• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.311-318
• /
• 2022

Tobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.777-782
• /
• 2017

The Signal Intelligence (SIGINT) system based on the adaptive beamformer, comprised of the AOA estimator followed by the interference canceller, is a cutting edge technology for collecting various signal information utilizing all sorts of devices such as the radar and satellite. In this paper, we present the efficient adaptive SIGINT structure consisted of an AOA estimator and an adaptive beamformer. For estimating AOA information of various signals, we employ the Multiple Signal Classification (MUSIC) algorithm and for efficiently suppressing high-power interference signals, we employ the Minimum Variance Distortionless Response (MVDR) algorithm. Also, we provide computer simulation examples to verify the performance of the presented adaptive beamformer structure.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.476-482
• /
• 2020

In this paper, we propose a block-based modularity architecture design method for distributed machine learning. The proposed architecture is a block-type module structure with various machine learning algorithms. It allows free expansion between block-type modules and allows multiple machine learning algorithms to be organically interlocked according to the situation. The architecture enables open data communication using the metadata query protocol. Also, the architecture makes it easy to implement an application service combining various edge computing devices by designing a communication method suitable for surrounding applications. To confirm the interlocking between the proposed block-type modules, we implemented a hardware-based modularity application system.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.1
• /
• pp.173-182
• /
• 1988

A program for drawing of penetrating lines was developed in personal computer. PROLOG, a language of Artificial Intelligence, was used and a data structure using relational data base was designed. An algorithm for finding the penetrating lines in the real space was developed. The program can be applied at any types of penetrating problems like curve-surface, surface-surface, curve-object, surface-object, object-object, etc. In developing the program, the following results were obtained. (1) Relational data base built in PROLOG and the function of backtracking are helpful in Computer Graphics. (2) In spite of increasing the number of edges, assigning direction to the edges makes it possible to represent the polygon meshes as the non ordered sets of directional half edges. (3) Topologicaly the penetrating lines of a polygon can be represented as the edge-pairs in the edge list of the polygon,

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.272-275
• /
• 2022

The federated learning can be utilized in conjunction with the blockchain technology to provide good privacy protection and reward distribution mechanism in the field of intelligent IOT in edge computing scenarios. Nonetheless, the synchronous federated learning ignores the waiting delay due to the heterogeneity of edge devices (different computing power, communication bandwidth, and dataset size). Moreover, the potential of smart contracts was not fully explored to do some flexible design. This paper investigates the fusion application based on the FLchain, which is the combination of asynchronous federated learning and blockchain, discusses the communication optimization, and explores the feasible design of smart contract to solve some problems.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.166-171
• /
• 2023

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.433-438
• /
• 2017

Containing an Angle-of-Arrival(: AOA) estimation and interference suppression techniques, an adaptive beamformer is one of core techniques for the Signal Intelligence(: SIGINT) which collect various intelligence utilizing cutting edge devices including the radar and satellite. It generates a beam with the directivity in a corresponding direction, to efficiently receive a signal from the specific direction, using antenna array. In this paper, we present the received signal model including interference signals and noise, which can be applied to an input of the signal intelligence satellite system equipped with the AOA estimation and the interference cancellation techniques, and analysis the characteristics of various signals, which can be included in the proposed received signal model. This proposed signal model can be directly applied to the performance evaluation for a variety of beamforming techniques. Also, we verify the spectrum characteristic of the presented received signal model in the frequency domain through computer simulation examples.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.300-306
• /
• 2022

Currently, Korea is building traffic infrastructure using Intelligent Transport Systems (ITS), but the pedestrian traffic accident rate is very high. The purpose of this paper is to prevent the risk of traffic accidents by jaywalking pedestrians. The development of this study aims to detect pedestrians who trespass using the public data set provided by the Artificial Intelligence Hub (AIHub). The data set uses training data: 673,150 pieces and validation data: 131,385 pieces, and the types include snow, rain, fog, etc., and there is a total of 7 types including passenger cars, small buses, large buses, trucks, large trailers, motorcycles, and pedestrians. has a class format of Learning is carried out using YOLOv5 as an implementation model, and as an object detection and edge detection method of an input image, a canny edge model is applied to classify and visualize human objects within the detected road boundary range. In this study, it was designed and implemented to detect pedestrians using the deep learning-based YOLOv5 model. As the final result, the mAP 0.5 showed a real-time detection rate of 61% and 114.9 fps at 338 epochs using the YOLOv5 model.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.22-29
• /
• 2022

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2^TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2^TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.865-871
• /
• 2022

In this paper, we propose a method of extracting prostate region using morphological characteristics of ultra-sonic image of prostate. In the first step of the proposed method, the edge area of the prostate image is extracted. The histogram of ultra-sonic image is used to extract base objects to detect the upper edge of prostate region by altering the contrast of the image, then, the lower edges of the extracted base objects are connected by using monotone cubic spline interpolation to extract the upper edge. Step 2, Otsu's binarization is applied to the region under the extracted upper edge of the prostate ultra-sonic image to extract the lower edge of prostate. In the last step, the upper and the lower edges are connected to extract prostate region and by comparing the extracted region of prostate with the one measured manually, the result showed that the morphological characteristics of prostate in ultrasonic image can be utilized to extract the prostate region.