In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

This paper addresses the critical need for quadcopters in GPS-denied indoor environments by proposing a novel attitude control mechanism that enables autonomous navigation without external guidance. Utilizing AR marker detection integrated with a dual PID controller algorithm, this system ensures accurate maneuvering and positioning of the quadcopter by compensating for the absence of GPS, a common limitation in indoor settings. This capability is paramount in environments where traditional navigation aids are ineffective, necessitating the use of quadcopters equipped with advanced sensors and control systems. The actual position and location of the quadcopter is achieved by AR marker detection technique with the image processing system. Moreover, in order to enhance the reliability of the attitude PID control, the dual closed loop control feedback PID control with dual update periods is suggested. With AR marker detection technique and autonomous attitude control, the proposed quadcopter system decreases the need of additional sensor and manual manipulation. The experimental results are demonstrated that the quadrotor's autonomous attitude control and operation with the dual closed loop control feedback PID controller with hierarchical (inner-loop and outer-loop) command update period is successfully performed under the non-GPS aided indoor environment and it enhanced the reliability of the attitude and the position PID controllers within 17 seconds. Therefore, it is concluded that the proposed attitude control mechanism is very suitable to GPS-denied indoor environments, which enables a quadcopter to autonomously navigate and hover without external guidance or control.

This study aims to derive a technology development roadmap in related fields by utilizing patent documents of financial technology. To this end, patent documents are extracted by dragging technical keywords from prior research and related reports on financial technology. By applying the TF-IDF (Term Frequency-Inverse Document Frequency) technique in the extracted patent document, which is a text mining technique, to the extracted patent documents, the Latent Dirichlet Allocation (LDA) algorithm was applied to identify the keywords and identify the topics of the core technologies of financial technology. Based on the proportion of topics by year, which is the result of LDA, promising technology fields and convergence fields were identified through trend analysis and similarity analysis between topics. A first-stage technology development roadmap for technology field development and a second-stage technology development roadmap for convergence were derived through network analysis about the technology data-based integrated management system of the high-dimensional payment system using RF and intelligent cards, as well as the security processing methodology for data information and network payment, which are identified financial technology fields. The proposed method can serve as a sufficient reason basis for developing financial technology R&D strategies and technology roadmaps.

The purpose of this study is to develop a sophisticated web-based artificial intelligence chatbot system designed to provide personalized dietary service for diabetic patients. According to a 2022 study, the prevalence of diabetes among individuals over 30 years old was 15.6% in 2020, identifying it as a significant societal issue with an increasing patient population. This study uses generative AI algorithms to tailor dietary recommendations for the elderly and various social classes, contributing to the maintenance of healthy eating habits and disease prevention. Through meticulous fine-tuning, the learning loss of the AI model was significantly reduced, nearing zero, demonstrating the chatbot's potential to offer precise dietary suggestions based on calorie intake and seasonal variations. As this technology adapts to diverse health conditions, ongoing research is crucial to enhance the accessibility of dietary information for the elderly, thereby promoting healthy eating practices and supporting disease prevention.

In this paper, we explore the application of Kodaly hand signs in enhancing children's music education, performances, and auditory assistance technologies. This research focuses on improving the recognition rate of Multilayer Perceptron (MLP) models in identifying Kodaly hand sign scales through the integration of Artificial Neural Networks (ANN). We developed an enhanced MLP model by augmenting it with additional parameters and optimizing the number of hidden layers, aiming to substantially increase the model's accuracy and efficiency. The augmented model demonstrated a significant improvement in recognizing complex hand sign sequences, achieving a higher accuracy compared to previous methods. These advancements suggest that our approach can greatly benefit music education and the development of auditory assistance technologies by providing more reliable and precise recognition of Kodaly hand signs. This study confirms the potential of parameter augmentation and hidden layers optimization in refining the capabilities of neural network models for practical applications.