Machine Learning-Assisted Speech Analysis for Early Detection of Parkinson's Disease: A Study on Speaker Diarization and Classification Techniques.

Parkinson's disease (PD) is a neurodegenerative disorder characterized by a range of motor and non-motor symptoms. One of the notable non-motor symptoms of PD is the presence of vocal disorders, attributed to the underlying pathophysiological changes in the neural control of the laryngeal and vocal tract musculature. From this perspective, the integration of machine learning (ML) techniques in the analysis of speech signals has significantly contributed to the detection and diagnosis of PD. Particularly, MEL Frequency Cepstral Coefficients (MFCCs) and Gammatone Frequency Cepstral Coefficients (GTCCs) are both feature extraction techniques commonly used in the field of speech and audio signal processing that could exhibit great potential for vocal disorder identification. This study presents a novel approach to the early detection of PD through ML applied to speech analysis, leveraging both MFCCs and GTCCs. The recordings contained in the Mobile Device Voice Recordings at King's College London (MDVR-KCL) dataset were used. These recordings were collected from healthy individuals and PD patients while they read a passage and during a spontaneous conversation on the phone. Particularly, the speech data regarding the spontaneous dialogue task were processed through speaker diarization, a technique that partitions an audio stream into homogeneous segments according to speaker identity. The ML applied to MFCCS and GTCCs allowed us to classify PD patients with a test accuracy of 92.3%. This research further demonstrates the potential to employ mobile phones as a non-invasive, cost-effective tool for the early detection of PD, significantly improving patient prognosis and quality of life.

Development of 2400-2450 MHz Frequency Band RF Energy Harvesting System for Low-Power Device Operation.

Recently, there has been an increasing fascination for employing radio frequency (RF) energy harvesting techniques to energize various low-power devices by harnessing the ambient RF energy in the surroundings. This work outlines a novel advancement in RF energy harvesting (RFEH) technology, intending to power portable gadgets with minimal operating power demands. A high-gain receiver microstrip patch antenna was designed and tested to capture ambient RF residue, operating at 2450 MHz. Similarly, a two-stage Dickson voltage booster was developed and employed with the RFEH to transform the received RF signals into useful DC voltage signals. Additionally, an LC series circuit was utilized to ensure impedance matching between the antenna and rectifier, facilitating the extraction of maximum power from the developed prototype. The findings indicate that the developed rectifier attained a peak power conversion efficiency (PCE) of 64% when operating at an input power level of 0 dBm. During experimentation, the voltage booster demonstrated its capability to rectify a minimum input AC signal of only 50 mV, yielding a corresponding 180 mV output DC signal. Moreover, the maximum power of 4.60 µW was achieved when subjected to an input AC signal of 1500 mV with a load resistance of 470 kΩ. Finally, the devised RFEH was also tested in an open environment, receiving signals from Wi-Fi modems positioned at varying distances for evaluation.

Can Data-Driven Supervised Machine Learning Approaches Applied to Infrared Thermal Imaging Data Estimate Muscular Activity and Fatigue?

Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless EMG devices are still sensitive to motion artifacts and often not comfortable for long monitoring. In this study, a non-invasive contactless method to estimate parameters indicative of muscular activity and fatigue, as they are assessed by EMG, through infrared thermal imaging (IRI) and cross-validated machine learning (ML) approaches is described. Particularly, 10 healthy participants underwent five series of bodyweight squats until exhaustion interspersed by 1 min of rest. During exercising, the vastus medialis activity and its temperature were measured through sEMG and IRI, respectively. The EMG average rectified value (ARV) and the median frequency of the power spectral density (MDF) of each series were estimated through several ML approaches applied to IRI features, obtaining good estimation performances (r = 0.886, p < 0.001 for ARV, and r = 0.661, p < 0.001 for MDF). Although EMG and IRI measure physiological processes of a different nature and are not interchangeable, these results suggest a potential link between skin temperature and muscle activity and fatigue, fostering the employment of contactless methods to deliver metrics of muscular activity in a non-invasive and comfortable manner in sports and clinical applications.

Prefrontal cortical activation associated with prospective memory while walking around a real-world street environment.

Rostral PFC (area 10) activation is common during prospective memory (PM) tasks. But it is not clear what mental processes these activations index. Three candidate explanations from cognitive neuroscience theory are: (i) monitoring of the environment; (ii) spontaneous intention retrieval; (iii) a combination of the two. These explanations make different predictions about the temporal and spatial patterns of activation that would be seen in rostral PFC in naturalistic settings. Accordingly, we plotted functional events in PFC using portable fNIRS while people were carrying out a PM task outside the lab and responding to cues when they were encountered, to decide between these explanations. Nineteen people were asked to walk around a street in London, U.K. and perform various tasks while also remembering to respond to prospective memory (PM) cues when they detected them. The prospective memory cues could be either social (involving greeting a person) or non-social (interacting with a parking meter) in nature. There were also a number of contrast conditions which allowed us to determine activation specifically related to the prospective memory components of the tasks. We found that maintaining both social and non-social intentions was associated with widespread activation within medial and right hemisphere rostral prefrontal cortex (BA 10), in agreement with numerous previous lab-based fMRI studies of prospective memory. In addition, increased activation was found within lateral prefrontal cortex (BA 45 and 46) when people were maintaining a social intention compared to a non-social one. The data were then subjected to a GLM-based method for automatic identification of functional events (AIDE), and the position of the participants at the time of the activation events were located on a map of the physical space. The results showed that the spatial and temporal distribution of these events was not random, but aggregated around areas in which the participants appeared to retrieve their future intentions (i.e., where they saw intentional cues), as well as where they executed them. Functional events were detected most frequently in BA 10 during the PM conditions compared to other regions and tasks. Mobile fNIRS can be used to measure higher cognitive functions of the prefrontal cortex in "real world" situations outside the laboratory in freely ambulant individuals. The addition of a "brain-first" approach to the data permits the experimenter to determine not only when haemodynamic changes occur, but also where the participant was when it happened. This can be extremely valuable when trying to link brain and cognition.

Interpersonal Emotion Dynamics in Couples With Somatic Symptom Disorder: Dyadic Coherence in Facial Temperature During Emotional Interactions.

OBJECTIVE: Disturbances in emotional processes are commonly reported in patients with a somatic symptom disorder (SSD). Although emotions usually occur in social interactions, little is known about interpersonal emotion dynamics of SSD patients during their actual emotional encounters. This study examined physiological coherence (linkage) between SSD patients and their partners, and in healthy couples during their emotional interactions. Secondarily, we explored group-level relationships between participants' and their partners' subjective affect. METHODS: Twenty-nine romantic couples (16 healthy and 13 SSD patient-couples) underwent a dyadic conversation task with neutral and anger-eliciting topics followed by a guided relaxation. Partners' cutaneous facial temperature was recorded simultaneously by functional infrared thermal imaging. Immediately after each condition, participants reported on their pain intensity, self-affect, and perceived partner-affect. RESULTS: Emotional conditions and having a partner with an SSD significantly affected coherence amplitude on the forehead (F(2,54) = 4.95, p = .011) and nose tip temperature (F(2,54) = 3.75, p = .030). From baseline to anger condition, coherence amplitude significantly increased in the patient-couples, whereas it decreased in the healthy couples. Correlation changes between partners' subjective affect comparably accompanied the changes in physiological coherence in healthy and patient-couples. CONCLUSIONS: Inability to reduce emotional interdependence in sympathetic activity and subjective affect during a mutual conflict observed in SSD patient-couples seems to capture emotion co-dysregulation. Interventions should frame patients' emotional experiences as embodied and social. Functional infrared thermal imaging confirms to be an ecological and reliable method for examining autonomic changes in interpersonal contexts.Registration Page: https://osf.io/8eyjr.

Automated Affective Computing Based on Bio-Signals Analysis and Deep Learning Approach.

Extensive possibilities of applications have rendered emotion recognition ineluctable and challenging in the fields of computer science as well as in human-machine interaction and affective computing. Fields that, in turn, are increasingly requiring real-time applications or interactions in everyday life scenarios. However, while extremely desirable, an accurate and automated emotion classification approach remains a challenging issue. To this end, this study presents an automated emotion recognition model based on easily accessible physiological signals and deep learning (DL) approaches. As a DL algorithm, a Feedforward Neural Network was employed in this study. The network outcome was further compared with canonical machine learning algorithms such as random forest (RF). The developed DL model relied on the combined use of wearables and contactless technologies, such as thermal infrared imaging. Such a model is able to classify the emotional state into four classes, derived from the linear combination of valence and arousal (referring to the circumplex model of affect's four-quadrant structure) with an overall accuracy of 70% outperforming the 66% accuracy reached by the RF model. Considering the ecological and agile nature of the technique used the proposed model could lead to innovative applications in the affective computing field.

Classification of Drivers' Mental Workload Levels: Comparison of Machine Learning Methods Based on ECG and Infrared Thermal Signals.

Mental workload (MW) represents the amount of brain resources required to perform concurrent tasks. The evaluation of MW is of paramount importance for Advanced Driver-Assistance Systems, given its correlation with traffic accidents risk. In the present research, two cognitive tests (Digit Span Test-DST and Ray Auditory Verbal Learning Test-RAVLT) were administered to participants while driving in a simulated environment. The tests were chosen to investigate the drivers' response to predefined levels of cognitive load to categorize the classes of MW. Infrared (IR) thermal imaging concurrently with heart rate variability (HRV) were used to obtain features related to the psychophysiology of the subjects, in order to feed machine learning (ML) classifiers. Six categories of models have been compared basing on unimodal IR/unimodal HRV/multimodal IR + HRV features. The best classifier performances were reached by the multimodal IR + HRV features-based classifiers (DST: accuracy = 73.1%, sensitivity = 0.71, specificity = 0.69; RAVLT: accuracy = 75.0%, average sensitivity = 0.75, average specificity = 0.87). The unimodal IR features based classifiers revealed high performances as well (DST: accuracy = 73.1%, sensitivity = 0.73, specificity = 0.73; RAVLT: accuracy = 71.1%, average sensitivity = 0.71, average specificity = 0.85). These results demonstrated the possibility to assess drivers' MW levels with high accuracy, also using a completely non-contact and non-invasive technique alone, representing a key advancement with respect to the state of the art in traffic accident prevention.

Improving Human-Robot Interaction by Enhancing NAO Robot Awareness of Human Facial Expression.

An intriguing challenge in the human-robot interaction field is the prospect of endowing robots with emotional intelligence to make the interaction more genuine, intuitive, and natural. A crucial aspect in achieving this goal is the robot's capability to infer and interpret human emotions. Thanks to its design and open programming platform, the NAO humanoid robot is one of the most widely used agents for human interaction. As with person-to-person communication, facial expressions are the privileged channel for recognizing the interlocutor's emotional expressions. Although NAO is equipped with a facial expression recognition module, specific use cases may require additional features and affective computing capabilities that are not currently available. This study proposes a highly accurate convolutional-neural-network-based facial expression recognition model that is able to further enhance the NAO robot' awareness of human facial expressions and provide the robot with an interlocutor's arousal level detection capability. Indeed, the model tested during human-robot interactions was 91% and 90% accurate in recognizing happy and sad facial expressions, respectively; 75% accurate in recognizing surprised and scared expressions; and less accurate in recognizing neutral and angry expressions. Finally, the model was successfully integrated into the NAO SDK, thus allowing for high-performing facial expression classification with an inference time of 0.34 ± 0.04 s.

A Motion Artifact Correction Procedure for fNIRS Signals Based on Wavelet Transform and Infrared Thermography Video Tracking.

Functional near infrared spectroscopy (fNIRS) is a neuroimaging technique that allows to monitor the functional hemoglobin oscillations related to cortical activity. One of the main issues related to fNIRS applications is the motion artefact removal, since a corrupted physiological signal is not correctly indicative of the underlying biological process. A novel procedure for motion artifact correction for fNIRS signals based on wavelet transform and video tracking developed for infrared thermography (IRT) is presented. In detail, fNIRS and IRT were concurrently recorded and the optodes' movement was estimated employing a video tracking procedure developed for IRT recordings. The wavelet transform of the fNIRS signal and of the optodes' movement, together with their wavelet coherence, were computed. Then, the inverse wavelet transform was evaluated for the fNIRS signal excluding the frequency content corresponding to the optdes' movement and to the coherence in the epochs where they were higher with respect to an established threshold. The method was tested using simulated functional hemodynamic responses added to real resting-state fNIRS recordings corrupted by movement artifacts. The results demonstrated the effectiveness of the procedure in eliminating noise, producing results with higher signal to noise ratio with respect to another validated method.

Fiberless, Multi-Channel fNIRS-EEG System Based on Silicon Photomultipliers: Towards Sensitive and Ecological Mapping of Brain Activity and Neurovascular Coupling.

Portable neuroimaging technologies can be employed for long-term monitoring of neurophysiological and neuropathological states. Functional Near-Infrared Spectroscopy (fNIRS) and Electroencephalography (EEG) are highly suited for such a purpose. Their multimodal integration allows the evaluation of hemodynamic and electrical brain activity together with neurovascular coupling. An innovative fNIRS-EEG system is here presented. The system integrated a novel continuous-wave fNIRS component and a modified commercial EEG device. fNIRS probing relied on fiberless technology based on light emitting diodes and silicon photomultipliers (SiPMs). SiPMs are sensitive semiconductor detectors, whose large detection area maximizes photon harvesting from the scalp and overcomes limitations of fiberless technology. To optimize the signal-to-noise ratio and avoid fNIRS-EEG interference, a digital lock-in was implemented for fNIRS signal acquisition. A benchtop characterization of the fNIRS component showed its high performances with a noise equivalent power below 1 pW. Moreover, the fNIRS-EEG device was tested in vivo during tasks stimulating visual, motor and pre-frontal cortices. Finally, the capabilities to perform ecological recordings were assessed in clinical settings on one Alzheimer's Disease patient during long-lasting cognitive tests. The system can pave the way to portable technologies for accurate evaluation of multimodal brain activity, allowing their extensive employment in ecological environments and clinical practice.

Tomographic Task-Related Functional Near-Infrared Spectroscopy in Acute Sport-Related Concussion: An Observational Case Study.

Making decisions regarding return-to-play after sport-related concussion (SRC) based on resolution of symptoms alone can expose contact-sport athletes to further injury before their recovery is complete. Task-related functional near-infrared spectroscopy (fNIRS) could be used to scan for abnormalities in the brain activation patterns of SRC athletes and help clinicians to manage their return-to-play. This study aims to show a proof of concept of mapping brain activation, using tomographic task-related fNIRS, as part of the clinical assessment of acute SRC patients. A high-density frequency-domain optical device was used to scan 2 SRC patients, within 72 h from injury, during the execution of 3 neurocognitive tests used in clinical practice. The optical data were resolved into a tomographic reconstruction of the brain functional activation pattern, using diffuse optical tomography. Moreover, brain activity was inferred using single-subject statistical analyses. The advantages and limitations of the introduction of this optical technique into the clinical assessment of acute SRC patients are discussed.

Working Memory Decline in Alzheimer's Disease Is Detected by Complexity Analysis of Multimodal EEG-fNIRS.

Alzheimer's disease (AD) is characterized by working memory (WM) failures that can be assessed at early stages through administering clinical tests. Ecological neuroimaging, such as Electroencephalography (EEG) and functional Near Infrared Spectroscopy (fNIRS), may be employed during these tests to support AD early diagnosis within clinical settings. Multimodal EEG-fNIRS could measure brain activity along with neurovascular coupling (NC) and detect their modifications associated with AD. Data analysis procedures based on signal complexity are suitable to estimate electrical and hemodynamic brain activity or their mutual information (NC) during non-structured experimental paradigms. In this study, sample entropy of whole-head EEG and frontal/prefrontal cortex fNIRS was evaluated to assess brain activity in early AD and healthy controls (HC) during WM tasks (i.e., Rey-Osterrieth complex figure and Raven's progressive matrices). Moreover, conditional entropy between EEG and fNIRS was evaluated as indicative of NC. The findings demonstrated the capability of complexity analysis of multimodal EEG-fNIRS to detect WM decline in AD. Furthermore, a multivariate data-driven analysis, performed on these entropy metrics and based on the General Linear Model, allowed classifying AD and HC with an AUC up to 0.88. EEG-fNIRS may represent a powerful tool for the clinical evaluation of WM decline in early AD.

Autonomic Responses to Emotional Stimuli in Children Affected by Facial Palsy: The Case of Moebius Syndrome.

According to embodied simulation theories, others' emotions are recognized by the unconscious mimicking of observed facial expressions, which requires the implicit activation of the motor programs that produce a specific expression. Motor responses performed during the expression of a given emotion are hypothesized to be directly linked to autonomic responses associated with that emotional behavior. We tested this hypothesis in 9 children (M age = 5.66) affected by Moebius syndrome (MBS) and 15 control children (M age = 6.6). MBS is a neurological congenital disorder characterized by underdevelopment of the VI and VII cranial nerves, which results in paralysis of the face. Moebius patients' inability to produce facial expressions impairs their capacity to communicate emotions through the face. We therefore assessed Moebius children's autonomic response to emotional stimuli (video cartoons) by means of functional infrared thermal (fIRT) imaging. Patients showed weaker temperature changes compared to controls, suggesting impaired autonomic activity. They also showed difficulties in recognizing facial emotions from static illustrations. These findings reveal that the impairment of facial movement attenuates the intensity of emotional experience, probably through the diminished activation of autonomic responses associated with emotional stimuli. The current study is the first to investigate emotional responses in MBS children, providing important insights into the role of facial expressions in emotional processing during early development.

Modelling Impulse Response Function of Functional Infrared Imaging for General Linear Model Analysis of Autonomic Activity.

Functional infrared imaging (fIRI) is a validated procedure to infer autonomic arousal. Currently, fIRI signals are analysed through descriptive metrics, such as average temperature changes in a region of interest (ROI). However, the employment of mathematical models could provide a powerful tool for the accurate identification of autonomic activity and investigation of the mechanisms underlying autonomic arousal. A linear temporal statistical model such as the general linear model (GLM) is particularly suited for its simplicity and direct interpretation. In order to apply the GLM, the thermal response linearity and time-invariance of fIRI have to be demonstrated, and the thermal impulse response (TIR) needs to be characterized. In this study, the linearity and time-invariance of the thermal response to sympathetic activating stimulation were demonstrated, and the TIR for employment of the GLM was characterized. The performance of the GLM-fIRI was evaluated by comparison with the GLM applied on synchronous measurements of the skin conductance response (SCR). In fact, the GLM-SCR is a validated procedure to estimate autonomic arousal. Assuming the GLM-SCR as the gold standard approach, a GLM-fIRI sensitivity and specificity of 86.4% and 75.9% were obtained. The GLM-fIRI may allow increased performances in the evaluation of autonomic activity and a broader range of application of fIRI in both research and clinical settings for the assessment of psychophysiological and psychopathological states.

Multi-Site Photoplethysmographic and Electrocardiographic System for Arterial Stiffness and Cardiovascular Status Assessment.

The development and validation of a system for multi-site photoplethysmography (PPG) and electrocardiography (ECG) is presented. The system could acquire signals from 8 PPG probes and 10 ECG leads. Each PPG probe was constituted of a light-emitting diode (LED) source at a wavelength of 940 nm and a silicon photomultiplier (SiPM) detector, located in a back-reflection recording configuration. In order to ensure proper optode-to-skin coupling, the probe was equipped with insufflating cuffs. The high number of PPG probes allowed us to simultaneously acquire signals from multiple body locations. The ECG provided a reference for single-pulse PPG evaluation and averaging, allowing the extraction of indices of cardiovascular status with a high signal-to-noise ratio. Firstly, the system was characterized on optical phantoms. Furthermore, in vivo validation was performed by estimating the brachial-ankle pulse wave velocity (baPWV), a metric associated with cardiovascular status. The validation was performed on healthy volunteers to assess the baPWV intra- and extra-operator repeatability and its association with age. Finally, the baPWV, evaluated via the developed instrumentation, was compared to that estimated with a commercial system used in clinical practice (Enverdis Vascular Explorer). The validation demonstrated the system's reliability and its effectiveness in assessing the cardiovascular status in arterial ageing.

Complexity of Frontal Cortex fNIRS Can Support Alzheimer Disease Diagnosis in Memory and Visuo-Spatial Tests.

Decline in visuo-spatial skills and memory failures are considered symptoms of Alzheimer's Disease (AD) and they can be assessed at early stages employing clinical tests. However, performance in a single test is generally not indicative of AD. Functional neuroimaging, such as functional Near Infrared Spectroscopy (fNIRS), may be employed during these tests in an ecological setting to support diagnosis. Indeed, neuroimaging should not alter clinical practice allowing free doctor-patient interaction. However, block-designed paradigms, necessary for standard functional neuroimaging analysis, require tests adaptation. Novel signal analysis procedures (e.g., signal complexity evaluation) may be useful to establish brain signals differences without altering experimental conditions. In this study, we estimated fNIRS complexity (through Sample Entropy metric) in frontal cortex of early AD and controls during three tests that assess visuo-spatial and short-term-memory abilities (Clock Drawing Test, Digit Span Test, Corsi Block Tapping Test). A channel-based analysis of fNIRS complexity during the tests revealed AD-induced changes. Importantly, a multivariate analysis of fNIRS complexity provided good specificity and sensitivity to AD. This outcome was compared to cognitive tests performances that were predictive of AD in only one test. Our results demonstrated the capabilities of fNIRS and complexity metric to support early AD diagnosis.

A novel GLM-based method for the Automatic IDentification of functional Events (AIDE) in fNIRS data recorded in naturalistic environments.

Recent technological advances have allowed the development of portable functional Near-Infrared Spectroscopy (fNIRS) devices that can be used to perform neuroimaging in the real-world. However, as real-world experiments are designed to mimic everyday life situations, the identification of event onsets can be extremely challenging and time-consuming. Here, we present a novel analysis method based on the general linear model (GLM) least square fit analysis for the Automatic IDentification of functional Events (or AIDE) directly from real-world fNIRS neuroimaging data. In order to investigate the accuracy and feasibility of this method, as a proof-of-principle we applied the algorithm to (i) synthetic fNIRS data simulating both block-, event-related and mixed-design experiments and (ii) experimental fNIRS data recorded during a conventional lab-based task (involving maths). AIDE was able to recover functional events from simulated fNIRS data with an accuracy of 89%, 97% and 91% for the simulated block-, event-related and mixed-design experiments respectively. For the lab-based experiment, AIDE recovered more than the 66.7% of the functional events from the fNIRS experimental measured data. To illustrate the strength of this method, we then applied AIDE to fNIRS data recorded by a wearable system on one participant during a complex real-world prospective memory experiment conducted outside the lab. As part of the experiment, there were four and six events (actions where participants had to interact with a target) for the two different conditions respectively (condition 1: social-interact with a person; condition 2: non-social-interact with an object). AIDE managed to recover 3/4 events and 3/6 events for conditions 1 and 2 respectively. The identified functional events were then corresponded to behavioural data from the video recordings of the movements and actions of the participant. Our results suggest that "brain-first" rather than "behaviour-first" analysis is possible and that the present method can provide a novel solution to analyse real-world fNIRS data, filling the gap between real-life testing and functional neuroimaging.

The role of expectation in multisensory body representation - neural evidence.

Sensory events contribute to body ownership, the feeling that the body belongs to me. However, the encoding of sensory events is not only reactive, but also proactive in that our brain generates prediction about forthcoming stimuli. In previous studies, we have shown that prediction of sensory events is a sufficient condition to induce the sense of body ownership. In this study, we investigated the underlying neural mechanisms. Participants were seated with their right arm resting upon a table just below another smaller table. Hence, the real hand was hidden from the participant's view and a life-sized rubber model of a right hand was placed on the small table in front of them. Participants observed a wooden plank while approaching - without touching - the rubber hand. We measured the phenomenology of the illusion by means of questionnaire. Neural activity was recorded by means of near-infrared spectroscopy (fNIRS). Results showed higher activation of multisensory parietal cortices in the rubber hand illusion induced by touch expectation. Furthermore, such activity was correlated with the subjective feeling of owning the rubber hand. Our results enrich current models of body ownership suggesting that our multisensory brain regions generate prediction on what could be my body and what could not. This finding might have interesting implications in all those cases in which body representation is altered, anorexia, bulimia nervosa and obesity, among others.

New Frontiers for Applications of Thermal Infrared Imaging Devices: Computational Psychopshysiology in the Neurosciences.

Thermal infrared imaging has been proposed, and is now used, as a tool for the non-contact and non-invasive computational assessment of human autonomic nervous activity and psychophysiological states. Thanks to a new generation of high sensitivity infrared thermal detectors and the development of computational models of the autonomic control of the facial cutaneous temperature, several autonomic variables can be computed through thermal infrared imaging, including localized blood perfusion rate, cardiac pulse rate, breath rate, sudomotor and stress responses. In fact, all of these parameters impact on the control of the cutaneous temperature. The physiological information obtained through this approach, could then be used to infer about a variety of psychophysiological or emotional states, as proved by the increasing number of psychophysiology or neurosciences studies that use thermal infrared imaging. This paper presents a review of the principal achievements of thermal infrared imaging in computational psychophysiology, focusing on the capability of the technique for providing ubiquitous and unwired monitoring of psychophysiological activity and affective states. It also presents a summary on the modern, up-to-date infrared sensors technology.

Thermographic imaging in sports and exercise medicine: A Delphi study and consensus statement on the measurement of human skin temperature.

The importance of using infrared thermography (IRT) to assess skin temperature (tsk) is increasing in clinical settings. Recently, its use has been increasing in sports and exercise medicine; however, no consensus guideline exists to address the methods for collecting data in such situations. The aim of this study was to develop a checklist for the collection of tsk using IRT in sports and exercise medicine. We carried out a Delphi study to set a checklist based on consensus agreement from leading experts in the field. Panelists (n = 24) representing the areas of sport science (n = 8; 33%), physiology (n = 7; 29%), physiotherapy (n = 3; 13%) and medicine (n = 6; 25%), from 13 different countries completed the Delphi process. An initial list of 16 points was proposed which was rated and commented on by panelists in three rounds of anonymous surveys following a standard Delphi procedure. The panel reached consensus on 15 items which encompassed the participants' demographic information, camera/room or environment setup and recording/analysis of tsk using IRT. The results of the Delphi produced the checklist entitled "Thermographic Imaging in Sports and Exercise Medicine (TISEM)" which is a proposal to standardize the collection and analysis of tsk data using IRT. It is intended that the TISEM can also be applied to evaluate bias in thermographic studies and to guide practitioners in the use of this technique.