Iskanje po repozitoriju

Opis: In this paper we present a multimethod approach for induction of a specific class of classifiers, which can assist physicians in medical diagnosing in the case of mitral valve prolapse. Mitral valve prolapse is one of the most controversial prevalent cardiac condition and may affect up to ten percent of the population and in the worst case results in sudden death. MultiVeDec is a general framework enabling researchers to generate various intelligent tools based on machine learning. In this paper we focused on various decision tree methods, which are capable of extracting knowledge in a form closer to human perception, a feature that is very important in medical field. The experiment included classifiers with various classical single method approaches, evolutionary approaches, hybrid approaches and also our newest multimethod approach. The main concern of the latest approach is to find a way to enable dynamic combination of methodologies to the somehow quasi unified knowledge representation. The proposed multimethod approach was capable to outperform all other tested approaches by producing classifier for diagnosing mitral valve prolapse with the highest overall and average class accuracy. More importantly, it was also capable to find some new knowledge important in diagnosing of mitral valve prolapse.
Objavljeno v RUP: 15.10.2013; Ogledov: 3276; Prenosov: 39
Povezava na celotno besedilo

Opis: The purpose of this research was to determine social interaction between hospitality employees and their guests, and consequently assess how front-line employees categorize and stereotype hotel guests based on their facial attractiveness with reference to three main characteristics. Social stereotypes represent a means of information transmission in the communication process and can enable a more rapid transfer of information during the service delivery in the hospitality industry. The experimental research was conducted with 113 hospitality employees at seven hospitality organizations on the Slovenian coast. The results showed a correlation between the perception of hotel guests' facial attractiveness with their assumed characteristics that can lead to stereotyping. Hotel employees often link the guests' facial attractiveness with three common perceived characteristics - guests' propensity to spend, guests' predisposition to being demanding and guests' 'kindness', and tend to stereotype them on the same basis. These research findings contribute to a better understanding of the complex interactions that occur during a service encounter and show how facial attractiveness of guests plays an important role in the construction of stereotypes by the hospitality employees.
Ključne besede: storitve, socialna interakcija, privlačnost obraza, stereotipi, eksperimentalna raziskava, turizem
Objavljeno v RUP: 15.10.2013; Ogledov: 12386; Prenosov: 68
Povezava na celotno besedilo

Ključne besede: Kras, avtoceste, Slovenija, kras, onesnaževanje, kraški vodonosniki, transportni promet, trajnostni razvoj prometa, DARS, geografija, diplomska dela
Objavljeno v RUP: 15.10.2013; Ogledov: 4075; Prenosov: 46
Celotno besedilo (3,59 MB)

Ključne besede: Tatra chamois, Alpine chamois, Rupicapra rupicapra, SNP chip, hybridization, non-model species
Objavljeno v RUP: 15.10.2013; Ogledov: 3339; Prenosov: 143
Povezava na celotno besedilo

Ključne besede: cerebralna paraliza, spremljajoče motnje, zaostanek v razvoju, gibalna oviranost, okvara možganov
Objavljeno v RUP: 15.10.2013; Ogledov: 4125; Prenosov: 139
Celotno besedilo (455,49 KB)