• Asia pacific journal of information systems
• /
• v.7 no.1
• /
• pp.67-83
• /
• 1997

The utility of learning techniques in investment analysis has been demonstrated in many areas, ranging from forecasting individual stocks to entire market indexes. To date, however, the application of artificial intelligence to financial forecasting has focused largely on short predictive horizons. Usually the forecast window is a single period ahead; if the input data involve daily observations, the forecast is for one day ahead; if monthly observations, then a month ahead; and so on. Thus far little work has been conducted on the efficacy of long-term prediction involving multiperiod forecasting. This paper examines the impact of alternative procedures for extended prediction using knowledge discovery techniques. One dimension in the study involves temporal granularity: a single jump from the present period to the end of the forecast window versus a web of short-term forecasts involving a sequence of single-period predictions. Another parameter relates to the numerosity of input variables: a technical approach involving only lagged observations of the target variable versus a fundamental approach involving multiple variables. The dual possibilities along each of the granularity and numerosity dimensions entail a total of 4 models. These models are first evaluated using neural networks, then compared against a multi-input jump model using case based reasoning. The computational models are examined in the context of forecasting the S&P 500 index.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.18-22
• /
• 2013

Input impedance of the inverted L antenna which is modified from a monopole antenna varies to very high input impedance value when the ratio of vertical height to horizontal length is reduced. So its impedance matching becomes very difficult. In this paper, we analyzed the input impedance variation range depending on the ratio of vertical height to horizontal length in the normal and ferrite thin film added configuration for the input impedance control. For the exact analysis involving the permittivity, permeability and conductivity of ferrite material, FDTD numerical method is used.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.25 no.1
• /
• pp.11-26
• /
• 2007

In this paper, an experiment was done where the input device used the linear multiple regression and the sRGB color space to perform a color transformation. The output device used the GOG, GOGO and sRGB for the color transformation. After the input device underwent a color transformation, a $3\;{\times}\;20\;size$ matrix was used in a linear multiple regression and the scanner's color representation of scanner was better than a digital still camera's color representation. When using the sRGB color space, the original copy and the output copy had a color difference of 11. Therefore it was more efficient to use the linear multiple regression method than using the sRGB color space. After the input device underwent a color transformation, the additivity of the LCD monitor's R, G and B signal value improved and therefore the error in the linear formula transformation decreased. From this change, the LCD monitor with the GOG model applied to the color transformation became better than LCD monitors with other models applied to the color transformation. Also, the color difference varied more than 11 from the original target in CRT and LCD monitors when a sRGB color transformation was done in restricted conditions.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.19-33
• /
• 2001

Link weight analysis approach is suggested as a heuristic for selection of input nodes in artificial neural network for bankruptcy prediction. That is to analyze each input node\\\\`s link weight-absolute value of link weight between an input node and a hidden node in a well-trained neural network model. Prediction accuracy of three methods in this approach, -weak-linked-neurons elimination method, strong-linked-neurons selection method and integrated link weight model-is compared with that of decision tree and multivariate discrimination analysis. In result, the methods suggested in this study show higher accuracy than decision tree and multivariate discrimination analysis. Especially an integrated model has much higher accuracy than any individual models.

• The Korean Journal of Physiology and Pharmacology
• /
• v.13 no.3
• /
• pp.221-227
• /
• 2009

For successful restoration of visual function by a visual neural prosthesis such as retinal implant, electrical stimulation should evoke neural responses so that the informat.ion on visual input is properly represented. A stimulation strategy, which means a method for generating stimulation waveforms based on visual input, should be developed for this purpose. We proposed to use the decoding of visual input from retinal ganglion cell (RGC) responses for the evaluation of stimulus encoding strategy. This is based on the assumption that reliable encoding of visual information in RGC responses is required to enable successful visual perception. The main purpose of this study was to determine the influence of inter-dependence among stimulated RGCs activities on decoding accuracy. Light intensity variations were decoded from multiunit RGC spike trains using an optimal linear filter. More accurate decoding was possible when different types of RGCs were used together as input. Decoding accuracy was enhanced with independently firing RGCs compared to synchronously firing RGCs. This implies that stimulation of independently-firing RGCs and RGCs of different types may be beneficial for visual function restoration by retinal prosthesis.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.312-316
• /
• 2010

In this paper, we propose a game theoretic channel sharing model that allocates resources of a base station between MNO(Mobile Network Operator) and MVNO(Mobile Virtual Network Operator) in a fair and efficient manner. Considering the input traffic loads of MNO and MVNO, the proposed model uses the bargaining game theory to allocate channel resources between MNO and MNVO. When the input loads of the carriers are asymmetric, the proposed model increases the resource utilization by allocating more channel resources to the operator with high input load. In addition, the proposed model prevents the quality of service of an operator from degrading even if the input load of the other operators increases excessively.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.621-630
• /
• 2001

Recently, users' demands for multimedia service are increasing. But, server systems offer inefficient multimedia data service to users. In this paper, to transport multimedia data in the server system more efficiently, we propose the SRTPIO(Special RTP Input/Output) module that process the RTP(Real-time Transport Protocol) data in the kernel with the SIO(Special Input/Output) Mechanism. The SIO mechanism improve a transfer speed because it reduces overheads associated with data copying and context-switching between the user mode and the kernel mode occured in general server system in the kernel-level. The SRTPIO module, integrating the SIO mechanism and the RTP data processing in the kernel, support efficient multimedia data transfer architecture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.11
• /
• pp.2569-2574
• /
• 2012

HMS(Hull Mount Sonar) equipment mounted on PCC(Patrol Combat Corvette) is suitably designed for active mode, and the specific character of sensor or system is not appropriate for the frequency range to detect a torpedo. In this article, in order to implement the function of detecting torpedoes with HMS of existing PCC, I will analyze the feature of input signals each PCCs and design a circuit to compensate reversely for the input signal in certain frequency. And also, I will suggest the most adequate torpedo defense system suitable for the special operating environment and the characteristic of naval vessels, implementing functions such as AGC of input signal and fixing the frequency range of different input signals per different warships.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2378-2384
• /
• 2009

A novel phase-locked loop(PLL) architecture of sub-micron locking time has been proposed. Input frequency is multiplied by using a delay-locked loop(DLL). The input frequency of a PLL is multiplied while the PLL is out of lock. The multiplied input frequency makes the PLL having a wider loop bandwidth. It has been simulated with a $0.18{\mu}m$ 1.8V CMOS process. The simulated locking time is $0.9{\mu}s$ at 162.5MHz and 2.6GHz, input and output frequency, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.12A
• /
• pp.1136-1146
• /
• 2005

In this paper, the radiative electric field intensity due to the communication signal and conductive noise is calculated in overhead medium voltage power lines for power line communication. The input impedance is calculated by means of 2 port equivalent model of medium voltage power line network and basic transmission line theory. And then, currents is calculated by calculated input impedance and finally, the emissive electric field is calculated. The input impedance appears like a standing wave form with a fixed cycle because high reflection at the input terminal due to the characteristic impedance of medium voltage power line is very large. A calculated current and radiative electric field also appears like this form. From the measurement results, the measured results are very similar to the calculated results.