The remote monitoring of the elderly and patients with diseases that promote physical weakness are a relevant trend in healthcare. This work presents a smartphone based tool to assist these people, which is capable for detecting a fall of monitored patient and to alert the responsible, enabling an agile medical assistance. Moreover, we analyzed and implemented machine learning algorithms to increase the accuracy of the monitoring process, in order to avoid false alarms and fall detection misses. The initial results show that the selected algorithms provide better results than models based on smartphone's accelerometer upper and lower thresholds to trigger the fall alarms, which are the main approaches observed in the literature.

Nowadays, the importance of mental health has become an increasinglyrelevant theme. Psychological assessments are part of thedaily life of clinical psychologists in order to identify possible issuesto be explored. Therefore, this work presents a preliminarystudy which aims to evaluate the accuracy of machine learningalgorithms for the detection of the predominant factor of big fivepersonality test. Real answers from a dataset were considered in thecomputational experiments, and two machine learning algorithmswere evaluated: the K-Nearest Neighbors (KNN) and the K-means.Results show that both algorithms could accurately detect the pedominantfactor of the big five test, and KNN obtained better resultsthan the other algorithm.

Nowadays depression is a relevant issue due the high level of stressobserved even in students and young people. Moreover, the detectionof the depression symptons is a complex task, since eachperson has different behaviors and reactions in these scenarios. Thiswork address the detection of depression symptoms using chatbotsbased on machine learning algorithms. The use of chatbots enablesa smooth approach for shy and introspective people, whose donot feel comfortable for talking to parents, psychologists or medicalprofessionals in general. To this end, an App for smart-phoneis proposed in order to perform a talk with a person, and verifyif some depression symptoms are observed based using machinelearning algorithms. The initial results show that the proposedmodel has a good accuracy on simulated scenarios, where basictalks are performed by the chatbot.

Nos dias atuais, em grande parte dos ambientes educacionais, o processo de comunicação com os alunos é realizada de forma ad hoc, com baixa padronização e pouca interação entre as partes. Entretanto, uma comunicação mais dinâmica é demandada pelo perfil jovem da maior parte dos alunos. Desta forma, os dispositivos móveis apresentam-se como um canal eficiente e flexível de atingir esse público. Nesse cenário, apresentamos uma plataforma ubíqua e pervasiva para prover a distribuição de conteúdo educacional utilizando um modelo sensível a contexto. Assim, a plataforma pode atender às demandas específicas informadas pelo usuário, e também reagir ao contexto atual do mesmo, enviando conteúdos personalizados conforme aspectos pré-definidos como localização, perfil, dentre outros.

No abstract