Emerging technologies, such as smart wearable devices, augmented reality (AR)/virtual reality (VR) displays, and naked-eye 3D projection, have gradually entered our lives, accompanied by an urgent market demand for high-end display technologies. Ultra-high-resolution displays, flexible displays, and transparent displays are all important types of future display technology, and traditional display technology cannot meet the relevant requirements. Micro-light-emitting diodes (micro-LEDs), which have the advantages of a high contrast, a short response time, a wide color gamut, low power consumption, and a long life, are expected to replace traditional liquid-crystal displays (LCD) and organic light-emitting diodes (OLED) screens and become the leaders in the next generation of display technology. However, there are two major obstacles to moving micro-LEDs from the laboratory to the commercial market. One is improving the yield rate and reducing the cost of the mass transfer of micro-LEDs, and the other is realizing a full-color display using micro-LED chips. This review will outline the three main methods for applying current micro-LED full-color displays, red, green, and blue (RGB) three-color micro-LED transfer technology, color conversion technology, and single-chip multi-color growth technology, to summarize present-day micro-LED full-color display technologies and help guide the follow-up research.
The system-in-package (SiP) has gained much interest in the current rapid development of integrated circuits (ICs) due to its advantages of integration, shrinking, and high density. This review examined the SiP as its focus, provides a list of the most-recent SiP innovations based on market needs, and discusses how the SiP is used in various fields. Reliability issues must be resolved if the SiP is to operate normally. Three factors—thermal management, mechanical stress and electrical properties—can be paired with specific examples in order to detect and improve package reliability. This review provides a thorough overview of SiP technology, serves as a guide and foundation for the SiP in package reliability design, and addresses the challenges and potential for further development of this kind of package.
High-resolution pixel LED headlamps are lighting devices that can produce high-resolution light distribution to adapt to road and traffic conditions, intelligently illuminate traffic areas, and assist drivers. Due to the complexity of roads and traffic conditions, the functional diversity of high-resolution pixel LEDs headlamps and traffic safety has come into question and is the subject of in-depth research conducted by car manufacturers and regulators. We summarize the current possible functions of high-resolution pixel LED headlamps and analyze ways in which they could be improved. This paper also discusses the prospect of new technologies in the future.
With the rapid development of computer hardware and the emergence of the parallel calculation of diffraction fields, a breakthrough has been made in terms of the limitation of the unacceptable amount of computational cost to design diffractive optical elements (DOEs), and more accurate global search algorithms can be introduced to the design of complex DOEs and holographic projections instead of traditional iterative algorithms. In this paper, a hybrid algorithm which combines particle swarm optimization (PSO) with a simulated annealing (SA) algorithm is proposed for the designing of DOEs and projecting holographic images with less noise. PSO is used to reduce the invalid disturbance in SA, and SA can jump out from local extreme points to find the global extreme points. Compared with the traditional Gerchberg–Saxton (GS) algorithm, the simulation and experimental results demonstrate that the proposed SA–PSO hybrid algorithm can improve uniformity by more than 10%.
Controlled Environmental Agriculture (CEA) has gained a lot of attention in recent years, mainly because of its ability to overcome extreme weather problems and ensure food safety. CEA can meet the full growth state monitoring of the crop period; however, the optimization of the growing environment is still limited by the algorithm defects. In this article, we present an optimization method of growing environment based on reinforcement learning, Q-learning and the time-series prediction model Informer. This approach is demonstrated for the first time as far as we know. By employing Informer, we predicted the growth of strawberries based on current environmental variables and plant status. The prediction results served as a reward to motivate Q-learning, guiding it to make optimal modifications to the environment in real-time. This approach aimed to achieve the optimal cultivation environment continuously. Two groups of validation experiments were conducted based on different cultivation objectives: “obtaining the most stolons” and “obtaining the highest fruit count”. Compared to the empirically planted groups, the experimental groups using the RL-Informer model achieved yield increases of 17.81% and 20.78%, respectively. These experiments highlight the outstanding performance of the proposed RL-Informer model in real-time prediction and modification of environmental variables.
Feature detection of strawberry multi-type defects and the ripeness stage faces huge challenges because of color diversity and visual similarity. Images from hyperspectral near-infrared (NIR) information sources are also limited by their low spatial resolution. In this study, an accurate RGB image (with a spatial resolution of pixels) and NIR image (ranging from 700–1100 nm in wavelength, covering 146 bands, and with a spatial resolution of pixels) fusion method was proposed to improve the detection of defects and features in strawberries. This fusion method was based on a pretrained VGG-19 model. The high-frequency parts of original RGB and NIR image pairs were filtered and fed into the pretrained VGG-19 simultaneously. The high-frequency features were extracted and output into ReLU layers; the -norm was used to fuse multiple feature maps into one feature map, and area pixel averaging was introduced to avoid the effect of extreme pixels. The high- and low-frequency parts of RGB and NIR were summed into one image according to the information weights at the end. In the validation section, the detection dataset included expanded 4000 RGB images and 4000 NIR images (training and testing set ratio was 4:1) from 240 strawberry samples labeled as mud contaminated, bruised, both defects, defect-free, ripe, half-ripe, and unripe. The detection neural network YOLOv3-tiny operated on RGB-only, NIR-only, and fused image input modes, achieving the highest mean average precision of 87.18% for the proposed method. Finally, the effects of different RGB and NIR weights on the detection results were also studied. This research demonstrated that the proposed fusion method can greatly improve the defect and feature detection of strawberry samples.