Mirela Danubianu

Distributed Intelligent System for Personalized Therapy of Speech Disorders

The aim of this paper is to describe an intelligent system designed for assisting the personalized therapy of dyslalia for the Romanian prescholars children. This system is developed in the frame of TERAPERS project that can be included in a very important research area: informational technologies in response to society challenges - for health: early diagnosis, personalized therapy. Taking into consideration the fact that Romanian language is a phonetic one that has its own special linguistic particularities, there is a real need for the development and use of audio-video systems, which can be used in the therapy of different speech problems. The system has a high degree of originality because his objective is to treat the pronunciation disorders in Romanian language. Also the complexity of the project results from the high number of different research areas involved: artificial intelligence, virtual reality, digital signal processing, digital electronic and psychology.

Towards the Optimized Personalized Therapy of Speech Disorders by Data Mining Techniques

Various speech disorders or language impairments can affect the whole life of a person. Discovered and treated in time, they can be corrected, most often in childhood. The use of information technology in order to assist and supervise speech disorder therapy allows specialists to collect a considerable volume of data about the personal or familial anamnesis, regarding various disorders or regarding the process of personalized therapy. These data can be the foundation of data mining processes that show interesting information for the design and adaptation of different therapies in order to obtain the best results in conditions of maximum efficiency. The aim of this paper is to make a short analyze of the use opportunity of the data mining techniques in order to improve the personalized therapy of speech disorders framework. We also present Logo-DM, a data mining system designed to be associated with TERAPERS system in order to provide information based on which one could improve the process of personalized therapy.

Managerial Tools for Sustainable Development

Abstract In the last decade, complex statistical studies related to top managerial tools proven to impact the most the performances of business companies show the following (changing) hierarchy (excerpts): - Strategic Planning; - Customer Relationship Management; - Employee Engagement Survey; - Corporate Social Responsibility; - Balanced Scorecard. These tools are, practically, unknown to the majority of companies with Romanian capital. This cannot go on like that. The main argument comes from the conditions in which these companies act, from increasing challenges from similar EU companies, from globalization and from increased awareness for sustainable development. The paper tries to identify a common mainframe for implementing such tools. Specific aspects are also given as examples. Main conclusions are: 1. Even in a general mainframe, there is no unique approach applicable to all companies; 2. Involvement of top managers is essential; 3. The appointed implementation team is multidisciplinary in every case (technical experts, economists, environmentalists, mathematicians, IT professionals, etc.). Their legitimacy gives consistence and coherence to the implementing process; 4. An external, neutral facilitator is a must. He is the guide, the referee, the one that deals with possible disputes and divergences in the team; 5. All new managerial tools must be based on what companies already have; This paper is the first in a series dedicated to the subject and comes as a side result of the PAZEWAIA Project, financed by Innovation Norway, project currently active in the North-East Development Region of Romania.

Industrial Symbiosis, Ecoefficiency, Sustainability a Case Study

Abstract In the last decade, international organizations have expressed their concern about the capacity of classical economical indicators to encompass the whole story of the developing processes, especially in their relationship with the environment. A comprehensive environmental metrics has been adopted (states and organizations reports indicators like greenhouse gas emissions, ozone concentrations, surface of contaminated land, number of threatened species, etc.) and operates in parallel with the traditional industrial indicators. But it seems not enough since this complementary metrics does not illustrate the entire complexity of development processes, in the 21st Century. Recent EU documents stress the importance of sustainable development, of the importance of industrial symbiosis as a tool to better manage material, energy and human resources and evaluate the possibility of generating and reporting new, synthetic, composite indicators that could include both the information in the classical economical indicators but also the environmental impact and the quality of life. The paper is a contribution in this respect and, starting from the results of the implementation of the Industrial Symbiosis paradigm in the case of a power plant, it presents how the EU recommendations about a more sophisticated metrics of ecoefficiency works, for the first time at the level of a Romanian enterprise. An original, new metrics is generated, that takes into account whether and how the technological and economical processes are accompanied by a favourable trend for the environment, A new, composite index for ecoefficiency and sustainability is presented in its structure and dynamic evolution, enabling local managers not only to assess their sustainable development trend, but also to identify where should their action be directed in the short term to correct unfavourable trends. The study was a part of the PAZEWAIA Project financed by Innovation Norway.

Data-Mining – A Valuable Managerial Tool for Improving Power Plants Efficiency

Abstract Energy and environment are top priorities for the EU’s Europe 2020 Strategy. Both fields imply complex approaches and consistent investment. The paper presents an alternative to large investments to improve the efficiencies of existing (outdated) power installations: namely the use of data-mining techniques for analysing existing operational data. Data-mining is based upon exhaustive analysis of operational records, inferring high-value information by simply processing records with advanced mathematical / statistical tools. Results can be: assessment of the consistency of measurements, identification of new hardware needed for improving the quality of data, deducing the most efficient level for operation (internal benchmarking), correlation of consumptions with power/ heat production, of technical parameters with environmental impact, scheduling the optimal maintenance time, fuel stock optimization, simulating scenarios for equipment operation, anticipating periods of maximal stress of equipment, identification of medium and long term trends, planning and decision support for new investment, etc. The paper presents a data mining process carried out at the TERMICA - Suceava power plant. The analysis calls for a multidisciplinary approach, a complex team (experts in power&heat production, mechanics, environmental protection, economists, and last but not least IT experts) and can be carried out with lower expenses than an investment in new equipment. Involvement of top management of the company is essential, being the driving force and motivation source for the data-mining team. The approach presented is self learning as once established, the data-mining analytical, modelling and simulation procedures and associated parameter databases can adjust themselves by absorbing and processing new relevant information and can be used on a long term basis for monitoring the performance of the installation, certifying the soundness of managerial measures taken and suggesting further adjustments

HOW USEFUL CAN BE DATA MINING FOR A CONTINUOS SPEECH THERAPIST'S EDUCATION?

Abstract Speech therapy can be viewed as a business in logopaedic area that aims to offer services for correcting language. A proper treatment of speech impairments ensures improved efficiency of therapy, so, in order to do that, a therapist must continuously learn how to adjust its therapy methods to patients characteristics. Using Information and Communication Technology in this area allowed collecting a lot of data regarding various aspects of treatment. These data can be used for a data mining process in order to find useful and usable patterns and models which help therapists to improve its specific education. Clustering, classification or association rules can provide unexpected information which help to complete therapists knowledge and to adapt the therapy to patients needs.

Joining Data Mining with a Knowledge-Based System for Efficient Personalized Speech Therapy

This paper to present an approach in which data mining technique could contribute to the enrichment of knowledge base of expert system embedded in TERAPERS.- an intelligent system which aims to assist the personalized therapy of speech disorders. Since March 2008 the system is used by the therapists from Regional Speech Therapy Center of Suceava, and it provides a data set which can serve as a foundation for data mining operations. Patterns resulted from these operations may complete the set of rules which form the knowledge base of expert system in TERAPERS.