The study applies the black kite algorithm (BKA), equilibrium optimizer (EO), and secretary bird optimization algorithm (SBOA) to optimize the placement of electric vehicle charge stations (EVCSs), wind turbine stations (WTSs), photovoltaic units (PVUs), and capacitor banks (CAPBs) in the IEEE 69-node distribution power grid. Three single objectives, including power loss minimization, grid power minimization, and total voltage deviation improvement, are considered. For each objective function, five scenarios are simulated under one single operation hour, including (1) place-only EVCSs; (2) place EVCSs and PVUs; (3) place EVCSs, PVUs, and CAPBs; (4) EVCSs and WTSs; and (5) EVCSs, PVUs, WTSs, and CAPBs. The results indicate that the EO can find the best solutions for the five scenarios. The results indicate that the EO and SBOA are the two powerful algorithms that can find optimal solutions for simulation cases. For one operating day, the total grid energy that is supplied to base loads and charge stations is 80,153.1 kWh, and many nodes at high load factors violate the lower limit of 0.95 pu. As for installing more renewable power sources, the energy that the base loads and charge stations need to supply from the grid is 39,713.4 kWh. As more capacitor banks are installed, the energy demand continues to be reduced to 39,578.9 kWh. The energy reduction is greater than 50% of the demand of all base loads and charge stations. Furthermore, the voltage can be significantly improved up to higher than 0.95 pu, and a few nodes at a few hours fall into the lowest range. Thus, the study concludes that the economic and technical aspects can be guaranteed for DPGs with additional installation of EVCSs.

Image-based ship detection is a critical function in maritime security. However, lacking high-quality training datasets makes it challenging to train a robust supervision deep learning model. Conventional methods use data augmentation to increase training samples. This approach is not robust because the data augmentation may not present a complex background or occlusion well. This paper proposes to use an information bottleneck and a reparameterization trick to address the challenge. The information bottleneck learns features that focus only on the object and eliminate all backgrounds. It helps to avoid background variance. In addition, the reparameterization introduces uncertainty during the training phase. It helps to learn more robust detectors. Comprehensive experiments show that the proposed method outperforms conventional methods on Seaship datasets, especially when the number of training samples is small. In addition, this paper discusses how to integrate the information bottleneck and the reparameterization into well-known object detection frameworks efficiently.

Fire is considered one of the most serious threats to human lives which results in a high probability of fatalities. Those severe consequences stem from the heavy smoke emitted from a fire that mostly restricts the visibility of escaping victims and rescuing squad. In such hazardous circumstances, the use of a vision-based human detection system is able to improve the ability to save more lives. To this end, a thermal and infrared imaging fusion strategy based on multiple cameras for human detection in low-visibility scenarios caused by smoke is proposed in this paper. By processing with multiple cameras, vital information can be gathered to generate more useful features for human detection. Firstly, the cameras are calibrated using a Light Heating Chessboard. Afterward, the features extracted from the input images are merged prior to being passed through a lightweight deep neural network to perform the human detection task. The experiments conducted on an NVIDIA Jetson Nano computer demonstrated that the proposed method can process with reasonable speed and can achieve favorable performance with a mAP@0.5 of 95%.