Active Assistance for Senior Healthcare: A Wearable System for Fall Detection

Elders lose independence and wellbeing, accompanied by decreased functions in terms of hearing, vision, strength and coordination abilities. These factors contribute to balance difficulties that eventually lead to falls. The injuries due to falls, at this age, are risky, since most of the times may cause a significant – and permanent – decrease of quality of life or, in extreme cases, death. In this context, a fall detection system can bring an added value to assist elderly people.This paper describes a system consisting of a wearable sensor unit, a smartphone and a website. When the sensor detects a fall it sends an alert using the smartphone via Bluetooth 4.0, to notify the family members or stakeholders. The sensor device includes an inertial unit, a barometer, and a temperature and humidity sensor. The website displays the log of previous falls and enables the configuration of emergency contact numbers. The proposed fall detection system is one of multiple components within a larger project under development that offers a holistic perspective on falls; the complete wearable solution will also feature, among others, physical protection (minimizing the impact of falls that occur).

People Detection and Tracking using Depth Camera

In this paper we present a method for real-time detection and tracking of people in video captured by a depth camera. For each object to be assessed, an ordered sequence of values that represents the distances between its center of mass to the boundary points is calculated. The recognition is based on the analysis of the total distance value between the above sequence and some pre-defined human poses, after apply the Dynamic Time Warping. This similarity approach showed robust results in people detection.

Automatic segmentation and 3D feature extraction of protein aggregates in Caenorhabditis Elegans

In the last years, it has become increasingly clear that neurodegenerative diseases involve protein aggregation, a process often used as disease progression readout and to develop therapeutic strategies. This work presents an image processing tool to automatic segment, classify and quantify these aggregates and the whole 3D body of the nematode Caenorhabditis Elegans. A total of 150 data set images, containing different slices, were captured with a confocal microscope from animals of distinct genetic conditions. Because of the animals’ transparency, most of the slices pixels appeared dark, hampering their body volume direct reconstruction. Therefore, for each data set, all slices were stacked in one single 2D image in order to determine a volume approximation. The gradient of this image was input to an anisotropic diffusion algorithm that uses the Tukey’s biweight as edge-stopping function. The image histogram median of this outcome was used to dynamically determine a thresholding level, which allows the determination of a smoothed exterior contour of the worm and the medial axis of the worm body from thinning its skeleton. Based on this exterior contour diameter and the medial animal axis, random 3D points were then calculated to produce a volume mesh approximation. The protein aggregations were subsequently segmented based on an iso-value and blended with the resulting volume mesh. The results obtained were consistent with qualitative observations in literature, allowing non-biased, reliable and high throughput protein aggregates quantification. This may lead to a significant improvement on neurodegenerative diseases treatment planning and interventions prevention

An approach for graphical user interface bad smells detection

In the context of an e ort to develop methodologies to support the evaluation of interactive system, this paper investigates an approach to detect graphical user interface bad smells. Our approach consists in detecting user interface bad smells through model-based reverse engineering from source code. Models are used to de ne which widgets are present in the interface, when can particular graphical user interface (GUI) events occur, under which conditions, which system actions are executed, and which GUI state is generated next.

Loneliness in Middle and Old Age

Purpose of the research: (a) To identify the degree of much loneliness reported in the Portuguese population over 50 years of age and (b) test whether loneliness can be predicted by socio-demographic, health related or social characteristic of the sample other than age. Materials and methods: 1174 late middle age and older adults were interviewed face to face by different interviewers across the country; after the informed consent was signed, we asked the participants several socio-demographic and health-related questions; finally we asked ‘‘How often do you feel lonely?’’ and participants responded according to a five point Likert scale. Principal results: The results showed that 12% of participants reporting feeling lonely often or always, whereas 40% reporting never feeling lonely. The remaining 48% self-reported they felt lonely seldom or sometimes. Additionally, results show that, when taken together, variables such as marital status, type of housing, residence settings, health conditions, social satisfaction, social isolation, lack of interest, transportation, and age were predictors of loneliness. Major conclusions: (1) The association of loneliness with advanced age has been greatly exaggerated by mass media and common sense; (2) But although our findings did not confirm the most alarmist views, the 12% of older adults reporting that they are feeling lonely always or often should be cause for attention and concern. It is necessary to understand the meaning, reasons and level of suffering implied on those feelings of loneliness. (3) Our findings suggest that it makes no sense to construe age as a singular feature or cause for feelings of loneliness. Instead, age and also a number of other features combine to predict feelings of loneliness. But even with our predictor variables there was a substantial of variance left unexplained. Therefore it is necessary to continue exploring how feelings of loneliness arise from the experience of living and how they can be changed.