• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.593-601
• /
• 2022

We call "fruad" the cases that are not frequently occurring but cause significant losses. Fraud detection is commonly encountered in various applications, including wafer production in the semiconductor industry. It is not trivial to directly extend the standard binary classification methods to the fraud detection context because the misclassification cost is much higher than the normal class. In this article, we propose the functional fraud detection support vector machine (F²DSVM) that extends the fraud detection support vector machine (FDSVM) to handle functional covariates. The proposed method seeks a classifier for a function predictor that achieves optimal performance while achieving the desired sensitivity level. F²DSVM, like the conventional SVM, has piece-wise linear solution paths, allowing us to develop an efficient algorithm to recover entire solution paths, resulting in significantly improved computational efficiency. Finally, we apply the proposed F²DSVM to the defective wafer detection problem and assess its potential applicability.

• Journal of Power Electronics
• /
• v.19 no.1
• /
• pp.168-178
• /
• 2019

Discrete space vector modulation (DSVM) is an effective method to improve the steady-state performance of the finite control set predictive control for permanent magnet synchronous motor drive systems. However, it requires complex computations due to the presence of numerous virtual voltage vectors. This paper proposes an improved finite control set model-free predictive control using DSVM to reduce the computational burden. First, model-free deadbeat current control is used to generate the reference voltage vector. Then, based on the principle that the voltage vector closest to the reference voltage vector minimizes the cost function, the optimal voltage vector is obtained in an effective way which avoids evaluation of the cost function. Additionally, in order to implement double-objective control, a two-level decisional cost function is designed to sequentially reduce the stator currents tracking error and the inverter switching frequency. The effectiveness of the proposed control is validated based on experimental tests.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.82-82
• /
• 2023

홍수기 하천에서 유량측정은 예산, 인력, 안전 및 측정 시 편의성 등의 이유로 측정에 제한이 많다. 특히, 태풍 등으로 인한 호우사상 발생 시 위와 같은 문제로 홍수량 측정에 어려움이 따른다. 이러한 문제점을 개선하기 위해 Lee et al.(2021)은 드론과 전자파표면유속계의 기능을 융합한 DSVM(Dron and Surface Veloctity Meter using doppler radar) 측정방법을 개발하였다. 전자파표면유속계 측정의 제한 요소인 진동을 감소시키기 위해 댐퍼플레이트를 개발하였고 금강의 지류인 봉황천에 현장 적용을 통해 DSVM 측정방법의 실용성을 확인하였다. 기존 연구에서 DSVM 방법은 드론의 각 측선 이동을 위한 조종과 전자파표면유속계 측정의 제어를 측정자가 수행하였는데 본 연구에서는 통합 드론측정시스템(IDMS, Integrated Drone Measurement System) 개발을 통해 측정자의 조종 의존도를 줄임과 동시에 안전하고 정확한 유량측정을 위해 노력하였다. 기존 댐퍼플레이트의 상하 진동 흡수 기능뿐만 아니라 전자파표면유속계의 흔들림 현상 등 자세 제어 기능을 보완하기 3축 모터를 적용한 방수짐벌을 개발하여 측정 정확도를 향상시켰다. 미션컴퓨터 개발로 측정지점의 측정 임무정보를 DB화하여 각 측선별 헤딩, 고도, 이동 등 자동항법 기능과 기체의 안정화 이후 전자파표면유속계를 자동으로 제어하여 측정을 실시하는 기능을 구현하였다. 또한 통합 GCS(Ground Control System)를 통해 비행 및 측정에 대한 모든 정보를 확인하고 컨트롤 할 수 있게 하였다. 2022년 금산군(제원대교), 무주군(취수장), 경주시(서천교) 지점에서 홍수기 유량측정에 도입하여 중간단면적법, 지표유속법을 적용하여 통합드론측정시스템의 실용성을 검증 완료하였다. 2023년 현장에 18대의 통합 드론측정시스템을 도입하여 홍수기 유량측정에 활용할 계획이다.

• Journal of Korea Water Resources Association
• /
• v.54 no.11
• /
• pp.903-913
• /
• 2021

In the flood season, the measurement of the river discharge has many restrictions due to reasons such as budget, manpower, safety, convenience in measurement and so on. In particular, when heavy rain events occur due to typhoons, etc., it is difficult to measure the amount of flood due to the above problems. In order to improve this problem, in this study, a method was developed that can measure the river discharge in a flood season simply and safely in a short time with minimal manpower by combining the functions of a drone and a surface velocity doppler radar. To overcome the mechanical limitations of drones caused by weather issues such as wind and rainfall derived from the measurement of the river discharge using the conventional drone, we developed a drone with P56 grade dustproof and waterproof performance, stable flight capability at a wind speed of up to 36 km/h, and a payload weight of up to 10 kg. Further, to eliminate vibration which is the most important constraint factor in the measurement with a surface velocity doppler radar, a damper plate was developed as a device that combines a drone and a surface velocity Doppler radar. The velocity meter DSVM (Dron and Surface Veloctity Meter using doppler radar) that combines the flight equipment with the velocity meter was produced. The error of ±3.5% occurred as a result of measuring the river discharge using DSVM at the point of Geumsan-gun (Hwangpunggyo) located at Bonghwang stream (the first tributary stream of the Geum River). In addition, when calculating the mean velocity from the measured surface velocity, the measurement was performed using ADCP simultaneously to improve accuracy, and the mean velocity conversion factor (0.92) was calculated by comparing the mean velocity. In this study, the discharge measured by combining a drone and a surface velocity meter was compared with the discharge measured using ADCP and floats, so that the application and utility of DSVM was confirmed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.90-90
• /
• 2022

전자파표면유속계를 이용한 유량측정은 전자파를 발사한 후 수표면에 반사되는 전자파의 도플러효과를 이용하여 표면유속을 측정하는 방법이다. 국제적으로 1980년대부터 홍수유량측정의 어려움을 극복하고자 전자파표면유속계를 개발하여 하천 유량측정 업무에 활용하였다. 미국의 경우U.S. Geological Survey (USGS)에서 교량, 케이블웨이, 제방, 헬리콥터, 비행기 등 전자파표면유속계의 측정 위치에 따라 주파수 범위를 달리하며 유속을 측정하는 연구가 진행되었다. 국내의 경우 Lee et al.(2021)은 드론을 이용한 전자파표면유속계 측정을 위해 드론으로부터 전자파표면유속계로 전달되는 진동을 제거하고 전자파표면유속계의 흔들림 방지를 위한 댐퍼플레이트를 개발하여 드론과 전자파표면유속계를 결합한 DSVM(Dron and Surface Veloctity Meter using doppler radar) 측정방법에 대한 실용성을 확인하였다. 기존 연구에서 DSVM 방법은 드론의 각 측선 이동을 위한 조종 및 전자파표면유속계 측정의제어를 측정자가 수행하였는데 본 연구에서는 자동 측정 시스템 개발을 통해 측정자의 조종 의존도를 줄임과 동시에 안전하고 정확한 유량측정을 위해 노력하였다. 측정지점의 위치정보를 DB화하여 각 측선별 이동하는 자율운항 기능과 전자파표면유속계를 자동으로 제어하여 측정을 실시하는 기능을 개발하였다. 또한 전자파표면유속계 컨트롤 시스템과 GCS(Ground Control System)를 통합하여 한 시스템에서 측정의 모든 상황을 컨트롤 할 수 있게 하였다. 현재까지는 DSVM 방법의 자율운항 기능과 자동 측정 시스템의 테스트를 완료하였고 2022년 홍수기 유량측정에 도입하여 홍수기 유량측정의 실용성을 판단할 계획이다.

• Transactions of the Korean hydrogen and new energy society
• /
• v.25 no.5
• /
• pp.491-499
• /
• 2014

It is important to accurately measure and control the relative humidity of humidified gas entering a PEM (polymer electrolyte membrane) fuel cell stack because the level of humidification strongly affects the performance and durability of the stack. Humidity measurement devices can be used to directly measure the relative humidity, but they cost much to be equipped and occupy spaces in a fuel cell system. We present soft sensors for predicting the relative humidity without actual humidity measuring devices. By combining FIR (finite impulse response) model with PLS (partial least square) and SVM (support vector machine) regression models, DPLS (dynamic PLS) and DSVM (dynamic SVM) soft sensors were developed to correctly estimate the relative humidity of humidified gases exiting a planar-type membrane humidifier. The DSVM soft sensor showed a better prediction performance than the DPLS one because it is able to capture nonlinear correlations between the relative humidity and the input data of the soft sensors. Without actual humidity sensors, the soft sensors presented in this work can be used to monitor and control the humidity in operation of PEM fuel cell systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.40-48
• /
• 2023

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: Zero Crossing Rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies.