• Journal of Information Processing Systems
• /
• v.19 no.2
• /
• pp.258-266
• /
• 2023

Aiming at the problems of poor customer satisfaction and poor accuracy of customer classification, this paper proposes a customer classification model based on speech recognition. First, this paper analyzes the temporal data characteristics of customer demand data, identifies the influencing factors of customer demand behavior, and determines the process of feature extraction of customer voice signals. Then, the emotional association rules of customer demands are designed, and the classification model of customer demands is constructed through cluster analysis. Next, the Euclidean distance method is used to preprocess customer behavior data. The fuzzy clustering characteristics of customer demands are obtained by the fuzzy clustering method. Finally, on the basis of naive Bayesian algorithm, a customer demand classification model based on speech recognition is completed. Experimental results show that the proposed method improves the accuracy of the customer demand classification to more than 80%, and improves customer satisfaction to more than 90%. It solves the problems of poor customer satisfaction and low customer classification accuracy of the existing classification methods, which have practical application value.

• Computational Structural Engineering
• /
• v.3 no.4
• /
• pp.113-122
• /
• 1990

An analytical simulation of the flexural behavior of SFRC beam has been illustrated. Curvature distributions and crack opening in critical region were taken into account. Compressive and tensile constitutive models which express post-peak behavior of SFRC with stress-crack opening relationships were incorporated in simulating nonlinear flexural behavior of the beam. The model was able to predict test results with reasonable accuracy. Behavior of the critical section and effects of different factors m the flexural behavior of SFRC beam were investigated. Simple observation and statistical approach have been made in selecting most influential parameters in flexural behavior of SFRC.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1997.10a
• /
• pp.213-218
• /
• 1997

Thermal deformation of machine origin of machine tools due to internal and external heat sources has been the most important problem to fabricate products with higher accuracy and performance. In order to solve this problem, GMDH models were constructed to estimate thermal deformation of machine origin for a vertical machining ceneter through measurement of temperature data of specific points on the machine tool. These models are nonlinear equations with high-order polynomials and implemented in a multilayered perceptron type network structure. Input variables and orders are automatically selected by correlation and optimization procedure. Sensors with small influence are deleted automatically in this algorithm. It was shown that the points of temperature measurement can be reduced without sacrificing the estimation accuracy of $\pm$5${\mu}{\textrm}{m}$. From the experimental result, it was confirmed that GMDH methodology was superior to least square models to estimate the thermal behavior of machine tools.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.22 no.3
• /
• pp.1-12
• /
• 1994

This study was carried out to identify destination choice behavior for one-day use recreation areas. Previous positioning study was utilized to select 4 study areas, and the secondary data were used for logit analyses. The Hausamn-McFadden test for IIA was conducted to examine whether conditional logit models are valid methodology for this study. The results revealed that IIA assumption among the study areas was violated; therefore, generalized binomial and generalized multinomial logit models were used in this study. In the binomial logit analysis, 2 to 5 independent variables were included in the models: their $\rho$2 values were from 0.1to 0.323, and accuracy of predictions were from 65.38 to 79.86 percent. In the multinomial logit analysis, 4 independent variables were included in the model: its $\rho$2 value was 0.207, and accuracy of prediction was 45.82 percent. The results showed that the conditional logit should be used with caution because of the IIA assumption. Several suggestions were described, mainly due to utilization of the secondary data for this study.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.132-137
• /
• 2012

To enhance the CAE accuracy, the definition of material behavior is one of key influence on the result. In case of plastic material with fiber reinforcement, the anisotropic material behavior should be taken into account to increase of CAE accuracy. BASF has developed an innovative CAE tool, ULTRASIM$^R$, which is capable of generating material models of thermoplastic materials for structural simulation. ULTRASIM$^R$, not only the glass fiber orientation effect, but also the weld line effect, tensile-compression anisotropy, strain rate effect are combined in a non-linear material law, which will be evaluated in a unique failure criterion, thus resulting in an highly accurate CAE approach.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.4
• /
• pp.97-103
• /
• 2001

The study on the high-speed machine tool is very important for the improvement of productivity since it can shortens cutting and non-cutting time. Especially, high speed of feed drive system is the major research field. In the industries of the advanced countries, the feed drive systems at the speed of 60 m/min have been already developed based on the high lead ball screws. In this study, a high speed feed drive system at the speed of 60 m/ min has been developed, and its movements characteris-tics are investigated. As the movement characteristics, positioning accuracy, angular accuracy, straightness and micro step-response are measured. Thermal characteristics of the system is also discussed. For measuring the movement characteris-tics, a laser interferometer, a memory-based Hi-coder and a cooling device are used. The experimental results confirm that the movement characteristics and the thermal behavior of the system are satisfactory in the aspect of accuracy and stability.

• Structural Engineering and Mechanics
• /
• v.12 no.2
• /
• pp.201-214
• /
• 2001

Four finite element (FE) models are examined to find the one that best estimates moment-rotation characteristics of top- and seat-angle with double web-angle connections. To efficiently simulate the real behavior of connections, finite element analyses are performed with following considerations: 1) all components of connection (beam, column, angles and bolts) are discretized by eight-node solid elements; 2) shapes of bolt shank, head, and nut are precisely taken into account in modeling; and 3) contact surface algorithm is applied as boundary condition. To improve accuracy in predicting moment-rotation behavior of a connection, bolt pretension is introduced before the corresponding connection moment being surcharged. The experimental results are used to investigate the applicability of FE method and to check the performance of three-parameter power model by making comparison among their moment-rotation behaviors and by assessment of deformation and stress distribution patterns at the final stage of loading. This research exposes two important features: (1) the FE method has tremendous potential for connection modeling for both monotonic and cyclic loading; and (2) the power model is able to predict moment-rotation characteristics of semi-rigid connections with acceptable accuracy.

• Steel and Composite Structures
• /
• v.38 no.4
• /
• pp.365-380
• /
• 2021

Although traditional steel-concrete composite beams have excellent structural characteristics, it cannot meet the requirement of quick assembly and repair in the engineering. This paper presents a study on static behavior of bolt connected steel-concrete composite beam without post-cast zone. A three-dimensional finite element model was developed with its accuracy and reliability validated by available experimental results. The analysis results show that in the normal service stage, the bolt is basically in the state of unidirectional stress with the loss of pretightening can be ignored. Parametric studies are presented to quantify the effects of the post-cast zone, size and position of splicing gap on the behavior of the beam. Based on the studies, suggested size of gap and installation order were proposed. It is also confirmed that optimized concrete slab in mid-span can reduce the requirement of construction accuracy.

• Steel and Composite Structures
• /
• v.43 no.5
• /
• pp.625-637
• /
• 2022

Axial compression capacity (P_u) is a significant yet complex parameter of concrete-filled steel tube (CFST) columns. This study offers a novel ensemble tool, adaptive neuro-fuzzy inference system (ANFIS) supervised by equilibrium optimization (EO), for accurately predicting this parameter. Moreover, grey wolf optimization (GWO) and Harris hawk optimizer (HHO) are considered as comparative supervisors. The used data is taken from earlier literature provided by finite element analysis. ANFIS is trained by several population sizes of the EO, GWO, and HHO to detect the best configurations. At a glance, the results showed the competency of such ensembles for learning and reproducing the P_u behavior. In details, respective mean absolute errors along with correlation values of 4.1809% and 0.99564, 10.5947% and 0.98006, and 4.8947% and 0.99462 obtained for the EO-ANFIS, GWO-ANFIS, and HHO-ANFIS, respectively, indicated that the proposed EO-ANFIS can analyze and predict the behavior of CFST columns with the highest accuracy. Considering both time and accuracy, the EO provides the most efficient optimization of ANFIS and can be a nice substitute for experimental approaches.