Bipolar disorders are characterized by an unpredictable behavior, resulting in depressive, hypomanic or manic episodes alternating with euthymic states. A multi-parametric approach can be followed to estimate mood states by integrating information coming from different physiological signals and from the analysis of voice. In this work we propose an algorithm to estimate speech features from running speech with the aim of characterizing the mood state in bipolar patients. This algorithm is based on an automatic segmentation of speech signals to detect voiced segments, and on a spectral matching approach to estimate pitch and pitch changes. In particular average pitch, jitter and pitch standard deviation within each voiced segment, are estimated. The performances of the algorithm are evaluated on a speech database, which includes an electroglottographic signal. A preliminary analysis on subjects affected by bipolar disorders is performed and results are discussed.

The electrodermal activity (EDA) is a reliable physiological signal for monitoring the sympathetic nervous system. Several studies have demonstrated that EDA can be a source of effective markers for the assessment of emotional states in humans. There are two main methods for measuring EDA: endosomatic (internal electrical source) and exosomatic (external electrical source). Even though the exosomatic approach is the most widely used, differences between alternating current (AC) and direct current (DC) methods and their implication in the emotional assessment field have not yet been deeply investigated. This paper aims at investigating how the admittance contribution of EDA, studied at different frequency sources, affects the EDA statistical power in inferring on the subject’s arousing level (neutral or aroused). To this extent, 40 healthy subjects underwent visual affective elicitations, including neutral and arousing levels, while EDA was gathered through DC and AC sources from 0 to 1 kHz. Results concern the accuracy of an automatic, EDA feature-based arousal recognition system for each frequency source. We show how the frequency of the external electrical source affects the accuracy of arousal recognition. This suggests a role of skin susceptance in the study of affective stimuli through electrodermal response.

The non-invasiveness of photoplethysmographic (PPG) acquisition systems, together with their cost-effectiveness and easiness of connection with IoT technologies, is opening up to the possibility of their widespread use. For this reason, the study of the reliability of PPG and pulse rate variability (PRV) signal quality has become of great scientific, technological, and commercial interest. In this field, sensor location has been demonstrated to play a crucial role. The goal of this study was to investigate PPG and PRV signal quality acquired from two body locations: finger and wrist. We simultaneously acquired the PPG and electrocardiographic (ECG) signals from sixteen healthy subjects (aged 28.5 ± 3.5, seven females) who followed an experimental protocol of affective stimulation through visual stimuli. Statistical tests demonstrated that PPG signals acquired from the wrist and the finger presented different signal quality indexes (kurtosis and Shannon entropy), with higher values for the wrist-PPG. Then we propose to apply the cross-mapping (CM) approach as a new method to quantify the PRV signal quality. We found that the performance achieved using the two sites was significantly different in all the experimental sessions (p < 0.01), and the PRV dynamics acquired from the finger were the most similar to heart rate variability (HRV) dynamics.

Bipolar disorder is one of the most common mood disorders characterized by large and invalidating mood swings. Several projects focus on the development of decision support systems that monitor and advise patients, as well as clinicians. Voice monitoring and speech signal analysis can be exploited to reach this goal. In this study, an Android application was designed for analyzing running speech using a smartphone device. The application can record audio samples and estimate speech fundamental frequency, F0, and its changes. F0-related features are estimated locally on the smartphone, with some advantages with respect to remote processing approaches in terms of privacy protection and reduced upload costs. The raw features can be sent to a central server and further processed. The quality of the audio recordings, algorithm reliability and performance of the overall system were evaluated in terms of voiced segment detection and features estimation. The results demonstrate that mean F0 from each voiced segment can be reliably estimated, thus describing prosodic features across the speech sample. Instead, features related to F0 variability within each voiced segment performed poorly. A case study performed on a bipolar patient is presented.

Surgeons are workers that are particularly prone to the development of musculoskeletal disorders. Recent advances in surgical interventions, such as laparoscopic procedures, have caused a worsening of the scenario, given the harmful static postures that have to be kept for long periods. In this paper, we present a sensor-based platform specifically aimed at monitoring the posture during actual surgical operations. The proposed system adopts a limited number of Inertial Measurement Units (IMUs) to obtain information about spine and neck angles across time. Such a system merges the reliability of sensor-based approaches and the validity of state-of-the-art scoring procedure, such as RULA. Specifically, three IMUs are used to estimate the flexion, lateral bending, and twisting angles of spine and neck. An ergonomic risk index is thus estimated in a time varying fashion borrowing relevant features from the RULA scoring system. The detailed functioning of the proposed systems is introduced, and the assessment results related to a real surgical procedure, consisting of a laparoscopy and mini-laparotomy sections, are shown and discussed. In the exemplary case study introduced, the surgeon kept a high score, indicating the need for an intervention on the working procedures, for a large time fraction. The system allows separately analyzing the contribution of spine and neck, also specifying the angle configuration. It is shown how the proposed approach can provide further information, as related to dynamical analysis, which could be used to enlarge the features taken into account by currently available approaches for ergonomic risk assessment. The proposed system could be adopted both for training purposes, as well as for alerting surgeons during actual surgical operations.