Adam Hartveg

Mr. Adam Hartveg

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
25 September 2024 in Computers in Biology and Medicine
Verified
Journal Article
Open access
Lehel Dénes-FazakasLehel Dénes-Fazakas
Lehel Dénes-Fazakas
BSBarbara Simon
Barbara Simon
AHAdam Hartveg
Adam Hartveg
László SzilágyiLászló Szilágyi
László Szilágyi
Levente KovácsLevente Kovács
Levente Kovács
György EignerGyörgy Eigner
György Eigner
For individuals diagnosed with diabetes mellitus, it is crucial to keep a record of the carbohydrates consumed during meals, as this should be done at least three times daily, amounting to an average of six meals. Unfortunately, many individuals tend to overlook this essential task. For those who use an artificial pancreas, carbohydrate intake proves to be a critical factor, as it can activate the insulin pump in the artificial pancreas to deliver insulin to the body. To address this need, we have developed personalized deep learning model that can accurately detect carbohydrate intake with a high degree of accuracy. Our study employed a publicly available dataset gathered by an Inertial Measurement Unit (IMU), which included accelerometer and gyroscope data. The data was sampled at a rate of 15 Hz, necessitating preprocessing. For our tailored to the patient model, we utilized a recurrent network comprising Long short-term memory (LSTM) layers. Our findings revealed a median F1 score of 0.99, indicating a high level of accuracy. Additionally, the confusion matrix displayed a difference of only 6 s, further validating the model's accuracy. Therefore, we can confidently assert that our model architecture exhibits a high degree of accuracy. Our model performed well above 90% on the dataset, with most results between 98%-99%. The recurrent networks improved the problem-solving capabilities significantly, though some outliers remained. The model's average prediction latency was 5.5 s, suggesting that later meal predictions result in extended meal progress predictions. The dataset's limitation of mostly single-day data points raises questions about multi-day performance, which could be explored by collecting multi-day data, including night periods. Future enhancements might involve transformer networks and shorter time windows to improve model responsiveness and accuracy. Therefore, we can confidently assert that our model exhibits a high degree of accuracy.

22 May 2024 in Information
Verified
Journal Article
Open access
PDF file
BSBarbara Simon
Barbara Simon
AHAdam Hartveg
Adam Hartveg
Lehel Dénes-FazakasLehel Dénes-Fazakas
Lehel Dénes-Fazakas
György EignerGyörgy Eigner
György Eigner
László SzilágyiLászló Szilágyi
László Szilágyi
In recent times, the prevalence of chatbot technology has notably increased, particularly in the realm of medical assistants. However, there is a noticeable absence of medical chatbots that cater to the Hungarian language. Consequently, Hungarian-speaking people currently lack access to an automated system capable of providing assistance with their health-related inquiries or issues. Our research aims to establish a competent medical chatbot assistant that is accessible through both a website and a mobile app. It is crucial to highlight that the project’s objective extends beyond mere linguistic localization; our goal is to develop an official and effectively functioning Hungarian chatbot. The assistant’s task is to answer medical questions, provide health advice, and inform users about health problems and treatments. The chatbot should be able to recognize and interpret user-provided text input and offer accurate and relevant responses using specific algorithms. In our work, we put a lot of emphasis on having steady input so that it can detect all the diseases that the patient is dealing with. Our database consisted of sentences and phrases that a user would type into a chatbot. We assigned health problems to these and then assigned the categories to the corresponding cure. Within the research, we developed a website and mobile app, so that users can easily use the assistant. The app plays a particularly important role for users because it allows them to use the assistant anytime and anywhere, taking advantage of the portability of mobile devices. At the current stage of our research, the precision and validation accuracy of the system is greater than 90%, according to the selected test methods.

10 April 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Lehel Dénes-FazakasLehel Dénes-Fazakas
Lehel Dénes-Fazakas
BSBarbara Simon
Barbara Simon
AHAdam Hartveg
Adam Hartveg
Levente KovácsLevente Kovács
Levente Kovács
Eva DulfEva Dulf
Eva Dulf
György EignerGyörgy Eigner
György Eigner
Diabetes mellitus (DM) is a persistent metabolic disorder associated with the hormone insulin. The two main types of DM are type 1 (T1DM) and type 2 (T2DM). Physical activity plays a crucial role in the therapy of diabetes, benefiting both types of patients. The detection, recognition, and subsequent classification of physical activity based on type and intensity are integral components of DM treatment. The continuous glucose monitoring system (CGMS) signal provides the blood glucose (BG) level, and the combination of CGMS and heart rate (HR) signals are potential targets for detecting relevant physical activity from the BG variation point of view. The main objective of the present research is the developing of an artificial intelligence (AI) algorithm capable of detecting physical activity using these signals. Using multiple recurrent models, the best-achieved performance of the different classifiers is a 0.99 area under the receiver operating characteristic curve. The application of recurrent neural networks (RNNs) is shown to be a powerful and efficient solution for accurate detection and analysis of physical activity in patients with DM. This approach has great potential to improve our understanding of individual activity patterns, thus contributing to a more personalized and effective management of DM.

10 July 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
AHAdam Hartveg
Adam Hartveg
DDDomonkos Dékány
Domonkos Dékány
BSBarbara Simon
Barbara Simon
SLSzász László
Szász László
Lehel Dénes-FazakasLehel Dénes-Fazakas
Lehel Dénes-Fazakas
Large language models are increasingly used for tasks that require prediction, interpretation, and decision support, yet their behavior in complex sports forecasting is still not well understood. This study evaluates how different large language models perform in predicting the FIFA World Cup 2026 under several forecasting settings. The benchmark covers three levels of tournament prediction: the group stage, the knockout stage, and the final outcome of the competition. The evaluation includes proprietary models, cloud hosted models, and open weight models, tested with standard prompting, reasoning based inference, web search support, and agent based forecasting workflows. The analysis goes beyond simple winner prediction and examines structural validity, qualification accuracy, hallucination rate, consistency, forecast plausibility, and agreement with mainstream football expectations. The results indicate that access to current external information has the strongest effect on forecasting reliability. In the OpenAI based experiments, web supported agent configurations increased structural validity from 58.50 to 90.87 and reduced hallucinations by 78.7 percent. A similar improvement was observed in the Ollama and cloud model group, where web access increased validity from 53.39 to 97.04 and reduced hallucinations by 75.7 percent. Reasoning improved the internal logic of several forecasts, but when it was used without external grounding, it sometimes produced confident but unsupported predictions. These findings suggest that reasoning alone is not sufficient for tournament forecasting when the task depends on current squads, recent performance, injuries, rankings, and evolving football context. The best results were achieved when models combined structured reasoning with access to up to date information. Overall, this study provides a reproducible evaluation framework for large language model based sports forecasting and shows how grounding, reasoning, and model design influence prediction quality in a complex international tournament setting.

4 September 2026 in Forecasting
Verified
Journal Article
Open access
PDF file
AHAdam Hartveg
Adam Hartveg
DDDomonkos Dékány
Domonkos Dékány
BSBarbara Simon
Barbara Simon
SLSzász László
Szász László
Lehel Dénes-FazakasLehel Dénes-Fazakas
Lehel Dénes-Fazakas
Large language models are increasingly used for tasks that require prediction, interpretation, and decision support, yet their behavior in complex sports forecasting is still not well understood. This study evaluates how different large language models perform in predicting the FIFA World Cup 2026 under several forecasting settings. The benchmark covers three levels of tournament prediction: the group stage, the knockout stage, and the final outcome of the competition. The evaluation includes proprietary models, cloud hosted models, and open weight models, tested with standard prompting, reasoning-based inference, web search support, and agent-based forecasting workflows. The analysis goes beyond simple winner prediction and examines structural validity, qualification accuracy, hallucination rate, consistency, forecast plausibility, and agreement with mainstream football expectations. The results indicate that access to current external information has the strongest effect on forecasting reliability. In the OpenAI-based experiments, web supported agent configurations increased structural validity from 58.50 to 90.87 and reduced hallucinations by 78.7 percent. A similar improvement was observed in the Ollama and cloud model group, where web access increased validity from 53.39 to 97.04 and reduced hallucinations by 75.7 percent. Reasoning improved the internal logic of several forecasts, but when it was used without external grounding, it sometimes produced confident but unsupported predictions. These findings suggest that reasoning alone is not sufficient for tournament forecasting when the task depends on current squads, recent performance, injuries, rankings, and evolving football context. The best results were achieved when models combined structured reasoning with access to up to date information. Overall, this study provides a reproducible evaluation framework for large language model-based sports forecasting and shows how grounding, reasoning, and model design influence prediction quality in a complex international tournament setting.