Recent improvements in networking technologies have led to a significant shift towards distributed cloud-based services. However, adequate management of computation resources by providers is vital to maintain the costs of operations and quality of services. A robust system is needed to forecast demand and prevent excessive resource allocations. Extensive literature review suggests that the potential of recurrent neural networks with attention mechanisms is not sufficiently explored and applied to cloud computing. To address this gap, this work proposes a methodology for forecasting load of cloud resources based on recurrent neural networks with and without attention layers. Utilized deep learning models are further optimized through hyperparameter tuning using a modified particle swarm optimization metaheuristic, which is also introduced in this work. To help models deal with complex non-stationary data sequences, the variational mode decomposition for decomposing complex series has also been utilized. The performance of this approach is compared to several state-of-the-art algorithms on a real-world cloud-load dataset. Captured performance metrics ( $$R^2$$R 2 , mean square error, root mean square error, and index of agreement) strongly indicate that the proposed method has great potential for accurately forecasting cloud load. Further, models optimized by the introduced metaheuristic outperformed competing approaches, which was confirmed by conducted statistical validation. In addition, the best-performing forecasting model has been subjected to SHapley Additive exPlanations analysis to determine the impact each feature has on model forecasts, which could potentially be a very useful tool for cloud providers when making decisions.

Monitoring heart electrical activity is an effective way of detecting existing and developing conditions. This is usually performed as a non-invasive test using a network of up to 12 sensors (electrodes) on the chest and limbs to create an electrocardiogram (ECG). By visually observing these readings, experienced professionals can make accurate diagnoses and, if needed, request further testing. However, the training and experience needed to make accurate diagnoses are significant. This work explores the potential of recurrent neural networks for anomaly detection in ECG readings. Furthermore, to attain the best possible performance for these networks, training parameters, and network architectures are optimized using a modified version of the well-established particle swarm optimization algorithm. The performance of the optimized models is compared to models created by other contemporary optimizers, and the results show significant potential for real-world applications. Further analyses are carried out on the best-performing models to determine feature importance.

Maritime vessels provide a wealth of data concerning location, trajectories, and speed. However, while these data are meticulously monitored and logged to maintain course, they can also provide a wealth of meta information. This work explored the potential of data-driven techniques and applied artificial intelligence (AI) to tackle two challenges. First, vessel classification was explored through the use of extreme gradient boosting (XGboost). Second, vessel trajectory time series forecasting was tackled through the use of long-short-term memory (LSTM) networks. Finally, due to the strong dependence of AI model performance on proper hyperparameter selection, a boosted version of the well-known particle swarm optimization (PSO) algorithm was introduced specifically for tuning the hyperparameters of the models used in this study. The introduced methodology was applied to real-world automatic identification system (AIS) data for both marine vessel classification and trajectory forecasting. The performance of the introduced Boosted PSO (BPSO) was compared to contemporary optimizers and showed promising outcomes. The XGBoost model tuned using boosted PSO attained an overall accuracy of 99.72% for the vessel classification problem, while the LSTM model attained a mean square error (MSE) of 0.000098 for the marine trajectory prediction challenge. A rigid statistical analysis of the classification model was performed to validate outcomes, and explainable AI principles were applied to the determined best-performing models, to gain a better understanding of the feature impacts on model decisions.

Neurodegenerative conditions are defined by the progressive deterioration and death of nerve cells in the core neural system. Most neurodegenerative conditions are not curable. While there have been significant improvements and techniques used to treat these diseases early diagnosis continues to play a crucial role in the entire approach. Conditions are often diagnosed only once they start negatively impacting the daily life of those affected. Early detection and timely preventative treatment can help improve patient subjective well-being. This study examines the application of a non-invasive gait analysis technique for the detection of Parkinson’s disease. Publicly available data collected from patients suffering from Parkinson’s along with control groups is utilized and combined with long-short-term neural networks to construct models capable of detecting signs on Parkinson’s disorder. However, because of the significant reliance of models on appropriate parameters selection, metaheuristic algorithms are used to fine tune the selection process, and a modified variation of the strongly founded PSO algorithm was proposed. Several contemporary optimizers are compared based on their ability to optimize model performance. This suggested approach achieved the superior outcomes with an accuracy of 89.92%. The constructed models have been evaluated to determine feature importance using game theory based methods.

Many research centers and medical institutions have been accumulating a vast amount of various biological and chemical data over the past decade and this trend continues. Based on Linked Data vision, many semantic applications for distributed access

Interactive multimedia simulations and computer game elements can be successfully combined in order to create new advanced educational resources for teaching today's generation of students. Such a learning environment, a game-based learning model (GBLm), has been designed as a research prototype. This paper describes one type of GBLm for computer engineering, which we have used in the subject of computer graphics for the teaching unit Z-buffer algorithm, in order to facilitate the learning process. The implementation of a GBLm for graphical algorithms (GBL4CAl) is presented in detail as a multimedia interactive learning module designed to motivate students by making learning a more enjoyable process. During the design of the GBL4CAl module, special attention was paid to the integration of pedagogical and game-play aspects.