• Journal of the Korea Fashion and Costume Design Association
• /
• v.15 no.1
• /
• pp.59-74
• /
• 2013

Post-modern society leads us to accept diversity and variability instead of pursuit of the absolute truth, beauty or classical value systems, thus leading to hybrid phenomena. The purpose of this study is to analyze characteristics and expressive effects of hybrid expressions through which to provide conceptual bases for interpreting expanded meanings of fashion illustrations that express aesthetic concepts of hybrid culture. Hybrid refers to a condition on which diverse elements are mixed with each other, so any one element can not dominate others. It is often used to create something unique and new by a combination of unprecedented things. Hybrid can be classified into four categories: temporal hybrid, spatial hybrid, morphological hybrid and hybrid of different genres. Temporal hybrid from a combination of past and present in fashion illustration includes temporal blending by repetition and juxtaposition. Spatial hybrid shows itself in the form of inter-penetration and interrelationship by means of projection, overlapping, juxtaposition and multiple space. Morphological hybrid expresses itself through combination of heterogenous forms and restructuring of deformed forms. Hybrid of different genres in fashion illustration applies various graphic elements or photos within the space, and represents blending of arts and daily living. Such hybrid expressions in fashion illustrations reflect the phenomena of diversity and variability of post-modern society. Hybrid expressions in fashion illustrations predict endless possibility of expressing new images through combining various forms or casual elements and can develop toward a new creative technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2468-2487
• /
• 2015

In web searching, trustable and precise results are greatly affected by the inherent uncertainty in the input queries. Queries submitted to search engines are by nature ambiguous and constitute a significant proportion of the instances given to web search engines. Ambiguous queries pose real challenges for the web search engines due to versatility of information. Temporal based approaches whereas somehow reduce the uncertainty in queries but still lack to provide results according to users aspirations. Web search science has created an interest for the researchers to incorporate contextual information for resolving the uncertainty in search results. In this paper, we propose an Adaptive Disambiguation Approach (ADA) of hybrid nature that makes use of both the temporal and contextual information to improve user experience. The proposed hybrid approach presents the search results to the users based on their location and temporal information. A Java based prototype of the systems is developed and evaluated using standard dataset to determine its efficacy in terms of precision, accuracy, recall, and F1-measure. Supported by experimental results, ADA demonstrates better results along all the axes as compared to temporal based approaches.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• pp.923-929
• /
• 2019

In this paper, biomimetic based physical ear model proposed for measuring the characteristics of a hybrid-acoustic sensor for fully implantable middle-ear hearing aid. The proposed physical ear model consists of the external ear, middle-ear, and cochlea. The physical ear model was implemented based on the anatomical structure and CT images of the human ear. To confirm the characteristics of the ear model, the vibrational characteristics of the stapes was measured after applying sound pressure to the tympanic membrane. The measured results were compared with the vibrational characteristics of the human temporal bone specified by ASTM F2504-05. Through the comparison results, the feasibility of the proposed ear model was confirmed. Then, after attaching the hybrid-acoustic sensor to the ear model, the output characteristics of the ECM and acceleration sensor were measured according to the sound pressure. The measured results were compared with previous studies using human temporal bone, and the usefulness of the proposed physical ear model was verified through the analysis results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.45-52
• /
• 2005

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper describes system identification using the hybrid neural network, composed of locally(LRNN) and globally recurrent neural networks(GRNN) to improve dynamics of multilayered recurrent networks(RNN). The structure of the hybrid nework combines IIR-MLP as LRNN and Elman RNN as GRNN. The hybrid network is evaluated in linear and nonlinear system identification, and compared with Elman RNN and IIR-MLP networks for the relative comparison of its performance. Simulation results show that the hybrid network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayered recurrent networks in system identification.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.4
• /
• pp.507-520
• /
• 2001

In this paper, a hybrid algorithm for well detecting both abrupt and gradual scene changes is proposed. This algorithm examines only the candidate intervals for speedup using the binary tree method and skips the intervals that are not candidate. For accuracy, the temporal difference of variance is used to detect the gradual scene changes while the temporal difference of histogram is used to detect the abrupt scene changes. Experimental results show that the proposed hybrid algorithm using the binary tree method works up about 10 times faster that the sequential method and is effective in detecting abrupt scene change and gradual transitions including dissolving and fading.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.852-857
• /
• 2005

This paper discusses a human body extraction method for intelligent robot system. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. The new hybrid silhouette extraction method is proposed to overcome this constrained environment. The temporal and gradient information is combined as hybrid silhouette. The motion region model is used to adjust combining parameters in hybrid silhouette. Finally, the experimental results show the superiority of the proposed method.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.93-99
• /
• 2017

A hybrid approach using Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) has showed great improvement in speech recognition accuracy. For training acoustic model based on hybrid approach, it requires forced alignment of HMM state sequence from Gaussian Mixture Model (GMM)-Hidden Markov Model (HMM). However, high computation time for training GMM-HMM is required. This paper proposes an end-to-end approach for LSTM RNN-based Korean speech recognition to improve learning speed. A Connectionist Temporal Classification (CTC) algorithm is proposed to implement this approach. The proposed method showed almost equal performance in recognition rate, while the learning speed is 1.27 times faster.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.61-68
• /
• 2012

Recommender Systems have gained much popularity among researchers and is applied in a number of applications. The exponential growth of users and products poses some key challenges for recommender systems. Recommender Systems mostly suffer from scalability and accuracy. The accuracy of Recommender system is somehow inversely proportional to its scalability. In this paper we proposed a Context Aware Hybrid Recommender System using matrix reduction for Hybrid model and clustering technique for predication of item features. In our approach we used user item-feature rating, User Demographic information and context information i.e. specific time and day to improve scalability and accuracy. Our Algorithm produce better results because we reduce the dimension of items features matrix by using different reduction techniques and use user demographic information, construct context aware hybrid user model, cluster the similar user offline, find the nearest neighbors, predict the item features and recommend the Top N- items.

• Journal of KIISE:Databases
• /
• v.33 no.5
• /
• pp.463-475
• /
• 2006

In applications such as a traffic management system, analysis using a spatial hierarchy of a spatial data warehouse and a simple aggregation is required. Over the past few years, several studies have been made on solution using a spatial index. Many studies have focused on using extended R-tree. But, because it just provides either the current aggregation or the total aggregation, decision support of traffic policy required historical analysis can not be provided. This paper proposes hybrid index based on extended aR-tree for the spatio-temporal aggregation. The proposed method supports a spatial hierarchy and the current aggregation by the R-tree. The sorted hash table using the time structure of the extended aR-tree provides a temporal hierarchy and a historical aggregation. Therefore, the proposed method supports an efficient decision support with spatio-temporal analysis and is Possible currently traffic analysis and determination of a traffic policy with historical analysis.