https://repository.utm.md/handle/5014/4668 2026-04-17T18:23:46Z https://repository.utm.md/handle/5014/5438 The Intelligent Support System for Remission in Patients with Psychiatric Disorders in Epilepsy BUTNARU, Maria; CAPATANA, Ana; CAPATANA, Gheorghe; COBILEANSCHI, Oleg; POPOV, Alexandru In the paper is related a project of an Intelligent Support System development for research and treatment of epilepsy. The tasks of this study are: a) to prove on material of over 100 patients with remissions that epilepsy is curable; b) to classify these persons by remissions groups; e) to develop and implement an intelligent support system for research, diagnostics and treatment assistance in epilepsy, d) principles development and implementation for psychological and psychiatric assistance and for critical situations remedy with which epileptics patients face, inclusively with socio-psychological assistance service conditions and within psycho neurologic consulting rooms. At the moment are developed: an expert system for diagnosis of epileptic patients with psychiatric disorders, an electronic textbook in the area of epilepsy problems, a support system for development of treatment programs of epileptic patients. 2011-01-01T00:00:00Z https://repository.utm.md/handle/5014/5437 SonaRes - Computer-Aided Approach for Advanced Ultrasound Medical Diagnostics BURTSEVA, Liudmila; COJOCARU, Svetlana; GAINDRIC, Constantin; POPCOVA, Olga; SECRIERU, Iulian Ultrasound image is the primary (input) information for every ultrasound examination. Despite the difficulties of ultrasound image interpretation, this source of information is still significant for diagnosis decision making. This paper describes the experience of SonaRes diagnostic decision support system (DDSS) for ultrasound examination development. Considering two-layer structure of the information contained in ultrasound images, two main approaches in DDSS creation may be distinguished: Image-based systems and Knowledge-based systems. In the SonaRes the advantages of both are combined. In the process of any DDSS development there are three points of major importance, influencing essential the success: i) knowledge acquisition and formalization; ii) image processing and search for similar ones, and iii) interaction with user [1]. SonaRes – represents one of the possible solutions to these problems aimed at increasing the DDSS functionality, user attitude and, as a result, adequacy of generated conclusions. 2011-01-01T00:00:00Z https://repository.utm.md/handle/5014/5436 Use of Telemedicine in Pilot Centers within the Perinatal System STRATULAT, P.; CARAUȘ, Tatiana; BLUNIER, M.; CURTEANU, Ala In the last decade of the twentieth century in many countries rapidly has developed telemedicine. Telemedicine is not a separate discipline within the health system, but a "transfer of information at distance regarding patient's medical care." In the Republic of Moldova telemedicine implementation into perinatal system started in 2009 in four pilot centers: MCRI (level III), CP Hospital no. 1 Chisinau, CP Balti and CP Cahul (level II). Thus the creation and development of this interdisciplinary network of teleconsultation and telediagnostic has followed the improvement of health care services quality and decrease of their costs, increasement of quality of patients life in perinatal system, orienting themselves to consultation of serious neonatal and obstetric cases from level II Perinatal centers. Although it’s on its beginning, telemedicine network in the frame of perinatal sytem has already achieved success. Cooperation between specialists from levels II and III of perinatal care has strengthened, interactive work and multidisciplinary cooperation between obstetricians-gynecologists and radiologists, imagists have strenghtened also. 2011-01-01T00:00:00Z https://repository.utm.md/handle/5014/5435 Towards an Images Dataset Processing trough Supervised and Unsupervised Learning ROGOVSCHI, Nicoleta; GROZAVU, Nistor Internet offers to its users an ever-increasing number of information. Among those, the multimodal data (images, text, video, sound) are widely requested by users, and there is a strong need for effective ways to process and to manage it, respectively. Most of existed algorithms/frameworks are doing only images annotations and the search is doing by these annotations, or combined with some clustering results, but most of them do not allow a quick browsing of these images. Even if the search is very quickly, but if the number of images is very large, the system must give the possibility to the user to browse this data. In this paper we investigate the use of the supervised learning to classify an images dataset and the unsupervised learning to browse the images. In our proposed schema, we used both PCA and LDA to transform the feature space and then to classify the dataset. We used this technique for all five datasets available on the challenge web site of The German Traffic Sign Recognition Benchmark: HOG1, HOG2, HOG3, HueHIst and Haar [7]. Finnaly we used a voting approach to find the consensus for all five partitions. Also, an application to the images browsing is shown using the topological unsupervised learning. 2011-01-01T00:00:00Z