• Journal of Plant Biotechnology
• /
• v.34 no.3
• /
• pp.201-205
• /
• 2007

To determine whether pattern recognition based on metabolite fingerprinting for whole cell extracts of higher plants is applied to discriminate plants genetically, leaf samples of eight cultivars of Catharanthus roseus were subjected to Fourier transform infrared spectroscopy (FT-IR). FT-IR fingerprint region data were analyzed by principal component analysis (PCA). Major peaks as biomarkers were identified as the most significant contributors to distinguish samples by using genetic programming. A hierarchical dendrogram based on the results from PCA separated the eight cultivars into two major groups in the same manner as the dendrograms based on genetic fingerprinting methods such as RAPD and AFLP. A slight difference between the dendrograms was found only in branching pattern within each subgroup. Therefore, we conclude that the hierarchical dendrogram based on PCA of the FT-IR data represents the most probable chemotaxonomical relationship between cultivars, which is in general agreement with the genetic relationship determined by conventional DNA fingerprinting methods.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.450-453
• /
• 2006

Hydrographic data including particulate organic carbon (POC) from the Northeastern Gulf of Mexico (NEGOM) study were used along with remotely sensed data obtained from NASA's Sea-viewing Wide Field-of-view Sensor (SeaWiFS) to develop POC algorithms to estimate POC concentration based on empirical and model-based principal component analysis (PCA) methods. In Case I and II waters empirical maximized simple ratio (MSR) and model-based PCA algorithms using full wavebands (blue, green and red wavelengths) provide more robust estimates of POC. The predicted POC concentrations matched well the spatial and seasonal distributions of POC measured in situ in the Gulf of Mexico. The ease in calculating the MSR algorithm compared to PCA analysis makes MSR the preferred algorithm for routine use. In order to determine the inter-annual variations of POC, MSR algorithms applied to calculate 100 monthly mean values of POC concentrations (September 1997-December 2005). The spatial and temporal variations of POC and sea surface temperature (SST) were analyzed with the empirical orthogonal function (EOF) method. POC estimates showed inter-annual variation in three different locations and may be affected by El $Ni{\tilde{n}}o/Southern$ Oscillation (ENSO) events.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2161-2166
• /
• 2015

This paper analyzes the straight line detection using the principal component analysis (PCA) and proposes its improved algorithm to which two new functions are added. The first function removes invalid pixels through the detected straight line and detects a line again. The second function detects lines from non-overlapped blocks, selects valid line candidates, and detects a valid line from pixels adjacent to each line candidate. The proposed algorithm detects a more accurate straight line with a low computation in comparison with the conventional algorithm in an image with somewhat refined lines.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.711-716
• /
• 2003

This paper proposes the method to select the number of optimal mixtures in each state in Continuous Density HMM (Hidden Markov Models), Previously, researchers used the same number of mixture components in each state of HMM regardless spectral characteristic of speaker, To model each speaker as accurately as possible, we propose to use a different number of mixture components for each state, Selection of mixture components considered the probability value of mixture by each state that affects much parameter estimation of continuous density HMM, Also, we use PCA (principal component analysis) to reduce the correlation and obtain the system' stability when it is reduced the number of mixture components, We experiment it when the proposed method used average 10% small mixture components than the conventional HMM, When experiment result is only applied selection of mixture components, the proposed method could get the similar performance, When we used principal component analysis, the feature vector of the 16 order could get the performance decrease of average 0,35% and the 25 order performance improvement of average 0.65%.

• Journal of Korea Game Society
• /
• v.13 no.2
• /
• pp.59-70
• /
• 2013

Although the history of the game of Go is more than 2,500 years, the theoretical studies of Go are still insufficient. In recent years a lot of studies using Artificial Intelligent(AI) have been conducted, but they do not provide the prominent theoretical reality. We applied Principal Component Analysis(PCA) to the professional Go openings, which are the early stage in Go, to analyze them especially focused on the Go game records of the professional 9-dan player Lee Sedol who is the world's top professional Go player. The results showed that among the 361 eigenvectors the 48 most significant eigenvectors capture most of the variance (99.9%) and the 30 most significant eigenvectors enable to possess 90.5 percent of the total variance. This result would be expected to considerably contribute to pattern recognition research of the professional Go openings in the near future.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12
• /
• pp.248-256
• /
• 2021

Now that we're in the big data era, data has taken on a new significance as the storage capacity has exploded from trillion bytes to petabytes at breakneck pace. As the use of cloud computing expands and becomes more commonly accepted, several businesses and institutions are opting to store their requests and data there. Cloud storage's concept of a nearly infinite storage resource pool makes data storage and access scalable and readily available. The majority of them, on the other hand, favour a single cloud because of the simplicity and inexpensive storage costs it offers in the near run. Cloud-based data storage, on the other hand, has concerns such as vendor lock-in, privacy leakage and unavailability. With geographically dispersed cloud storage providers, multicloud storage can alleviate these dangers. One of the key challenges in this storage system is to arrange user data in a cost-effective and high-availability manner. A multicloud storage architecture is given in this study. Next, a multi-objective optimization problem is defined to minimise total costs and maximise data availability at the same time, which can be solved using a technique based on the non-dominated sorting genetic algorithm II (NSGA-II) and obtain a set of non-dominated solutions known as the Pareto-optimal set.. When consumers can't pick from the Pareto-optimal set directly, a method based on Principal Component Analysis (PCA) is presented to find the best answer. To sum it all up, thorough tests based on a variety of real-world cloud storage scenarios have proven that the proposed method performs as expected.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.1
• /
• pp.71-79
• /
• 2009

Currently much research is being done on host based intrusion detection using system calls which is a portion of kernel based data. Sequence based and frequency based preprocessing methods are mostly used in research for intrusion detection using system calls. Due to the large amount of data and system call types, it requires a significant amount of preprocessing time. Therefore, it is difficult to implement real-time intrusion detection systems. Despite this disadvantage, the frequency based method which requires a relatively small amount of preprocessing time is usually used. This paper proposes an effective method for detecting denial of service attacks using the frequency based method. Principal Component Analysis(PCA) will be used to select the principle system calls and a bayesian network will be composed and the bayesian classifier will be used for the classification.

• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.94-99
• /
• 2021

Atopic dermatitis (AD), a chronic inflammatory skin disease, is characterized by itchy and age-dependent lesions. Previous studies have shown that pulsed electromagnetic field (PEMF) significantly improved chronic ulcers and ununited fractures, providing an evidence for the application of PEMF in resolving inflammation caused by AD. This study investigated the anti-inflammatory effect of PEMF on DNCB-induced AD in animal models. Five male hairless mice (6 weeks old) per group were assigned to a normal group, a sham group, and two PEMF groups (15Hz, 75Hz). Mice were treated with 2,4-Dinitrochlorobenzene (DNCB) to induce uniform AD among all groups excluding a normal group. To examine the inflammatory progress and the improvement of AD after the PEMF stimulation, images are taken with various cameras for non-invasive evaluation and the results are expressed using principal component analysis (PCA) for visualization. The results of this study demonstrated that PEMF effectively improved skin lesions without the use of drugs.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.598-601
• /
• 2004

In this paper, we suggest method that change odors to digital data. For this, we selected emotional adjective of odors as olfactory receptor This emotional adjective(expressional receptor) is about 40. Each odors are expressed by adjective equivalent to oneself. Expressed odors as emotional receptor is encoded as proposed method for transmission, and after transmission, It should be decoded for expression again. The applied decoding method is fuzzy c-means clustering algorithm(FCMA). But, because odor data is expressed to 40 dimensions, FCMA uses a lot of computing times and memories. To solve this problem, after we reduce dimension through principal component analysis(PCA), we use FCMA algorithm.