Kyriaki Kalimeri

Exploring multimodal biosignal features for stress detection during indoor mobility

This paper presents a multimodal framework for assessing the emotional and cognitive experience of blind and visually impaired people when navigating in unfamiliar indoor environments based on mobile monitoring and fusion of electroencephalography (EEG) and electrodermal activity (EDA) signals. The overall goal is to understand which environmental factors increase stress and cognitive load in order to help design emotionally intelligent mobility technologies that are able to adapt to stressful environments from real-time biosensor data. We propose a model based on a random forest classifier which successfully infers in an automatic way (weighted AUROC 79.3%) the correct environment among five predefined categories expressing generic everyday situations of varying complexity and difficulty, where different levels of stress are likely to occur. Time-locating the most predictive multimodal features that relate to cognitive load and stress, we provide further insights into the relationship of specific biomarkers with the environmental/situational factors that evoked them.

Identifying Urban Mobility Challenges for the Visually Impaired with Mobile Monitoring of Multimodal Biosignals

In this study, we aim to better the user experience of the visually impaired when navigating in unfamiliar outdoor environments assisted by mobility technologies. We propose a framework for assessing their cognitive-emotional experience based on ambulatory monitoring and multimodal fusion of electroencephalography, electrodermal activity, and blood volume pulse signals. The proposed model is based on a random forest classifier which successfully infers in an automatic way the correct urban environment among eight predefined categories (AUROC 93 %). Geolocating the most predictive multimodal features that relate to cognitive load and stress, we provide further insights into the relationship of specific biomarkers with the environmental/situational factors that evoked them.

Towards Happier Organisations: Understanding the Relationship between Communication and Productivity

This work investigates in-depth the communication practices within a workplace to understand whether workers interact face to face or more indirectly with email. We analysed the interactions to understand how these changes affect our work (productivity, deadlines, interesting task) and our wellbeing (positive and negative affective states),by using a variety of data collection methods (sensors and surveys). Our analysis revealed that overall email was the most frequent medium of communication, but when taking into account just the communication within working hours (8am to 7pm), that face to face interactions were preffered. Correlation analysis revealed significant relationships between Affective States and Situational Factors while Longitudinal Analysis revealed an impact of communication features and measures of self reported Productivity and Creativity. These findings lead us to believe that different communication processes (synchronous and asynchronous) can impact Positive and Negative Affective States as well as how productive and creative you feel at work.

Unsupervised Extraction of Epidemic Syndromes from Participatory Influenza Surveillance Self-reported Symptoms

Seasonal influenza surveillance is usually carried out by sentinel general practitioners who compile weekly reports based on the number of influenza-like illness (ILI) clinical cases observed among visited patients. This practice for surveillance is generally affected by two main issues: i) reports are usually released with a lag of about one week or more, ii) the definition of a case of influenza-like illness based on patients symptoms varies from one surveillance system to the other, i.e. from one country to the other. The availability of novel data streams for disease surveillance can alleviate these issues; in this paper, we employed data from Influenzanet, a participatory web-based surveillance project which collects symptoms directly from the general population in real time. We developed an unsupervised probabilistic framework that combines time series analysis of symptoms counts and performs an algorithmic detection of groups of symptoms, hereafter called syndromes. Symptoms counts were collected through the participatory web-based surveillance platforms of a consortium called Influenzanet which is found to correlate with Influenza-like illness incidence as detected by sentinel doctors. Our aim is to suggest how web-based surveillance data can provide an epidemiological signal capable of detecting influenza-like illness’ temporal trends without relying on a specific case definition. We evaluated the performance of our framework by showing that the temporal trends of the detected syndromes closely follow the ILI incidence as reported by the traditional surveillance, and consist of combinations of symptoms that are compatible with the ILI definition. The proposed framework was able to predict quite accurately the ILI trend of the forthcoming influenza season based only on the available information of the previous years. Moreover, we assessed the generalisability of the approach by evaluating its potentials for the detection of gastrointestinal syndromes. We evaluated the approach against the traditional surveillance data and despite the limited amount of data, the gastrointestinal trend was successfully detected. The result is a real-time flexible surveillance and prediction tool that is not constrained by any disease case definition. Author summary This study suggests how web-based surveillance data can provide an epidemiological signal capable of detecting influenza-like illness’ temporal trends without relying on a specific case definition. The proposed framework was able to predict quite accurately the ILI trend of the forthcoming influenza season based only on the available information of the previous years. Moreover, we assessed the generalisability of the approach by evaluating its potentials for the detection of gastrointestinal syndromes. We evaluated the approach against the traditional surveillance data and despite the limited amount of data, the gastrointestinal trend was successfully detected. The result is a real-time flexible surveillance and prediction tool that is not constrained by any disease case definition.

Cognitive Load Assessment from EEG and Peripheral Biosignals for the Design of Visually Impaired Mobility Aids

Reliable detection of cognitive load would benefit the design of intelligent assistive navigation aids for the visually impaired (VIP). Ten participants with various degrees of sight loss navigated in unfamiliar indoor and outdoor environments, while their electroencephalogram (EEG) and electrodermal activity (EDA) signals were being recorded. In this study, the cognitive load of the tasks was assessed in real time based on a modification of the well-established event-related (de)synchronization (ERD/ERS) index. We present an in-depth analysis of the environments that mostly challenge people from certain categories of sight loss and we present an automatic classification of the perceived difficulty in each time instance, inferred from their biosignals. Given the limited size of our sample, our findings suggest that there are significant differences across the environments for the various categories of sight loss. Moreover, we exploit cross-modal relations predicting the cognitive load in real time inferring on features extracted from the EDA. Such possibility paves the way for the design on less invasive, wearable assistive devices that take into consideration the well-being of the VIP.

Beyond demographics: How search engine data can enhance the understanding of determinants of suicide in India and inform prevention (Preprint)

Background India is home to 20% of the world’s suicide deaths. Although statistics regarding suicide in India are distressingly high, data and cultural issues likely contribute to a widespread underreporting of the problem. Social stigma and only recent decriminalization of suicide are among the factors hampering official agencies’ collection and reporting of suicide rates. Objective As the product of a data collaborative, this paper leverages private-sector search engine data toward gaining a fuller, more accurate picture of the suicide issue among young people in India. By combining official statistics on suicide with data generated through search queries, this paper seeks to: add an additional layer of information to more accurately represent the magnitude of the problem, determine whether search query data can serve as an effective proxy for factors contributing to suicide that are not represented in traditional datasets, and consider how data collaboratives built on search query data could inform future suicide prevention efforts in India and beyond. Methods We combined official statistics on demographic information with data generated through search queries from Bing to gain insight into suicide rates per state in India as reported by the National Crimes Record Bureau of India. We extracted English language queries on “suicide,” “depression,” “hanging,” “pesticide,” and “poison”. We also collected data on demographic information at the state level in India, including urbanization, growth rate, sex ratio, internet penetration, and population. We modeled the suicide rate per state as a function of the queries on each of the 5 topics considered as linear independent variables. A second model was built by integrating the demographic information as additional linear independent variables. Results Results of the first model fit (R2) when modeling the suicide rates from the fraction of queries in each of the 5 topics, as well as the fraction of all suicide methods, show a correlation of about 0.5. This increases significantly with the removal of 3 outliers and improves slightly when 5 outliers are removed. Results for the second model fit using both query and demographic data show that for all categories, if no outliers are removed, demographic data can model suicide rates better than query data. However, when 3 outliers are removed, query data about pesticides or poisons improves the model over using demographic data. Conclusions In this work, we used search data and demographics to model suicide rates. In this way, search data serve as a proxy for unmeasured (hidden) factors corresponding to suicide rates. Moreover, our procedure for outlier rejection serves to single out states where the suicide rates have substantially different correlations with demographic factors and query rates.