• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2627-2642
• /
• 2023

Parkinson's disease (PD) is a typical, chronic neurodegenerative disease involving the concentration of dopamine, which can disrupt motor activity and cause different degrees of gait disturbance relevant to PD severity in patients. As current clinical PD diagnosis is a complex, time-consuming, and challenging task that relays on physicians' subjective evaluation of visual observations, gait disturbance has been extensively explored to make automatic detection of PD diagnosis and severity rating and provides auxiliary information for physicians' decisions using gait data from various acquisition devices. Among them, wearable sensors have the advantage of flexibility since they do not limit the wearers' activity sphere in this application scenario. In this paper, an attention-based temporal network (ATN) is designed for the time series structure of gait data (vertical ground reaction force signals) from foot sensor systems, to learn the discriminative differences related to PD severity levels hidden in sequential data. The structure of the proposed method is illuminated by Transformer Network for its success in excavating temporal information, containing three modules: a preprocessing module to map intra-moment features, a feature extractor computing complicated gait characteristic of the whole signal sequence in the temporal dimension, and a classifier for the final decision-making about PD severity assessment. The experiment is conducted on the public dataset PDgait of VGRF signals to verify the proposed model's validity and show promising classification performance compared with several existing methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.131-138
• /
• 2023

In this paper, a free space optical communication device that can be used in a mobile base station of several km or less was fabricated and its characteristics were investigated. To overcome the loss due to atmospheric transmission, an optical fiber amplifier (EDFA) with an output of 23 dBm or more was used. In order to increase the focusing speed and miniaturization of the laser beam, an optical lens was manufactured, and a transmission lens was designed to have beam divergence within the range of 1.5 to 1.8 [mrad]. A PT module that controls PAN/TILT was fabricated in order to reduce pointing errors and effective automatic alignment between transceiver devices. In this study, Reed-Solomon (RS) code was used to maintain the transmission quality above a certain level. It was manufactured to be able to communicate at a wireless distance of 300m in a weather situation with visibility of 300m. For performance measurement, it was measured using BERT and eye pattern analyzer, and it was confirmed that BER can be maintained at 2.5Gbps.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.203-211
• /
• 2024

Utilizing programming languages for data visualization can enhance the efficiency and effectiveness in handling data volume, processing time, and flexibility. However, practice is required to become proficient in programming. Therefore public data-based the problem bank was developed to practice data visualization in a programming automatic assessment system. Public data were collected based on topics suggested in the curriculum and were preprocessed to make it suitable for users to visualize. The problem bank was associated with the mathematics curriculum to learn various data visualization methods. The developed problems were reviewed to expert and pilot testing, which validated the level of the questions and the potential of integrating data visualization in math education. However, feedback indicated a lack of student interest in the topics, leading us to develop additional questions using student-center data. The developed problem bank is expected to be used when students who have learned Python in primary school information gifted or middle school or higher learn data visualization.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.4
• /
• pp.126-138
• /
• 2017

Recently, the national interest in environment is increasing and for dealing with water environment-related issues swiftly and accurately, the demand to facilitate the analysis of water environment data using a GIS is growing. To meet such growing demands, a spatial network data-based stream network analysis map(Korean Reach File; KRF) supporting spatial analysis of water environment data was developed and is being provided. However, there is a difficulty in delineating catchment areas, which are the basis of supplying spatial data including relevant information frequently required by the users such as establishing remediation measures against water pollution accidents. Therefore, in this study, the development of a computer program was made. The development process included steps such as designing a delineation method, and developing an algorithm and modules. DEM(Digital Elevation Model) and FDR(Flow Direction) were used as the major data to automatically delineate catchment areas. The algorithm for the delineation of catchment areas was developed through three stages; catchment area grid extraction, boundary point extraction, and boundary line division. Also, an add-in catchment area delineation module, based on ArcGIS from ESRI, was developed in the consideration of productivity and utility of the program. Using the developed program, the catchment areas were delineated and they were compared to the catchment areas currently used by the government. The results showed that the catchment areas were delineated efficiently using the digital elevation data. Especially, in the regions with clear topographical slopes, they were delineated accurately and swiftly. Although in some regions with flat fields of paddles and downtowns or well-organized drainage facilities, the catchment areas were not segmented accurately, the program definitely reduce the processing time to delineate existing catchment areas. In the future, more efforts should be made to enhance current algorithm to facilitate the use of the higher precision of digital elevation data, and furthermore reducing the calculation time for processing large data volume.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.203-219
• /
• 2011

Previously common users just want to watch the video contents without any specific requirements or purposes. However, in today's life while watching video user attempts to know and discover more about things that appear on the video. Therefore, the requirements for finding multimedia or browsing information of objects that users want, are spreading with the increasing use of multimedia such as videos which are not only available on the internet-capable devices such as computers but also on smart TV and smart phone. In order to meet the users. requirements, labor-intensive annotation of objects in video contents is inevitable. For this reason, many researchers have actively studied about methods of annotating the object that appear on the video. In keyword-based annotation related information of the object that appeared on the video content is immediately added and annotation data including all related information about the object must be individually managed. Users will have to directly input all related information to the object. Consequently, when a user browses for information that related to the object, user can only find and get limited resources that solely exists in annotated data. Also, in order to place annotation for objects user's huge workload is required. To cope with reducing user's workload and to minimize the work involved in annotation, in existing object-based annotation automatic annotation is being attempted using computer vision techniques like object detection, recognition and tracking. By using such computer vision techniques a wide variety of objects that appears on the video content must be all detected and recognized. But until now it is still a problem facing some difficulties which have to deal with automated annotation. To overcome these difficulties, we propose a system which consists of two modules. The first module is the annotation module that enables many annotators to collaboratively annotate the objects in the video content in order to access the semantic data using Linked Data. Annotation data managed by annotation server is represented using ontology so that the information can easily be shared and extended. Since annotation data does not include all the relevant information of the object, existing objects in Linked Data and objects that appear in the video content simply connect with each other to get all the related information of the object. In other words, annotation data which contains only URI and metadata like position, time and size are stored on the annotation sever. So when user needs other related information about the object, all of that information is retrieved from Linked Data through its relevant URI. The second module enables viewers to browse interesting information about the object using annotation data which is collaboratively generated by many users while watching video. With this system, through simple user interaction the query is automatically generated and all the related information is retrieved from Linked Data and finally all the additional information of the object is offered to the user. With this study, in the future of Semantic Web environment our proposed system is expected to establish a better video content service environment by offering users relevant information about the objects that appear on the screen of any internet-capable devices such as PC, smart TV or smart phone.

• 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 architectural history
• /
• v.12 no.1 s.33
• /
• pp.25-41
• /
• 2003

This paper is a study of Le Corbusier's trace regulateur of the 1920s, particularly its role in the design of the Villas La Roche-Jeanneret and Stein-de Monzie. It proceeds on the basis of the following three themes: first, the relation between the regulating line and the dom-ino frame; second, its status as a proportional device based not on a module system but one that defines relations; third, its function as an essential practical device in the design process. In the Villa La Roche-Jeanneret, the embedded horizontal planes of the dom-ino frame were constant, but the vortical lines of the columns were altered according to the changes in plan. Initially, a left-hand bay window formed a symmetry with the right-hand bay window, the only constant in the design process. With subsequent changes, mullion sections of the horizontal window and roof elements came to provide the reference points for the regulating line. Eventually, a regulating line different from the one that controlled the bay window and the elongated volume came to control the entrance hall of Villa La Roche, resulting in three different kinds of regulating lines in the final version. In contrast to the Villa La Roche-Jeanneret, a singular and consistent regulation line was anticipated in the earliest design stages of the Villa Stein-de Monzie. The repetition of its A:B grid and the standard $2.5m{\times}1.0m$ sliding window determined the proportions of both its plan and elevation, and thus the regulating line became 'automatic,' losing its viability as a practical tool. Though the regulating titles of the La Roche-Jeanneret look as if they were an afterthought, drawn after the design was complete, they were most active, requiring tenacity and discipline in their application. On the other hand, the seemingly 'redundant' regulating line of the Villa Stein-de Monzie gains its raison d'etre from the dom-ino frame. Its cantilevers and uninterrupted horizontal window could be used in decisive fashion because of the guarantee that the correct proportion would always be maintained. Thus we discover that Le Corbusier's discipline of the 1920s had a certain spectrum of flexibility. His 'parti' ranged from the extremely loose and malleable grid of the Villa La Roche-Jeanneret to the fixed grid of the Villa Stein-de Monzie. In different ways, these projects retain the tension between the dom-ino frame and the regulating line. For Le Corbusier, as much as the grid was an object with fixed attributes, it was also an active medium manipulated by the will of the architect.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04b
• /
• pp.731-734
• /
• 2001

우편물을 집배원이 배달하는 순서로 자동구분 처리하기 위한 요소기술 줌에서 4-state 바코드 시스템이 개발되고 있으며 우편번호, 배달순서코드, 고객정보 등이 적용될 예정이다. 기존의 고객 바코드 판독 시스템은 우편물상의 바코드 심볼로지가 존재하는 판독대상 영역의 기울기가 ${\pm}4.47^{\circ}$ 이하이고, 심볼의 훼손과 잡영이 없을 경우에 $79{\sim}100msec(35,000{\sim}45,000$통/시간)의 속도로 자동 구분 정보가 판독된다. 본 논문에서는 판독범위 및 판독성능을 개선을 위하여 CCD(Charge Coupled Device) 센서로부터 획득된 이미지상에서 존재하는 심볼로지 정보의 고속판독 방법을 제시한 것이다. 이 판독방법은 그레이(gray) 이미지 바탕면의 경계값(threshold) 기울기 분포를 기준으로 2개의 경계값을 설정하여 판독대상 정보를 획득하였다. 또한, 4-state 바코드 심볼로지의 존재 가능성 영역만을 탐색하고, 판독대상 영역에서 트래커(tracker)를 탐색하여 심볼로지의 기울기값, 심볼로지 경계값, 심볼위치 좌표값을 생성한 후 심볼값이 판독한 것이다. 판독시험 결과는 판독대상 영역의 심볼로지가 ${\pm}45^{\circ}$ 기울어지고, 잡영이 존재할 경우에도 $30{\sim}60msec(58,000{\sim}l16,000$통/시간) 이내에 판독되었다. 우편물 자동구분용 바코드 판독기로써 적용될 경우에 판독속도가 평균 57.25% 이상 개선되고, 판독범위의 확장으로 0.2%의 기계적인 오류(이송과정예서의 Jam 발생 비율)를 제외할 경우에 거의 99.8% 우편물을 판독하여 자동구분 처리할 수 있게 될 것으로 기대된다.onebook 엑세스 모들(Server Phonebook Access Module)로 구성되어 있다.외 보다 높았다(I/O ratio 2.5). BTEX의 상대적 함량도 실내가 실외보다 높아 실내에도 발생원이 있음을 암시하고 있다. 자료 분석결과 유치원 실내의 벤젠은 실외로부터 유입되고 있었고, 톨루엔, 에틸벤젠, 크실렌은 실외뿐 아니라 실내에서도 발생하고 있었다. 정량한 8개 화합물 각각과 총 휘발성 유기화합물의 스피어만 상관계수는 벤젠을 제외하고는 모두 유의하였다. 이중 톨루엔과 크실렌은 총 휘발성 유기화합물과 좋은 상관성 (톨루엔 0.76, 크실렌, 0.87)을 나타내었다. 이 연구는 톨루엔과 크실렌이 총 휘발성 유기화합물의 좋은 지표를 사용될 있고, 톨루엔, 에틸벤젠, 크실렌 등 많은 휘발성 유기화합물의 발생원은 실외뿐 아니라 실내에도 있음을 나타내고 있다.>10)의 $[^{18}F]F_2$를 얻었다. 결론: $^{18}O(p,n)^{18}F$ 핵반응을 이용하여 친전자성 방사성동위원소 $[^{18}F]F_2$를 생산하였다. 표적 챔버는 알루미늄으로 제작하였으며 본 연구에서 연구된 $[^{18}F]F_2$가스는 친핵성 치환반응으로 방사성동위원소를 도입하기 어려운 다양한 방사성의 약품개발에 유용하게 이용될 수 있을 것이다.었으나 움직임 보정 후 영상을 이용하여 비교한 경우, 결합능 변화가 선조체 영역에서 국한되어 나타나며 그 유의성이 움직임 보정 전에 비하여 낮음을 알 수 있었다. 결론: 뇌활성화 과제 수행시에 동반되는 피험자의 머리 움직임에 의하여 도파민 유리가 과대평가되었으며 이는 이 연구에서 제안한 영상정합을 이용한 움직임 보정기법에 의해서 개선되었다. 답이 없는 문제, 문제 만

• Science of Emotion and Sensibility
• /
• v.6 no.4
• /
• pp.15-23
• /
• 2003

Recently, there have been many attempts to develop BCI (brain computer interface) based on EEG (electroencephalogram). Measurement and analysis of EEG evoked by particular stimulation is important for the design of brain wave pattern and interface of BCI. The purpose of this study is to develop a general-purpose system that measures subject's reaction time after audio-visual stimulation which can work together with any other biosignal measurement systems. The entire system is divided into four modules, which are stimulation signal generation, reaction time measurement, evoked potential measurement and synchronization. Stimulation signal generation module was implemented by means of Flash. Measurement of the reaction time (the period between the answer request and the subject reaction) was achieved by self-made microcontroller system. EEG measurement was performed using the ready-made hardware and software without any modification. Synchronization of all modules was achieved by, first, the black-and-white signals on the stimulation screen synchronized with the problem presentation and the answer request, second, the photodetectors sensing the signals. The proposed method offers easy design of purpose-specific system only by adding simple modules (reaction time measurement, synchronization) to the ready-made stimulation and EEG system, and therefore, it is expected to accelerate the researches requiring the measurement of evoked response and reaction time.