Laura M. Roa

Distributed intelligent architecture for falling detection and physical activity analysis in the elderly

A novel approach for the detection of falls, the analysis of body postures, mobility and metabolic energy expenditure of elderly people has been developed. It is based on a distributed intelligence architecture, supported by it wireless personal area network (WPAN) which allows a full 24-hour supervision of the user, both indoor and outdoor home. An open design methodology lets the addition of new sensors for the on-line monitorization or other biosignals. In this paper general guidelines and design issues are reported, with special emphasis on the Intelligent Accelerometer Unit (IAU), based on a four-axis accelerometer, the signals of which are transmitted to the WPAN server (PSE) for on-line processing. The availability of three axis in the median plane provides an inclination measurement with high sensibility. The IAU can be worn like a patch, fixed to the back, at the height of the sacrum. A prototype of the IAU is currently under validation phase, in order to optimize signal transmission between IAU and PSE.

Preliminary evaluation of a full-time falling monitor for the elderly

The article presents the early outcomes of the evaluation of an intelligent accelerometer unit (IAU) utilized for detecting the falling events of elderly people . The overall design of the monitor where the IAU is integrated is briefly exposed. The outcomes of a laboratory study carried out over 8 volunteers show that the device is able to distinguish true falling events from normal activities like fast walking or going up/downstairs. The influences of the subject and the environment have been taken into account profiting from the processing capacity of the monitor distributed architecture.

A Comprehensive Study Into Intrabody Communication Measurements

One of the main objectives of research into intrabody communication (IBC) is the characterization of the human body as a transmission medium for electrical signals. However, such characterization is strongly influenced by the conditions under which the experiments are performed. In addition, the outcomes reported in the literature vary according to the measurement method used, frequently making comparisons among them unfeasible. Further studies are still required in order to establish a methodology for IBC characterization and design. In this paper, both galvanic and capacitive coupling setups have been implemented and a comprehensive set of measurements has been carried out by analyzing fundamental IBC parameters such as optimum frequency range, maximum channel length, and type of electrodes, among others. Consequently, practical conclusions regarding the experimental conditions that optimize IBC performance for each coupling technique have been obtained.

Design and Implementation of a Distributed Fall Detection System—Personal Server

In this paper, the main results related to a fall detection system are shown by means of a personal server for the control and processing of the data acquired from multiple intelligent biomedical sensors. This server is designed in the context of a telehealthcare system for the elderly, to whom falls represent a high-risk cause of serious injuries, and its architecture can be extended to patients suffering from chronic diseases. The main design issues and developments in terms of the server hardware and software are presented with the aim of providing a real-time analysis of the processed biosignals. As a result, the evaluation study of the implemented algorithm for fall detection through a set of laboratory experiments is presented, together with some important issues in terms of the devices consumption. The proposed algorithm exhibits excellent outcomes in fall detection.

Digital imaging in remote diagnosis of burns

Images are capable of giving an accurate representation of skin color and have been used extensively in teaching about and researching burn therapy. The advance from analogue to digital imaging allows the remote transmission of the clinical information contained in the digital image of a burn, using a suitable system. The large size of these image files reduces transmission speed and makes data compression desirable. Compression, by means of the JPEG algorithm, of up to 50 times the original size of 38 digital images of burns suffered by 22 consecutive patients did not lessen its great usefulness in determining the depth of burn injuries, according to a group of experts in burn care. The success rate was close to 90%, both for non-compressed images in original BMP format (mean size:1500 Kb) and for compressed images with a Q index of 50 (30 Kb files), when compared with the clinical diagnoses confirmed one week after the accident.

Distributed Circuit Modeling of Galvanic and Capacitive Coupling for Intrabody Communication

Modeling of intrabody communication (IBC) entails the understanding of the interaction between electromagnetic fields and living tissues. At the same time, an accurate model can provide practical hints toward the deployment of an efficient and secure communication channel for body sensor networks. In the literature, two main IBC coupling techniques have been proposed: galvanic and capacitive coupling. Nevertheless, models that are able to emulate both coupling approaches have not been reported so far. In this paper, a simple model based on a distributed parameter structure with the flexibility to adapt to both galvanic and capacitive coupling has been proposed. In addition, experimental results for both coupling methods were acquired by means of two harmonized measurement setups. The model simulations have been subsequently compared with the experimental data, not only to show their validity but also to revise the practical frequency operation range for both techniques. Finally, the model, along with the experimental results, has also allowed us to provide some practical rules to optimally tackle IBC design.

SoM: A Smart Sensor for Human Activity Monitoring and Assisted Healthy Ageing

This paper presents the hardware and software design and implementation of a low-cost, wearable, and unobstructive intelligent accelerometer sensor for the monitoring of human physical activities. In order to promote healthy lifestyles to elders for an active, independent, and healthy ageing, as well as for the early detection of psychomotor abnormalities, the activity monitoring is performed in a holistic manner in the same device through different approaches: 1) a classification of the level of activity that allows to establish patterns of behavior; 2) a daily activity living classifier that is able to distinguish activities such as climbing or descending stairs using a simple method to decouple the gravitational acceleration components of the motion components; and 3) an estimation of metabolic expenditure independent of the activity performed and the anthropometric characteristics of the user. Experimental results have demonstrated the feasibility of the prototype and the proposed algorithms.

How technology is empowering patients? A literature review.

The term ‘Patient Empowerment’ (PE) is a growing concept – so in popularity as in application – covering situations where citizens are encouraged to take an active role in the management of their own health. This concept is serving as engine power for increasing the quality of health systems, but a question is still unanswered, ‘how PE will be effectively achieved?’ Beyond psychological implications, empowerment of patients in daily practice relies on technology and the way it is used. Unfortunately, the heterogeneity of approaches and technologies makes difficult to have a global vision of how PE is being performed.

Segmentation and classification of burn images by color and texture information

In this paper, a burn color image segmentation and classification system is proposed. The aim of the system is to separate burn wounds from healthy skin, and to distinguish among the different types of burns (burn depths). Digital color photographs are used as inputs to the system. The system is based on color and texture information, since these are the characteristics observed by physicians in order to form a diagnosis. A perceptually uniform color space (L*u*v*) was used, since Euclidean distances calculated in this space correspond to perceptual color differences. After the burn is segmented, a set of color and texture features is calculated that serves as the input to a Fuzzy-ARTMAP neural network. The neural network classifies burns into three types of burn depths: superficial dermal, deep dermal, and full thickness. Clinical effectiveness of the method was demonstrated on 62 clinical burn wound images, yielding an average classification success rate of 82%.

Study of Attenuation and Dispersion Through the Skin in Intrabody Communications Systems

Intrabody communication (IBC) is a technique that uses the human body as a transmission medium for electrical signals to connect wireless body sensors, e.g., in biomedical monitoring systems. In this paper, we propose a simple, but accurate propagation model through the skin based on a distributed-parameter circuit in order to obtain general expressions that could assist in the design of IBC systems. In addition, the model is based on the major electrophysiological properties of the skin. We have found the attenuation and dispersion parameters and they have been successfully compared with several published results, thus showing the tuning capability of the model to different experimental conditions. Finally, we have evaluated different digital modulation schemes in order to assess the tradeoffs between symbol rate, bit error rate, and distance between electrodes of the skin communication channel.