Natural language problems have already been investigated for around five years. Recent progress in artificial intelligence (AI) has greatly improved the performance of models. However, the results are still not sufficiently satisfying. Machines cannot imitate human brains and the way they communicate, so it remains an ongoing task. Due to the increasing amount of information on this topic, it is very difficult to keep on track with the newest researches and results achieved in the image captioning field. In this study a comprehensive Systematic Literature Review (SLR) provides a brief overview of improvements in image captioning over the last four years. The main focus of the paper is to explain the most common techniques and the biggest challenges in image captioning and to summarize the results from the newest papers. Inconsistent comparison of results achieved in image captioning was noticed during this study and hence the awareness of incomplete data collection is raised in this paper. Therefore, it is very important to compare results of a newly created model produced with the newest information and not only with the state of the art methods. This SLR is a source of such information for researchers in order for them to be precisely correct on result comparison before publishing new achievements in the image caption generation field.

No abstract

Image captioning is an important task for improving human-computer interaction as well as for a deeper understanding of the mechanisms underlying the image description by human. In recent years, this research field has rapidly developed and a number of impressive results have been achieved. The typical models are based on a neural networks, including convolutional ones for encoding images and recurrent ones for decoding them into text. More than that, attention mechanism and transformers are actively used for boosting performance. However, even the best models have a limit in their quality with a lack of data. In order to generate a variety of descriptions of objects in different situations you need a large training set. The current commonly used datasets although rather large in terms of number of images are quite small in terms of the number of different captions per one image. We expanded the training dataset using text augmentation methods. Methods include augmentation with synonyms as a baseline and the state-of-the-art language model called Bidirectional Encoder Representations from Transformers (BERT). As a result, models that were trained on a datasets augmented show better results than that models trained on a dataset without augmentation.

Abstract. In this paper, a technology enabling the optimization of the topology of truss or frame structures with genetic algorithms is presented. It has been shown that due to a huge number of possible variants the global solution of similar problems with exhaustive search algorithms is feasible only for systems possessing small numbers of d.o.f. s (usually until 10 nodes). These problems can be solved in a reasonable time by genetic algorithms. The modified genetic algorithm for optimization of topology of truss systems is suggested, where the repair of the genotype, instead of some constraint is used. The solution of numerical examples with original software illustrates the efficiency of proposed technology; the global solutions are obtained in all cases.

No abstract

No abstract

In this paper, a new simplified version of the Bayesian Approach to coordinate global optimization (BAcoor) is compared with the well-known algorithms. BAcoor is a method of multi-dimensional optimization by applying a sequence of one-dimensional global optimizers starting from the best points obtained by previous one-dimensional optimization. The globality of one-dimension search is controlled by the only parameter. The new element is that observation points are defined by explicit formulas. In other similar methods this is performed by some numerical techniques that minimize the risk functions. The efficiency of suggested method is investigated and compared with other methods by solving a real-life civil engineering global optimization problem of pile placement schemes in grillage-type foundations. This problem is a good benchmark, because the minimal value of the objective function is known so the optimization error can be defined exactly.

No abstract