• Korean Journal of Food Science and Technology
• /
• v.34 no.2
• /
• pp.186-193
• /
• 2002

This study was conducted to enhance the protein quality of wheat flour extrudates with the addition of fish sauce by-products and dried biji. The experimental design was used to determine the optimum ratio of each ingredient. The compositional and functional properties of test extrudate were measured, and these values were applied to the mathematical models. A canonical form and trace plot showed that the influence of each ingredient on the mixture final product. Protein content of extrudate was increased by the addition of the dried biji, and bending failure stress of extrudate became hardened due to interaction effects between dried biji and pacific sand lance sauce by-product. Also, the addition of dried biji decreased ash and salt contents. An optimum formulation was obtained as 15.83 : 44.17 : 40% with numerical and 15.74 : 44.26 : 26.40% with graphical method (pacific sand lance sauce by-product : dried biji : wheat flour). Based on the growth performance, feed conversion efficiency was slightly lower than control group, but the protein content in feed extrudate increased to a large extent compared to that mixed with wet biji.

• Progress in Medical Physics
• /
• v.13 no.4
• /
• pp.224-228
• /
• 2002

Myocardial tagging technique such as spatial modulation of magnetization (SPAMM) allows the study of myocardial motion with high accuracy. However, the accuracy of the estimation of tag intersection can be affected by tagline spacing. The aim of this study was to investigate the relationship between tagline spacing of SPAMM image and tagging contrast-to-noise ratio (CNR) in in-vivo study. Two healthy volunteers were undergone electrocardiographically triggered MR imaging with SPAMM-based tagging pulse sequence at a 1.5T MR scanner. Horizontally modulated stripe patterns were imposed with a range from 3.6 to 9.6 mm of tagline spacing. Images of the left ventricle(LV) wall were acquired at the mid-ventricle level during cardiac cycle with FE-EPI (TR/TE = 5.8/2.2 msec, FA= 10$^{\circ}$. Tagging CNR for each image was calculated with a software which developed in our group. During contraction, tagging CNR was more rapidly decreased in case of narrow tagline spacing than in case of wide tagline spacing. In the same heart phase, CNR was increased corresponding with tagline spacing. Especially, at the fully contracted heart phase, CNR was more rapidly increased than the other heart phases as a function of tagline spacing. The results indicated that the optimization of tagline spacing provides better tagging CNR in order to analyze the myocardial motion more accurately.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.80-90
• /
• 2002

Clustering is a useful technique for grouping data points such that points within a single group/cluster have similar characteristics. Many clustering algorithms have been developed and used in engineering applications including pattern recognition and image processing etc. Recently, it has drawn increasing attention as one of important techniques in data mining. However, clustering algorithms such as K-means and Fuzzy C-means suffer from difficulties. Those are the needs to determine the number of clusters apriori and the clustering results depending on the initial set of clusters which fails to gain desirable results. In this paper, we propose a new clustering algorithm, which solves mentioned problems. In our method we use evolutionary algorithm to solve the local optima problem that clustering converges to an undesirable state starting with an inappropriate set of clusters. We also adopt a new measure that represents how well data are clustered. The measure is determined in terms of both intra-cluster dispersion and inter-cluster separability. Using the measure, in our method the number of clusters is automatically determined as the result of optimization process. And also, we combine heuristic that is problem-specific knowledge with a evolutionary algorithm to speed evolutionary algorithm search. We have experimented our algorithm with several sets of multi-dimensional data and it has been shown that one algorithm outperforms the existing algorithms.

• Clean Technology
• /
• v.27 no.4
• /
• pp.332-340
• /
• 2021

With the recent reinforcement of emission standards, it is necessary to make efforts to reduce NOx from air pollutant-emitting workplaces. The NOx reduction method mainly used in industrial facilities is selective catalytic reduction (SCR), and the most commercial SCR catalyst is the ceramic honeycomb catalyst. This study was carried out to reduce the NOx emitted from steel plants by applying De-NOx catalyst coated on metallic monolith. The De-NOx catalyst was synthesized through the optimized coating technique, and the coated catalyst was uniformly and strongly adhered onto the surface of the metallic monolith according to the air jet erosion and bending test. Due to the good thermal conductivity of metallic monolith, the De-NOx catalyst coated on metallic monolith showed good De-NOx efficiency at low temperatures (200 ~ 250 ℃). In addition, the optimal amount of catalyst coating on the metallic monolith surface was confirmed for the design of an economical catalyst. Based on these results, the De-NOx catalyst of commercial grade size was tested in a semi-pilot De-NOx performance facility under a simulated gas similar to the exhaust gas emitted from a steel plant. Even at a low temperature (200 ℃), it showed excellent performance satisfying the emission standard (less than 60 ppm). Therefore, the De-NOx catalyst coated metallic monolith has good physical and chemical properties and showed a good De-NOx efficiency even with the minimum amount of catalyst. Additionally, it was possible to compact and downsize the SCR reactor through the application of a high-density cell. Therefore, we suggest that the proposed De-NOx catalyst coated metallic monolith may be a good alternative De-NOx catalyst for industrial uses such as steel plants, thermal power plants, incineration plants ships, and construction machinery.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1041-1043
• /
• 1993

Fuzzy logic based Control Theory has gained much interest in the industrial world, thanks to its ability to formalize and solve in a very natural way many problems that are very difficult to quantify at an analytical level. This paper shows a solution for treating membership function inside hardware circuits. The proposed hardware structure optimizes the memoried size by using particular form of the vectorial representation. The process of memorizing fuzzy sets, i.e. their membership function, has always been one of the more problematic issues for the hardware implementation, due to the quite large memory space that is needed. To simplify such an implementation, it is commonly [1,2,8,9,10,11] used to limit the membership functions either to those having triangular or trapezoidal shape, or pre-definite shape. These kinds of functions are able to cover a large spectrum of applications with a limited usage of memory, since they can be memorized by specifying very few parameters ( ight, base, critical points, etc.). This however results in a loss of computational power due to computation on the medium points. A solution to this problem is obtained by discretizing the universe of discourse U, i.e. by fixing a finite number of points and memorizing the value of the membership functions on such points [3,10,14,15]. Such a solution provides a satisfying computational speed, a very high precision of definitions and gives the users the opportunity to choose membership functions of any shape. However, a significant memory waste can as well be registered. It is indeed possible that for each of the given fuzzy sets many elements of the universe of discourse have a membership value equal to zero. It has also been noticed that almost in all cases common points among fuzzy sets, i.e. points with non null membership values are very few. More specifically, in many applications, for each element u of U, there exists at most three fuzzy sets for which the membership value is ot null [3,5,6,7,12,13]. Our proposal is based on such hypotheses. Moreover, we use a technique that even though it does not restrict the shapes of membership functions, it reduces strongly the computational time for the membership values and optimizes the function memorization. In figure 1 it is represented a term set whose characteristics are common for fuzzy controllers and to which we will refer in the following. The above term set has a universe of discourse with 128 elements (so to have a good resolution), 8 fuzzy sets that describe the term set, 32 levels of discretization for the membership values. Clearly, the number of bits necessary for the given specifications are 5 for 32 truth levels, 3 for 8 membership functions and 7 for 128 levels of resolution. The memory depth is given by the dimension of the universe of the discourse (128 in our case) and it will be represented by the memory rows. The length of a world of memory is defined by: Length = nem (dm(m)＋dm(fm) Where: fm is the maximum number of non null values in every element of the universe of the discourse, dm(m) is the dimension of the values of the membership function m, dm(fm) is the dimension of the word to represent the index of the highest membership function. In our case then Length=24. The memory dimension is therefore 128*24 bits. If we had chosen to memorize all values of the membership functions we would have needed to memorize on each memory row the membership value of each element. Fuzzy sets word dimension is 8*5 bits. Therefore, the dimension of the memory would have been 128*40 bits. Coherently with our hypothesis, in fig. 1 each element of universe of the discourse has a non null membership value on at most three fuzzy sets. Focusing on the elements 32,64,96 of the universe of discourse, they will be memorized as follows: The computation of the rule weights is done by comparing those bits that represent the index of the membership function, with the word of the program memor . The output bus of the Program Memory (μCOD), is given as input a comparator (Combinatory Net). If the index is equal to the bus value then one of the non null weight derives from the rule and it is produced as output, otherwise the output is zero (fig. 2). It is clear, that the memory dimension of the antecedent is in this way reduced since only non null values are memorized. Moreover, the time performance of the system is equivalent to the performance of a system using vectorial memorization of all weights. The dimensioning of the word is influenced by some parameters of the input variable. The most important parameter is the maximum number membership functions (nfm) having a non null value in each element of the universe of discourse. From our study in the field of fuzzy system, we see that typically nfm 3 and there are at most 16 membership function. At any rate, such a value can be increased up to the physical dimensional limit of the antecedent memory. A less important role n the optimization process of the word dimension is played by the number of membership functions defined for each linguistic term. The table below shows the request word dimension as a function of such parameters and compares our proposed method with the method of vectorial memorization[10]. Summing up, the characteristics of our method are: Users are not restricted to membership functions with specific shapes. The number of the fuzzy sets and the resolution of the vertical axis have a very small influence in increasing memory space. Weight computations are done by combinatorial network and therefore the time performance of the system is equivalent to the one of the vectorial method. The number of non null membership values on any element of the universe of discourse is limited. Such a constraint is usually non very restrictive since many controllers obtain a good precision with only three non null weights. The method here briefly described has been adopted by our group in the design of an optimized version of the coprocessor described in [10].

• Journal of Korean Society of Transportation
• /
• v.18 no.1
• /
• pp.75-85
• /
• 2000

In existing models in optimization, the crisp data improve has been used in the objective or constraints to derive the optimal solution, Besides, the subjective environments are eliminated because the complex and uncertain circumstances were regarded as Probable ambiguity, In other words those optimal solutions in the existing models could be the complete satisfactory solutions to the objective functions in the Process of application for industrial engineering methods to minimize risks of decision-making. As a result of those, decision-makers in location Problems couldn't face appropriately with the variation of demand as well as other variables and couldn't Provide the chance of wide selection because of the insufficient information. So under the circumstance. it has been to develop the model for the location and size decision problems of logistics facility in the use of the fuzzy theory in the intention of making the most reasonable decision in the Point of subjective view under ambiguous circumstances, in the foundation of the existing decision-making problems which must satisfy the constraints to optimize the objective function in strictly given conditions in this study. Introducing the Process used in this study after the establishment of a general mixed integer Programming(MIP) model based upon the result of existing studies to decide the location and size simultaneously, a fuzzy mixed integer Programming(FMIP) model has been developed in the use of fuzzy theory. And the general linear Programming software, LINDO 6.01 has been used to simulate, to evaluate the developed model with the examples and to judge of the appropriateness and adaptability of the model(FMIP) in the real world.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Radiation Oncology Journal
• /
• v.21 no.4
• /
• pp.299-305
• /
• 2003

Purpose: In order to develop the national guide-lines for the standardization of radiotherapy we are planning to establish a web-based, on-line data-base system for laryngeal cancer. As a first step this study was performed to accumulate the basic clinical information of laryngeal cancer and to determine the items needed for the data-base system. Materials and Methods: We analyzed the clinical data on patients who were treated under the diagnosis of laryngeal cancer from January 1998 through December 1999 In the South-west area of Korea. Eligiblity criteria of the patients are as follows: 18 years or older, currently diagnosed with primary epithelial carcinoma of larynx, and no history of previous treatments for another cancers and the other laryngeal diseases. The items were developed and filled out by radiation oncologlst who are members of forean Southwest Radiation Oncology Group. SPSS vl0.0 software was used for statistical analysis. Results: Data of forty-five patients were collected. Age distribution of patients ranged from 28 to 88 years(median, 61). Laryngeal cancer occurred predominantly In males (10 : 1 sex ratio). Twenty-eight patients (62$\%$) had primary cancers in the glottis and 17 (38$\%$) in the supraglottis. Most of them were diagnosed pathologically as squamous cell carcinoma (44/45, 98$\%$). Twenty-four of 28 glottic cancer patients (86$\%$) had AJCC (American Joint Committee on Cancer) stage I/II, but 50$\%$ (8/16) had In supraglottic cancer patients (p=0.02). Most patients(89$\%$) had the symptom of hoarseness. indirect laryngoscopy was done in all patients and direct laryngoscopy was peformed in 43 (98$\%$) patients. Twenty-one of 28 (75$\%$) glottic cancer cases and 6 of 17 (35$\%$) supraglottic cancer cases were treated with radiation alone, respectively. The combined treatment of surgery and radiation was used in 5 (18$\%$) glottic and 8 (47$\%$) supraglottic patients. Chemotherapy and radiation was used in 2 (7$\%$) glottic and 3 (18$\%$) supraglottic patients. There was no statistically significant difference in the use of combined modality treatments between glottic and supraglottic cancers (p=0.20). In all patients, 6 MV X-ray was used with conventional fractionation. The iraction size was 2 Gy In 80$\%$ of glottic cancer patients compared with 1.8 Gy in 59$\%$ of the patients with supraglottic cancers. The mean total dose delivered to primary lesions were 65.98 ey and 70.15 Gy in glottic and supraglottic patients treated, respectively, with radiation alone. Based on the collected data, 12 modules with 90 items were developed or the study of the patterns of care In laryngeal cancer. Conclusion: The study Items for laryngeal cancer were developed. In the near future, a web system will be established based on the Items Investigated, and then a nation-wide analysis on laryngeal cancer will be processed for the standardization and optimization of radlotherapy.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.