• Bulletin of the Korean Chemical Society
• /
• v.32 no.7
• /
• pp.2397-2404
• /
• 2011

Variable selection k nearest neighbor QSAR modeling approach was applied to a data set of 80 3-arylisoquinolines exhibiting cytotoxicity against human lung tumor cell line (A-549). All compounds were characterized with molecular topology descriptors calculated with the MolconnZ program. Seven compounds were randomly selected from the original dataset and used as an external validation set. The remaining subset of 73 compounds was divided into multiple training (56 to 61 compounds) and test (17 to 12 compounds) sets using a chemical diversity sampling method developed in this group. Highly predictive models characterized by the leave-one out cross-validated $R^2$ ($q^2$) values greater than 0.8 for the training sets and $R^2$ values greater than 0.7 for the test sets have been obtained. The robustness of models was confirmed by the Y-randomization test: all models built using training sets with randomly shuffled activities were characterized by low $q^2{\leq}0.26$ and $R^2{\leq}0.22$ for training and test sets, respectively. Twelve best models (with the highest values of both $q^2$ and $R^2$) predicted the activities of the external validation set of seven compounds with $R^2$ ranging from 0.71 to 0.93.

• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.63-90
• /
• 2017

Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.428-432
• /
• 2007

We present a novel method for determining k nearest neighbors, which accurately recognizes the underlying clusters in a data set. To this end, we introduce the "tiling neighborhood" which is constructed by tiling a number of small local circles rather than a single circle, as existing neighborhood schemes do. Then we formulate the problem of determining the tiling neighborhood as a minimax optimization, leading to an efficient message passing algorithm. For several real data sets, our method outperformed the k-nearest neighbor method. The results suggest that our method can be an alternative to existing for general classification tasks, especially for data sets which have many missing values.

• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.53-61
• /
• 2017

The preferred feature selection methods for text classification are filter-based. In a common filter-based feature selection scheme, unique scores are assigned to features; then, these features are sorted according to their scores. The last step is to add the top-N features to the feature set. In this paper, we propose an improved global feature selection scheme wherein its last step is modified to obtain a more representative feature set. The proposed method aims to improve the classification performance of global feature selection methods by creating a feature set representing all classes almost equally. For this purpose, a local feature selection method is used in the proposed method to label features according to their discriminative power on classes; these labels are used while producing the feature sets. Experimental results obtained using the well-known 20 Newsgroups and Reuters-21578 datasets with the k-nearest neighbor algorithm and a support vector machine indicate that the proposed method improves the classification performance in terms of a widely known metric ($F_1$).

• Journal of Information Processing Systems
• /
• v.3 no.2
• /
• pp.73-81
• /
• 2007

In this paper, we introduce a domain-independent classification framework based on both k-nearest neighbor and Naive Bayesian classification algorithms. The architecture of our system is simple and modularized in that each sub-module of the system could be changed or improved efficiently. Moreover, it provides various feature selection mechanisms to be applied to optimize the general-purpose classifiers for a specific domain. As for the enhanced classification performance, our system provides conditional probability boosting (CPB) mechanism which could be used in various domains. In the mood classification domain, our optimized framework using the CPB algorithm showed 1% of improvement in precision and 2% in recall compared with the baseline.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.173-190
• /
• 2015

The purpose of this study is to improve bankruptcy prediction models by using a novel hybrid under-sampling approach. Most prior studies have tried to enhance the accuracy of bankruptcy prediction models by improving the classification methods involved. In contrast, we focus on appropriate data preprocessing as a means of enhancing accuracy. In particular, we aim to develop an effective sampling approach for bankruptcy prediction, since most prediction models suffer from class imbalance problems. The approach proposed in this study is a hybrid under-sampling method that combines the k-Reverse Nearest Neighbor (k-RNN) and one-class support vector machine (OCSVM) approaches. k-RNN can effectively eliminate outliers, while OCSVM contributes to the selection of informative training samples from majority class data. To validate our proposed approach, we have applied it to data from H Bank's non-external auditing companies in Korea, and compared the performances of the classifiers with the proposed under-sampling and random sampling data. The empirical results show that the proposed under-sampling approach generally improves the accuracy of classifiers, such as logistic regression, discriminant analysis, decision tree, and support vector machines. They also show that the proposed under-sampling approach reduces the risk of false negative errors, which lead to higher misclassification costs.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.145-150
• /
• 2015

Needs about safety of residents are important in urbanized society, elderly and small-size family. People are looking for safety information system and device of CPTED. That is, Needs and Installations of CCTV increased steadily. But, scientific analysis about validity, systematic plan and location of security CCTV is nonexistent. It is simply put these devised in more demanded areas. It has limits to look for safety of residents by increasing density of CCTVs. One of the characteristics of crime is clustering and stong interconnectivity. So, exploratory spatial data of crime is geo-coded using 2 years data and carried out cluster analysis and space statistical analysis through GIS space analysis by dividing 18 variables into social economy, urban space, crime prevention facility and crime occurrence index. The result of analysis shows cluster of 5 major crimes, theft, violence and sexual violence by Nearest Neighbor distance analysis and Ripley's K function. It also shows strong crime interconnectivity through criminal correlation analysis. In case of finding criminal cluster, you can find criminal hotspot. So, in this study I found concept of hotspot and considered technique about selection of hotspot. And then, selected hotspot about 5 major crimes, theft, violence and sexual violence through Nearest Neighbor Hierarchical Spatial Clustering.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.71-81
• /
• 2018

Forklifts in a shipyard lift and transport heavy objects. Tasks occur dynamically and the rate of the task occurrence changes over time. Especially, the rate of the task occurrence is high immediately after morning and afternoon business hours. The weight of objects varies according to task characteristic, and a forklift also has the workable or allowable weight limit. In this study, we propose an online forklift dispatching algorithm based on nearest-neighbor dispatching rule using minimal cost assignment approach in order to attain the efficient operations. The proposed algorithm considers various types of forklift and multiple jobs at the same time to determine the dispatch plan. We generate dummy forklifts and dummy tasks to handle unbalance in the numbers of forklifts and tasks by taking their capacity limits and weights. In addition, a method of systematic forklift selection is also devised considering the condition of the forklift. The performance indicator is the total travel distance and the average task waiting time. We validate our approach against the priority rule-based method of the previous study by discrete-event simulation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.2
• /
• pp.39-48
• /
• 2011

Global warming causes the climate change and makes severe damage to ecosystem and civilization Carbon dioxide greatly contributes to global warming, thus many studies have been conducted to estimate the forest biomass carbon stock as an important carbon storage. However, more studies are required for the selection and use of technique and remotely sensed data suitable for the carbon stock estimation in Korea In this study, the aboveground forest biomass carbon stocks of Danyang-Gun in South Korea was estimated using $k$NN($k$-Nearest Neighbor) algorithm and regression model, then the results were compared. The Landsat TM and 5th NFI(National Forest Inventory) data were prepared, and ratio images, which are effective in topographic effect correction and distinction of forest biomass, were also used. Consequently, it was found that $k$NN algorithm was better than regression model to estimate the forest carbon stocks in Danyang-Gun, and there was no significant improvement in terms of accuracy for the use of ratio images.