Saso Koceski

Evaluation of an Assistive Telepresence Robot for Elderly Healthcare

In this paper we described the telepresence robot system designed to improve the well-being of elderly by supporting them to do daily activities independently, to facilitate social interaction in order to overcome a sense of social isolation and loneliness as well as to support the professional caregivers in everyday care. In order to investigate the acceptance of the developed robot system, evaluation study involved elderly people and professional caregivers, as two potential user groups was conducted. The results of this study are also presented and discussed.

General Assisted Living System Architecture Model

Novel information and communication technologies create possibilities to change the future of health care and support. Ambient Assisted Living (AAL) is seen as a promising alternative to the current care models so a number of researchers have developed AAL systems with promising results. The main goal of AAL solutions is to apply ambient intelligence technologies to enable people with specific needs to continue to live in their preferred environments. In this paper, we are presenting a general architecture of system for assisted living that supports most of the use cases for such system.

Towards a Patient-Centered Collaborative Health Care System Model

Recent advances in wireless sensor networks (WSN)technologies are enabling patient-centered, result oriented health care services, in the most cost-effective manner. Furthermore, technological advances are enabling a greater shift from institutional services to community-based services. The model of the collaborative health care system (COHESY) presented in this paper offers 24 hour monitoring of the condition of patients and the possibility of sending an emergency call for sudden deterioration of his medical condition. In addition, the system enables the patient (system user) to contact other people with similar condition and exchange their experience. This system improves the terms of home care treatment of the patient and also increases the medical capacity of the appropriate institutions. The result is significant reduction of the overall costs for patients and hospitals.

Suppression of Intensive Care Unit False Alarms Based on the Arterial Blood Pressure Signal

Patient monitoring in intensive care units requires collection and processing of high volumes of data. High sensitivity of sensors leads to significant number of false alarms, which cause alarm fatigue. Reduction of false alarms can lead to better reaction time of medical personnel. This paper aims to develop a method for false alarm suppression and evaluate it on a publicly available data set with manually annotated alarms. First, an automated feature engineering was performed using the signal for arterial blood pressure (ABP) and a processed signal that contained the times of each heartbeat from the ABP signal. Next, support vector machines, random forest, and extreme random trees classifiers were trained to create classification models. The best suppression performance was achieved for the extreme tachycardia alarm, for which 90.3% of the false alarms were suppressed, while only 0.54% of the true alarms were incorrectly suppressed. This paper demonstrates that alarm suppression can be achieved with high accuracy using an automated feature engineering coupled with machine learning algorithms. The proposed approach can be utilized as aid to medical personnel and experts, allowing them to be more productive and to respond to alarms in a more timely manner.

Evaluation of Health Care System Model Based on Collaborative Algorithms

The rapid development and use of information and communication technologies in the last two decades has influenced a dramatic transformation of public health and health care, changing the roles of the health care support systems and services. Recent trends in health care support systems are focused on developing patient-centric pervasive environments and the use of mobile devices and technologies in medical monitoring and health care systems [1].

Evaluating an Ordered List of Recommended Physical Activities within Health Care System

Information and communication technologies make it possible to bridge the gap and time barriers in the flow of health information and knowledge, allowing every involved part in the health process to have access to the information. This approach provides the knowledge of the individual to contribute effectively to the improvement in human health. But also, helps the collective knowledge effectively to solve health problems on individual level. In this paper we are evaluating the algorithm that generates recommendation for users. We are using simulations on generic data to see how different types of activities are affecting the accuracy of the algorithm. On the basis of the performed activities and blood glucose measurements, our recommendation algorithm should determine list of activities that have bigger influence on the change of the blood glucose levels. Generic data for our simulations are based on modeling of food intake and physical activity influence over the blood glucose level.

Game-based learning: educational game Azbuka to help young children learn writing Cyrillic letters

A working prototype for a mobile application called Azbuka is presented in this paper. The application is developed in a form of interactive educational game for mobile touch screen devices and is intended to help young children to learn writing Cyrillic letters. An important challenge during the research was the design of the graphical user interface (GUI) and game logic that should be acceptable, intuitive and easy to use for the target users i.e. children without previous training or technological experience. In order to investigate the application’s acceptance and its impact on children motivation for learning, the Azbuka application was evaluated in a real case scenario on a selected set of test users. The study results revealed that the children are highly motivated to learn writing Cyrillic using new technologies, which are quickly accepted and adopted.

Ubiquitous Computing in the context of developing countries

Ubiquitous computing is an ultra-interdisciplinary field. Because of its capacity to affect every sphere of human life, it is endowed with a wide range of characteristics and features. This paper attempts to describe the more salient and diverse features of Pervasive Computing in an organized manner that appreciates the multi-disciplinary nature of the field. Five categories: Setup, design, architecture, deployment and operations; interface; security; engineering and socio-economic; are used to systematically outline the current characteristics of Ubiquitous computing. Sample applications from the field of Ubicomp are also discussed to illustrate some of the characteristics of pervasive computing. Moreover, we have also tried to highlight the challenges and opportunities for implementing Pervasive Computing in the context of developing countries.

Gesture Control of a Mobile Robot using Kinect Sensor

This paper describes a methodology for gesture control of a custom developed mobile robot, using body gestures and Microsoft Kinect sensor. The Microsoft Kinect sensor’s ability is to track joint positions has been used in order to develop software application gestures recognition and their mapping into control commands. The proposed methodology has been experimentally evaluated. The results of the experimental evaluation, presented in the paper, showed that the proposed methodology is accurate and reliable and it could be used for mobile robot control in practical applications.

Context-aware Technologies and Systems

The move from traditional desktop computing environment to ubiquitous and mobile computing have brought to the front Context-aware applications which are capable of providing appropriate information and services to the user depending upon the computational/user context. This paper attempts to discuss the concept of Context-awareness from functionality perspective. The components and characteristics of Context-aware systems are identified and described in terms of the requirements expected from other applications. The different architectural approaches used in the envisioning of context-aware systems are presented to highlight the functionalities and quality concerns which dictate their choice. Moreover, Context-aware frameworks and middleware which facilitate the efficient development of Context-aware applications are highlighted as instantiations of various architectural styles. Finally, the paper highlights the importance of context-awareness for pervasive computing by discussing sample applications in diverse fields of education, health and tourism.