Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction:a review

Support Vector Machines (SVMs) are widely used classifiers for detecting physiological patterns in Human-Computer Interaction (HCI). Their success is due to their versatility, robustness and large availability of free dedicated toolboxes. Frequently in the literature, insufficient details about the SVM implementation and/or parameters selection are reported, making it impossible to reproduce study analysis and results. In order to perform an optimized classification and report a proper description of the results, it is necessary to have a comprehensive critical overview of the application of SVM. The aim of this paper is to provide a review of the usage of SVM in the determination of brain and muscle patterns for HCI, by focusing on electroencephalography (EEG) and electromyography (EMG) techniques. In particular, an overview of the basic principles of SVM theory is outlined, together with a description of several relevant literature implementations. Furthermore, details concerning reviewed papers are listed in tables, and statistics of SVM use in the literature are presented. Suitability of SVM for HCI is discussed and critical comparisons with other classifiers are reported.

Peer interaction in mixed age groups: a study in the computer area of an early childhood education center in Portugal

The study was developed as a teacher-research project during initial teacher education – Masters Degree of Early Childhood and Primary Education, in Portugal. It analysed the interactions between children of 3 to 6 years old, during the use of the computer as a free choice activity, confronting situations between peers of the same age and situations between peers of different ages. The focus of the analysis was the collaborative interactions. This was a qualitative study. Children could choose the computer, amongst other interest areas, and work for around an hour in pairs. In the computer, children used mainly educational games. During four weeks, the interactions between the pairs were audio recorded. Field notes and informal interviews to the children were also used to collect data. Eleven children were involved in the study with ages ranging from 3 to 6 years old. Baseline data on children’s basic computer proficiency was collected using the Individualized Computer Proficiency Checklist (ICPC) by Hyun. The recorded interactions were analysed using the types of talk offered by Scrimshaw and Perkins and Wegerif and Scrimshaw: cumulative talk, exploratory talk, disputational talk, and tutorial talk. This framework was already used in a study in an early childhood education context in Portugal by Amante. The results reveal differences in computer use and characterize the observed interactions. Seven different pairs of children's interactions were analysed. More than a third of the interactions were cumulative talk, followed by exploratory talk, tutorial talk and disputational talk. Comparing same and mixed age pairs, we observed that cumulative talk is the more present interaction, but in same age pairs this is followed by exploratory talk whereas in the mixed age pairs it is tutorial talk that has the second largest percentage. The pairs formed by the children were very asymmetrical in terms of age and computer proficiency. This lead to the more tutorial interactions, where one children showed the other or directed him/her on how to play. The results show that collaboration is present during the use of a computer area in early childhood education. The free choice of the children means the adults can only suggest pairing suited to specific interactions between the children. Another way to support children in more exploratory talk interactions could be by discussing the way the older children can help the younger ones beyond directing or correcting their work.

A service-oriented user interaction analysis framework supporting adaptive applications

A comprehensive user model, built by monitoring a user's current use of applications, can be an excellent starting point for building adaptive user-centred applications. The BaranC framework monitors all user interaction with a digital device (e.g. smartphone), and also collects all available context data (such as from sensors in the digital device itself, in a smart watch, or in smart appliances) in order to build a full model of user application behaviour. The model built from the collected data, called the UDI (User Digital Imprint), is further augmented by analysis services, for example, a service to produce activity profiles from smartphone sensor data. The enhanced UDI model can then be the basis for building an appropriate adaptive application that is user-centred as it is based on an individual user model. As BaranC supports continuous user monitoring, an application can be dynamically adaptive in real-time to the current context (e.g. time, location or activity). Furthermore, since BaranC is continuously augmenting the user model with more monitored data, over time the user model changes, and the adaptive application can adapt gradually over time to changing user behaviour patterns. BaranC has been implemented as a service-oriented framework where the collection of data for the UDI and all sharing of the UDI data are kept strictly under the user's control. In addition, being service-oriented allows (with the user's permission) its monitoring and analysis services to be easily used by 3rd parties in order to provide 3rd party adaptive assistant services. An example 3rd party service demonstrator, built on top of BaranC, proactively assists a user by dynamic predication, based on the current context, what apps and contacts the user is likely to need. BaranC introduces an innovative user-controlled unified service model of monitoring and use of personal digital activity data in order to provide adaptive user-centred applications. This aims to improve on the current situation where the diversity of adaptive applications results in a proliferation of applications monitoring and using personal data, resulting in a lack of clarity, a dispersal of data, and a diminution of user control.

Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences

Fully articulated hand tracking promises to enable fundamentally new interactions with virtual and augmented worlds, but the limited accuracy and efficiency of current systems has prevented widespread adoption. Today's dominant paradigm uses machine learning for initialization and recovery followed by iterative model-fitting optimization to achieve a detailed pose fit. We follow this paradigm, but make several changes to the model-fitting, namely using: (1) a more discriminative objective function; (2) a smooth-surface model that provides gradients for non-linear optimization; and (3) joint optimization over both the model pose and the correspondences between observed data points and the model surface. While each of these changes may actually increase the cost per fitting iteration, we find a compensating decrease in the number of iterations. Further, the wide basin of convergence means that fewer starting points are needed for successful model fitting. Our system runs in real-time on CPU only, which frees up the commonly over-burdened GPU for experience designers. The hand tracker is efficient enough to run on low-power devices such as tablets. We can track up to several meters from the camera to provide a large working volume for interaction, even using the noisy data from current-generation depth cameras. Quantitative assessments on standard datasets show that the new approach exceeds the state of the art in accuracy. Qualitative results take the form of live recordings of a range of interactive experiences enabled by this new approach.

Aplicación del modelo Discovering Hands en Argentina

Discovering Hands (DH) es un proyecto que nace en Alemania en el 2006, liderado por el doctor Frank Hoffmann. El programa se desarrolla pensando en el importante problema de salud pública en el cual se ha convertido en el cáncer de mama, pues según la Organización Mundial de la Salud es el mayor causal de muerte en mujeres, tanto en países desarrollados como en vía de desarrollo, y en Alemania esta enfermedad acaba con la vida de aproximadamente 18.000 mujeres cada año. (The Global Journal, 2014) DH entrena y capacita mujeres visualmente impedidas para detectar de manera temprana los signos de cáncer de mama, dado que estas poseen un sentido del tacto más desarrollado que el de una persona que no se encuentre limitada visualmente. Esto les permite localizar el cáncer de forma más rápida que un médico general ya que son capaces de identificar los tumores más pequeños, logrando así reducir notablemente los costos totales del tratamiento de esta enfermedad. Adicional a esto, el capacitar y preparar a mujeres con discapacidad visual para la detección temprana de cáncer de mama, incrementa la fuerza laboral del país, pues estas mujeres pasarían a ser parte de la población económicamente activa del mismo (PEA) y lograrían que las personas dejen de percibir esta condición como una discapacidad y por el contrario la vean como una ventaja. Después de unos años de prueba, el programa ha sido mejorado y extendido tanto en Alemania como en otros países (Austria), razón por la cual se realizó el estudio de factibilidad del proyecto en países como Colombia - donde se quiere llevar a cabo un proyecto piloto en la ciudad de Cali - México y Argentina. El presente trabajo se enfoca en Argentina, por medio del cual se busca proponer aportes para disminuir las causas de muertes originadas por esta enfermedad y los altos costos que estas le generan al sector de la salud de este país. Con el estudio se logró identificar la factibilidad de la implementación del modelo de negocio, evidenciando que Argentina cuenta con unas particularidades en su sistema de gobierno que pueden hacer que la puesta en práctica del proyecto sea más compleja que en otros países.

Data privacy in interoperability environments – a case study in the Portuguese healthcare sector

Data sharing between organizations through interoperability initiatives involving multiple information systems is fundamental to promote the collaboration and integration of services. However, in terms of data, the considerable increase in its exposure to additional risks, require a special attention to issues related to privacy of these data. For the Portuguese healthcare sector, where the sharing of health data is, nowadays, a reality at national level, data privacy is a central issue, which needs solutions according to the agreed level of interoperability between organizations. This context led the authors to study the factors with influence on data privacy in a context of interoperability, through a qualitative and interpretative research, based on the method of case study. This article presents the final results of the research that successfully identifies 10 subdomains of factors with influence on data privacy, which should be the basis for the development of a joint protection program, targeted at issues associated with data privacy.

An investigation of contact transmission of methicillin-resistant staphylococcus aureus

Hand hygiene is critical in the healthcare setting and it is believed that methicillin-resistant Staphylococcus aureus (MRSA), for example, is transmitted from patient to patient largely via the hands of health professionals. A study has been carried out at a large teaching hospital to estimate how often the gloves of a healthcare worker are contaminated with MRSA after contact with a colonized patient. The effectiveness of handwashing procedures to decontaminate the health professionals' hands was also investigated, together with how well different healthcare professional groups complied with handwashing procedures. The study showed that about 17% (9–25%) of contacts between a healthcare worker and a MRSA-colonized patient results in transmission of MRSA from a patient to the gloves of a healthcare worker. Different health professional groups have different rates of compliance with infection control procedures. Non-contact staff (cleaners, food services) had the shortest handwashing times. In this study, glove use compliance rates were 75% or above in all healthcare worker groups except doctors whose compliance was only 27%.