• Journal of Information Processing Systems
• /
• 제20권1호
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• Journal of Electrical Engineering and Technology
• /
• 제13권3호
• /
• pp.1285-1293
• /
• 2018

This paper proposes a new type of consequent-pole permanent-magnet (CPPM) machine with stator axial magnetic ring that increases torque capability over a wide speed range and enhances efficiency for the built-in rare-earth permanent magnet synchronous machine used in new energy vehicles. The excitation winding of the CPPM hybrid excitation synchronous machine in the stator is replaced by ferrite magnetic ring to simplify the structure and manufacturing process of the machine. The basic structure and magnetic regulation principle of the proposed machine are introduced and compared with the traditional interior rare-earth permanent magnet synchronous machine and CPPM hybrid excitation synchronous machine. Finally, experimental results of a new type of CPPM synchronous motor prototype with axial magnetic ring are introduced in the paper.

• Geomechanics and Engineering
• /
• 제15권6호
• /
• pp.1207-1217
• /
• 2018

Geomechanics parameters are critical to numerical simulation, stability analysis, design and construction of geotechnical engineering. Due to the limitations of laboratory and in situ experiments, back analysis is widely used in geomechancis and geotechnical engineering. In this study, a hybrid back analysis method, that coupling numerical simulation, response surface (RS) and relevance vector machine (RVM), was proposed and applied to identify geomechanics parameters from hydraulic fracturing. RVM was adapted to approximate complex functional relationships between geomechanics parameters and borehole pressure through coupling with response surface method and numerical method. Artificial bee colony (ABC) algorithm was used to search the geomechanics parameters as optimal method in back analysis. The proposed method was verified by a numerical example. Based on the geomechanics parameters identified by hybrid back analysis, the computed borehole pressure agreed closely with the monitored borehole pressure. It showed that RVM presented well the relationship between geomechanics parameters and borehole pressure, and the proposed method can characterized the geomechanics parameters reasonably. Further, the parameters of hybrid back analysis were analyzed and discussed. It showed that the hybrid back analysis is feasible, effective, robust and has a good global searching performance. The proposed method provides a significant way to identify geomechanics parameters from hydraulic fracturing.

• Communications for Statistical Applications and Methods
• /
• 제17권2호
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.881-891
• /
• 2023

최근에는 인공지능을 활용하여 악성 URL을 탐지하는 다양한 연구가 진행되고 있으며, 대부분의 연구 결과에서 높은 탐지 성능을 보였다. 그러나 고전 머신러닝을 활용하는 경우 feature를 분석하고 선별해야 하는 추가 비용이 발생하며, 데이터 분석가의 역량에 따라 탐지 성능이 결정되는 이슈가 있다. 본 논문에서는 이러한 이슈를 해결하기 위해 URL lexical feature를 자동으로 추출하는 딥러닝 모델의 일부가 고전 머신러닝 모델에 결합된 형태인 DL-ML Fusion Hybrid 모델을 제안한다. 제안한 모델로 직접 수집한 총 6만 개의 악성과 정상 URL을 학습한 결과 탐지 성능이 최대 23.98%p 향상되었을 뿐만 아니라, 자동화된 feature engineering을 통해 효율적인 기계학습이 가능하였다.

• 한국융합학회논문지
• /
• 제12권6호
• /
• pp.9-16
• /
• 2021

과거 주가 데이터와 금융 관련 빅 데이터를 사용해 머신러닝 기법으로 주식시장을 예측하는 연구는 다양하게 있어 왔지만, HTS와 MTS를 통해 거래가 가능한 주가지수 연동 ETF가 생기면서 주가지수를 예측하는 연구가 최근 주목받고 있다. 본 논문에서는 KOSPI 연동 ETF를 거래할 목적으로 KOSPI의 상승 예측을 위한 머신러닝 모델과 하락예측을 위한 모델을 각각 구현한다. 이들 모델은 매개변수의 그리드 탐색을 통해 최적화 된다. 또한 정밀도를 개선해 ETF 거래 수익률을 높일 수 있도록 개별 모델들을 조합한 하이브리드 머신러닝 모델을 제안한다. 예측 모델의 성능은 정확도와 ETF 거래 수익률에 큰 영향을 미치는 정밀도로 평가된다. 하이브리드 상승 예측 모델의 정확도와 정밀도는 72.1 %와 63.8 %이고 하락 예측 모델은 79.8 %와 64.3 %이다. 하이브리드 하락 예측 모델에서 정밀도는 개별 모델보다 최소 14.3 %, 최대 20.5 % 개선되었다. 테스트 기간에 하이브리드 모델은 하락에서 10.49 %, 상승에서 25.91 %의 ETF 거래 수익률을 보였다. 인버스×2와 레버리지 ETF로 거래하면 수익률을 1.5 ~ 2배로 높일 수 있다. 하락예측 머신러닝 모델에 대한 추가 연구로 수익률을 더 높일 수 있을 것으로 기대한다.

• Journal of Power Electronics
• /
• 제19권1호
• /
• pp.158-167
• /
• 2019

This research comparatively studies three kinds of flux regulation methods, namely, stored capacitor discharge pulse (SCDP), constant current source pulse (CCSP), and quantitative flux regulation pulse (QFRP), which are used for hybrid permanent magnet (PM) axial field flux-switching memory machines (HPM-AFFSMMs). Through an analysis of the operation principle and the series hybrid PM flux regulation mechanism of the objective machine, the circuit topologies and flux regulation process of these flux regulation methods are addressed in detail. On the basis of a simulation, the flux regulation characteristics of the researched machine during the magnetization and demagnetization processes are comparatively evaluated. Then, machine performance, including back EMF, direct and quadrature axis inductances, and magnetization and demagnetization characteristics, is quantitatively investigated. Results show that the QFRP enables the HPM-AFFSMM to achieve a less harmonic component of back EMF by approximately 7.28% and 7.97% at the magnetization and demagnetization states, respectively, and a more complete magnetization process than the SCDP and CCSP.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 추계학술대회 논문집
• /
• pp.87-88
• /
• 2012

• 한국통신학회논문지
• /
• 제21권5호
• /
• pp.1256-1265
• /
• 1996

연판정 검출기는 시스템의 비트오류율과 처리율을 높이기 위해서 많은 순방향 에러정정(FEC) 방식과 자동반복요구(ARQ) 방식에서 사용되고 있다. 또한 FEC 방식과 ARQ 방식을 결합한 복합-ARQ 방식은 시스템의 전체적인 성능을 높이기 위해 매우 효율적인 방식이다. 본 논문에서는 연판정 검출기를 사용하고 채널부호로는 1차 Reed-Muller 부호를 사용한 복합-ARQ 방식을 제시한다. Reed-Muller 부호는 다른 부호에 비하여 매우 간단하면서 빠른 Green machine 복호기를 사용할 수 있는 장점을 가지고 있다. 시스템의 성능을 평가하기 위하여 비트오류율과 처리율을 구하고 다른 시스템과 비교하였다. 그 결과 제안된 시스템이 복잡도면에서의 큰 손실없이 성능면에서 높은 개선을 보임을 알 수 있었다.

• 한국정밀공학회지
• /
• 제30권11호
• /
• pp.1139-1145
• /
• 2013

Machine tools are the cores of industrial development in recent period. It is difficult to develop a system which can do cutting and grinding process in the one system. Hybrid Vertical Grinding System is capable of processing in a single apparatus cutting or grinding. The modal analysis and structural analysis for the development of Hybrid Vertical Grinding System is the first time of domestic work. This paper describes the technologies of Hybrid Vertical grinding machine and intend to introduce the studies in the development of the Hybrid Vertical Grinding System.