Publications Archives - Page 7 of 9

26.11.2022.06.01.2023.

A scientific paper at IEEE ACIT 2022 conference

Researchers from UDG and NCC Montenegro presented a scientific paper at the 2022 International Arab Conference on Information Technology (ACIT). The conference took place at the Al Ain University – Abu Dhabi Campus on November 22-24, 2022. The paper “Overcoming Limitations of Statistical Methods with Artificial Neural Networks” was authored by M. Grebovic, L. Filipovic, I. Katnic, M. Vukotic, and T. Popovic. More information about the conference is available here. The paper is available at IEEE Xplore at the following link.

ABSTRACT – Traditional statistical models as tools for summarizing patterns and regularities in observed data can be used for making predictions. However, statistical prediction models contain small number of important predictors, which means limited informative capability. Also, predictive statistical models that provide some type of pseudo-correct regular statistical patterns, are used without previous understanding of the used data causality. Machine Learning (ML) algorithms as area in Artificial Intelligence (AI) provide the ability to interpret and understand data in more sophisticated way. Artificial Neural Networks as kind of ML methods use non-linear algorithms, considering links and associations between parameters, while statistical use one-step-ahead linear processes to improve only short-term prediction’s accuracy by minimizing cost function. Disregarding that designing an optimal artificial neural network is very complex process, they are considered as potential solution for overcoming main flaws of statistical prediction models. However, they will not automatically improve predictions accuracy, so several artificial neural networks and traditional statistical methods are evaluated and analyzed through accuracy measures for prediction purposes in various fields of applications. Based on gained results, couple of techniques for improving artificial neural networks are proposed to get better accuracy results than statistical predictive methods.

Click on image to open link to IEEE Xplore

20.10.2022.27.10.2022.

BSc Thesis: AI/ML Computer Vision for Smart Parking

Ms Zoja Scekic, a student of the Faculty of Applied Sciences, defended her BSc Thesis in Electrical Engineering and Computer Science. The topic of the thesis work was the use of machine learning to detect and classify the parking spaces by processing images from camera sensors. Such a solution could find application in Smart city solutions. The work focused on the creation of a prediction model as well as validation with images collected at the UDG parking. She has done her thesis work under the supervision of prof. Tomo Popovic, PhD, and mr Stevan Cakic, MSc.

ABSTRACT – Smart city is one area with the growing use of Internet of Things and Artificial Intelligence. The concept of smart cities relies on making quality of life better, and solving important problems, such as global warming, public health, energy and resources. Smart parking management is one of the smart city use cases. This paper describes the use of deep learning algorithms to process images of parking lots and determine their current occupancy. The development of prediction models was done using PKLot dataset with 12417 images, Detectron2 software library, and Faster R-CNN algorithm. The resulting models can be integrated into parking space sensors and used for building smart parking solutions, and thus lead to more efficient use of space in urban areas, reduced traffic congestion, as well as reducing parking surfing to minimum.

Another excellent graduate from the Faculty of Applied Sciences

04.08.2022.27.10.2022.

IEEE COINS 2022: HPC and Deep Learning for Computer Vision in Smart Farms

Researchers from EuroCC Montenegro presented two papers at the IEEE International Conference on Omni-Layer Intelligent Systems (COINS). IEEE COINS (link) is the right place to be. IEEE COINS brings together experts in Digital Transformation (from AI and IoT to Cloud, Blockchain, Cybersecurity, and Robotics) from around the globe. IEEE COINS includes a multi-disciplinary program from technical research papers, to panels, workshops, and tutorials on the latest technology developments and innovations addressing all important aspects of the IoT & AI ecosystem. The conference took place 1-3 August in Barcelona.

This paper was a result of the collaboration on FF4EuroHPC application experiment project called AIMHiGH that focuses on computer vision and the use of HPC to develop object detection prediction models for the use in smart agriculture, more specifically in the poultry sector. The title of the paper is “Developing Object Detection Models for Camera Applications in Smart Poultry Farms”.

ABSTRACT – This paper proposes the use of high-performance computing and deep learning to create prediction models that can be deployed as a part of smart agriculture solutions in the poultry sector. The idea is to create object detection models that can be ported onto edge devices equipped with camera sensors for the use in Internet of Things systems for poultry farms. The object detection prediction models could be used to create smart camera sensors that could evolve into sensors for counting chickens or detecting dead ones. Such camera sensor kits could become a part of digital poultry farm management systems in shortly. The paper discusses the approach to the development and selection of machine learning and computational tools needed for this process. Initial results, based on the use of Faster R-CNN network and high-performance computing are presented together with the metrics used in the evaluation process. The achieved accuracy is satisfactory and allows for easy counting of chickens. More experimentation is needed with network model selection and training configurations to increase the accuracy and make the prediction useful for developing a dead chicken detector. (link)

03.08.2022.27.10.2022.

IEEE COINS 2022: Detecting Pneumonia with TensorFlow and CNNs

Click on image to open the conference website

The paper called “Detecting Pneumonia with TensorFlow and Convolutional Neural Networks”, authored by D. Babic, I. Jovovic, T: Popovic, S. Cakic and L. Filipovic discussed the use of deep learning and HPC to create prediction models aimed at detecting pneumonia in chest x-ray images.

ABSTRACT – Artificial intelligence is getting more and more involved in our everyday life as a result of enormous amounts of data available for feeding the machine and deep learning algorithms. Deep learning introduced new dimensions and possibilities of applications in medical science. With COVID-19 outbreak in 2020 at global level, the health systems of many countries were overwhelmed. With many patients infected, health system is pressured to correctly diagnose patient’s state of illness. In a lot of occasions, it was almost impossible to correctly diagnose many COVID-19 positive patients that have pneumonia due to many outbreaks in many areas. The intelligent system that could detect pneumonia with certainty could help in easing the pressure on the health system and make doctors focus on more severely ill patients. This paper describes development of pneumonia detection model using TensorFlow to processes the chest X-ray images to determine whether the patient has pneumonia. The model is based on deep learning algorithm supported through convolutional neural network. The model presented in this paper has achieved rather high accuracy (over 95%) in analyzing X-Ray images and could be used to speed up decision process in healthcare. (link)

06.07.2022.27.10.2022.

BSc Thesis: The use of ML to assess plant health

Ms Almira Suljovic, a student of the Faculty of Applied Sciences, defended her BSc Thesis in Electrical Engineering and Computer Science. The topic of the thesis work was the use of machine learning to detect diseased plants by processing images of the leaves. The work included creation of a prediction model as well as the integration of the model into a mobile application for the use by farmers. She has done her thesis work under the supervision of prof. Tomo Popovic, PhD, and mr Stevan Cakic, MSc.

BSc Thesis – the use of ML to detect plant disease

ABSTRACT – Early detection and prevention are one of the biggest difficulties in the field of agriculture. Late detection of plant diseases or the use of wrong pesticides often leads to crop damage, reducing food quality. As the leaf is the best indicator of whether a plant is healthy or not, we can construct prediction models using machine learning to identify leaf status in the shortest possible time, thus preventing or reducing losses. This thesis shows how to determine leaf health status using the Detectron2 software library and the faster R-CNN neural network. The model was trained using a dataset with 6407 images. The initial dataset was extended using the RoboFlow tool. Google Colab, an environment for the development of cloud computing and machine learning, was used for testing and implementation. The practical application of the machine learning model was realized using an application developed using the Flutter platform.

27.06.2022.27.10.2022.

Master Thesis: Practical Use of ML in the Fight Against COVID-19

Mr Bogdan Laban, a master student at the University of Donja Gorica, defended his Master thesis titled “Practical Use of Machine Learning in the Fight Against COVID-19”. The thesis was done at the Master academic studies “Information Management in Health Care” at the Faculty of International Economics, Finance and Business, under the supervision of his mentor prof. dr Tomo Popovic.

Mr. Bogdan Laban defended his MSc thesis on the use of ML to fight COVID-19

The presentation included interested real-life examples

ABSTRACT – This study aims to find applicable combination of recent AI technologies and its uses during the COVID-19 pandemic. As AI has shown great improvements in the last few years, with many new feature-filled tools out on the market, it is almost certain that AI can help find ways to circumvent the dangers of COVID-19, in the form of noticing it, and preventing it. Authors cited in this work are AI professional, specializing in neural networks and their appliances in real world, in the form of visual processing and understanding, which will provide me with a solid hypothesis to base my master thesis on.

As this pandemic still has a solid grasp on the world, especially on less developed countries like Montenegro, I believe it makes a great testing ground for attributes like – percentage of people abiding pandemic specific laws (social distancing, mask wearing, etc.). Unfortunately, people of Montenegro are very divided on this issue, ranging from avid abiders, to those who completely ignore all safety procedures, even the most basic ones. As such, I believe this study will provide me with an insight into the right tools and tests for the residents of Montenegro, which vary a lot.

Another Master Thesis in Applied Machine Learning

20.03.2022.27.10.2022.

Evaluation of trends in jobs and skill‑sets using data analytics: a Case study, by Dr Armin Alibasic et al.

Member of the EuroCC Montenegro National Competence Center team, Dr Armin Alibasic together with co-authors Himanshu Upadhyay, Mecit Can Emre Simsekler, Thomas Kurfess, Wei Lee Woon and Mohammed Atif Omar conducted research published in the paper titled “Evaluation of trends in jobs and skill ‑ sets using data analytics: a Case study” in the Journal of Big Data. The article is available at the following link.

APSTRACT – A novel data-driven approach is developed to identify trending jobs through a case study in the oil and gas industry. The proposed approach leverages a range of data analytics tools, including Latent Semantic Indexing (LSI), Latent Dirichlet Allocation (LDA), Factor Analysis and Non-Negative Matrix Factorization (NMF), to study changes in the market. Further, our approach is capable of identifying disparities between skills that are covered by the educational system, and the skills that are required in the job market. Novel data-driven approach is developed to identify trending jobs through a case study in the oil and gas industry. The proposed approach leverages a range of data analytics tools, including Latent Semantic Indexing (LSI), Latent Dirichlet Allocation (LDA), Factor Analysis and Non-Negative Matrix Factorization (NMF), to study changes in the market. Further, our approach is capable of identifying disparities between skills that are covered by the educational system, and the skills that are required in the job market.