Abstract
Multi-label image classification models often inevitably learn on partially labeled datasets, where a considerable proportion of labels are missing. However, the popular PyTorch deep learning ecosystem is less compatible with training on partially labeled datasets, as many built-in functions like loss functions and metrics do not work correctly or raise errors when unknown labels are present. To this end, we present an original and easy-to-install Python package called mlcpl, which expands the PyTorch ecosystem to offer a friendly environment for learning with partially labeled datasets. The package provides a series of multi-label loss functions and metrics that are compatible with unknown labels. Seven recently proposed approaches are also implemented for the convenient use of cutting-edge techniques. In addition, eleven dataset loading functions, followed by three partial label simulation schemes, expedite the development of experiments. Furthermore, these functions are simple to use, have a PyTorch-like interface, and can collaborate well with other PyTorch components. Several examples of experiments with mlcpl are also provided for demonstration. We wish the release of this package could facilitate relevant academic research and real-world applications. The source code is available at https://github.com/ maxium0526/mlcpl.

Abstract
Solar photovoltaic (PV) power generation has become one of the most widely adopted forms of clean energy worldwide. In large-scale PV farm operation and maintenance, unmanned aerial vehicles equipped with thermal infrared (TIR) cameras are increasingly used to enable automated fault detection and classification. However, the long imaging distance and the inherently low resolution of TIR images often lead to fault patterns appearing with low contrast, making subtle discriminative features difficult to extract and posing significant challenges to achieving highly accurate fault identification and classification. To address these challenges, we propose GEPFNet, a network that exploits Group Equivariant Convolutions to explicitly model the geometric structures of faults, incorporates multi-scale processing with unified local-global contextual representations, and adopts a parallel feature fusion strategy to integrate multi-level features and enhance contextual utilization effectively. The design of feature extraction and fusion mechanisms ensures the proposed GEPFNet achieves strong robustness and generalization under complex operational conditions. The effectiveness of GEPFNet was validated on two public datasets with distinct resolutions, class distributions, and feature characteristics: PVF-10 and the Infrared Solar Module (ISM) dataset. Extensive experiments and statistical analyses demonstrate that the proposed GEPFNet achieves state-of-the-art performance on the PVF-10 dataset, obtaining an accuracy of 96.05 %+/- 0.42 for the 2-Class task and 94.64 %+/- 0.35 for the 10-Class task. On the ISM dataset, GEPFNet achieves an improvement of approximately 5 % over the baseline models. Moreover, under highly imbalanced data distributions, the proposed GEPFNet achieves average accuracy improvements of 5.83% and 3.82% on PVF-10 and ISM, respectively, further demonstrating its capability to enhance class-wise performance. With only 9.51 GFLOPs, GEPFNet also exhibits notable computational efficiency, making it well suited for PV fault classification in TIR imagery.

Abstract
The main aim of this chapter is to analyze the potential of the metaverse in the context of religious marketing. Positioned within the wider process of digitalization, the chapter examines how digital channels, from websites and social media to immersive environments, create opportunities for religious institutions to reach, engage, and involve their audiences. Several illustrations of uses of digital platforms, applications, virtual reality, and the metaverse are presented and discussed. Particular attention is given to the opportunities offered by the metaverse, while also acknowledging the challenges of adoption and the need for strategies aligned with institutional values and the expectations of faith communities. © 2026 by IGI Global Scientific Publishing. All rights reserved..

Abstract
Purpose Grounded in source credibility and the elaboration likelihood model (ELM), the current study examines the impact of influencers' credibility and consumer involvement on consumer attitudes and purchase intention, exploring potential changes in consumer behaviour before and after the COVID-19 pandemic. In addition, the mediating role of consumer involvement was examined. Design/methodology/approach A repeated cross-sectional research design was applied to compare consumer behaviour at two different time points. Two sets of data (pre-pandemic, consisting of 297 participants and post-pandemic, consisting of 307 participants) were collected through an online survey among female consumers of beauty products. Findings The findings confirm the positive effect of influencers' credibility on attitudes and consumer involvement. Moreover, the findings highlight the direct impact of consumer involvement on consumer attitudes and purchase intention. In addition, the mediating role of consumer involvement is supported. The comparison between pre- and post-pandemic periods revealed that influencers' credibility demonstrated a weaker effect on attitudes towards influencer-endorsed products after the pandemic. Conversely, consumer involvement had a strong influence on attitudes toward influencer-endorsed products after the pandemic. Practical implications The findings, along with the comparison of the two data sets, provide theoretical and practical implications regarding the relationship between influencers' credibility and consumer involvement. Originality/value This study provides empirical evidence on consumer behaviour before and after the COVID-19 pandemic, using a repeated cross-sectional design to identify and compare changes in habits and attitudes across two distinct time periods.

Abstract
Integrating Industry 4.0 and Quality 4.0 optimises manufacturing through IoT and ML, improving processes and product quality. The primary challenge involves identifying patterns in computer numerical control (CNC) machining time-series data to boost manufacturing quality control. The proposed solution involves an experimental study comparing one-class and binary classification algorithms. This study aims to classify time-series data from CNC turning machines, offering insight into monitoring and adjusting tool wear to maintain product quality. The methodology entails extracting spectral features from time-series data to train both one-class and binary classification algorithms, assessing their effectiveness and computational efficiency. Although certain models consistently outperform others, determining the best performing is not possible, as a trade-off between classification and computational performance is observed, with gradient boosting standing out for effectively balancing both aspects. Thus, the choice between one-class and binary classification ultimately relies on dataset's features and task objectives.

Abstract
Outlier detection is a widely used technique for identifying anomalous or exceptional events across various contexts. It has proven to be valuable in applications like fault detection, fraud detection, and real-time monitoring systems. Detecting outliers in real time is crucial in several industries, such as financial fraud detection and quality control in manufacturing processes. In the context of big data, the amount of data generated is enormous, and traditional batch mode methods are not practical since the entire dataset is not available. The limited computational resources further compound this issue. Boxplot is a widely used batch mode algorithm for outlier detection that involves several derivations. However, the lack of an incremental closed form for statistical calculations during boxplot construction poses considerable challenges for its application within the realm of big data. We propose an incremental/online version of the boxplot algorithm to address these challenges. Our proposed algorithm is based on an approximation approach that involves numerical integration of the histogram and calculation of the cumulative distribution function. This approach is independent of the dataset's distribution, making it effective for all types of distributions, whether skewed or not. To assess the efficacy of the proposed algorithm, we conducted tests using simulated datasets featuring varying degrees of skewness. Additionally, we applied the algorithm to a real-world dataset concerning software fault detection, which posed a considerable challenge. The experimental results underscored the robust performance of our proposed algorithm, highlighting its efficacy comparable to batch mode methods that access the entire dataset. Our online boxplot method, leveraging dataset distribution to define whiskers, consistently achieved exceptional outlier detection results. Notably, our algorithm demonstrated computational efficiency, maintaining constant memory usage with minimal hyperparameter tuning.