Abstract: For achieving an optimal esthetic result from a dental treatment we need to create a suitable smile design that creates a perception which fulfills the esthetic expectations of the patient. It is also important that the teeth proportions to be correctly diagnosed and designed before an irreversible restorative dental procedure to be done.
Excellent quality digital smile design software products exist on the market. However these solutions do not apply in its fullness the visagism concept which produces a smile design in relation to the facial type and personality of the patient which is perceived as more harmonious. The visagism concept has been recently applied in the dental software “VisagiSMile” which helps clinicians to personalize and improve smile designs.
VisagiSMile is a software that automates the process of creating personalized digital smile design. VisagiSMile is a multiplatform web application for aesthetic dentistry which does not require installation, but only a simple registration process to get started. All cases and data are stored on a server to allow dentists to work on different devices and platforms – computers, tablets and smartphones. The research on the visagism concept is an ongoing process which constantly changes the requirements for the software. With the ongoing development of the software as an agile web application new versions are released every few weeks. Future plans include improvement of the accuracy of algorithms and of the teeth designs. Together with the product development, VisagiSMile’s user base also grows with over 1000 currently registered dentists.
Abstract: The visagism concept in dentistry tries to achieve the most appropriate smile design for every individual patient. The design is based on facial analysis, the patient’s personality and their preferences, and is calculated and visualized as a teeth configuration. The paper presents VisagiSMile — aesthetic dentistry software which automates the theory of dental visagism. The goal of VisagiSMile is to automate this process of creating aesthetic cases and to eliminate the human factor from the analysis. Based on innovative data mining approach, the software learns to classify patients’ faces correctly and then makes the necessary calculations to produce harmonious teeth configuration which can be further adjusted.
Резюме: Методиката и моделите за предсказване на успеха на стартиращи компании, представени в статията, са резултат от тригодишно проучване на предприемаческата екосистема в България. Предложени са модел на процеса на създаване на компания и модел за предсказване на успеха, които са базирани на проведено качествено изследване. Проведено е и количествено изследване върху набор от данни за 136 компании. Чрез прилагането на метода факторен анализ, са потвърдени предложените в модела категории и подкатегории фактори, определящи успеха на стартиращите компании. С помощта на софтуерните продукти за извличане на знания от данни – IBM SPSS Modeler и Weka са синтезирани класификационни модели, които с висока точност предсказват успеха. Получените резултати са приложени и внедрени в I3SP – информационна система за предсказване на успеха на стартиращи компании.
Abstract: The methodology and the success prediction models presented in the articles are results from three years of research of the entrepreneurial ecosystem in Bulgaria. A model of the process of creating a company and a success prediction model have been proposed, based on the conducted qualitative research. A qualitative research on a dataset for 136 companies has been conducted. The method factor analysis confirms the proposed categories and subcategories of factors in the model, which determine the success of start-ups. Classification models, which predict the success of start-ups with high accuracy, have been synthesized by applying the data mining software products IBM SPSS Modeler and Weka. The results are applied and implemented in I3SP – Information System for Start-ups Success Prediction.
Резюме: Проведено е количествено изследване на факторите за успех на стартиращи компании от България. Наборът от данни за 136 компании е анализиран с помощта на софтуерните продукти за извличане на знания от данни – IBM SPSS Modeler и Weka. Като резултат са синтезирани класификационни модели за предсказване на успеха на стартиращи компании от България. Получените модели са анализирани и сравнени, като са избрани най-точните и ефективни модели. Идентифицирани са факторите за успех на компаниите, включени в моделите, както и принципът на вземане на решение за тяхната класификация.
Автори: Янков, Б.
Abstract: The designs presented in the article are fastened in the authors’ years-long research on entrepreneurship and business model innovations. A quantitative research was performed to derive a model for predicting the success of Bulgarian startup companies. The authors started this research with in-depth inquiries of start-up companies in Bulgaria. Under our guidance, several research analysts investigated each start-up using approximately 100 questions. The preceding research stages included an overview and an analysis of existing success prediction models, a new abstract success prediction model, a venture creation process model and a qualitative research. The abstract success prediction model was extended with measurable variables with the help of a quantitative research of Bulgarian entrepreneurs. The current dataset of companies has been enriched with more cases and has been analyzed using data mining software: IBM SPSS Modeler, which automatically tests different models and suggests the best performing ones and also with the open source product Weka. The best derived model is a classification tree that correctly predicts the success of technology start-ups from the dataset in 83,76% of the test cases. The analysis revealed the answers to challenges and questions that start-up companies face and implemented a model that was deployed into an information system for start-ups success prediction. The developed information system will help to predict the success of start-ups. The software will evolve iteratively, and by involving more companies to use it, will grow its database.
Abstract: An Information System (IS) for predicting the success of Bulgarian start-up companies has been designed and developed. The IS is based on a model for success prediction derived from a quantitative research of 137 Bulgarian start-up companies. Entrepreneurs ﬁll in a survey and based on a prediction model the IS estimates the chances of success of their start-up and shows a graphical decision tree with the factors that led to the result.
Authors: Yankov, B., Vitanov, N.
Abstract: A quantitative research is performed to improve the accuracy of a previously derived model for predicting the success of Bulgarian start-up companies. The preceding research stages include an overview and analysis of older success prediction models, creation of a new abstract success prediction model, a venture creation process model, a qualitative and a quantitative research. The dataset is extended with 31 more cases and is analyzed in higher detail using the IBM SPSS Modeler software. The previously derived models are compared to the new ones in terms of accuracy of the success prediction and the predicting variables.
Authors: Yankov, B.
Abstract: A quantitative research is performed to derive a model for predicting the success of Bulgarian start-up companies. The preceding research stages included an overview and analysis of older success prediction models, a new abstract success prediction model, a venture creation process model and a qualitative research. The abstract success prediction model is extended with measurable variables which are included in a survey. The survey is currently in progress with 105 responses by owners and managers of Bulgarian companies. The current dataset was analyzed using the IBM SPSS Modeler software which automatically tests different models and suggests the best performing ones. The best derived model is a decision tree model that predicts the success of the start-up companies from the dataset with 91,86% probability using 11 variables.
Authors: Yankov, B., Haralampiev, K., Ruskov P.
Abstract: A new venture success prediction model is proposed based on an overview and analysis of success prediction models, analysis of the venture creation process, and a qualitative research – interviews with company owners. The success prediction model is extended with measurable variables. A survey to statistically validate the success prediction model is currently in progress with 68 responses by owners and managers of Bulgarian companies. A brief profile of the enterprises and their owners are presented. The available data is analyzed with IBM SPSS Statistics and shows a correlation of the company success and the success prediction model variables.
Authors: Yankov, B.