• Journal of Cadastre & Land InformatiX
• /
• v.48 no.2
• /
• pp.79-98
• /
• 2018

The purpose of this study is to suggest a model analysing spatio-temporal characteristics of the civil complaints for the officially assessed land price based on big data mining. Specifically, in this study, the underlying reasons for the civil complaints were found from the spatio-temporal perspectives, rather than the institutional factors, and a model was suggested monitoring a trend of the occurrence of such complaints. The official documents of 6,481 civil complaints for the officially assessed land price in the district of Jung-gu of Incheon Metropolitan City over the period from 2006 to 2015 along with their temporal and spatial poperties were collected and used for the analysis. Frequencies of major key words were examined by using a text mining method. Correlations among mafor key words were studied through the social network analysis. By calculating term frequency(TF) and term frequency-inverse document frequency(TF-IDF), which correspond to the weighted value of key words, I identified the major key words for the occurrence of the civil complaint for the officially assessed land price. Then the spatio-temporal characteristics of the civil complaints were examined by analysing hot spot based on the statistics of Getis-Ord $Gi^*$. It was found that the characteristic of civil complaints for the officially assessed land price were changing, forming a cluster that is linked spatio-temporally. Using text mining and social network analysis method, we could find out that the occurrence reason of civil complaints for the officially assessed land price could be identified quantitatively based on natural language. TF and TF-IDF, the weighted averages of key words, can be used as main explanatory variables to analyze spatio-temporal characteristics of civil complaints for the officially assessed land price since these statistics are different over time across different regions.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.7
• /
• pp.1296-1306
• /
• 2015

Nowadays the research of energy saving on the IP networks have been studied the various methods in many research institutes. This paper suggests the energy saving method in IP networks which have the various energy profiles, and analyzes its energy saving characteristics in detail. Especially this paper proposes the energy profile based OSPF routing method which have the selectable weighted value in OSPF metric and energy consumption in IP network. This paper analyzes the energy saving effects of the various situations to minimize the energy consumption using the various weighted value on the proposed scheme. The results show that the energy saving efficiency can get about 67% at in ingress input load ${\rho}=0.5$ by using random energy profiles in IP networks. Although the number of hops is a slight increased due to routing the paths for the minimum energy consumption in the algorithm of this method, the increment hop number is limited the mean 1.4 hops. This paper confirms that the energy profile of core router has the large effects of energy saving than the energy profile of edge router, and the proposed method has the excellent energy saving characteristics in IP networks.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.326-334
• /
• 2022

In this paper, we propose speech enhancement algorithm as a pre-processing for robust speech recognition in noisy environments. Auxiliary-function-based Independent Vector Analysis (AuxIVA) is performed with weighted covariance matrix using time-varying variances with scaling factor from target masks representing time-frequency contributions of target speech. The mask estimates can be obtained using Neural Network (NN) pre-trained for speech extraction or diffuseness using Coherence-to-Diffuse power Ratio (CDR) to find the direct sounds component of a target speech. In addition, outputs for omni-directional noise are closely chained by sharing the time-varying variances similarly to independent subspace analysis or IVA. The speech extraction method based on AuxIVA is also performed in Independent Low-Rank Matrix Analysis (ILRMA) framework by extending the Non-negative Matrix Factorization (NMF) for noise outputs to Non-negative Tensor Factorization (NTF) to maintain the inter-channel dependency in noise output channels. Experimental results on the CHiME-4 datasets demonstrate the effectiveness of the presented algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.17-26
• /
• 2023

In this paper, we propose a several smoothing techniques are compared and applied to increase the application of the LSTM-based learning model and its effectiveness. The applied smoothing technique is Savitky-Golay, exponential smoothing, and weighted moving average. Through this study, the LSTM algorithm with the Savitky-Golay filter applied in the preprocessing process showed significant best results in prediction performance than the result value shown when applying the LSTM model to Bitcoin data. To confirm the predictive performance results, the learning loss rate and verification loss rate according to the Savitzky-Golay LSTM model were compared with the case of LSTM used to remove complex factors from Bitcoin price prediction, and experimented with an average value of 20 times to increase its reliability. As a result, values of (3.0556, 0.00005) and (1.4659, 0.00002) could be obtained. As a result, since crypto-currencies such as Bitcoin have more volatility than stocks, noise was removed by applying the Savitzky-Golay in the data preprocessing process, and the data after preprocessing were obtained the most-significant to increase the Bitcoin prediction rate through LSTM neural network learning.

• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.989-998
• /
• 2018

Connectivity between water source and demand node can be served as a critical system performance indicator of the degree of water distribution network (WDN)' failure severity under abnormal conditions. Graph theory-based approaches have been widely applied to quantify the connectivity due to WDN's graph-like topological feature. However, most previous studies used undirected-unweighted graph theory which is not proper to WDN. In this study, the directed-weighted graph theory was applied for WDN connectivity analyses. We also proposed novel connectivity indicators, Source-to-Node Shortest Pathway (SNSP) and SNSP-Degree (SNSP-D) which is an inverse of the SNSP value, that does not require complicate hydraulic simulation of a WDN of interest. The proposed SNSP-D index was demonstrated in total 42 networks in J City, South Korea in which Pearson Correlation Coefficient (PCC) between the proposed SNSP-D and four other system performance indicators was computed: three resilience indexes and an energy efficiency metric. It was confirmed that a system representative value of the SNSP-D has strong correlation with all resilience and energy efficiency indexes (PCC = 0.87 on average). Especially, PCC was higher than 0.93 with modified resilience index (MRI) and energy efficiency indicator. In addition, a multiple linear regression analysis was performed to identify the system hydraulic characteristic factors that affect the correlation between SNSP-D and other system performance indicators. The proposed SNSP is expected to be served as a useful surrogate measure of resilience and/or energy efficiency indexes in practice.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.4
• /
• pp.851-868
• /
• 2012

After the financial crisis in 2008, the financial market still seems to be unstable with expanding the insolvency of the financial companies' real estate project financing loan in the aftermath of the lasted real estate recession. Especially after the illegal actions of people's financial institutions disclosed, while increased the anxiety of economic subjects about financial markets and weighted in the confusion of financial markets, the potential risk for the overall national economy is increasing. Thus as economic recession prolongs, the people's financial institutions having a weak profit structure and financing ability commit illegal acts in a variety of ways in order to conceal insolvent assets. Especially it is hard to find the loans of shareholder and the same borrower sharing credit risk in advance because most of them usually use a third-party's name bank account. Therefore, in order to effectively detect the fraud under other's name, it is necessary to analyze by clustering the borrowers high-related to a particular borrower through an analysis of association between the whole borrowers. In this paper, we introduce Analysis Techniques for detecting financial loan frauds in advance through an analysis of association between the whole borrowers by extending SNA(social network analysis) which is being studied by focused on sociology recently to the forensic accounting field of the financial frauds. Also this technique introduced in this pager will be very useful to regulatory authorities or law enforcement agencies at the field inspection or investigation.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.373-380
• /
• 2022

This paper presents a deep learning based group synchronization that supports networked immersive interactions between remote users. The goal of group synchronization is to enable all participants to synchronously interact with others for increasing user presence Most previous methods focus on NTP-based clock synchronization to enhance time accuracy. Moving average filters are used to control media playout time on the synchronization server. As an example, the exponentially weighted moving average(EWMA) would be able to track and estimate accurate playout time if the changes in input data are not significant. However it needs more time to be stable for any given change over time due to codec and system loads or fluctuations in network status. To tackle this problem, this work proposes the Deep Group Synchronization(DeepGroupSync), a group synchronization based on deep learning that models important features from the data. This model consists of two Gated Recurrent Unit(GRU) layers and one fully-connected layer, which predicts an optimal playout time by utilizing the sequential playout delays. The experiments are conducted with an existing method that uses the EWMA and the proposed method that uses the DeepGroupSync. The results show that the proposed method are more robust against unpredictable or rapid network condition changes than the existing method.

• Journal of Wetlands Research
• /
• v.24 no.1
• /
• pp.44-51
• /
• 2022

In this study, TOPSIS(Techniques for Order Performance by Similarity to Ieal Solution) was used to evaluate the installation points of water quality monitoring networks in 34 streams of the Nakdong River watershed. The Nakdong River System has been measuring water quality and flow in 195 local streams since 2011. In particular, the 34 key management points are areas with many pollutants and poor water quality, requiring continuous water quality management. For the selection of points requiring management, 10 indicators were selected for evaluation, and the selected indicators were standardized and weighted using the entropy method. As a result of weight calculation, the presence or absence of a nearby measuring network received the greatest weight, and the average water quality and presence of an industrial complex obtained the highest weight. The evaluated data are judged to be the research results necessary for the establishment of a new water quality measurement network in the Nakdong River system and continuous water quality management in tributaries.