Using Generative AI to Transform Poultry Farming with Computer Vision

A new scientific publication by researchers from the University of Donja Gorica and DunavNET explores the innovative use of generative AI in digital agriculture. Titled “Evaluating the FLUX.1 Synthetic Data on YOLOv9 for AI-Powered Poultry Farming”, the study demonstrates how synthetic data, generated using FLUX.1, can effectively enhance deep learning models for chicken detection in smart farms. The paper was published in the Journal of Applied Sciences, a special issue dedicated to the application of computer vision in industry and agriculture [link].

Using generative AI to create sytnhetic data used to train computer vision models for agriculture sector

By combining real and AI-generated images and streamlining annotation with Grounding DINO and SAM2 models, the team achieved impressive detection accuracy—proving that generative AI can bridge the data gap in precision farming. This research is a part of broader effortsincluding PhD research of mr. Stevan Cakic, as well as collaboration with company that produces smart agriculture platform. This was also supported through EuroCC Montenegro initiatives, showcasing how high-performance computing and AI can drive sustainable innovation in agriculture.

High-level architectureused for experiment execution

ABSTRACT – This research explores the role of synthetic data in enhancing the accuracy of deep learning models for automated poultry farm management. A hybrid dataset was created by combining real images of chickens with 400 FLUX.1 [dev] generated synthetic images, aiming to reduce reliance on extensive manual data collection. The YOLOv9 model was trained on various dataset compositions to assess the impact of synthetic data on detection performance. Additionally, automated annotation techniques utilizing Grounding DINO and SAM2 streamlined dataset labeling, significantly reducing manual effort. Experimental results demonstrate that models trained on a balanced combination of real and synthetic images performed comparably to those trained on larger, augmented datasets, confirming the effectiveness of synthetic data in improving model generalization. The best-performing model trained on 300 real and 100 synthetic images achieved mAP = 0.829, while models trained on 100 real and 300 synthetic images reached mAP = 0.820, highlighting the potential of generative AI to bridge data scarcity gaps in precision poultry farming. This study demonstrates that synthetic data can enhance AI-driven poultry monitoring and reduce the importance of collecting real data.

Click on image to open

NCC Montenegro Supported Paper to be presented at the INFOTEH conference

At the 24th International Symposium INFOTEH-JAHORINA (March 19-21, 2025), the paper “Transforming Matrix Problem Solving with Intelligent Tutoring Systems” will be presented. It explores the use of OCR and NLP technologies for automated matrix processing through an intelligent tutoring chatbot.

This effort was supported by the NCC Montenegro and resulted in a system that utilizes EasyOCR and the Qwen2-Math-7B-Instruct model for matrix operations with 95% accuracy. Implemented on our HPC cluster, it enables fast and precise processing of user queries, enhancing learning through AI-powered tools. The paper will be presented by Ms. Enisa Trubljanin and Mr Elvis Taruh, students at the Master AI program at UDG.

Click on image for sessions schedule for accepted papers.

HPC/AI for Tuberculosis Detection: Advancing X-Ray Diagnosis with Deep Learning at IT2025

Researchers from the University of Donja Gorica presented a deep learning model for automated tuberculosis detection from chest X-rays at IEEE IT2025 conference. Using a convolutional neural network (CNN), the model classifies images as normal or tuberculosis-positive with an impressive 97.55% accuracy. This breakthrough has the potential to speed up diagnoses, reduce radiologist workload, and improve early detection rates, particularly in low-resource healthcare settings. By leveraging AI for fast and reliable medical imaging analysis, this research highlights the growing role of computer vision in modern healthcare and its ability to enhance efficiency and accuracy in disease detection.

ABSTRACT – This article presents a deep learning model that enables fast and accurate diagnosis of tuberculosis based on chest X-rays. The developed model uses convolutional neural network that enable the automatic classification of chest x-rays into one of two classes: Normal or Tuberculosis with a high degree of accuracy. The model achieved an accuracy of 97.55% on the test data set, indicating its potential to open new perspectives for medical professionals in establishing a tuberculosis diagnosis. This model can significantly speed up the diagnostic process, reducing the workload of medical workers and increasing their productivity in the fight against tuberculosis, one of the most common lung diseases.

Paper on Preserving Cultural Heritage Through Speech Synthesis at IT2025

At the IT2025 IEEE Conference in Žabljak, researchers from the University of Donja Gorica presented a study on voice cloning and text-to-speech (TTS) technology for cultural heritage preservation. Their research compared state-of-the-art AI models, including Realtime Voice Cloning (RVC), Tortoise AI, Bark, and Coqui AI, to evaluate how small, high-quality datasets can produce more accurate and natural-sounding speech than large, unstructured ones. The study highlights the potential of AI in preserving the Montenegrin language and oral traditions, enabling the creation of audiobooks, digital archives, and interactive experiences. This research paves the way for more accessible educational resources and enhanced cultural engagement using AI-driven speech synthesis.

ABSTRACT – This research presents a comparative analysis of modern voice cloning systems, focusing on their ability to generate high-quality speech from limited training data. The paper aims to demonstrate that carefully curated smaller datasets can produce superior results to larger, less structured datasets. The investigation of multiple state-of-the-art models, including Realtime Voice Cloning (RVC), Tortoise AI, Bark, and Coqui AI, establishes optimal data preparation protocols and identifies critical factors in training data quality, with particular emphasis on applications for the Montenegrin language and cultural preservation.

Paper on AI-Driven Breast Cancer Detection with Deep Learning at IT2025

At the IT2025 IEEE Conference in Žabljak, researchers from the University of Donja Gorica presented their latest study on using Artificial Intelligence (AI) for breast cancer diagnostics. The research explores the application of deep learning models, ResNet152 and DenseNet121, to analyze mammographic images. Beyond the clinical results, the study emphasizes the implications of leveraging high-performance computing (HPC) infrastructure to optimize model training and evaluation. By porting the experimental setup to HPC resources, the research opens pathways for faster development cycles, the exploration of more complex architectures, and scalability for real-world implementation. 

ABSTRACT – Artificial Intelligence is rapidly advancing the medical field by providing innovative disease diagnosis, treatment, and research approaches. This study explores the application of artificial intelligence in breast cancer diagnostics, focusing on using convolutional neural networks and deep learning to analyze mammographic images. ResNet152 and DenseNet121 models were used to classify malignant changes, achieving AUC scores exceeding 0.9, demonstrating their clinical utility. The research emphasizes how artificial intelligence can enhance screening efficiency, expedite diagnostic processes, and facilitate personalized treatment approaches. Ethical considerations, including patient safety and the transparency of artificial intelligence systems, were also analyzed. The findings underscore the potential of artificial intelligence to transform diagnostic procedures for breast cancer and highlight the importance of further research to integrate these technologies into clinical practice.

Master thesis: HPC/AI for breast cancer detection

Ms. Tamara Pavlovic defended her MSc thesis on the use of HPC/AI for creating prediction models for breast cancer detection on 23.10.2024. With the support from NCC Montenegro, Ms Pavlovic did her research in the context of the HPC4S3ME project and the focus was on AI and computer vision applications in medicine. From the motivational point of view, we congratulate Tamara for finalizing and defending her thesis during the Breast Cancer Awareness Month (‘Pink October’) as people around the world adopt the pink colour and display a pink ribbon to raise awareness about breast health.

ABSTRACT – Artificial Intelligence (AI) is revolutionizing numerous sectors, including medicine, by offering innovative methods for diagnosing, treating, and researching diseases. This master’s thesis focuses on the application of AI in the diagnosis of breast cancer, using computer vision algorithms to analyze mammographic images. Through a combination of convolutional neural networks (CNNs) and deep learning, models have been developed that identify malignant changes, potentially contributing to earlier and more precise disease detection. The thesis examines in detail how AI can improve the efficiency of screening processes, reduce the time required for diagnosis, and enable a more personalized approach to treatment. In addition to technological progress, ethical issues such as patient safety and the transparency of AI systems are also considered. The results of this study confirm that the application of AI in breast cancer diagnostics can significantly enhance medical procedures. The models tested, ResNet152 and DenseNet121, demonstrated quite good performance in classifying breast cancer. Their AUC scores, which exceed the threshold of 0.9, indicate their potential for use in clinical practice. These findings not only contribute to the improvement of diagnostic processes but also open up opportunities for further research and development of AI technologies in medicine.

This research was done in th context of HPC4S3ME and with the support from EUROCC NCC Montenegro
Ms Pavlovic finalized her thesis during the Breast Cancer Awareness Month (‘Pink October’)

Master thesis: HPC/AI in precision agriculture

Mr Mato Martinovic defended his MSc thesis on 23 octiber 2024. His research focused on detecting plant deseases for applications in vineyards. He was experimenting with HPC/AI and computer vision. He is one of the latest graduates from the AI master program created under EUROCC project and his mentoring was done with the support of EUROCC NCC Montenegro.

ABSTRACT – This research analyzes the use of computer vision in the field of viticulture. The thesis describes problems in viticulture, computer vision and its use in this field. The paper analyzed the performance of ResNet50, VGG16 and MobileNet models in the classification of diseases and grapevine species. The models achieved accuracy of 98.67%, 97.28%, and 98.72% on the original test data set, while on the extended one, they achieved 87.47%, 72.07%, and 86.64%, respectively, when classifying diseases. In species classification, the models achieved accuracies of 70%, 78% and 88% on the original test data set, and 66%, 51% and 72% on the extended one, respectively. The VGG-16 model had the largest difference in accuracy over extended data, while ResNet had the smallest decrease in accuracy in both cases, which implies that ResNet generalizes the data better. The paper presents the process of creating a platform that allows users to post an image and receive a prediction value through a mobile application.

HPC/AI and computer vision for applications in smart viticulture