• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of radiological science and technology
• /
• v.32 no.1
• /
• pp.101-106
• /
• 2009

Purpose of this study is to compare the signal intensity (SI) and CNR with T1 weighted image using FLASH at 3T abdominal MRI by varying flip angle (FA). Totally 20 patients (male : 12, female : 8, Age : $28{\sim}63$ years with mean : 51) were examined by 3 Tesla MR scanner (Magnetom Tim Trio, SIEMENS, Germany) with 8 channel body array coil between september and October 2008. Imaging parameters were as follows : FLASH sequence, TR : 120 ms, TE : minimum, FOV (field of view) : $360{\times}300\;mm$, Matrix : $256{\times}224$, slice : 6 mm, scan time : 15 sec and Breath-hold technique. Abdominal image, with a 50 ml syringe filled with water placed in the FOV measuring the water signal, were acquired with varying FA through $10^{\circ}$ to $90^{\circ}$ with $10^{\circ}$ interval. SI's were measured three times at liver parenchyme, water, spleen and background and averaged. The CNR's were measured between the ROIs (region of interest). Statistic analysis was performed with ANOVA test using SPSS software (version 17.0). Less than FA $30^{\circ}$, abdominal images were severely inhomogeneity. Especially, T1 effect of water signal was weak. As the flip angle increased, the signal intensity decreased at all the regions. Especially, flip angle of the highest signal intensity was observed with $40^{\circ}$ at the liver parenchyme, $20^{\circ}$ at water, $30^{\circ}$ at the spleen, respectively. The CNR between liver and water was -60.92 at FA $10^{\circ}$ and 15.16 at FA $80^{\circ}$. The CNR between liver and spleen was -3.18 at FA $10^{\circ}$ and 9.65 at $80^{\circ}$. In conclusion, FA $80^{\circ}$ is optimal for T1 weighted effect using FLASH pulse sequence at 3.0 T abdominal MRI.

• Radiation Oncology Journal
• /
• v.21 no.1
• /
• pp.94-99
• /
• 2003

Purpose : To explore a 3D conformal radiotherapy technique for a posterior fossa boost, and the potential advantages of a prone position for such radiotherapy. Materials and Methods :A CT simulator and 3D conformal radiotherapy Planning system was used for the posterior fossa boost treatment on a 13-year-old medulloblastoma patient. He was placed In the prone position and Immobilized with an aquaplast mask and immobilization mold. CT scans were obtained of the brain from the top of the skull to the lower neck, with IV contrast enhancement. The target volume and normal structures were delineated on each slice, with treatment planning peformed using non-coplanar conformal beams. Results : The CT scans, and treatment In the prone position, were peformed successfully. In the prone position, the definition of the target volume was made easier due to the well enhanced tentorium, In audition, the posterior fossa was located anteriorly, and with the greater choice of beam arrangements, more accurate treatment planning was possible as the primary beams were not obstructed by the treatment table. Conclusion : .A posterior fossa boost, in the prone position, Is feasible in cooperating patients, but further evaluation is needed to define the optimal and most comfortable treatment positions.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.1 s.6
• /
• pp.15-29
• /
• 2005

Truck Shipment Safety Information, which is a part of the development of NERIS is divided into Optimal Route Guidance System and Emergency Response System. This research is for establishing an advance warning system, which aims for preventing damages(fire, explosion, gas-escape etc.) and detecting incidents that are able to happen during transporting hazardous materials in advance through monitoring the position of moving vehicles and the state of hazardous materials in real-time. This research is peformed to confirm the practical possibility of application of the advance warning system that monitors whether the hazardous materials transport vehicles move the allowed routes, finds the time and the location of incidents of the vehicles promptly and develops the emergency system that is able to respond to the incidents as well by using the technologies of CPS, CDMA and CIS with testing the ability of performance. As the results of the test, communication accuracies are 99$\%$ in freeway, 96$\%$ in arterial, 97$\%$ in hilly sections, 99$\%$ in normal sections, 96$\%$ in local sections, 99$\%$ in urban sections and 98$\%$ in tunnels. According to those results, the system has been recorded a high success rate of communication that enough to apply to the real site. However, the weak point appeared through the testing is that the system has a limitation of communication that is caused in the rural areas and certain areas where are fewer antennas that make communication possible between on-board unit and management server. Consequently, for the practical use of this system, it is essential to develop the exclusive en-board unit for the vehicles and find the method that supplements the receiving limitation of the GPS coordinates inside tunnels. Additionally, this system can be used to regulate illegal acts automatically such as illegal negligence of hazardous materials. And the system can be applied to the study about an application scheme as a guideline for transporting hazardous materials because there is no certain management system and act of toxic substances in Korea.

• Progress in Medical Physics
• /
• v.14 no.4
• /
• pp.211-217
• /
• 2003

The Principal component analysis (PCA) is a well-known data analysis method that is useful in linear feature extraction and data compression. The PCA is a linear transformation that applies an orthogonal rotation to the original data, so as to maximize the retained variance. PCA is a classical technique for obtaining an optimal overall mapping of linearly dependent patterns of correlation between variables (e.g. neurons). PCA provides, in the mean-squared error sense, an optimal linear mapping of the signals which are spread across a group of variables. These signals are concentrated into the first few components, while the noise, i.e. variance which is uncorrelated across variables, is sequestered in the remaining components. PCA has been used extensively to resolve temporal patterns in neurophysiological recordings. Because the retinal signal is stochastic process, PCA can be used to identify the retinal spikes. With excised rabbit eye, retina was isolated. A piece of retina was attached with the ganglion cell side to the surface of the microelectrode array (MEA). The MEA consisted of glass plate with 60 substrate integrated and insulated golden connection lanes terminating in an 8${\times}$8 array (spacing 200 $\mu$m, electrode diameter 30 $\mu$m) in the center of the plate. The MEA 60 system was used for the recording of retinal ganglion cell activity. The action potentials of each channel were sorted by off­line analysis tool. Spikes were detected with a threshold criterion and sorted according to their principal component composition. The first (PC1) and second principal component values (PC2) were calculated using all the waveforms of the each channel and all n time points in the waveform, where several clusters could be separated clearly in two dimension. We verified that PCA-based waveform detection was effective as an initial approach for spike sorting method.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Progress in Medical Physics
• /
• v.16 no.1
• /
• pp.24-31
• /
• 2005

The stereotactic radiosurgery (SRS) describes a method of delivering a high dose of radiation to a small tar-get volume in the brain, generally in a single fraction, while the dose delivered to the surrounding normal tissue should be minimized. To perform automatic plan of the SRS, a new method of multi-isocenter/shot linear accelerator (linac) and gamma knife (GK) radiosurgery treatment plan was developed, based on a physical lattice structure in target. The optimal radiosurgical plan had been constructed by many beam parameters in a linear accelerator or gamma knife-based radiation therapy. In this work, an isocenter/shot was modeled as a sphere, which is equal to the circular collimator/helmet hole size because the dimension of the 50% isodose level in the dose profile is similar to its size. In a computer-aided system, it accomplished first an automatic arrangement of multi-isocenter/shot considering two parameters such as positions and collimator/helmet sizes for each isocenter/shot. Simultaneously, an irregularly shaped target was approximated by cubic structures through computation of voxel units. The treatment planning method by the technique was evaluated as a dose distribution by dose volume histograms, dose conformity, and dose homogeneity to targets. For irregularly shaped targets, the new method performed optimal multi-isocenter packing, and it only took a few seconds in a computer-aided system. The targets were included in a more than 50% isodose curve. The dose conformity was ordinarily acceptable levels and the dose homogeneity was always less than 2.0, satisfying for various targets referred to Radiation Therapy Oncology Group (RTOG) SRS criteria. In conclusion, this approach by physical lattice structure could be a useful radiosurgical plan without restrictions in the various tumor shapes and the different modality techniques such as linac and GK for SRS.

• Journal of Distribution Research
• /
• v.5 no.2
• /
• pp.49-68
• /
• 2001

In this chapter, we summarize the results on the optimal location selection and present limitation and direction of research. In order to reach the objective, this study selected and tested the interaction model which obtains the value of co-ordinates on location selection through the optimization technique. This study used the original variables in the model, but the results indicated that there is difference in reality. In order to overcome this difference, this study peformed market survey and found the new variables (first data such as price, quality and assortment of goods, and the second data such as aggregate area, and area of shop, and the number of cars in the parking lot). Then this study determined an optimal variable by empirical analysis which compares an actual value of market share in 1988 with the market share yielded in the model. However, this study found the market share in each variables does not reflect a reality due to an assumption of λ-value in the model. In order to improve this, this study performed a sensitivity analysis which adds the λ value from 1.0 to 2.9 marginally. The analyzed result indicated the highest significance with the market share ratio in 1998 at λ of 1.0. Applying the weighted value to a variable from each of the first data and second data yielded the results that more variables from the first data coincided with the realistic rank on sales. Although this study have some limits and improvements, if a marketer uses this extended model, more significant results will be produced.

• Journal of the Korean Society of Radiology
• /
• v.12 no.2
• /
• pp.201-208
• /
• 2018

The purpose of this study was to investigate the optimal flip angle by measuring the SNR and CNR according to the angle of changes of the MRI technique using the Image J program. A total of 30 normal volunteers were assessed by using a 1.5T magnetic resonance imaging system (Philips, Medical System, Achieva). For the MRI angiography, we set the region of interest in four regions and evaluated the SNR and CNR. The statistical significance of SNR and CNR was calculated by one-way ANOVA using quantitative analysis at five different positions. The Bonferroni method was used for post-hoc analyzes. Statistical significance was determined by using ANOVA analysis at p<0.05 and Bonferroni method was used as a post-hoc analysis. The results of this study, the measurement values of ACA(SNR:$876.59{\pm}14.22$, CNR:$1999.7{\pm}12.5$), PCA(SNR:$863.48{\pm}13.29$, CNR:$1870.18{\pm}12.56$), ICA(SNR:$1116.87{\pm}08.34$, CNR:$2979.37{\pm}14.69$) and MCA(SNR:$848.66{\pm}15.25$, CNR:$2199.25{\pm}13.48$) were obtained with the high signal intensity at $25^{\circ}$(p<0.05). The values of a1, a2, a3, p1, p2, p3, m1, m2 and m3 were also the same (p<0.05). Post-hoc analysis results, There was a statistically significant difference (p=0.000) between $10^{\circ}$, $15^{\circ}$, $20^{\circ}$ on the $25^{\circ}$ reference for the flip angle, but no significant results were obtained with $30^{\circ}$(p<0.05). In concision, because the signal intensity decreased at $30^{\circ}$, this study revealed that the optimal flip angles were $25^{\circ}$ in cerebrovascular MR angiography.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.31 no.3
• /
• pp.199-218
• /
• 2005

Purpose of Study: Peripheral nerve regeneration depends on neurotrophism of distal nerve stump, recovery potential of neuron, supporting cell like Schwann cell and neurotrophic factors such as BDNF. Peripheral nerve regeneration can be enhanced by the conduit which connects the both sides of transected nerve. The conduit maintains the effects of neurotrophism and BDNF produced by Schwann cells which can be made by gene therapy. In this study, we tried to enhance the peripheral nerve regeneration by using calcium phosphate coated porous conduit and BDNF-Adenovirus infected Schwann cells in sciatic nerve of rats. Materials and Methods: Microporous filter which permits the tissue fluid essential for nerve regeneration and does not permit infiltration of fibroblasts, was made into 2mm diameter and 17mm length conduit. Then it was coated with calcium phosphate to improve the Schwann cell adhesion and survival. The coated filter was evaluated by SEM examination and MTT assay. For effective allogenic Schwann cell culture, dorsal root ganglia of 1-day old rat were extracted and treated with enzyme and antimitotic Ara-C. Human BDNF cDNA was obtained from cDNA library and amplified using PCR. BDNF gene was inserted into adenovirus shuttle vector pAACCMVpARS in which E1 was deleted. We infected the BDNF-Ad into 293 human mammary kidney cell-line and obtained the virus plaque 2 days later. RT-PCR was performed to evaluate the secretion of BDNF in infected Schwann cells. To determine the most optimal m.o.i of BDNF-Ad, we infected the Schwann cells with LacZ adenovirus in 1, 20, 50, 75, 100, 250 m.o.i for 2 hours and stained with ${\beta}$-galactosidase. Rats(n=24) weighing around 300g were used. Total 14mm sciatic nerve defect was made and connected with calcium phosphate coated conduits. Schwann cells$(1{\times}10^6)$ or BDNF-Ad infected Schwann cells$(1{\times}10^6)$ were injected in conduit and only media(MEM) was injected in control group. Twelve weeks after surgery, degree of nerve regeneration was evaluated with gait analysis, electrophysiologic measurements and histomorphometric analysis. Results: 1. Microporous Millipore filter was effective conduit which permitted the adhesion of Schwann cells and inhibited the adhesion of fibroblast. We could enhance the Schwann cell adhesion and survival by coating Millipore filter with calcium phosphate. 2. Schwann cell culture technique using repeated treatment of Ara-C and GDNF was established. The mean number of Schwann cells obtained 1 and 2 weeks after the culture were $1.54{\pm}4.0{\times}10^6$ and $9.66{\pm}9.6{\times}10^6$. 3. The mRNA of BDNF in BDNF-Ad infected Schwann cells was detected using RT-PCR. In Schwann cell $0.69\;{\mu}g/{\mu}l$ of DNA was detected and in BDNF-Adenovirus transfected Schwann cell $0.795\;{\mu}g/{\mu}l$ of DNA was detected. The most effective infection concentration was determined by LacZ Adenovirus and 75 m.o.i was found the most optimal. Conclusion: BDNF-Ad transfected Schwann cells successfully regenerated the 14mm nerve gap which was connected with calcium phosphate coated Millipore filter. The BDNF-Ad group showed better results compared with Schwann cells only group and control group in aspect to sciatic function index, electrophysiologic measurements and histomorphometric analysis.