In automotive manufacturing, the final assembly of car body parts requires repeated measurements of gap and flush, which are essential not just for aesthetics but also for aerodynamics and noise reduction. This paper initially presents an innovative portable wireless laser line triangulation profilometer for human operators in assembly lines. It then describes how the wireless and ergonomic measurement device exploits embedded AI solutions to improve measurement accuracy. Two semantic segmentation approaches were tested (U-Net vs. LinkNet) to compare their performance in isolating the effective laser line from unwanted reflections, as well as inferring accurate segmentation with short inference times. These approaches were deployed at the edge, requiring pruning and quantization steps to comply with the computational capabilities of the System on Module (SoM) mounted on the device. The LinkNet demonstrated superior accuracy (Dice loss of 0.1127) and faster execution speed (166.77 ms). This approach, particularly with semantic segmentation algorithms implemented on the edge device, paves the way to improve the detection of laser line images on transparent surfaces even in the presence of low contrast and multiple reflections, ensuring precise and efficient measurement of gap and flush, even on front lights.

With the rapid advancement of wearable devices, sensor-based human activity recognition has emerged as a fundamental research area with broad applications in various domains. While significant progress has been made in this research field, energy consumption remains a critical aspect that deserves special attention. Recognizing human activities while optimizing energy consumption is essential for prolonging device battery life, reducing charging frequency, and ensuring uninterrupted monitoring and functionality. The primary objective of this survey paper is to provide a comprehensive review of energy-aware wearable human activity recognition techniques based on wearable sensors without considering vision-based systems. In particular, it aims to explore the state-of-the-art approaches and methodologies that integrate activity recognition with energy management strategies. Finally, by surveying the existing literature, this paper aims to shed light on the challenges, opportunities and potential solutions for energy-aware human activity recognition.

The design of IoT systems supporting deep learning capabilities is mainly based today on data transmission to the cloud back-end. Recently, edge computing solutions, which keep most computing and communication as close as possible to user devices have emerged as possible alternatives to reduce energy consumption, limit latency, and safeguard privacy. Early-exit models have been proposed as a way to combine models with different depths into a single architecture. The aim of this article is to investigate the energy expenditure of a distributed IoT system based on early exit architectures, by taking human activity recognition as a case study. We propose a simulation study based on an analytical model and hardware characterization to estimate the trade-off between the accuracy and energy of early exit-based configurations. Experimental results highlight nontrivial relationships between architectures, computing platforms, and communication link. For instance, we found that early-exit strategies do not ensure energy reductions with respect to a cloud-based solution if the same accuracy levels are kept; nonetheless, by tolerating a 1.5% decrease in accuracy, it is possible to achieve a reduction of around 40% of the total energy consumption.

Mobile devices entered people's lives by leaps and bounds, offering various applications relying on private third-party entities to manage their users' data. Centralized control of personal health data endangers the privacy of the users directly involved. In the future, there will likely be a trend toward decentralizing the health data collection, relieving central entities of this task. This comes with several challenges in a decentralized environment, such as avoiding a single point of failure to guarantee data availability. The following work proposes an architecture based on Distributed Ledger Technology to allow users to decide on their data while ensuring availability by employing social networks. We will outline the mechanisms behind data storage and the implications of using smart contracts in the architecture. In concluding the work, we show the developed architecture and results deriving from its assessment, highlighting possible use cases applied to the specific health data management context.

Deep learning is nowadays considered state-of-the-art technology in many applications thanks to huge performance capabilities. However, the accuracy levels that can be obtained with these models entail computationally demanding resources. This results in a challenging task when such systems have to be deployed on edge devices with tight computing, memory, and communication requirements and when energy expenditure and inference delays have to be kept under control. Early exit is a design methodology aimed at reducing the burden of neural networks on computational resources, trading off accuracy for latency. In this work, we aim at exploring the use of early exit for human activity recognition tasks. In particular, we propose an experimental assessment of the accuracy–latency trade-off on different deep network architectures across various publicly available datasets. We also evaluate the impact of early exiting in distributed environments by taking into account communication technologies. Experimental results provide evidence of the significant gain provided by early exits in terms of latency (up to 35×), without a reduction in accuracy (in most cases), confirming the viability of an adaptive approach. In a distributed environment, early exit results are not beneficial in all situations. In particular, it is not convenient for models that are very fast (with inference latency lower than, or as equal as, that of communication) and for models that are forced to make extensive use of far exit points to satisfy the accuracy requirements. Therefore, communication delays in a distributed environment shape performance in an architecture-dependent way.

Wearable devices have become increasingly popular in recent years, and they offer a great opportunity for sensor-based continuous human activity recognition in real-world scenarios. However, one of the major challenges is their limited battery life. In this study, we propose an energy-aware human activity recognition framework for wearable devices based on a lightweight accurate trigger. The trigger acts as a binary classifier capable of recognizing, with maximum accuracy, the presence or absence of one of the interesting activities in the real-time input signal and it is responsible for starting the energy-intensive classification procedure only when needed. The measurement results conducted on a real wearable device show that the proposed approach can reduce energy consumption by up to 95% in realistic case studies, with a cost of performance deterioration of at most 1% or 2% compared to the traditional energy-intensive classification strategy.

Abstract The capability of effectively quantifying the uncertainty associated to a given prediction is an important task in many applications that range from drug design to autonomous driving, providing valuable information to many downstream decision-making processes. The increasing capacity of novel machine learning models, and the growing amount of data on which these systems are trained poses however significant issues to be addressed. Recent research advocated the need for evaluating learning systems not only according to traditional accuracy metrics but also according to the computational complexity required to design them, toward a perspective of sustainability and inclusivity. In this work, we present an empirical investigation aimed at assessing the impact of uniform sampling on the reduction in computational requirements, the quality of regression, and on its uncertainty quantification. We performed several experiments with recent state-of-the-art methods characterized by statistical guarantees whose performances have been measured according to different metrics for evaluating uncertainty quantification (i.e., coverage and length of prediction intervals) and regression (i.e., errors measures and correlation). Experimental results highlight possible interesting trade-offs between computation time, regression and uncertainty evaluation quality, thus confirming the viability of sampling-based approaches to overcome computational bottlenecks without significantly affecting the quality of predictions.

The development of large-scale systems of networked embedded devices with sensing capabilities relies on the availability of low-cost and resource-constrained components However, the reduced precision and accuracy of low-cost sensors on board of low-power platforms risks to impair the overall reliability of these systems, thus preventing their potential diffusion, especially in deployments with several (e.g., hundreds or more) nodes. Hence, ensuring the required quality of measurements along the lifetime of a sensor network represents a key challenge, which is often tackled also by means of calibration techniques. In this article, we propose a novel approach to multihop calibration, targeting the derivation of a spanning tree that encompasses the optimization of a biobjective problem. Indeed, since minimum spanning trees can be related to the energy budget of a network and shortest path trees can be used as a model for the minimization of the cumulative calibration errors, the search for a spanning tree that simultaneously optimizes the two metrics represents a useful direction toward the design of effective and efficient calibration strategies. To this aim, we introduce a method based on the Prim-Dijkstra algorithm, which represents an effective heuristics for effective search of solutions that could represent a tradeoff between the accuracy of multihop calibration and the energy expenditure needed to calibrate sensors. The proposed approach allows fast derivation of different solutions by means of a single parameter, thus enabling the efficient exploration of the design space even in large-scale scenarios as confirmed by numerical results obtained for validation.

Reliability is nowadays considered a key requirement in wireless sensor networks for their increasing diffusion in various Internet of Things applications. However, radio interference from various sources may heavily affect the performance of wirelessly connected embedded devices, resulting into increased packet collisions and congestions. There is therefore a widely recognized need of both theoretical and practical investigations capable of shedding light on the factors affecting the operativeness of sensor networks subject to interference. In this paper, we investigate the role of packet length into the reliability and energy efficiency of low-power medium access protocols. Specifically, we propose a mathematical model to explore the functional dependence of the reliability of a pair of sensor nodes under interference from packet length. We also present a wide range of experimental evaluations aimed at validating the model and at providing novel insights on dependability issues. In particular, we assess the performance of Contiki's default medium access control layer (together with that of an always listening receiver, as a baseline) in terms of packet loss rate and energy efficiency for varying payload lengths. Experimental results highlight the interplay between packet size and interference and in particular the tradeoff between the robustness against interference and the overhead imposed to communication as a function of the length of data packets. The Pareto curve describing the energy efficiency as a function of the packet loss rate, demonstrates the existence of intermediate packet size representing an optimal choice for balancing energy consumption and communication reliability, enabling adequate system dimensioning at design-level.

This work is part of a project, SmartRoadSense, aimed to estimate the quality of the road surface exploiting the sensors of a mobile device anchored to the car cabin. Using the data of the triaxial accelerometer and the vehicle speed provided by GPS system, it has been shown that an estimate of the quality of road surface can be obtained. In order to improve this estimate, the paper studies the dependence of the mobile device vertical acceleration on the vehicle speed. Using a theoretical model and experimental results, it is shown how the average power of the vertical acceleration and the road roughness index estimated by SmartRoadSense are related to speed.

No abstract available.

Out-of-band signaling provides a valuable support to the management of wireless sensor networks. Among other signals, sound has a propagation speed in air which is fast enough to be neglected in typical sensor network applications, and slow enough to be measured by means of low-cost embedded systems. An ultrasonic triggering mechanism has been recently developed for VirtualSense, an ultra-low-power sensor node featuring a Java runtime environment. Ultrasonic triggers provide on-demand wakeup capabilities that can be exploited by routing nodes to be switched on whenever there is a packet to be routed towards the sink, while spending all the idle time in an ultra low power inactive state where even the radio module is turned off. In addition, the same hardware components can be used to perform pairwise distance measurements that can be exploited for localization. In this demonstration we show the possible use of VirtualSense ultrasonic wake-up modules as distance estimators.

The widespread diffusion of wireless sensor networks and wearable devices, together with the emergence of energy harvesting techniques, has motivated the development of ultra-low-power micro controller units (MCUs) which are highly energy efficient in active mode and provide a wide range of sleep states to be possibly exploited to save power during idle periods. In spite of their energy efficiency, state-of-the-art MCUs exhibit 16-bit RISC architectures clocked at up to tens of MHz and equipped with at least 16kbytes of main memory and 64kbytes of flash. This makes them suitable to run a virtual machine, bringing the benefits of a virtual runtime environment to power-constrained embedded systems. Virtual machines, however, impair the effectiveness of dynamic power management since they are seen as always-active processes by the scheduler of the operating system. This paper presents a power-manageable open-source embedded virtual environment based on a modified version of the Darjeeling VM running on top of Contiki OS. The proposed architecture has been implemented and tested on Texas Instruments' MSP430 MCUs which have been used as a testbed for the characterization of the power consumption and transitions cost of each power state.

Energy harvesting technologies make it possible to exploit environmental power to realize autonomous wireless sensor networks with unlimited lifetime. However, the actual autonomy of a wireless network depends on the energetic sustainability of its workload that depends, on its turn, on the algorithms adopted to route packets from the sensor nodes to the sink. A theoretical framework for assessing and optimizing the energetic sustainability of routing algorithms has been recently proposed. In this paper we discuss the actual applicability of optimal energetically sustainable routing algorithms and the issues raised by non-stationary environmental conditions. Furthermore, we present a distributed algorithm, running on sensor nodes, that is able to re-compute optimal routing tables on the field in order to adapt to the actual distribution of environmental power.

Virtual memory is considered to be an unlimited resource in desktop or notebook computers with high storage capabilities. However, in wireless mobile devices, like palmtops and personal digital assistants (PDAs), storage memory is limited or absent due to weight, size, and power constraints, so that swapping over remote memory devices can be considered as a viable alternative. However, power-hungry wireless network interface cards (WNICs) may limit the battery lifetime and application performance if not efficiently exploited. In this paper, we study performance and energy of network swapping in comparison with swapping on local microdrives and flash memories. We report the results of extensive experiments conducted on different WNICs and local swapping devices, using both synthetic and natural benchmarks. Our study points out that remote swapping over power-manageable WNICs can be more efficient than local swapping, especially in bursty workload conditions. Such conditions can be forced where possible by reshaping swapping requests to increase energy efficiency and performance.

Virtual memory is considered to be an unlimited resource in desktop or notebook computers with high storage memory capabilities. However, in wireless mobile devices like palmtops and personal digital assistants (PDA), storage memory is limited or absent due to weight, size and power constraints. As a consequence, swapping over remote memory devices can be considered as a viable alternative. Nevertheless, power hungry wireless network interface cards (WNIC) may limit the battery lifetime and application performance if not efficiently exploited. In this work we explore performance and energy of network swapping in comparison with swapping on local micro-drives and flash memories. Our study points out that remote swapping over power-manageable WNICs can be more efficient than local swapping and that both energy and performance can be optimized through power-aware reshaping of data requests. Experimental results show that our optimization technique can save up to 60% of communication energy while improving performance.

In this paper we provide an incremental methodology to assess the effect of the introduction of a dynamic power manager in a mobile embedded computing device. The methodology consists of two phases. In the first phase, we verify whether the introduction of the dynamic power manager alters the functionality of the system. We show that this can be accomplished by employing standard techniques based on equivalence checking for noninterference analysis. In the second phase, we quantify the effectiveness of the introduction of the dynamic power manager in terms of power consumption and overall system efficiency. This is carried out by enriching the functional model of the system with information about the performance aspects of the system, and by comparing the values of the power consumption and the overall system efficiency obtained from the solution of the performance model with and without dynamic power manager. To this purpose, first we employ a more abstract performance model based on the Markovian assumption, then we use a more realistic performance model - to be validated against the Markovian one - where general probability distributions are considered. The methodology is illustrated by means of its application to the study of a remote procedure call mechanism - through which a battery-powered device is used by some application requesting information - and of a streaming video service - which is accessed by a mobile client equipped with a power-manageable network interface card.

Summary form only given. With the diffusion of Java in advanced multimedia mobile devices, there is a growing need for speeding up the execution of Java bytecode beyond the limits of traditional interpreters and just-in-time compilers. In this area, Java coprocessors are viewed as a promising technology, which marries the flexibility of a general-purpose microprocessor to run legacy code and lightweight Java methods, with the high performance of a specialized execution engine on speed-critical bytecode. We propose and analyze a microprocessor with FPGA coprocessor architecture with efficient shared-memory communication support. Furthermore, we describe a complete run-time environment that supports dynamic migration of Java methods to the coprocessor, and we quantitatively analyze speedups achievable under a number of system configurations using an accurate complete-system simulator.

One of the major concern for 802.11b wireless local area network is energy efficiency. In fact, mobile devices spend a large amount of power on their radio interface for accessing multimedia services such as audio and video streaming.In this work we address the problem of energy-aware scheduling of treaming data provided by a single server to multiple clients. We propose both open-loop and closed-loop strategies that exploit application level information to perform energy-effiocient traffic reshaping.We evaluate the effectiveness of the proposed trategies by means of accurate power/performance imulations performed on top of Mathworks' Simulink. System component are modeled as generalized semi-markov processes (GSMPs) and characterized by mean of real-world measurements. In particular, the timing and power behavior of wireless network interface cards is accurately captured in order to evaluate the impact of power management strategies on a wireless 802.11b link. Experimental result how that up to 75%of the communication energy can be aved by mean of power-aware traffic scheduling with negligible user-perceived performance degradation.

Dynamic power management encompasses several techniques for reducing energy dissipation in electronic systems by selective slowdown or shutdown of components. We present a theoretical framework for explaining and classifying different approaches to power management. Within this framework, we model power-manageable components, workloads, and controllers as discrete-event systems (DESs). The structure of these DESs is specified in terms of physical states (representing operation modes) and events (triggering state transitions), while system behavior is specified in terms of next-event and next-state functions. In particular, nondeterministic next-event and next-state functions are modeled by conditional probability distributions, according to generalized semi-Markov processes (GSMPs). The modeling framework provides a general denotational model for system specification and a rigorous execution semantics that enables event-driven simulation. We introduce a modeling framework, built on top of MathWork's Simulink, supporting the specification and execution of our model. In particular, we present templates for the Simulink simulator to execute GSMP models, and we describe how to use such templates for specifying, analyzing, and optimizing dynamic power-managed systems. Finally, we demonstrate the expressive power and versatility of the proposed approach by using the modeling framework and the simulator for the analysis of representative real-life case studies, including the Intel Xscale processor architecture, a multitasking real-time system, and a sensor network.

We use a case study (namely, the interactive continuous browsing of large geographical maps provided by a remote GIS server) to evaluate the suitability of state-of-the-art personal digital assistants (PDA) with an embedded Java virtual machine to be used as mobile access points of continuous graphical contents provided on demand by a remote server.