DSpace 集合:

A robust color enhancement for underwater images

2026-03-12T03:49:02Z

標題: A robust color enhancement for underwater images 作者: Hu, Kuo-Jui; Pan, Yi-Tsung; Huang, Ching-Chung; Pan, Ya-Ling; Kao, Sheng-Long 摘要: Due to various complex factors in underwater environments. Several issues must to be considered in obtaining clear underwater images, including color cast, low contrast, blurry details, haze, climate, environment and human factors can significantly affect the analysis and research applications of underwater images. The primary causes are the atomization effect caused by dispersion and the color cast caused by inconsistent energy attenuation of each wavelength as light propagates through water. Different original underwater images exhibit varying characteristics, such as diverse color distributions or illumination levels. Applying a single enhancement method to all underwater images may lead to inconsistent results, where some images are effectively enhanced while others are not. To address this issue, this research proposed a novel 2 stage classification-based mechanism after images were dehazed. We employ four image enhancement techniques with proper conditions and proposes a classification-based mechanism for enhancing underwater images. Furthermore, a color correction method based on an improved Gray-World white balance algorithm is introduced. We address the limited dynamic range and brightness issues in underwater images. Quantitative and qualitative results show that our research performs relatively well in the Underwater Image Enhancement Benchmark (UIEB) dataset compared to other recent methods. It is expected to be applied to different types of underwater work and environments, reducing the severe degradation issues commonly encountered in underwater images.

Measuring energy and CO₂ efficiency of global airlines using dynamic network DEA under natural and managerial disposability framework

2026-03-12T03:37:00Z

標題: Measuring energy and CO₂ efficiency of global airlines using dynamic network DEA under natural and managerial disposability framework 作者: See, Kok Fong; Guo, Yongli; Yu, Ming-Miin 摘要: Despite strong demand for air transportation, airlines are experiencing profitability and environmental sustainability challenges. This study uses a dynamic network DEA model to evaluate the operational and environmental efficiency of 24 airlines from 2017 to 2019, considering natural disposability, managerial disposability, and unified efficiency. The results show efficiency level based on managerial disposability concept is higher than natural disposability, indicating proactive environmental regulation responses. In addition, high energy and CO2 efficiencies were observed, especially under managerial disposability. However, balancing operational and environmental performance remains challenging, with many airlines struggling to achieve simultaneous improvements. This study offers new perspectives for sustainable development in the industry by assessing airline performance under a unified framework.

Optimal airside reassignment following temporary incidents with variations in arrival or departure times

2026-03-12T03:36:59Z

標題: Optimal airside reassignment following temporary incidents with variations in arrival or departure times 作者: Tang, Ching-Hui; Chen, Yu-Yang 摘要: We develop an integrated model for gate, taxiway, and runway reassignments following airside incidents such as temporary gate closures, taxiway closures, or changes in wind direction. We consider changes in aircraft ground movements and times due to these temporary incidents and variations in arrival or departure times. An airside network is developed to model runway, taxiway, and gate operations. Arrival, departure, and transit aircraft airside operations are considered simultaneously. The results indicate that taxiway and gate closures always have a negative influence on airside ground operations, but a change in wind direction does not follow any specific trend. In addition, a gate closure has a greater negative influence than a taxiway closure, by as much as 19% for a 10-hour closure.

Minimizing Order Picking Travel Distance using a DNN-Based Method Within a High-Level Storage Warehouse

2026-03-12T03:36:40Z

標題: Minimizing Order Picking Travel Distance using a DNN-Based Method Within a High-Level Storage Warehouse 作者: Yang, Ming-Feng; Wu, Ming-Hung; Kao, Sheng-Long; Hsu, Ching-Cheng; Chen, Jeng-Chung; Wang, Jen-Chieh; Kuo, Jun-Yuan; Fu, Kai-Wei 摘要: With the rapid growth of e-commerce, the increasing volume of orders and demand for shorter delivery times pose significant challenges to warehouse management, particularly in optimizing high-level storage systems where complex calculations are required. In recent years, deep neural networks (DNNs) have demonstrated remarkable success in pattern recognition and classification, offering a promising avenue for warehouse optimization. This study proposes a novel DNN-based order batching algorithm aimed at minimizing pickers' total travel time in high-level storage systems. The method consists of two stages: in the first stage, a deep neural network is trained to recognize and classify picking route patterns; in the second stage, a Genetic Algorithm (GA) is employed to batch orders within the categories identified by the DNN. Numerical experiments across eight scenarios demonstrate that the proposed DNN-GA method achieves travel distance reductions of up to 34.8% compared to random batching, while traditional GA achieves reductions of up to 10.8%, highlighting the superior efficiency of the proposed approach. Theoretically, this study establishes a foundational framework for utilizing DNNs in order classification, while practically, it demonstrates the potential to reduce warehouse operating costs by optimizing computational resources and minimizing travel distances.

DSpace 集合:

A robust color enhancement for underwater images

Measuring energy and CO2 efficiency of global airlines using dynamic network DEA under natural and managerial disposability framework

Optimal airside reassignment following temporary incidents with variations in arrival or departure times

Minimizing Order Picking Travel Distance using a DNN-Based Method Within a High-Level Storage Warehouse

Measuring energy and CO₂ efficiency of global airlines using dynamic network DEA under natural and managerial disposability framework