Ilijoski, Bojan
Preferred name
Ilijoski, Bojan
Official Name
Ilijoski, Bojan
Main Affiliation
Email
bojan.ilijoski@finki.ukim.mk
23 results
Now showing 1 - 10 of 23
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Deep Learning Methods for Bug Bite Classification: An End-to-End System(MDPI AG, 2023-04-21); ;Trojachanec Dineva, Katarina ;Tojtovska Ribarski, Biljana ;Petrov, PetarMladenovska, Teodora<jats:p>A bite from a bug may expose the affected person to serious, life-threatening conditions, which may require immediate medical attention. The identification of the bug bite may be challenging even for experienced medical personnel due to the different manifestations of the bites and similarity to other skin conditions. This motivated our work on a computer-aided system that offers information on the bug bite based on the classification of bug bite images. Recently, there have been significant advances of methods for image classification for the detection of various skin conditions. However, there are very few sources that discuss the classification of bug bites. The goal of our research is to fill in this gap in the literature and offer a comprehensive approach for the analysis of this topic. This includes (1) the creation of a dataset that is larger than those considered in the related sources; (2) the exploration and analysis of the application of pre-trained state-of-the-art deep learning architectures with transfer learning, used in this study to overcome the challenges of low-size datasets and computational burden; (3) the further improvement of the classification performance of the individual CNNs by proposing an ensemble of models, and finally, (4) the implementation and description of an end-to-end system for bug bite classification from images taken with mobile phones, which should be beneficial to the medical personnel in the diagnostic process. In this paper, we give a detailed discussion of the models’ architecture, back-end architecture, and performance. According to the general evaluation metrics, DenseNet169 with an accuracy of 78% outperformed the other individual CNN models. However, the overall best performance (accuracy of 86%) was achieved by the proposed stacking ensemble model. These results are better than the results in the limited related work. Additionally, they show that deep CNNs and transfer learning can be successfully applied to the problem of the classification of bug bites.</jats:p> - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Digital Shift: Assessment of Mental States Through Passive Mobile Sensing(Springer International Publishing, 2022) ;Krajchevska, Evgenija ;Petreska, Nina ;Handjiski, Ognen ;Andovska, Sandra - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Developing Applications for Children With Special Needs Into a Project Based Learning Approach at Human-Computer Interaction Course(IEEE, 2022-03-28); Caring for the vulnerable categories of people is particularly important for the development of societies. Especially when it comes to children with special needs, who should be offered a variety of opportunities for education and integration. We try to help in the creation of digital tools by integrating project development for these target groups within the subject of human-computer interaction. This approach has several benefits for all parties involved. Students learn new technologies, and develop a complete product, while getting acquainted with the problems that children with special needs have. In this way, in addition to the technical knowledge, they also get satisfaction from the work they do to help the society. As end users, the children and their parents receive a wide range of tools they can use in education or in everyday functioning. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Creation of educational games — Project based learning in e-Learning systems course(IEEE, 2017-04); ; ; In this paper we present a successful example of implementation of project-based learning in e-Learning Systems course. Starting with an overview of the organization of the “e-Learning Systems” course held at the Faculty of Computer Science and Engineering (FCSE) in Skopje, we look into the importance of project-based learning as a learning method, the benefits of team work, and also we describe the purpose of educational games. The paper focuses on the general form of the project assigned to students which we describe in details, the organization of the lab exercises and the process of implementation of the projects. Based on the results that we will present, we may conclude that we have managed to organize the course in such a way that many of the students will achieve the course goals and pass, and also, will have exciting and challenging project to work on. We believe that the material in this paper will be valuable to other lecturers that teach similar or even quite different courses, and also facing the problem of teaching a course with high student/teacher ratio. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Creating Effective Quizzes by Balancing the Distribution of Question Types(IATED, 2018-03); ; The creation of quizzes as a method of student evaluation is a complex process. Quizzes are very convenient method of evaluation when the number of students is large and the deadline is close, especially if the reviewing is organized as e-testing. In that case a teacher must choose appropriate questions in order to get the right picture of student’s acquired knowledge. Usually those tests are based on questions which are single or multiple choice, dropdowns etc. in one hand and short/essay answers in another. In the first group there is possibility for random guessing and the offered answers to these questions can be very similar and sometimes confusing which can lead students that know the material to select the wrong answer. Also the answers can be drastically different and completely disjunctive so the correct answer is very predictable.Short answer/essay questions cancel these shortcoming. But, when we have short/essay answers one of the main drawbacks is that they must be manually graded, which can be very time consuming and subjective. This article will present the comparison of efficiency between the answers on single choice, multiple choice and short answer/essay questions in several courses in the IT field. The idea is to find the correlation between those two groups of answers, compare the average scores between them and estimate the minimal percent of short answer/essay questions that is necessary to grade a student. The solution will help with creating efficient quizzes so teachers can get plausible tool for estimation of student knowledge. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A New Collection of Educational Scratch Projects Produced by Computer Science Students(FCSE, 2017); ; Scratch is a free educational programming language specifically designed to be convenient for students of very young age to learn programming. The course “e-Learning Systems” is an elective course for the students at our institution – Faculty of Computer Science and Engineering (FCSE) in Skopje, primarily offered to the students enrolled in the “Computer Science Education” track, in the third semester of the undergraduate studies. Starting from the current academic year (2016/17), students of this course are asked, as a project activity, to implement an educational game or story in Scratch. In this paper we present the new website we have developed for the purposes of the course, which contains the student projects developed throughout the winter semester of 2016/17, as part of the course activities. We describe the form of the student projects and the collection of projects present on the website, as well as their functionalities and application. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Check for Unveiling Insights: Analyzing Application Logs to Enhance Autism Therapy Outcomes(Springer Nature, 2024-02-26); Leveraging advancements in information technology and the inherent interest of children with autism in robots and technology, this study explores the crucial role of analyzing application logs in enhancing therapy experiences for children with autism. By examining these logs, valuable insights can be obtained, enabling performance tracking, evidence-based evaluation, personalization of interventions, and continuous improvement. This will allow us to get more information about children's preferences and behavior even when we are not in direct contact with them, by extending onsite robot therapies to the home environment. This research contributes to the understanding of the transformative power of log analysis and its implications for optimizing therapy experiences and advancing treatment for children with autism. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Extending Robot Therapy for Children with Autism Using Mobile and Web Application(MDPI AG, 2022-08-09); ; ; Robot treatments for children with autism have proven to be successful and effective. However, the resources needed for the treatments do not always meet the needs of the children. We overcame the lack of equipment and staff by extending the concept of robot therapy using a web and mobile application. This application enables greater availability and personification of the therapy itself. Its use in the majority of respondents contributes to improving their condition. This approach increases the flexibility of the therapy itself and makes it more accessible, enabling the patients to progress more rapidly. Although the robotic treatment presented in this paper is specific to children with autism, this approach can be generalized and applied to other areas where there are similar types of therapies.</jats:p> - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Online availability of a robot therapy for children with autism(IEEE, 2023-04-01); In this paper we will present a case in which a robot therapy for children with autism was transferred from clinic to home conditions. The developed application enables the children to continue with the interventions in home conditions. This proved especially important in the COVID-19 pandemic. The application also allows monitoring of the child’s activities, through which the therapist can later analyze the patient’s behavior and offer appropriate therapy. The application shows reliable results and gives promise to develop beyond the user case we are considering. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Framework for Genetic Algorithms Using Pilot Jobs in Adaptive Grid Workflows(Springer Berlin Heidelberg, 2014); ; ; Sahpaski, Dragan
- «
- 1 (current)
- 2
- 3
- »
