• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.135-147
• /
• 2001

This study proposes bankruptcy prediction model using fuzzy neural networks. Neural networks offer preeminent learning ability but they are often confronted with the inconsistent and unpredictable performance for noisy financial data. The existence of continuous data and large amounts of records may pose a challenging task to explicit concepts extraction from the raw data due to the huge data space determined by continuous input variables. The attempt to solve this problem is to transform each input variable in a way which may make it easier fur neural network to develop a predictive relationship. One of the methods selected for this is to map each continuous input variable to a series of overlapping fuzzy sets. Appropriately transforming each of the inputs into overlapping fuzzy membership sets provides an isomorphic mapping of the data to properly constructed membership values, and as such, no information is lost. In addition, it is easier far neural network to identify and model high-order interactions when the data is transformed in this way. Experimental results show that fuzzy neural network outperforms conventional neural network for the prediction of corporate bankruptcy.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.179-188
• /
• 2005

Much research for spatial join has been extensively studied over the last decade. In this paper, we focus on the filtering step of candidate objects for spatial join operations on the input tables that none of the inputs is indexed. In this case, many algorithms has presented and showed excellent performance over most spatial data. However, if data sets of input table for the spatial join ale skewed, the join performance is dramatically degraded. Also, little research on solving the problem in the presence of skewed data has been attempted. Therefore, we propose a spatial hash strip join (SHSJ) algorithm that combines properties of the existing spatial hash join (SHJ) algorithm based on spatial partition for input data set's distribution and SSSJ algorithm. Finally, in order to show SHSJ the outperform in uniform/skew cases, we experiment SHSJ using the Tiger/line data sets and compare it with the SHJ algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.12
• /
• pp.1345-1352
• /
• 2014

Bus architecture of SoC has been replaced by NoC in recent years. Noc uses the multi-clock domains to transmit and receive data between neighbor network interfaces and they have same frequency, but a phase difference because of clock skew. So a synchronizer is used for a mesochronous frequency in interconnection between network interfaces. In this paper the metastability is defined and analyzed in a D latch and a D flip-flop to search the possibilities that data can be lost in the process of sending and receiving data between interconnects when a local frequency and a transmitted frequency have a phase difference. 180nm CMOS model parameter and 1GHz are used to simulate them in HSpice. The simulation results show that the metastability happens in a latch and a flip-flop when input data change near the clock edges and there are intermediate states for a longer time as input data change closer at the clock edge. And the next stage can lose input data depending on environmental conditions such as temperature, processing variations, power supply, etc. The simulation results are very useful to design a mescochronous synchronizer for NoC.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.205-211
• /
• 2019

Steganalysis is a technique that aims to detect and recover data hidden by steganography. Steganalytic methods detect hidden data by analyzing visual and statistical distortions caused during data embedding. However, for recovering the hidden data, they need to know which steganographic methods the hidden data has been embedded by. Therefore, we propose a hierarchical convolutional neural network (CNN) structure that identifies a steganographic method applied to an input image through multi-level classification. We trained four base CNNs (each is a binary classifier that determines whether or not a steganographic method has been applied to an input image or which of two different steganographic methods has been applied to an input image) and connected them hierarchically. Experimental results demonstrate that the proposed hierarchical CNN structure can identify four different steganographic methods (LSB, PVD, WOW, and UNIWARD) with an accuracy of 79%.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.299-307
• /
• 2012

Data mining is a method of searching for an interesting relationship among items in a given database. The decision tree is a typical algorithm of data mining. The decision tree is the method that classifies or predicts a group as some subgroups. In general, when researchers create a decision tree model, the generated model can be complicated by the standard of model creation and the number of input variables. In particular, if the decision trees have a large number of input variables in a model, the generated models can be complex and difficult to analyze model. When creating the decision tree model, if there are marginally conditional variables (intervening variables, external variables) in the input variables, it is not directly relevant. In this study, we suggest the method of creating a decision tree using marginally conditional variables and apply to actual data to search for efficiency.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.275-283
• /
• 2018

Cancer show distinct pattern of gene expression when it is compared to normal. This difference results malignant characteristic of cancer. Many cancer drugs are targeting this difference so that it can selectively kill cancer cells. One of the recent demand for personalized treating cancer is retrieving normal tissue from a patient so that the gene expression difference between cancer and normal be assessed. However, in most clinical situation it is hard to retrieve normal tissue from a patient. This is because biopsy of normal tissues may cause damage to the organ function or a risk of infection or side effect what a patient to take. Thus, there is a challenge to estimate normal cell's gene expression where cancers are originated from without taking additional biopsy. In this paper, we propose in-silico based prediction of normal cell's gene expression from gene expression data of a tumor sample. We call this challenge as reverting the cancer into normal. We divided this challenge into two parts. The first part is making a generator that is able to fool a pretrained discriminator. Pretrained discriminator is from the training of public data (9,601 cancers, 7,240 normals) which shows 0.997 of accuracy to discriminate if a given gene expression pattern is cancer or normal. Deceiving this pretrained discriminator means our method is capable of generating very normal-like gene expression data. The second part of the challenge is to address whether generated normal is similar to true reverse form of the input cancer data. We used, cycle-consistent adversarial networks to approach our challenges, since this network is capable of translating one domain to the other while maintaining original domain's feature and at the same time adding the new domain's feature. We evaluated that, if we put cancer data into a cycle-consistent adversarial network, it could retain most of the information from the input (cancer) and at the same time change the data into normal. We also evaluated if this generated gene expression of normal tissue would be the biological reverse form of the gene expression of cancer used as an input.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.47-57
• /
• 2021

Neuromorphic technology is proposed to complement the shortcomings of existing artificial intelligence technology by mimicking the human brain structure and computational process with hardware. NA-IDE has also been proposed for developing neuromorphic hardware-based IoT applications. To implement an SNN model in NA-IDE, commonly used input data must be transformed for use in the SNN model. In this paper, we implemented a neural coding method encoder component that converts image data into a spike train signal and uses it as an SNN input. The decoder component is implemented to convert the output back to image data when the SNN model generates a spike train signal. If the decoder component uses the same parameters as the encoding process, it can generate static data similar to the original data. It can be used in fields such as image-to-image and speech-to-speech to transform and regenerate input data using the proposed encoder and decoder.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.5
• /
• pp.94-102
• /
• 2012

Recently, the global financial crisis and the increasing number of unsold houses in Korea are construction companies to assess their efficiency. The most important factor in analyzing the efficiency of a company is the input-output variable. However, systematic stud the core input-output variables, which have a great influence on the efficiency analysis. Thus, to the core input-output variables for efficiency analysis of construction companies, this study propose a model that includes all combinations of input-output variables and to find the core input-output variables using the Data Envelopment Analysis(DEA) model and Principal Component Analysis(PCA). Existing research and theories were studied variables and 21 models were established to measure efficiency. were obtained that the core input and output variable in 2006 the number of employees and sales. For 2008, the core input variable was capital stock and the core output variable was quarterly net profit. For 2010, the core input variable was fixed asset and the core output variable was sales. Through obtaining the variables that greatly affect the efficiency of construction companies, it is considered that individual construction companies will be able to prepare a priority strategy to enhance efficiency.

• Journal of Acupuncture Research
• /
• v.17 no.1
• /
• pp.89-105
• /
• 2000

In order to obtain the clinical data on the different effects of the three different methods of indirect moxibustion, moxa-combustion time, peak temperature, average temperature, maximum gradient temperature, average gradient temperature, and moxa-combustion calorie rate of the input period in ARIRANG, JANG, PUNG were measured through this experiment. The results of the experiment were as follows : 1. In the combustion time, during the input period ARIRANG had the longest combustion time followed by PUNG, JANG in a descending order but these were not acknowledged to have significant difference each other. 2. In the peak temperature of the input period, PUNG had the highest temperature followed by ARIRANG, JANG in a descending order. ARIRANG and JANG were acknowledged to have significant difference with PUNG. ARIRANG and JANG however were not acknowledged to have difference each other. 3. In the average temperature, during the input period, PUNG had the highest temperature followed by JANG, ARIRANG in a descending order. ARIRANG and JANG were acknowledged to have significant difference with PUNG. ARIRANG and JANG however were not acknowledged to have difference each other. 4. In the maximum gradient temperature, during the input period, PUNG had the highest temperature followed by ARIRANG, JANG in a descending order. ARIRANG and JANG were acknowledged to have significant difference with PUNG. ARIRANG and JANG however were not acknowledged to have difference each other. 5. In the average gradient temperature, during the input period, PUNG had the highest temperature followed by ARIRANG, JANG in a descending order. ARIRANG and JANG were acknowledged to have significant difference with PUNG. ARIRANG and JANG however were not acknowledged to have difference each other. 6. In the moxa-combustion calorie rate, during the input period, JANG had the highest temperature followed by ARIRANG, PUNG in a descending order. ARIRANG and PUNG were acknowledged to have significant difference with JANG. ARIRANG and PUNG however were not acknowledged to have difference each other.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.265-267
• /
• 2004

A blind separation problem in a multiple-input-multiple-output (MIMO) linear time-invariant (LTI) system with finite-alphabet inputs is considered. A discrete-time matrix equation model is used to describe the input-output relation of the system in order to make full use of the advantages of modern digital signal processing techniques. At first, ambiguity problem is investigated. Then, based on the results of the investigation, a new identifiability condition is proposed for the case of an input-data set which is widely used in digital communication. A probability bound such that an arbitrary input matrix satisfies the identifiability condition is derived. Finally, Monte-Carlo simulation is performed to demonstrate the validity of our suggestions.