• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1975-1988
• /
• 2019

Short-term traffic flow prediction plays an important role in intelligent transportation systems (ITS) in areas such as transportation management, traffic control and guidance. For short-term traffic flow regression predictions, the main challenge stems from the non-stationary property of traffic flow data. In this paper, we design an ensemble cascading prediction framework based on extremely randomized trees (extra-trees) using a boosting technique called EET to predict the short-term traffic flow under non-stationary environments. Extra-trees is a tree-based ensemble method. It essentially consists of strongly randomizing both the attribute and cut-point choices while splitting a tree node. This mechanism reduces the variance of the model and is, therefore, more suitable for traffic flow regression prediction in non-stationary environments. Moreover, the extra-trees algorithm uses boosting ensemble technique averaging to improve the predictive accuracy and control overfitting. To the best of our knowledge, this is the first time that extra-trees have been used as fundamental building blocks in boosting committee machines. The proposed approach involves predicting 5 min in advance using real-time traffic flow data in the context of inherently considering temporal and spatial correlations. Experiments demonstrate that the proposed method achieves higher accuracy and lower variance and computational complexity when compared to the existing methods.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.290-295
• /
• 1999

Lineament extraction from mountain area often provides valuable geological information. In many cases, the lineaments correspond to a series of continuous large valleys. This paper introduces a new lineament extraction method from Digital Elevation Model (DEM) using Raindrop Tracing Algorithm (RTA). The main advantage of this algorithm over conventional Segment Tracing Algorithm (STA) is that it utilizes DEM directly unlike the STA Which utilizes the shaded relief of DEM. The RTA simulates the real life of raindrops that converge into a large valley. The simulation has been done by sprinkling the randomized raindrops over DEM and counting the number of raindrop path that follows the negative gradient of the DEM. The large counting number indicates the location of a big valley where the raindrops converge. With the help of the counting number array (accumulator array) recording the flowing path information, RTA can produce perfectly unbiased binary image of the lineament.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.1
• /
• pp.61-73
• /
• 2012

The paper presents the novel approach to solve some problems occurred in application of the genetic algorithm to the determination of the optimal tire pattern sequence in order to reduce the tire air-pumping noise which is generated by the repeated compression and expansion of the air cavity between tire pattern and road surface. The genetic algorithm has been used to find the optimal tire pattern sequence having a low level of tire air-pumping noise using the image based air-pumping model. In the genetic algorithm used in the previous researches, there are some problems in the encoding structure and the selection of objective function. The paper proposed single encoding element with five integers, divergent objective function based on evolutionary process and the optimal evolutionary rate based on Shannon entropy to solve the problems. The results of the proposed genetic algorithm with evolutionary process are compared with those of the randomized algorithm without evolutionary process on the two-dimensional normal distribution. It is confirmed that the genetic algorithm is more effective to reduce the peak value of the predicted tire air-pumping noise and the consistency and cohesion of the obtained simulation results are also improved in terms of probability.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.8
• /
• pp.22-33
• /
• 2009

Mobile Ad Hoc Networks (MANETs) are self-organized networks that do not rely in their operation on wired infrastructure. As in any networking technology, security is an essential element in MANET as well, for proliferation of this type of networks. But supporting secure communication in MANETs proved to be a significant challenge, mainly due to the fact that the set of nodes in the network can change frequently and rapidly and due to the lack of access to the wired infrastructure. In particular, the trust model and the authentication protocols, which were developed for wired and infrastructure-based networks, cannot be used in MANETs. In [1], we addressed the problem of efficient authentication of distributed mobile users in geographically large networks and proposed a new authentication scheme for this case of MANETs. The proposed scheme exploits randomized groups to efficiently share authentication information among nodes that together implement the function of a distributive Certification Authority(CA). In this paper, we analyze numerically the performance of authentication method using randomized groups and compare with the simulation result.

• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1577-1584
• /
• 2007

Fingerprint verification is being adopted widely to provide positive identification with a high degree of confidence in all practical areas. This popular usage requires reliable methods for matching of these patterns. To meet the latest expectations, the paper presents a pair wise distance histogram method for fingerprint matching. Here, we introduced a randomized algorithm which exploits pair wise distances between the pairs of minutiae, as a basic feature for match. The method undergoes two steps for completion i.e. first it performs the matching locally then global matching parameters are calculated in second step. The proposed method is robust to common problems that fingerprint matching faces, such as scaling, rotation, translational changes and missing points etc. The paper includes the test of algorithm on various randomly generated minutiae and real fingerprints as well. The results of the tests resemble qualities and utility of method in related field.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.43-51
• /
• 2008

Evolutionary Algorithms (EAs) cover all the applications involving the use of Evolutionary Computation in electronic system design. It is largely applied to complex optimization problems. EAs introduce a new idea for automatic design of electronic systems; instead of imagine model, ions, and conventional techniques, it uses search algorithm to design a circuit. In this paper, a method for automatic optimization of the digital circuit design method has been introduced. This method is based on randomized search techniques mimicking natural genetic evolution. The proposed method is an iterative procedure that consists of a constant-size population of individuals, each one encoding a possible solution in a given problem space. The structure of the circuit is encoded into a one-dimensional genotype as represented by a finite string of bits. A number of bit strings is used to represent the wires connection between the level and 7 types of possible logic gates; XOR, XNOR, NAND, NOR, AND, OR, NOT 1, and NOT 2. The structure of gates are arranged in an $m{\times}n$ matrix form in which m is the number of input variables.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• Journal of Korean Society for Quality Management
• /
• v.46 no.3
• /
• pp.651-658
• /
• 2018

Purpose: The algorithm described in Lim(1998) is available to determine the sample size directly given specified significance level, power and signal-to-noise ratio. We research on the efficient determination of the sample size by visual methods. Methods: We propose three graphs for investigating the mutual relationship between the sample size r, power $1-{\beta}$ and the detectable signal-to-noise ratio ${\Delta}$. First graph shows the relationship between ${\Delta}$ and $1-{\beta}$ for the given r and it can be checked whether the power is sufficient enough. Second graph shows the relationship between r and ${\Delta}$ for the given power $1-{\beta}$. Third graph shows the relationship between r and $1-{\beta}$ for the given ${\Delta}$. It can be checked that which effects are sensitive to the efficient sample size by investigating those graphs. Results: In factorial design, randomized block design and the split plot design how to determine the sample size directly given specified significance level, power and signal-to-noise ratio is programmed by using R. A experiment to study the split plot design in Hicks(1982) is used as an example. We compare the sample sizes calculated by randomized block design with those by split plot design. By using graphs, we can check the possibility of reducing the sample size efficiently. Conclusion: The proposed visual methods can help an engineer to make a proper plan to reduce the sample size.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.27 no.4
• /
• pp.1-15
• /
• 2014

Objective : This study was carried out to analyze the quality and quantity of Clinical Trials that have been published in the journal of korean medical ophthalmology, otolaryngology, dermatology(JKOOD). Methods : We analyzed 25 clinical trials that published in JKOOD from 1988 to 2014. We excluded case reports, protocol and retrospective studies and classified searched papers into three categories; Randomized Clinical Trials(RCT), Non Randomized Clinical Trials(NRCT), Before After Study(BAS) by using study Design Algorithm for Medical literature of Intervention(DMAI). All articles were analyzed according to diagnosis, statistics program and intervention period. The bias of RCTs were evaluated by Cochrane Risk of Bias(RoB). Result : 1. The number of searched journals is 25 papers; 13 RCT, 2 NRCT, 10 BAS 2. Distribution of clinical trial; 'Atopic dermatitis' ranked the highest(44%) in disease, 'External application' raked the highest(71%) in treatment method. 3. 'allocation sequence' and 'prevention of allocated intervent to patients and therapists' are graded 'Low' but 'incomplete outcome date' and 'selective outcome' are graded 'Uncertain'. Conclusions : It is necessary to study more RCT. It will be helpful to study systematic reviews and meta analysis in JKOOD.

• Clinical Psychopharmacology and Neuroscience
• /
• v.16 no.4
• /
• pp.376-382
• /
• 2018

We reviewed clinical studies investigating the pharmacological treatment of major depressive episodes (MDEs) with mixed features diagnosed according to the dimensional criteria (more than two or three [hypo]manic symptoms+principle depressive symptoms). We systematically reviewed published randomized controlled trials on the pharmacological treatment of MDEs with mixed features associated with mood disorders, including major depressive disorder (MDD) and bipolar disorder (BD). We searched the PubMed, Cochrane Library, and ClinicalTrials.gov databases through December 2017 with the following key word combinations linked with the word OR: (a) mixed or mixed state, mixed features, DMX, mixed depression; (b) depressive, major depressive, MDE, MDD, bipolar, bipolar depression; and (c) antidepressant, antipsychotic, mood stabilizer, anticonvulsant, treatment, medication, algorithm, guideline, pharmacological. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We found few randomized trials on pharmacological treatments for MDEs with mixed features. Of the 36 articles assessed for eligibility, 11 investigated MDEs with mixed features in mood disorders: six assessed the efficacy of antipsychotic drugs (lurasidone and ziprasidone) in the acute phase of MDD with mixed features, although four of these were post hoc analyses based on large randomized controlled trials. Four studies compared antipsychotic drugs (olanzapine, lurasidone, and ziprasidone) with placebo, and one study assessed the efficacy of combination therapy (olanzapine+fluoxetine) in the acute phase of BD with mixed features. Pharmacological treatments for MDEs with mixed features have focused on antipsychotics, although evidence of their efficacy is lacking. Additional well-designed clinical trials are needed.