We are examining autonomic sleep patterns using a wrist-worn biosensor that enables comfortable measurement of skin conductance, skin temperature, and motion. The skin conductance reflects sympathetic arousal. We are looking at sleep patterns in healthy groups, in groups with autism, and in groups with sleep disorders. We are looking especially at sleep quality and at performance on learning and memory tasks.

Technologies to automatically recognize stress, are extremely important to prevent chronic psychological stress and the pathophysiological risks associated to it. The introduction of comfortable and wearable biosensors have created new opportunities to measure stress in real-life environments, but there is often great variability in how people experience stress and how they express it physiologically. In this project, we modify the loss function of Support Vector Machines to encode a person's tendency to feel more or less stressed, and give more importance to the training samples of the most similar subjects. These changes are validated in a case study where skin conductance was monitored in nine call center employees during one week of their regular work. Employees working in this type of settings usually handle high volumes of calls every day, and they frequently interact with angry and frustrated customers that lead to high stress levels.

Individuals diagnosed with autism spectrum disorder (ASD) often have intense, focused interests. These interests, when harnessed properly, can help motivate an individual to persist in a task that might otherwise be too challenging or bothersome. For example, past research has shown that embedding focused interests into educational curricula can increase task adherence and task performance in individuals with ASD. However, providing this degree of customization is often time-consuming and costly and, in the case of computer-mediated interventions, high-level computer-programming skills are often required. We have recently designed new software to solve this problem. Specifically, we have built an algorithm that will: (1) retrieve user-specified images from the Google database; (2) strip them of their background; and (3) embed them seamlessly into Flash-based computer programs.

This work builds on our earlier work with FaceSense, created to help automate the understanding of facial expressions, both cognitive and affective. The FaceSense system has now been made available commercially by Media Lab spin-off Affectiva as Affdex. In this work we present the first project analyzing facial expressions at scale over the Internet. The interface analyzes the participants' smile intensity as they watch popular commercials. They can compare their responses to an aggregate from the larger population. The system also allows us to crowd-source data for training expression recognition systems and to gain better understanding of facial expressions under natural at-home viewing conditions instead of in traditional lab settings.

Complex and expensive medical devices are mainly used in medical facilities by health professionals. IDA is an attempt to disrupt this paradigm and introduce a new type of device: easy to use, low cost, and open source. It is a digital stethoscope that can be connected to the Internet for streaming the physiological data to remote clinicians. Designed to be fabricated anywhere in the world with minimal equipment, it can be operated by individuals without medical training.

We present a novel sensor system and interface that enables an individual to capture and reflect on their daily activities. The wearable system gathers both physiological responses and visual context through the use of a wearable biosensor and a cell-phone camera, respectively. Collected information is locally stored and securely transmitted to a novel digital mirror. Through interactive visualizations, this interface allows users to reflect not only on their outer appearance but also on their inner physiological responses to daily activities. Finally, we illustrate how combining a time record of physiological data with visual contextual information can improve and enhance the experience of reflection in many real-life scenarios, and serve as a useful tool for behavior science and therapy.

How can we better understand people’s emotional experiences with a product or service? Traditional interview methods require people to remember their emotional state, which is difficult. We use psychophysiological measurements such as heart rate and skin conductance to map people’s emotional changes across time. We then interview people about times when their emotions changed, in order to gain insight into the experiences that corresponded with the emotional changes. This method has been used to generate hundreds of insights with a variety of products including games, interfaces, therapeutic activities, and self-driving cars.

This project will define and explore a new research area we call Computational Behavior Science–integrated technologies for multimodal computational sensing and modeling to capture, measure, analyze, and understand human behaviors. Our motivating goal is to revolutionize diagnosis and treatment of behavioral and developmental disorders. Our thesis is that emerging sensing and interpretation capabilities in vision, audition, and wearable computing technologies, when further developed and properly integrated, will transform this vision into reality. More specifically, we hope to: (1) enable widespread autism screening by allowing non-experts to easily collect high-quality behavioral data and perform initial assessment of risk status; (2) improve behavioral therapy through increased availability and improved quality, by making it easier to track the progress of an intervention and follow guidelines for maximizing learning progress; and (3) enable longitudinal analysis of a child's development based on quantitative behavioral data, using new tools for visualization.

Sleep is critical to a wide range of biological functions; inadequate sleep results in impaired cognitive performance and mood, and adverse health outcomes including obesity, diabetes, and cardiovascular disease. Recent studies have shown that healthy and unhealthy sleep behaviors can be transmitted by social interactions between individuals within social networks. We investigate how social connectivity and light exposure influence sleep patterns and their health and performance. Using multimodal data collected from closely connected MIT undergraduates with wearable sensors and mobile phones, we will develop the statistical and multi-scale mathematical models of sleep dynamics within social networks based on sleep and circadian physiology. These models will provide insights into the emergent dynamics of sleep behaviors within social networks, and allow us to test the effects of candidate strategies for intervening in populations with unhealthy sleep behaviors.