Wyniki wyszukiwania - BazTech

1

Application of artificial intelligence methods to determine the optimal process parameters in resistance projection welding of steel nuts

Karski Szymon, Awtoniuk Michał, Szala Mirosław

Applied Computer Science

|

2026

|

Vol. 22, no. 1

184--198

EN

The study employed applied computer modelling to identify the optimal process parameters for resistance projection welding using the original procedure. The influence of technological parameters (welding power, welding time, electrode pressure) on the quality of 184 welded joints produced by resistance projection welding of steel nuts and S235JR steel plates was examined using computer modelling methods, specifically a combination of machine learning and an evolutionary algorithm. A tree-based model was used to identify relationships between signals, and a genetic algorithm for multi-criteria optimisation. The prepared joints were then examined to determine the impact of the welding parameters on the microstructure, Vickers hardness, and strength of the welded joints (as assessed by pull-off testing). The superior strength of the projection welding joints was achieved through short welding times and high power. Additionally, limited welding time effectively restricted the heat-affected zone, reducing weld hardness and improving the joint's plasticity. The original modelling process enables energy consumption (welding current) to be minimised while maximising joint strength, which was the main aim of the work. Finally, the set of optimised welding parameters selected by AI was verified through sample welding and strength testing, and this was confirmed through final strength testing experiments.

2

Processing of Heading Data with Machine Learning for MBES Survey

Kazimierski Witold, Włodarczyk-Sielicka Marta

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2025

|

Vol. 19 No. 3

879--885

EN

The paper presents research on using machine learning algorithms for heading signal smoothing recorded during MBES surveys. Several numerical methods, typically used for time series smoothing and prediction in Data Science applications are tested, like moving average, Gauss filter, Holt Winters filter and Wittaker filter. Additionally, recurrent neural networks are analyzed. Data from real use cases are used and parameters of the methods are verified. The methods are validated against smoothing performance (with variance analysis) and against original function fitting (with RMSE), allowing the qualitative and quantitative assessment. Open source python libraries are used. The results shows efficiency of such approach for this problem.

3

An improved human pose estimation using Deep Neural Network for the optimization of human-robot interactions

Raj Ravi, Kos Andrzej

International Journal of Electronics and Telecommunications

|

2025

|

Vol. 71, No. 4

art. no. 19, s. 1-10

EN

Research shows that mobile support robots are becoming increasingly valuable in various situations, such as monitoring daily activities, providing medical services, and supporting elderly people. For interpreting human conduct and intention, these robots largely depend on human activity recognition (HAR). However, previous awareness of human appearance (human recognition) and recognition of humans for monitoring (human surveillance) are necessary to enable HAR to work with assistance robots. Al-so However, multimodal human behavior recognition is constrained by costly hardware and a rigorous setting, making it challenging to effectively balance inference accuracy and system expense. Naturally, a key problem in human pose or behavior detection is the ability to extract additional purposeful interpretations from easily accessible live videos. In this paper, we employ human pose detection to address the problem and provide well-crafted assessment measures to show demonstrate the effectiveness of our approach, which utilizes deep neural networks (DNNs) This article proposes a human intention detection system that anticipates human intentions in human- and robot-centered scenarios by utilizing the incorporation of visual information as well as input features, including human positions, head orientations, and critical skeletal key points. Our goal is to aid human-robot interactions by helping mobile robots through real-time human pose prediction using the recognition of 18 distinct key points in the body's structure. The effectiveness of this strategy is demonstrated by the suggested study using Python, and the results of simulations verify the reliability and accuracy of this method.

4

Multi-horizon air pollution prediction using interpretable machine learning techniques in a growing urban area

Fetahi Endrit, Ovuoraye Prosper Eguono, Canhasi Ercan, Susuri Arsim, Misini Arta

Ecological Engineering & Environmental Technology

|

2025

|

Vol. 26, iss. 8

97--114

EN

Air pollution continues to be a critical public health and environmental challenge, particularly in fast-growing urban areas. This study presents an interpretable, multi-horizon forecasting framework for PM2.5 concentrations in Prishtina, the capital of Kosovo. Using hourly observations from 2018 to 2024, the study evaluates the predictive performance of five machine learning models: XGBoost, LightGBM, Random Forest, Support Vector Machine, and Linear Regression. Feature engineering, incorporating pollutant lags, rolling statistics, and cyclical time encoding on model performance, was investigated. The results show that among the selected ML models, XGBoost achieves the best one-hour forecast with R2 of 0.862, MAE of 3.524, and RMSE of 6.513, while maintaining reasonable accuracy, with R2 of 0.50 even at 24-hour horizons. To promote transparency, the study employs SHAP (SHapley Additive exPlanations) to quantify feature importance across different forecast horizons. Key drivers include recent PM2.5 lags, wind speed, and meteorological indicators. The proposed framework offers a robust, scalable, and interpretable approach for predicting air pollution, thereby supporting efforts to reduce emissions in Prishtina and similarly affected urban environments, enabling real-time alerts and data-informed environmental policy planning. Scientifically, this study uniquely integrates multi-horizon forecasting using advanced ML models with detailed temporal feature engineering and SHAP interpretability to reveal temporal shifts in feature importance, previously unaddressed systematically in air pollution modeling literature. These insights significantly enhance the understanding of dynamic air pollution interactions and are broadly applicable to urban environments globally with analogous pollution and meteorological dynamics.

5

Prediction of remaining useful life and downtime of induction motors with supervised machine learning

Anindhito Muhammad Dzulfiqar, Suharjito Suharjito

Applied Computer Science

|

2025

|

Vol. 21, no. 3

72--86

EN

This research aims to use a vibration monitoring system along with machine learning techniques to predict the downtime and Remaining Useful Life (RUL) of three-phase induction motors in the manufacturing sector. The study obtains measurement data from accelerometer sensors that collect various parameters related to motor performance. The research includes a data preprocessing stage to handle missing data, select predictor attributes, and remove duplicates. Supervised learning algorithms are applied, including Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Artificial Neural Network (ANN). The results show that DT and NB models have the best performance in downtime classification, achieving 100% accuracy, recall, precision and F1 values. In terms of predicting Remaining Useful Life (RUL), the RF model outperforms the base model and ANN, showing better results in Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and correlation coefficient.

6

Sztuczna inteligencja a bezpieczeństwo zarządzania operacjami lotniskowymi

Żmigrodzka Małgorzata

Rocznik Bezpieczeństwa Morskiego

|

2024

|

R. XVIII

777--794

PL

Nowoczesne lotniska to takie, które korzystają z inteligentnych systemów w celu zwiększenia wydajności operacyjnej, personelu, optymalizacji przepływów pasażerów, poprawy zrównoważonego rozwoju, a także zwiększenia bezpieczeństwa lotnisk. Celem artykułu jest zweryfikowanie aktualnego stanu wiedzy na temat wdrożenia systemów inteligentnego zarządzania operacjami lotniczymi w portach lotniczych. Jednym z istotniejszych aspektów poruszonych w artykule jest etyczne podejście do AI co ma bardzo ważne znaczenie w zakresie budowania zaufania człowieka do rozwoju cyfrowego. Żeby zrozumieć złożoność procesu zarządzania operacjami lotniczymi analizie zostaną poddane istotne dokumenty normatywne a także dostępna literatura w tym obszarze.

EN

Modern airports are those that use intelligent systems to increase operational efficiency, personnel, optimize passenger flows, improve sustainability, and enhance airport security. The purpose of the article is to verify the current state of knowledge on the implementation of intelligent systems for airport operations management. One of the most important aspects addressed in the article is the ethical approach to AI which is very important in terms of building human trust in digital development. To understand the complexity of the process of aviation operations management, relevant normative documents will be analyzed, as well as the available literature in this area.

7

Metody detekcji oraz rozpoznawania sygnałów dronów

Flakowski Wojciech, Krasicki Maciej, Krenz Rafał

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2024

|

nr 4

129--134

PL

Niniejsza publikacja prezentuje przegląd metod detekcji oraz klasyfikacji sygnałów radiowych wykorzystywanych do komunikacji z bezzałogowymi statkami powietrznymi. Artykuł przedstawia zarówno techniki wstępnego przetwarzania sygnału, algorytmy detekcyjne, jak również wybrane sposoby klasyfikacji sygnałów, bazujące na technikach uczenia maszynowego oraz sieciach neuronowych. Dodatkowo prezentowane są architektury wybranych algorytmów detekcyjnych w ujęciu złożoności obliczeniowej oraz skuteczności detekcji pożądanych sygnałów.

EN

This publication presents an overview of detection and classification methods of radio signals used to communicate with unmanned aerial vehicle. The article presents signal pre-processing techniques, detection algorithms, as well as selected signal classification problems based on ma- chine learning techniques and neural networks. Additionally, the architectures of selected detection algorithms are presented in terms of computational complexity and effectiveness of detecting the desired signals.

8

Evolution of FinTech : A systematic literature review

Surabhi R., Kumar Shiva

Nowoczesne Systemy Zarządzania

|

2024

|

T. 19, nr 2

49--62

EN

“FinTech” is a term derived from “Financial technology,” relating to innovative financial solutions permitted by technology. It denotes a contemporary combination of financial services and information technology. However, the integration of finance and technology has deep historical heritages and has advanced through four distinct eras: initially financial globalization then Analogue to digital, after transitioning to digital finance in the late 20th century. Since 2018, a new FinTech era has emerged globally, marked not merely by new financial products, but by state-of-the-art delivery methods driven by swiftly advancing technology, particularly in retail banking. This latest phase, Disruptive Technologies, presents regulatory and operational challenges, emphasizing the need to balance the potential aids of innovation against inherent risks. Our analysis of FinTech’s 157-year evolution maintains against premature or overly rigid regulation at this fundamental crisis.

PL

„FinTech” to termin wywodzący się od „technologii finansowej”, odnoszący się do innowacyjnych rozwiązań finansowych dozwolonych przez technologię. Oznacza nowoczesne połączenie usług finansowych i technologii informacyjnych. Jednak integracja finansów i technologii ma głębokie dziedzictwo historyczne i przeszła przez cztery różne epoki: początkowo globalizację finansową, następnie analogową i cyfrową, a pod koniec XX wieku przejście na finanse cyfrowe. Od 2018 roku na całym świecie nastała nowa era FinTech, naznaczona nie tylko nowymi produktami finansowymi, lecz także najnowocześniejszymi metodami dostarczania, napędzanymi szybko rozwijającą się technologią, szczególnie w bankowości detalicznej. Najnowsza faza, technologie przełomowe, wiąże się z wyzwaniami regulacyjnymi i operacyjnymi, podkreślając potrzebę zrównoważenia potencjalnej pomocy w zakresie innowacji z nieodłącznym ryzykiem. Nasza analiza 157-letniej ewolucji FinTech potwierdza, że w obliczu tego fundamentalnego kryzysu nie ma przedwczesnych lub zbyt sztywnych regulacji.

9

Sztuczna inteligencja, uczenie maszynowe i analiza big data w energetyce przyszłości

Sikorski Wojciech

Kierunek Energetyka

|

2024

|

Nr 3

75--77

PL

Sztuczna inteligencja, uczenie maszynowe i analiza big data odegrają kluczową rolę w transformacji energetyki. Dzięki tym zaawansowanym technologiom możliwe jest zwiększenie efektywności, promowanie zrównoważonego rozwoju i lepsze zarządzanie zasobami energetycznymi.

10

Pupil Diameter and Machine Learning for Depression Detection: a comparative study with deep learning models

Mohamed Islam, El-Wakad Mohamed, Abbas Khaled, Aboamer Mohamed, Mohamed Nader A. Rahman

Applied Computer Science

|

2024

|

Vol. 20, no. 4

77--99

EN

According to the World Health Organization, the Global Mental Health Report estimated that between 251 and 310 million individuals worldwide experienced depression during the first year of the COVID-19 pandemic. Most methods for detecting depression rely on clinical diagnoses and surveys. However, the American Psychiatric Association reports that over 50% of patients do not receive appropriate treatment. This study aims to utilize machine learning and pupil diameter features to identify depression and evaluate the accuracy of these classifiers in comparison to our previous deep learning model. While limited research has explored the use of pupillary diameter as a classification tool for distinguishing between individuals with and without depression, several studies have focused on EEG signals for this purpose. The study involved 58 participants, with 29 classified as depressed and 29 as healthy. The classification was based on statistical features extracted from the Hilbert-Huang Transform. Results showed a significant improvement in average accuracy compared to the authors’ prior work, with the current study achieving 77.72% accuracy, compared to 64.78% in their previous research. Machine learning methods, particularly Bagging, outperformed deep learning models such as AlexNet when classifying data from the left and right eyes individually (90.91% vs. 78.57% for the left eye; 90.91% vs. 71.43% for the right eye). However, when combining data from both eyes, deep learning using AlexNet demonstrated superior performance (98.28% accuracy compared to 93.75% using Bagging with statistical features from both eyes). Despite the higher accuracy of deep learning, machine learning is recommended for its faster execution times.

11

Automatyczne rozpoznawanie treści dokumentów ze wspomaganiem technik sztucznej inteligencji

Gulczyński Tomasz, Eljaszak Piotr

Wiadomości Elektrotechniczne

|

2023

|

R. 91, nr 10

24--27

PL

Przedsiębiorstwa i organizacje przetwarzają ogromne ilości dokumentacji papierowej, co angażuje pracowników do żmudnej i błędogennej pracy. Artykuł opisuje techniki, które można zastosować, aby zautomatyzować ten proces w celu wydobywania istotnych informacji z dokumentów takich jak podmiot i przedmiot umowy, terminy i daty, lokalizacja, dane techniczne obiektów i inne, specyficzne dla danego typu dokumentu. System iDoc stosuje elementy sztucznej inteligencji w rozpoznawaniu treści dokumentów, pozwala osiągnąć 10-krotne przyspieszenie przetwarzania przy zachowaniu wysokiej dokładności, a także umożliwia ręczną weryfikację danych.

EN

In today's business landscape, companies and organizations grapple with processing extensive volumes of paper documents, burdening their employees with tedious and error-prone tasks. This article presents innovative techniques for automating this process by efficiently extracting critical information from various documents, including contract subjects and objects, dates, deadlines, locations, technical data about devices, and other specific contents pertaining to distinct document types. Leveraging Artificial Intelligence, the iDoc system identifies document contents, enabling users to process data ten times faster while maintaining a high level of accuracy. By adopting iDoc, manual data processing becomes obsolete, while still allowing users to validate extracted information.

12

Artificial intelligence versus natural intelligence in mineral processing

Özkan Şafak Gökhan

Physicochemical Problems of Mineral Processing

|

2023

|

Vol. 59, iss. 5

art. no. 167501

EN

This article aims to introduce the terms NI-Natural Intelligence, AI-Artificial Intelligence, ML-Machine Learning, DL-Deep Learning, ES-Expert Systems and etc. used by modern digital world to mining and mineral processing and to show the main differences between them. As well known, each scientific and technological step in mineral industry creates huge amount of raw data and there is a serious necessity to firstly classify them. Afterwards experts should find alternative solutions in order to get optimal results by using those parameters and relations between them using special simulation software platforms. Development of these simulation models for such complex operations is not only time consuming and lacks real time applicability but also requires integration of multiple software platforms, intensive process knowledge and extensive model validation. An example case study is also demonstrated and the results are discussed within the article covering the main inferences, comments and decision during NI use for the experimental parameters used in a flotation related postgraduate study and compares with possible AI use.

13

Restoration of Remote Satellite Sensing Images using Machine and Deep Learning : a Survey

Abdellaoui Meriem, Benabdelkader Souad, Assas Ouarda

Machine Graphics and Vision

|

2023

|

Vol. 32, No. 2

147--167

EN

Remote sensing satellite images are affected by different types of degradation, which poses an obstacle for remote sensing researchers to ensure a continuous and trouble-free observation of our space. This degradation can reduce the quality of information and its effect on the reliability of remote sensing research. To overcome this phenomenon, the methods of detecting and eliminating this degradation are used, which are the subject of our study. The original aim of this paper is that it proposes a state of art of recent decade (2012-2022) on advances in remote sensing image restoration using machine and deep learning, identified by this survey, including the databases used, the different categories of degradation, as well as the corresponding methods. Machine learning and deep learning based strategies for remote sensing satellite image restoration are recommended to achieve satisfactory improvements.

14

Ensemble Model for Network Intrusion Detection System Based on Bagging Using J48

Otoom Mohammad Mahmood, Sattar Khalid Nazim Abdul, Al Sadig Mutasim

Advances in Science and Technology. Research Journal

|

2023

|

Vol. 17, no. 2

322--329

EN

Technology is rising on daily basis with the advancement in web and artificial intelligence (AI), and big data developed by machines in various industries. All of these provide a gateway for cybercrimes that makes network security a challenging task. There are too many challenges in the development of NID systems. Computer systems are becoming increasingly vulnerable to attack as a result of the rise in cybercrimes, the availability of vast amounts of data on the internet, and increased network connection. This is because creating a system with no vulnerability is not theoretically possible. In the previous studies, various approaches have been developed for the said issue each with its strengths and weaknesses. However, still there is a need for minimal variance and improved accuracy. To this end, this study proposes an ensemble model for the said issue. This model is based on Bagging with J48 Decision Tree. The proposed models outperform other employed models in terms of improving accuracy. The outcomes are assessed via accuracy, recall, precision, and f-measure. The overall average accuracy achieved by the proposed model is 83.73%.

15

Inteligentna predykcja stanu zajętości widma z uwzględnieniem wpływu zaników

Wasilewska Małgorzata, Bogucka Hanna

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2022

|

nr 4

481--485

PL

W pracy przedstawiono algorytm predykcji wolnych zasobów w sieciach radiowych 5G. Sygnał 5G nadawany przez użytkownika pierwotnego (PU) poddawany jest zanikom występującym w kanale, co uniemożliwia poprawną detekcję i tym samym właściwą ochronę transmisji PU. Zaproponowany algorytm wykorzystuje możliwości głębokiego uczenia maszynowego w celu rozpoznania zależności czasowo-częstotliwościowych występujących w odebranym sygnale, a także rozpoznania stopnia zaniku. Znając te informacje, algorytm dokonuje lepszej detekcji wolnych zasobów, przy jednoczesnej ochronie transmisji PU.

EN

In this paper, we present a 5G spectrum resources prediction algorithm. 5G signal, transmitted by the primary user (PU) is transmitted through fading channel, which makes negatively affects prediction performance and proper protection of PU’s transmission. The proposed algorithm applies deep learning for estimating fading level and recognizing time-frequency patterns in a received signal. Having this information, the algorithm can perform better signal prediction and PU’s transmission protection.

16

Dynamics of Land Use and Land Cover Change Using Geospatial Techniques – A Case Study of Baghdad, Iraq

Mezaal Mustafa Ridha, Mahmoud Ammar S., Jasim Mohammed A., Naje Ahmed Samir

Ecological Engineering & Environmental Technology

|

2022

|

Vol. 23, iss. 6

216--226

EN

Urban land-cover change is increasing dramatically in most emerging countries. In Iraq and in the capital city (Baghdad). Active socioeconomic progress and political stability have pushed the urban border into the countryside at the cost of natural ecosystems at ever- growing rates. Widely used classifier of Maximum Likelihood was used for classification of 2003 and 2021 Landsat images. This classifier achieved 83.20% and 99.58% overall accuracies for 2003 and 2021 scenes, respectively. This study found that the urban area decreases by 16.4% and the agriculture area decrease by 5.4% over the period. On the other hand, barren land has been expanded up to more than 7% as well as increasing in water land that should probably due to flooding (almost 15% more than 2003). To reduce the undesirable effects of land-cover changes over urban ecosystems in Baghdad and in the municipality in specific, it is suggested that Baghdad develops an urban development policy. The emphasis of policy must be the maintenance an acceptable balance among urban infrastructure development, ecological sustainability and agricultural production.

17

Analiza wydajności bibliotek uczenia maszynowego

Kędziora Ewa Justyna, Maksim Grzegorz Krzysztof

Journal of Computer Sciences Institute

|

2021

|

Vol. 20

230--236

PL

W artykule zaprezentowane zostały wyniki analizy wydajności bibliotek uczenia maszynowego. Badania oparte zostały na narzędziach ML.NET i TensorFlow. Przeprowadzona analiza bazowała na porównaniu czasu działania bibliotek podczas wykrywania obiektów na zbiorach zdjęć, przy użyciu sprzętu o różnych parametrach. Biblioteką, zużywającą mniejsze zasoby sprzętowe, okazała się TensorFlow. Nie bez znaczenia okazał się wybór platformy sprzętowej oraz możliwość użycia rdzeni graficznych, mających wpływ na zwiększenie wydajności obliczeń.

EN

The paper presents results of performance analysis of machine learning libraries. The research was based on ML.NET and TensorFlow tools. The analysis was based on a comparison of running time of the libraries, during detection of objects on sets of images, using hardware with different parameters. The library, consuming fewer hardware resources, turned out to be TensorFlow. The choice of hardware platform and the possibility of using graphic cores, affecting the increase in computational efficiency, turned out to be not without significance.

18

A Deep-Learning-Based Bug Priority Prediction Using RNN-LSTM Neural Networks

Bani-Salameh Hani, Sallam Mohammed, Al shboul Bashar

e-Informatica Software Engineering Journal

|

2021

|

Vol. 15, nr 1

29--45

EN

Context: Predicting the priority of bug reports is an important activity in software maintenance. Bug priority refers to the order in which a bug or defect should be resolved. A huge number of bug reports are submitted every day. Manual filtering of bug reports and assigning priority to each report is a heavy process, which requires time, resources, and expertise. In many cases mistakes happen when priority is assigned manually, which prevents the developers from finishing their tasks, fixing bugs, and improve the quality. Objective: Bugs are widespread and there is a noticeable increase in the number of bug reports that are submitted by the users and teams’ members with the presence of limited resources, which raises the fact that there is a need for a model that focuses on detecting the priority of bug reports, and allows developers to find the highest priority bug reports. This paper presents a model that focuses on predicting and assigning a priority level (high or low) for each bug report. Method: This model considers a set of factors (indicators) such as component name, summary, assignee, and reporter that possibly affect the priority level of a bug report. The factors are extracted as features from a dataset built using bug reports that are taken from closed-source projects stored in the JIRA bug tracking system, which are used then to train and test the framework. Also, this work presents a tool that helps developers to assign a priority level for the bug report automatically and based on the LSTM’s model prediction. Results: Our experiments consisted of applying a 5-layer deep learning RNN-LSTM neural network and comparing the results with Support Vector Machine (SVM) and K-nearest neighbors (KNN) to predict the priority of bug reports. The performance of the proposed RNN-LSTM model has been analyzed over the JIRA dataset with more than 2000 bug reports. The proposed model has been found 90% accurate in comparison with KNN (74%) and SVM (87%). On average, RNN-LSTM improves the F-measure by 3% compared to SVM and 15.2% compared to KNN. Conclusion: It concluded that LSTM predicts and assigns the priority of the bug more accurately and effectively than the other ML algorithms (KNN and SVM). LSTM significantly improves the average F-measure in comparison to the other classifiers. The study showed that LSTM reported the best performance results based on all performance measures (Accuracy = 0.908, AUC = 0.95, F-measure = 0.892).

19

Reduced Complexity by Combining Norm Based Ordering MMSE-BSIDE Detection in MIMO Systems

Jothikumar R., Rangaswamy N.

International Journal of Electronics and Telecommunications

|

2017

|

Vol. 63, No. 3

305--308

EN

The breadth first signal decoder (BSIDE) is well known for its optimal maximum likelihood (ML) performance with lesser complexity. In this paper, we analyze a multiple-input multiple-output (MIMO) detection scheme that combines; column norm based ordering minimum mean square error (MMSE) and BSIDE detection methods. The investigation is carried out with a breadth first tree traversal technique, where the computational complexity encountered at the lower layers of the tree is high. This can be eliminated by carrying detection in the lower half of the tree structure using MMSE and upper half using BSIDE, after rearranging the column of the channel using norm calculation. The simulation results show that this approach achieves 22% of complexity reduction for 2x2 and 50% for 4x4 MIMO systems without any degradation in the performance.

20

Can Machine Learning Learn a Decision Oracle for NP Problems? A Test on SAT

Grozea C., Popescu M.

Fundamenta Informaticae

|

2014

|

Vol. 131, nr 3-4

441--450

EN

This note describes our experiments aiming to empirically test the ability of machine learning models to act as decision oracles for NP problems. Focusing on satisfiability testing problems, we have generated random 3-SAT instances and found out that the correct branch prediction accuracy reached levels in excess of 99%. The branching in a simple backtracking-based SAT solver has been reduced in more than 90% of the tested cases, and the average number of branching steps has reduced to between 1/5 and 1/3 of the one without the machine learning model. The percentage of SAT instances where the machine learned heuristic-enhanced algorithm solved SAT in a single pass reached levels of 80-90%, depending on the set of features used.