Justyna Golec

Ms. Justyna Golec

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2020 in Entropy
Verified
Journal Article
Open access
PDF file
Tomasz HachajTomasz Hachaj
Tomasz Hachaj
JGJustyna Golec
Justyna Golec
Hashtag-based image descriptions are a popular approach for labeling images on social media platforms. In practice, images are often described by more than one hashtag. Due the rapid development of deep neural networks specialized in image embedding and classification, it is now possible to generate those descriptions automatically. In this paper we propose a novel Voting Deep Neural Network with Associative Rules Mining (VDNN-ARM) algorithm that can be used to solve multi-label hashtag recommendation problems. VDNN-ARM is a machine learning approach that utilizes an ensemble of deep neural networks to generate image features, which are then classified to potential hashtag sets. Proposed hashtags are then filtered by a voting schema. The remaining hashtags might be included in a final recommended hashtags dataset by application of associative rules mining, which explores dependencies in certain hashtag groups. Our approach is evaluated on a HARRISON benchmark dataset as a multi-label classification problem. The highest values of our evaluation parameters, including precision, recall, and accuracy, have been obtained for VDNN-ARM with a confidence threshold 0.95. VDNN-ARM outperforms state-of-the-art algorithms, including VGG-Object + VGG-Scene precision by 17.91% as well as ensemble–FFNN (intersection) recall by 32.33% and accuracy by 27.00%. Both the dataset and all source codes we implemented for this research are available for download, and our results can be reproduced.

17 August 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JGJustyna Golec
Justyna Golec
Tomasz HachajTomasz Hachaj
Tomasz Hachaj
The review enumerates the predominant applications of large language models (LLMs) in natural language processing (NLP) tasks, with a particular emphasis on the years 2023 to 2025. A particular emphasis is placed on applications pertaining to information retrieval, named entity recognition, text or document classification, text summarization, machine translation, question-and-answer generation, fake news or hate speech detection, and sentiment analysis of text. Furthermore, metrics such as ROUGE, BERT, METEOR, BART, and BLEU scores are presented to evaluate the capabilities of a given language model. The following example illustrates the calculation of scores for the aforementioned metrics, utilizing sentences generated by ChatGPT 3.5, which is free and publicly available.

1 October 2020 in Technical Transactions
Verified
Journal Article
Open access
PDF file
JGJustyna Golec
Justyna Golec
Tomasz HachajTomasz Hachaj
Tomasz Hachaj
In this paper, we compare the following machine learning methods as classifiers for sentiment analysis: k – nearest neighbours (kNN), artificial neural network (ANN), support vector machine (SVM), random forest. We used a dataset containing 5,000 movie reviews in which 2,500 were marked as positive and 2,500 as negative. We chose 5,189 words which have an influence on sentence sentiment. The dataset was prepared using a term document matrix (TDM) and classical multidimensional scaling (MDS). This is the first time that TDM and MDS have been used to choose the characteristics of text in sentiment analysis. In this case, we decided to examine different indicators of the specific classifier, such as kernel type for SVM and neighbour count in kNN. All calculations were performed in the R language, in the program R Studio v 3.5.2. Our work can be reproduced because all of our data sets and source code are public.

30 November 2021 in Entropy
Verified
Journal Article
Open access
PDF file
JGJustyna Golec
Justyna Golec
Tomasz HachajTomasz Hachaj
Tomasz Hachaj
GSGrzegorz Sokal
Grzegorz Sokal
We propose an algorithm to generate graphical summarising of longer text passages using a set of illustrative pictures (TIPS). TIPS is an algorithm using a voting process that uses results of individual “weak” algorithms. The proposed method includes a summarising algorithm that generates a digest of the input document. Each sentence of the text summary is used as the input for further processing by the sentence transformer separately. A sentence transformer performs text embedding and a group of CLIP similarity-based algorithms trained on different image embedding finds semantic distances between images in the illustration image database and the input text. A voting process extracts the most matching images to the text. The TIPS algorithm allows the integration of the best (highest scored) results of the different recommendation algorithms by diminishing the influence of images that are a disjointed part of the recommendations of the component algorithms. TIPS returns a set of illustrative images that describe each sentence of the text summary. Three human judges found that the use of TIPS resulted in an increase in matching highly relevant images to text, ranging from 5% to 8% and images relevant to text ranging from 3% to 7% compared to the approach based on single-embedding schema.

8 June 2026 in Electronics
Verified
Journal Article
Open access
PDF file
JGJustyna Golec
Justyna Golec
Tomasz HachajTomasz Hachaj
Tomasz Hachaj
Many methods have been proposed for visualizing and interpreting the results of artificial intelligence (AI) algorithms. AI explainability (XAI) methods vary in mathematical basis, effectiveness, and scope of application. Knowing this, an important question arises: how do their results differ from a statistical point of view, and are some of them more useful than the others in certain scenarios? Our article aims to assess the robustness of the most popular AI models’ explainability visualization methods and to identify differences in the results obtained. We did this by analyzing fundamental convolutional neural network models that classified 598 cat images from the Oxford III-T Pet database and 580 filtered pictures of Boeing planes from the Aircraft Images Dataset. We performed a comparative analysis of the similarities between methods based on Class Activation Mapping (CAM), gradients, and Local Interpretable Model-agnostic Explanations (LIME). To evaluate them, we used Pearson Correlation Coefficient (CC), Matthews Correlation Coefficient (MCC), Spearman’s Rank, Structural Similarity Index Measure (SSIM), Kullback–Leibler divergence, Intersection over Union (IoU), and Soft IoU. To check the fidelity and robustness of the XAI methods, we used RandomCAM and ran an ablation test, checking for a decrease in prediction confidence as we gradually removed the least significant regions. Our results provide an up-to-date and broad comparative analysis of this field. They can serve as a reference point for machine learning scientists and engineers.

23 June 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Serhii SemenovSerhii Semenov
Serhii Semenov
OWOlga Wasiuta
Olga Wasiuta
AJAlla Jammine
Alla Jammine
JGJustyna Golec
Justyna Golec
MKMagdalena Krupska-Klimczak
Magdalena Krupska-Klimczak
AMArtem Moskalenko
Artem Moskalenko
The object of this research is the process of tracking air targets at the initial stage of radar system operation. The problem lies in the lack of a comprehensive approach to tracking air targets in difficult conditions that is able to dynamically adapt filtering parameters, predict signal reliability, and change the processing mode depending on the level of interference. In conditions of signal loss, noise, and unstable measurement reliability, traditional methods do not provide stable and accurate tracking, especially at the initial stages of radar operation. To address this issue, an intelligent method is proposed that integrates a probabilistic graphical evaluation and review technique (GERT) model, a recursive Kalman filter, and a measurement reliability prediction module based on a long short-term memory (LSTM) neural network. The proposed approach allows for the real-time adaptation of filtering parameters, fusion of local and global trajectory estimates, and dynamic switching between tracking modes depending on the environmental conditions. The dynamic weighting algorithm between model estimates ensures a balance between accuracy and robustness. Simulation experiments confirmed the effectiveness of the method: the root mean square error (RMSE) of coordinate estimation was reduced by 25%; the probability of tracking loss decreased by half (from 0.2 to 0.1); and the accuracy of loss prediction exceeded 85%. The novelty of the approach lies in integrating stochastic modeling, machine learning, and classical filtering into a unified adaptive loop. The proposed system can be adapted to various types of radar and easily scaled to multi-sensor architectures. This makes it suitable for practical implementation in both defense and civilian air object detection systems operating under complex conditions.