Before automobiles were invented and widely adopted, animals like horses were the most common mode of transportation. While this change brought significant improvements in terms of reliability and efficiency, it also removed a core component: the emotional relationship that existed between the person and the animal. While largely ignored, the emotional states of drivers are quite important, as they influence not only driving behavior but also the safety of all road users. For instance, driving can be quite an emotionally stressful experience and, while certain amounts of stress help the driver to remain alert and attentive, too much or too little can negatively impact driving performance and safety. Furthermore, stress in large doses has been linked to a large array of adverse health conditions such as depression and various forms of cardiovascular disease.

Occupational stress can be described as a harmful emotional and physical response that occurs when high demanding job conditions cannot be met by the resources of the worker. This type of stress is usually associated with feelings of frustration, anger, and fear and can lead to dissatisfaction and lack of motivation in the long-term. Furthermore, high levels of stress can impair decision making, decrease productivity, and lead to high amounts of accidents and job absenteeism. Despite the well-studied negative outcomes, workplace stress is still considered a necessary evil by many people as it helps us keep up with the pace of modern society. Leveraging state-of-the-art sensing technologies and AI, this project seeks to advance the measurement, understanding, and management of stress in real-life settings.

Pervasive physiological monitoring offers the possibility of better capturing the health condition of people. This information is not only useful to help inform medical diagnosis, but also to help track chronic health conditions and therapeutic interventions as well as understanding the emotional state of people. While great strides have been made to provide comfortable physiological monitoring, traditional methods still require attaching electrodes to the skin, buying expensive custom-made hardware, and/or interrupting daily activity to collect measurements. Moreover, these sensors tend to measure a limited set of metrics at a time. In contrast, Global Vitals offers an alternative solution that provides accurate, low-cost and comfortable multi-physiological parameter with the goal of democratizing physiological sensing.

Epidermal sensing has enabled significant advancements towards the measurement and understanding of health. Most of the existing medical instruments require direct expert manipulation of a doctor, measure a single parameter, and/or have limited sensing coverage. In contrast, this work demonstrates the first epidermal robot with the ability to move over the surface of the skin and capture a large range of body parameters. In particular, we developed SkinBot, a 2x4x2 centimeter-size robot that moves over the skin surface with a two-legged suction-based locomotion. We demonstrate three of the potential medical sensing applications which include the measurement of body biopotentials (e.g., electrodermal activity, electrocardiography) through modified suction cups that serve as electrodes, skin imaging through a skin-facing camera that can capture skin anomalies, and inertial body motions through a 6-axis accelerometer and gyroscope that can capture changes of body posture and subtle cardiorespiratory vibrations.

This work introduces a novel wearable olfactory display that provides just-in-time release of scents based on the physiological state of the wearer. The device can release up to three scents and passively captures subtle chest vibrations associated with the beating of the heart and respiration through clothes. BioEssence is controlled via a custom-made smartphone app that allows the creation of physiological rules to trigger different scents (e.g., when the heart rate is above 80 beats per minute, release lavender scent). The device is wireless and lightweight, and it is designed to be used during daily life, clipped on clothes around the sternum area or used as a necklace. We provide a description of the design and implementation of the prototype and potential use cases in the context of mental wellbeing.

What if you could see what calms you down or increases your stress as you go through your day? What if you could see clearly what is causing these changes for your child or another loved one? People could become better at accurately interpreting and communicating their feelings, and better at understanding the needs of those they love. This project explores the possibilities of integrating biosensing technologies with Google Glass to enable fundamental advances for Affective Computing research in real-life settings. The first prototype enables people to see and respond to their autonomic stress in new ways with the ultimate goal of increasing (self-)awareness and improving regulation of stress in daily life.

Recognizing when computer users are stressed can help reduce their frustration and prevent a large variety of negative health conditions associated with chronic stress. However, measuring stress non-invasively and continuously at work remains an open challenge. This work explores the possibility of using a pressure-sensitive keyboard and a capacitive mouse to discriminate between stressful and relaxed conditions in a laboratory study.

MIT Mood Meter is designed to assess and display the overall mood of the MIT community, by placing cameras at four different prime spots on the MIT campus. The cameras are equipped with affect-sensing software that counts number of people and whether they are smiling or not. This project is intended to raise awareness of how our own smiles can positively affect the surrounding environment, and to assess how congenial MIT is as a community. The dynamic, real-time information may lead to answers to questions such as: “Are people from one department happier than others?”, “Do midterms lower the mood?”, or “Does warmer weather lead to happiness?”

With the recent development of wearable and comfortable biosensors, larger datasets of physiological data are being collected in challenging real-life scenarios. In order to gain insight from these datasets, behavioral scientists need tools that enable agile and efficient data exploration. In this work, we designed and implemented two visualization tools for large-scale time-based datasets, and combined the lessons learned to create a more general-purpose tool.

This project presents 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.

This work studies the feasibility of using visual information to automatically measure the engagement level of TV viewers. Previous studies usually utilize expensive and invasive devices (e.g., eye trackers or physiological sensors) in controlled settings. This work differs by only using an RGB video camera in a naturalistic setting, where viewers move freely and respond naturally and spontaneously.

People diagnosed with Autism Spectrum Disorders (ASD) often have challenging behaviors (CBs), such as self-injury or property destruction, which negatively impacts their quality of life as well as that of those around them. Recent advances in mobile and ubiquitous technologies provide an opportunity to efficiently and accurately capture such behavioral information. The ability to obtain this type of data will help with both intervention and behavioral phenotyping efforts. With the collaboration of behavioral scientists and therapists, we identified the main design requirements and created an easy-to-use mobile application for collecting, labeling, and sharing in-situ CB data in individuals diagnosed with ASD.

This project will define and explore a new research area we call Computational Behavior Science. More specifically, we hope to: (1) Enable widespread screening of autism by allowing non-experts to easily collect high-quality behavioral data and perform an 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.

Understanding if a movement is being executed correctly is important to a number of manipulation tasks. We present a preliminary study using inertial measurement units (IMUs) to evaluate the correct execution of squash swings, as well as discriminating them from similar racquet sport swings such as tennis and badminton. Additionally, we show some preliminary results that suggest that it is possible to detect at what point in time the movement was done incorrectly and why.

This project is funded by The Defense Advanced Research Projects Agency (DARPA) and seeks to create a "smart" computer that captures and evaluates ways in which expert users perform certain tasks. The computer then uses this knowledge in order to increase the productivity of non-expert users performing the same tasks.

The aim of this project is to develop an expert system capable of recognizing gunshots in audio files. We explore different types of audio features (e.g. Fast Fourier Transform, RASTA PLP) that are capable of characterizing the acoustic signatures of gunshots such as N-wave. Moreover, we compare the performance of Hidden Markov Models and Support Vector Machines.

Standard ensemble methods do not explicitly consider the performance of experts to be variable across the problem domain. In contrast, this work proposes Specialized Weighted Majority. Specialists for each area of the feature space are created by augmenting experts with a classifier that chooses on which samples to vote.

The hot flash is a sensation ranging from warmth to intense heat around the face, head, and neck. Populations experiencing hot flashes include male and female cancer patients, and most notably, women transitioning through menopause. Hot flashes are associated with impairments in quality of life and increased treatment seeking, and include contributions of both psychological and physiological factors in their experience and reporting. The goal of this project is to research temporal classifiers to predict hot flashes using several physiological measures (e.g. skin conductance, skin temperature, heat flux) and to understand which of the physiological factors are the most informative.

Complex knee injuries are common, often resulting from multiple forces (e.g. rotational, varus-valgus loading, anterior/posterior displacement). Identification of the specific injury pattern of the ACL (Anterior Cruciate Ligament) and other knee structures using non-invasive methods may improve pre-operative planning and guide treatment, reducing costs and facilitating high quality patient care. The main goal of this project is to present a classification system based on a set of non-invasive measures and state-of-the-art Machine Learning techniques to preempt the exact ACL rupture pattern. Standard classification techniques as Support Vector Machines (SVM) and Genetics Algorithms are combined for this purpose.

The purpose of this work is to explore the use of Conditional Random Fields (CRFs) in the automatic recognition of the basic units of facial expression (aka. Action Units). Facial expression recognition is a complex problem aggravated by variability between the subjects and variability in the dynamics of expression. The discriminative nature of CRFs and their ability to capture temporal dependencies makes them well suited to tackle these two difficulties. To aid the recognition of subtle expressions, a combination of shape and appearance features is used.

This work intends to develop a new kernel-based algorithm for horse recognition. The intuition behind this approach is that each horse has a set of distinctive features which may be different from other horses such as facial markings or color. With a unique structured sparse regularization, the proposed algorithm can be formulated as a non-smooth convex optimization problem.

Identifying facial features (e.g. eye corners) on images is an important task for many computer vision applications like face recognition, facial expression recognition, tracking, and 3D face modeling from 2D images. Some of the current methods to detect facial keypoints are based on sophisticated classifiers. This project proposes a purely data-driven approach based on template matching. The novelty of this method is finding a final template which will be a linear combination of other templates.

This project aims to perform transparent object segmentation on cluttered environments from a sequence of images. The main idea is that standard algorithms such as MeanShift do not perform well with transparent objects due to their properties. Because of that, we use standard algorithms to detect possible outliers and find the transparent object.

This project aims to develop a customized solution for managing the human resources of the 'Research Group in Intelligent Systems' from Ramon Llull University. With the objective of facilitating access to the application by all of its members, this project proposes a client-server implementation using LAMP (Linux + Apache + MySql + PhP). This project became my B.S thesis and earned an A with honors.