Miha Ravber

University of Maribor, Faculty of Electrical Engineering and Computer Science, Faculty Member

Follower

Following

Co-author

Public Views

Miha Ravber received his Ph.D. in computer science from the University of Maribor in 2018. He is currently a teaching assistant at the University of Maribor, Faculty of Electrical Engineering and Computer Science. His research interests include evolutionary computation, single- and multi-objective optimization, soft computing and bio-inspired algorithms.

less

Interests

Uploads

Papers by Miha Ravber

Searching for soil models’ parameters using metaheuristics

Grounding systems are an important part of protection systems which protect people and devices in... more Grounding systems are an important part of protection systems which protect people and devices in case of defects in electro energetic systems or lightning strikes. The Finite Element Method (FEM) is often used for proper dimensioning of the grounding systems. Often data about the soil in the surroundings of the grounding system are obtained using measurements. Soil parameters can be determined using analytical soil models, and the determination of the soil models' parameters, which are based on the measured data, is an optimization problem. In this paper, different soil models are tested on different measured data and compared with each other. Different metaheuristics are used and tested for the determination of soil parameters: A Genetic Algorithm, Differential Evolution with two different strategies, Teaching-Learning Based Optimization, Artificial Bee Colony and Dynamic Optimization using Self-Adaptive Differential Evolution. Based on the test results, we improved the most appropriate method. As a result, the most appropriate soil model among those tested is selected, and a method for parameter determination is presented which combines Artificial Bee Colony and Teaching-Learning Based Optimization. The presented solution is appropriate to be used with, or as a part of, FEM calculation software.

Download

Long Term Memory Assistance for Evolutionary Algorithms

Short term memory that records the current population has been an inherent component of Evolution... more Short term memory that records the current population has been an inherent component of
Evolutionary Algorithms (EAs). As hardware technologies advance currently, inexpensive memory
with massive capacities could become a performance boost to EAs. This paper introduces a Long
Term Memory Assistance (LTMA) that records the entire search history of an evolutionary process.
With LTMA, individuals already visited (i.e., duplicate solutions) do not need to be re-evaluated,
and thus, resources originally designated to fitness evaluations could be reallocated to continue
search space exploration or exploitation. Three sets of experiments were conducted to prove the
superiority of LTMA. In the first experiment, it was shown that LTMA recorded at least 50% more
duplicate individuals than a short term memory. In the second experiment, ABC and jDElscop were
applied to the CEC-2015 benchmark functions. By avoiding fitness re-evaluation, LTMA improved
execution time of the most time consuming problems F03 and F05 between 7% and 28% and 7% and
16%, respectively. In the third experiment, a hard real-world problem for determining soil models’
parameters, LTMA improved execution time between 26% and 69%. Finally, LTMA was implemented
under a generalized and extendable open source system, called EARS. Any EA researcher could
apply LTMA to a variety of optimization problems and evolutionary algorithms, either existing or
new ones, in a uniform way.

format_quoteAnalyzing 250 configurations revealed that long-term memory is essential to identify 50%-90% of duplicate individuals effectively.format_quote

Download

From Grammar Inference to Semantic Inference—An Evolutionary Approach

This paper describes a research work on Semantic Inference, which can be regarded as an extension... more This paper describes a research work on Semantic Inference, which can be regarded as an
extension of Grammar Inference. The main task of Grammar Inference is to induce a grammatical
structure from a set of positive samples (programs), which can sometimes also be accompanied by
a set of negative samples. Successfully applying Grammar Inference can result only in identifying
the correct syntax of a language. With the Semantic Inference a further step is realised, namely,
towards inducing language semantics. When syntax and semantics can be inferred, a complete
compiler/interpreter can be generated solely from samples. In this work Evolutionary Computation
was employed to explore and exploit the enormous search space that appears in Semantic Inference.
For the purpose of this research work the tool LISA.SI has been developed on the top of the
compiler/interpreter generator tool LISA. The first results are encouraging, since we were able
to infer the semantics only from samples and their associated meanings for several simple languages,
including the Robot language.

format_quoteThe MAGIc algorithm enables automatic grammar production for Domain-Specific Languages (DSLs), improving the Grammar Inference process.format_quote

Download

Inferring Absolutely Non-Circular Attribute Grammars with a Memetic Algorithm

When valid syntactical structures are additionally constrained with context-sensitive information... more When valid syntactical structures are additionally constrained with context-sensitive information the Grammar Inference needs to be extended to the Semantic Inference. In this paper, it is shown that a complete compiler/interpreter for small Domain-Specific Languages (DSLs) can be generated automatically solely from given programs and their associated meanings using Semantic Inference. In this work a wider class of Attribute Grammars has been learned, while only S-attributed and Lattributed Grammars have previously been inferred successfully. Inferring Absolutely Non-Circular Attribute Grammars (ANC-AG) with complex dependencies among attributes has been achieved by integrating a Memetic Algorithm (MA) into the LISA.SI tool. The results show that the proposed Memetic Algorithm is at least four times faster on the selected benchmark than the previous method.

Download

Automatic compiler/interpreter generation from programs for Domain-Specific Languages: Code bloat problem and performance improvement

Using advanced AI approaches, the development of Domain-Specific Languages (DSLs) can be facilita... more Using advanced AI approaches, the development of Domain-Specific Languages (DSLs) can be facilitated for
domain experts who are not proficient in programming language development. In this paper, we first addressed
the aforementioned problem using Semantic Inference. However, this approach is very time-consuming.
Namely, a lot of code bloat is present in the generated language specifications, which increases the time
required to evaluate a solution. To improve this, we introduced a multi-threaded approach, which accelerates
the evaluation process by over 9.5 times, while the number of fitness evaluations using the improved Long
Term Memory Assistance (LTMA) was reduced by up to 7.3%. Finally, a reduction in the number of input
samples (fitness cases) was proposed, which reduces CPU consumption further.

Download

A Graph Pointer Network-Based Multi-Objective Deep Reinforcement Learning Algorithm for Solving the Traveling Salesman Problem

Traveling Salesman Problems (TSPs) have been a long-lasting interesting challenge to researchers ... more Traveling Salesman Problems (TSPs) have been a long-lasting interesting challenge to researchers in different areas. The difficulty of such problems scales up further when multiple objectives are considered concurrently. Plenty of work in evolutionary algorithms has been introduced to solve multi-objective TSPs with promising results, and the work in deep learning and reinforcement learning has been surging. This paper introduces a multi-objective deep graph pointer network-based reinforcement learning (MODGRL) algorithm for multi-objective TSPs. The MODGRL improves an earlier multi-objective deep reinforcement learning algorithm, called DRL-MOA, by utilizing a graph pointer network to learn the graphical structures of TSPs. Such improvements allow MODGRL to be trained on a small-scale TSP, but can find optimal solutions for large scale TSPs. NSGA-II, MOEA/D and SPEA2 are selected to compare with MODGRL and DRL-MOA. Hypervolume, spread and coverage over Pareto front (CPF) quality indicators were selected to assess the algorithms’ performance. In terms of the hypervolume indicator that represents the convergence and diversity of Pareto-frontiers, MODGRL outperformed all the competitors on the three well-known benchmark problems. Such findings proved that MODGRL, with the improved graph pointer network, indeed performed better, measured by the hypervolume indicator, than DRL-MOA and the three other evolutionary algorithms. MODGRL and DRL-MOA were comparable in the leading group, measured by the spread indicator. Although MODGRL performed better than DRL-MOA, both of them were just average regarding the evenness and diversity measured by the CPF indicator. Such findings remind that different performance indicators measure Pareto-frontiers from different perspectives. Choosing a well-accepted and suitable performance indicator to one’s experimental design is very critical, and may affect the conclusions. Three evolutionary algorithms were also experimented on with extra iterations, to validate whether extra iterations affected the performance. The results show that NSGA-II and SPEA2 were greatly improved measured by the Spread and CPF indicators. Such findings raise fairness concerns on algorithm comparisons using different fixed stopping criteria for different algorithms, which appeared in the DRL-MOA work and many others. Through these lessons, we concluded that MODGRL indeed performed better than DRL-MOA in terms of hypervolumne, and we also urge researchers on fair experimental designs and comparisons, in order to derive scientifically sound conclusions.

Download

Innovative Approach for the Determination of a DC Motor's and Drive's Parameters Using Evolutionary Methods and Different Measured Current and Angular Speed Responses

The determination is presented of seven parameters of a DC motor’s drive. The determination was b... more The determination is presented of seven parameters of a DC motor’s drive. The determination was based on a comparison between the measured and simulated current and speed responses. For the parameters’ determination, different evolutionary methods were used and compared to each other. The mathematical model presenting the DC drives model was written using two coupled differential equations, which were solved using the Runge–Kutta first-, second-, third- and fourth-order methods. The approach allows determining the parameters of controlled drives in such a way that the controller is taken into account with the measured voltage. Between the tested evolutionary methods, which were Differential Evolution with three strategies, Teaching-Learning Based Optimization and Artificial Bee Colony, the Differential Evolution (DE/rand/1/exp) can be suggested as the most appropriate for the presented problem. Measurements with different sampling times were used, and it was found out that at least some measuring points should be at the speed-up interval. Different lengths of the measured signal were tested, and it is sufficient to use a signal consisting of the drive’s acceleration and a short part of the stationary operation. The analysis showed that the procedure has good repeatability. The biggest deviation of calculated parameters considering 10 repeated measurements was 6% in case of the La calculation. The deviations of all the other parameters’ calculations were less than 2%.

format_quoteSeven key parameters of the DC motor drive were successfully determined, including resistance, inductance, and various friction loads.format_quote

Download