• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.199-206
• /
• 2023

This study utilizes deep learning algorithms to automatically classify construction waste into three categories: wood waste, plastic waste, and concrete waste. Two models, VGG-16 and ViT (Vision Transformer), which are convolutional neural network image classification algorithms and NLP-based models that sequence images, respectively, were compared for their performance in classifying construction waste. Image data for construction waste was collected by crawling images from search engines worldwide, and 3,000 images, with 1,000 images for each category, were obtained by excluding images that were difficult to distinguish with the naked eye or that were duplicated and would interfere with the experiment. In addition, to improve the accuracy of the models, data augmentation was performed during training with a total of 30,000 images. Despite the unstructured nature of the collected image data, the experimental results showed that VGG-16 achieved an accuracy of 91.5%, and ViT achieved an accuracy of 92.7%. This seems to suggest the possibility of practical application in actual construction waste data management work. If object detection techniques or semantic segmentation techniques are utilized based on this study, more precise classification will be possible even within a single image, resulting in more accurate waste classification

• Journal of Broadcast Engineering
• /
• v.10 no.4 s.29
• /
• pp.599-609
• /
• 2005

There are many test parameters in the DTV measurement, which uses several test measuring instruments and miscellaneous devices. To operate all of those devices and analyse test results is a tedious and time-consuming process with a high error rate committed by inexperienced test crews. In this paper, we propose an integrated DTV measurement and analysis system(IMAS) that remotely controls and manages any instruments with standard network interface. This system can take, organize, store the field data into an integrated database and easily produce systematic output according to user-defined form. It can also measure several types of digital broadcasting signals such as DTV, DMB, DAB with generalized measurement procedures. Proposed measurement system was applied in the DTV field test by KBS and proved that it could enhance the accuracy and efficiency of entire test sequences and also dramatically reduce measurement time compared to conventional measurement systems.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.529-539
• /
• 2012

Testing is an important part of quality control in the software life cycle. One of the most important issues in the software testing is to generate the appropriate test cases. Generally, the software can be tested based on product understanding. However, it is not easy to create test cases that can ensure the quality of the software according to the clients' request. Especially, it is difficult to create test cases for abnormal or exceptional situations. In this paper, we present a novel approach to generate exceptional test cases at the design level of UML model. Furthermore, we describe the results of actual experiment where DAB(Digital Audio Broadcasting) parsing program is tested with previous method and also with the proposed method. The results implies that our proposed method of generating test cases for exceptional situations detect more faults than that of previous method by 7.08%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.269-274
• /
• 2004

In this paper, proposed is the dual-mode algorithm of blind decision feedback equalizer (DFE) for digital terrestrial television signals. According to channel impairments, the proposed dual-mode algorithm for blind DFE operates in decision-directed mode or in blind mode of operation. The error signals being used in tap update of the equalizer are generated in the best mode of operations, so that the confidence of equalizer tap coefficient update is more accurate. As a result, it is possible to track the channel characteristics variations by automatic switching over between two modes of operations. For 8-level vestigial sideband modulated digital television signals, the mean square errors and symbol error rates of the proposed algorithm are compared with those of conventional methods. And the usability of the proposed scheme is assessed by computer simulations under various static and dynamic multipath channel environments.

• International journal of advanced smart convergence
• /
• v.5 no.3
• /
• pp.66-71
• /
• 2016

Smart building gate security control system using smartphone integrated with near field communication (NFC) has become part of daily life usage these days. The technology change in replacing RF NFC device using visible light communication technology based approach growing faster in recent days. This paper propose a design and development of gate security control system using color code based user authentication ID generation as part of an intelligent access control system to control automatic door open and close. In this approach gate security access control use the recent visible light communication technology trends to transfer the user specific authentication code to door access control system using color code on smartphone screen. Using a camera in the door access control system (ACS), color codes on smartphone screens are detected and matched to the database of authenticated user to open the door automatically in gate security system. We measure the visual light communication technology efficiency as a part of the research and the experiments have revealed that more than 95% users authenticated correctly at the suggested experiment environment on gate security control system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.631-636
• /
• 2010

With the growing trends of communication- broadcasting convergence, a hybrid IPTV that supports both IP network-based on-demand media and terrestrial or cable-based broadcast media is gaining attraction. This paper proposes a rich media framework for hybrid IPTV with support of the latest H.264 codec. For this purpose, we design and implement a media component and a RIA run-time engine customized for TV with the hybrid media. The media component has been designed to provide a uniform and efficient application interface to the various playback methods for RF broadcast and IP-based stored or live media. For performance and portability, it exploits media stream abstraction, adaptive on-demand I-frame search, and automatic calculation of play duration. Based on the proposed media interface, we develop a RIA run-time prototype. It has been carefully designed to fully utilize the built-in graphic acceleration hardware for optimized rendering in the resource-constrained IPTV environments. Demonstration and experiment results validate the performance and usefulness of the developed framework. The framework is expected to be used effectively to support graphics and hybrid media in the applications of IPTV-based VOD, advertisement, and education.

• Journal of Korea Game Society
• /
• v.10 no.1
• /
• pp.135-146
• /
• 2010

The development of image technologies in such area as broadcasting and movies has recently increased our attention to 3D stereoscopic images. In addition, the development of stereoscopic image representation technologies in 3D contents becomes more active over time due to the representational limitations of 2D images. Without limitation to the above-mentioned area, stereoscopic image technologies have been developed and studied so that they can be widely accessed in diverse areas including medical services and education. Due to the refined production, however, required to represent a three dimensional effects and the fatigue caused by the perception of a three dimensional effects, the stereoscopic image technologies are not combined into real time systems such as games where environments change unforeseeably. In this study we design a technique to adjust the depth scaling that will enable efficient management of a three dimensional effects and to relieve fatigue through automatic view point interval adjustment in accordance with situations based on the geometrical structure of the DirectX SDK graphic pipeline. Through this, we would like to suggest a new alternative idea to activate the production of games combined with stereoscopic image technologies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4B
• /
• pp.391-398
• /
• 2011

In this paper, we propose a MAC protocol for visible light wireless LAN using LED light. The proposed MAC protocol has a function of automatic direction optimization for LED transceiver. There is periodical time slot for broadcasting and registration in the proposed MAC protocol. We used polling method for data transfer in the protocol since visible light is hard to detect carrier and collision by other mobile stations; thus we cannot use CSMA/CD method in visible light LAN. We also amended the MAC frame of IEEE 802.11 to propose a revised version for visible light wireless LAN using LED light. We investigate the performance of the proposed MAC protocol. When the bit rate of physical layer is 100 Mb/s, the net data throughput using the proposed MAC protocol is estimated to 94.386 Mb/s.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.75-84
• /
• 2018

In this study, the researchers attempted to automate the process of painting the characters on the road surface, which is currently done by manual labor, by using the information and communication technology. Here are the descriptions of how we put in our efforts to achieve such a goal. First, we familiarized ourselves with the current regulations about painting letters or characters on the road, with reference to Road Mark Installation Management Manual of the National Police Agency. Regarding the graphemes, we adopted a new one using connection components, in Gothic print characters which was within the range of acceptance according to the aforementioned manual. We also made it possible for the automated program to recognize the graphemes by means of the feature dots of the isolated dots, end dots, 2-line gathering dots, and gathering dots of 3 lines or more. Regarding the database, we built graphemes database for plotting information, classified the characters by means of the arrangement information of the graphemes and the layers that the graphemes form within the characters, and last but not least, made the character shape information database for character plotting by using such data. We measured the layers and the arrangement information of the graphemes consisting the characters by using the information of: 1) the information of the position of the center of gravity, and 2) the information of the graphemes that was acquired through vertical exploration from the center of gravity in each grapheme. We identified and compared the group to which each character of the database belonged, and recognized the characters through the use of the information gathered using this method. We analyzed the input characters using the aforementioned analysis method and database, and then converted into plotting information. It was shown that the plotting was performed after the correction.

• Journal of Broadcast Engineering
• /
• v.11 no.2 s.31
• /
• pp.207-221
• /
• 2006

A fully automatic and computationally efficient method is proposed for intelligent display of soccer video on small multimedia mobile devices. The rapid progress of the multimedia signal processing has contributed to the extensive use of multimedia devices with a small LCD panel. With these emerging small mobile devices, the video sequences captured for standard- or HDTV broadcasting may give the small-display-viewers uncomfortable experiences in understanding what is happening in a scene. For instance, in a soccer video sequence taken by a long-shot camera technique, the tiny objects (e.g., soccer ball and players) may not be clearly viewed on the small LCD panel. Thus, an intelligent display technique is needed for small-display-viewers. To this end, one of the key technologies is to determine region of interest (ROI), which is a part of the scene that viewers pay more attention to than other regions. In this paper, the focus is on soccer video display for mobile devices. Instead of taking visual saliency into account, we take domain-specific approach to exploit the characteristics of the soccer video. The proposed scheme includes three modules; ground color learning, shot classification, and ROI determination. The experimental results show the propose scheme is capable of intelligent video display on mobile devices.