Skip to main content
Top

2014 | Book

Advanced Intelligent Computational Technologies and Decision Support Systems

insite
SEARCH

About this book

This book offers a state of the art collection covering themes related to Advanced Intelligent Computational Technologies and Decision Support Systems which can be applied to fields like healthcare assisting the humans in solving problems. The book brings forward a wealth of ideas, algorithms and case studies in themes like: intelligent predictive diagnosis; intelligent analyzing of medical images; new format for coding of single and sequences of medical images; Medical Decision Support Systems; diagnosis of Down’s syndrome; computational perspectives for electronic fetal monitoring; efficient compression of CT Images; adaptive interpolation and halftoning for medical images; applications of artificial neural networks for real-life problems solving; present and perspectives for Electronic Healthcare Record Systems; adaptive approaches for noise reduction in sequences of CT images etc.

Table of Contents

Frontmatter
Medical Decision Support System Using Pattern Recognition Methods for Assessment of Dermatoglyphic Indices and Diagnosis of Down’s Syndrome
Abstract
The development and implementation of the telemedical system for the diagnosis of Down’s syndrome is described in the chapter. The system is a tool supporting medical decision by automatic processing of dermatoglyphic prints and detecting features indicating the presence of genetic disorder. The application of image processing methods for the pre-processing and enhancement of dermatoglyphic images has also been presented. Classifiers for the recognition of fingerprint patterns and patterns of the hallucal area of the soles, which are parts of an automatic system for rapid screen diagnosing of trisomy 21 (Down’s Syndrome) in infants, are created and discussed. The method and algorithms for the calculation of palmprint’s ATD angle are presented then. The images of dermatoglyphic prints are pre-processed before the classification stage to extract features analyzed by Support Vector Machines algorithm. The application of an algorithm based on multi-scale pyramid decomposition of an image is proposed for ridge orientation calculation. RBF and triangular kernel types are used in training of SVM multi-class systems generated with one-vs.-one scheme. A two stage algorithm for the calculation of palmprint’s singular points location, based on improved Poincare index and Gaussian-Hermite moments is subsequently discussed. The results of experiments conducted on the database of Collegium Medicum of the Jagiellonian University in Cracow are presented.
Hubert Wojtowicz, Wieslaw Wajs
New Format for Coding of Single and Sequences of Medical Images
Abstract
The recent development and use of huge image databases creates various problems concerning their efficient archiving and content protection. A wide variety of standards, methods and formats have been created, most of them aimed at the efficient compression of still images. Each standard and method has its specific advantages and demerits, and the best image compression solution is still to come. This chapter presents new format for archiving of still images and sequences of medical images, based on the Inverse Pyramid Decomposition, whose compression efficiency is comparable to that of JPEG. Main advantages of the new format are the comparatively low computational complexity and the ability to insert resistant and fragile watermarks in same digital image.
Roumen Kountchev, Vladimir Todorov, Roumiana Kountcheva
Rule-Based Classification of Patients Screened with the MMPI Test in the Copernicus System
Abstract
The Copernicus system is a tool for computer-aided diagnosis of mental disorders based on personality inventories. Knowledge representation in the form of rules is the closest method to human activity and reasoning, among others, in making a medical diagnosis. Therefore, in the Copernicus system, rule-based classification of patients screened with the MMPI test is one of the most important parts of the tool. The main goal of the chapter is to give more precise view of this part of the developed tool.
Daniel Jachyra, Jerzy Gomuła, Krzysztof Pancerz
An Adaptive Approach for Noise Reduction in Sequences of CT Images
Abstract
CT presents images of cross-sectional slices of the body. The quality of CT images varies depending on penetrating X-rays in a different anatomically structures. Noise in CT is a multi-source problem and arises from the fundamentally statistical nature of photon production. This chapter presents an adaptive approach for noise reduction in sequences of CT images, based on the Wavelet Packet Decomposition and adaptive threshold of wavelet coefficients in the high frequency sub-bands of the shrinkage decomposition. Implementation results are given to demonstrate the visual quality and to analyze some objective estimation parameters such as PSNR, SNR, NRR, and Effectiveness of filtration in the perspective of clinical diagnosis.
Veska Georgieva, Roumen Kountchev, Ivo Draganov
Intelligent Predictive Diagnosis on Given Practice Data Base: Background and Technique
Abstract
Medical diagnosis is a model of technical diagnosis for historical reasons. At this point, technical diagnosis results as a set of information processing techniques to identify technical faults can be extent to the medical field. Such situation is referring to the modeling of the cases and to the use of the information regarding the states, medical interventions and their effects. Diagnosis is possible not only through a rigorous modeling but also through an intelligent use of the practice bases that already exist. We examine the principles of such diagnosis and the specific means of implementation for the medical field using artificial intelligence techniques usual in engineering.
George Isoc, Tudor Isoc, Dorin Isoc
Towards ICT Revolution in Healthcare: Present and Perspectives for Electronic Healthcare Record Systems
Abstract
This chapter will describe and discuss the applications and solutions under development or implemented in the e-Health care systems, from the technological, social, organizational dimensions. A survey of the present status in relation with e-Government will cover the leading countries (and not only) in ICT-based developments in these sectors. The major implemented solutions will be outlined regarding their actual implementation and administration. Key aspects will be outlined for Electronic Healthcare Record Systems as core systems in present or future national or regional health programs.
Iulian Furdu, Bogdan Pătruţ
Compression of CT Images with Branched Inverse Pyramidal Decomposition
Abstract
In this chapter a new approach is suggested for compression of CT images with branched inverse pyramidal decomposition. A packet of CT images is analyzed and the correlation between each couple inside it is found. Then the packet is split into groups of images with almost even correlation, typically into six or more. One is chosen as a referent being mostly correlated with all of the others. From the rest difference images with the referent are found. After the pyramidal decomposition a packet of spectral coefficients is formed and difference levels which are coded by entropy coder. Scalable high compression is achieved at higher image quality in comparison to that of the JPEG2000 coder. The proposed approach is considered perspective also for compression of MRI images.
Ivo R. Draganov, Roumen K. Kountchev, Veska M. Georgieva
Adaptive Interpolation and Halftoning for Medical Images
Abstract
Two methods for local adaptive two-dimensional processing of medical images are developed. In the first one the adaptation is based on the local information from the four neighborhood pixels of the processed image and the interpolation type is changed to zero or bilinear. In the second one the adaptive image halftoning is based on the generalized 2D LMS error-diffusion filter. An analysis of the quality of the processed images is made on the basis of the calculated PSNR, SNR, MSE and the subjective observation. The given experimental results from the simulation in MATLAB 6.5 environment of the developed algorithms, suggest that the effective use of local information contributes to minimize the processing error. The methods are extremely suitable for different types of images (for example: fingerprints, contour images, cartoons, medical signals, etc.). The methods have low computational complexity and are suitable for real-time applications.
Rumen Mironov
Classification of EEG-Based Brain–Computer Interfaces
Abstract
This chapter demonstrates the development of a brain computer interface (BCI) decision support system for controlling the movement of a wheelchair for neurologically disabled patients using their Electroencephalography (EEG). The subject was able to imagine his/her hand movements during EEG experiment which made EEG oscillations in the signal that could be classified by BCI. The BCI will translate the patient’s thoughts into simple wheelchair commands such as “go” and “stop”. EEG signals are recorded using 59 scalp electrodes. The acquired signals are artifacts contaminated. These artifacts were removed using blind source separation (BSS) by independent component analysis (ICA) to get artifact-free EEG signal from which certain features are extracted by applying discrete wavelet transformation (DWT). The extracted features were reduced in dimensionality using principal component analysis (PCA). The reduced features were fed to neural networks classifier yielding classification accuracy greater than 95 %.
Ahmad Taher Azar, Valentina E. Balas, Teodora Olariu
Negotiation-Based Patient Scheduling in Hospitals
Reengineering Message-Based Interactions with Services
Abstract
Nowadays, hospitals in Germany and other European countries are faced with substantial economic challenges stemming from increased costs and increased demands inter alia resulting from a changing age pyramid. In this respect, patient scheduling is an interesting parameter that determines on the one hand the length of the patients stay in the hospital and the efficiency of the hospital resource allocation on the other hand. Due to the specific characteristics of hospitals such as unexpectedly arriving emergencies or unintended complications during treatments the optimization of patient scheduling is an extraordinary difficult task that cannot be easily solved using a typical centralized optimization algorithm. Thus, in this chapter a decentralized agent based approach is presented that represents patients as well as hospital resources as agents with individual goals that negotiate to find appropriate solutions. The approach has been extensively studied within the MedPAge project and also has been implemented using an agent platform. In this work it will be shown how the traditional message based implementation, which was difficult to construct and even more difficult to maintain, can be replaced with a service based design.
Lars Braubach, Alexander Pokahr, Winfried Lamersdorf
A New Generation of Biomedical Equipment Based on FPGA. Arguments and Facts
Abstract
The chapter is aiming to broaden the bridge that covers the gap between the engineering and the biomedical science communities, by encouraging the developers and the users of biomedical equipment to apply at a large scale and to promote the Field-Programmable Gate Array technology. The chapter provides a brief recall of this technology and of its key advantages: high electrical performances (great complexity, high speed, low energy consumption, etc.), extremely short time-to-market, high reliability even in field conditions, flexibility, portability, standardization, etc. The positive FPGA experience, issued from the military and the aerospace domains, is beginning to spread into the biomedical and healthcare field, where the personnel should be aware and prepared for this substantial and presumably long term advance.
Marius M. Balas
A Survey of Electronic Fetal Monitoring: A Computational Perspective
Abstract
Electronic Fetal Monitoring (EFM) records fetal heart rate in order to assess fetal well being in labor. Since its suggestion in clinical practise by de Kergeradee in the nineteenth century, it has been adopted as standard medical practise in many delivery scenarios across the globe. The extent of its use has augmented from its original purpose and is now used to not only reduce prenatal mortality, but also neonatal encephalopathy and cerebral palsy. One of the difficulties with EFM is interpreting the data, which is especially difficult if it is acquired in a continuous fashion. A grading system has been developed (utilised for developing a guideline for Clinical Practise Algorithm) which consists of grading fetal heart rate (FHR) into fairly rough categories (three). These categories are defined by values associated with a set of four features. The values for this set of features are potentially influenced by the particular collection equipment and/or operating conditions. These factors, in conjunction with a stressful condition such as a complicated delivery scenario may render rapid and unequivocal reporting of the neonatal status sometimes difficult. This chapter examines the development of automated approaches to classifying FHR into one of three clinically defined categories. The ultimate goal is to produce a reliable automated system that can be deployed in real-time within a clinical setting and can therefore be considered as an adjunctive tool that will provide continuous on-line assistance to medical staff.
Kenneth Revett, Barna Iantovics
Quantifying Anticipatory Characteristics. The AnticipationScope™ and the AnticipatoryProfile™
Abstract
Anticipation has frequently been acknowledged, but mainly on account of qualitative observations. To quantify the expression of anticipation is a challenge in two ways: (1) Anticipation is unique in its expression; (2) given the non-deterministic nature of anticipatory processes, to describe quantitatively how they take place is to describe not only successful anticipations, but also failed anticipations. The AnticipationScope is an original data acquisition and data processing environment. The Anticipatory Profile is the aggregate expression of anticipation as a realization in the possibility space. A subsystem of the AnticipationScope could be a predictive machine that monitors the performance of deterministic processes.
Mihai Nadin
Generating Sample Points in General Metric Space
Abstract
The importance of general metric spaces in modeling of complex objects is increasing. A key aspect in testing of algorithms on general metric spaces is the generation of appropriate sample set of objects. The chapter demonstrates that the usual way, i.e. the mapping of elements of some vector space into general metric space is not an optimal solution. The presented approach maps the object set into the space of distance-matrixes and proposes a random walk sample generation method to provide a better uniform distribution of test elements.
László Kovács
A Distributed Security Approach for Intelligent Mobile Multiagent Systems
Abstract
Intelligent systems are used for many difficult problems solving, like: clinical decision support, health status monitoring of humans etc. The intelligence could give to a system advantages versus a system that does not have intelligence. Software mobile agents as network-computing technology has been applied for various distributed problems solving like: ubiquitous healthcare, network administration etc. The endowment of mobile agents with intelligence is difficult. Another difficulty in mobile multiagent systems consists in the limited security of mobile agents against networks sources, other agents and hosts. In this chapter a novel mobile agent architecture called IntelligMobAg (Complex Intelligent Mobile Agent Architecture) is proposed. IntelligMobAg represents an extension of a previous mobile agent architecture called ICMA [(Iantovics in A new intelligent mobile multiagent system. IEEE Computer Society Press, Silver Spring, pp. 53–159, 2005), (Iantovics in A novel mobile agent architecture. Acta Universitatis Apulensis, Alba Iulia, vol. 11, pp. 295–306, 2006)]. The purpose of the proposal consists in the limitation of some disadvantages related with security and intelligence of an ICMA agent by including in the static part of an evolutionary subagent. In this chapter we will present some preliminary results related with the increased security and intelligence that emerge in a cooperative multiagent system formed by agents endowed with the proposed architecture.
Barna Iantovics, Bogdan Crainicu
Day Trading the Emerging Markets Using Multi-Time Frame Technical Indicators and Artificial Neural Networks
Abstract
This chapter addresses the topic of automated day trading systems based on artificial neural networks and multi-timeframe technical indicators, a very common market analysis technique. After we introduce the context of this study and give a short overview of day trading, we set out our approach and methodological framework. Then, we present the results obtained through these procedures on several of the most liquid stocks in the Romanian stock market. The final section of the chapter concludes the study and brings some insight about possible future work in the area.
Alexandru Stan
Teaching for Long-Term Memory
Abstract
A major goal of education is to help students store information in long-term memory and use that information on later occasions, in the most efficient manner. This chapter investigates the use of analogy as a strategy for encoding information in long-term memory. The results of a study concerning the ability of students to use analogy when learning computer science are presented.
Elena Nechita
A Recognition Algorithm and Some Optimization Problems on Weakly Quasi-Threshold Graphs
Abstract
Graph theory provides algorithms and tools to handle models for important applications in medicine, such as drug design, diagnosis, validation of graph-theoretical methods for pattern identification in public health datasets. In this chapter we characterize weakly quasi-threshold graphs using the weakly decomposition, determine: density and stability number for weakly quasi-threshold graphs.
Mihai Talmaciu
Large Graphs: Fast Cost Update and Query Algorithms. Application for Emergency Vehicles
Abstract
This chapter presents a method that can be used to solve the shortest path problem in large graphs, together with arc cost updates. Our approach uses a contracted graph, which is obtained from the important nodes of the original graph. Every non-important vertex has one or more assigned important nodes as references. A reference node will help us to quickly find the arcs to be updated. The advantage of our method is that we can quickly update the contracted graph, so it can be safely used for future queries. An application of these algorithms can be used by emergency vehicles.
Ion Cozac
Scan Converting OCT Images Using Fourier Analysis
Abstract
Scan conversion is the process by which a polar image is transformed into Cartesian coordinates. Several image modalities such as radar and catheter based imaging modalities acquire data in a polar image format. While suitable for the acquisition process, this format poses a challenge both in displaying as well as on the analyses of the image. Intravascular optical coherence tomography (IVOCT) is a catheter-based imaging modality utilizing a polar image format. Current interpolation techniques used to fill in the uneven spacing between the lines of IVOCT images create visual artifacts and render the resulting image unsuitable for reliable analysis. We present a novel technique that estimates the unsampled pixel values between the lines of IVOCT images using the Fourier analysis of the acquired data. This technique should minimize the visual artifacts as well as provide images more reliable for further analysis.
Amr Elbasiony, Haim Levkowitz
Metadata
Title
Advanced Intelligent Computational Technologies and Decision Support Systems
Editors
Barna Iantovics
Roumen Kountchev
Copyright Year
2014
Electronic ISBN
978-3-319-00467-9
Print ISBN
978-3-319-00466-2
DOI
https://doi.org/10.1007/978-3-319-00467-9

Premium Partner