The global community has recognized an increasing amount of pollutants entering oceans and other water bodies as a severe environmental, economic, and social issue. In addition to prevention, one of the key measures in addressing marine pollution is the cleanup of debris already present in marine environments. Deployment of machine learning (ML) and deep learning (DL) techniques can automate marine waste removal, making the cleanup process more efficient. This study examines the performance of six well-known deep convolutional neural networks (CNNs), namely VGG19, InceptionV3, ResNet50, Inception-ResNetV2, DenseNet121, and MobileNetV2, utilized as feature extractors according to three different extraction schemes for the identification and classification of underwater marine debris. We compare the performance of a neural network (NN) classifier trained on top of deep CNN feature extractors when the feature extractor is (1) fixed; (2) fine-tuned on the given task; (3) fixed during the first phase of training and fine-tuned afterward. In general, fine-tuning resulted in better-performing models but is much more computationally expensive. The overall best NN performance showed the fine-tuned Inception-ResNetV2 feature extractor with an accuracy of $91.40\%$ and F1-score $92.08\%$, followed by fine-tuned InceptionV3 extractor. Furthermore, we analyze conventional ML classifiers’ performance when trained on features extracted with deep CNNs. Finally, we show that replacing NN with a conventional ML classifier, such as support vector machine (SVM) or logistic regression (LR), can further enhance the classification performance on new data.

This paper discusses an approach to teaching programming that would allow elementary school children to adopt basic problem solving concepts. Adopting those concepts should help them in their further education, not only in programming but also in other areas that require logical thinking and problem solving.Elementary school children are too young for traditional approach to teaching programming so in this paper we describe an approach appropriate for their age designed to avoid problems associated with young children such as short attention span. Preliminary experiment with 30 elementary school children was conducted and details and results are presented in this paper

Learning programming at university level is the challenge for both students and teachers, especially for students without previous exposure to programming. Most of the programming courses are compulsory and tough to learn for novice programmers. Students lack the understanding of basic programming concepts and algorithms and find programming difficult. Early failure of understanding important concepts weakens students’ confidence and increases drop-out rate. Students’ success rate and perception during most important programming courses at the undergraduate level at the Faculty of Science, University of Split over extended period of time were analyzed. Results of this research are presented in this paper

In the global maritime industry, ship grounding represents about one-third of commercial groundings. Grounding is a type of accident where the hull of a ship strikes the seabed, causing damage to the hull. This type of accident can lead to damage to the hull and water penetration, but also to the pollution of the marine environment by the spillage of ship fuel or some liquid cargo carried by the ship. This paper presents a chronological overview of the contribution of ship grounding frequency, where one of the first ideas of grounding probability was presented by Macduff (1974) and Fuji (1974) in their models. Their ideas, such as grounding candidates and causing probability, laid the foundation for the development of future models. After their models, years later, other models continued to be developed; e.g., analytically (Macduff, Fujii, Amrowitcz, etc.) and statistically (Pedersen, Simonsen, etc.). To find the probability of grounding in an area of interest or in a scenario, it is necessary to have the number of grounding candidates and the causing probability. There are different internal and external factors that affect both probabilities, and in this paper, we analyze how various authors approach their grounding models and have tried to show the actual event as faithfully as possible and thus contribute to greater safety in maritime transport. The number of grounding frequency models significantly complicates their selection in practice; accordingly, the review of models in this paper should facilitate this, but also it should facilitate future research on this topic.

In the Republic of Croatia Informatics is an elective course in elementary school for students from 5th to 8th grade. When it comes to programming language teachers can choose between BASIC and Logo. There are a lot of new programming environments for learning and teaching programming like Scratch and also new ways of teaching programming like game based learning. This study compares attitudinal and learning outcomes of 7thgrade students programming in Logo and Scratch. The classes were normal classes, non-extracurricular activities. The questionnaire is used to measure the attitude towards programming and programming languages. The test is constructed to measure learned programming concepts in both compared programming languages Logo and Scratch. Results showed that learning Scratch first can provide a better understanding of basic programming concept for novices in elementary school than Logo.