This study introduces the HBV-DS dataset, a novel clinical resource designed for predicting hepatic fibrosis and necroinflammatory activity in patients with Hepatitis B Virus (HBV). The dataset is unique as it comprises the same patient instances annotated with multiple classification schemes, allowing for a comprehensive analysis of liver conditions. We implemented a robust end-to-end machine learning (ML) pipeline that includes essential preprocessing steps such as data cleaning, normalization, and encoding, alongside class balancing using the Synthetic Minority Oversampling Technique (SMOTE). This approach effectively addresses class imbalance, which is critical for enhancing model performance in clinical settings. Our evaluation involved six different classifiers: Support Vector Machine (SVM), Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, and XGBoost. Notably, the Random Forest classifier achieved an impressive accuracy of 92% and an AUC of 0.98, demonstrating the dataset’s effectiveness in clinical prediction tasks. The findings highlight the significant impact of dataset-specific labeling on predictive outcomes and establish benchmark metrics for future research in HBV progression modeling. This work not only underscores the importance of preprocessing and model selection in medical machine learning applications but also provides actionable insights for integrating these models into clinical decision support systems.

Understanding pedestrian behavior is crucial for ensuring road safety, as underscored by the alarming rates of pedestrian-involved accidents worldwide. This study presents a questionnaire conducted in various parts of the district of Sousse, Tunisia, wherein we analyze the creation of a predictive output variable to determine accident severity based on pedestrian crossing behaviors. An Exploratory Data Analysis and unsupervised machine learning were employed to assess behaviors described by different variables and determine probable accident severity. Through analysis of the dataset encompassing pedestrian behaviors and various specifications, including gender and educational level, among others, it becomes evident that certain behaviors, such as crossing roads outside designated pedestrian crossings or disregarding traffic signals, significantly elevate the likelihood of severe accidents. By leveraging machine learning techniques with this proposed dataset, predictive models could be developed to evaluate accident risk and injury severity based on pedestrian behaviors. The primary objective of this dataset is to inform road safety policies and awareness campaigns, with the potential to mitigate pedestrian-involved accidents and enhance overall road safety.

Solar Active Regions are characterised by their intense magnetic activity, which often leads to solar phenomena such as solar flares, and coronal mass ejections (CMEs). With the recent advancement of computing technologies and the huge integration of Artificial Intelligence (AI), many approaches have been proposed for forecasting solar eruptions using machine learning. In this study, we propose the use of a Temporal Convolutional Network (TCN) for predicting whether an active region will be flaring in a specific window of time and defining the flare class. The dataset is categorised into three different subsets based on the flare class and trained separately with the same TCN architecture to apply late fusion. The proposed solar flare prediction ensemble (EoFNets) is based on both the physical characteristics of the active region (EoFPhyNet) and geometric features (EoFGeoNet). Experimental results show that TCN outperforms long short-term memory (LSTM) in three cases. Our main aim is to deploy deep-learning-based approaches onboard for faster and more accurate real-time monitoring as well as leveraging the higher sampling rates for improved time-series predictions. Many major benefits can be realised if the deep learning models can be implemented onboard, including a sizeable reduction in the volume of downlinked data, and improved system latency. However, implementing deep learning models in space can be a critical task, as most approaches require high computational and memory resources, both of which are limited in typical spacecraft onboard data handling systems. Nevertheless, the EoFNets network outlined in this paper has been optimised to fit the resource constraints of a space platform deployed at the extreme edge far from Earth. Two low-power hardware targets are considered, namely the IntelMovidius MyriadX and Rockchip RK3588S. To the best of our knowledge, this is the first time that such a TCN network has been proposed for solar flare forecasting.

Melanoma is the most lethal form of skin cancer, but early detection can lead to effective treatment. Subsequently, the main concern of the health management community is to create efficient systems to detect melanoma earlier by utilizing computer vision systems since the traditional screening methods are manual, time-consuming, and inaccurate in some cases. These systems use measurable visual components describing the shape, color, and texture. These features are extracted based on rules invented by dermatologists to determine the malignancy of skin lesions. In this paper, we propose a novel approach to melanoma detection based on the “ugly duckling” concept, which suggests that nevi in the same individual usually resemble each other, and malignant melanomas often do not follow this pattern. Our method uses a convolutional neural network architecture to extract feature vectors from dermatoscopic images of skin lesions. Then, out-liers are detected by applying principal component analysis. The outliers are indicative of potential melanoma lesions. We evaluate the performance of our method using a dataset of dermatoscopic images. Our proposed method has shown the potential to improve melanoma detection rates.

To develop an efficient device that helps dermatologists to early evaluate and inspect a specific kind of skin disease, computer vision systems have been intensively studied. These systems replace the traditional screening ways which are manual and time-consuming. These systems use some measurable visual component describing the shape, color, and texture of skin diseases to recognize them and to specify their malignancy. This article will be concentrated on the importance of using some statistical features and extracting the most relevant features of texture-colored images by calculating their degree of characterization. Using these highly-rated static textural features, non-fatal skin disease and melanoma classification results are presented and discussed.