
Collaborative Inference (CI) optimizes the latency and energy consumption of deep learning inference through the inter-operation of edge and cloud devices. Albeit beneficial for other tasks, CI has never been applied to the sequence- to-sequence mapping problem at the heart of Neural Machine Translation (NMT). In this work, we address the specific...
Preprint
Full-text available
Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy. An effective way to obtain energy-efficiency with small accuracy drops is to sequentially execute a set of increasingly complex models, early-stoppin...
Preprint
Full-text available
A wrist-worn PPG sensor coupled with a lightweight algorithm can run on a MCU to enable non-invasive and comfortable monitoring, but ensuring robust PPG-based heart-rate monitoring in the presence of motion artifacts is still an open challenge. Recent state-of-the-art algorithms combine PPG and inertial signals to mitigate the effect of motion arti...
Preprint
Full-text available
Temporal Convolutional Networks (TCNs) are promising Deep Learning models for time-series processing tasks. One key feature of TCNs is time-dilated convolution, whose optimization requires extensive experimentation. We propose an automatic dilation optimizer, which tackles the problem as a weight pruning on the time-axis, and learns dilation factor...
Preprint
Full-text available
Human-machine interaction is gaining traction in rehabilitation tasks, such as controlling prosthetic hands or robotic arms. Gesture recognition exploiting surface electromyographic (sEMG) signals is one of the most promising approaches, given that sEMG signal acquisition is non-invasive and is directly related to muscle contraction. However, the a...
Preprint
Full-text available
Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Learning models for Time Series analysis. We introduce an automated exploration approach and a library of optimized kernels to map TCNs on Parallel Ultra-Low Power (PULP) microcontrollers. Our approach minimizes latency and energy by exploiting a layer tiling optimizer to jointly...
Preprint
Full-text available
Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by movements of the subject's arm affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial s...
Article
Traffic Load Estimation (TLE) is increasingly adopted in public road infrastructures to regulate the access and limit heavy vehicles circulation. Standard approaches to TLE are based either on installing dedicated sensors such as intelligent cameras or infrared sensors or using existing smartphone sensors. However, both approaches have severe limit...
Article
Full-text available
Human activity recognition (HAR) is a classification problem involving time-dependent signals produced by body monitoring, and its application domain covers all the aspects of human life, from healthcare to sport, from safety to smart environments. As such, it is naturally well suited for on-edge deployment of personalized point-of-care (POC) analy...
Article
Full-text available
Residential demand side management (DSM) strategies increase the efficiency of the smart grid. However, the efficacy of these strategies relies on the participation of customers in DSM programs, an issue usually neglected in the analysis. To encompass all aspects, we tried to identify what are the drivers for the user engagement, focusing on the so...
Article
Full-text available
In the Demand Side Management (DSM) context, residential customers have the potential for reducing costs and relieving the grid with non-thermostatic appliances. These appliances might be optimally scheduled by a central entity, taking into account user preferences. However, the user might not be able to communicate its preferences “a-priori”, leav...
Article
Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial sensor. Unfortunately, most standard appro...
Conference Paper
Full-text available
Over the past decade, battery modeling using datasheets has been intensively researched due to the growing number of battery-powered devices. One of the typical non-ideal discharge behaviors of certain batteries is the partial recovery of their energy after a current pulse; this is known as recovery effect. Consequently, the battery runtime is gene...
Article
Full-text available
Due to the continuous increasing importance of renewable energy sources as an alternative to fossil fuels, to contrast air pollution and global warming, the prediction of Global Horizontal Irradiation (GHI), one of the main parameters determining solar energy production of photovoltaic systems, represents an attractive topic nowadays. Solar irradia...
Chapter
In recent years various maintenance strategies have been adopted to maintain industrial equipment in an operational condition. Adopted techniques include approaches based on statistics generated by equipment manufacturers, human knowledge, and intuition based on experience among others. However, techniques like those mentioned above often address o...
Chapter
The advent of Industry4.0 in automation and data exchange leads to a constant evolution towards intelligent environments, including an intensive adoption of Cyber-Physical SystemPredictive maintenanceCyber-Physical System (CPS) features. Thus, full integration of manufacturing IT and control systems with physical objects embedded with electronics,...
Chapter
Additive Manufacturing, in great part due to its huge advantages in terms of design flexibility and parts customization, can be of major importance in maintenance engineering and it is considered one of the key enablers of Industry 4.0. Nonetheless, major improvements are needed towards having additive manufacturing solutions achieve the quality an...
Chapter
A Predictive MaintenanceRemaining Useful Life (RUL)Predictive maintenance strategy for a complex machine requires a sophisticated and non-trivial analytical stage to provide accurate and trusted predictions. It must be planned and carried out carefully to maximise the information extracted from available data. The SERENA project provided an excelle...
Chapter
Predictive maintenancePredictive maintenancePredictive maintenance aims at proactively assessing the current condition of assets and performing maintenance activities if and when needed to preserve them in the optimal operational condition. This in turn may lead to a reduction of unexpected breakdowns and production stoppages as well as maintenance...
Chapter
The role of maintenance in the industry has been shown to improve companies’ productivity and profitability. Industry 4.0Industry 4.0 revolutionised this field by exploiting emergent cloud technologies and IoTInternet of Things (IoT) to enable predictive maintenancePredictive maintenance. Significant benefits can be obtained by taking advantage of...
Chapter
The ever increasing demand for shorter production times and reduced production costsPredictive maintenance require manufacturing firms to bring down their production costs while preserving a smooth and flexible production process. To this aim, manufacturers could exploit data-driven techniques to monitor and assess equipmen’s operational state and...
Article
Nowadays, buildings are responsible for large consumption of energy in our cities. Moreover, buildings can be seen as the smallest entity of urban energy systems. On these premises, in this paper, we present a flexible and distributed co-simulation platform that exploits a multi-modelling approach to simulate and evaluate energy performance in smar...
Article
Full-text available
A well-known system-level strategy to reduce the energy consumption of microprocessors or microcontrollers is to organize the scheduling of the executed tasks so that it is aware of the main battery non-idealities. In the IoT domain, devices rely on simpler microcontrollers; workloads are less rich and, batteries are typically sized to guarantee li...
Article
Full-text available
SpiNNaker is a neuromorphic hardware platform, especially designed for the simulation of Spiking Neural Networks (SNNs). To this end, the platform features massively parallel computation and an efficient communication infrastructure based on the transmission of small packets. The effectiveness of SpiNNaker in the parallel execution of the PageRank...
Preprint
Full-text available
Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effe...
Conference Paper
Full-text available
Human Activity Recognition (HAR) is a relevant inference task in many mobile applications. State-of-the-art HAR at the edge is typically achieved with lightweight machine learning models such as decision trees and Random Forests (RFs), whereas deep learning is less common due to its high computational complexity. In this work, we propose a novel im...
Article
Nowadays, we are moving forward to more sustainable energy production systems based on renewable sources. Among all Photovoltaic (PV) systems are spreading in our cities. In this view, new models are needed to forecast Global Horizontal Solar Irradiance (GHI), which strongly influences PV production. For example, this forecast is crucial to develop...
Article
Recent trends in intelligent manufacturing are transforming shop floor environments into digital factories, thanks to a pervasive integration of information and communication technologies in production lines. Industrial processes become the source of high-volume heterogeneous data, paving the way to create manufacturing intelligence by means of mac...
Article
The Global Horizontal Solar Irradiance prediction (GHI) allows estimating in advance the future energy production of photovoltaic systems, thus ensuring their full integration into the electricity grids. This paper investigates the effectiveness of using exogenous inputs in performing short-term GHI forecasting. Thus, we identified a subset of rele...
Article
The first three industrial revolutions came about as a result of mechanization, electricity, and information technology (IT), respectively. Now, the introduction of the Internet of Things and Services into the manufacturing environment is fostering a 4th industrial revolution (Industry 4.0), where the smart optimization and computerization of all t...
Preprint
Full-text available
Convolutional Neural Networks (CNNs) are supposed to be fed with only high-quality annotated datasets. Nonetheless, in many real-world scenarios, such high quality is very hard to obtain, and datasets may be affected by any sort of image degradation and mislabelling issues. This negatively impacts the performance of standard CNNs, both during the t...
Chapter
In modern data centers, storage system failures are major contributors to downtimes and maintenance costs. Predicting these failures by collecting measurements from disks and analyzing them with machine learning techniques can effectively reduce their impact, enabling timely maintenance. While there is a vast literature on this subject, most approa...
Article
One of the key targets of Industry 4.0 and digital production, in general, is the support of faster, cleaner, and increasingly customizable manufacturing processes. Additive manufacturing (AM) is a natural fit in this context, as it offers the possibility to produce complex parts without the design constraints of traditional manufacturing routes, t...