Nevzudin Buzađija
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nevzudin Buzađija has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Elmin Marevac
Polytechnic Faculty, University of Zenica, 72000 Zenica, Bosnia and Herzegovina
2 shared publications - Esad Kadušić
Faculty of Educational Sciences, University of Sarajevo, 71000 Sarajevo, Bosnia and Herzegovina
2 shared publications - Natasa Zivic
Faculty of Digital Transformation, Leipzig University of Applied Sciences, 04277 Leipzig, Germany
2 shared publications - Samir Lemeš
University of Zenica
2 shared publications - Ajna Fetić1 shared publication
- Amar Ćatović
Isatis Software Solutions, Sarajevo, Bosnia and Herzegovina
1 shared publication
Latest Publications
- Open Access
- 10 September 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (9) , 572
Multimodal Video Summarization Using Machine Learning: A Comprehensive Benchmark of Feature Selection and Classifier Performance
The exponential growth of user-generated video content necessitates efficient summarization systems for improved accessibility, retrieval, and analysis. This study presents and benchmarks a multimodal video summarization framework that classifies segments as informative or non-informative using audio, visual, and fused features. Sixty hours of annotated video across ten diverse categories were analyzed. Audio features were extracted with pyAudioAnalysis, while visual features (colour histograms, optical flow, object detection, facial recognition) were derived using OpenCV. Six supervised classifiers—Naive Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and XGBoost—were evaluated, with hyperparameters optimized via grid search. Temporal coherence was enhanced using median filtering. Random Forest achieved the best performance, with 74% AUC on fused features and a 3% F1-score gain after post-processing. Spectral flux, grayscale histograms, and optical flow emerged as key discriminative features. The best model was deployed as a practical web service using TensorFlow and Flask, integrating informative segment detection with subtitle generation via beam search to ensure coherence and coverage. System-level evaluation demonstrated low latency and efficient resource utilization under load. Overall, the results confirm the strength of multimodal fusion and ensemble learning for video summarization and highlight their potential for real-world applications in surveillance, digital archiving, and online education.
- 10 September 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (9) , 572
Open AccessMultimodal Video Summarization Using Machine Learning: A Comprehensive Benchmark of Feature Selection and Classifier Performance
The exponential growth of user-generated video content necessitates efficient summarization systems for improved accessibility, retrieval, and analysis. This study presents and benchmarks a multimodal video summarization framework that classifies segments as informative or non-informative using audio, visual, and fused features. Sixty hours of annotated video across ten diverse categories were analyzed. Audio features were extracted with pyAudioAnalysis, while visual features (colour histograms, optical flow, object detection, facial recognition) were derived using OpenCV. Six supervised classifiers—Naive Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and XGBoost—were evaluated, with hyperparameters optimized via grid search. Temporal coherence was enhanced using median filtering. Random Forest achieved the best performance, with 74% AUC on fused features and a 3% F1-score gain after post-processing. Spectral flux, grayscale histograms, and optical flow emerged as key discriminative features. The best model was deployed as a practical web service using TensorFlow and Flask, integrating informative segment detection with subtitle generation via beam search to ensure coherence and coverage. System-level evaluation demonstrated low latency and efficient resource utilization under load. Overall, the results confirm the strength of multimodal fusion and ensemble learning for video summarization and highlight their potential for real-world applications in surveillance, digital archiving, and online education.
- Open Access
- 18 March 2025
- Published by IntechOpen
Evaluation of U-Net Algorithm Precision for Segmentation and Classification of Breast and Lung Images on CBIS-DDSM and LIDC-IDRI Datasets
Cancer is the leading disease in the world in terms of increasing numbers of new patients and deaths annually, making it one of the most formidable diseases today. Lung cancer and breast cancer are widely acknowledged as two of the most prevalent forms of cancer, both falling under the carcinoma subtype. Early detection of these cancers is particularly crucial for patient outcomes. With cancer being a longstanding health challenge, comprehensive datasets containing essential information for cancer prediction and diagnosis are now available. Radiologists primarily rely on Computed Tomography (CT) scans for cancer diagnosis. However, the escalating demand for CT scans and their interpretation has led to radiologists prioritizing throughput over the quality of readings. To address this challenge, Computer-Aided Diagnosis (CAD) systems have been introduced into medical practice. This research paper delves into evaluating the accuracy of the implemented U-Net algorithm for segmentation and classification on two prominent medical datasets: Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The primary objective of the study is to assess the algorithm’s performance in accurately identifying and classifying Regions of Interest (ROIs) in breast and lung medical images.
- 18 March 2025
- Published by IntechOpen
Open AccessEvaluation of U-Net Algorithm Precision for Segmentation and Classification of Breast and Lung Images on CBIS-DDSM and LIDC-IDRI Datasets
Cancer is the leading disease in the world in terms of increasing numbers of new patients and deaths annually, making it one of the most formidable diseases today. Lung cancer and breast cancer are widely acknowledged as two of the most prevalent forms of cancer, both falling under the carcinoma subtype. Early detection of these cancers is particularly crucial for patient outcomes. With cancer being a longstanding health challenge, comprehensive datasets containing essential information for cancer prediction and diagnosis are now available. Radiologists primarily rely on Computed Tomography (CT) scans for cancer diagnosis. However, the escalating demand for CT scans and their interpretation has led to radiologists prioritizing throughput over the quality of readings. To address this challenge, Computer-Aided Diagnosis (CAD) systems have been introduced into medical practice. This research paper delves into evaluating the accuracy of the implemented U-Net algorithm for segmentation and classification on two prominent medical datasets: Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The primary objective of the study is to assess the algorithm’s performance in accurately identifying and classifying Regions of Interest (ROIs) in breast and lung medical images.
- Open Access
- 7 January 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (1) , 23
Framework Design for the Dynamic Reconfiguration of IoT-Enabled Embedded Systems and “On-the-Fly” Code Execution
Embedded systems, particularly when integrated into the Internet of Things (IoT) landscape, are critical for projects requiring robust, energy-efficient interfaces to collect real-time data from the environment. As these systems become complex, the need for dynamic reconfiguration, improved availability, and stability becomes increasingly important. This paper presents the design of a framework architecture that supports dynamic reconfiguration and “on-the-fly” code execution in IoT-enabled embedded systems, including a virtual machine capable of hot reloads, ensuring system availability even during configuration updates. A “hardware-in-the-loop” workflow manages communication between the embedded components, while low-level coding constraints are accessible through an additional abstraction layer, with examples such as MicroPython or Lua. The study results demonstrate the VM’s ability to handle serialization and deserialization with minimal impact on system performance, even under high workloads, with serialization having a median time of 160 microseconds and deserialization having a median of 964 microseconds. Both processes were fast and resource-efficient under normal conditions, supporting real-time updates with occasional outliers, suggesting room for optimization and also highlighting the advantages of VM-based firmware update methods, which outperform traditional approaches like Serial and OTA (Over-the-Air, the ability to update or configure firmware, software, or devices via wireless connection) updates by achieving lower latency and greater consistency. With these promising results, however, challenges like occasional deserialization time outliers and the need for optimization in memory management and network protocols remain for future work. This study also provides a comparative analysis of currently available commercial solutions, highlighting their strengths and weaknesses.
- 7 January 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (1) , 23
Open AccessFramework Design for the Dynamic Reconfiguration of IoT-Enabled Embedded Systems and “On-the-Fly” Code Execution
Embedded systems, particularly when integrated into the Internet of Things (IoT) landscape, are critical for projects requiring robust, energy-efficient interfaces to collect real-time data from the environment. As these systems become complex, the need for dynamic reconfiguration, improved availability, and stability becomes increasingly important. This paper presents the design of a framework architecture that supports dynamic reconfiguration and “on-the-fly” code execution in IoT-enabled embedded systems, including a virtual machine capable of hot reloads, ensuring system availability even during configuration updates. A “hardware-in-the-loop” workflow manages communication between the embedded components, while low-level coding constraints are accessible through an additional abstraction layer, with examples such as MicroPython or Lua. The study results demonstrate the VM’s ability to handle serialization and deserialization with minimal impact on system performance, even under high workloads, with serialization having a median time of 160 microseconds and deserialization having a median of 964 microseconds. Both processes were fast and resource-efficient under normal conditions, supporting real-time updates with occasional outliers, suggesting room for optimization and also highlighting the advantages of VM-based firmware update methods, which outperform traditional approaches like Serial and OTA (Over-the-Air, the ability to update or configure firmware, software, or devices via wireless connection) updates by achieving lower latency and greater consistency. With these promising results, however, challenges like occasional deserialization time outliers and the need for optimization in memory management and network protocols remain for future work. This study also provides a comparative analysis of currently available commercial solutions, highlighting their strengths and weaknesses.
- Open Access
- 30 April 2022
- Published by "IMS" Vogosca in Science, Engineering and Technology
- Vol. 2 (1) , 30-37
Microservice development using RabbitMQ message broker
Nowadays, when applications are being developed faster with the introduction of agile methodologies and new technologies, microservices are emerging. The microservices make applications easier to create and maintain when broken down into smaller parts, which form a whole application. RabbitMQ acts as an intermediary between the various services. It reduces the load and delivery time on server web applications by delegating tasks that would typically take a lot of time and resources. Message queuing allows web servers to respond quickly to requests rather than being forced to perform complex procedures that can take more time and resources. AMQP (Advanced Message Queuing Protocol) is a message protocol that deals with publishers and consumers like any other messaging system. Publishers produce messages while consumers download and process them. The job of message brokers, such as RabbitMQ, is to ensure that messages from publishers go to the right consumers. To do this, the broker uses two key components: exchange and order. We demonstrated that the style of microservice architecture is an approach to the development of an application as a set of small services, each in charge of its own process and communication with other services.
- 30 April 2022
- Published by "IMS" Vogosca in Science, Engineering and Technology
- Vol. 2 (1) , 30-37
Open AccessMicroservice development using RabbitMQ message broker
Nowadays, when applications are being developed faster with the introduction of agile methodologies and new technologies, microservices are emerging. The microservices make applications easier to create and maintain when broken down into smaller parts, which form a whole application. RabbitMQ acts as an intermediary between the various services. It reduces the load and delivery time on server web applications by delegating tasks that would typically take a lot of time and resources. Message queuing allows web servers to respond quickly to requests rather than being forced to perform complex procedures that can take more time and resources. AMQP (Advanced Message Queuing Protocol) is a message protocol that deals with publishers and consumers like any other messaging system. Publishers produce messages while consumers download and process them. The job of message brokers, such as RabbitMQ, is to ensure that messages from publishers go to the right consumers. To do this, the broker uses two key components: exchange and order. We demonstrated that the style of microservice architecture is an approach to the development of an application as a set of small services, each in charge of its own process and communication with other services.