The increasing dependence and demands on cloud infrastructure have brought to light challenges associated with cloud instance pricing. The often unpredictable nature of demand as well as changing costs of supplying a reliable instance can leave companies struggling to appropriately budget to support a healthy cash flow while maintaining operating costs. This work explores the potential of multi-headed recurrent architectures to forecast cloud instance prices based on historical and instance data. Two architectures are explored, long short-term memory (LSTM) and gated recurrent unit (GRU) networks. A modified optimizer is introduced and tested on a publicly available Amazon elastic compute cloud dataset. The GRU model, enhanced by the proposed modified approach, had the most impressive outcomes with an MAE score of 0.000801. Results have undergone meticulous statistical validation with the best-performing models further analyzed using explainable artificial intelligence techniques to provide further insight into model reasoning and information on feature importance.

Accurate evaluation of a cardiac patient’s risk at the point of hospital entry is critical for efficient triage and ensuring timely, suitable medical intervention. This study aims to forecast a range of clinical outcomes by leveraging admission data from a cardiac care unit, utilizing a refined and optimized machine learning approach. This research introduces a hybrid architecture that integrates convolutional neural networks (CNNs) with advanced machine learning classifiers, namely light gradient boosting machine (LightGBM) and categorical boosting (CatBoost), further enhanced through metaheuristic optimization techniques to maximize their performance. The proposed two-tiered design organizes feature extraction and final decision modeling into a coherent pipeline tailored for multi-class hospital admission classification. A comprehensive evaluation using a real-world hospital admission dataset demonstrates the framework’s effectiveness on a real-world, publicly available hospital admission dataset, supporting its utility for multi-class cardiac outcome prediction. Three experiments were conducted using publicly available datasets, where the best-performing models achieved a peak classification accuracy of 99.79%. Furthermore, explainable AI techniques were employed to interpret model predictions, offering actionable insights that can guide future data acquisition and strengthen the accurate classification of cardiac patients.

Electroencephalography (EEG) represents an essential neurological assessment technique that captures the brain’s bioelectrical signals via electrodes positioned on the scalp. Although artificial intelligence has shown substantial potential across various areas of medical analysis, its application within neurodiagnostic procedures is still not widely examined. This study tackles that shortfall by introducing a novel methodology based on time-series categorization of EEG recordings, utilizing gated recurrent unit neural architectures to pinpoint irregular neural patterns, with a focus on seizure detection. To further boost the accuracy of the proposed framework, metaheuristic optimization strategies are applied for refining hyperparameter configurations. Moreover, a customized variant of particle swarm optimization is developed, designed specifically for this neurodiagnostic context. The performance of the approach is assessed using a carefully selected dataset containing authentic EEG traces from neurologically healthy subjects as well as individuals diagnosed with epilepsy. The resulting software-driven solution yields impressive outcomes, demonstrating strong capability in identifying anomalies even when operating with comparatively limited sample counts.