• Journal of Information Technology Applications and Management
• /
• v.12 no.2
• /
• pp.15-27
• /
• 2005

Text categorization systems generally use single words (unigrams) as features. A deceptively simple algorithm for improving text categorization is investigated here, an idea previously shown not to work. It is to identify useful word pairs (bigrams) made up of adjacent unigrams. The bigrams it found, while small in numbers, can substantially raise the quality of feature sets. The algorithm was tested on two pre-classified datasets, Reuters-21578 for English and Korea-web for Korean. The results show that the algorithm was successful in extracting high quality bigrams and increased the quality of overall features. To find out the role of bigrams, we trained the Na$\"{i}$ve Bayes classifiers using both unigrams and bigrams as features. The results show that recall values were higher than those of unigrams alone. Break-even points and F1 values improved in most documents, especially when documents were classified along the large classes. In Reuters-21578 break-even points increased by 2.1%, with the highest at 18.8%, and F1 improved by 1.5%, with the highest at 3.2%. In Korea-web break-even points increased by 1.0%, with the highest at 4.5%, and F1 improved by 0.4%, with the highest at 4.2%. We can conclude that text classification using unigrams and bigrams together is more efficient than using only unigrams.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.823-833
• /
• 1996

An ultimate purpose of this study is to develop an automatic brown rice quality inspection system using image processing technique. In this study emphasis was put on developing an algorithm for discriminating the brown rice kernels depending on their external quality with a color image processing system equipped with an adaptor for magnifying the input image and optical fiber for oblique illumination. Primarily , geometrical and optical features of sample images were analyzed with unhulled paddy and various brown rice kernel samples such as sound, cracked, green-transparent , green-opaque, colored, white-opaque and brokens. Secondary, an algorithm for discrimination of the rice kernels in static state was developed on the basis of the geometrical and optical parameters screened by a statistical analysis(STEPWISE and DISCRIM Procedure, SAS ver.6). Brown rice samples could be discriminated by the algorithm developed in this study with an accuracy of 90% to 96% for the sound , cracked, colored, broken and unhulled , about 81% for the green-transparent and the white-opaque and about 75% for the green-opaque, respectively. A total computing time required for classification was about 100 seconds/1000 kernels with the PC 80486-DX2, 66MHz.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.1065-1071
• /
• 2023

In this paper discuss with research developing an LSTM model for classifying the behavior of occupants within a residence. The multi-sensor consists of an IAQ (Indoor Air Quality) sensor that measures indoor air quality, a UWB radar that tracks occupancy detection and location, and a Piezo sensor to measure occupants' biometric information, and collects occupant behavior data such as going out, staying, cooking, cleaning, exercise, and sleep by constructed an experimental environment similar to the actual residential environment. After the data with removed outliers and missing, the LSTM model is used to calculate accuracy, sensitivity, specificity of the occupant behavior classification model, T1 score.

• Food Science and Biotechnology
• /
• v.18 no.2
• /
• pp.307-311
• /
• 2009

This study examined variations in postmortem meat quality characteristics and consumer sensory evaluations of different pork quality classes in fresh and cooked meat. Pale, soft, and exudative (PSE) meat had the highest drip loss, lightness, and the lowest $pH_{24\;hr}$ whereas dark, firm, and dry (DFD) meat showed the opposite results. When the fresh meat was evaluated by consumer panelists, they could only distinguish the PSE class of meat and it scored lowest in overall acceptability. However, the panelists did not consider cooked PSE or DFD pork to be unacceptable overall, indicating that consumers cannot distinguish the quality of cooked pork.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.293-310
• /
• 2022

In this study, we analyzed the performance of the BERT-based document classification model by automatically classifying documents in the field of library and information science based on the KoBERT. For this purpose, abstract data of 5,357 papers in 7 journals in the field of library and information science were analyzed and evaluated for any difference in the performance of automatic classification according to the size of the learned data. As performance evaluation scales, precision, recall, and F scale were used. As a result of the evaluation, subject areas with large amounts of data and high quality showed a high level of performance with an F scale of 90% or more. On the other hand, if the data quality was low, the similarity with other subject areas was high, and there were few features that were clearly distinguished thematically, a meaningful high-level performance evaluation could not be derived. This study is expected to be used as basic data to suggest the possibility of using a pre-trained learning model to automatically classify the academic documents.

• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.1-8
• /
• 2009

With the development of IT convergence technology and the construction of master plan for the four rivers restoration of the government, the importance of the eco-friendly water pollution management is being spotlighted. In this paper, we proposed the effective water pollution management using the reservoir tank automatic classification for improving the water quality and on-line managing efforts of ceo-friendly reservoir tanks. The proposed method defined the seven factors of water pollution evaluation and managed the water pollution according to hydrogen ion concentration(pH), chemical oxygen demand(COD), suspend solid(SS), dissolved oxygen(DO), count of coliform group(MPN), total phosphorus(T-P), and total nitrogen(T-N) using the sensors. We measured the values for the seven factors from the reservoir tank and normalized to ranging from 1 to 9. To evaluate the performance of the water pollution management using the reservoir tank automatic classification, we conducted F-measure so as to verify usefulness. This evaluation found that the difference of satisfaction by the traditional system was statistically meaningful.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.87-95
• /
• 2002

In this paper, we proposed a fast multi-resolution motion estimation(MRME) algorithm. This algorithm exploits the half-pixel accuracy motion estimation(HPAME) for exact motion vectors in the baseband and block classification for the reduction of bit amounts and computational loads. Generally, as the motion vector in the baseband are used as initial motion vector in the high frequency subbands, it has crucial effect on quality of the motion compensated image. For this reason, we exploit HPAME in the motion estimation for the baseband. But HPAME requires additional bit and computational loads so that we use block classification for the selective motion estimation in the high frequency subbands to compensate these problems. In result, we could reduce the bit rate and computational load at the similar image quality with conventional MRME. The superiority of the proposed algorithm was confirmed by the computer simulation.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.7
• /
• pp.383-389
• /
• 2011

In this paper, we propose a improved speech absence probability estimation algorithm by applying environmental noise classification for speech enhancement. The previous speech absence probability required to seek a priori probability of speech absence was derived by applying microphone input signal and the noise signal based on the estimated value of a posteriori SNR threshold. In this paper, the proposed algorithm estimates the speech absence probability using noise classification algorithm which is based on Gaussian mixture model in order to apply the optimal parameter each noise types, unlike the conventional fixed threshold and smoothing parameter. Performance of the proposed enhancement algorithm is evaluated by ITU-T P.862 PESQ (perceptual evaluation of speech quality) and composite measure under various noise environments. It is verified that the proposed algorithm yields better results compared to the conventional speech absence probability estimation algorithm.

• Spatial Information Research
• /
• v.20 no.5
• /
• pp.25-35
• /
• 2012

This study compared the influence of water quality according to the data sources of spatial information. Firstly, land cover map was constructed through image classification of Daecheong-dam basin and the accuracy of image classification from satellite image showed high as 88.76% in comparison with the large-scaled land cover map in Ministry of Environment, to calculate Event Mean Concentration (EMC) by land cover that impact on the evaluation of nonpoint source pollutant loads. Also curve number and direct runoff were calculated by spatial overlay with soil map and land cover map from image classification. And Seokcheon and Daecheong-Dam basin showed high in the analysis of curve number and direct runoff. Samgacheon-Joint and Sokcheon-Downstream basin showed high in the nonpoint source pollutant loads of BOD from direct runoff and EMC. And Samgacheon-Joint and Bonghwangcheon- Downstream basin showed high in the nonpoint source pollutant loads of TN and TP. Nonpoint source pollutant loads from image classification were compared with those by the land cover map from Ministry of Environment to present the effectivity of nonpoint source pollutant loads from satellite image. And Daecheong-Dam Upstream basin showed high as 10.64%, 11.70% and 20.00% respectively in the errors of nonpoint source pollutant loads of BOD, TN, and TP. Therefore, it is desirable that spatial information including with paddy and dry field is applied to the evaluation of nonpoint source pollutant loads in order to simulate water quality of basin effectively.