Savo Tomovic

The therapeutic potential of royal jelly in benign prostatic hyperplasia. Comparison with contemporary literature.

Abstract The aim of this study is to establish the scientific benefit of royal jelly (RJ) on prostatic-specific antigen (PSA), post-void residual (PVR) volume and International Prostate Symptom Score (IPSS) in benign prostatic hyperplasia. For the study, a group of 40 men were administered 38 mg of RJ over a period of three months, their PSA values, prostate volumes and the volumes of their transitory prostate zones, PVR and IPPS values were measured at the end of the first month, and at the end of the third month. The results of this study confirm the potential of RJ in reducing PSA scores and improving IPSS values. Since the use of RJ did not lead to any significant reduction in PVR, prostate volume, or to any involution of the transitory zone, it appears that it may only affect the blood marker of prostatic hyperplasia and to improve quality-of-life (QoL) in those patients. Overall, in comparison to phytotherapy and conventional therapy, RJ had similar positive effects on QoL in patients with BPH, however it exhibited markedly better effects on reducing PSA levels in blood. The therapeutical use of RJ exhibited no side effects.

Frequent itemset mining as set intersection problem

In this paper we present novel mathematical model of the frequent itemset mining problem. The model is based on set intersection terminology and theory. We use linear algebra method in order to prove our results.

Upper bounds on the number of candidate itemsets in Apriori like algorithms

Frequent itemset mining has been a focused theme in data mining research for years. It was first proposed for market basket analysis in the form of association rule mining. Since the first proposal of this new data mining task and its associated efficient mining algorithms, there have been hundreds of followup research publications. In this paper we further develop the ideas presented in [1]. In [1] we consider two problems from linear algebra, namely set intersection problem and scalar product problem and make comparisons to the frequent itemset mining task. In this paper we formulate and prove new theorems that estimate the number of candidate itemsets that can be generated in the level-wise mining approach.

Analyzing clusters in the university of Montenegro collaboration network

In this paper we present the first case study on collaboration network of researchers at the University of Montenegro - UoM. We identify the largest clusters or groups of scientists that are interested in the same topic, using Girvan-Newman algorithm. The results show that these clusters constantly grow over the period 2005-2015 and at the moment they occupy more than 50% authors from the UoM. It indicates that there exists increasingly collaboration between authors from the UoM network. But, according to classification of real networks the UoM network is in “sub-critical” regime, and still far away from “connected” regime. The study is limited to the authors from the UoM and we do not consider any collaboration outside of the UoM. Also, we consider only papers published in the SCI, SCIE, SSCI, A&HCI and SCOPUS categories, because they are recognized as the most important for professional career of professors at the UoM.

Fast algorithm for enumerating frequent itemset pairs in database of transactions

In this paper we present efficient algorithm for enumerating frequent pairs in database of transactions. Counting support for itemset pairs can be dominant step in frequent itemset mining occupying in some cases greater that 90% of total execution time. For efficient implementation we use one-dimensional array and define one-to-one function that maps 2-itemsets to array indexes preserving lexicographic order. In that way 2-itemsets are not generated explicitly; they are represented by indexes in one-dimensional array while their support counts are stored in appropriate array elements.