This research delineates a pivotal advancement in the domain of sustainable energy systems, with a focused emphasis on the integration of renewable energy sources—predominantly wind and solar power—into the hydrogen production paradigm. At the core of this scientific endeavor is the formulation and implementation of a deep-learning-based framework for short-term localized weather forecasting, specifically designed to enhance the efficiency of hydrogen production derived from renewable energy sources. The study presents a comprehensive evaluation of the efficacy of fully connected neural networks (FCNs) and convolutional neural networks (CNNs) within the realm of deep learning, aimed at refining the accuracy of renewable energy forecasts. These methodologies have demonstrated remarkable proficiency in navigating the inherent complexities and variabilities associated with renewable energy systems, thereby significantly improving the reliability and precision of predictions pertaining to energy output. The cornerstone of this investigation is the deployment of an artificial intelligence (AI)-driven weather forecasting system, which meticulously analyzes data procured from 25 distinct weather monitoring stations across Latvia. This system is specifically tailored to deliver short-term (1 h ahead) forecasts, employing a comprehensive sensor fusion approach to accurately predicting wind and solar power outputs. A major finding of this research is the achievement of a mean squared error (MSE) of 1.36 in the forecasting model, underscoring the potential of this approach in optimizing renewable energy utilization for hydrogen production. Furthermore, the paper elucidates the construction of the forecasting model, revealing that the integration of sensor fusion significantly enhances the model’s predictive capabilities by leveraging data from multiple sources to generate a more accurate and robust forecast. The entire codebase developed during this research endeavor has been made available on an open access GIT server.

In this technical note, we examine the capabilities of deep convolutional neural networks (DCNNs) for diagnosing osteoporosis through cone-beam computed tomography (CBCT) scans of the mandible. The evaluation was conducted using 188 patients’ mandibular CBCT images utilizing DCNN models built on the ResNet-101 framework. We adopted a segmented three-phase method to assess osteoporosis. Stage 1 focused on mandibular bone slice identification, Stage 2 pinpointed the coordinates for mandibular bone cross-sectional views, and Stage 3 computed the mandibular bone’s thickness, highlighting osteoporotic variances. The procedure, built using ResNet-101 networks, showcased efficacy in osteoporosis detection using CBCT scans: Stage 1 achieved a remarkable 98.85% training accuracy, Stage 2 minimized L1 loss to a mere 1.02 pixels, and the last stage’s bone thickness computation algorithm reported a mean squared error of 0.8377. These findings underline the significant potential of AI in osteoporosis identification and its promise for enhanced medical care. The compartmentalized method endorses a sturdier DCNN training and heightened model transparency. Moreover, the outcomes illustrate the efficacy of a modular transfer learning method for osteoporosis detection, even when relying on limited mandibular CBCT datasets. The methodology given is accompanied by the source code available on GitLab.

Differential privacy has recently gained prominence, especially in the context of private machine learning. While the definition of differential privacy makes it possible to provably limit the amount of information leaked by an algorithm, practical implementations of differentially private algorithms often contain subtle vulnerabilities. Therefore, there is a need for effective methods that can audit $(ϵ,\delta )$ differentially private algorithms before they are deployed in the real world. The article examines studies that recommend privacy guarantees for differential private machine learning. It covers a wide range of topics on the subject and provides comprehensive guidance for privacy auditing schemes based on privacy attacks to protect machine-learning models from privacy leakage. Our results contribute to the growing literature on differential privacy in the realm of privacy auditing and beyond and pave the way for future research in the field of privacy-preserving models.

Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.

The RaspberrySet dataset is a valuable resource for those working in the field of agriculture, particularly in the selection and breeding of ecologically adaptable berry cultivars. This is because long-term changes in temperature and weather patterns have made it increasingly important for crops to be able to adapt to their environment. To assess the suitability of different cultivars or to make yield predictions, it is necessary to describe and evaluate berries’ characteristics at various growth stages. This process is typically carried out visually, but it can be time-consuming and labor-intensive, requiring significant expert knowledge. The RaspberrySet dataset was created to assist with this process, and it includes images of raspberry berries at five different stages of development. These stages are flower buds, flowers, unripe berries, and ripe berries. All these stages of raspberry images classified buds, damaged buds, flowers, unripe berries, and ripe berries and were annotated using ground truth ROI and presented in YOLO format. The dataset includes 2039 high-resolution RGB images, with a total of 46,659 annotations provided by experts using Label Studio software (1.7.1). The images were taken in various weather conditions, at different times of the day, and from different angles, and they include fully visible buds, flowers, berries, and partially obscured buds. This dataset is intended to improve the efficiency of berry breeding and yield estimation and to identify the raspberry phenotype more accurately. It may also be useful for breeding other fruit crops, as it allows for the reliable detection and phenotyping of yield components at different stages of development. By providing a homogenized dataset of images taken on-site at the Institute of Horticulture in Dobele, Latvia, the RaspberrySet dataset offers a valuable resource for those working in horticulture.

Segmentation neural networks are widely used in medical imaging to identify anomalies that may impact patient health. Despite their effectiveness, these networks face significant challenges, including the need for extensive annotated patient data, time-consuming manual segmentation processes and restricted data access due to privacy concerns. In contrast, classification neural networks, similar to segmentation neural networks, capture essential parameters for identifying objects during training. This paper leverages this characteristic, combined with explainable artificial intelligence (XAI) techniques, to address the challenges of segmentation. By adapting classification neural networks for segmentation tasks, the proposed approach reduces dependency on manual segmentation. To demonstrate this concept, the Medical Segmentation Decathlon ‘Brain Tumours’ dataset was utilised. A ResNet classification neural network was trained, and XAI tools were applied to generate segmentation-like outputs. Our findings reveal that GuidedBackprop is among the most efficient and effective methods, producing heatmaps that closely resemble segmentation masks by accurately highlighting the entirety of the target object.