• 한국정보처리학회논문지
• /
• 제7권9호
• /
• pp.2867-2875
• /
• 2000

본 논문은 인터넷 문서 자동 분류 시스템의 구현에 대하여 논한다. 문서 자동분류 알고리즘을 설정하고, 역전파 학습 모델을 이용하여 문서의 범주화를 수행하는 시스템을 구축한다. 문서학습을 위해서 범주별 인터넷 문서들을 수집하고 수집한 문서에 대하여 카이제곱($\chi^2$)검정을 수행함으로써 범주화 자질을 추출한다. 이 범주화 자질을 바탕으로 하여 학습 및 분류 벡터 집합을 생성한다. 실험 결과의 평가로부터 본 논문에서 구현한 시스템이 유사도 계산을 이용한 문서의 분류 시스템보다 성능이 향상된 것을 알 수 있었다.

• Journal of Biosystems Engineering
• /
• 제18권4호
• /
• pp.371-381
• /
• 1993

Threshing operation is performed by impact, compression and friction forces inside the thresher. These values should be appropriate to the crop condition to enhance the threshing and separating efficiency and to decrease the grain damage. To analyze the threshing process inside the rasp-bar type thresher, impact, friction and compression forces were measured using transducers with strain gage circuits. To measure the impact forces and friction forces between the rasp-bar and crop, full bridge strain gage circuit was built on the rasp-bar holder. To measure the compression forces and circumferential friction forces between the concave and crop, two sets of full bridge strain gage circuits were built on the T-type concave transducer. Threshing work of wheat crop with 12% of moisture content was performed at 3 levels of compression ratio and with 3 replications. Each transducer could not measure the exact forces continuously because the transducer oscillates with the forces. However they could measure maximum forces and force distribution according to the time. Average friction coefficients between crop and concave was 0.61 not showing any significant difference according to the compression ratio. Average acceleration of the crop in the cylinder appeared from $70.6m/s^2$ to $140.8m/s^2$ according to the compression ratio. The velocity of the crop at the exit of the cylinder appeared from 10.7m/s to 15.0m/s according to the compression ratio.

• 한국습지학회지
• /
• 제4권2호
• /
• pp.23-41
• /
• 2002

In this paper, changes of the coliform bacteria were investigated when aquatic plant pond was used for separating algal particles from waste stabilization ponds(WSPs). Three different types of integrated natural systems were operated. It was found that there were no significant interferences for the disinfection efficiency of two integrated systems (WSPs coupled with water hyacinth ponds) used for treating domestic sewage and upgrading the secondary effluent as well. However, when constructed wetland (CW) was combined with the shallow algal ponds and used for the secondary effluent, it seriously interfered with the disinfection efficiency due to the regrowth and/or after-growth of the coliform bacteria, which can readily metabolize the amino acids and sugars leached from plants. In order to find out the primary disinfection parameters, several sets of the batch test were run. It was found that sunlight is the most predominant factor for the coliform decay. During the night, algal toxicity partly supports the decay but during the day, deteriorates it by attenuating the sunlight. The pH in the range of 4 to 10 did not affect the decay in the dark.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.294-300
• /
• 2021

The current society relies upon social media on an everyday basis, which contributes to finding which of the following supervised machine learning algorithms used in sentiment analysis have higher accuracy in detecting Malay internet slang and short forms which can be offensive to a person. This paper is to determine which of the algorithms chosen in supervised machine learning with higher accuracy in detecting internet slang and short forms. To analyze the results of the supervised machine learning classifiers, we have chosen two types of datasets, one is political topic-based, and another same set but is mixed with 50 tweets per targeted keyword. The datasets are then manually labelled positive and negative, before separating the 275 tweets into training and testing sets. Naïve Bayes and Random Forest classifiers are then analyzed and evaluated from their performances. Our experiment results show that Random Forest is a better classifier compared to Naïve Bayes.

• 방송공학회논문지
• /
• 제22권5호
• /
• pp.632-642
• /
• 2017

본 논문에서는 미디어 오디오의 음향 특성 및 문맥 정보를 활용한 DNN 기반 음성 검출 시스템을 제안한다. 미디어 오디오 내에 포함되어 있는 음성과 비음성을 구분하기 위한 음성 검출 기법은 효과적인 음성 처리를 위해 필수적인 전처리 기술이지만 미디어 오디오 신호에는 다양한 형태의 음원이 복합적으로 포함되어 있으므로 기존의 신호처리 기법으로는 높은 성능을 얻기에는 어려움이 있었다. 제안하는 기술은 미디어 오디오의 고조파와 퍼커시브 성분을 분리하고, 오디오 콘텐츠에 포함된 문맥 정보를 반영하여 DNN 입력 벡터를 구성함으로써 음성 검출 성능을 개선할 수 있다. 제안하는 시스템의 성능을 검증하기 위하여 20시간 이상 분량의 드라마를 활용하여 음성 검출용 데이터 세트를 제작하였으며 범용으로 공개된 8시간 분량의 헐리우드 영화 데이터 세트를 추가로 확보하여 실험에 활용하였다. 실험에서는 두 데이터 세트에 대한 교차 검증을 통하여 제안하는 시스템이 기존 방법에 비해 우수한 성능을 보임을 확인하였다.

• 응용통계연구
• /
• 제18권2호
• /
• pp.421-434
• /
• 2005

기계학습은 패턴분류의 한 도구로써 광범위하게 연구되고 있다. 기계학습 방법들 중에서 서포트 벡터 기계(Support Vector Machines)는 많은 분야에서 연구되어지는 것으로 이진 패턴 분류문제에서 고차원의 특징공간에서 두 집합들 사이에 가장 큰 분리를 제공하는 최대 여유도(margin)를 가지는 분리 초평면을 찾는 것이다. 최대 여유도의 분리의 개념에 기초하여 Mangasarian(1968)은 다중-표면 방법(multi-surface method)을 제안하였고, 1980년대에 목적 계획법을 이용한 방법들이 광범위하게 개발되었다. 본 논문에서는 다목적 계획법과 목적 계획법을 이용한 수리계획법인 서포트 벡터 기계의 두가지 방법들을 제안하고 수치 예제들을 통하여 효용성에 대하여 논의하고자 한다.

• Parasites, Hosts and Diseases
• /
• 제47권4호
• /
• pp.353-357
• /
• 2009

Cryptosporidium can cause gastrointestinal diseases worldwide, consequently posing public health problems and economic burden. Effective techniques for detecting contaminated oocysts in water are important to prevent and control the contamination. Immunomagnetic separation (IMS) method has been widely employed recently due to its efficiency, but, it is costly. Sucrose floatation technique is generally used for separating organisms by using their different specific gravity. It is effective and cheap but time consuming as well as requiring highly skilled personnel. Water turbidity and parasite load in water sample are additional factors affecting to the recovery rate of those 2 methods. We compared the efficiency of IMS and sucrose floatation methods to recover the spiked Cryptosporidium oocysts in various turbidity water samples. Cryptosporidium oocysts concentration at 1, $10^1$, $10^2$, and $10^3$ per $10{\mu}l$ were spiked into 3 sets of 10 ml-water turbidity (5, 50, and 500 NTU). The recovery rate of the 2 methods was not different. Oocyst load at the concentration < $10^2$ per 10 ml yielded unreliable results. Water turbidity at 500 NTU decreased the recovery rate of both techniques. The combination of sucrose floatation and immunofluorescense assay techniques (SF-FA) showed higher recovery rate than IMS and immunofluorescense assay (IMS-FA). We used this SF-FA to detect Cryptosporidium and Giardia from the river water samples and found 9 and 19 out of 30 (30% and 63.3%) positive, respectively. Our results favored sucrose floatation technique enhanced with immunofluorescense assay for detecting contaminated protozoa in water samples in general laboratories and in the real practical setting.

• 자원환경지질
• /
• 제26권2호
• /
• pp.227-237
• /
• 1993

Lineaments in the Kyungsang basin most intensely develop in the East coast domain including the Yangsan fault, which dominantly run in NNE direction. The geometry of small fault population near or along the Yangsan fault represents the dominant strikes of N35E, high angle dips and shallowly plunging rakes with dextral movement sense. Stereographic solution on the Yangsan fault geometry gives the dip of 88SE, the slip direction of 17,024 and the slip rake of 18, which were determined from the strike (N23E) of the fault measured on map, and the average attitude (N35E, 84SE) and fault striation (16, 037) of small fault population considered as Riedel shears. It is judged from the geometry of small fault population to the main Yangsan fault and dragging features of bedding attitude near the fault that the Yangsan fault was produced from dextrally strike-slip movement. The movement of the Yangsan and the adjacent parallel faults is thought to be taken place much later than the other fault sets in the Kyungsang basin. It might occur during the geologic age from Eocence to early Miocene according to the consideration of K-Ar ages of the igneous rocks near the fault. The estimated paleostress state indicates ENE shortening and NNW extension. The displacement of the Yangsan fault in the study area is not constant along the fault but decreases from the south to the north. Taking the northern end of the study area as a separating point the whole extension of the Yangsan fault may be divided into southern and northern segments.

• Journal of Animal Science and Technology
• /
• 제63권4호
• /
• pp.740-750
• /
• 2021

This study was performed to investigate genetic relationship of age at first calving (AFC) with body development and reproduction capacity in female Hanwoo. The data sets of 52,299 reproduction records of 19,566 heads calved from 2011 to 2019 and conformation records of 19565 heads born from 1997 to 2017 were analyzed by separating them based on age at first calving. In the analysis, conformation traits included the body condition score (BCS), height (HT), body width (BW), hip bone length (HL), hip bone width (HW), and final score (FS). The heritability and genetic correlation of AFC with conformation traits and calving interval (CI) were analyzed. The heritability for AFC was 0.716, 0.087, and 0.097 for the before and after 24 months and combined data, respectively. The genetic correlation of AFC before 24 months with BCS was -0.778, -0.600 with BW, and 0.442 with HT. The genetic correlation of AFC after 24 months with HT was -0.826, -0.706 with BW, -0.623 with HL, -0.456 with HW, and -0.675 with FS. When the first calving age of young heifers approached 24 months, BCS and BW decreased, and HT increased. When first calving is delayed to after 24 months, the conformation traits become smaller, which indicates that conformation to some extent affects the delay in AFC. The genetic correlation between CI and AFC was -0.116, 0.307, and 0.250 for the before and after 24 month of AFC and combined data, respectively. When first calving date approached 24 months, CI was reduced. The obtained results suggest that it is important that first calving occurs at an appropriate age. Additional research is needed to perform proper genetic evaluation of first calving age in Hanwoo cattle in Korea.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.