Gheorghe Sebestyen

eHealth solutions in the context of Internet of Things

The article analyzes the impact of “IoT - Internet of Things” on the design of new eHealth solutions. The authors aim to illustrate that the communication models, protocols and technologies promoted under the IoT concept have a great potential in the implementation of Internet-based healthcare systems. The experiments performed by the authors in the field of eHealth reveal some possible solutions, but also some open questions.

Data clustering-based anomaly detection in industrial control systems

Modern Networked Critical Infrastructures (NCI), involving cyber and physical systems, are exposed to intelligent cyber attacks targeting the stable operation of these systems. In order to ensure anomaly awareness, the observed data can be used in accordance with data mining techniques to develop Intrusion Detection Systems (IDS) or Anomaly Detection Systems (ADS). There is an increase in the volume of sensor data generated by both cyber and physical sensors, so there is a need to apply Big Data technologies for real-time analysis of large data sets. In this paper, we propose a clustering based approach for detecting cyber attacks that cause anomalies in NCI. Various clustering techniques are explored to choose the most suitable for clustering the time-series data features, thus classifying the states and potential cyber attacks to the physical system. The Hadoop implementation of MapReduce paradigm is used to provide a suitable processing environment for large datasets. A case study on a NCI consisting of multiple gas compressor stations is presented.

EtherCAT Protocol Implementation Issues on an Embedded Linux Platform

The paper presents the most important implementation issues of an industrial communication protocol, the EtherCAT (Ethernet control automation technology) protocol, on an embedded Linux platform. The authors underscore critical aspects (e.g. reliability, timeliness, predictability) concerning the use of an Ethernet-like protocol in an industrial environment

Distributed e-Health system with Smart Self-care Units

In order to assure remote monitoring of patients with chronic diseases and also to improve the responsiveness and quality of medical services a distributed eHealth system was designed. A key element of this system is the Smart Self-Care Unit (SSCU) that allows remote acquisition of medical data from patients treated or monitored at home. This unit is composed of a set of smart medical sensors and devices connected through a wireless network. The system assures mobility for the patients under observation and seamless transfer of medical data to the healthcare centers (hospitals, clinics, general practitioners, etc). The patients can interact remotely with medical personnel and may have access to medical services through a distributed, multiserver-based application. A number of autonomous medical applications (servers) deployed in every medical center cooperate in order to offer an integrated healthcare system. Medical information concerning patients enrolled in this system is exchanged between medical entities and self-care units. As part of this system a portal application offers a set of useful medical services such as: information about doctors, medical units and their services, secure storage of personal medical records, discussion forum for patients and doctors or statistical processing of recorded medical data.

Remote monitoring of patients with mobile healthcare devices

This paper describes a generic framework of a remote patient monitoring and treatment system as part of an e-Health system. The framework is composed of a set of mobile and wearable medical devices and a communication platform that assure real-time acquisition of medical data from patients placed in remote locations. The main contributions of the paper are: the modular and versatile design of the medical devices and the webservice based data transfer solution.

Ontology-based distributed health record management system

The paper presents the architecture of a distributed software system that manages patientspsila health records and assures remote and interactive access to medical services. In order to cover the complex relationships between different medical concepts (symptoms, diseases, treatment, medication, etc.) and also to include ldquointelligencerdquo in the software system an ontology-based approach was adopted. This solution together with the adoption of some widely accepted medical standards (e.g. HL7, LOINC, etc.) assure interoperability and transparent data exchange between various medical applications. The paper presents a distributed healthcare system model in which patients, doctors and software components interact in order to assure better medical services. The key factor in the implementation of this model is the extensive use of the domainpsilas ontology as the bases for database definition and medical data processing. In order to show the usefulness of the proposals as well as their effectiveness in electronic management of patientpsilas health records an experimental implementation of the proposed methodology is in work in the filed of cardio-vascular diseases.

Human activity recognition and monitoring for elderly people

Statistics show that the population in Europe is aging and in the near future human assistance for elderly persons will be prohibitive. This paper analyses the possibilities to implement a supervision system, which is capable of monitoring a persons activity in his/her home without violating intimacy. The main idea is to collect information from various sensors placed in house and on mobile devices and infer a most probable sequence of activities performed by the supervised person. A Hidden Markov chain method is adapted for the activity chain recognition.

Reservation-Based Data Flow Scheduling in Distributed Control Applications

Remote process control and supervision applications developed over the Internet require special communication models and techniques, which can guarantee the real-time and safety restrictions inherent to automation systems. This paper presents a communication model based on dataflow analysis and bandwidth reservation that offers a good control over the transmission time of critical data. As part of the model, an analytical method is proposed that allows a-priory evaluation of the required minimum bandwidth necessary to assure the fulfillment of real-time transmission restrictions. The model is based on the QoS facilities offered by the IPv6 protocol.

Hardware virtualization based security solution for embedded systems

We describe the implementation and the evaluation of a hypervisor level, hardware-enforced security solution suitable for the latest embedded platforms. Our solution is based on thin layer bare-metal hypervisor, a memory introspection engine and is validated on Silvermont microarchitecture based Intel x86 processors, running Windows. The approach is well suited to enhance the security of many POS and industrial embedded devices. We also present various kinds of attacks our solution defends against, and several remaining limitations.

Self-tuning Multimedia Streaming System on Cloud Infrastructure☆

Abstract In this paper we present an automatic performance tuning solution for the optimization of a high-demand multimedia streaming service built on a dedicated private cloud architecture. The optimization focuses mainly on two aspects: energy efficiency and quality assurance of streaming services. As QoS factors we take into consideration the minimum initial waiting time and the cumulative disruption time of continuous playing at the client side. To achieve the best performance, a cloud-based architecture is proposed with on-demand dynamic allocation of resources and a multi-level data flow with caching capabilities.