• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.455-467
• /
• 2017

When performing target detection using hyperspectral imagery, a feature extraction process is necessary to solve the problem of redundancy of adjacent spectral bands and the problem of a large amount of calculation due to high dimensional data. This study proposes a new band selection method using the $L_{2,1}$-norm regression model to apply the feature selection technique in the machine learning field to the hyperspectral band selection. In order to analyze the performance of the proposed band selection technique, we collected the hyperspectral imagery and these were used to analyze the performance of target detection with band selection. The Adaptive Cosine Estimator (ACE) detection performance is maintained or improved when the number of bands is reduced from 164 to about 30 to 40 bands in the 350 nm to 2500 nm wavelength band. Experimental results show that the proposed band selection technique extracts bands that are effective for detection in hyperspectral images and can reduce the size of the data without reducing the performance, which can help improve the processing speed of real-time target detection system in the future.

• Korean Management Science Review
• /
• v.17 no.3
• /
• pp.19-30
• /
• 2000

Customization and personalization services are considered as a critical success factor to be a successful Internet store or web service provider. As a representative personalization technique, personalized recommendation techniques are studied and commercialized to suggest products or services to a customer of Internet storefronts based on demographics of the customer or based on an analysis of the past purchasing behavior of the customer. The underlining theories of recommendation techniques are statistics, data mining, artificial intelligence, and/or rule-based matching. In the rule-based approach for personalized recommendation, marketing rules for personalization are usually collected from marketing experts and are used to inference with customers data. however, it is difficult to extract marketing rules from marketing experts, and also difficult to validate and to maintain the constructed knowledge base. In this paper, we proposed a marketing rule extraction technique for personalized recommendation on Internet storefronts using market basket analysis technique, a well-known data mining technique. Using marketing basket analysis technique, marketing rules for cross sales are extracted, and are used to provide personalized advertisement selection when a customer visits in an Internet store. An experiment has been performed to evaluate the effectiveness of proposed approach comparing with preference scoring approach and random selection.

• Journal of Korean Society on Water Environment
• /
• v.33 no.3
• /
• pp.348-358
• /
• 2017

The process of evaluating and selecting the best available techniques presents various characteristics for each country. In the case of EU, BAT is selected through TWG meeting after first screening, mass and energy balance, impact assessment and decision support process. Korea has proposed four principles to select BAT that can be carbon neutral for each environmental infrastructure in order to reduce greenhouse gas emissions. In order to evaluate and select the best available technique, it is necessary to differentiate the method according to whether it is a technique generally applied at the current workplace, whether it is a single technique or a combination technique, and whether it is a technology technique or management technique. In the case of a single technique, it should be evaluated whether it is a technique applied in the workplace, excessive cost, superior environmental technique over BAT, and secondary environmental pollution. In the case of multiple techniques, it is necessary to examine whether the emission standards are met and whether the pollutants can be treated at the same level as BAT. In the case of BAT candidates for management techniques, whether or not they contribute directly or indirectly to lowering the emission level of pollutants can be an important evaluation item. In the case of environmental techniques that are not generally applied in the workplace, it is recommended that the following 8 steps be carried out, including those prescribed by law. In the first stage, the list of performance evaluation factors is listed. In the second stage, the level of disposal of pollutants and the level of satisfaction with standards are listed. In the third stage, the environmental evaluation elements are listed. In the fourth stage, Is to list the economic evaluation elements, step 6 is to list the pollution and accident prevention evaluation factors, step 7 is the quantitative evaluation of the technical working group, and step 8 is BAT confirmation through deliberation of the central environmental policy committee.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.30-37
• /
• 2023

Alzheimer's disease (AD) symptoms are being treated by early diagnosis, where we can only slow the symptoms and research is still undergoing. In consideration, using T1-weighted images several classification models are proposed in Machine learning to identify AD. In this paper, we consider the improvised feature selection, to reduce the complexity by using wrapping techniques and Restricted Boltzmann Machine (RBM). This present work used the subcortical and cortical features of 278 subjects from the ADNI dataset to identify AD and sMRI. Multi-class classification is used for the experiment i.e., AD, EMCI, LMCI, HC. The proposed feature selection consists of Forward feature selection, Backward feature selection, and Combined PCA & RBM. Forward and backward feature selection methods use an iterative method starting being no features in the forward feature selection and backward feature selection with all features included in the technique. PCA is used to reduce the dimensions and RBM is used to select the best feature without interpreting the features. We have compared the three models with PCA to analysis. The following experiment shows that combined PCA &RBM, and backward feature selection give the best accuracy with respective classification model RF i.e., 88.65, 88.56% respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2521-2526
• /
• 2013

In this paper, a novel spatial modulation (SM) with transmit antenna selection (TAS) based on maximizing channel capacity is proposed. Comparing to the conventional TAS technique, the proposed TAS considers the channel capacity of the MIMO channel with antenna selection. The optimal antenna set selection is applied to SM by taking account of the all possible sets, and then, a sub-optimal antenna set selection is also proposed for reducing the computational complexity of the optimal method. Computer simulations show that the proposed TAS significantly outperforms the existing SM scheme based on the magnitude of the channel vectors in terms of bit error rate (BER) in various environments.

• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.179-200
• /
• 2008

We develop a feature selection method that can improve both the efficiency and the effectiveness of classification technique. In this research, we employ case-based reasoning as a classification technique. Basically, this research integrates the two existing feature selection methods, i.e., the univariate analysis and the LVF algorithm. First, we sift some predictive features from the whole set of features using the univariate analysis. Then, we generate all possible subsets of features from these predictive features and measure the inconsistency rate of each subset using the LVF algorithm. Finally, the subset having the lowest inconsistency rate is selected as the best subset of features. We measure the performances of our feature selection method using the data obtained from UCI Machine Learning Repository, and compare them with those of existing methods. The number of selected features and the accuracy of our feature selection method are so satisfactory that the improvements both in efficiency and effectiveness are achieved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10A
• /
• pp.752-759
• /
• 2009

Cooperative diversity is an effective technique to combat multi-path fading. When this technique is applied to energy-constrained wireless sensor networks, it is a key issue to design appropriate relay selection and power allocation strategies. In this paper, we proposed a new multi-relay selection and power allocation algorithm to maximize network lifetime. The algorithm are composed of two relay selection stages, where the channel condition and residual power of each node were considered in multi-relay selection and the power is fairly allocated proportional to the residual power, satisfies the required SNR at destination and minimizes the total transmit power. In this paper, proposed algorithm is based on AF (amplify and forward) model. We evaluated the proposed algorithm by using extensive simulation and simulation results show that proposed algorithm obtains much longer network lifetime than the conventional algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.286-288
• /
• 2012

파일 공유를 위해 널리 사용되는 BitTorrent는 대표적인 P2P 프로토콜이다. BitTorrent는 전송을 요구한 클라이언트가 작은 단위로 쪼개진 하나의 파일을 다수의 클라이언트들로부터 받는 방식으로 기존의 일대일 P2P 전송방식에 대비하여 빠른 다운로드 속도를 낼 수 있다. 이러한 다운로드 성능을 발휘하기위해 다수의 조각으로 분리 된 파일 조각을 선택하는 Pieces Selection 기법은 매우 중요하다. 이에 본 논문에서는 BitTorrent에서 활용되는 네 가지의 Pieces Selection 기법에 대해 알아보고, 성능 개선을 위한 새로운 기법을 제안한다.

• Proceedings of the CALSEC Conference
• /
• 2000.08a
• /
• pp.207-214
• /
• 2000

Over the last several decades, the topic of the source selection and evaluation has gained a great attention in the information systems community as an effective tool to acquire information systems in an organization. The source selection and evaluation process is a multiple-criteria decision-making problem associated with several evaluation issues. In this case study, evaluation issues include management, technologies, logistics, and cost. This case study was conducted to compare a new source selection and evaluation process by using the analytic hierarchy process with the traditional approach. This study provides useful insight about how to apply the analytic hierarchy process technique to the traditional approach.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1238-1240
• /
• 2009

In the wireless sensor network, cooperative transmission is an effective technique to combat multi-path fading and reduce transmitted power. Relay selection and power allocation are important technical issues to determine the performance of cooperative transmission. In this paper, we proposed a new multi-relay selection and power allocation algorithm to increase network lifetime. The proposed relay selection scheme minimizes the transmitted power and increase the network lifetime by considering residual power as well as channel conditions. Simulation results show that proposed algorithm obtains much longer network lifetime than the conventional algorithm.