High-quality underwater images are a vital source of modern marine vision and multimedia applications. But low visibility with color and contrast distortions in uneven underwater illumination conditions poses several challenges to these applications (e.g., visual servoing, long-range navigation, unmanned underwater vehicles, and SONAR imaging, etc.) working in robust conditions from dawn to dusk. Direct enhancement deteriorates the structure and texture with objectionable color casts due to distance-dependent attenuation and light scattering. This paper presents an adaptive self-supervised network for underwater image enhancement (ASSU-Net), which can work without relying on the type and quantity of training images, rather, it is capable of working with only a few input images. In this network, we split the image into reflection and illumination components to simplify the solution space, allowing us to handle the artifacts associated with each component independently. A structure and texture awareness scheme is introduced while following the mutual consistency of decomposition in combination with the histogram distribution. This scheme is embedded in the network to constrain objectionable artifacts (i.e., structure texture and edge distortions). The network loss is optimized to force the network to learn with a few shots of unpaired data, where we preserve visual details for low-lit underwater images. Extensive experiments are performed to demonstrate the superiority of the proposed method.

Data centers (DC) host a large number of servers, computing devices and computing infrastructure, which incur significant electricity / energy. This also results in huge amount of heat produced, which if not addressed can lead to overheating of computing devices in the DC. In addition, temperature mismanagement can lead to thermal imbalance within the DC environment, which may result in the creation of hotspots. The energy consumed during the life of a hotspot is greater than the energy saved during computation. Hence, the thermal imbalance impacts on the efficiency of the cooling mechanism installed inside the DC, which can result in high energy consumption. One popular strategy to minimize energy consumption is to optimize resource allocation within the DC. However, existing scheduling strategies do not consider the ambient effect of the surrounding nodes at the time of job allocation. Moreover, thermal-aware resource scheduling as an optimization problem is a topic that is relatively understudied in the literature. Therefore, in this research, we propose a novel Game-based Thermal-Aware Resource Allocation (GTARA) strategy to reduce the thermal imbalances within the DC. Specifically, we use cooperative game theory with a Nash-bargaining solution concept to model the resource allocation as an optimization problem, where the user jobs are assigned to the computing nodes based on their thermal profiles and their potential effect on the surrounding nodes. This allows us to improve the thermal balance and avoid the hotspots. We then demonstrate the effectiveness of GTARA, TACS, TASA, and FCFS, in terms of minimizing thermal imbalance and the hotspots.