Hugo Fuks

Wearable computing: accelerometers' data classification of body postures and movements

During the last 5 years, research on Human Activity Recognition (HAR) has reported on systems showing good overall recognition performance. As a consequence, HAR has been considered as a potential technology for e-health systems. Here, we propose a machine learning based HAR classifier. We also provide a full experimental description that contains the HAR wearable devices setup and a public domain dataset comprising 165,633 samples. We consider 5 activity classes, gathered from 4 subjects wearing accelerometers mounted on their waist, left thigh, right arm, and right ankle. As basic input features to our classifier we use 12 attributes derived from a time window of 150ms. Finally, the classifier uses a committee AdaBoost that combines ten Decision Trees. The observed classifier accuracy is 99.4%.

Qualitative activity recognition of weight lifting exercises

Research on activity recognition has traditionally focused on discriminating between different activities, i.e. to predict which activity was performed at a specific point in time. The quality of executing an activity, the how (well), has only received little attention so far, even though it potentially provides useful information for a large variety of applications. In this work we define quality of execution and investigate three aspects that pertain to qualitative activity recognition: specifying correct execution, detecting execution mistakes, providing feedback on the to the user. We illustrate our approach on the example problem of qualitatively assessing and providing feedback on weight lifting exercises. In two user studies we try out a sensor- and a model-based approach to qualitative activity recognition. Our results underline the potential of model-based assessment and the positive impact of real-time user feedback on the quality of execution.

Beauty tech nails: interactive technology at your fingertips

Looking for wearables that are fashionable, smart and augment human interaction, we introduce the term Beauty Technology as an emergent field in Wearable Computing. It is an on-body computing approach that turns non-invasive, wireless and without power required electromagnetic devices into beauty products for interacting with different surfaces and devices. This paper describes the materials and the prototyping process used in the making of Beauty Tech Nails exemplifying its application in everyday beauty products.

Beauty Technology: Body Surface Computing

As wearable technology assumes an increasingly important function in daily life, sensors and other electronic devices applied directly to the skin, in forms like artificial nails and makeup, might further revolutionize human experience.

Beauty technology as an interactive computing platform

Just blink and levitate objects, just move your fingernails and open the door. Chemically metalized eyelashes, RFID nails and conductive makeup are some examples of Beauty Technology products, an emergent field in Wearable Computers. Beauty Technology embedded electromagnetic devices into non-invasive beauty products that could be attached to the human body for interacting with different surfaces like water, clothes, the own wearers body and other objects, just blinking or even without touching any of these surfaces.

Collaborative museums: an approach to co-design

This paper describes a systemic approach to co-design of collaborative museums, using ethnography, co-creation workshops and fast prototyping, amongst other Social Science and Human Centered Design methods. Focused on the creation of immersive and collaborative museum experiences, it provides a rationale for involving carefully selected multidisciplinary teams and users in the entire design cycle, and presents a process that supports this task, from research to development, pointing its value and limitations. In order to bring the discussion into context and exemplify the use of a group of methods that can support collaborative design, it introduces the case of a Brazilian Planetarium and Science Museum.

FX e-Makeup for Muscle Based Interaction

Our aim with Beauty Technology is to transform our body in an interactive platform by hiding technology into beauty products for creating muscle based interfaces that don’t give the wearer a cyborg look. FX e-makeup is a Beauty Technology prototype that applies FX makeup materials embedded with electronics for sensing the face’s muscles. This work presents Winkymote and Kinisi as proof of concept of the FX e-makeup.

Hairware: The Conscious Use of Unconscious Auto-contact Behaviors

Beauty Technology is a wearable computing paradigm that uses the bodys surface as an interactive platform by integrating technology into beauty products applied directly to ones skin, fingernails and hair. Hairware is a Beauty Technology Prototype that connects chemically metalized hair extensions to a microcontroller turning it into an input device for triggering different objects. Hairware acts as a capacitive touch sensor that detects touch variations on hair and uses machine learning algorithms in order to recognize users intention. Normally, while someone touches her own hair, unconsciously she is bringing comfort to herself and at the same time is emitting a non-verbal message decodable by an observer. However, when she replays that touch on Hairware, she is not just emitting a message to an observer, because touching her hair would trigger an object, creating in this way, a concealed interface to different devices. Therefore, Hairware brings the opportunity to make conscious use of an unconscious auto-contact behavior. We present Hairwares hardware and software implementation.

Landmark identification with wearables for supporting spatial awareness by blind persons

This paper describes our research on feedback mechanisms of wearables for supporting indoor landmark identification in the context of blind pedestrians mobility. It contributes with a promising alternative to audible patterns, which are consistently related to the masking phenomenon. It also contributes with many lessons and insights that could benefit the designer of wearables for blind users. We started from an observational study followed by co-creation workshops with designers and potential users. The resulting prototypes were used in two Case Studies. The first study investigated the occurrence of masking, a problem caused by technology that affects negatively the sensorial perception of the wearer. The second study investigated the usefulness of the wearables for the identification of landmarks. The wearable succeeded in both tests for the particular context in which it was used.

Lessons Learned in the Design of Configurable Assistive Technology with Smart Devices

Assistive Technology (AT) aims at compensating for motor, sensory or cognitive functional limitations of its users. We report on a study with a single tetraplegic participant using AT that we have been developing for interaction with multiple devices in smart connected environments. We wanted to investigate a user’s reaction during his first encounter with this technology and to verify if needs and opportunities for AT configuration would emerge from study activities and interviews. Results show implicit and explicit configuration needs and opportunities suggesting that we must address both hardware and software configuration, some to be done by the end user, others by assistants. At this initial stage our contribution is to propose a structure for organizing the AT configuration problem space in order to support the design of similar technologies.