Pervasive Computing Paradigms for Mental Health

This paper presents a Japanese emotional database that contains speech and physiological signals that can be used to develop algorithms for emotion recognition using audio, physiological signals, or several combined signals. Research on emotions was underpinned by using this database, and health-care oriented applications were the main reason this database was constructed. All six basic human emotions were elicited by using real emotional experiences, which had different impacts on health conditions. We also describe the experimental setup and protocols. Finally, signals from more than 50 people were included in the database.

We have developed a new method to estimate no only stress occurrence, but also various workplace stress types. The method relies on adaptive selection of physiological indices integrated into an intelligent multi-steps discrimination process. Preliminary results revealed the method promising to improve estimation accuracy of workplace stress types. The study reported here, has two purposes: investigate if it is effectively possible to estimate stress type independently from individual differences, and validate the performances of proposed method in real situation. Four subjects that were not part of the preliminary study were assigned whether a tape dictation task or a presentation task as real situation tasks. The occurrence of various types of harmful stress could be correctly discriminated, confirming proposed method as an effective solution to estimate stress type regardless individual differences.

Assessment of neurocognitive functioning is a critical task in clinical settings. In many disorders, cognitive impairment precedes the onset of behavioral symptoms, and cognitive decline is a major factor contributing to functional disability. The purpose of the current study was to evaluate the executive functions by comparing the evaluations obtained using a neuropsychological battery with the one obtained using the virtual reality version of the Multiple Errands Test (V-MET). The study population included three groups: 10 patients affected by Obsessive Compulsive Disorder (OCD); 10 Schizophrenic patients; 10 healthy Controls. The results identified executive problems in clinical samples. By contrast, controls have higher level of efficiency and better performance. The correlation across the two assessment support the validity of V-Met, as a neurocognitive assessment.

We analyzed long period of time (more than 10 h) autonomic nervous system data of 128 subjects (78 males and 50 females in 20’s, 30’s, 40’s and 50’s respectively) by using small wearable heart rate sensors. As a result, we found that there was a significant negative correlation (p value < 0.05) between LnTP (Total-Power as an indicator of comprehensive autonomic nervous system activity) and age for both sexes (genders). Moreover, the negative correlation value for male was higher than for female. The noticeable difference from the preceding study is that our research was based on data measured by many advanced wearable heart rate sensors which enabled to accumulate long period of time data in our daily life for many subjects and that we found the similar correlation between TP and aging comparing to the preceding study.

Computerised learning much like classic learning is subject to a host of adverse emotions such as boredom, frustration and anxiety. These emotions can cause serious negative impacts on memory and attention, which in turn affect learning achievement. Thus, many researchers strongly agree that intelligent tutoring systems (ITSs) would significantly improve performance if they can adapt to the affective state (emotional state) of the learners. This idea has spawned an important trend in the development of ITSs, which are systems with the ability to regulate a learner’s adverse emotions. In the present study, we review six dominant researches that have implemented different emotion management strategies such as coping strategies and emotion regulation strategies in an intelligent tutoring system. Then, we concisely discuss the results of the best practice that applies emotion regulation strategies to schoolchildren, without using an ITS. The results show that applying emotion management strategies during computerised or non-computerised learning produces more optimistic emotions as well as better learning gain.

Intelligent neck cooler has been proposed as an energy-saving indoor air-conditioning method by direct cooling of human body. This paper reports evaluation results of intelligent neck cooler’s effectiveness regarding labor productivity and comfort in hot summer office environment. We studied through trial subjects how neck cooling affects physiology, psychology, and task productivity in summer heat environment. Higher comfort level were reported (0.05 statistical significance), and better maintenance of attention (0.01 statistical significance) in long lasting tasks in neck cooling condition were demonstrated.

Over the past two decades, a shift and rethinking has occurred by placing focus on patient-centered care. In 2001, the Institute of Medicine included patient-centered care as 1 of 6 specific aims at improving and bridging the quality, effectiveness, and efficiency of care required for patients. However, one area that patient-centered care has failed to clearly address is the psychological experience of patients waiting in clinics. In this paper, we address such psychological factors that impact patients and introduce a novel approach that has the potential for reducing stress and anxiety while waiting in clinical environments. Through this approach, we attempt at answering the following questions: Since patients might experience anxiety and stress while waiting, can a perceptual change in the environment help minimize such level of discomfort? And furthermore, can such a stress-reduction approach assist patients in communicating their symptoms more clearly to doctors?

Light reflex and oculogyration analysing system is proposed in order to diagnose the Alzheimer type dementia (DAT) objectively. 19 patients are studied, which shows that the maximum miosis ratio and miosis velocity are sensitive parameters to evaluate the severity of dementia and the changing time of internal and external rectus eye muscles is the effective index for screening of the dementia. The threshold of the changing time over 0.35 s can discriminate DAT clearly from the normal. Biofeedback trainings of the demented are executed by the objective diagnosing method, which shows improvement in MMSE, ADL score and the eye reflex parameters. The proposed method may become a safe non-pharmacological treatment of the dementia.

Children afflicted with developmental disabilities, namely autism, suffer from a natural aversion to dyadic (i.e., eye-to-eye) contact. Research has shown this aversion to be an early indicator of slower development of linguistic skills, a narrow vocabulary, as well as social issues later in life. In addition, this aversion may also result in the loss of already acquired abilities such as language and life skills. Consequently, manual prompt techniques have been adopted to address this issue. However, they are plagued with some inherent flaws: (i) the teacher must make unnatural movements when using a manual prompt such as gesturing towards the face; (ii) The child’s attention will follow this prompt as it is removed from the face defeating the purpose as it detracts the child’s attention from the teacher’s eyes. To tackle these issues we have developed a system that can utilize effective prompt methodologies aimed at conditioning these children to establish and maintain dyadic contact. Our system not only reduces, but eliminates shortcomings present in the current manual method. This is accomplished through the use of a stereo camera and virtual reality headset to augment the child’s vision when eye contact is not being established. The prompt is displayed in the child’s vision over the eyes of the teacher to attract their attention. Once dyadic contact has been ascertained, the prompt is gradually fading leaving the child only to focus on the eyes of the teacher as is needed.

The ability to communicate with others is of paramount importance for mental well-being. In this paper, we describe an interaction system to reduce communication barriers for people with severe speech and physical impairments (SSPI) such as cerebral palsy. The system consists of two main components: (i) the head-mounted human-computer interaction (HCI) part consisting of smart glasses with gaze trackers and text-to-speech functionality (which implement a communication board and the selection tool), and (ii) a natural language processing pipeline in the backend in order to generate complete sentences from the symbols on the board. We developed the components to provide a smooth interaction between the user and the system thereby including gaze tracking, symbol selection, symbol recognition, and sentence generation. Our results suggest that such systems can dramatically increase communication efficiency of people with SSPI.

In this work we show how phone call conversations can be used to objectively predict manic and depressive episodes of people suffering from bipolar disorder. In particular, we use phone call statistics, speaking parameters derived from phone conversations and emotional acoustic features to build and test user-specific classification models. Using the random forest classification method, we were able to predict the bipolar states with an average F1 score of 82 %. The most important variables for prediction were speaking length and phone call length, the HNR value, the number of short turns and the variance of pitch F\(_0\).

One of the major diseases that afflict the elderly population in Mexico is depression. This document describes the process of designing a system for early detection and treatment of the state of depression in older adults, taking advantage of the technological development of the Internet of Things, the Context Awareness and the concept of e-Health to determine the Daily Activities living (ADL) using the gesture recognition log events to determine an abnormality in as a means to conclude the variations in the ADL.

Online communities are emerging as important sources of support for people with chronic illnesses such as diabetes and obesity, both of which have been associated with depression. The goal of this study was to assess the performance of text classification in identifying at-risk patients. We manually created a corpus of chat messages based on the ICD-10 depression diagnostic criteria, and trained multiple classifiers on the corpus. After selecting informative features and significant bigrams, a precision of 0.92, recall of 0.88, f-score of 0.92 was reached. Current findings demonstrate the feasibility of automatically identifying patients at risk of developing severe depression in online communities.

Lifelogging techniques help individuals to log their life and retrieve important events, memories and experiences. Structuring lifelogs is a major challenge in lifelogging systems since the system should present the logs in a concise and meaningful way to the user. In this paper the authors present an approach for structuring lifelogs as places and activities based on location data. The structured lifelogs are achieved using a combination of density-based clustering algorithms and convex hull construction to identify the places of interest. The periods of time where the user lingers at the same place are then identified as possible activities. In addition to structuring lifelogs the authors present an application in which images are associated to the structuring results and presented to the user for reviewing. The system is evaluated through a user study consisting of 12 users, who used the system for 1 day and then answered a survey. The proposed approach in this paper allows automatic inference of information about significant places and activities, which generates structured image-annotated logs of everyday life.

In this paper we present and discuss the design, implementation and evaluation of a visual programming environment. The proposed application allows authoring of therapeutic training sequences for the CareToy system, a hardware system developed for the purpose of in-home rehabilitation training for infants, aiming to improve the motor skills of preterm infants diagnosed with neurological conditions.

The aim of this research is to present a novel idea of interoperable, independent living ICT solutions using global standards that will improve the quality of life of older people in their home or community environment, by enabling them to stay active, mobile and independent for longer. The proposed innovation takes a multidisciplinary approach using both open source standards and technology for maximum interoperability and affordability, and user driven content development for sustainable care systems of tomorrow. In addition to the development of interoperable independent living technology solutions, guidelines for business models and methodologies to create appropriate content will also be developed.