• Journal of Biosystems Engineering
• /
• v.40 no.4
• /
• pp.417-427
• /
• 2015

Purpose: This study investigated different band selection methods to classify spectrally similar data - obtained from aerial images of healthy citrus canopies and citrus greening disease (Huanglongbing or HLB) infected canopies - using small differences without unmixing endmember components and therefore without the need for an endmember library. However, large number of hyperspectral bands has high redundancy which had to be reduced through band selection. The objective, therefore, was to first select the best set of bands and then detect citrus Huanglongbing infected canopies using these bands in aerial hyperspectral images. Methods: The forward feature selection algorithm (FFSA) was chosen for band selection. The selected bands were used for identifying HLB infected pixels using various classifiers such as K nearest neighbor (KNN), support vector machine (SVM), naïve Bayesian classifier (NBC), and generalized local discriminant bases (LDB). All bands were also utilized to compare results. Results: It was determined that a few well-chosen bands yielded much better results than when all bands were chosen, and brought the classification results on par with standard hyperspectral classification techniques such as spectral angle mapper (SAM) and mixture tuned matched filtering (MTMF). Median detection accuracies ranged from 66-80%, which showed great potential toward rapid detection of the disease. Conclusions: Among the methods investigated, a support vector machine classifier combined with the forward feature selection algorithm yielded the best results.

• Journal of Communications and Networks
• /
• v.16 no.5
• /
• pp.502-511
• /
• 2014

In this paper, we evaluate performance of a hybrid decode-amplify-forward relaying protocol in underlay cognitive radio. In the proposed protocol, a secondary relay which is chosen by partial relay selection method helps a transmission between a secondary source and a secondary destination. In particular, if the chosen relay decodes the secondary source's signal successfully, it will forward the decoded signal to the secondary destination. Otherwise, it will amplify the signal received from the secondary source and will forward the amplified signal to the secondary destination. We evaluate the performance of our scheme via theory and simulation. Results show that the proposed protocol outperforms the amplify-and-forward and decode-and-forward protocols in terms of outage probability.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.616-623
• /
• 2010

In this paper, exact closed-form expressions for outage probability and bit error probability (BEP) are presented for multi-hop decode-and-forward (DF) relaying schemes in conjunction with cooperative diversity, in which selection combining technique is employed at each node. We have shown that the proposed protocol offers remarkable diversity advantage over direct transmission as well as the conventional DF relaying schemes with the same combining technique. We then investigate the system performance when different diversity schemes are employed. It has been observed that the system performance loss due to selection combining relative to maximal ratio combining is not significant. Simulations are performed to confirm our theoretical analysis.

• Journal of Korea Multimedia Society
• /
• v.14 no.12
• /
• pp.1544-1548
• /
• 2011

A process of choosing a subset of original features, so called feature selection, is considered as a crucial preprocessing step to image processing applications. There are already large pools of techniques developed for machine learning and data mining fields. In this paper, basically two methods, non-feature selection and feature selection, are investigated to compare their predictive effectiveness of classification. Color co-occurrence feature is used for defining image features. Standard Sequential Forward Selection algorithm are used for feature selection to identify relevant features and redundancy among relevant features. Four color spaces, RGB, YCbCr, HSV, and Gaussian space are considered for computing color co-occurrence features. Gray-level image feature is also considered for the performance comparison reasons. The experimental results are presented.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4623-4643
• /
• 2015

This paper considers physical-layer security protocols in multicast cognitive radio (CR) networks. In particular, we propose dual-hop cooperative decode-and-forward (DF) and randomize-and-forward (RF) schemes using partial relay selection method to enhance secrecy performance for secondary networks. In the DF protocol, the secondary relay would use same codebook with the secondary source to forward the source's signals to the secondary destination. Hence, the secondary eavesdropper can employ either maximal-ratio combining (MRC) or selection combining (SC) to combine signals received from the source and the selected relay. In RF protocol, different codebooks are used by the source and the relay to forward the source message secretly. For each scheme, we derive exact and asymptotic closed-form expressions of secrecy outage probability (SOP), non-zero secrecy capacity probability (NzSCP) in both independent and identically distributed (i.i.d.) and independent but non-identically distributed (i.n.i.d.) networks. Moreover, we also give a unified formula in an integral form for average secrecy capacity (ASC). Finally, our derivations are then validated by Monte-Carlo simulations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.1A
• /
• pp.1-9
• /
• 2010

This paper offers performance analysis of selection decode and forward (DF) networks with differential modulation/demodulation for an arbitrary number of relays in independent but not identically distributed Rayleigh fading channels. We have shown that the selection DF protocol with differential modulation can achieve full diversity in both independent identically distributed (i.i.d.) and independent but not identically distributed (i.n.d.) Rayleigh fading channels, and the performance loss due to using non-coherent detection is not substantial. Furthermore, we study the impact of combining techniques on the performance of the system by comparing a system that uses selection combining (SC) to one that uses maximum ratio combining (MRC). Simulations are performed and show that they match exactly with analytic ones in high SNR regime.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.83-92
• /
• 2004

Gene expression profile is numerical data of gene expression level from organism measured on the microarray. Generally, each specific tissue indicates different expression levels in related genes, so that we can classify cancer with gene expression profile. Because not all the genes are related to classification, it is needed to select related genes that is called feature selection. This paper proposes a new gene selection method using forward selection method in regression analysis. This method reduces redundant information in the selected genes to have more efficient classification. We used k-nearest neighbor as a classifier and tested with colon cancer dataset. The results are compared with Pearson's coefficient and Spearman's coefficient methods and the proposed method showed better performance. It showed 90.3% accuracy in classification. The method also successfully applied to lymphoma cancer dataset.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.3
• /
• pp.87-95
• /
• 2013

In this paper, the outage probability of efficient partial relay selection(EPRS) using only one-hop channel information in multi-hop systems is analyzed in Rayleigh fading channels. In particular, we derive an exact and closed-form expression for the outage probability of decode-and-forward relaying based EPRS. In order to prove the usefulness of EPRS in multi-hop systems, we also analyze the correlation between the end-to-end signal-to-noise ratio(SNR) and the SNR for each hop at an arbitrary relaying path. Furthermore, through numerical investigation, we compare the outage performances for EPRS and the best relay selection using all channel information.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.2
• /
• pp.81-87
• /
• 2017

Nowadays wine is increasingly enjoyed by a wider range of consumers, and wine certification and quality assessment are key elements in supporting the wine industry to develop new technologies for both wine making and selling processes. There have been many attempts to construct a more methodical approach to the assessment of wines, but most of them rely on objective decision rather than subjective judgement. In this paper, we propose a data mining approach to predict human wine taste preferences that is based on easily available analytical tests at the certification step. We used sequential forward selection and decision tree for this purpose. Experiments with the wine quality dataset from the UC Irvine Machine Learning Repository demonstrate the accuracies of 76.7% and 78.7% for red and white wines respectively.

• Journal of Communications and Networks
• /
• v.11 no.5
• /
• pp.480-488
• /
• 2009

Cooperative transmission is an effective solution to improve the performance of wireless communications over fading channels without the need for physical co-located antenna arrays. In this paper, selection combining is used at the destination instead of maximal ratio combing to optimize the structure of destination and to reduce power consumption in selective decode-and-forward relaying networks. For an arbitrary number of relays, an exact and closed-form expression of the bit error rate (BER) is derived for M-PAM, M-QAM, and M-PSK, respectively, in both independent identically distributed and independent but not identically distributed Rayleigh fading channels. A variety of simulations are performed and show that they match exactly with analytic ones. In addition, our results show that the optimum number of relays depend not only on channel conditions (operating SNRs) but also on modulation schemes which to be used.