Over the past few decades the increased level of public awareness concerning healthcare, physical activities, safety and environmental sensing has created an emerging need for smart sensor technologies and monitoring devices able to sense, classify, and provide feedbacks to users’ health status and physical activities, as well as to evaluate environmental and safety conditions in a pervasive, accurate and reliable fashion. Monitoring and precisely quantifying users’ physical activity with inertial measurement unit-based devices, for instance, has also proven to be important in health management of patients affected by chronic diseases, e.g., Parkinson’s disease, many of which are becoming highly prevalent in Italy and in the Western world. This review paper will focus on MEMS sensor technologies developed in Italy in the last three years describing research achievements for healthcare and physical activity, safety and environmental sensing, in addition to smart systems integration. Innovative and smart integrated solutions for sensing devices, pursued and implemented in Italian research centres, will be highlighted, together with specific applications of such technologies. Finally, the paper will depict the future perspective of sensor technologies and corresponding exploitation opportunities, again with a specific focus on Italy.

https://www.mdpi.com/1424-8220/15/3/6441/pdf

MEMS sensor technologies for human centred applications in healthcare, physical activities, safety and environmental sensing: a review on research activities in Italy.

This paper addresses the intractable problem of attaining precise attitude estimation efficiently using MEMS MARG (magnetic, angular rate, and gravity) sensors for 3-D motion tracking, which is called attitude and heading reference system (AHRS). The performance of AHRS is adversely affected by sensor noise and measurement disturbances. To overcome this problem, we propose a novel adaptive extended Kalman filter (AEKF) in this paper, including a multiplicative extended Kalman filter (MEKF) and a hidden Markov Model (HMM) recognizer. MEKF is built on sensor noise model. An HMM recognizer is developed to identify the measurement disturbance caused by motion or environmental interference and then to adjust the noise covariance of MEKF adaptively. The proposed AEKF was assessed with a high-precision test platform by using a high-caliber commercial AHRS. Experimental results indicate that the proposed method achieves a higher level of stability and accuracy in comparison to other attitude estimators, especially in dynamic tests, which demonstrates the availability of 3-D motion tracking.

Adaptive EKF Based on HMM Recognizer for Attitude Estimation Using MEMS MARG Sensors

Researches on machine vision-based driver fatigue detection algorithm have improved traffic safety significantly. Generally, many algorithms do not analyze driving state from driver characteristics. It results in some inaccuracy. The paper proposes a fatigue driving detection algorithm based on facial multi-feature fusion combining driver characteristics. First, we introduce an improved YOLOv3-tiny convolutional neural network to capture the facial regions under complex driving conditions, eliminating the inaccuracy and affections caused by artificial feature extraction. Second, on the basis of the Dlib toolkit, we introduce the Eye Feature Vector(EFV) and Mouth Feature Vector(MFV), which are the evaluation parameters of the driver's eye state and mouth state, respectively. Then, the driver identity information library is constructed by offline training, including driver eye state classifier library, driver mouth state classifier library, and driver biometric library. Finally, we construct the driver identity verification model and the driver fatigue assessment model by online assessment. After passing the identity verification, calculate the driver's closed eyes time, blink frequency and yawn frequency to evaluate the driver's fatigue state. In simulated driving applications, our algorithm detects the fatigue state at a speed of over 20fps with an accuracy of 95.10%.

/pdf/a-fatigue-driving-detection-algorithm-based-on-facial-multi-2kvikjprva.pdf

A Fatigue Driving Detection Algorithm Based on Facial Multi-Feature Fusion

The paper presents an approach and case study of a distributed driver monitoring system. The system utilizes smartphone sensors for detecting dangerous states for a driver in a vehicle. We use a mounted smartphone on a vehicle windshield directed towards the driver's face tracked by the front-facing camera. Using information from camera video frames as well as other sensors, we determine drowsiness, distraction, aggressive driving, and high pulse rate dangerous states that can lead to road accidents. We propose a cloud system architecture to capture statistics from vehicle drivers, analyze it and personalize the smartphone application for the driver. The cloud service provides reports on driver trips as well as statistics to developers. This allows to monitor and improve the system by developing modules for personification and taking into account context situation. We identified statistically that the driver eye closeness is related to the light brightness and drowsiness recognition should be adjusted accordingly.

Cloud-Based Driver Monitoring System Using a Smartphone

Received: 24 September 2019 Accepted: 28 November 2019 Driver drowsiness is one of the reasons for large number of road accidents these days. With the advancement in Computer Vision technologies, smart/intelligent cameras are developed to identify drowsiness in drivers, thereby alerting drivers which in turn reduce accidents when they are in fatigue. In this work, a new framework is proposed using deep learning to detect driver drowsiness based on Eye state while driving the vehicle. To detect the face and extract the eye region from the face images, Viola-Jones face detection algorithm is used in this work. Stacked deep convolution neural network is developed to extract features from dynamically identified key frames from camera sequences and used for learning phase. A SoftMax layer in CNN classifier is used to classify the driver as sleep or non-sleep. This system alerts driver with an alarm when the driver is in sleepy mood. The proposed work is evaluated on a collected dataset and shows better accuracy with 96.42% when compared with traditional CNN. The limitation of traditional CNN such as pose accuracy in regression is overcome with the proposed Staked Deep CNN.

/pdf/deep-cnn-a-machine-learning-approach-for-driver-drowsiness-81qpmazddm.pdf

Deep CNN: A Machine Learning Approach for Driver Drowsiness Detection Based on Eye State

The main objective of this paper is to determine the feasibility of designing a driver drunkenness detection system based on the dynamic analysis of a subject’s pupillary light reflex (PLR). This involuntary reaction is widely utilized in the medical field to diagnose a variety of diseases, and in this paper, the effectiveness of such a method to reveal an impairment condition due to alcohol abuse is evaluated. The test method consists in applying a light stimulus to one eye of the subject and to capture the dynamics of constriction of both eyes; for extracting the pupil size profiles from the video sequences, a two-step methodology is described, where in the first phase, the iris/pupil search within the image is performed, and in the second stage, the image is cropped to perform pupil detection on a smaller image to improve time efficiency. The undesired pupil dynamics arising in the PLR are defined and evaluated; a spontaneous oscillation of the pupil diameter is observed in the range [0, 2] Hz and the accommodation reflex causes pupil constriction of about 10% of the iris diameter. A database of pupillary light responses is acquired on different subjects in baseline condition and after alcohol consumption, and for each one, a first-order model is identified. A set of features is introduced to compare the two populations of responses and is used to design a support vector machine classifier to discriminate between “Sober” and “Drunk” states.

Automatic Detection of Driver Impairment Based on Pupillary Light Reflex

Acne Vulgaris is the most common skin disease and affects 85% of population at some point in life, typically in adolescence Objective evaluation of acne severity is necessary to asses the efficacy of medical treatment procedures Traditionally acne evaluation is done by dermatologists manually counting the number of acne lesions through visual inspection or scanning acquired images of the patient's skin This method is time consuming and requires excessive effort by the physician In this paper a prototype application for automatic acne detection, lesion counting and reporting through the processing of distance picture taken by mobile devices is developed The pipeline of the application is composed of body part detection, skin segmentation, heat-mapping, acne extraction and blob detection Body part detection is accomplished using different Haar-Cascade classifiers; frontal face, right profile, left profile and torso are discriminated Skin segmentation has been performed using an ensemble of random forest models trained on a augmented version of the FSD dataset The set of features was engineered combining colour, texture, spatial, shape and unsupervised descriptors and selected by a feature importance step The a∗ channel of the CIELab colour space was used for enhance the visual contrast between inflamed zones and healthy skin Finally acne extraction and blob detection were accomplished through Adaptive Thresholding and Laplacian of Gaussian filtering Reports are generated containing number, position and ray size of the detected spots

Automated detection, extraction and counting of acne lesions for automatic evaluation and tracking of acne severity

This work presents a novel wireless and low power Attitude and Heading Reference Systems network based on low-cost MEMS (Micro Electro-Mechanical System) sensors, developed for motion tracking systems. Biomedical and rehabilitation purposes as well as gaming and consumer electronics may be the potential applications of this network. The paper aims to describe the hardware architecture, the embedded sensor fusion algorithm and the motion tracking system.

Development of a wireless low-power multi-sensor network for motion tracking applications

In this paper, we analyze and discuss the time optimal control problem for bridge cranes. Specifically, we employ the geometric approach introduced in [12] to address the control issue without computing the analytic trajectory of the costate. As a second contribution, we show that an alternative approach based on a proportional controller accounting for the limits of the control action can be tuned to resemble to the time-optimal solution, but with simpler and more robust implementation. The above ideas are validated by means of some simulation examples.

Michele Ermidoro

Papers

Automatic Detection of Driver Impairment Based on Pupillary Light Reflex

Automated detection, extraction and counting of acne lesions for automatic evaluation and tracking of acne severity

Development of a wireless low-power multi-sensor network for motion tracking applications

On time-optimal anti-sway controller design for bridge cranes

Fixed-order gain-scheduling anti-sway control of overhead bridge cranes