Underwater object detection is critical for marine ecological monitoring and biodiversity research, yet existing algorithms struggle in detecting densely packed objects of varying sizes, particularly in occluded and complex underwater environments. This study introduces Underwater-Yolo, a novel detection network that enhances performance in these challenging scenarios by integrating a dual-branch occlusion-handling attention mechanism (GLOAM) and a Cross-Stage Partial Dilated Deformable Convolution (CSP-DDC) backbone. The dilated deformable convolutions (DDCs) in the backbone and neck expand the receptive field, thereby improving the detection of small objects, while the deformable convolutions enhance the model’s adaptive feature extraction capabilities for unstructured objects. Additionally, the CARAFE up-sampling operator in the neck aggregates contextual information across a broader spatial domain. The GLOAM, consisting of a global branch (using a Vision Transformer to capture global features and object–background relationships) and a local branch (enhancing the detection of occluded objects through depthwise–pointwise convolutions), further optimizes performance. By incorporating these innovations, the model effectively addresses the challenges of detecting small and occluded objects in dense underwater environments. The evaluation on the CLfish-V1 dataset shows significant improvements over state-of-the-art algorithms, with an AP50 of 93.8%, an AP75 of 88.9%, and an AP-small of 76.4%, marking gains of 4.7%, 16.7%, and 6%, respectively. These results demonstrate the model’s effectiveness in complex underwater scenarios.

The working temperature is one of the key factors affecting the efficiency and safety performance of automotive power batteries. Current battery pack design primarily focuses on single layout configurations, overlooking the potential impact of mixed arrangements on thermal management performance. This study presents a module-based optimization methodology for comprehensive concept design of Lithium-ion (Li-ion) battery pack. Firstly, the arrangement modules is optimized and performed using particle swarm optimization algorithms considering various arrangement layout (i.e. rectangular, diamond, and staggered arrangements) by taking the intercell spacing and maximum temperature of the modules as design objectives. Secondly, the battery pack configuration design is performed employing a neural network model reflect diverse battery module configurations within the pack, exploring their impact on thermal management performance. The hybrid battery arrangement effectively improves thermal management, and the module spacing helps to enhance heat dissipation. The staggered arrangement has a greater impact on the heat dissipation performance of the battery pack, but the spacing between different modules varies with the position of the modules. When all configuration schemes are staggered modules, the optimal range of the spacing between modules is between 6 and 7 mm. However, the study observes a non-linear relationship between module spacing and the maximum temperature difference within the battery pack. While increasing module spacing initially decreases temperature differences, it eventually reverses, suggesting that spacing alone may not consistently enhance thermal management. Validation with a lithium-ion battery pack case study demonstrates the method’s effectiveness, providing valuable knowledge for future cell and pack designs that employ different battery cell arrangements and diverse cooling strategies.

Underwater vision technology is crucial for marine exploration, aquaculture, and environmental monitoring. However, the challenging underwater conditions, including light attenuation, color distortion, reduced contrast, and blurring, pose difficulties. Current deep learning models and traditional image enhancement techniques are limited in addressing these challenges, making it challenging to acquire high-quality underwater image signals. To overcome these limitations, this study proposes an approach called adaptive multi-scale multi-color space underwater image enhancement with GAN-physics fusion (AMSMC-UGAN). AMSMC-UGAN leverages multiple color spaces (RGB, HSV, and Lab) for feature extraction, compensating for RGB’s limitations in underwater environments and enhancing the use of image information. By integrating a membership degree function to guide deep learning based on physical models, the model’s performance is improved across different underwater scenes. In addition, the introduction of a multi-scale feature extraction module deepens the granularity of image information, learns the degradation distribution of different image information of the same image content more comprehensively, and provides useful guidance for more comprehensive data for image enhancement. AMSMC-UGAN achieved maximum scores of 26.04 dB, 0.87, and 3.2004 for PSNR, SSIM, and UIQM metrics, respectively, on real and synthetic underwater image datasets. Additionally, it obtained gains of at least 6.5%, 6%, and 1% for these metrics. Empirical evaluations on real and artificially distorted underwater image datasets demonstrate that AMSMC-GAN outperforms existing techniques, showcasing superior performance with enhanced quantitative metrics and strong generalization capabilities.

Design solution space (DSS) exploration is a pivotal process for comprehending design challenges and identifying diverse solution alternatives based on varying requirements. Computer-aided design (CAD) approaches, such as parametric design, knowledge-based design, and generative design, have proven successful in DSS exploration. However, a comparative study evaluating their performance is lacking in the technical literature. This paper addresses this gap by conducting a comparative analysis of these approaches regarding their performance in exploring DSS. The research begins by providing an overview of parametric design, knowledge-based design, and generative design, establishing the foundation for the study. Six evaluation criteria are identified based on the DSS exploration process. A qualitative analysis is then conducted, considering these criteria, to objectively assess the performance of each modeling approach. The results highlight the strengths and weaknesses of each approach, revealing that DSS exploration success is directly tied to the quantity of implemented knowledge. The results also emphasize the complementarity of those approaches, as their strengths and weaknesses are based on different problem-solving logics, demonstrating the synergy that can be achieved through strategic combinations of them. Additionally, the paper discusses open issues related to DSS exploration, contributing valuable insights for future developments in this field.

Lightweight and adaptive adjustment are key research directions for deep neural networks (DNNs). In coal industry mining, frequent changes in raw coal sources and production batches can cause uneven distribution of appearance features, leading to concept drift problems. The network architecture and parameters should be adjusted frequently to avoid a decline in model accuracy. This poses a significant challenge for those without specialist expertise. Although the Neural Architecture Search (NAS) has a strong ability to automatically generate networks, enabling the automatic design of highly accurate networks, it often comes with complex internal topological connections. These redundant architectures do not always effectively improve network performance, especially in resource-constrained environments, where their computational efficiency is significantly reduced. In this paper, we propose a method called Topology Complexity Neural Architecture Search (TCNAS). TCNAS proposes a new method for evaluating the topological complexity of neural networks and uses both topological complexity and accuracy to guide the search, effectively obtaining lightweight and efficient networks. TCNAS employs an adaptive shrinking search space optimization method, which gradually eliminates poorly performing cells to reduce the search space, thereby improving search efficiency and solving the problem of space explosion. In the classification experiments of coal and gangue, the optimal network designed by TCNAS has an accuracy of 83.3%. And its structure is much simpler, which is about 1/53 of the parameters of the network dedicated to coal and gangue recognition. Experiments have shown that TCNAS is able to generate networks that are both efficient and simple for resource-constrained industrial applications.