Dimitrios K. Lymberopoulos

A New Framework Architecture for Next Generation e-Health Services

The challenge for fast and low-cost deployment of ubiquitous personalized e-Health services has prompted us to propose a new framework architecture for such services. We have studied the operational features and the environment of e-Health services and we led to a framework structure that extends the European Telecommunications Standards Institute (ETSI)/Parlay architecture, which is used for the deployment of standardized services over the next generation IP networks. We expanded the ETSI/Parlay architecture with new service capability features as well as sensor, profiling, and security mechanisms. The proposed framework assists the seamless integration, within the e-Health service structure, of diverse facilities provided by both the underlying communication and computing infrastructure as well as the patients bio and context sensor networks. Finally, we demonstrate the deployment of a telemonitoring service in smart home environment based on the proposed framework architecture.

Improving EMG based classification of basic hand movements using EMD

This paper presents a pattern recognition approach for the identification of basic hand movements using surface electromyographic (EMG) data. The EMG signal is decomposed using Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs) and subsequently a feature extraction stage takes place. Various combinations of feature subsets are tested using a simple linear classifier for the detection task. Our results suggest that the use of EMD can increase the discrimination ability of the conventional feature sets extracted from the raw EMG signal.

Medical disease prediction using Artificial Neural Networks

This study examines a variety of artificial neural network (ANN) models in terms of their classification efficiency in an orthopedic disease, namely osteoporosis. Osteoporosis risk prediction may be viewed as a pattern classification problem, based on a set of clinical parameters. Multilayer perceptrons (MLPs) and probabilistic neural networks (PNNs) were used in order to face the osteoporosis risk factor prediction. This approach is the first computational intelligence technique based on ANNs for osteoporosis risk study on Greek population. MLPs and PNNs are both feed-forward networks; however, their modus operandi is different. Various MPL architectures were examined after modifying the number of nodes in the hidden layer, the transfer functions and the learning algorithms. Moreover, PNNs were implemented with spread values ranging from 0.1 to 50, and 4 or 2 neurons in output layer, according to coding of osteoporosis desired outcome. The obtained results lead to the conclusion that the PNNs outperform to MLPs, thus they are proved as appropriate computation intelligence technique for osteoporosis risk factor prediction. Furthermore, the overfitting problem was more frequent to MLPs, contrary to PNNs as their spread value increased. The aim of proposed PNN is to assist specialists in osteoporosis prediction, avoiding unnecessary further testing with bone densitometry.

WADA Service: An Extension of DICOM WADO Service

The Web Access to Digital Imaging and Communication in Medicine (DICOM) Persistent Objects (WADO) service is standardized as the Web extension to DICOM. This paper analyzes the operational specifications of the WADO service and extends its access capability to the whole DICOM hierarchy (patient, study, series, and object). The proposed Web Access to DICOM Archives (WADA) service, as opposed to WADO, also includes an extrainternal query mechanism and support of medical reports submission. A pilot implementation of WADA as software components and their integration into a three-tier architecture are also presented. Advanced security mechanisms are augmented to ensure communication encryption, user identification, and access restriction to data according to user roles. The proposed service is a simple approach, and can be embedded in any system managing medical images and reports. WADA can also be integrated into the Cross-Enterprise Document Sharing-Imaging (XDS-I) standard, which is considered to be the most likely future standard for medical imaging exchange.

e-SCP-ECG+ protocol: an expansion on SCP-ECG protocol for health telemonitoring—pilot implementation

Standard Communication Protocol for Computer-assisted Electrocardiography (SCP-ECG) provides standardized communication among different ECG devices and medical information systems. This paper extends the use of this protocol in order to be included in health monitoring systems. It introduces new sections into SCP-ECG structure for transferring data for positioning, allergies, and five additional biosignals: noninvasive blood pressure (NiBP), body temperature (Temp), Carbon dioxide (CO2), blood oxygen saturation (SPO2), and pulse rate. It also introduces new tags in existing sections for transferring comprehensive demographic data. The proposed enhanced version is referred to as e-SCP-ECG+ protocol. This paper also considers the pilot implementation of the new protocol as a software component in a Health Telemonitoring System.

Group profile management in ubiquitous healthcare environment

Nowadays, ubiquitous healthcare is of utmost importance in the patient-centric model. Furthermore, the personalization of ubiquitous healthcare services plays a very important role to make the patient-centric model a reality. The personalization of the ubiquitous healthcare services is based on the profiles of the entities participating in these services. In this paper, we propose a group profile management system in a ubiquitous healthcare environment. The proposed system is responsible for the dynamic creation of a group profile and its management.

Monitoring of patients suffering from special phobias exploiting context and profile information

Context acquisition and active context construction is key to delivering personalized services and ubiquitous medical treatment to patients suffering from special phobias, which are disorders caused by excessive anxiety. User profiles turn out to be a critical tool for this. This paper proposes an active context construction method, which exploits user profiles to resolve active contexts. Moreover, it analyzes context information investigating the parameters that play significant role in certain phobias. We also propose an ontology based context and profile information model and an active context-aware framework based on a standardized computing environment that adds the appropriate functionality to our approach, while handling security and interoperability issues. In order to show the significance of active context-awareness and user profiles in the psychology domain, a discussion regarding patients, medical stuff and personalized medical treatments is made.

On optimal cell planning: Case study for a DCS 1800 system

Micro and pico cell planning strategies are adopted in personal communication systems (PCS) in order to increase their capacity. The usage of the upper UHF band in combination with greater bandwidth is already proposed by telecom engineers in order to achieve the promised service quality and data rates. These strategies are characterized by an increased number of cells in specific geographical areas with the corresponding operating base transceiving stations (BTS) located at relatively low heights above the street level. In this case, the cell planning procedure in linear streets under line-of-sight (LOS) conditions needs further study concerning the technical characteristics of the PCS. In this paper, the propagation characteristics of a DCS 1800 system are investigated on a theoretical and experimental basis in a specific geographical area (center of Patras City in Northern Pelloponesse). An improved RF propagation model is proposed in order to determine the propagation path losses occurring under certain multipath fading conditions. Hence an optimum determination of a systems cellular area can be achieved. Copyright

Integrity mechanism for eHealth tele-monitoring system in smart home environment

During the past few years, a lot of effort has been invested in research and development of eHealth tele-monitoring systems that will provide many benefits for healthcare delivery from the healthcare provider to the patients home. However, there is a plethora of security requirements in eHealth tele-monitoring systems. Data integrity of the transferred medical data is one of the most important security requirements that should be satisfied in these systems, since medical information is extremely sensitive information, and even sometimes life threatening information. In this paper, we present a data integrity mechanism for eHealth tele-monitoring system that operates in a smart home environment. Agent technology is applied to achieve data integrity with the use of cryptographic smart cards. Furthermore, the overall security infrastructure and its various components are described.

A proposed Next Generation Service Delivery Platform (NG-SDP) for eHealth domain

Nowadays, providing healthcare personalized services in users intelligent space is an important issue for improving personal health, supporting predictive care and saving medical costs. In this paper, we propose an architecture for the Next Generation Service Delivery Platform (NG-SDP), suitable for composing and delivering personalized healthcare services. The core component of NG-SDP is a Context Decision Making Enabler (CDME) that assesses user contextual and bio information to yield personalized services. A prototype implementation of the proposed NG-SDP is also demonstrated. Finally a real case study demonstrates the CDME performance.