• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.6
• /
• pp.295-306
• /
• 2016

The purpose of this paper is both to analyze research trends and to predict industrial flows using the meta-data from the previous studies on data quality. There have been many attempts to analyze the research trends in various fields till lately. However, analysis of previous studies on data quality has produced poor results because of its vast scope and data. Therefore, in this paper, we used a text mining, social network analysis for time series network analysis to analyze the vast scope and data of data quality collected from a Web of Science index database of papers published in the international data quality-field journals for 10 years. The analysis results are as follows: Decreases in Mathematical & Computational Biology, Chemistry, Health Care Sciences & Services, Biochemistry & Molecular Biology, Biochemistry & Molecular Biology, and Medical Information Science. Increases, on the contrary, in Environmental Sciences, Water Resources, Geology, and Instruments & Instrumentation. In addition, the social network analysis results show that the subjects which have the high centrality are analysis, algorithm, and network, and also, image, model, sensor, and optimization are increasing subjects in the data quality field. Furthermore, the industrial connection analysis result on data quality shows that there is high correlation between technique, industry, health, infrastructure, and customer service. And it predicted that the Environmental Sciences, Biotechnology, and Health Industry will be continuously developed. This paper will be useful for people, not only who are in the data quality industry field, but also the researchers who analyze research patterns and find out the industry connection on data quality.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.4
• /
• pp.345-353
• /
• 2007

We have obtained a topographical image nondestructively for a Cu thin film in liquid using a near-field scanning microwave microscope (NSMM), its operating frequency was 3.5 to 5.5 GHz. We have kept a distance of 10 nm between tip and sample using a quartz tuning fork shear force feedback system. As an end of tip was attached to one prong of the quartz tuning fork has a length of 2 mm, the only tip of tuning fork was immersed in water tank. A loss cause by evaporation in water tank is regulated with actuator was connected to a supplementary tank. Moreover, using a revise program of LabView, we could increase the accuracy of a measurement in liquid.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1227-1234
• /
• 2008

In this paper is designed a 256-bit synchronous OTP(one-time programmable) memory required in application fields such as automobile appliance power ICs, display ICs, and CMOS image sensors. A 256-bit synchronous memory cell consists of NMOS capacitor as antifuse and access transistor without a high-voltage blocking transistor. A gate bias voltage circuit for the additional blocking transistor is removed since logic supply voltage VDD(=1.5V) and external program voltage VPPE(=5.5V) are used instead of conventional three supply voltages. And loading current of cell to be programmed increases according to RON(on resistance) of the antifuse and process variation in case of the voltage driving without current constraint in programming. Therefore, there is a problem that program voltage can be increased relatively due to resistive voltage drop on supply voltage VPP. And so loading current can be made to flow constantly by using the current driving method instead of the voltage driving counterpart in programming. Therefore, program voltage VPP can be lowered from 5.9V to 5.5V when measurement is done on the manufactured wafer. And the sens amplifier circuit is simplified by using the sens amplifier of clocked inverter type instead of the conventional current sent amplifier. The synchronous OTP of 256 bits is designed with Magnachip $0.13{\mu}m$ CMOS process. The layout area if $298.4{\times}314{\mu}m2$.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.2
• /
• pp.257-264
• /
• 2007

In order to obtain a fine picture, a camera has many convenient functions. Its representative functions are Auto Focus(AF), Auto White Balance(AWB) and Auto Exposure(AE). In this paper, we present the new algorithm of Auto Exposure control system, one of its useful functions The proposed algorithm of Auto Exposure control system is based on IIR Filter with Variable Time Constant. First, in order to establish the standards of exposure control, we compare change of the picture luminance with luminance of an object in the Zone system. Second, we make an ideal characteristic graph of luminance by using the results. Finally, we can find the value of the right exposure by comparing an ideal characteristic graph of the luminance with the value of the current expose of a scene. We can find an appropriate exposure as comparing the ideal characteristic graph of the luminance with current exposure of a scene. In order to find a suitable exposure state, we make use of IIR Filter instead of a conventional method using micro-controller. In this paper, the proposed system has therefore simple structure, we use it for compact image sensor module used in the handheld device.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.9
• /
• pp.57-65
• /
• 2010

This paper describes the method of efficient container number recognition in colored container image with number plate at ATC(Automatic Transfer Crane) in container terminal yard. At the Sinseondae terminal gate in Busan, the container number recognition system is installed by "intelligent port-logistics system technology development", that is government research and development project. It is the method that it sets up the tunnel structure inside camera on the gate and it recognizes the container number in order to recognize the export container cargo automatically. However, as the automation equipment is introduced to the container terminal and the unmanned of a task is gradually accomplished, the container number recognition system for the confirmation of the object of work is required at ATC in container terminal yard. Therefore, the container number recognition system fitted for it is necessary for ATC in container terminal yard in which there are many intrusive of the character recognition through image including a sunlight, rain, snow, shadow, and etc. unlike the gate. In this paper, hardware components of the camera, illumination, and sensor lamp were altered and software elements of an algorithm were changed. that is, the difference of the brightness of the surrounding environment, and etc. were regulated for recognize a container number. Through this, a shadow problem, and etc. that it is thickly below hung with the sunlight or the cargo equipment were solved and the recognition time was shortened and the recognition rate was raised.

• Korean Journal of Remote Sensing
• /
• v.35 no.3
• /
• pp.375-387
• /
• 2019

The use of drone-based hyperspectral image offers considerable advantages in high resolution remote sensing applications. The primary objective of this study was to select the optimal bands based on hyperspectral image for the estimation yield of the chinese cabbage. The hyperspectral narrow bands were acquired over 403.36 to 995.19 nm using a 3.97 nm wide, 150 bands, drone-based hyperspectral imaging sensor. Fresh weight data were obtained from 2,031 sample for each field survey. Normalized difference vegetation indices were computed using red, red-edge and near-infrared bands and their relationship with quantitative each fresh weights were established and compared. As a result, predominant proportion of fresh weights are best estimated using data from three narrow bands, in order of importance, centered around 697.29 nm (red band), 717.15 nm (red-edge band) and 808.51 nm (near-infrared band). The study determined three spectral bands that provide optimal chinese cabbage productivity in the visible and near-infrared portion of the spectrum.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.257-270
• /
• 2022

In this paper, we design a smart factory risk improvement system and risk improvement method using AI edge devices. The smart factory risk improvement system collects, analyzes, prevents, and promptly responds to the worker's work performance process in the smart factory using AI edge devices, and can reduce the risk that may occur during work with improving the defect rate when workers perfom jobs. In particular, based on worker image information, worker biometric information, equipment operation information, and quality information of manufactured products, it is possible to set an abnormal risk condition, and it is possible to improve the risk so that the work is efficient and for the accurate performance. In addition, all data collected from cameras and IoT sensors inside the smart factory are processed by the AI edge device instead of all data being sent to the cloud, and only necessary data can be transmitted to the cloud, so the processing speed is fast and it has the advantage that security problems are low. Additionally, the use of AI edge devices has the advantage of reducing of data communication costs and the costs of data transmission bandwidth acquisition due to decrease of the amount of data transmission to the cloud.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.

• Korean Journal of Optics and Photonics
• /
• v.35 no.1
• /
• pp.9-17
• /
• 2024

A plenoptic optical system for microscopy comprises an objective lens, tube lens, microlens array (MLA), and an image sensor. Numerical aperture (NA) matching between the tube lens and MLA is used for optimal performance. This paper extends performance predictions from NA matching to unmatching cases and introduces a computational technique for plenoptic configurations using optical analysis software. Validation by fabricating and experimenting with two sample systems at 10× and 20× magnifications resulted in predicted spatial resolutions of 12.5 ㎛ and 6.2 ㎛ and depth of field (DOF) values of 530 ㎛ and 88 ㎛, respectively. The simulation showed resolutions of 11.5 ㎛ and 5.8 ㎛, with DOF values of 510 ㎛ and 70 ㎛, while experiments confirmed predictions with resolutions of 11.1 ㎛ and 5.8 ㎛ and DOF values of 470 ㎛ and 70 ㎛. Both formula-based prediction and simulations yielded similar results to experiments that were suitable for system design. However, regarding DOF values, simulations were closer to experimental values in accuracy, recommending reliance on simulation-based predictions before fabrication.