• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.43-50
• /
• 2024

This paper evaluates the Korean sentiment analysis performance of large language models like GPT-3.5 and GPT-4 using a zero-shot approach facilitated by the ChatGPT API, comparing them to pre-trained Korean models such as KoBERT. Through experiments utilizing various Korean sentiment analysis datasets in fields like movies, gaming, and shopping, the efficiency of these models is validated. The results reveal that the LMKor-ELECTRA model displayed the highest performance based on F1-score, while GPT-4 particularly achieved high accuracy and F1-scores in movie and shopping datasets. This indicates that large language models can perform effectively in Korean sentiment analysis without prior training on specific datasets, suggesting their potential in zero-shot learning. However, relatively lower performance in some datasets highlights the limitations of the zero-shot based methodology. This study explores the feasibility of using large language models for Korean sentiment analysis, providing significant implications for future research in this area.

• Proceedings of the Korean Reliability Society Conference
• /
• 2011.06a
• /
• pp.305-309
• /
• 2011

Reliability evaluation of One-Shot systems which fly at speed of Mach must evaluate as the result which leads a many firing test. But many firing test the fact that is impossible is actuality with problem of budget. Method of prediction leads consequently with alternative and will be able to present the alternative which evaluates. Prediction of One-Shot systems that how many did accumulate a many experience data according to the accuracy is decided, there is a possibility of seeing. One like shot our country and the method which is indirect leads from the environment where the test data is insufficient and only will not be able to set the direction of prediction, the present paper about such method describes 217 Plus where is a reliability prediction standard which is new the thing in standard.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.967-980
• /
• 2007

Video objects of interest play an important role in representing the video content and are useful for improving the performance of video retrieval and compression. The objects of interest may be a main object in describing contents of a video shot or a core object that a video producer wants to represent in the video shot. We know that any object attracting one's eye much in the video shot may not be an object of interest and a non-moving object may be an object of interest as well as a moving one. However it is not easy to define an object of interest clearly, because procedural description of human interest is difficult. In this paper, a set of four filtering conditions for extracting moving objects of interest is suggested, which is defined by considering variation of location, size, and moving pattern of moving objects in a video shot. Non-moving objects of interest are also defined as another set of four extracting conditions that are related to saliency of color/texture, location, size, and occurrence frequency of static objects in a video shot. On a test with 50 video shots, the segmentation method based on the two sets of conditions could extract the moving and non-moving objects of interest chosen manually on accuracy of 84%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.5
• /
• pp.58-64
• /
• 2001

Recently many informations are transmitted ,md stored as video data, and they are on the rapid increase because of popularization of high performance computer and internet. In this paper, to retrieve video data, shots are found through analysis of video stream and the method of detection of key frame is studied. Finally users can retrieve the video efficiently. This Paper suggests a new feature that is robust to object movement in a shot and is not sensitive to change of color in boundary detection of shots, and proposes the characterizing value that reflects the characteristic of kind of video (movie, drama, news, music video etc,). The key frames are pulled out from many frames by using the local minima and maxima of differential of the value. After original frame(not de image) are reconstructed for key frame, indexing process is performed through computing parameters. Key frames that arc similar to user's query image arc retrieved through computing parameters. It is proved that the proposed methods are better than conventional method from experiments. The retrieval accuracy rate is so high in experiments.

• Korean Journal of Optics and Photonics
• /
• v.4 no.2
• /
• pp.226-232
• /
• 1993

A broadband CARS system is constructed for shot by shot measurement of a full CARS spectrum, which consists of a frequency doubled Nd:Yag laser, broadband mode-less laser and optical multi-channel analyzer installed in a double grating monochromator. To increase the accuracy of CARS temperature measurement and get better the fitting goodness, we have measured the slit function of the detection system and determined the analytical functional form of the slit function. Accuracy of the CARS system for temperature measurement is evaluated from the difference between the best-fit temperature of CARS spectrum and temperature of thermocouple reading. The uncertainty of the temperature measurement is found to be less than 1.5% in temperature range from 300 K to 1300 K.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.107-113
• /
• 2002

In this paper, we propose a method and a software system for automatic summarization of baseball game videos. The proposed system pursues fast execution and high accuracy of summarization. To satisfy the requirement, the detection of important events in baseball video is performed through DC-based shot boundary detection algorithm and simple caption recognition method. Furthermore, the proposed system supports a hierarchical description so that users can browse and navigate videos in several levels of summarization. In this paper, we propose a method and a software system for automatic summarization of baseball game videos. The proposed system pursues fast execution and high accuracy of summarization. To satisfy the requirement, the detection of important events in baseball video is performed through DC-based shot boundary detection algorithm and simple caption recognition method. Furthermore, the proposed system supports a hierarchical description so that users can browse and navigate videos in several levels of summarization.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.547-550
• /
• 2011

We measured that is Gantry, Collimator Star Shot, Light vs. Radiation, HDR QA with Medical LINAC Then, PACS was implemented on the digital images on the monitor that can be confirmed through the QA. Also, for cooperation with OCS system that is using from present source and impose code that need in treatment in each treatment, did so that Order that connect to network, input to CR may appear, did so that can solve support data mistake of Pinacle and PACS that is Planning System and look at Planning premier in PACS.

• Journal of Astronomy and Space Sciences
• /
• v.19 no.4
• /
• pp.385-394
• /
• 2002

Satellite laser ranging is a technique for precisely measuring the range between a laser station and a satellite that is equipped with retro-reflectors. SLR technique was first used for Beacon-B satellite in 1964 with the ranging accuracy of meter level. Now the single shot have centimeter level accuracy and the normal point have mm level in ranging. In this study we developed the algorithm for precise orbit determination using SLR data and performed the orbit determination of GPS-36 satellite using the algorithm. RMS of the estimated orbit was 74cm when compared with IGS precise orbit. It is known that RMS of SLR measurement residual is below 55mm. But we were able to achieve 44mm RMS of residual throughout this study.

• Journal of Broadcast Engineering
• /
• v.12 no.4
• /
• pp.311-320
• /
• 2007

In this paper, an efficient detection algorithm of an anchor shot in news video is presented. We observed the audio visual characteristics of news video and proposed several low level features which are appropriate for detecting an anchor shot in news video. The overall structure of the proposed algorithm is composed of 3 stages: the pause detection, the audio cluster classification, and the matching with motion activity stage. We used the audio features as well as the motion feature in order to improve the indexing accuracy and the simulation results show that the performance of the proposed algorithm is quite satisfactory.

• Geophysics and Geophysical Exploration
• /
• v.7 no.1
• /
• pp.7-13
• /
• 2004

In this paper, we demonstrate that Common Mid-Point (CMP) cross-correlation gathers of multi-channel and multi-shot surface waves give accurate phase-velocity curves, and enable us to reconstruct two-dimensional (2D) velocity structures with high resolution. Data acquisition for CMP cross-correlation analysis is similar to acquisition for a 2D seismic reflection survey. Data processing seems similar to Common Depth-Point (CDP) analysis of 2D seismic reflection survey data, but differs in that the cross-correlation of the original waveform is calculated before making CMP gathers. Data processing in CMP cross-correlation analysis consists of the following four steps: First, cross-correlations are calculated for every pair of traces in each shot gather. Second, correlation traces having a common mid-point are gathered, and those traces that have equal spacing are stacked in the time domain. The resultant cross-correlation gathers resemble shot gathers and are referred to as CMP cross-correlation gathers. Third, a multi-channel analysis is applied to the CMP cross-correlation gathers for calculating phase velocities of surface waves. Finally, a 2D S-wave velocity profile is reconstructed through non-linear least squares inversion. Analyses of waveform data from numerical modelling and field observations indicate that the new method could greatly improve the accuracy and resolution of subsurface S-velocity structure, compared with conventional surface-wave methods.