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.

With long-term changes in temperature and weather patterns, ecologically adaptable fruit varieties are becoming increasingly important in agriculture. For selection of candidate cultivars in fruit breeding or for yield predictions, fruit set characteristics at different growth stages need to be described and evaluated, which is largely done visually. This is a time-consuming and labor-intensive process that also requires sufficient expert knowledge. The annotated dataset for Japanese quince - QuinceSet - consists of images of Japanese quince (Chaenomeles japonica) fruits taken at two phenological developmental stages and annotated for detection and phenotyping. First, after flowering, when the second fruit fall is over and the fruits have reached 30-50% of their final size, and second, at the ripening stage of quince, just before the fruits are yielded. Both stages of quince images classified as unripe and ripe were annotated using ground truth ROI and presented in YOLO format. The dataset contains 1515 high-resolution RGB .jpg images with the same number of annotated .txt files. Images in the dataset were manually annotated using LabelImg software. A total of 17,171 annotations were provided by the experts. The images were acquired on site at the Institute of Horticulture in Dobele, Latvia. Homogenization of the images was performed under different weather conditions, at different times of the day, and from different capturing angles. The dataset contains both fully visible quinces and quinces partially obscured by leaves. Care was also taken to ensure that the foreground, which contains the leaves has adequate brightness with minimal shadows, while the background is darker. The presented dataset will allow to increase the efficiency of the breeding process and yield estimation, to identify and phenotype quinces more reliably, and may also be useful for breeding other crops.

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.

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.

Model understanding is critical in many domains, particularly those involved in high-stakes decisions, e.g., medicine, criminal justice, and autonomous driving. Explainable AI (XAI) methods are essential for working with black-box models such as convolutional neural networks. This paper evaluates the traffic sign classifier of the Deep Neural Network (DNN) from the Programmable Systems for Intelligence in Automobiles (PRYSTINE) project for explainability. The results of explanations were further used for the CNN PRYSTINE classifier vague kernels’ compression. Then, the precision of the classifier was evaluated in different pruning scenarios. The proposed classifier performance methodology was realised by creating an original traffic sign and traffic light classification and explanation code. First, the status of the kernels of the network was evaluated for explainability. For this task, the post-hoc, local, meaningful perturbation-based forward explainable method was integrated into the model to evaluate each kernel status of the network. This method enabled distinguishing high- and low-impact kernels in the CNN. Second, the vague kernels of the classifier of the last layer before the fully connected layer were excluded by withdrawing them from the network. Third, the network’s precision was evaluated in different kernel compression levels. It is shown that by using the XAI approach for network kernel compression, the pruning of 5% of kernels leads to a 2% loss in traffic sign and traffic light classification precision. The proposed methodology is crucial where execution time and processing capacity prevail.