Abstract

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

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
Methane (CH4) detection plays a crucial role in atmospheric monitoring, industrial safety, global climate assessments, and environmental sensing. Laser absorption spectroscopy techniques have become the gold standard for achieving fast, selective, and highly sensitive CH4 measurements across a wide range of conditions. This review summarizes the main spectroscopic methods used for methane detection, their operating principles, performance characteristics, and practical implementation considerations. Emphasis is placed on tunable diode laser absorption spectroscopy (TDLAS), wavelength modulation spectroscopy (WMS), Dual-Comb Spectroscopy (DCS), cavity-enhanced methods such as CRDS, photoacoustic and photothermal techniques including QEPAS and hollow-core fiber photothermal interferometry, and emerging MIR/quantum-cascade–based approaches. © 2001-2012 IEEE.

Abstract
Similarity is a key property across two or more interactive systems. Indeed, interacting with similar systems can bring benefits (e.g., reduced learning efforts and training time) but may also raise issues (e.g., interference errors and higher cognitive load). Interactive systems may be similar, as they correspond to the same work and tasks performed with different underlying systems, such as the pilots’ tasks in the cockpit of an Airbus A320 and a Boeing 737. They may also be similar by design, as they belong to the same suite as, for instance, the Microsoft Office software suite, where several tools are designed to be used concurrently by the same users. Previous work on similarity has focused on the visual presentation of interactive applications, highlighting commonalities and differences in terms of layout, shape, colours and other features of the user interface. This paper proposes a systematic and formal approach to analyse and assess the similarity between several interactive systems, focusing on their behaviours. To this end, we propose a tool-supported process that exploits both interactive formal system behaviour models and user task models. These models are analysed with the help of formal tools (model checking) to identify commonalities and differences in their exhibited behaviours. Beyond, we compare the specific and generic behavioural properties of each model, which provide semantic and meaningful information about how similar they are and how they differ. The approach is applied to two similar critical command and control interactive systems for flight safety operations in the space domain. © 2026 Copyright held by the owner/author(s).