10 research outputs found
Distinction of The Authors of Texts Using Multilayered Feedforward Neural Networks
Full text linkThis paper proposes a means of using a multilayered feedforward neural network to identify the author of a text. The network has to be trained where multilayer feedforward neural network as a powerful scheme for learning complex input-output mapping have been used in learning of the average number of words and average characters of words in a paragraphs of an author. The resulting training information we get will be used to identify the texts written by authors. The computational complexity is solved by dividing it into a number of computationally simple tasks where the input space is divided into a set of subspaces and then combining the solutions to those tasks. By this, we have been able to successfully distinguish the books authored by Leo Tolstoy, from the ones authored by George Orwell and Boris Pasternak
Multilayered feedforward neural networks as a tool for distinction of the authors of texts
No full text
Revised inventory of the butterflies of Bosnia and Herzegovina (Insecta: Lepidoptera: Hesperioidea, Papilionidea)
Full text linkU ovom radu je izvršena treća revizija popisa dnevnih leptira u Bosni i Hercegovini po sistemu Karsholt – Razowski. Revizija je napravljena analizom stručne literature i objavljenih radova s terena u B-H. Prisutnost L. reali (Reissinger, 1989) autor je osobno utvrdio vlastitim terenskim istraživanjima te naknadnim laboratorijskim pretragama.This work presents a third revision of the inventory of butterflies of Bosnia and Herzegovina according to the Karsholt – Razowski system. The revision was carried out from analysis of the scientific literature and published field observations from B-H. The presence of L. reali (Reissinger, 1989) has been verified personally by the author in the course of his own field research and subsequent laboratory investigations
Complex Ecological System Modeling
Full text linkIn this paper we extend our previous results in dual approach to analysis and simulation of a complex ecological system of preys and predators. We first define nonlinear dynamic equations Lotka-Volterra Model (LVM) with three preys and three predators and then simulate the equivalent situation with an Agent Based Model (ABM) which models a variety of species attributes and behaviors using NetLogo simulation environment for ABM model. The idea is that the LVM and ABM methods reinforce each other as the predator-prey models become more complex and their dimensionality rises. In particular LVM’s parameters, components of community matrix, can be fine tuned using ABM simulations. Dual approach may be able to answer and qualify some of the long standing ecological paradoxes.
 
Intelligent Memory Allocation based on Fuzzy Logic
Full text linkBased on the Computerized Parkinson’s Law “work expands so as to fill the time available for its completion” (Thimbleby, 1993) it can be deduced that regardless of the size of the memory, there will always be programs to completely fill, or even overload that memory. Thus intelligent/sensible memory allocation process is crucial to system’s performance. However, due to the constant increase of processing power and the growth and spread of distributed systems, such as grid and cloud computing, memory allocation becomes a great challenge in the area of memory management today. Making allocation intelligent, so that the memory fragmentation and response time are reduced would be great, and in this research, this was attempted. The research presents Fuzzy Allocator, memory allocator based on fuzzy inference system. The allocator manages to sort the incoming memory requests according to their size and the size of free memory slot (hole). The output of the fuzzy allocator is the order in which the allocation of memory will be performed on the incoming memory requests. It reorders the incoming memory request queue so that the response time is reduced, and fragmentation is minimized
