• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.239-240
• /
• 2012

With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.92-99
• /
• 2016

A wind turbine is controlled for the purpose of obtaining the maximum power below its rated wind speed. Among the methods of obtaining the maximum power, TSR (Tip Speed Ratio) optimal control and P&O (Perturbation and Observation) control are widely used. The P&O control algorithm using the turbine power and rotational speed is simple, but its slow response is a weak point. Whereas TSR control's response is fast, it requires the precise wind speed. A method of measuring or estimating the wind speed is used to obtain a precise value. However, estimation methods are mostly used, because it is difficult to avoid the blade interference when measuring the wind speed near the blades. Neural networks and various numerical methods have been applied for estimating the wind speed, because it involves an inverse problem. However, estimating the wind speed is still a difficult problem, even with these methods. In this paper, a new method is introduced to estimate the wind speed in the wind-power graph by using the turbine power and rotational speed. Matlab/Simulink is used to confirm that the proposed method can estimate the wind speed properly to obtain the maximum power.

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.396-408
• /
• 2007

After the Human Genome Project finished the sequencing of a human DNA sequence, the concerns on protein functions are increasing. Since the structures of proteins are conserved in divergent evolution, their functions are determined by their structures rather than by their amino acid sequences. Therefore, if similarities between two protein structures are observed, we could expect them to have common biological functions. So far, a lot of researches on protein structure alignment have been performed. However, most of them use RMSD(Root Mean Square Deviation) as a similarity measure with which it is hard to judge the similarity level of two protein structures intuitively. In addition, they retrieve only one result having the highest alignment score with which it is hard to satisfy various users of different purpose. To overcome these limitations, we propose a novel protein structure alignment algorithm based on MRPD(Maximum of Residue Pair Distance) and SG (Similarity Graph). MRPD is more intuitive similarity measure by which fast tittering of unpromising pairs of protein pairs is possible, and SG is a compact representation method for multiple alignment results with which users can choose the most plausible one among various users' needs by providing multiple alignment results without compromising the time to align protein structures.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.282-294
• /
• 2017

In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.

• Nuclear Engineering and Technology
• /
• v.52 no.11
• /
• pp.2452-2459
• /
• 2020

Neutron spectrum is essential to the safe operation of reactors. Traditional online neutron spectrum measurement methods still have room to improve accuracy for the application cases of wide energy range. From the application of artificial neural network (ANN) algorithm in spectrum unfolding, its accuracy is difficult to be improved for lacking of enough effective training data. In this paper, an adaptive deviation-resistant neutron spectrum unfolding method based on transfer learning was developed. The model of ANN was trained with thousands of neutron spectra generated with Monte Carlo transport calculation to construct a coarse-grained unfolded spectrum. In order to improve the accuracy of the unfolded spectrum, results of the previous ANN model combined with some specific eigenvalues of the current system were put into the dataset for training the deeper ANN model, and fine-grained unfolded spectrum could be achieved through the deeper ANN model. The method could realize accurate spectrum unfolding while maintaining universality, combined with detectors covering wide energy range, it could improve the accuracy of spectrum measurement methods for wide energy range. This method was verified with a fast neutron reactor BN-600. The mean square error (MSE), average relative deviation (ARD) and spectrum quality (Qs) were selected to evaluate the final results and they all demonstrated that the developed method was much more precise than traditional spectrum unfolding methods.

• Spatial Information Research
• /
• v.23 no.5
• /
• pp.1-7
• /
• 2015

Twitter has the fast propagation and diffusion of information compare to other SNS. Therefore, many researches about detecting real-time event using twitter are progressing. Twitter real-time event detecting system assumes every twitter user as a sensor and analyzes their written tweet in order to detect the event. Researches that are related to this twitter have already obtained good results but confronted the limits because of some problems. Especially, many existing researches are using the method that can trace an event location by using GPS coordinate. However, it can be suggested a definite limitation through the present user's skeptical responses about making personal location information public. Therefore, this paper suggests the method that traces the location information in tweet contents text without using the provided location information from twitter. Associated words were grouped by using the keyword that extracted in tweet contents text. The place that the events have occurred and whether the events have surely occurred are detected by this experiment using this algorithm. Furthermore, this experiment demonstrated the necessity of the suggested methods by showing faster detection compare to the other existing media.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.12
• /
• pp.17-23
• /
• 2010

In the mobile cloud computing, the mobile node should request and receive the services while being connected. In PMIPv6, all packets sent by mobile nodes or correspondent nodes are transferred through the local mobility anchor. This unnecessary detour still results in high delivery latency and significant processing cost. Several PMIPv6 route optimization schemes have been proposed to solve this issue. However, they also suffer from the high signaling costs and handover latency when determining the optimized path. We propose the route optimization handover scheme which adopts the prediction algorithm in PFMIPv6. In the proposed scheme, the new mobile access gateway establishes the bi-directional tunnel with the correspondent node's MAG using the context message when the mobile node's handover is imminent. This tunnel may eliminate the need of separate route optimization procedure. Hence, the proposed scheme can reduce the signaling cost than other conventional schemes do. Analytical performance evaluation is preformed to show the effectiveness of the proposed scheme. The result shows that our scheme is more effective than other schemes.

• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.125-144
• /
• 2006

The development of mobile applications is fast in recent years. However, nearly all applications are for messaging, financial, locating services based on simple interactions with mobile users because of the limited screen size, narrow network bandwidth, and low computing power. Processing an algorithm for supporting a group decision process on mobile devices becomes impossible. In this paper, we introduce the mobile-oriented simple interactive procedure for support a group decision making process. The interactive procedure is developed for multiple objective linear programming problems to help the group select a compromising solution in the mobile Internet environment. Our procedure lessens the burden of group decision makers, which is one of necessary conditions of the mobile environment. Only the partial weak order preferences of variables and objectives from group decision makers are enough for searching the best compromising solution. The methodology is designed to avoid any assumption about the shape or existence of the decision makers' utility function. For the purpose of the experimental study of the procedure, we developed a group decision support system in the mobile Internet environment, MOBIGSS and applied to an allocation problem of investor assets.

• The KIPS Transactions:PartD
• /
• v.15D no.4
• /
• pp.485-494
• /
• 2008

Huge amounts of various web items such as keywords, images, and web pages are being made widely available on the Web. The popularities of such web items continuously change over time, and mining temporal patterns in popularities of web items is an important problem that is useful for several web applications. For example, the temporal patterns in popularities of search keywords help web search enterprises predict future popular keywords, enabling them to make price decisions when marketing search keywords to advertisers. However, presence of millions of web items makes it difficult to scale up previous techniques for this problem. This paper proposes an efficient method for mining temporal patterns in popularities of web items. We treat the popularities of web items as time-series, and propose gapmeasure to quantify the similarity between the popularities of two web items. To reduce the computation overhead for this measure, an efficient method using the Fast Fourier Transform (FFT) is presented. We assume that the popularities of web items are not necessarily following any probabilistic distribution or periodic. For finding clusters of web items with similar popularity trends, we propose to use a density-based clustering algorithm based on the gap measure. Our experiments using the popularity trends of search keywords obtained from the Google Trends web site illustrate the scalability and usefulness of the proposed approach in real-world applications.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.95-102
• /
• 2005

In this paper, we propose a user friendly object-based image retrieval system using the interaction between cortex and hippocampus. Most existing ways of queries in content-based image retrieval rely on query by example or query by sketch. But these methods of queries are not adequate to needs of people's various queries because they are not easy for people to use and restrict. We propose a method of automatic color object extraction using CSB tree map(Color and Spatial based Binary をn map). Extracted objects were transformed to bit stream representing information such as color, size and location by region labelling algorithm and they are learned by the hippocampal neural network using the interplay between cortex and hippocampus. The cells of exciting at peculiar features in brain generate the special sign when people recognize some patterns. The existing neural networks treat each attribute of features evenly. Proposed hippocampal neural network makes an adaptive fast content-based image retrieval system using excitatory learning method that forwards important features to long-term memories and inhibitory teaming method that forwards unimportant features to short-term memories controlled by impression.