• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.123-128
• /
• 2019

This paper proposes the stock price prediction based on the artificial intelligence, where the model with recurrent convolution neural network (RCNN) layers is adopted. In the motivation of this prediction, long short-term memory model (LSTM)-based neural network can make the output of the time series prediction. On the other hand, the convolution neural network provides the data filtering, averaging, and augmentation. By combining the advantages mentioned above, the proposed technique predicts the estimated stock price of next day. In addition, in order to emphasize the recent time series, a custom weighted loss function is adopted. Moreover, stock data related to the stock price index are adopted to consider the market trends. In the experiments, the proposed stock price prediction reduces the test error by 3.19%, which is over other techniques by about 19%.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.3 no.2
• /
• pp.21-25
• /
• 2015

Investment process on startup companies faces several difficulties based on the characteristics of this type of companies, such as lack of historical data, current operating losses and absence of comparable companies. In this paper we focus in a new methodology based on ordered weighted averaging (OWA) operators. OWA operators are useful instruments that enable the aggregation of information; in other words, from a data set we are able to obtain a single representative value of that set. The investment methodology presented consists on the application of OWA operators to the targeted startup companies based on the capacity of cash-flow generation and also on the planned scenario of future growth for each company. This paper shows that the methodology proposed can serve as a valuable tool, complementing the qualitative criteria (which, obviously, should not be ignored) for assessing and selecting a start-up investment.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.59 no.4
• /
• pp.401-404
• /
• 2010

In multibit Sigma-Delta Modulator, DWA(Data Weighted Averaging) among the DEM(Dynamic Element Matching) techniques was widely used to get rid of non-linearity that caused by mismatching of unit capacitor in feedback DAC path. this paper proposed the improved DWA architecture by adjusting clock timing of the existing DWA architecture. 2n Register block used for output was replaced with 2n S-R latch block. As a result of this, MOS Tr. can be reduced and extra clock can also be removed. Moreover, two n-bit Register block used to delay n-bit data code is decreased to one n-bit Register. In order to confirm characteristics, DWA for the 3-bit output with the proposed DWA architecture was designed on 0.18um process under 1.8V supply. Compared with the existing architecture. It was able to reduce the number of 222 MOS Tr.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1081-1086
• /
• 2008

This paper presents the $3^{rd}$ 4bit sigma delta modulator with the block and timing diagrams of DWA(Data Weighted Averaging) to optimize a operating time. In the modulator, the proposed DWA structure has a stable operation and timing margin so as to remove three latches and another clock. Because the modulator with proposed DWA structure improve timing margin about 23%. It can increase sampling frequency up to 244MHz. Through the MATLAB modeling, the optimized coefficients are obtained to design the modulator. The fully differential SC integrators, DAC, switch, quantizer, and DWA are designed by considering the nonideal characteristics. The designed $3^{rd}$ order 4bit modulator has a power consumption of 40mW and SNR(signal to noise ratio) of 77.2dB under 1.2V supply and 64MHz sampling frequency.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.75-78
• /
• 2003

In this paper, a second-order 3-bit DSM using DWA(Data Weighted Averaging) algorithm is designed for bluetooth Zero-IF Receiver. The designed circuit has two integrators using a designed OTA, nonoverlapping two-phase clerk generator, 3-bit A/D converter, DWA algorithm and 3-bit D/A converter An ideal model of second-order lowpass DSM with a 3-bit quantizer was configured by using MATLAB, and each coefficients and design specification of each blocks were determined to have 10-bit resolution in 1MHz channel bandwidth. The designed second-order 3-blt lowpass DSM has maximum SNR of 74dB and power consumption is 50mW at 3.3V.

• Proceedings of the KOSOMBE Conference
• /
• v.1993 no.05
• /
• pp.63-65
• /
• 1993

We have done a preliminary study on the detection of ventricular late potentials using high-resolution electrocardiography. We designed a battery powered low-noise ECG amplifier. We used the XYZ lead system and the amplifier provides 3 channels of X, Y, and Z signals with a conventional gain and another 3 channels of the amplitude-limited X, Y, and Z signals with high-gain. 12-bit data acquisition system interfaces the amplifiers to a personal computer for further signal analysis. Beat alignment algorithm was implemented on the low-gain signals to synchronize the signal averaging of the high-gain amplitude-limited signals. We suggest the use of the weighted vector sum of X', Y', and Z' signals based on the SNR of each channel. We speculate that this new method will increase the accuracy of the LP detector at the expense of more complicated hardware.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.105-111
• /
• 2017

In this paper, the analysis results are shown about several weights of Weighted K-Nearest Neighbor method, Recently, it is employed for the indoor positioning technologies using WiFi fingerprint which has been actively studied. In spite of the simplest feature, the W-KNN method shows comparable performance to another methods using WiFi fingerprint technology. So W-KNN method has employed in the existing indoor positioning system. It shows positioning error performance according to data preprocessing and weight factor, and the analysis on the weight is very important. In this paper, based on the real measured WiFi fingerprint data, the estimation error is analyzed and the performances are compared, for the case of data processing methods, of the weight of average, variance, and distance, and of the averaging several position of number K. These results could be practically useful to construct the real indoor positioning system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4584-4599
• /
• 2021

In IEEE 802.11p-based wireless access in vehicular environments (WAVE) communication systems, channel estimation (CE) is one of the important issues to provide stable communication service. It is hard to apply conventional CE schemes based on data pilot to real systems, because error propagation occurs in high mobility and modulation order environments, resulting in degrading the CE performance. In this paper, we propose one data pilot using multiple receive antennas (ODPM) CE scheme based on the weighted sum using update matrix (WSUM) with time-domain averaging (TDA) to overcome this problem. Within the process of WSUM-TDA in the proposed scheme, the maximum ratio combining (MRC) technique is applied so as to create more accurate one data pilot. Moreover, a new reliability test criterion is proposed as the fashion of utilizing MRC, which makes it possible to apply selective TDA that guarantees performance improvement. In simulation results, the packet error rate (PER) performance of the proposed ODPM is compared with that of conventional CE methods and its superiority is demonstrated.

• Journal of environmental and Sanitary engineering
• /
• v.9 no.2
• /
• pp.1-7
• /
• 1994

Rainwater was collected in Seoul area from January 1991 to December 1993 (over 3years) and by the analysis of the chemical components contained in rainwater, investigated the components that effect on rainwater pH Through the above studies the following conclusions were obtained. 1) Method for Averaging pH Volume weighted method is considered to be acceptable providing that precipitation is measured at the same time when the samples are taken, without precipitation data a simple averaging method should be the next choice. 2) Annual average rainwater pH was 4.98 in 1991, 4.80 in 1992, 4.67 in 1993, measurement range was 3.6-8.1. 3) In the relationship between rainwater pH and rainfall amounts rainwater pH for light rain(<15mm rainfall) was existent in the wide range(pH 4-7), but for heavy rain was corresponded to the annual average values. 4) Annual frequency of pH was Birrndat the frequency($\gamma $) between the density of the [$H^{+}$] and pH in the rainwater(over 3years ), $NO_{3}^{-}$ was excellent and the obtained results was 0.62 in 1992. Also In the correlation coefficient($\gamma $) according to the pH range $SO_{4}^{2-}, NO_{3}^{-}$, were 0.85 ,0.68 at 3.6 $Cl^-$ was 0.99(1993). At 4.1$NO_{3}^{-}(\gamma=0.48)$ in 1992, SO_4^{2-}($\gamma$=0.54), $NO_{3}^{-}(\gamma$=0.72), $Cl^- (\gamma$=0.49) in 1993. 6) pH values gradually increased with increase in $Ca^{2+}/SO_{4}^{2-}$.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.39 no.12
• /
• pp.965-973
• /
• 2015

Recently, an emission test procedure using a portable emissions measurement system(PEMS) has received much attention as an effective means of controlling real driving emissions from light-duty diesel vehicles. The PEMS-based test procedure will be implemented from 2017 in Europe and Korea as a complementary test procedure for certification and regulation. In the present study, on-road NOx emissions were measured for four kinds of Euro 5 Korean light-duty diesel vehicles under real driving conditions, including urban, rural, and motorway test routes. The real driving emission characteristics were evaluated using both a moving averaging window(MAW) and the weighted emission method(WEM). The evaluated NOx emission results (under real driving conditions) from the MAW and WEM showed similar tendencies for the test vehicles and routes, while exceeding the certification emission limit by 1.8~8.5 and 2.0~10.6 times, respectively.