This paper introduces a novel approach for making a statistical comparison of meta-heuristic stochastic optimisation algorithms over multiple single-objective problems, where a new ranking scheme is proposed to obtain data for multiple problems. The main contribution of this approach is that the ranking scheme is based on the whole distribution, instead of using only one statistic to describe the distribution, such as average or median. Averages are sensitive to outliers and consequently medians are sometimes used. The experimental results obtained on Black-Box Benchmarking 2015, show that our approach gives more robust results compared to the common approach in cases when the results are affected by outliers or by a misleading ranking scheme.
COBISS.SI-ID: 30670119
The paper presents the optimisation of a production schedule that satisfies different, contradictory production and business constraints. We show the challenges faced in the application of the multiobjective optimisation approach, which is gaining influence in the management of production scheduling. We implement a memetic version of the evolutionary algorithm with customized reproduction operators and local search procedures. This memetic algorithm was applied to two real order lists from the production company ETA Cerkno d.o.o. Additionally, we also lay out an efficient presentation of the multiobjective results for an expert's support in decision making. This provides the management with the possibility to gain additional insights into how the production schedule dynamically reacts to changes in the decision criteria. We show that the multi objective approach is able to find high quality solutions, which enables flexibility when it comes to quickly adapting to specific business conditions.
COBISS.SI-ID: 26777127
Many promising optimisation algorithms for solving numerical optimisation problems come from population-based metaheuristics. A few of them are based on Swarm-Intelligence Algorithms, which are inspired by the collective behavior of social organisms. One of the most successful of such algorithms is the Differential AntStigmergy Algorithm (DASA), which uses stigmergy, a method of communication in emergent systems where the individual parts (artificial ants) of the system communicate with one another by modifying their local environment (pheromone intensity). The main characteristic of the DASA is its underlying structure (pheromone graph) that uses discrete steps to move through a continuous search space. We show that the DASA is a competitive continuous optimisation algorithm that solves high-dimensional problems effectively and efficiently.
COBISS.SI-ID: 23618855
This paper addresses the problem of online obstacle detection by constrained, unsupervised segmentation to be used in unmanned surface vehicles (USV) in coastal waters. A new graphical model of marine environment is proposed that enables a fast and continuous obstacle image-map estimation from a single video stream captured on board a USV. The main importance of the approach is that it does not require computationally intensive extraction of texture features and comfortably runs in real time. Results show that the model outperforms the related approaches, while requiring a fraction of computational effort. Therefore the influence on USV software applications is expected in the future.
COBISS.SI-ID: 1536310979
The paper presents biometric method for user identification on multitouch displays. The method is based on limited data about the user's hand available on all multitouch displays without requiring additional hardware and regardless of the display's underlying sensing technology. A dataset of 34 users was created on which our method reported 94.69% identification accuracy. The method's scalability was tested on a subset of the Bosphorus hand database (100 users, 94.33% identification accuracy) and a usability study was performed. The identity of the users involved in interaction is an important aspect of context. MTi makes multitouch displays user-aware and enables features like "role taking", "interface adaptation" and "access restrictions". Features that further augment experiences within scenarios that were made possible by the intuitiveness, directness and expressive power of multitouch interaction (interactive tables in education, public multitouch installations, music production, data visualisation, and computer supported collaborative work). The paper has been cited very frequently in the narrow field of identification on tabletop devices or its applications.
COBISS.SI-ID: 26717479
This paper presents a novel named-entity recognition (NER) method, called drNER, for knowledge extraction of evidence-based dietary information. To the best of our knowledge this is the first attempt at extracting dietary concepts. DrNER is a rule-based NER that consists of two phases. The first one involves the detection and determination of the entities mention, and the second one involves the selection and extraction of the entities. We evaluate the method by using text corpora from heterogeneous sources, including text from several scientifically validated web sites and text from scientific publications. Evaluation of the method showed that drNER gives good results.
COBISS.SI-ID: 30594343
We presented a new approach to distributed computing that employs an external database in order to improve the calculation–communication overlap, thus reducing the idle times for the worker processes. The presented approach is implemented as part of a parallel radio-coverage prediction tool for the Geographic Resources Analysis Support System (GRASS) environment. The prediction calculation employs digital elevation models and land-usage data in order to analyze the radio coverage of a geographical area. We provide an extended analysis of the experimental results, which are based on real data from an Long Term Evolution (LTE) network currently deployed in Slovenia. Based on the results of the experiments, which were performed on a computer cluster, the new approach exhibits better scalability than the traditional master–worker approach. We successfully tackled real-world-sized data sets, while greatly reducing the processing time and saturating the hardware utilisation. The presented results allow solving of bigger problems from radio-coverage prediction domain, which were previously been considered unfeasible.
COBISS.SI-ID: 27452711
A hardware accelerator for the compression of LIDAR data has been developed. Airborne LIDAR gathers vast amount of terrain data and requires huge storage space. Efficient compression techniques does exist but require substantial processing effort. A hardware compressor was developed to speed-up the compression as well as to reduce CPU computational effort.
COBISS.SI-ID: 26726695
A hypercube is one of the widely studied computer architecture due to its elegant properties. We study the resilience to the removal of edges or robustness of network. The problems of mutually-independent Hamiltonian paths with prescribed end-vertices and mutually-independent starting Hamiltonian cycles in the hypercube with faulty edges are studied. The study is motivated by the problem of transferring different pieces of a given message from one vertex to all recipients simultaneously such that they never meet in the same vertex. This is important in sensitivity analysis of fault tolerance of Hypercube structure. The obtained results on mutually-independent Hamiltonian paths with prescribed end-vertices is used to prove that there are n – m mutually-independent starting Hamiltonian cycles in the n-dimensional hypercube with m faulty edges.
COBISS.SI-ID: 26622247
Simultaneous broadcasting of multiple messages from the same source vertex in synchronous networks is considered under restrictions that each vertex receives at most one message in a unit time step, every received message can be sent out only in the next time step, no message is sent to already informed vertices. The number of outgoing messages is unrestricted, messages have unit length, and we assume full-duplex mode. In previous works we developed a concept of level-disjoint partitions to study simultaneous broadcasting under this model. In this work, we consider the optimal number of level-disjoint partitions. We also provide a necessary condition in terms of eccentricity and girth on existence of k v-rooted level-disjoint partitions of optimal height. In particular, we provide a structural characterisation of graphs admitting two level-disjoint partitions with the same root. This work is of high importance for understanding, how network topology implies network ability of efficient broadcasting under the studied model.
COBISS.SI-ID: 31040807