• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• 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
• /
• v.2 no.3
• /
• 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
• /
• v.39 no.1
• /
• 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.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.11 no.2
• /
• 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.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.9
• /
• 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
• /
• v.16 no.3
• /
• 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.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.9
• /
• pp.536-542
• /
• 2004

An architecture of direct digital frequency synthesizers (DDFS) is studied in this paper The Direct digital frequency synthesizers (DDFS) provide fast frequency switching with high spectral purity and are widely used in modern spread spectrum wireless communication systems. ROM-based DDFS uses a ROM lookup table to store the amplitude of a sine wave. In this paper, we suggest three new techniques to reduce the ROM size. One new technique uses more number of hierarchical levels in ROM structures. Another techniques use simple interpolation techniques combined with hierarchical ROM structures. A 12 bit sine wave is generated by using these techniques. Experimental results show that the new proposed techniques can reduce the required ROM size by up to 24%, when compared to that of a resent method[1].

• Journal of Sensor Science and Technology
• /
• v.17 no.6
• /
• 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.

• Journal of the Korea Society for Simulation
• /
• v.11 no.3
• /
• 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.

• Journal of the Korea Convergence Society
• /
• v.6 no.5
• /
• pp.241-248
• /
• 2015

Nursing clinical practice, especially because it is required to reproduce this fusion education is very urgent. This Study was done to examine the effect of action learning techniques in simulation class. The study was designed using a nonequivalent control group pretest-posttest design. The participants consisted of control group 92, experimental group 92. The data analyzed using SPSS 18.0 program. Professional self-concept are higher than in the control group were measured.(t=-5.118, p=>.001). communication competence and self-directed learning capability of experimental group increased significantly from those control group. This result means that can help to significantly improve the professional nursing students learning techniques to simulate the application of an action class. In other words, if the act of creative training techniques such as future action learning hands-on training to be a big help.