Research

ADAS+ - Advanced Driver Assistance System

Recently, the ability to monitor the level of attention of a car-driver has attracted a great deal of interest, in the context of the automotive industry, due to the possibility to prevent any dangers that could arise from an inadequate psycho-physical state of the car driver. In terms of development, that recalled issue required Computer Vision development to constitute an effective ad-hoc real time warning system. Firstly, the researchers focused their effort on the development of integrated devices capable of evaluating not only the road route but also the position of the vehicle, the speed, the sudden change in acceleration and so on. Lately, the need to implement increasingly sophisticated machine learning methods has given more credit to the work based on the study of the psycho-physical condition of the driver as a considerable support for the detection of drowsiness. The intuition that underlies these methods is to verify the attention threshold through the so called heart rate variability (HRV) i.e. a complex physiological indicator for drowsiness. The analysis of HRV allows to understand the state of activity of the autonomic nervous system which is designed to manage a series of automatic, unconscious and involuntary activities, relating, for example, to heartbeat, blood pressure etc ... This variability can be calculated with the aid of appropriate physiological signals: the electrocardiographic (ECG) signal and the photoplethysmographic (PPG) signal. The proposed method has the purpose to show the existence of such correlation between the PPG signal, obtained through appropriate sensors, and the PPG signal reconstructed using the landmarks extracted from a face image. For the recording of biometric signals such as PPG, it will no longer be necessary to make use of integrated devices (sensors, etc.) but it is needed a simple low frame-rate video camera, resulting in a consequent saving in terms of both costs and resources.. For this purpose, we studied the skin micromovements and changes in facial color due to blood circulation quite indistinguishable with naked eye and related to the circulation controlled through the activity of sympathetic and parasympathetic nerves strongly regulated by autonomic nervous system.

Physiological Data

F.Rundo, A.Ortis, S.Battiato, S.Conoci (2018). Advanced bio-inspired system for noninvasive cuff-less blood pressure estimation from physiological signal analysis. Computation 6 (3), 46

Blood Pressure (BP) is one of the most important physiological indicators that provides useful information in the field of health-care monitoring. Blood pressure may be measured by both invasive and non-invasive methods. A novel algorithmic approach is presented to estimate systolic and diastolic blood pressure accurately in a way that does not require any explicit user calibration, ie, it is non-invasive and cuff-less. The approach herein described can be applied in a medical device, as well as in commercial mobile smartphones by an ad hoc developed software based on the proposed algorithm. The authors propose a system suitable for blood pressure estimation based on the PhotoPlethysmoGraphy (PPG) physiological signal sampling time-series. Photoplethysmography is a simple optical technique that can be used to detect blood volume changes in the microvascular bed of tissue. It is non-invasive since it takes measurements at the skin surface. In this paper, the authors present an easy and smart method to measure BP through careful neural and mathematical analysis of the PPG signals. The PPG data are processed with an ad hoc bio-inspired mathematical model that estimates systolic and diastolic pressure values through an innovative analysis of the collected physiological data.

Quantitative Finance

F.Rundo, F. Trenta , A. L. Di Stallo and S. Battiato (2018), Advanced Markov-based Machine Learning Framework for making Adaptive Trading System. Computation (SUBMITTED)

Stock market prediction and trading has attracted effort of many researchers in several scientific areas because it is a challenging task due to high market complexity. More investors put their effort to the development of a systematic approach i.e. the so called “Trading System (TS)” for stocks price and trend prediction. The introduction of the Trading On-Line (TOL) has significantly improved the overall number of daily transactions on the stock market with the consequent increasing of the market complexity and liquidity. One of the most main consequence of the TOL is the so called “automatic trading” i.e. ad-hoc algorithmic robot able to automatically analyze a lot of financial data with target to open/close several trading operations in such reduced time for increasing the profitability of the trading system. When the number of such automatic operations increase significantly, the trading approach is known as High Frequency Trading (HFT). In this context, recently, the usage of machine learning as well as of the soft computing has improved the robustness of the trading systems including HFT sector. The authors propose an innovative approach based on usage of ad-hoc machine learning approach which starting from historical data analysis is able to perform careful stock pricing prediction. The stock price prediction accuracy is further improved by using adaptive correction based on hypothesis that stock price formation is regulated by Markov stochastic dynamic.