• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.261-282
• /
• 2024

This study proposed and evaluated electroencephalography (EEG)-based and eye-tracking-based methods to determine relevance by utilizing users' implicit relevance feedback while navigating content in a digital library. For this, EEG/eye-tracking experiments were conducted on 32 participants using video, image, and text data. To assess the usefulness of the proposed methods, deep learning-based artificial intelligence (AI) techniques were used as a competitive benchmark. The evaluation results showed that EEG component-based methods (av_P600 and f_P3b components) demonstrated high classification accuracy in selecting relevant videos and images (faces/emotions). In contrast, AI-based methods, specifically object recognition and natural language processing, showed high classification accuracy for selecting images (objects) and texts (newspaper articles). Finally, guidelines for implementing a digital library interface based on EEG, eye-tracking, and artificial intelligence technologies have been proposed. Specifically, a system model based on implicit relevance feedback has been presented. Moreover, to enhance classification accuracy, methods suitable for each media type have been suggested, including EEG-based, eye-tracking-based, and AI-based approaches.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.2
• /
• pp.147-156
• /
• 2024

The sustainable management and enhancement of marine resources are becoming increasingly important issues worldwide. This study was conducted in response to these challenges, focusing on the development and performance comparison of fish detection and classification models as part of a deep learning-based technique for assessing the effectiveness of marine resource enhancement projects initiated by the Korea Fisheries Resources Agency. The aim was to select the optimal model by training various sizes of YOLOv8-Seg models on a fish image dataset and comparing each performance metric. The dataset used for model construction consisted of 36,749 images and label files of 12 different species of fish, with data diversity enhanced through the application of augmentation techniques during training. When training and validating five different YOLOv8-Seg models under identical conditions, the medium-sized YOLOv8m-Seg model showed high learning efficiency and excellent detection and classification performance, with the shortest training time of 13 h and 12 min, an of 0.933, and an inference speed of 9.6 ms. Considering the balance between each performance metric, this was deemed the most efficient model for meeting real-time processing requirements. The use of such real-time fish detection and classification models could enable effective surveys of marine resource enhancement projects, suggesting the need for ongoing performance improvements and further research.

• Journal of Platform Technology
• /
• v.12 no.2
• /
• pp.34-44
• /
• 2024

This paper proposes a dynamic clock supply control algorithm and a system load power stabilization algorithm that minimizes the power consumption of the sensing system, which accounts for the largest percentage of power consumption in mobile devices, to extend the usage time of the rechargeable battery mounted on the mobile device. The dynamic clock supply control algorithm can reduce the power consumed by the sensing system by configuring a circuit to cut off the power of the sensing system and by recognizing the state of low sensor change and adjusting the measurement cycle. The system load power stabilization algorithm is an algorithm that controls the power of the surrounding module according to the power consumption state, and when it requires a lot of power, it controls the clock supply to stabilize the operation. The experimental results confirmed that applying only the dynamic clock supply control algorithm reduces the power consumed by the sensing system by 17%, and applying only the system load power stabilization algorithm reduces power consumption by 9.3%, enabling it to operate stably in situations that require a lot of power such as image processing. When both algorithms were applied, the power consumption of the battery was reduced by 67% compared to before applying the algorithm. Through this, the reliability of the proposed method was confirmed.

• Geophysics and Geophysical Exploration
• /
• v.8 no.4
• /
• pp.270-279
• /
• 2005

Under the research project supported by Japanese Ministry of Education, Culture, Sports, Science and Technology (MEXT), we have conducted the development of GPR systems for landmine detection. Until 2005, we have finished development of two prototype GPR systems, namely ALIS (Advanced Landmine Imaging System) and SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar). ALIS is a novel landmine detection sensor system combined with a metal detector and GPR. This is a hand-held equipment, which has a sensor position tracking system, and can visualize the sensor output in real time. In order to achieve the sensor tracking system, ALIS needs only one CCD camera attached on the sensor handle. The CCD image is superimposed with the GPR and metal detector signal, and the detection and identification of buried targets is quite easy and reliable. Field evaluation test of ALIS was conducted in December 2004 in Afghanistan, and we demonstrated that it can detect buried antipersonnel landmines, and can also discriminate metal fragments from landmines. SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar) is a machine mounted sensor system composed of B GPR and a metal detector. The GPR employs an array antenna for advanced signal processing for better subsurface imaging. SAR-GPR combined with synthetic aperture radar algorithm, can suppress clutter and can image buried objects in strongly inhomogeneous material. SAR-GPR is a stepped frequency radar system, whose RF component is a newly developed compact vector network analyzers. The size of the system is 30cm x 30cm x 30 cm, composed from six Vivaldi antennas and three vector network analyzers. The weight of the system is 17 kg, and it can be mounted on a robotic arm on a small unmanned vehicle. The field test of this system was carried out in March 2005 in Japan.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.19-29
• /
• 2006

As the security of personal information is becoming more important in mobile phones, we are starting to apply iris recognition technology to these devices. In conventional iris recognition, magnified iris images are required. For that, it has been necessary to use large magnified zoom & focus lens camera to capture images, but due to the requirement about low size and cost of mobile phones, the zoom & focus lens are difficult to be used. However, with rapid developments and multimedia convergence trends in mobile phones, more and more companies have built mega-pixel cameras into their mobile phones. These devices make it possible to capture a magnified iris image without zoom & focus lens. Although facial images are captured far away from the user using a mega-pixel camera, the captured iris region possesses sufficient pixel information for iris recognition. However, in this case, the eye region should be detected for accurate iris recognition in facial images. So, we propose a new fast iris detection method, which is appropriate for mobile phones based on corneal specular reflection. To detect specular reflection robustly, we propose the theoretical background of estimating the size and brightness of specular reflection based on eye, camera and illuminator models. In addition, we use the successive On/Off scheme of the illuminator to detect the optical/motion blurring and sunlight effect on input image. Experimental results show that total processing time(detecting iris region) is on average 65ms on a Samsung SCH-S2300 (with 150MHz ARM 9 CPU) mobile phone. The rate of correct iris detection is 99% (about indoor images) and 98.5% (about outdoor images).

• Journal of Korean Home Economics Education Association
• /
• v.23 no.4
• /
• pp.105-124
• /
• 2011

To achieve this objective, practical problem-teaching lesson plans and instructor-led teaching and learning plans were developed and integrated into the Technology Home Economics, and Human Development curricula at both academic and vocational high schools. The impact of these plans was examined, as were connections between the teaching methods and types of schools. As part of this study, a survey was conducted on 1,263 students in 46 classes at 6 randomly selected high schools: 4 academic and 2 vocational. A total of 9 teachers conducted classes for both experimental and comparative groups between October 2009 and November 2010. Pre- and post-tests were used to study the impact of the lessons on the experimental and comparative groups. In terms of data analysis and statistics processing, this study implemented mean and standard deviations, t-test, and analysis of covariance using the SPSS 12.0 program. The results of this study are as follows. The practical problem-teaching lessons produced more positive results in the students than the instructor-led lessons, in terms of their image of the elderly, their level of knowledge about them, their understanding of their need for welfare services, and preparation for Successful aging. When comparing the results by type of school, the experimental groups at academic high schools appeared to have a more positive image and better understanding of the elderly and their need for welfare services, and were better prepared for Successful aging than during their previous lessons. They also showed an increase in independence from their children in aging. As for the comparative groups, students at academic high schools showed an increase in preparation for Successful aging compared to the previous lessons. Finally, as for future research on preparation for aging in high schools, more schools should include this subject in their regular curriculum for Technology Home Economics, Human Development and Home Economics in order to generalize the results, and they need to evaluate the content. Additionally, this study suggests that new high school curricula should include lessons on preparation for aging so that students can deal successfully with our aging society.

• Journal of Bio-Environment Control
• /
• v.27 no.1
• /
• pp.34-39
• /
• 2018

This research was conducted to estimate moisture content in cucurbitaceae seedlings, such as cucumber and watermelon, using hyperspectral imagery. Using a hyperspectral image acquisition system, the reflectance of leaf area of cucumber and watermelon seedlings was calculated after providing water stress. Then, moisture content in each seedling was measured by using a dry oven. Finally, using reflectance and moisture content, the moisture content estimation models were developed by PLSR analysis. After developing the estimation models, performance of the cucumber showed 0.73 of $R^2$, 1.45% of RMSE, and 1.58% of RE. Performance of the watermelon showed 0.66 of $R^2$, 1.06% of RMSE, and 1.14% of RE. The model performed slightly better after removing one sample from cucumber seedlings as outlier and unnecessary. Hence, the performance of new model for cucumber seedlings showed 0.79 of $R^2$, 1.10% of RMSE, and 1.20% of RE. The model performance combined with all samples showed 0.67 of $R^2$, 1.26% of RMSE, and 1.36% of RE. The model of cucumber showed better performance than the model of watermelon. This is because variables of cucumber are consisted of widely distributed variation, and it affected the performance. Further, accuracy and precision of the cucumber model were increased when an insignificant sample was eliminated from the dataset. Finally, it is considered that both models can be significantly used to estimate moisture content, as gradients of trend line are almost same and intersected. It is considered that the accuracy and precision of the estimating models possibly can be improved, if the models are constructed by using variables with widely distributed variation. The improved models will be utilized as the basis for developing low-priced sensors.

• Journal of the Korean Society of Radiology
• /
• v.3 no.2
• /
• pp.27-31
• /
• 2009

Now a days, the Medical X-ray equipments has become digitalized from analog type such as film, cassette to CR, DR. And many scientists are still researching and developing the Medical X-ray equipment. In this study, we used the Bismuth tri-iodide to conversion material for digital X-ray equipments and we couldn't get the satisfying result than previous study, but it opened new possibility to cover the disadvantage of a-Se is high voltage aplly and difficultness of make. In this paper, we use $BiI_3$ powder(99.99%) as x-ray conversion material and make films that have thickness of 200um and the film size is $3cm{\times}3cm$. Also, we deposited an ITO(Indium Tin Oxide) electrode as top electrode and bottom electrode using a Magnetron Sputtering System. To evaluate a characteristics of the produced films, an electrical and structural properties are performed. Through a SEM analysis, we confirmed a surface and component part. And to analyze the electrical properties, darkcurrent, sensitivity and SNR(Signal to Noise Ratio) are measured. Darkcurrent is $1.6nA/cm^2$ and sensitivity is $0.629nC/cm^2$ and this study shows that the electrical properties of x-ray conversion material that made by screen printing method are similar to PVD method or better than that. This results suggest that $BiI_3$ is suitable for a replacement of a-Se because of the reduced manufacture processing and improved yield.

• Archives of design research
• /
• v.18 no.1 s.59
• /
• pp.39-48
• /
• 2005

In the age of digital culture, TV broadcasting is exercising more influence as a information and communication medium compared to past. With the appearance of satellite broadcasting service in 2002, the broadcasting environment became a diversified field of local TV, cable TV, satellite, internet, etc. and created the time of multi-media and multi-channel. This ongoing change of broadcasting environment made the passive audience of the past, active image makers and new accepters, participants and users of communications, who know how to choose and use media as the active centerpiece, The active acceptor as the centerpiece of channel selections has become the center of the broadcasting, whereby they pick up and enjoy their favorite TV programs and came to remember the list of their favorite channels and zap them finally. In this point of spotting their favorite channels and improving the degree of recognition for the channels, the development of the noticeable brand for a particular program has made a great contribution. The aim of this study, therefore, is to recognize the factors, which are important in the habits of watching TV and to develop professional brands for TV broadcasting programs. The range of the survey for this study was home news programs and broadcasting stations abroad, which were on air from March to May in 2004. The focus of the survey was universal and professional news programs. Through this study, it was ascertained that, in the case of news, developing a brand for an anchor as well as for a professional brand of TV program could be an important element.

• The Journal of Korean Society for Radiation Therapy
• /
• v.24 no.2
• /
• pp.77-84
• /
• 2012

Purpose: To develop a geometrical quality control real-time analysis program using an electronic portal imaging to replace film evaluation method. Materials and Methods: A geometrical quality control item was established with the Eclipse treatment planning system (Version 8.1, Varian, USA) after the Electronic Portal Imaging Device (EPID) took care of the problems occurring from the fixed substructure of the linear accelerator (CL-iX, Varian, USA). Electronic portal image (single exposure before plan) was created at the treatment room's 4DTC (Version 10.2, Varian, USA) and a beam was irradiated in accordance with each item. The gaining the entire electronic portal imaging at the Off-line review and was evaluated by a self-developed geometrical quality control real-time analysis program. As for evaluation methods, the intra-fraction error was analyzed by executing 5 times in a row under identical conditions and procedures on the same day, and in order to confirm the infer-fraction error, it was executed for 10 days under identical conditions of all procedures and was compared with the film evaluation method using an Iso-align$^{TM}$ quality control device. Measurement and analysis time was measured by sorting the time into from the device setup to data achievement and the time amount after the time until the completion of analysis and the convenience of the users and execution processes were compared. Results: The intra-fraction error values for each average 0.1, 0.2, 0.3, 0.2 mm at light-radiation field coincidence, collimator rotation axis, couch rotation axis and gantry rotation axis. By checking the infer-fraction error through 10 days of continuous quality control, the error values obtained were average 1.7, 1.4, 0.7, 1.1 mm for each item. Also, the measurement times were average 36 minutes, 15 minutes for the film evaluation method and electronic portal imaging system, and the analysis times were average 30 minutes, 22 minutes. Conclusion: When conducting a geometrical quality control using an electronic portal imaging, it was found that it is efficient as a quality control tool. It not only reduces costs through not using films, but also reduces the measurement and analysis time which enhances user convenience and can improve the execution process by leaving out film developing procedures etc. Also, images done with evaluation from the self-developed geometrical quality control real-time analysis program, data processing is capable which supports the storage of information.