• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2199-2213
• /
• 2024

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

• Journal of Energy Engineering
• /
• v.26 no.2
• /
• pp.64-72
• /
• 2017

The performance analysis of the 70 W class LED lighting system suitable for the Middle East environment was performed using the lumped parameter model. The LED light is composed of a heating substrate, a heat pipe, and a heat sink. We divided the LED lights into four objects and applied energy equilibrium to each of them to establish four lumped nonlinear differential equations. The solution of the simultaneous equations was obtained by the Runge-Kutta method. Convective heat transfer coefficients of the lumped model were obtained by multidimensional CFD analysis. As a result of comparison with experiment, it was found that the heating substrate had an error of $1.5^{\circ}C$ and the upper heat sink had an error of $1.8^{\circ}C$ and the relative error was about 0.6 %. Using this model, temperature distribution analysis was performed for normal operating conditions with an ambient temperature of $55^{\circ}C$, with sunlight only, with abnormal operating conditions with sunlight, and without an upper heat sink.

• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.449-460
• /
• 2005

This paper proposes a method to track persons robustly in illumination changes and partial occlusions in color video frames acquired from a fixed camera. To solve a problem of changing appearance by illumination change, a time-independent intrinsic image is used to remove noises in an frame and is adaptively updated frame-by-frame. We use a hierarchical human model including body color information in order to track persons in occlusion. The tracked human model is recorded into a persons' list for some duration after the corresponding person's exit and is recovered from the list after her reentering. The proposed method was experimented in several indoor and outdoor scenario. This demonstrated the potential effectiveness of an adaptive model-base method that corrected distorted person's color information by lighting changes, and succeeded tracking of persons which was overlapped in a frame.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.649-655
• /
• 2020

This study determined effective educational strategies by investigating and analyzing the related educational demands for SMEs (small and medium-sized enterprises) in the 4th Industrial Revolution based area of smart farms. In order to derive the approprate educational strategies, Importance-Performance Analysis (IPA) and Borich's Needs Assessment Model were conducted based on the smart farm technological field. As a result, the education demand survey showed high demand for production systems and intelligent farm machinery. In detail, Borich's analysis showed the need for pest prevention and diagnosis technology (8.03), network and analysis SW linkage technology (7.83), and intelligent farm worker-agricultural power system-electric energy hybrid technology (7.43). In contrast, smart plant factories (4.09), lighting technology for growth control (4.46) and structure construction technology (4.62) showed low demands. Based on this, the IPA portfolio shows that the network and analysis SW linkage technology and the CAN-based complex center are urgently needed. However, the technology that has already been developed, such as smart factory platform development, growth control lighting technology and structure construction technology, was oversized. Based on these results, it is possible to strategically suggest the customized training programs for industrial sectors of SMEs that reflect the needs for efficiently operating smart farms. This study also provides effective ways to operate the relevant training programs.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1597-1609
• /
• 2004

A lot of lipreading system has been proposed to compensate the rate of speech recognition dropped in a noisy environment. Previous lipreading systems work on some specific conditions such as artificial lighting and predefined background color. In this paper, we propose a real-time lipreading system which allows the motion of a speaker and relaxes the restriction on the condition for color and lighting. The proposed system extracts face and lip region from input video sequence captured with a common PC camera and essential visual information in real-time. It recognizes utterance words by using the visual information in real-time. It uses the hue histogram model to extract face and lip region. It uses mean shift algorithm to track the face of a moving speaker. It uses PCA(Principal Component Analysis) to extract the visual information for learning and testing. Also, it uses HMM(Hidden Markov Model) as a recognition algorithm. The experimental results show that our system could get the recognition rate of 90% in case of speaker dependent lipreading and increase the rate of speech recognition up to 40～85% according to the noise level when it is combined with audio speech recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.67-74
• /
• 2012

In this paper, we propose an efficient dynamic background modelling method by using eigenbackground to extract moving objects from video stream. Even if a background model has been created, the model has to be updated to adapt to change due to several reasons such as weather or lighting. In this paper, we update a background model based on R-SVD method. At this time we define a change ratio of images and update the model dynamically according this value. Also eigenbackground need to be modelled by using sufficient training images for accurate models but we reorganize input images to reduce the number of images for training models. Through simulation, we show that the proposed method improves the performance against traditional eigenbackground method without background updating and a previous method.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.6
• /
• pp.103-110
• /
• 2011

The aim of this study was to analysis the Heating/cooling performance and Daylighting performance of Solar Window System built in apartments. the solar window is the idea to integrate daylight as a third form of solar energy into a PV/Solar Collector system. The process of this study is as follows: 1)Solar Window system was designed through the investigation of previous paper and work. 2)The simulation program(Lightscape3.2) was used in daylighting performance analysis. the reference model of simulation was made up to analysis daylighting performance on Solar Window system. 3)The simulation program(ESP-r, Therm5.0, Window6.0) was used in energy performance analysis. the reference model of simulation was made up to analysis energy and daylighting performance on Solar Window system. 4)The Size of Simulation model for daylighting and heating/cooling energy analysis was $148.5m^2$ 5)The lighting performance analysis was carried out with various variants, such as the size and installed area of Solar Window system. 6)Energy performance simulation was carried out with various variants, such as Integrated U-value of Solar Window system according to its position, installed angle and insulation thickness. Consequently, When Solar Window system is equipped with balcony window of Apartment, Annual heating and cooling energy of reference model was cut down at the average of $4.1kWh/m^2$ or 4.2%.

• Korea Real Estate Review
• /
• v.27 no.1
• /
• pp.17-32
• /
• 2017

The openness of residential space directly affecting lighting, view, and ventilation leads to the variation of open floor plan type in apartment construction project. This study intends to substantiate the effect to the apartment price by design property of open floor plan based on actual design information of apartment and price. The open floor plan type and associated design property, and actual transaction price of apartment have been considered as variables for analysis by the hedonic price function model and artificial neural networks model. Research findings indicate that the openness affects the price of apartment positively and the three sides open plan is the most preferred with the highest price. This study aims to provide the implication to the developer in planning and design stage of apartment and the purchaser seeking the suitable price by floor plan design.

• Journal of the Korean Society of Safety
• /
• v.31 no.2
• /
• pp.18-25
• /
• 2016

The incandescent lamp is an electric light fixture with a tungsten filament heated to a high temperature, by passing an electric current through it, until it glows with visible light. The hot filament is protected from oxidation with a glass bulb that is filled with inert gas. The incandescent lamp has fire risk when combustible materials are close to its glass bulb. Because its lamp has the property which converts 90~95 percents of the electric power to heat energy. 2015 national fire statistics show that fires caused by lighting fixtures were 652 cases, and incandescent lamps(44 cases) and halogen lamps(53 cases) accounted for 15 percents in those of high heating light fixtures. Since incandescent lamp fires account for about 45 percents in the high heating light fixture, we could not overlook the fire risks by the incandescent lamp. Although many studies related with those have been conducted, incandescent lamp fires are continuously occurred. This study was carried out to study the fire risk of ignition of wood due to radiant heat of incandescent lamp. Radiant heat flux of the incandescent lamp was predicted by applying point source model, and critical distance for ignition of wood was calculated by applying integral model. The results from this study could applied to fire prevention activities related to light bulb, and it could be used in fire cause investigations related to radiant heat of incandescent lamp.