• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1413-1432
• /
• 2023

Recommender systems aim to recommend items to users by taking into account their probable interests. This study focuses on creating a model that utilizes multiple sources of information about users and items by employing a multimodality approach. The study addresses the task of how to gather information from different sources (modalities) and transform them into a uniform format, resulting in a multi-modal feature description for users and items. This work also aims to transform and represent the features extracted from different modalities so that the information is in a compatible format for integration and contains important, useful information for the prediction model. To achieve this goal, we propose a novel multi-modal recommendation model, which involves extracting latent features of users and items from a utility matrix using matrix factorization techniques. Various transformation techniques are utilized to extract features from other sources of information such as user reviews, item descriptions, and item categories. We also proposed the use of Principal Component Analysis (PCA) and Feature Selection techniques to reduce the data dimension and extract important features as well as remove noisy features to increase the accuracy of the model. We conducted several different experimental models based on different subsets of modalities on the MovieLens and Amazon sub-category datasets. According to the experimental results, the proposed model significantly enhances the accuracy of recommendations when compared to SVD, which is acknowledged as one of the most effective models for recommender systems. Specifically, the proposed model reduces the RMSE by a range of 4.8% to 21.43% and increases the Precision by a range of 2.07% to 26.49% for the Amazon datasets. Similarly, for the MovieLens dataset, the proposed model reduces the RMSE by 45.61% and increases the Precision by 14.06%. Additionally, the experimental results on both datasets demonstrate that combining information from multiple modalities in the proposed model leads to superior outcomes compared to relying on a single type of information.

• Journal of Computing Science and Engineering
• /
• 제2권3호
• /
• pp.274-300
• /
• 2008

Software testing cost can be reduced if the process of testing is automated. However, the test data generation task is still performed mostly by hand although numerous theoretical works have been proposed to automate the process of generating test data and even commercial test data generators appeared on the market. Despite prolific research reports, few attempts have been made to evaluate and characterize those techniques. Therefore, a lot of works have been proposed to automate the process of generating test data. However, there is no overall evaluation and comparison of these techniques. Evaluation and comparison of existing techniques are useful for choosing appropriate approaches for particular applications, and also provide insights into the strengths and weaknesses of current methods. This paper conducts experiments on four representative test data generation techniques and discusses the experimental results. The results of the experiments show that the genetic algorithm (GA)-based test data generation performs the best. However, there are still some weaknesses in the GA-based method. Therefore, we modify the standard GA-based method to cope with these weaknesses. The experiments are carried out to compare the standard GA-based method and two modified versions of the GA-based method.

• ETRI Journal
• /
• 제39권1호
• /
• pp.124-134
• /
• 2017

Data races are one of the most difficult types of bugs in concurrent multithreaded systems. It requires significant time and cost to accurately detect bugs in complex large-scale programs. Although many race detection techniques have been proposed by various researchers, none of them are effective in all aspects. In this paper, we compare the performance of five recent dynamic race detection techniques: FastTrack, Acculock, Multilock-HB, SimpleLock+, and causally precedes (CP) detection. We experimentally demonstrate the strengths and weaknesses of these dynamic race detection techniques in terms of their detection capability, running time, and runtime overhead using 20 benchmark programs with different characteristics. The comparison results show that the detection capability of CP detection does not differ from that of FastTrack, and that SimpleLock+ generates the lowest overhead among the hybrid detection techniques (Acculock, SimpleLock+, and Multilock-HB) for all benchmark programs. SimpleLock+ is 1.2 times slower than FastTrack on average, but misses one true data race reported from Mutilock-HB on the large-scale benchmark programs.

• 한국압력기기공학회 논문집
• /
• 제11권2호
• /
• pp.20-24
• /
• 2015

During refueling Outage, In-service inspections(ISIs) for the Nuclear Power Plant components are mandatory requirement in accordance with ASME Code Sec. XI. Especially, in current ultrasonic testing is one of the most important NDT techniques that are used for volumetric examination methods for nuclear power plant components, and accurate sizing of flaw indication by UT is essential to assure the integrity of the components. However, ASME code specifies minimum requirement for vessel examination procedure, and so far many different flaw sizing approaches have been tried to apply. Through the Round Robin Test(RRT), the accuracy of ultrasonic flaw sizing using DAC techniques was measured with the mock-ups simulating typical pressure vessel welds. These mock-ups contain artificially introduced flaws of known size and location. This paper shows experimental comparison data on the accuracy of techniques using such as 6dB drop, 50%DAC, 20%DAC and 20%DAC with beam spread correction, and also shows that diverse DAC techniques can be effectively applied to the assessment of the flaw sizing for pressure vessel welds in the stage of welding and fabrication.

• 한국소음진동공학회논문집
• /
• 제20권9호
• /
• pp.863-875
• /
• 2010

The vibration of a cylindrical shell is generated due to elastic waves propagating on the shell. Those elastic waves include propagating waves such as flexural, longitudinal and shear waves. Those also include non-propagating decaying waves, i.e. evanescent waves. In order to separate contributions of each type of waves to the data for the vibration of the cylindrical shell, spatial signal processing techniques for wavenumber analysis are investigated in this paper. Those techniques include Fast Fourier transform(FFT) algorithm, Extended Prony method and Overdetermined Modified Extended Prony method(OMEP). Those techniques have been applied to identify the waves from simulated vibration signals with various signal-to-noise ratios. Futhermore, the experimental data for in-plane vibration of the cylindrical shell has been processed with those techniques to identify propagating waves(longitudinal, shear and flexural waves) and evanescent waves.

• Journal of Power Electronics
• /
• 제16권3호
• /
• pp.1097-1109
• /
• 2016

Fault detection and isolation are related to system monitoring, identifying when a fault has occurred, and determining the type of fault and its location. Fault detection is utilized to determine whether a problem has occurred within a certain channel or area of operation. Fault detection and diagnosis have become increasingly important for many technical processes in the development of safe and efficient advanced systems for supervision. This paper presents an integrated technique for fault diagnosis and classification for open- and short-circuit faults in three-phase inverter circuits. Discrete wavelet transform and principal component analysis are utilized to detect the discontinuity in currents caused by a fault. The features of fault diagnosis are then extracted. A fault dictionary is used to acquire details about transistor faults and the corresponding fault identification. Fault classification is performed with a fuzzy logic system and relevance vector machine (RVM). The proposed model is incorporated with a set of optimization techniques, namely, evolutionary particle swarm optimization (EPSO) and cuckoo search optimization (CSO), to improve fault detection. The combination of optimization techniques with classification techniques is analyzed. Experimental results confirm that the combination of CSO with RVM yields better results than the combinations of CSO with fuzzy logic system, EPSO with RVM, and EPSO with fuzzy logic system.

• 한국정보과학회논문지:시스템및이론
• /
• 제31권9호
• /
• pp.536-542
• /
• 2004

본 논문에서는 디지털 주파수 합성기의 구조에 대하여 연구하였다. 디지털 주파수 합성기는 높은 스펙트럼 순도로 빠른 주파수 전환이 가능하고, 현대의 확산 스펙트럼 무선통신 시스템에 널리 사용된다. 롬 기반의 디지털 주파수 합성기는 싸인 파형의 크기를 저장한 롬 테이블을 사용한다. 본 논문에서는 롬의 크기를 줄이는 세 가지 새로운 기술을 제안하였다. 새로운 기법 중 한 가지는 여러 개의 계층적 구조를 사용하였다. 다른 기법들은 계층적 롬 구조를 간단한 보간 기법으로 결합하였다. 이러한 기법으로 12비트의 싸인 파형을 생성하였다. 실험 결과 새롭게 제안한 기법은 기존 방법[1]에 비해 ROM 크기를 24%까지 줄일 수 있다.

• 센서학회지
• /
• 제17권6호
• /
• pp.406-413
• /
• 2008

We have been implemented simple statistical pattern recognition methods for harmful gases classification using gas sensors array fabricated by MEMS (Micro Electro Mechanical System) technology. The performance of pattern recognition method as a gas classifier is highly dependent on the choice of pre-processing techniques for sensor and sensors array signals and optimal classification algorithms among the various classification techniques. We carried out pre-processing for each sensor's signal as well as sensors array signals to extract features for each gas. We adapted simple statistical pattern recognition algorithms, which were PCA (Principal Component Analysis) for visualization of patterns clustering and MLR (Multi-Linear Regression) for real-time system implementation, to classify harmful gases. Experimental results of adapted pattern recognition methods with pre-processing techniques have been shown good clustering performance and expected easy implementation for real-time sensing system.

• 한국시뮬레이션학회논문지
• /
• 제11권3호
• /
• pp.1-12
• /
• 2002

Experimental design in simulation provides an efficient way of economizing simulation runs since a considerable number of simulation runs that originally were planned can be reduced by this approach. This experimental design method is an active area of research together with the output analysis and so no single panacea seems to exist so far. Thus, selection of techniques of experimental design and output analysis more likely depends upon the objective of simulation analysis, budget constraint and sometimes the analyst's subjective judgment. This paper attempts to describe an experimental design methodology for port investment analysis using a case study in a bulk terminal in Korea. Detailed display will be focused on simulation period, warm-up period, the number of replications needed in production runs after brief explanation on the system configuration.

• 한국융합학회논문지
• /
• 제6권5호
• /
• pp.241-248
• /
• 2015

간호학에서 임상상황을 재현한 융합교육은 간호학생의 전문직 향상에 매우 절실하다. 이에 본 연구는 융합액션러닝 기법을 이용하여 시뮬레이션 교육을 실시한 교육방법에 대해 그 효과를 검증하기 위해 시도되었다. 본 연구는 동일 대학의 동일 학제 하에 교육을 받은 1년 차이를 둔 대상자를 대상으로 교육전후의 결과를 비교하였다. 교육 후 전문직 자아개념은 통계적으로 유의한 차이가 없었다(t=1.349, p=.187). 그러나 의사소통 능력(t=-5.118, p=>.001)과 자기주도적 학습능력(t=-3.032, p=.003)은 통계적으로 유의한 차이가 있었다. 이러한 결과는 시뮬레이션 수업에 액션러닝기법을 적용 시 간호학생의 전문직 향상에 크게 도움을 줄 수 있음을 의미한다. 즉 향후 액션러닝과 같은 창의적인 교육기법을 작용한다면 실습교육에 크게 도움이 될 것이다.