The thickness of the indium tin oxide (ITO) layer is a critical parameter affecting the performance of solar cells. Traditional measurement methods require sample collection, leading to manufacturing interruptions and potential quality issues. In this paper, we propose a real-time, non-contact approach using deep learning and optical interference phenomena to estimate the thickness of ITO layers in solar cells. We develop a convolutional neural network (CNN) model that processes microscopic images of solar cells and predicts the ITO layer thickness. In addition, mean absolute error (MAE) and mean squared error (MSE) loss functions are combined to train the model. Experimental results demonstrate the effectiveness of our approach in accurately estimating the ITO layer thickness. The integration of computer vision and deep learning techniques provides a valuable tool for non-destructive testing and quality control in the manufacturing of solar cells. The loss of the model after training is reduced to 0.83, and the slope of the test value in the scatter plot with the true value of the ellipsometer is approximately equal to 1, indicating the high reliability of the model.

Cameras are becoming more pervasive and ubiquitous. The daily activities of individuals are being captured by millions of cameras in public spaces, while individuals are obtaining massive amounts of egocentric videos by employing wearable cameras intended for life-logging. However, recording devices are inexpensive, highly computational, and inconvenient for privacy. We used a low-resolution infrared sensor to detect human activity, including sitting, standing, and lying down, and to locate humans. We acquired the data from a low-cost infrared device and preprocessed them to train the YOLO-v5 network. We developed and tested an infrared technology-based system consisting of $32 \times 24$ thermal input. Our proposed model is trained on 3,864 low-resolution images and made publicly available. The trained YOLO-v5 achieved 96.34% mean Average Precision (mAP) using our designed lightweight and low-cost activity recognition device. We proposed Artificial Intelligence of Things (A-IoT) system can be used either as a stand-alone data collection such as an IoT device or as a data processing and analysis sub-center. Our system consists of a low-power edge computing device and a cost-effective low-resolution infrared module. Our proposed dataset is now available at https://github.com/InfoLab-SKKU/Thermal-Human-Detection

In the 5G era, the emergence of various base stations and the extensive deployment across large areas exacerbate the interference problem, particularly between macro base stations and micro base stations. To address these challenges, we consider both inter-layer and intra-layer interference and propose a comprehensive mechanism for clustering-based resource allocation. This mechanism consists of three key components. First, we cluster the femtocell base stations (FBS). The FBSs are then classified into optimal disjoint clusters through graph theory and convex optimization, making the system more adaptive. Second, we allocate channels to users using a subchannel allocation algorithm that prioritizes user fairness, assigning subchannels to both the femtocell users (FUE) and the macro users (MUE) based on rate fairness. Finally, the FBS employs distributed power allocation to minimize power adjustment complexity. Results demonstrate that the proposed method suppresses both inter-layer and intra-layer interference effectively, enhances the average user rate and increases overall user satisfaction.

Software simulation of building energy consumption has become one of the normal means of measuring building energy consumption. This paper uses Openstudio energy simulation software to construct passive residential building models from the perspective of envelope, internal loads and air conditioning systems, and future climate change. Selecting the SRESA2 emissions scenario downscales to generate weather files for the 2050s and 2080s, forecasts future passive residential building energy consumption, and analyzes the influencing factors of passive residential energy consumption. The software simulation results show that the lighting density power and equipment power of the internal load, as well as the COP of the air conditioning system and the interior design temperature, all affect the total energy consumption of the building to varying degrees. The heat transfer coefficient of the exterior walls and the temperature of the COP air conditioning system and the interior design temperature have the greatest influence on passive residential buildings. To provide reference for strategies related to passive residential building design under future climate change.