• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.78-86
• /
• 1999

In this paper, a distributed arithmetic digital neural network with learning and testing phase implemented in a body has been studied. The proposed technique is based on the two facts; one is that the weighting coefficients adjusted will be stored in registers without shift, because input values or input patterns are not changed while learning and the other is that the input patterns stored in registers are not changed while testing. The proposed digital neural network is simulated by hardware description language such as VHDL and verified the performance that the neural network was applied to the recognition of seven-segment. To verify proposed neural networks, we compared the learning process of modified perceptron learning algorithm simulated by software with VHDL for 7-segment number recognizer. The results are as follows: There was a little difference in learning time and iteration numbers according to the input pattern, but generally the iteration numbers are 1000 to 10000 and the learning time is 4 to 200$\mu\textrm{s}$. So we knew that the operation of the neural network is learned in the same way with the learning of software simulation, and the proposed neural networks are properly operated. And also the implemented neural network can be built with less amounts of components compared with board system neural network.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.9
• /
• pp.31-39
• /
• 2011

In this paper, we propose a signal readout system with small area and low power consumption for CNT sensor arrays. The proposed system consists of signal readout circuitry, a digital controller, and UART I/O. The key components of the signal readout circuitry are 64 transimpedance amplifiers (TIA) and SAR-ADC with 11-bit resolution. The TIA adopts an active input current mirror (AICM) for voltage biasing and current amplification of a sensor. The proposed architecture can reduce area and power without sampling rate degradation because the 64 TIAs share a variable gain amplifier (VGA) which needs large area and high power due to resistive feedback. In addition, the SAR-ADC is designed for low power with modified algorithm where the operation of the lower bits can be skipped according to an input voltage level. The operation of ADC is controlled by a digital controller based on UART protocol. The data of ADC can be monitored on a computer terminal. The signal readout circuitry was designed with 0.13${\mu}m$ CMOS technology. It occupies the area of 0.173 $mm^2$ and consumes 77.06${\mu}W$ at the conversion rate of 640 samples/s. According to measurement, the linearity error is under 5.3% in the input sensing current range of 10nA - 10${\mu}A$. The UART I/O and the digital controller were designed with 0.18${\mu}m$ CMOS technology and their area is 0.251 $mm^2$.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4475-4481
• /
• 2014

A histogram equalization method have been used traditionally for the image enhancement of low quality images. This uses the transformation function, which is a cumulative density function of an input image, and it has mathematically maximum entropy. This method, however, may yield whitening artifacts. This paper proposes the weighted histogram equalization method based on histogram equalization. It has Weber-Fechner's law for a human's vision characteristics, and a dynamic range modification to solve the problem of some methods, which yield a transformation function, regardless of the input image. Finally, the proposed transformation function was calculated using the weighted average of Weber-Fechner and the histogram equalization transformation functions in a modified dynamic range. The simulation results showed that the proposed algorithm effectively enhances the contrast in terms of the subjective quality. In addition, the proposed method has similar or higher entropy than the other conventional approaches.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.2 s.105
• /
• pp.110-116
• /
• 2006

In this paper the algorithm of a methodology for the calculation of spectrum requirements was implemented. As well, the influence of traffic distribution ratio among radio access technology groups, spectral efficiency, and flexible spectrum usage(FSU) margin was analyzed in terms of the spectrum requirements, with a view toward for future development of IMT-2000 and systems beyond IMT-2000. The ratio of the spectrum requirement to the traffic distribution ratio is approximately $1\;GHz/20\;\%$, and the spectrum requirement varies from 5 to 9 GHz. As the FSU margin increases by 1.0 dB, the total spectrum requirement decreases by 0.9 dB. The required spectrum for the market input parameter, ${\rho}=0.5$ is 801.63 MHz, while the required spectrum for ${\rho}=1.0$ is 6295.4 MHz. It can be concluded that the market input parameter is the most effective parameter in the calculation of spectrum requirements.

• Fire Science and Engineering
• /
• v.27 no.6
• /
• pp.77-82
• /
• 2013

This research suggested smart fire recognition system which trances firing location with CCD camera with wired/wire-less TCP/IP function and Pan/Tilt function, delivers information in real time to android system installed by smart mobile communication system and controls fire and disaster remotely. To embody suggested method, firstly, algorithm which applies hue saturation intensity (HSI) Transform for input video, eliminates surrounding lightness and unnecessary videos and segmentalized only firing videos was suggested. Secondly, Pan/Tilt function traces accurate location of firing for proper control of firing. Thirdly, android communication system installed by mobile function confirms firing state and controls it. To confirm the suggested method, 10 firing videos were input and experiment was conducted. As the result, all of 10 videos segmentalized firing sector and traced all of firing locations.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1058-1065
• /
• 2014

In order to assist user's who are in the process of executing a search, a query expansion method suggests keywords that are related to an input query. Recently, several studies have suggested keywords that are identified by finding domains using a clustering method over the documents that are retrieved. However, the clustering method is not relevant when presenting various domains because the number of clusters should be fixed. This paper proposes a method that suggests keywords by finding various domains related to the input queries by using a community detection algorithm. The proposed method extracts words from the top-30 documents of those that are retrieved and builds communities according to the word graph. Then, keywords representing each community are derived, and the represented keywords are used for the query expansion method. In order to evaluate the proposed method, we compared our results to those of two baseline searches performed by the Google search engine and keyword recommendation using TF-IDF in the search results. The results of the evaluation indicate that the proposed method outperforms the baseline with respect to diversity.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.104-109
• /
• 2017

We propose a new machine learning algorithm which analyzes daily activity patterns of users from multi-modal wearable sensor data. The proposed model learns and extracts activity patterns using input from wearable devices in real-time. Inspired by cue integration of human's property, we constructed gated multi-modal neural networks which integrate wearable sensor input data selectively by using gate modules. For the experiments, sensory data were collected by using multiple wearable devices in restaurant situations. As an experimental result, we first show that the proposed model performs well in terms of prediction accuracy. Then, the possibility to construct a knowledge schema automatically by analyzing the activation patterns in the middle layer of our proposed model is explained.

• Journal of Communications and Networks
• /
• v.5 no.2
• /
• pp.157-166
• /
• 2003

This paper deals with the problem of channel identification for Single Input Multiple Output (SIMO) slow fading channels using clustering algorithms. Due to the intrinsic memory of the discrete-time model of the channel, over short observation periods, the received data vectors of the SIMO model are spread in clusters because of the AWGN noise. Each cluster is practically centered around the ideal channel output labels without noise and the noisy received vectors are distributed according to a multivariate Gaussian distribution. Starting from the Markov SIMO channel model, simultaneous maximum ikelihood estimation of the input vector and the channel coefficients reduce to one of obtaining the values of this pair that minimizes the sum of the Euclidean norms between the received and the estimated output vectors. Viterbi algorithm can be used for this purpose provided the trellis diagram of the Markov model can be labeled with the noiseless channel outputs. The problem of identification of the ideal channel outputs, which is the focus of this paper, is then equivalent to designing a Vector Quantizer (VQ) from a training set corresponding to the observed noisy channel outputs. The Linde-Buzo-Gray (LBG)-type clustering algorithms [1] could be used to obtain the noiseless channel output labels from the noisy received vectors. One problem with the use of such algorithms for blind time-varying channel identification is the codebook initialization. This paper looks at two critical issues with regards to the use of VQ for channel identification. The first has to deal with the applicability of this technique in general; we present theoretical results for the conditions under which the technique may be applicable. The second aims at overcoming the codebook initialization problem by proposing a novel approach which attempts to make the first phase of the channel estimation faster than the classical codebook initialization methods. Sample simulation results are provided confirming the effectiveness of the proposed initialization technique.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.217-225
• /
• 2009

In case of sketching a conceptual model in 3D space, it's not easy for designer to recognize the depth cue accurately and to draw a model correctly in short time. In this paper, multi-strokes based sketch is adopted not only to reduce the error of input point but to substantiate the shape o) the conceptual design effectively. The designer can see the drawing result immediately after stroking some curves. The shape can also be modified by stroking curves repeatedly and be confirmed the modified shape in real time. However, the multi-strokes based sketch needs to manage the great amount of input data. Therefore, the drawing space is divided into the limited spatial cubical grids and the movable infernal vertex in each spatial grid is implemented and used to define the surface by the multi-strokes. We implemented the spatial sketching system which allows the concept designer's intention to 3D model data efficiently.