• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.3
• /
• pp.31-39
• /
• 2021

In this study, the fiber blending ratio and strain rate effect on the tensile properties synergy effect of hybrid fiber reinforced cement composite was evaluated. Hooked steel fiber(HSF) and smooth steel fiber(SSF) were used for reinforcing fiber. The fiber blending ratio of HSF+SSF were 1.5+0.5, 1.0+1.0 and 0.5+1.5vol.%. As a results, in the cement composite(HSF2.0) reinforced with HSF, as the strain rate increases, the tensile stress sharply decreased after the peak stress because of the decrease in the number of straightened pull-out fibers by increase of micro cracks in the matrix around HSF. When 0.5 vol.% of SSF was mixed, the micro cracks was effectively controlled at the static rate, but it was not effective in controlling micro cracks and improving the pull-out resistance of HSF at the high rate. On the other hand, the specimen(HSF1.0SSF1.0) in which 1.0vol.% HSF and 1.0vol.% SSF were mixed, each fibers controls against micro and macro cracks, and SSF improves the pull-out resistance of HSF effectively. Thus, the fiber blending effect of the strain capacity and energy absorption capacity was significantly increased at the high rate, and it showed the highest dynamic increase factor of the tensile strength, strain capacity and peak toughness. On the other hand, the incorporation of 1.5 vol.% SSF increases the number of fibers in the matrix and improves the pull-out resistance of HSF, resulting in the highest fiber blending effect of tensile strength and softening toughness. But as a low volume fraction of HSF which controlling macro crack, it was not effective for synergy of strain capacity and peak toughness.

• Composites Research
• /
• v.34 no.3
• /
• pp.192-198
• /
• 2021

Due to enormous market growing of electric vehicles without combustion engine, reducing unwanted BSR (buzz, squeak, and rattle) noise is highly demanded for vehicle quality and performance. Particularly, innerbelt weatherstrips which not only block wind noise, rain, and dust from outside, but also reduce noise and vibration of door glass and vehicle are required to exhibit high damping properties for improved BSR performance of the vehicle. Thermoplastic elastomers (TPEs), which can be recycled and have lighter weight than thermoset elastomers, are receiving much attention for weatherstrip material, but TPEs exhibit low material damping and compression set causing frictional noise and vibration between the door glass and the weatherstrip. In this study, high damping EPDM (ethylene-propylene-diene monomer)/PP (polypropylene) thermoplastic vulcanizates (TPV) were investigated by varying EPDM/PP ratio and ENB (ethylidene norbornene) fraction in EPDM. Viscoelastic properties of TPV materials were characterized by assuming that the material damping is directly related to the viscoelasticity. The optimum material damping factor (tanδ peak 0.611) was achieved with low PP ratio (14 wt%) and high ENB fraction (8.9 wt%), which was increased by 140% compared to the reference (tanδ 0.254). The improved damping is believed due to high fraction of flexible EPDM chains and higher interfacial slippage area of EPDM particles generated by increasing ENB fraction in EPDM. The stick-slip test was conducted to characterize frictional noise and vibration of the TPV weatherstrip. With improved TPV material damping, the acceleration peak of frictional vibration decreased by about 57.9%. This finding can not only improve BSR performance of electric vehicles by designing material damping of weatherstrips but also contribute to various structural applications such as urban air mobility or aircrafts, which require lightweight and high damping properties.