Explore the vast range of titles available.

The prompt and accurate identification of the causes of pneumonia is necessary to implement rapid treatment and preventative approaches, reduce the burden of infections, and develop more successful intervention strategies. There has been an increase in the number of new pneumonia cases and diseases known as acute respiratory distress syndrome (ARDS) as a direct consequence of the spread of COVID-19. Chest radiography has evolved to the point that it is now an indispensable diagnostic tool for COVID-19 infection pneumonia in hospitals. To fully exploit the technique, it is crucial to design a computer-aided diagnostic (CAD) system to assist doctors and other medical professionals in establishing an accurate and rapid diagnosis of pneumonia. This article presents a robust hybrid deep convolutional neural network (DCNN) for rapidly identifying three categories (normal, COVID-19 and pneumonia (viral or bacterial)) using X-ray image data sourced from the COVID-QU-Ex dataset. The proposed approach on the test set achieved a rate of 99.25% accuracy, 99.10% Kappa-score, 99.43% AUC, 99.24% F1-score, 99.25% recall, and 99.23% precision, respectively. The outcomes of the experiments demonstrate that the presented hybrid DCNN mechanism for identifying three categories utilising X-ray images is robust and effective.

The aim of the study was to examine potential cognitive, mood (depression and anxiety) and behavioral changes that may be related to the quarantine and the lockdown applied during the COVID-19 pandemic in Greek older adults with mild cognitive impairment (MCI), and AD dementia in mild and moderate stages. Method: 407 older adults, diagnosed either with MCI or AD dementia (ADD), were recruited from the Day Centers of the Greek Association of Alzheimer Disease and Related Disorders (GAADRD). Neuropsychological assessment was performed at baseline (at the time of diagnosis) between May and July of 2018, as well as for two consecutive follow-up assessments, identical in period, in 2019 and 2020. The majority of participants had participated in non-pharmacological interventions during 2018 as well as 2019, whereas all of them continued their participation online in 2020. Results: Mixed measures analysis of variance showed that participants’ ‘deterioration difference—D’ by means of their performance difference in neuropsychological assessments between 2018–2019 (D1) and 2019–2020 (D2) did not change, except for the FUCAS, RAVLT, and phonemic fluency tests, since both groups resulted in a larger deterioration difference (D2) in these tests. Additionally, three path models examining the direct relationships between performance in tests measuring mood, as well as everyday functioning and cognitive measures, showed that participants’ worsened performance in the 2019 and 2020 assessments was strongly affected by NPI performance, in sharp contrast to the 2018 assessment. Discussion: During the lockdown period, MCI and ADD patients’ neuropsychological performance did not change, except from the tests measuring verbal memory, learning, and phonemic fluency, as well as everyday functioning. However, the natural progression of the MCI as well as ADD condition is the main reason for participants’ deterioration. Mood performance became increasingly closely related to cognition and everyday functioning. Hence, the role of quarantine and AD progression are discussed as potential factors associated with impairments.

Energy-Efficient Coverage Path Planning (CPP) in dynamic environments remains a key challenge for autonomous systems operating in real-world scenarios. This paper introduces the Energy-Aware Predictive Coverage (EAPC) framework, a hybrid approach that integrates Deep Reinforcement Learning (DRL) with predictive modelling to enable adaptive and sustainable navigation. EAPC incorporates Gated Recurrent Unit (GRU) to forecast the motion of dynamic obstacles, allowing the agent to proactively adjust its trajectory. These predictions are embedded into an augmented state vector alongside terrain and obstacle features. A multi-objective reward function penalizes energy-intensive actions, abrupt accelerations, and potential collisions, encouraging smoother, more efficient behaviors. The framework is evaluated in a simulated environment with procedurally generated terrain and moving obstacles. Comparisons with classical planners (A*, RRT) and modern RL methods (PPO, SAC) are made using metrics such as coverage, energy usage, collision rate, and adaptability. Results show that EAPC significantly improves both energy efficiency and robustness in dynamic settings. This work advances the development of intelligent, resilient, and energy-aware autonomous systems. Potential applications include precision agriculture, infrastructure monitoring, and post-disaster inspection, where energy-conscious autonomy is crucial.