• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1031-1042
• /
• 2023

In this study, a deep learning model was developed to predict the yield of cabbage and radish, one of the five major supply and demand management vegetables, using satellite images of Landsat 8. To predict the yield of cabbage and radish in Gangwon-do from 2015 to 2020, satellite images from June to September, the growing period of cabbage and radish, were used. Normalized difference vegetation index, enhanced vegetation index, lead area index, and land surface temperature were employed in this study as input data for the yield model. Crop yields can be effectively predicted using satellite images because satellites collect continuous spatiotemporal data on the global environment. Based on the model developed previous study, a model designed for input data was proposed in this study. Using time series satellite images, convolutional neural network, a deep learning model, was used to predict crop yield. Landsat 8 provides images every 16 days, but it is difficult to acquire images especially in summer due to the influence of weather such as clouds. As a result, yield prediction was conducted by splitting June to July into one part and August to September into two. Yield prediction was performed using a machine learning approach and reference models , and modeling performance was compared. The model's performance and early predictability were assessed using year-by-year cross-validation and early prediction. The findings of this study could be applied as basic studies to predict the yield of field crops in Korea.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Proceedings of the Korean Aquaculture Society Conference
• /
• 2003.10a
• /
• pp.103-104
• /
• 2003

어류의 양식생산 과정중에는 사육중인 어류에게 스트레스로 작용할 수 있는 여러 가지 요인들이 있다. 그 중에서도 생산된 종묘의 양식장 운송, 수확한 어류의 소비지 운반 등은 양식과정중 피할 수 없는 작업이다. 어류의 수송 후에는 혈장 corticosteroid, glucose, 전해질, 삼투질 농도, 적혈구수, hematocrit, hemoglobin 등이 변화하는 것으로 알려지고 있다(Chang et al. 2001; Hur et al., 2002, 2003). 스트레스 요인별 연구로는 염분, 수온, 밀도 및 마취제에 관한 것 등이며, 아울러 이들의 복합적인 요인에 대하여 스트레스 반응을 최소화시키려는 연구가 진행되고 있다. 어류종묘의 수송이나 수확된 어류가 대량으로 수송되고 있으므로, 넙치(Paralichthys olivaceus)와 같은 대량수송 어류의 수송에 따른 스트레스 반응에 대한 연구의 필요성이 제기된다. 그러므로 본 연구에서는 넙치를 사용하여 염분, 수온 및 마취제에 의한 수송이 스트레스 지표로 알려져 있는 혈액학적 요인, cortisol, glucose, lactic acid 및 삼투질 농도 둥에 나타나는 생리학적 반응을 조사하여, 활어수송 과정에서 나타나는 스트레스 반응에 대한 기초자료를 제공하고자 하였다. 실험어는 21.2 cm, 97.4 g인 양식 넙치를 사용하여, 수온은 20℃ (natural water temperature, NWT)와 15℃ (cooling water temperature, CWT), 염분은 해수(35‰)와 15‰해수, 마취제(anesthesia, Anes., MS-222)는 50 ppm의 조건으로 혼합한 실험구를 설정하였다. 실험구는 각각 NWT＋35‰, CWT＋35‰, NWT＋15‰, NWT＋15‰, NWT＋35‰＋Anes., CWT+35‰＋Anes., NWT＋15‰+Anes. 및 CWT+15‰＋Anes.의 8개 실험구를 2반복으로 설정하여 경북울진∼부산까지 약 400 km (6시간)를 차량수송하였다. 수송용기는 스티로폼상자(66×42×20 cnn)로서, 여기에 해수 3 L와 액화산소를 넣은 비닐봉지에 넙치 8마리씩 수용하여 수송하였다. 혈액의 성상 및 분석항목은 수송전ㆍ후에 채혈하여 비교하였다. 수송전 hematocrit는 22.2±3.8%에서 수송후 NWT＋35‰에서 15.3＋3.9%, CWT＋35‰은 16.7±3.0%, NWT+15‰구에서는 19.2±1.8%로 낮아졌으며, CWT+15‰구는 20.9±3.6%로 수송전과 차이가 없었다. 한편 NWT＋15‰＋Anes.구는 17.8±0.9%, CWT＋15‰＋Anes.구는 14.5±1.5%로 낮아졌다. Cortisol은 수송전 2.4±0.1 ng/ml로부터 CWT＋35‰구는 16.7±12.8 ng/ml, NWT＋35‰구는 47.9＋19.8 ng/ml, NWT＋15‰구는 43.5±13.9 ng/ml, CWT＋15‰구는 26.1±8.3 ng/ml, NWT＋15‰+Anes.구는 61.7±3.3 ng/ml, CWT+15‰+Anes.구는 86.1±19.0 ng/ml로 높아졌다. Glucose는 수송전 74.2±32.6 mg/dl로부터 NWT＋35‰구는 197.9±27.5 mg/dl, CWT＋35‰구도 272.1±29.9 mg/dl로 유의하게 높아졌다. Na/sup +/의 수송전 농도는 163.5±0.6 mEq/L로부터 NWT＋35‰구와 CWT＋35‰구는 각각 175.3±1.2 mEq/L, 190.0±5.0 mEq/L로 높아졌으며, 다른 실험구에서는 차이가 없었다. 본 연구 결과, cortisol과 glucose에서 수송전보다는 모든 실험구에서 높게 나타나 수온, 염분 및 마취제를 사용하여도 스트레스를 받고 있는 것으로 나타났다. 특히, cortisol의 경우, 수온과 염분만을 혼합한 실험구보다 마취제를 혼합한 실험구에서 높게 나타났다. 다른 혈액학적 항목에서는 염분과 마취제를 사용하지 않았던 실험구인 NWT＋35‰구와 CWT＋35‰구에서 다른 실험구에 비하여 glucose, Na/sup +/ 및 Cl/sup -/ 등에서는 높게 나타나는 경향을 보였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.94-104
• /
• 2000

The accuracy and reliability of the target tracking is very critical issue in the design of automotive collision warning radar A significant problem in multi-target tracking (MTT) is the target-to-measurement data association If an incorrect measurement is associated with a target, the target could diverge the track and be prematurely terminated or cause other targets to also diverge the track. Most methods for target-to-measurement data association tend to coalesce neighboring targets Therefore, many algorithms have been developed to solve this data association problem. In this paper, a new multi-target data association method based on order statistics is described The new approaches. called the order statistics probabilistic data association (OSPDA) and the order statistics joint probabilistic data association (OSJPDA), are formulated using the association probabilities of the probabilistic data association (PDA) and the joint probabilistic data association (JPDA) filters, respectively Using the decision logic. an optimal or near optimal target-to-measurement data association is made A computer simulation of the proposed method in a heavy cluttered condition is given, including a comparison With the nearest-neighbor CNN). the PDA, and the JPDA filters, Simulation results show that the performances of the OSPDA filter and the OSJPDA filter are superior to those of the PDA filter and the JPDA filter in terms of tracking accuracy about 18% and 19%, respectively In addition, the proposed method is implemented using a developed digital signal processing (DSP) board which can be interfaced with the engine control unit (ECU) of car engine and with the d?xer through the controller area network (CAN)

• Proceedings of the International Microelectronics And Packaging Society Conference
• /
• 2001.11a
• /
• pp.37-39
• /
• 2001

21세기의 벽두부터 국내외적으로 활발히 논의되고 있는 나노기술에 대한 정의를 생각해보는 것으로부터 우리가 나아갈 방향을 살펴보고자 한다. 나노기술이란, 원자 하나 하나 혹은 분자단위의 조작을 통해 1~100nm정도의 범위 안에서 근본적으로 새로운 물질이나 구조체를 만들어 내는 기술을 말한다. 즉 앞으로 우리는 경험해 보지 못한 새로운 현상에 대한 이해를 할 수 있어야 하고, 새로운 물질 자체를 다룰 수 있는 방법이 우리가 해야 할 구체적인 일이 될 것이란 말이 된다. 뿐만 아니라 나노기술은 종래의 정보.통신.전자 분야에서 주로 추구하던 마이크로화와 달리 재료, 기계, 전자, 의학, 약학, 에너지, 환경, 화학, 생물학, 농학, 정보, 보안기술 등 과학기술 분야 전반을 위시하여 사회분야가지 새로운 인식과 철학적인 이해가 필요하게 되었다. 21세기를 맞은 인류가 나아갈 방향을 나노세계에 대한 도전으로 보아야 하며, 과학기술의 새로운 틀을 제공할 것 임에 틀림 없다. 그러나, 이와 같은 나노기술의 출발점을 살펴보면 VLSI기술로 통칭할 수 있는 마이크로전자소자 기술이란 점이다. 국내의 VLSI기술은 메모리기술이라고 해도 과언이 아닐 것이다. 문제는 종래의 메모리기술은 대규모 투자와 집중적인 인력양성을 통해서 세계 최고 수준에 도달 할 수 있었다. 그러나 여기까지 오는 동안 사식 우리는 선진국의 뒷꽁무니를 혼신의 힘을 다해 뒤쫓아 온 결과라고 보아도 틀리지 않는다. 즉, 앞선자를 보고 뒤쫓는 사람은 갈방향과 목표가 분명하므로 최선을 다하면 따라 잡을 수 있다. 그런데 나노기술은 앞선 사람이 없다는 점이 큰 차이이다 따라서 뒷껑무니를 쫓아가는 습성을 가지고는 개척해 나갈 수 없다는 점을 깨닫지 않으면 안된다. 그런 점에서 이 시간 나노기술의 국내외 현황을 살펴보고 우리가 어떻게 할 것인가를 생각해 보는데 의미가 있을 것이다.하여 분석한 결과 기존의 제한된 RICH-DP는 실시간 서비스에 대한 처리율이 낮아지며 서비스 시간이 보장되지 못했다. 따라서 실시간 서비스에 대한 새로운 제안된 기법을 제안하고 성능 평가한 결과 기존의 RICH-DP보다 성능이 향상됨을 확인 할 수 있었다.(actual world)에서 가상 관성 세계(possible inertia would)로 변화시켜서, 완수동사의 종결점(ending point)을 현실세계에서 가상의 미래 세계로 움직이는 역할을 한다. 결과적으로, IMP는 완수동사의 닫힌 완료 관점을 현실세계에서는 열린 미완료 관점으로 변환시키되, 가상 관성 세계에서는 그대로 닫힌 관점으로 유지 시키는 효과를 가진다. 한국어와 영어의 관점 변환 구문의 차이는 각 언어의 지속부사구의 어휘 목록의 전제(presupposition)의 차이로 설명된다. 본 논문은 영어의 지속부사구는 논항의 하위간격This paper will describe the application based on this approach developed by the authors in the FLEX EXPRIT IV n$^{\circ}$EP29158 in the Work-package "Knowledge Extraction & Data mining"where the information captured from digital newspapers is extracted and reused in tourist information context.terpolation performance of CNN was relatively better than NN.콩과 자연 콩이 성분 분석에서 차이를 나타내지 않았다는 점, 네 번째. 쥐를 통한 다양섭취 실험에서 아무런 이상 반응이 없었다는 점등의 결과를 기준으로 알레르기에 대한 개별 검사 없이 안전한

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.2
• /
• pp.138-144
• /
• 2020

Currently, an autonomous vehicle studies are working to develop a four-level autonomous vehicle that can cope with emergencies. In order to flexibly respond to an emergency, the autonomous vehicle must move in a direction to minimize the damage, which must be conducted by judging all the states of the road, such as the surrounding pedestrians, road conditions, and surrounding vehicle conditions. Therefore, in this paper, we suggest a passenger detection and sharing system to detect the passenger situation inside the autonomous vehicle and share it with V2V to the surrounding vehicles to assist in the operation of the autonomous vehicle. Passenger detection and sharing system improve the weighting method that recognizes passengers in the current vehicle to identify the passenger's position accurately inside the vehicle, and shares the passenger's position of each vehicle with other vehicles around it in case of emergency. So, it can help determine the driving of a vehicle. As a result of the experiment, the body pressure sensor applied to the passenger recognition sub-module showed about 8% higher accuracy than the conventional resonant sensor and about 17% higher than the piezoelectric sensor.

• Journal of Biomedical Engineering Research
• /
• v.39 no.5
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.8-14
• /
• 2020

Recently, there was an increasing demand for an integrated access control system which is capable of user recognition, door control, and facility operations control for smart buildings automation. The market available door lock access control solutions need to be improved from the current level security of door locks operations where security is compromised when a password or digital keys are exposed to the strangers. At present, the access control system solution providers focusing on developing an automatic access control system using (RF) based technologies like bluetooth, WiFi, etc. All the existing automatic door access control technologies required an additional hardware interface and always vulnerable security threads. This paper proposes the user identification and authentication solution for automatic door lock control operations using camera based visible light communication (VLC) technology. This proposed approach use the cameras installed in building facility, user smart devices and IoT open source controller based LED light sensors installed in buildings infrastructure. The building facility installed IoT LED light sensors transmit the authorized user and facility information color grid code and the smart device camera decode the user informations and verify with stored user information then indicate the authentication status to the user and send authentication acknowledgement to facility door lock integrated camera to control the door lock operations. The camera based VLC receiver uses the artificial intelligence (AI) methods to decode VLC data to improve the VLC performance. This paper implements the testbed model using IoT open-source based LED light sensor with CCTV camera and user smartphone devices. The experiment results are verified with custom made convolutional neural network (CNN) based AI techniques for VLC deciding method on smart devices and PC based CCTV monitoring solutions. The archived experiment results confirm that proposed door access control solution is effective and robust for automatic door access control.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.672-680
• /
• 2019

This paper proposes "A Smart Farm Environment Optimization and Yield Prediction Platform based on IoT and Deep Learning" which gathers bio-sensor data from farms, diagnoses the diseases of growing crops, and predicts the year's harvest. The platform collects all the information currently available such as weather and soil microbes, optimizes the farm environment so that the crops can grow well, diagnoses the crop's diseases by using the leaves of the crops being grown on the farm, and predicts this year's harvest by using all the information on the farm. The result shows that the average accuracy of the AEOM is about 15% higher than that of the RF and about 8% higher than the GBD. Although data increases, the accuracy is reduced less than that of the RF or GBD. The linear regression shows that the slope of accuracy is -3.641E-4 for the ReLU, -4.0710E-4 for the Sigmoid, and -7.4534E-4 for the step function. Therefore, as the amount of test data increases, the ReLU is more accurate than the other two activation functions. This paper is a platform for managing the entire farm and, if introduced to actual farms, will greatly contribute to the development of smart farms in Korea.