The use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency and color can be indicators of serious and infectious diseases. While most studies have prioritized the classification of droppings into two categories (normal and abnormal), with some relevant studies dealing with up to five categories, this investigation goes a step further by employing image processing algorithms to categorize droppings into six classes, based on visual information indicating some level of abnormality. To ensure a diverse dataset, data were collected in three different poultry farms in Lithuania by capturing droppings on different types of litter. With the implementation of deep learning, the object detection rate reached 92.41% accuracy. A range of machine learning algorithms, including different deep learning architectures, has been explored and, based on the obtained results, we have proposed a comprehensive solution by combining different models for segmentation and classification purposes. The results revealed that the segmentation task achieved the highest accuracy of 0.88 in terms of the Dice coefficient employing the K-means algorithm. Meanwhile, YOLOv5 demonstrated the highest classification accuracy, achieving an ACC of 91.78%.

The issue of sustainability in education has never been more important for the future of our environment, and strategies to develop the skills needed by younger generations to meet this significant global challenge should be developed across all curricula. There is much focus on the topic of sustainability in business, finance, climate, health, water and education; however, there are some challenges when sustainability needs to be integrated into engineering or fundamental study programs (SPs). In the latter, sustainability is more often emphasized and implemented through its general principles or separate modules in social sciences and project activities. There are a number of questions and challenges in how to highlight sustainability aspects and evaluation metrics due to the specifics of the engineering study field. For evaluating the sustainability level in engineering studies, a hierarchical methodology employing the SAMR (Substitution, Augmentation, Modification, Redefinition) model is proposed, taking a technological university in Lithuania as the case study. As a more concrete example, the first and second cycle SPs titled ‘Artificial Intelligence’ are described and analyzed in all relevant perspectives of sustainability. The study proposes five tangible criteria that must be emphasized in the learning process in order to ensure the development of sustainability goals in IT/AI study programs.

Vehicle detection and classification is an important part of an intelligent transportation surveillance system. Although car detection is a trivial task for deep learning models, studies have shown that when vehicles are visible from different angles, more research is relevant for brand classification. Furthermore, each year, more than 30 new car models are released to the United States market alone, implying that the model needs to be updated with new classes, and the task becomes more complex over time. As a result, a transfer learning approach has been investigated that allows the retraining of a model with a small amount of data. This study proposes an efficient solution to develop an updatable local vehicle brand monitoring system. The proposed framework includes the dataset preparation, object detection, and a view-independent make classification model that has been tested using two efficient deep learning architectures, EfficientNetV2 and MobileNetV2. The model was trained on the dominant car brands in Lithuania and achieved 81.39 % accuracy in classifying 19 classes, using 400 to 500 images per class.

This publication presents a novel approach to predicting the amount of electricity generated by wind power plants. The research focuses on data-driven models such as XGBoost, Liquid Time-constant Networks, and covers both the analysis of properties of individual forecasting models as well as aspects of their integration into a hybrid model. By analyzing real-world weather scenarios, the approach aims to identify the highest accuracy forecasting model for the short-term 24-h forecast of wind farm power output. A more accurate forecast allows for more efficient resource planning and better distribution of resources on the electricity grids, thus ensuring a greener approach to energy production. The study shows that the proposed Hybrid (XGBoost + LTC) model predicts wind power generation with an nMAE of 0.0856, representing an improvement over standalone XGBoost and LTC models, and outperforming classical approaches such as LSTM and statistical models like ARIMAX in terms of forecasting accuracy.