Low-dose computed tomography (LDCT) is critical for minimizing radiation exposure, but it often leads to increased noise and reduced image quality. Traditional denoising methods, such as iterative optimization or supervised learning, often fail to preserve image quality. To address these challenges, we introduce PPORLD-EDNetLDCT, a reinforcement learning-based (RL) approach with Encoder–Decoder for LDCT. Our method utilizes a dynamic RL-based approach in which the Proximal Policy Optimization (PPO) algorithm is employed to optimize the denoising policy during training, guided by image quality feedback in a custom gym environment, while inference is performed using the trained fixed-parameter encoder–decoder model. The experimental results on the low dose CT image and projection dataset demonstrate that the proposed PPORLD-EDNetLDCT model outperforms traditional denoising techniques and other DL-based methods, achieving a peak signal-to-noise ratio of 41.87, a structural similarity index measure of 0.9814 and a root mean squared error of 0.00236. Moreover, in NIH-AAPM-Mayo Clinic Low Dose CT Challenge dataset our method achieved a PSNR of 41.52, SSIM of 0.9723 and RMSE of 0.0051. Furthermore, we validated the quality of denoising using a classification task in the COVID-19 LDCT dataset, where the images processed by our method improved the classification accuracy to 94%, achieving 4% higher accuracy compared to denoising without RL-based denoising.
Accurate land cover classification from satellite imagery is crucial in environmental monitoring and sustainable resource management. However, it remains challenging due to the complexity of natural landscapes, the visual similarity between classes, and the significant class imbalance in the available datasets. To address these issues, we propose a dual encoder architecture that independently extracts modality-specific features from optical and Synthetic Aperture Radar (SAR) imagery, which are then fused using a cross-modality attention-fusion module named Cross-modality Land cover segmentation with Attention and Imbalance-aware Reasoning-Enhanced Explanations (CLAIRE). This fusion mechanism highlights complementary spatial and textural features, enabling the network to better capture detailed and diverse land cover patterns. We incorporate a hybrid loss function that utilizes Weighted Focal Loss and Tversky Loss named RIFT (Rare-Instance Focal-Tversky) to address class imbalance and improve segmentation performance across underrepresented categories. Our model achieves competitive performance across multiple benchmarks: a mean Intersection over Union (mIoU) of 56.02% and Overall Accuracy (OA) of 84.56% on the WHU-OPT-SAR dataset; strong generalization with a mIoU of 59.89% and OA of 73.92% on the OpenEarthMap-SAR dataset; and remarkable robustness under cloud-obstructed conditions, achieving an mIoU of 86.86% and OA of 94.58% on the PIE-RGB-SAR dataset. Additionally, we introduce a metric-driven reasoning module generated by a Small Language Model (Phi-3), which generates sample-specific justifications for model predictions, thereby enhancing transparency and interpretability.
The current study evaluates how policy uncertainty, green finance, green innovation, and environmental policy stringency affect the sustainable energy mix in OECD economies from 1996 through 2023. It fills an important gap in the existing literature, where these determinants have traditionally been viewed as independent rather than as part of a unified probabilistic model. In a given analysis, macro-policy uncertainty, climate-policy turbulence, financial variables, innovation, and regulatory intensity combine to form a single analytical framework, thereby addressing unanswered questions about how these variables interact to affect renewable-energy transitions. To address this weakness, the research questions include whether economic and global uncertainties asymmetrically harm sustainable energy development, whether climate-policy uncertainty can elicit positive behavioural responses, and whether green finance and innovation can counteract the harmful impact of uncertain policy regimes. The analytical methodology uses a set of Bayesian structures, including linear, heteroskedastic, multilevel, random-effects, and dynamic PVAR structures, to produce complete posterior distributions for each mechanism and to explain heterogeneity, feedback, and volatility across advanced economies. Findings show that there are continuously positive impacts of green finance, green innovation, and the tightness of environmental policy on renewable-energy growth; domestic and global uncertainties suppress growth and increase volatility. Climate-policy uncertainty, in turn, has a positive, stabilising effect within a credible institutional framework. The current study dynamically confirms that finance, innovation, and strict policy Granger-causally improve the energy mix, and it indicates a stable feedback mechanism in OECD entities. The experiment provides new evidence that the probabilistic interactions among financial mobilisation, technological capability, institutional credibility, and uncertainty environments govern sustainable-energy transitions, offering policy-designable insights to be acted upon to emphasise the roles of stability, long-term commitment, and the multifaceted acceleration of green innovation and investment.
The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A-ranked and Q1 journals. A structured analysis of the LLM agents’ architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLMs, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we have evaluated current benchmarks and assessment protocols and provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.
Abstract Dementia is a debilitating disease that leads to a gradual loss of memory and other cognitive abilities and tends to develop in people over 60 years of age. The number of people worldwide with dementia is expected to increase from 57.4 million in 2019 to 131.5 million in 2050. Diagnosis of dementia is a critical task, and some biomarkers and psychological and demographic measures have been used to diagnose dementia clinically. The advent of artificial intelligence (AI) has created new opportunities to improve diagnostic accuracy. In this study, we propose an approach based on machine learning and graph analysis to identify important patterns and diagnostic markers for dementia. The novel contributions of this study include a descriptive probability density function (PDF) analysis to examine the distribution of clinically relevant markers across diagnostic groups, providing exploratory insights into group-wise feature behavior. A comprehensive evaluation of ten machine learning (ML) models is conducted under strict subject-level data separation to identify robust classification performance. In addition, feature ranking is assessed using three complementary strategies (Random Forest importance, Chi-Square statistics, and Boruta ranking) to evaluate the consistency and robustness of marker relevance. Out of ten ML models evaluated, the Random Forest achieved the highest accuracy of 94.37%, with a macro F1-score of 86.96%. The result of the ML model is further validated using a graphical analysis of critical markers. The results of this study might help to improve the diagnostic accuracy.
