L. Miclea

3D printing bone models extracted from medical imaging data

Additive manufacturing in the form of 3D printing is becoming more common with the rise of low-cost hobby machines which makes research in the field of medicine more accessible. This article explores and experiments with methods of producing three dimensional replicas of body parts as education material from the medical imaging data of Computed Tomography and Magnetic Resonance Imaging.

A data mining experiment on a SCADA system’s historical acquired data

In the SCADA system implemented for a hydroelectric power plants cascade, monitoring, control and over-limit alarm processes provide large amounts of historical data stored in distributed databases. In their preliminary form these data donpsilat offer a performance knowledge discovery. Intelligent data mining framework applied over historical acquired data is used to extract hidden information directly from the SCADA systempsilas database records. This paper presents a data mining and visualization experiment performed on a real data and results achieved in the experiment. The decision trees algorithm is used in order to find patterns in historical data and to establish a data mining flow.

Medical information system based on electronic healthcare records

This article approaches the shortcomings of the current medical information systems and describes a solution compliant with the openEHR standard, used to structure and markup the clinical content. The paper puts forward a prototype for a medical software based on electronic healthcare records which meets the requirements of interoperability and high security of data. It ensures the accuracy and reliability of operations and the adaptability of the system to the continuous changes in the medical field. The application is applied to the particularities of the Romanian healthcare environment.

Computational Complexity Reduction of the Support Vector Machine Classifiers for Image Analysis Tasks Through the Use of the Discrete Cosine Transform

Support vector machines (SVMs) are powerful classifiers, with very good recognition rates in image analysis tasks. However their computational time in the object recognition phase is often large due to the number of classifications per scene and to the feature vector size, especially when the feature space is formed from raw image data. Several methods are reported in the literature to make the classification faster, as selecting only the most significant support vectors or reducing the feature vector length by image transforms (wavelets, PCA) prior to SVM training and classification. The method we propose is different in principle. Instead of applying the transform prior to training and thus changing the representation space, we only perform a unitary orthogonal real transform in the classification phase on the resulting support vectors and on the pattern to be classified. As the inverse matrices of these transforms are exactly the transposed of the transform matrices, we mathematically prove that the dot product of any two vectors has the same expression in the original and the transformed space. This, combined with the energy compaction property of a suitable transform, leads to a faster computation of the dot products, if the transform has a fast implementation algorithm. We use the discrete cosine transform (DCT) due to its good energy compaction on digital images. Our first experiments on a face recognition application are promising: at the same recognition rate, our algorithm leads to an average 30% reduction in the number of elementary operations per classification

Electronic healthcare record according to general clinical observation file

Medical software systems in Romania lack the data interchange capability. By combining the force of knowledge in the computer science, information science and healthcare, this article provides a viable runtime solution for the electronic data management of the Romanian General Clinical Observation File in an efficient manner according with openEHR specifications. GCOF is composed of varied medical and demographical data and its content is regulating by the Ministry of Public Health.

Electronic vote scheme based on ring signature

This paper proposes an electronic vote scheme generated by the ring signature with divised private key. The algorithm respects the basic requirements regarding the voting process. The fact that it comes from a ring signature confers a strong anonymity to the developed scheme. The mathematical structure where the work in done is the remainder classes modulo n ring. There are presented two variants, the first one refers to the situation when all voting entities are registered before the voting process and the second one offers the possibility to vote other entities, entities who werent registered before, too. The security from the cryptographic view is also analized.

Elderly Fall Risk Prediction System

Preventing diseases of older persons and promoting the lack of necessity in consulting professionals is a priority in the Romanian health system as all these will lead to cost reduction in this important sector of the Romanian economy. Taking these in mind, we propose a new king of medicine, a medicine that is based on connectivity, collaboration, customization and computing. For this kind of medicine to work, we have developed an integrated system that will be used for compulsory planning and for compulsory regularly evaluation of the elder persons. Furthermore, where needed, telemonitoring and assistance will be used.

SCADA plug-in modules and instruments for federative organisation: Application on water management

Present paper presents an approach related to the question of structuring a federation of SCADA systems, associated with the integrated water resource exploitation, from a certain catchment area. Utilized instruments for federation development there are: (i) DESCRIPTOR component, achieving topology description - resources (roots) associated with protocols, functionality and governance rules, combined in plug-in module TOPOLOGY; (ii) Integrated Supervisor, having supervision role related to exchanges between federation partners. This plug-in application is auto-configurable and is running correlated with the TOPOLOGY modules.

Wind farms modeling files transformation

Wind farms modeling software are very important in the process of planning, dimensioning, and developing a wind farm. These applications offer valuable information about some key factors in the process of wind farm creation. The platforms do not offer information just about the placement of the wind farms but also about wind condition, wind resource, management predictions, cost and efficiency predictions, what hardware to use in the creation of the farm. There are special types of files that are used as input files for different software platforms and as a result the user obtains other files with other extension types that contain the modeling result or other useful information. A big problem is that the gainer is not a specialist in using these platforms and working with the specific files types. The goal of this paper is to present an easier way to access these files without having to buy or install the wind farms modeling platforms. Our goal is that a person that has certain files containing information of any sort will not have to buy expensive applications in order to extract the information necessary but transform the files into an .xls file that is a wide range used file extension.

Electronic signature with ordered and divided private key

The encryption systems with public keys are related to algebraic structures, which have to ensure by the means of their computational properties or their dimensions, a high level of security for the generated keys, which are private. The ElGamal algorithm is defined over the group of remainder classes modulo n, which is a suitable structure for an encryption algorithm. This algorithm can be defined over another mathematical structure: symmetrical group of degree p. The properties which ensure the opportunity of choosing this structure are: the cardinal of the group is sufficiently great, the operation of composition of the permutations is simple from the computational point of view and every permutation can be decomposed uniquely into a product of disjunctive functions. The main objective of this paper is to create a signature scheme with ordered and divided private key starting from the ElGamal algorithm with public keys over the symmetrical group of degree p. The auxiliary objectives of the paper are: the outline of the obtained results in this field from the corresponding literature and putting forward a comparative study. The paper is structured according to these objectives and includes a study of the literature of the field, the algorithms for the created schemes and conclusions. The scheme is included in the category of the ones with divided or shared private key and it is not part of the category of group signatures or of the ring signature. In this situation the private key is divided and from a number of entities, each owns a division. In order to create the signature, it is necessary for each entity to use, in a default order its own division from the private key, while the checking of the signature is realized using a unique public key. The conclusions and the contributions of the scheme are addressed in the last part of the paper.