To see the other types of publications on this topic, follow the link: Gray Relation Analysis.
Dissertations / Theses on the topic 'Gray Relation Analysis'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Gray Relation Analysis.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Price, Matthew. "Automatic Modulation Classification Using Grey Relational Analysis." Thesis, Virginia Tech, 2011. http://hdl.handle.net/10919/42441.
Full textAbstract:
One component of wireless communications of increasing necessity in both civilian and military applications is the process of automatic modulation classification. Modulation of a
detected signal of unknown origin requiring interpretation must first be determined before
the signal can be demodulated. This thesis presents a novel architecture for a modulation
classifier that determines the most likely modulation using Grey Relational Analysis with the
extraction and combination of multiple signal features. An evaluation of data preprocessing
methods is conducted and performance of the classifier is investigated with the addition of
each new signal feature used for classification.<br>Master of Science
2
Martinho, Joana de Oliveira. "Application of grey systems theory to the brazilian airline insurance market." Master's thesis, Instituto Superior de Economia e Gestão, 2013. http://hdl.handle.net/10400.5/11365.
Full textAbstract:
Mestrado em Ciências Actuariais<br>Este projecto consiste no estudo da aplicação da análise de relação geral, no contexto da teoria de sistemas grey, ao mercado de seguros de aviação Brasileiro. Em particular, descrevemos a teoria subjacente à abordagem e analisamos 19 transportadoras aéreas brasileiras ao longo de 9 variáveis para identificar os principais factores de risco no cálculo do prémio dos seguros de aviação. Posteriormente, discutimos as vantagens e desvantagens do método aplicado e fornecemos uma comparação dos resultados obtidos com a literatura existente.<br>In this work we study the application of general relational analysis within the context of grey systems theory to the Brazilian airline insurance market. In particular, we provide the theoretical background of this approach and analyze 19 Brazilian carriers across 9 variables to assess the main risk factors in airline insurance pricing. Further, we discuss the advantages and disadvantages of the method and provide a comparison of the results obtained with existing literature.
3
Wolfe, Brian Thomas. "An analysis of texture, timbre, and rhythm in relation to form in Magnus Lindberg's "Gran Duo"." Thesis, The University of Oklahoma, 2013. http://pqdtopen.proquest.com/#viewpdf?dispub=3592105.
Full textAbstract:
<p> <i>Gran Duo</i> (1999-2000) by Magnus Lindberg (b. 1958) is the result of a commission by Sir Simon Rattle, former conductor of the City of Birmingham (England) Symphony Orchestra, and the Royal Festival Hall to commemorate the third millennium. Composed for twenty-four woodwinds and brass, Lindberg divides the woodwind and brass families into eight characters that serve as participants in an attentive twenty-minute conversation.</p><p> The document includes biographical information about the composition to further understand Lindberg’s writing style. The composer’s use of computer-assisted composition techniques inspires an alternative structural analysis of <i>Gran Duo.</i> Spectral graphs provide a supplementary tool for score study assisting with the verification of formal structural elements. A tempo chart allows the conductor to easily identify form and tempo relationships between each of the nineteen sections throughout the five-movement composition.</p><p> In order to reveal character areas and their relation to the structure of the work, the analysis of texture, timbre, and rhythm reveal the formal structure of the composition, which reflects a conversation between the brass and woodwinds in this setting for wind instruments.</p>
4
Chang, Jen-Chieh, and 張仁傑. "Application of Gray Relation Analysis in Promoting Military Image and voluntarism." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/09497408003766098633.
Full textAbstract:
碩士<br>建國科技大學<br>自動化工程系暨機電光系統研究所<br>99<br>In following with the change of social environment and moral value, people tend to pursuit vanity and utility. Young people seek for indolence, shallow values and hard to resist temptation. They sometimes committee relevant crimes and ruin their promising future.
Recently, corruption, seeking for personal gain and disclosure frequently occurred in the army. The situation brought about negative reports from mass media and serious damaged military image. It also destroyed the diligent training and hardness. It even damaged military morale and reputation. Therefore, this paper proposes Grey relation analysis to find out a method to encourage and promote military image. We expect to really improve the military image in the minds of people and set up accurate virtues, value judgments and self-discipline.
In addition, simplifying soldiers is an international streamline recently, our country’s military recently took effect of “Fine reality policy”, "sophisticated policy" and "essence policy" is the goal to meet the need of professional, scientific and technological exports in Taiwan/Peng-hu defense operations. The gradually rising rate of voluntarism has improved the military overall efficiency as well as the personnel quality. The future military service system will base on voluntarism and assist with military conscription. Therefore, if the government can offer a better retire career planning and payment promotion, there will be more high-quality and professional young people join the army and become a professional soldier.
5
鄭功成. "Envelope-Slope Gray Relation Analysis And Its Application In Handwritten Character Recognition." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/38284050612816068175.
Full textAbstract:
碩士<br>中原大學<br>電子工程學系<br>85<br>In this paper, an envelope feature extraction algorithm (EFEA) and a slope gray relation analysis (SGRA) for pattern recognition such as handwritten characteristic recognition are presented. Our developed SGRA method achieve very high recognition rate since the features of envelope-slope of an image are extracted. EFEA has very high speed since only the distance of the first black pixel of an image is required.
SGRA highly reduces the recognition time since only addition and subtraction are involved in computation comparing to the FCM method which needs a bulky exponential data computation. The handwritten character recognition rate using our SGRA is 98.91% using the U.S. postal services database.
6
Sheau-Nenu, Lin, and 林曉能. "Handwritten Character Recognition Using Left and Right Fallen-point Feature Extraction And Gray Relation Analysis." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/48533316318842839104.
Full textAbstract:
碩士<br>中原大學<br>電子工程研究所<br>86<br>In this paper, we have much progress in feature extraction and classifier to have high speed and good recognition rate in handwritten characteristic recognition system. We take the left and right fallen-point in feature extraction. This method has better performance than projections and crossing numbers and also has higher endurance to the tilting characters. Besides we take the gray relation analysis (GRA) in classifier. The gray relational analysis highly reduces the recognition time since it's algorithm is easy in computation comparing to the FCM method which needs a bulky exponential data computation. After a series of experiments , we prove our system not only has a good recognition rate, and has high speed, but also this system has easy architecture and very convenient to hardware upgrade.
7
KAO, JUI-CHANG, and 高瑞昌. "Applying Gray Relation Analysis and Entropy Method to Analyze - The Performance of Taiwan Machine Tool industry." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/c4j5ja.
Full textAbstract:
碩士<br>國立高雄應用科技大學<br>國際企業研究所<br>105<br>This research has selected total of eleven tool machine companies which acquire thorough financial data from TWSE’s listed company for the past eleven years (2006-2016). Aiming to be acquainted of the industry’s development and business performance, this research mainly focuses on tool machine industry’s characteristic including its operating cost, research and development costs, operating profit margins, operating margin, net operating income, business interests and fixed assets. For the purpose of examining tool Machine Company’s comprehensive business performance, this measure applies Entropy weighting analysis and gray relation analysis to construct a comprehensive and quantitative index.
The chosen tool machine companies have been divided into three different groups based on the results of gray relation and grade which are analyzed by Entropy weighting and gray relation analysis. The first group is the one that its gray-related value is more than 0.58, and that means its operating performance ranks top three: C08, C10 and C05. The second group is the one that its gray correlation degree presents in the interval of 0.45 ~ 0.54: C01, C03, C11 and C06, a total of four companies. The third group is C02, C04, C09 and C07, in which the gray correlation degree stays in the interval of 0.39 ~ 0.40. Finally, Based on each company’s financial statement data, it shows that business scale makes tremendous impact on its performance. Within the machine tool industry, the greater volume of business turnover is, the larger the business scale would be. The largest business scale company in the sample embraces first place in the gray relation sequences each year. Therefore, investors should choose the most overwhelming company in the industry as his or her first decision while investing.
8
Tsai, Chung-Lun, and 蔡宗倫. "Optimizing the Parameters of Multi-Objective Quality Characterization by Integrating Fuzzy Taguchi、TOPSIS and Gray Relation Analysis." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/80890859310914119772.
Full textAbstract:
碩士<br>國立高雄大學<br>亞太工商管理學系碩士班<br>97<br>With advances in technology development recent year, quality has become a more and more important subject. Traditionally, most problem of quality improvement that only can depend on the engineer's experience, it's easy to have the different stander and the fuzziness. Besides, the product or the process frequently has many quality characteristics, and these quality characteristics may have interaction, so, developing a model to solve the problem of multi-objective quality characterization is the quite important subject for an enterprise.
In view of that, this research uses Taguchi method to experiment first, provide stability for product design and quality through the lowest cost and minimum experiment. But Taguchi method mainly aims at the optimizing of the single quality characteristics, so, this research would integrate Fuzzy Theory、Technique for Order Preference by Similarity to Ideal Solution(TOPIS)、Grey Relational Analysis(GRA) for multi-objective quality characterization problems. Using Fuzzy Theory to deal with the S/N ration form Taguchi, it can easy to compare with all different units of quality characterization, and then integrate TOPSI and GRA to establish two model with that “Fuzzy TOPSIS”and “Fuzzy GRA”, Getting the significant parameters and correlation indicators to find the bet parameter combination through the two models, therefore, it could get the more objective judgment and understand which model should be selected in different environment by analysis the different initial best parameter combination and overall best parameter combination.
Finally, this research would use the case-LCD manufacturing process to demonstrate the effectiveness and the usability of the models, and helps the company to do quality control at the first, also can save time and cost.
9
Cheng, Tsai-Lin, and 鄭才琳. "Optimizing the Machining Multiple Quality of Deep Hole Drilling by Integrating the Taguchi Method with Gray Relation Analysis." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/04882056746472624562.
Full textAbstract:
碩士<br>國立交通大學<br>機械工程系所<br>97<br>Among drilling machining, the deep-hole drilling can drill deep holes with depth-diameter-ratio above 100 with excellent machining quality. In fact, the work-piece has many kinds of working quality characteristics and more than one quality characteristic must be considered simultaneously to improve the work-piece quality. Therefore, the main purpose of this research is to discuss the machining multi-quality of the BTA deep-hole drilling and propose an approach to optimize multi-quality characteristics by using the Taguchi method combined with the grey relational analysis. Roundness error, surface roughness are considered as quality characteristic. The Taguchi’s orthogonal array is used to plan experiments and then separately calculating the SN ratio according to the quality characteristic. However, the Taguchi method can only manage analysis of the optimization for a single quality characteristic. Thus, Grey Relational Analysis is used to convert the SN ratio into Grey Relational Grade as a single performance index. Finally, optimal machining parameters can be determined by Grey Relational Grade response table and Analysis of Variance. Experimental results have shown that machining multi-quality in deep-hole drilling can be improved effectively through this approach.
10
黃衍凱. "A Study on Applying Gray Relational Analysis to Compare and Detect the Relation Similarities among Criminal Cases—Taipei City’s Habitual Offenders in Theft as an Example." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/b62733.
Full textAbstract:
碩士<br>中央警察大學<br>資訊管理研究所<br>100<br>According to official statistics by National Police Agency of Ministry of the Interior, clearance rate is always not 100%. To be able to raise the clearance rate has been concerns in our society. It has been one of the recent ways of detection that if modus operandi and crime patterns can be analyzed through collecting related information before, during and after committing a crime and through criminal record database. Crime patterns are a result of systematically assembling modus operandi from criminal cases of the same type. Through compiling modus operandi, we hope to achieve the goal of narrowing detection scopes.
Through analyzing criminal records, this study is to perform weighted entropy calculation on the statistics of crime causes, crime habits, preparation processes, modus operandi, criminal tools and features and bad hobbies, so that the importance of each factor can be distinguished more easily. And then further applying the localization of gray relational analysis to work out the similarity among individuals, with a view to offering data for comparison among different objects and to judge if the crime pattern is possibly similar to past ones (habitual offenders) in criminal records, and see if the violations are actually out of the same subject. Moreover, with the application of globalization of gray relational analysis, the non-specific groups and that of the highest similarity can be sub-grouped, so as to find out groups of criminals of the same crime patterns. Therefore, the possible subtle accomplices or criminal rings can be detected, which aims to provide prosecutors as well as the police with the referable directions to locate law violators during criminal investigation.
11
Wu, Chien-Hsing, and 吳建興. "Research in prevention oil pollution from oil tanker-An application of gray relation analysis on marine casualty of oil tanker of aframan type." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/23260404470795329049.
Full textAbstract:
碩士<br>國立臺灣海洋大學<br>商船學系所<br>94<br>This research concerned about the effect and measures of prevention oil pollution for oil tanker under the framework of International Convention for the Prevention of Pollution form Ship (MARPOL), the prevention measures include the prevention of operational and accidental oil pollutions. An application of gray relation analysis on marine casualty of oil tanker of AFRAMAX type, concerned about the relation of Structural Failure, Collision, Contact, Grounding, Fire and Explosion and application of gray relation matrix for analysis the relation between marine casualty with casualty site that include port area, canal & river, berth, port approach coastal waters and open sea, which in order to contribute to prevention accidental oil pollution form oil tanker.
12
CHENG, CHUNG-HUNG, and 鄭仲宏. "Oceanic Pollution in Tanker Gray Relational Analysis." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/27354760177133155013.
Full textAbstract:
碩士<br>國立高雄海洋科技大學<br>航運技術研究所<br>104<br>Taiwan is an island surrounded by oceans. This geographical superiority brings us scenic environment and various oceanic resources, having our daily lives get involved with it a lot. However, the fuel pollution resulting from the ships sailing back and forth among counties is getting increased tendency; Consequently, PSC is taking this subject under supervision more strictly than ever, the subject of how to prevent the pollution made by vessel evokes enthusiastic discussion and emphasis.
To discuss related statute of ship's pollution, the domestic laws as: The Commercial Port Law of 1980, and Marine Pollution Control Act of 2000, and Marine Environment Pollution Cleanup and Disposal Regulations of 2002; and International Laws as: The International Convention for The Prevention of The Pollution from Ships, MARPOL 73/78, and Convention On The Prevention of Marine Pollution by Dumping of Wastes and other Matters, 1972-London Dumping Convention, LCD of 1972, and United Nations Convention on The Law of Sea, 1982, UNCLOS 1982, the laws are strictly demand vessels to follow the relative regulations about how to prevent the oceanic pollution.
The research is based on the Gray Relational Analysis model to study the methods of oil tanker spill statistics for a study analyzing, since the gray theory can use the limited and incomplete data information to predict future values, and no other putative and restrictions can be predicted, due to the research is used on the Grey Relational Analysis, and the other document to auxiliary, and discussed to proceeding analysis. The results showed that Grey Relational Analysis can effectively analyze important factor to affect oil spill, and can predict the future number of accidents and oil spills statistics and accuracy over 99 percent credibility, and can provide the relevant unit of reference to improve marine pollution.
13
Garside, Chelsea Faye. "Relating gray whale abundance to environmental variables." Thesis, 2009. http://hdl.handle.net/1828/1456.
Full textAbstract:
The abundance of gray whales along the coast of Flores Island, BC, varies on an annual basis. This thesis searches for a relationship between gray whale abundance in this area and environmental forcing factors. Regression analysis was used to search for relationships, using gray whale abundance as the dependent variable and sea-surface temperature, salinity, wind speed, upwelling indices and hours of bright sunlight. Independent variables were also lagged against gray whale abundance to search for time lags between variables. When combine in a multiple regression model, wind speed and upwelling lagged two years explained 89.6% (p = 0.004) of the variance in gray whale abundance. A possible pathway for this relationship may exist through local kelp populations, which have the ability to affect gray whale prey abundance.
14
Zou, Yu-Ren, and 鄒雨人. "Data Prefetching for Cellular Networks using Grey Relation Analysis." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/36488054614444104198.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>電子工程系<br>93<br>People who live in these times seize every minute and second. They always catch a lot of information including: where have parking area, whether there is a vacancy at the parking area, where smooth traffic and more multimedia message at short time. If user uses data prefetching policy that loads information about location to mobile host beforehand, he will save a large of time. On the contrary, he will search useless information constantly. So people use data prefetching policy to solve the problem that waiting time and wireless network line is unstable, it is one of the questions that everybody discusses.
People's movement is an uncertain system that often be influenced by the factor of surroundings, including landform, time etc.. If we want to predict the human movement, we will need to consider the influence factors. So, this research uses the grey relation analysis to predict People's movement, and expects that mobile host can prefetch proper object by considering the influencing factors. Especially, this research set two-layer adaptive law so that it promote hit ratio and reduce prefetching object.
Finally, we compare two-layer data prefetching policy with other policies, including distance-base data prefetching policy, partition-data prefetching policy and path-base data prefetching policy. The above comparisons are based on the two evaluation factors: hit ratio and prefetching object. The experimental results verify that the two-layer data prefetching policy is better than others.
15
Yumin, Su, and 蘇育民. "The Application of Grey Relation Analysis on Food Technology." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/67408795992258541428.
Full textAbstract:
碩士<br>國立屏東科技大學<br>食品科學系<br>87<br>Principle Component Analysis （PCA）, a statistical method, has been used broadly to analyze data in which similar nature of data will be closely or roughly clustered together, while rest of data may be scattered around the graph. To obtain well results of clustering, PCA needs enough input data. Besides, it shows no quantitative information that cannot help to interpret the relationship between each datum.
In this paper, Grey Relational Analysis （GRA） was proposed to apply to assist PCA for data clustering, identification of food system, and analysis of the food quality. The applications have been extended to the adulteration problems of soybean sauce, sesame oil, and multiple attribute decision making that can be used for choosing the proper brand of market milk powders.
The experimental results show that GRA is capable of identifying and ordering those similar nature of input samples based on standard data that we have built in data-base. Therefore, GRA can be regarded as an efficient technology for food analysis.
16
BettyDennison and 唐貝蒂. "Benchmarking Financial Ratios:A Grey Relational Analysis Approach." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/55548647372235212313.
Full textAbstract:
碩士<br>國立成功大學<br>國際管理碩士在職專班<br>98<br>This study focused on how financial ratios could be used as indicators of the overall performance of banks relative to their competitors. In addition, this study introduced Grey Relational Analysis (GRA) as a methodological approach to analyzing small sample sets in financial research. We used GRA to rank 28 financial ratios from 43 separate banks spanning 8 countries within the ASEAN region for the study period; 2004-2008. The results produced two sets of rankings: one that ranked the performance of each financial ratio by individual country, as well as a total ranking for the 28 financial variables for all banks included in the study. GRA was then administered to cluster each of the variables into references ratios based on the following six financial dimensions: profitability, asset utilization, leverage, liquidity, growth, and stock performance. Study limitations and suggestions for future research were further outlined in the discussion.
17
Chang, Hao-Chun, and 張皓鈞. "Image Compression Based on Grey Relational Analysis." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/39449307730730698079.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>資訊工程研究所<br>88<br>VQ is a well-known effective technology for image compression at low bit rate with high performance. General Lloyd Algorithm is the kernel idea of VQ method and usually used in the clustering applications. However, in a large volume and high dimension system such as image compression, the conventional GLA technique usually falls into local optimal trap. To solve the problem in the practical applications, this paper proposes a new image compressor based on the grey relational analysis, which includes of three parts, preprocessing, training, and splitting algorithms. Experiment results show that at the same bit rate, the proposed image compressor has higher quality reconstructed image than that of traditional GLA technique.
18
LO, CHING-CHUNG, and 羅敬忠. "Gray Relational Analysis used in the Furnace excess air volume contro." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/31482913776643651766.
Full textAbstract:
碩士<br>高苑科技大學<br>土木工程研究所<br>100<br>According to a 2008 technical report by the International Energy Agency (IEA), by 2050, the global economy will grow to be four times of its current size, energy demand will increase by1.7 times, and CO2 emissions will increase by 2.3 times. In addition, global temperature will rise to 6℃ or higher. These findings reinforce the understanding that it is an urgent global issue to respond to the trend in changes in global energy use, the reduction of GHGs emission, and soaring energy prices.
From 1980 to 2010, Taiwan’s energy consumption grew at a dramatic rate of approximately 4.66% and in 2010, among total energy supply, domestically produced energy in Taiwan accounted for 0.61% with the other 99.39% imported from other countries. This indicates Taiwan’s heavy reliance on imported energy. In terms of type of energy in demand, 42.79% comes from crude oil and fossil fuel products followed by 33.08% from coal and coal products, 14.10% from natural gas, 9.54% from nuclear power, 0.32% from regular hydro power, 0.10% from solar and photovoltaic power and 56% from wind power.
This shows that 56% of Taiwan’s energy consumption depends on fossil fuel and natural gas energy. In order to achieve the optimal effectiveness of minimizing energy consumption, this study examines correlations between variables of the petrochemical industry refining process that provides fossil fuel and natural gas as energy. During the petrochemical refining process, there are variables such as the furnace type used for the distilling process. This study uses the test values of furnace plants during the distilling process to apply an analytical process derived from “The Model Study of the Application of Ash Associated Analysis to the Optimal Value of Independent Variables of the Experiment.” With the numerical method of ash associated analysis, residual air at different volumes (2.4%~3.6%) is used as the expected value of a certain series to discuss the average associated level of factors in the series including “vacuum pressure (mmH2O)”, “NOx”, “FG”, “radiation area (T)”, “convection area (T)”, “FO”, and “pre-heated temperature (T)” for the reference of “residual O2” obtained during the normal operation of the furnace. The results are shown below:
1.When residual O2 increases from 2.4% to 3.0%, there is an increasing trend for the average correlation of other factors analyzed.
2.After residual O2 increases higher than 3.0%, there is a decreasing trend. For the convenience of factory operation, it is suggested that residual O2 shall be controlled between the ranges of 2.9% - 3.1% for optimal energy effectiveness.
3.The application of the expected value to an on-site furnace test is found to reduce the emission of nitrogen oxides, which saves an annual fuel consumption of 1.1 × 106 m3, and decreases CO2 emissions by 1.3×103 tons.
19
Chieh, Lin Heng, and 林亨杰. "Grey Relation Analysis and Neural Network for Analog Fault Diagnosis." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/05613242738986683188.
Full textAbstract:
碩士<br>國立臺北科技大學<br>電腦通訊與控制研究所<br>90<br>For analog circuit fault diagnosis, the thesis proposes a novel model called Grey Relation and Neural Diagnosis Model (GRNDM). Grey Relation and Neural Diagnosis Model not only can detect the errors but also diagnosis the fault location. GRNDM first uses grey diagnosis model to detect whether the circuit has faults then uses neural network model to find the fault location. It improves the efficient of analog diagnosis. GRNDM also solves the problem that there does not exist a fixed and efficient model for analog testing. Using GRNDM, we can quickly build our fault dictionary and then diagnosis. GRNDM can get a low operation, fast and simple to design suitable for any different analog circuits. At last, we used a continuous variable state filter circuit for simulation. In the result, GRNDM model can easily fast and efficiently to establish the diagnosis system not only for hard faults but also for soft faults.
20
Chan, Su-Ming, and 詹書銘. "Analysis of Credit card risk management Using Evolutional neural network and Gray relational analysis." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/567266.
Full textAbstract:
碩士<br>朝陽科技大學<br>財務金融系碩士班<br>93<br>The amount of issued credit cards has increased rapidly and is sixteen times the size of the past decade issues owing to the competition of credit card market in Taiwan. The annual amount of credit has also growth 9.54 times. However, most financial institutions focus on the prior process of credit card verification instead of the posterior process of the risk management after issued. As a result, the delinquent payment of credit card grows fast. The aim of this study is to construct an efficient credit risk prediction system to detect the default of card holders correctly.
This study divides the information of the card holders into essential, account details and payment ranking and then applies evolutional neural network to predict the default cases. Our research has found that more additional variables can not improve the accuracy of the perdition. The account details and payment ranking produce higher performance during the empirical study. This study also applied gray relational analysis to make a comparison of variables including gender, ages, incomings, resident, marital status and educational level. Four different gray relational methods are used to filter the most important variables which act as the inputs for the evolutional neural network to predict the next delinquent payment and achieve the risk management.
This study focuses on the account details and payment conditions after credit cards have issued will enable the banks to trace the behaviors of the consumer, manage default risks and improve their profits eventually.
21
Chen, Huang-po, and 陳惶博. "The Study of the Relation between Volatility Index and Macroeconomic Indicators-Using Grey Relational Analysis and Artificial Neural Network." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/58936758002465364765.
Full textAbstract:
碩士<br>中原大學<br>企業管理研究所<br>97<br>Abstract
In the process of economic development, short-term economic fluctuations of the business cycle will be detrimental to long-term economic development. Since the 1980s, financial market liberalization and international trends have been initiated, but in 1997 after the Asian financial crisis, the macroeconomic indicators such as the exchange rate, interest rates, stock index and other factors affected the stability of financial markets. Since June 2007, the global economy experienced by a brutal Subprime Mortgage Crisis, the scholars have began to explore how effectively the relevant economic data can be used to forecast the volatility of the financial market, with a view to the prevention of the possibility of economic recession. To explore the grey correlation among variables, this study used the macroeconomic indicators as the impact factors to examine volatility index as a predicting indicator of analysis of market returns and future stock prices. With a view to the timely amending of monetary policy helps for stablizing monetary policy and curbing inflation.
In this study, six volatility indexes including VIX (CBOE Volatility Index), VXD (CBOE Dow Jones Volatility Index), VCAC (CAC 40 Volatility Index), VAEX (Amsterdam Exchange Volatility Index), VBEL (Brussels stock Exchange Volatility Index) and VFTSE ( FAST 100R Volatility Index) from the five countries, and six macroeconomic factors such as the exchange rate index (euros / dollars), the interest rate (6-month yield U.S), stock price index, Commodity Research Bureau Index (CRB index), and crude oil futures index (Brent Crude, WTI West Texas Intermediate crude oil) have been used. First, this paper utilized Grey Relational Analysis on the variables by a relevant rank, then applied Artificial Neural Network system of Back-propagation Network and of Recurrent Neural Network to verify the predicted results respectively.
The daily data was taken from January 2000 to December 2008 of the nine-year period. By sorting the Grey Relational correlation from six variables, the results showed that volatility index has a higher grey relational correlation with Brent crude oil futures index; followed by WTI West Texas Intermediate crude oil index; exchange rate (euro / dollar) and CRB Commodity Research Bureau index ; and then followed by stock price index and the interest rate. For testing the system of Back-propagation Network and the system of Recurrent Neural Network, the values of Mean Absolute Error (MAE) for two types of neural networks can be largely reduced to 0.1 and below, while Back-propagation Network obtained better forecasting results. Most MAEs can be decreased for the test results of 33%samples. By examing Artificial Neural Network system, the factors with the lower Grey Relational correlation with relatively large difference were superior to those with higher correlation, inferencing better learning results from the neural network.
22
Lin, Shih-fu, and 林士福. "Plating Film Process Optimization with Grey Relational Analysis." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/29771405608340395637.
Full textAbstract:
碩士<br>逢甲大學<br>工業工程與系統管理學研究所<br>94<br>The objective of this paper is to search the optimal process parameters level by the Taguchi method with Grey relational analysis.
This model would benefit the thin film industry who seeks the practical quality engineering technology of the best parameter level when it faces the requirements of a multi-response. In this thesis, L8(27) orthogonal array was used to plan experiment and to acquire data for the optical properties(working pressure, substrate temperature, deposition rate and annealing temperature). For process of the thin film, the overall process quality to achieve three quality characteristics including mean refractive index, mean extinction coefficient, and surface roughness were discovered by Grey Relational Analysis in light of overall process quality consideration. The results show that (1) substrate temperature and deposition rate are apparent to influence the three quality characteristics. (2) substrate temperature 300(℃) and the deposition rate 3(Å/S) are the best parameter level。
23
Lin, Hsin-Hsu, and 林信旭. "Applications of Grey Relational Analysis for Integrated Navigation." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/48108251433287413375.
Full textAbstract:
碩士<br>國立臺灣海洋大學<br>通訊與導航工程系<br>96<br>The Global Positioning System (GPS) and inertial navigation systems (INS) have complementary operational characteristics and the synergy of both systems has been widely explored. Most of the present navigation sensor integration techniques are based on Kalman filtering estimation procedures. For obtaining optimal (minimum mean square error) estimate, the designers are required to have exact knowledge on both dynamic process and measurement noise. However, noise are unknown and varying with time, the vehicle also with difficulty guarantees continues the regular movement, therefore to establish the actual dynamic model is extremely difficult, resulting in the Kalman filtering performance degradation. The case that theoretical behavior of a filter and its actual behavior do not agree may lead to divergence problems. In system design, H∞ filter can be employed to ensure that the energy gain from the disturbances to the estimation error will not exceed a pre-specified level. The philosophy of such type of filter is designed based on the approach of linear quadratic (LQ) game theory, which is sometimes called a minimax filter due to the fact that it minimizes the worst-case performance under noise uncertainties. Results based on H∞ filtering approach may provide better performance than those based on standard Kalman filtering when the noises are non-Gaussian, or when the statistical knowledge of noise is poor. The more the uncertainty of noise knowledge is, the worse the solution of the Kalman filter becomes.
In this paper, tuning of the prescribed level of noise attenuation (r) of the H∞ filter is performed through the grey relation. The system with partial unknown structure, parameters, and characteristics is called a grey system. The grey system theory can be employed to improve the navigation accuracy performance without sufficient information or with highly nonlinear property. The grey relational analysis (GRA) uses information from the grey system to dynamically compare each factor quantitatively. This approach is based on the level of similarity and variability among all factors to establish their relation. The relational analysis suggests one approach to make prediction and decision, and generate reports that make suggestions for tuning the parameter. It also provides data to support quantification and comparison analysis. The GRA-aided H∞ filtering for GPS navigation processing is conducted and the resulting performance is discussed.
24
Chen, Hsiao-Ying, and 陳曉瑩. "Applied Grey Relational Analysis in the liver Function." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/83299755799315246533.
Full textAbstract:
碩士<br>建國科技大學<br>自動化工程系暨機電光系統研究所<br>97<br>Abstract
Liver diseases and liver cancer has been the top ten causes of death among ten leading causes of death in Taiwan and always in the top. Usually, in the general liver function examination, biochemical test is the most common and a test that show the most direct reflection of the body condition. The health subject can determine the further inspection according to the inspection results. Nevertheless, the result of biochemical tests is not absolute, nor is the results represent in the normal range will not be suffering from liver disease. Therefore, how to let the health subject understand his/her own health condition is the main purpose of this paper. So, this paper makes use of grey relational analysis method and according to the standard values of hospital test results to be divided into Level method and compare with the health subject’s test results. It will convert the past ordinal decision into cardinal quantitative evaluation value and evaluate liver function’s level. At the same time, it develops MATLAB GUI toolbox to assist the numerical calculation, which can complete a medical assistance platform for liver function evaluation. It not only provides a further step of making decision for doctors in order to promote medical quality, but also provides a new research direction of this field.
Keywords-liver disease, liver cancer, biochemical tests, grey relational analysis, cardinal, MATLAB, liver function evaluation.
25
LIN, SHUN-TE, and 林順德. "Digital Watermarking Field Research Using Grey-relational Analysis." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/06716099152677352491.
Full textAbstract:
博士<br>國立臺灣科技大學<br>電機工程系<br>100<br>Watermarking technology has been widely used in multimedia copyright protection with good progress in development. Watermarking in sound files and 2D or 3D images with good features has been reported in many studies. However, each watermarking scheme has its advantages and disadvantages against various attacks, and the optimal resistance against all attacks has yet to be achieved. Usually, the grey-relational analysis method is used to analyze uncertain factors, as it can obtain good results. In this dissertation, we first find the optimal watermarking scheme using grey-relational analysis. The experimental results show that a relatively better watermarking scheme can be selected based on the various requirements of watermarking. The aim of this study is to use the grey-relational analysis method to assess watermarking schemes that have been published in recent years. Watermarking methods proposed in recent studies have needed to determine the strength of the factor-added watermark or the threshold value factor strength in the watermark inspection method. The parameter is a tradeoff between the strength of the watermark and the quality of the watermarked image. In the proposed method, the optimal threshold value factor strength and the optimal embedding region allow the watermarking methods to achieve a combined effect for the optimal resistance to various attacks. The experimental results show that the optimal threshold value factor strength and the optimal embedding region can be selected using grey-relational analysis.
26
Chung, Hsiang-Yun, and 鍾翔雲. "Evaluating Facility Layout by Using Grey Relational Analysis." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/jngwp7.
Full textAbstract:
碩士<br>國立臺北科技大學<br>工業工程與管理研究所<br>97<br>Facility Layout Problem means the problems of facility
or department’s assignment. Due to find an available
solution, more studies let facility layouts reach to minimum of total transportation cost or maximum of total closeness rating. Thus the study should consider more factors simultaneously to evaluating facility layout.
In order to obtain the research need effectively, and increases the findings worthily. The study expects to consider more factors to evaluating facility layout. It considers the minimum of total transportation cost and shape ratio of the entire layout , maximum of total closeness rating, area utilization of the entire layout and layout flexibility.
The study will build an easy and convenient model to evaluating facilities layout. In addition, the study also develop a application of visual basic with excel to calculate the value of considering factors and evaluate the suitable facilities layout.
27
Liao, Hong Yi, and 廖紘毅. "Grey Relational Analysis for Trailing Arm Tube Hydroforming." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/2n5956.
Full textAbstract:
碩士<br>國立虎尾科技大學<br>創意工程與精密科技研究所<br>100<br>Along with the trend of development for weight reduction, energy-saving, low-cost, and high performance, tube hydroforming technique has become one of the major manufacturing technologies in the automotive industry worldwide.
This work presents the tube forming of a trailing arm. The trailing arm is an automotive tube part in a complicated 3D geometrical shape. The process of forming should be performed pre-bending twice and a hydroforming. This work firstly utilizes the finite element method to simulate the forming process of the trailing arm. Through the adjustments of the process parameters, such as velocity of left and right punch, internal pressure, and so on, it examines the level changes of these parameters related to the influence trend of the wall thickness of the forming tube, the distribution of equivalent stresses and strains, and the formability.
Secondly, by the orthogonal array and factor response table in Taguchi Method, take the minimum wall thickness and the maximum equivalent stress as the object functions, and obtain the optimal parameter combinations corresponding to each single quality object with nominal-the-best and smaller-the-best, respectively. Finally, by grey relational analysis, the above single quality objects are integrated as a multi-quality object. Re-establish the factor response table to figure out the optimal parameter combination fulfilling a multi-quality object, and compare the results with those obtained from the single quality object.
From the analytical results, due to the complicated geometrical shape of the trailing arm, it found that the velocity of the right punch for billet material feeding should be higher than the left to prevent the bursting of the tube wall on the right side due to the bulging of the internal pressure since the tube diameter on the right side is larger than the left one. This is also helpful for the success opportunity of forming. From the factor contribution rate in analysis of variance for single quality object, it can be found that the major process parameter that affects the wall thickness is the left punch velocity, and the major process parameter that affects the equivalent stress is the internal pressure. The minimum wall thickness obtained from the single quality object is larger than that obtained from the multi-quality object; meanwhile, the optimal maximum equivalent stress obtained from the single quality object is smaller than the multi-quality object. This is because the single quality object only satisfies the single object and unable to match the other quality requirements at the same time. With grey relational analysis, the optimal process parameter combination of the multi-quality object can be obtained.
28
Hsu, Wei-Chun, and 徐偉鈞. "Evaluation Criterion of Hillsides Development Established on the basis of Grey Relation Analysis in Grey Theory." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/5afsyp.
Full textAbstract:
碩士<br>國立成功大學<br>都市計劃學系碩博士班<br>90<br>Architectural industry developed rapidly during 1981-1997. There were a lot of hillsides development cases at urban edges. They caused hillsides disasters by unreasoning land use and overloaded development. Therefore this study aim at effective control hillsides development with the view of total mass control. At is expected to reduce natural ecological impact to the minimum and to protect people's living quality and safety.
These improbable executions not only trigger the immediate construction disasters. In order to effectively manage the hillside construction project, key execution factors must be first identified .The focus of this paper is to adopt method of Grey Ranking process to survey the factors and their weights. Based upon the above-mentioned results, an appropriate hillside construction procedure is then proposed.
29
Wei-Jen, Tsai, and 蔡幃任. "Application of Grey Relational Analysis on Insurance Products Choice." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/24612919359544173392.
Full textAbstract:
碩士<br>亞洲大學<br>資訊工程學系碩士班<br>98<br>Insurance have two hundred years of history. Insurance form and appearance are constantly changing along with society's pace. In recent years, the Government is actively promoting the pace of internationalization and liberalization. In addition to financial and insurance personnel must be familiar with insurance, general business, families, and individuals also need to know about the insurance. Today, everyone has two life insurance policies has become a foundation. Select insurance products become increasingly progressive general population or family must face an important topic. However, the insurance have many kinds. Selling insurance salesman, marketing methods used are the following. The latest insurance products sold to existing customers. Selling all the basic insurance products of people in the first met. In recent years, but adds the items of investment insurance of such goods. The emergence of new products to sell goods salesman in need has been learning. Experienced salesman to a customer will want to sell all and keep all the kind of the insurance products. The new salesman is to find his favorite event has been selling goods. When choosing insurance products, salesman and the customer choice between the way of the few. In this paper, we use “Grey relational analysis” method with insurance products of choice. Using this method, the most important thing is to use fewer data and data uncertainty in the choice of insurance products. In principle, our research approach is based on ordinary salesman doing based on data from market research to obtain data. Then we use data to arrange obtain from grey system. So we can understand the intention of select insurance products about people. To provide decision-making information to allow salesmen to understand the first time the people in the choice of insurance products on the based.
30
Horng, Yeong-Chang, and 洪永昌. "Taifex Option Trading Strategy based on Grey Relational Analysis." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/62952002252919881586.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>資訊工程系<br>99<br>The thesis is based on Grey Relational Analysis of Grey Theory to analyze the Relationship of Grey Relational Grade between TAIEX and technological Index, then obtain the buy or sell signal to construct Trading Models for Taifex Option Market. The research of thesis has theree stage. First stage’s purpose is obtain the optimum day parameter of every index decide against the Grey Relational Analysis between TAIEX(D+30 Day) and every index. Second stage’s purpose is obtain the optimum value range of every index decide against the win probability of Grey Relational Analysis between every index and TAIEX in rise or fall down status. Last stage, according to second stage’s result to construct Trading Models based on AiSM Trading System.
Estimating the profit of every Trading Model got several conclusions as below. The combination of K&D can obtain the highest profit. The profit of combination of D and other index is higher than K and others. The profit of combination of RSI and other index is higher than CCI and others. The profit of entering into with out-of-money ±200 and ±100 respectively according to first and second win probability is better than entering into with out-of-money ±100 totally.
31
Shen, Kuei-Feng, and 沈桂鳳. "Applying Grey Relation Analysis to Dynamic Materialized View Selection for Data Warehouses." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/14771207468539669702.
Full textAbstract:
碩士<br>義守大學<br>資訊管理學系碩士班<br>92<br>Data warehouse is a repository that stores a large amount of history data and provides the OLAP tool (On-Line Analytical Processing) for users to view the data from many different perspectives. However, aggregating heavy data by OLAP is very consuming. An effective approach to reduce the response time is to precompute and store the results of user’s queries, called materialized views.
Due to the limited storage of warehouses, it is impossible to store all materialized views. Therefore, materialized view selection and maintenance become a very important issue in the data warehouse environment. Many different factors affect the choice of materialized views. In a dynamic environment, it is difficult to determine which factors are more important and which are inferior. Picking the suitable views to materialize thus has become an imperative issue for warehouse implementation. In this paper, we apply the grey relation analysis to select and replace the materialized view in order to respond to the user’s queries efficiently.
32
Jiuan-Hung, Ke, and 柯俊宏. "Grey Relation Analysis and Taguchi Method in Reverse Engineering Points Cloud Processing." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/83330696982126678580.
Full textAbstract:
碩士<br>大葉大學<br>自動化工程學系碩士班<br>91<br>In recent years, reverse engineering develops rapidly. Its definition changes from narrow contact, non-contact 3D points data scanning, processing to broad figures scanning and computed tomography (CT) medical image processing. Image processing transforms image data to contour data points. Immense data points will affect the rate of processing time. How to deal with such a lot of points data is the crucial issue for the RE process.
The research is dedicated to integrate the geometric model for curves interpolation, Taguchi’s parametric design method for reducing experiment times, grey relation theory for optimum combination. Geometry model builds fitting curve characteristics in less data points. Taguchi method can abridge experiments in cost and time saving. Grey relation analysis search for optimum solution.
The following aims have been achieved：
(1)Image processing and grey prediction used to transform image data to points data.
(2)Grey relation analysis and Taguchi’s method integrated the geometric model to establish an optimum fitting curve module.
(3)Two examples are shown to verify the system：
(a) 2D calligraphy is used and verified in copying technology.
(b) CT files of skeleton used to establish 3D RP model in medical image processing.
33
Lin, Yung-Chei, and 林永吉. "A Study on the Relating Factors of the Operating Performance of Financial Holding Companies-By Grey Relational Analysis." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/84425036352467069799.
Full textAbstract:
碩士<br>朝陽科技大學<br>企業管理系碩士班<br>91<br>Abstract
Recently, financial liberalization and internationalization have become a world trend with innovative financial goods, a flourishing development of communicative technology, and synthetic managing various business in banking, negotiable securities, insurance, and investment since developed countries lifted up or liberated all kinds of financial controls. In 1999, “Gramm-Leach-Bliley Act” was legislated in the U.S., and the limits set to banking industry’s operating other business were eliminated formally. Adapting to the whole environmental changes, the Taiwan authority practiced “Law of Financial Holding Company” officially on January 1, 2001, intending to strengthen domestic financial systems, to assist the financial industry developing into a large scale, and finally to lift up the global competition of Taiwan financial industry.
In 2001, 14 financial holding companies were permitted to set up by Financial Department, which announced a new era of size-enlarging of Taiwanese financial industry. After entering WTO, it goes without saying Taiwan is confronting a harsh competition; therefore financial holding companies has to draw up various kinds of competitive strategies to adapt the surroundings simultaneously.
This research chooses 33 variants which influence financial holding companies managing performance through questionnaires, inspecting higher ranking managers in financial holding companies, banking, insurance, stocking, and etc, and their opinions on the managing performance as well. Besides, grey relational analysis together with scholars’ opinions will be organized and compared with purpose of explore the maximum variants. A proved result that influential factors tallied with now.
By exploring the financial market and environment in Taiwan and analyzing the problems confronted by these corporations, several crucial factors, which profoundly influence imminent managing development in Taiwanese financial holding companies, can be concluded and consequently, with the guidelines, the companies can inspect the changeable surroundings, their advantages and weakness in different periods in order to adapt, to strengthen their competence and to offer effective management models and directions for their own operating course and global strategy.
34
CHOU, PO-YEH, and 周伯燁. "Design of Taiex Options Strategy based on Grey Relational Analysis and Grey Model Prediction." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/5mt9ws.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>資訊工程系<br>100<br>The main purpose of this paper is to use AiSMFO trading platform to find out the Grey Relations among the daily closing-price of TAIEX and some popular technical indicators with different durations to get the best long-term technical indicators. Then, using these known long-term technical indicators to develop buying and selling trading strategies which apply GM(1,1) on these short-term technical indicators. In the process of analyzing trading strategies, the best constructing points of GM(1,1) are determined by the evaluating results of TAIEX training data. Finally, the enhanced performance can be evaluated though the comparison between TS (Traditional Strategy) and GPS (Grey Prediction Strategy).
35
Pai, Jheng-Cyuan, and 白正權. "Apply Grey Relational Analysis in the Performance Analysis of in 161kV GIS." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/93661842172177249985.
Full textAbstract:
碩士<br>建國科技大學<br>電機工程系暨研究所<br>103<br>According to TBM, GISs are routinely subjected to an external inspection every 6 years and an internal inspection every 12 years. Because of the high number of GIS equipment, problems associated with excessive maintenance and increases in the maintenance costs emerge. Furthermore, the controversial termination of the construction of nuclear reactor 4 and the increase in the price of electronic products necessitates examining the operation cost discreetly. To evaluate the feasibility of circuit breaker maintenance (CBM), each file must be inspected routinely. The data obtained in such inspections can be used as a reference in evaluating the risk of accidents. In addition, the aforementioned data can be combined with relevant references to evaluate risks. Finally, the standard of the maintenance reference can be obtained, ranging from high-risk to low-risk.
Because of the importance of GISs to electronic systems,Grey systems theory was applied in this study. The 161-KV GIS in five transformer sections of the TPC maintenance station in Taichung was also used. Furthermore, this study collected inspection and electricity supply data spanning 6 years. These data were used to determine how the GISs operate and rank the GISs of the same brand at the same transformer station to create a reference of CBM and low-cost maintenance. In addition, this study evaluated the durability of each GIS brand to determine the relationship between operating structure and durability. This analysis was performed to prevent the looming danger associated with GISs and to
heighten the stability of electricity supplies.
36
Li, Chia-Yuan, and 李嘉淵. "Apply Evolutional Neural Network, Gray Relational Analysis and Fuzzy-Neural in Real Estate Appraisement." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/8e6amh.
Full textAbstract:
碩士<br>朝陽科技大學<br>財務金融系碩士班<br>93<br>Real estate is one of the most useful financial instruments and can be applied to the purposes of the settlement of claims, financing, auction and taxing. To make most use of this financial tool requires appraising the assets accurately. In general, the comparative method of markets is a common approach for the evaluation of real estate. However, the selection of variables and related weights of this method relies on the assessor’s subjective judgment and the justice and rationality of results are disputed.
Appraisement plays a very important role in the real estate market. Appropriate appraisement can provide the consumers and investors sufficient trade information and also support the planning of the government real estate police. As the real estate market in Taiwan is not a perfect market, the consumers are prone to suffer loss due to the lack of correct appraisement information. As a result, the precision and circulation of the appraisement information is critical for the real estate market.
Without the assistance of sophisticated appraisement techniques, real estate appraiser’s results can not convince the consumers. This study integrated evolutional neural network, gray relational and neural-fuzzy analysis approaches to construct an intelligent system and provide an objective view for the appraiser. The gray relational analysis is applied to extract important variables which are the inputs for the neural network during the empirical test. The structure of prototype system built in this study will provide a reference and basis for the development of advance real estate appraisement system in the future.
37
賴旻佑. "Using Gray Relational Analysis for Assessing Recreation Potential in the Tributaries of Shihmen Reservoir." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/40289442635402634146.
Full textAbstract:
碩士<br>中華大學<br>營建管理研究所<br>95<br>Ecotourism has been a hot domestic leisure and entertainment activities, it was also affect regional economic development, which biological diversity, uniqueness and the environment condition impacting on Ecotourism activities promotion.There are many rivers in internal ground, which originates from the mountains and through the changeable forest then entered plain, the river itself and surroundings has been providing a diversity of recreational functions.Although there were relevant research of the water areas activity for home, but for evaluated river recreation potential of related research is lacking. For the Shihmen Reservoir in the upper reaches of four streams, two years investigating the situation, to probe into river recreation potential and values for various streams. The results show that：(1) Assessment model three dimensions under some test items showed no difference validity, and therefore be deleted. And the evaluation of different evaluators consistency analysis, showing good consistency, showed high reliability. (2) The difference from the test can take place to assess the potential value of the river, showing different section of the river showing different environmental characteristics, has also shown the difference potential and value.(3) Every river section comparison with potential and value, among them Karla river ST4 have the highest evaluation, according to priority Kuzhi river ST3 and Kuzhi river ST4, and appraise the lower have Shibichiao river ST1, Junghua ST4, and Shibichiao river ST3. Based on the findings, the assessment model based on the river's environmental resource properties, to assess its potential for recreational value, and this offers application to river recreatiion planning, judge that develops different tactics. In Shihmen case, these characteristics and the potential for resource evaluation results, contribute to the future development different activities and Ecotourism routes Planing.
38
Teng-ChinYu and 游登進. "Applying Fuzzy Theory and Grey Relation Analysis to Optimize Solar PV System Design." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/50946089839866410397.
Full textAbstract:
碩士<br>國立成功大學<br>工業設計學系碩士在職專班<br>104<br>A new methodology to perform the optimal decision of developing a solar PV system is pro-posed in this study. The methodology provides an integrated design decision for engineers with different backgrounds and meets the desired system reliability requirements with the best value of solar PV system (BIPV). This study combines Fuzzy Theory and Grey Relation Analysis (GRA) to generate the optimum design decision and improve the efficacy of the solar PV system according to the concept of Concurrent Engineering (CE). This methodology can enhance the efficacy and quality of the solar PV system. The planning of solar PV system and its design examination in this study follows the laws and regulations of Taiwanese solar energy policy. All of the solar PV system data will be uploaded to the cloud system (Dropbox), and the standards of management authority are set simultaneously throughout the performance of different professional stages. The proposed model could be applied to solar PV systems with the power less than 50kW. The results show that the factors that trigger project failure can be known in advance and then be excluded from the process of developing a solar PV system. Moreover, an application (APP) constructed in this study can be used to mobile the results of the solar PV system, and get a report generated based on Fuzzy Theory and Grey Relation Analysis. With this methodology, the best location and design plan can easily be obtained; whereas, the Concurrent Engineering (CE) concept applied will effectively shorten the pre-required schedule and enhance the engineering quality of developing a solar PV sys-tem. Finally, a Solar PV System (4.16kW) was adopted to verify the feasibility of the methodology proposed in this study.
39
Liu, Kuan-Hua, and 劉冠鷨. "Applying Grey Relation Analysis and Fuzzy Inference on Processes with Multiple Quality Characteristics." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/26246459758300371224.
Full textAbstract:
碩士<br>東海大學<br>工業工程與經營資訊學系<br>94<br>Taguchi method has been extensively used for enhancing product quality in industry. More than one quality characteristics must be simultaneously considered to effectively improve the product quality due to the increasing complexity of product design. However, Taguchi’s methodology only optimize on single quality characteristic.
Optimizing each quality characteristic separately may not result the optimality for the entire production. More often, considering one quality characteristic may conflict with the other. When the conflict exits, it is mainly resolved by the engineer's experience. Thus, the quality may not be optimized and could present the possible lost. The decisions made by the engineer are to choose the parameter levels which have the properties of uncertainty and fuzziness.
To find a feasible and effective solution for the aforementioned problem, this research first uses Taguchi method by only considering the single quality characteristic; then separately calculating the SN ratio according to the quality characteristic; then, using the obtained SN ratio and grey relation generation to conduct a pre-process on data; adopting the grey relational coefficient to construct the process parameter and the individual quality characteristic relations; finally using the fuzzy inference mechanism to find the best solution. This research proposed a parameter level selection method which solves conflicts on the selection of the quality characteristic and the parameter level. The proposed algorithm is implemented by MATLAB. To demonstrate its capability of determining the optimal parameter levels combination.
In order to show the effectiveness and practicality of the proposed algorithm, we apply this method to Carbon Nanotube Back Light Unit (CNT-BLU) Thick-Film Screen Printing Process. The results show that Grey Relation Analysis and Fuzzy Inference System can find the best production process parameter level combination. The proposed methodology can significantly reduce the cost and time on experiment during the period of new product experiment and the pilot production stage.
40
Liao, Yi-Ting, and 廖翊廷. "A Study of The Implication of Grey Relation Analysis to Assess Teacher’s Teaching." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/50410487242759465064.
Full textAbstract:
碩士<br>國立臺北科技大學<br>技術及職業教育研究所<br>89<br>Abstract
In the field of education, educators often needed to assess the performance of a person on a certain subject at a certain time. Most often statistics was applied as an interpretational tool to analyze data collected. However, when the number of sample was small, or when there was little data, the application of statistics would somewhat limited. Hence, Professor Julong Deng introduced the Grey system for effective processing of matters containing small sample, least data, and uncertainty. The applicability of the Grey system has already been verified in some areas.
This research explored (1) theories related to the application of Grey system in assessments; (2) feasibility of application of Grey association in assessment; and (3) advantages and disadvantages of the Grey system and statistics released to assessment analysis. In addition to explore the application of the Grey system the field of education, an empirical study was carried out to compare the results between Grey relational analysis and statistics analysis based on the data of student evaluate teachers’ teaching during 1997-1999 school years at National Taipei University of Technology.
After the analysis, this study discovered that the results generate from Grey relational analysis and statistics analysis were no different, statistically.
Keyword: test, measurement, assessment, Grey relational analysis, Grey system theory
41
Ma, Ming-Wei, and 馬銘偉. "Using Grey Relation Analysis in Competitive Strategies on TFT-LCD Industry in Taiwan." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/10731466102691657487.
Full textAbstract:
碩士<br>中原大學<br>國際貿易研究所<br>98<br>TFT-LCD is most important application about monitor industry, such as mobile phone, notebook, TV, car monitor and camera monitor. We can say that TFT-LCD is around our world.
Asia is the leader producer area in the world, include Taiwan、 Korea、 Japan and China. Taiwan and Korea are the top two countries that produce the TFT-LCD products. Strongly competition makes the two countries on edge. Then Japan put more effort on developing materials and equipments. China own large market in TFT-LCD and also have low cost production advantageous. So it will become more effective country in the world.
Because of the different resources about those countries, choosing the right strategies are important about competition advantage and gross profit. After the financial tsunami, there will be a lot of change about human consumption habits. It’s really a good opportunity to create more advantage. All countries will bring up more positive strategies to become the leader in the industry.
The research use Grey Relational Analysis method in grey system to calculate the priority about the Core Competence and Competitive Strategies. Grey System has common applied in different academic researches, and the applied range increase rapidly. Grey Relational Analysis is most important theory in Grey System. This research could provide the business to select the right strategies and contribute to the grey system application in the TFT-LCD research.
42
Chen, Yi-Shan, and 陳怡珊. "Applying Taguchi Grey Relation Analysis on Biological Freezer with Multiply-Object Optimal Design." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/95071289052545104889.
Full textAbstract:
碩士<br>國立高雄應用科技大學<br>機械與精密工程研究所<br>101<br>The objective of this study is to investigate the design of blocking temperature structure of biological freezer. In the study, ANSYS ICEM CFD software was used to create unstructured grids, and ANSYS FLUENT software was applied to analyze the performance of blocking temperature structure. Taguchi method combined with robust design method and gray relational analysis was used to optimal the design parameters such as the dimensions of blocking temperature structure, the height of the refrigerant tube, and the number of refrigerant tube lap. The analysis of variance was employed to find out the most significant factor influencing the product quality.
The results show that the best combination of parameters are A1B1C1D1E1, that is the dimension of blocking temperature structure with length of 500mm, width of 390mm, and height of 340mm, the height of refrigerant tube with 90mm, and the number of refrigerant tube lap with 3. These parameters combinations can indeed help company save cost and development time.
43
Hsieh, Tsung-Yen, and 謝宗諺. "The Optimal conditions in Electrochemical Machining by Grey Relational Analysis." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/73660033404071622973.
Full textAbstract:
碩士<br>國立中央大學<br>機械工程學系<br>105<br>Electrochemical machining (ECM), which is one of the non-traditional manufacturing processes, shapes workpieces by electrolysis. The advantages of ECM include high processing speed, independent of metal properties, no surface residual stress, no heat zone, and smooth workpiece surface with enormous potentialities and highly added values.
In this study, grey relational analysis (GRA) is used as the analysis tool. Compared with Taguchi method, GRA could have multi-objective optimization, while Taguchi has only single-objective optimization. This study has two parts, and material selection is the first part. The second part of this research is to analyze the influences of parameters (e.g.: electrolyte flow rate, electrolyte concentration, the feed rate of the tool and applied voltage) on the material removal rate (MRR), surface roughness (SR), and overcut (OC) by GRA in the spherical hole machining by ECM.
At first part, two kinds of novel stainless steel are conducted under the same conditions for selecting the workpiece with higher removal rate material (MRR). The choosing basis is the MRR because a lower MRR means more energy should be used to have the same results. As the result, SKD61 is chosen as the working material.
In the second part, grey relational analysis (GRA) is used to analyze the optimal conditions for spherical hole machining on SKD61 by ECM. Results show that the most important factors are electrolyte concentration and applied voltage. And the best parameter combination simultaneously acquired from the research is A3B2C2D3(electrolyte flow rate 3.98 m/s, electrolyte concentration 9wt%, the feed rate of the tool 0.2mm/min and applied voltage 15V).The resulting material removal rate(MRR), surface roughness(SR) and overcut(OC) of machined specimenare2.92mm3/min, Ra 0.69μm,0.71mm and average error is 2.0% respectively. Compared with the original working condition (A1B1C1D1), the GRA is increased from 0.34 to 0.96. It is more closed to the ideal working condition.
44
Huang, Yu-Yuan, and 黃佑元. "THE CMAC QUANTIZATION RULE BASED ON THE GREY RELATIONAL ANALYSIS." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/35208271101536910933.
Full textAbstract:
碩士<br>大同大學<br>電機工程研究所<br>91<br>Cerebellar model articulation controller (CMAC) is a kind of neural networks that imitates the human cerebellum and has attractive properties of learning convergence and speed. Quantization of input space plays an important role in the design of CMAC. Equal-sized quantization is a commonly used approach, but it cannot well represent the trend of a nonlinear function by finite knots, and then result in reducing the learning accuracy and wasting the memory storage size. This thesis therefore focuses on the quantization problem of CMAC. The proposed quantization rule is on the basis of grey relational analysis. In the beginning, the input space is adopted the equal-sized quantization by finite knots. After a complete learning iteration, the grey relation between the target outputs and the actual ones can be obtained. In accordance with the grey relational coefficients, the input space can be re-quantized to achieve a better learning accuracy and a well generalization ability. Simulation results on the function approximation shows that our method performs better than the conventional one in both the learning speed and the learning precision.
45
Huang, Chung-Chih, and 黃崇誌. "Applying FMEA and Grey Relational Analysis for Manufacturing Process Improvement." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/72200734559325583695.
Full textAbstract:
碩士<br>國立成功大學<br>工學院工程管理專班<br>96<br>This thesis studies how FMEA management tool is introduced into TFT-LCD Material manufacturer for process improvement. It is connected with Grey Relational Analysis and Analytic Hierarch Process.This methodology of structural and systematic procedure can be used to prevent the potential failure of models from happening during the manufacturing process, to discover the root causes, and then to take appropriate preventive actions. Based on this case study, we hope to review the application and effectiveness of failure risk management during the manufacturing process with FMEA, Grey Relational Analysis and Analytic Hierarch Process.
The results show that FMEA is able to improve the TFT-LCD Material throughput, and process performance during early mass-production. The conclusions are being drawn in the thesis as follows.
a. After implementing FMEA, not only have the risk levels significantly improved, but also the overall productivity and capacity increased.
b. With AHP and FMEA for accessing the risk weights respectively, and connecting with Grey Relational Analysis, we will accuracy to prioritize the failure models and causes which have negative impacts on process. This lets engineers find the opportunities for improvement in short time, and also avoid production cost loss from time delay.
c. This thesis conducts one procedure and management framework of how to improve TFT-LCD Material manufacturing process, which provides a knowledge management tool for precise manufacturing technology.
46
Chang, Yu-Teng, and 張譽騰. "The Study on the Data Processing of Grey Relational Analysis." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/84523107198668756356.
Full textAbstract:
碩士<br>南台科技大學<br>工業管理研究所<br>95<br>In the grey relational generation, there are four data processing methods nowadays. They are traditional data processing, linear data processing, generalized data processing, and piecewise linear data processing methods. For the traditional data processing method, there is no linear relationship between the raw data series and the after-processing series for the larger the better or nominal the best cases. The generated series will also become undefined while the minimum raw value is zero for the smaller the better case. The linear data processing method will generate a new series which may magnify or shrink the relationship among the raw data series. The generalized data processing method will lead to the new series undefined while the minimum raw value is zero for the smaller the better case. The piecewise linear data processing method consists of multiple linear relationships. Its calculation is complicated. The four data processing methods didn’t take the specification limits into consideration which is very popular in the manufacturing industry. In order to solve the problem, the research developed a data processing method which considers about the specification limits of quality characteristics. In addition, the research also proposed a data processing method which will not magnifies or shrinks the relationship among the raw data series while the raw data series are very close to each other.
In the real application, the relationship between the raw data series and after-processing data series is not necessary linear. It can be nonlinear. Based on this, the research proposed a method which first transformed the raw data series by loss function or signal–to-noise ratio method. Then apply the transformed data to any available data processing methods. This will make it become more suitable to the real cases.
47
Peng, Jui-Mei, and 彭瑞美. "Emotional Intelligence Training Needs of Teachers by Grey Relational Analysis." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/65529895552538149418.
Full textAbstract:
碩士<br>銘傳大學<br>教育研究所碩士班<br>103<br>Emotional intelligence (EI) has become an emerging topic of interest in various occupations research, including the field of education and teacher training. The aim of this thesis was to demonstrate the application of grey relational analysis (GRA) as a workable decision-making tool to prioritize emotional intelligence (EI) training needs of teachers. The literature has documented numerous studies showing that EI can be developed through proper trainings. However, measurement tools and method that could facilitate the evaluations of training needs among participants who are in need of EI training for better performance in their chosen fields of expertise. The study involved administering the emotional skills assessment process to 60 teachers in Taiwan. GRA was utilized to prioritize EI training needs of teachers. GRA is introduced as a valid decision-making technique for planning effective EI interventions. The results have implications for designing training courses targeting on enhancing weak areas of emotional competency. Interventions based on a training toolkit for developing high prioritized EI dimensions will be suggested for practitioners in order to enhance overall EI for participants in the study. Research implications will be discussed in accordance to findings of the study.
The utility of GRA as a decision-making tool to prioritizing training needs
for teachers.
48
Zhou, Zong-Sheng, and 周宗生. "Apply Grey Relational Analysis for the Influence Factor Weighting analysis in Liver Function." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/07640451322908795370.
Full textAbstract:
碩士<br>建國科技大學<br>電機工程系暨研究所<br>99<br>Abstract
Liver disease is the most cause of death in Taiwan, and there are about ten thousand people died of liver disease every year, and the rate is very high. Therefore, this paper aims to choose the most important impact factors, recognized by the medical field, as the judgment of liver function. It is hoped that through the in-depth research, the countermeasures to identify liver disease could be found effectively. Currently, biochemistry is the most common and direct way to reflect the quality of liver. However, only check the function of liver does not represent the health of liver entirely. Many considerations must be done to determine the full extent of liver function in professional judgment. Based on the reason and the limitation of national health insurance and medical scale in Taiwan, this paper applies GRA and grey weighting analysis of the grey system theory to identify the weighting of health index and impact factors of liver function. Moreover, in order to verify the accuracy of large amounts of data, the development of Matlab GUI has been done as the soft computing tool box. Through the actual analysis, the participants (312 inspected subjects) were entered into GRA into four levels. According to the Department of Health which provided the reference standard value basis, and the health index reached after calculation, the importance of five impact factors could be found through grey weighting analysis, and the orders are as follows: T-Bilirubin, Albumin, GOT, GPT and LDH, which are in good agreement with the actual situation. The paper integrated math methods and computer numerical calculation to construct the objective liver weighting factor analysis platform for medical assistance, which not only enhances the quality of medical care of liver function, but also provides a new research direction in the medical field of liver function.
Keywords: Liver disease, Biochemistry, Grey system theory, MATLAB GUI, Weighting, Quality of medical care
49
Lin, Chih-wei, and 林智偉. "On the performance measurement of new product development: an application of Gray Relational Analysis and Data Envelopment Analysis." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/7mnqx2.
Full textAbstract:
碩士<br>國立虎尾科技大學<br>工業工程與管理研究所<br>94<br>Rapid changes of science and technology and market have caused product life cycle getting shorter and shorter. The ability to introduce new product has already become the foundation for conpany to compete in globalization. The success of the new products can bring a great number of benefits and gain advantages of competition to company. However, on the contrary, if it is failed, it may cause company to lose seriously. It is therefore that company must develop new products with effective way. The measurement of new product development performance is appearing its important position gradually.
This research is focused on three ways of evaluating the new product development performance. Those are the Data Envelopment Analysis approach, the Gay Relational Analysis approach and a combination of the two approaches above. Followed by a case of electrical company in Taiwan for analysis, this research is also aimed at exploring the measurement results to specify the advantages and disadvantages for each of the measurement approach. It is hoped that the results could be considered as the reference for the industry and future study.
50
Chang, Pin-Chieh, and 張品傑. "The study of combination Grey Relation Analysis, Genetic Analysis, and Particle Swarm Optimization on the Credit Ranking." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/60904825355912639754.
Full textAbstract:
碩士<br>義守大學<br>財務金融學系碩士班<br>98<br>The study of combination Grey Relation Analysis, Genetic Analysis(GA), and Particle Swarm Optimization(PSO). Set up a credit appraised ranking another tool. First look for analyze the appraisal factor parameter enough to influence credit to comment in financial statement and financial affairs by grey relational analysis.
The study of the financial statements of an open information, integration of GA and PSO, Building up a Credit rating prediction model, the reference of the general public as an investment, this will help to enhance the credit rating of the fairness and reduce the human fault in evaluation, to establish an effective and has a fair credit rating system. The construction of the new credit rating model system, the first use of gray correlation analysis to filter the assessment of credit rating factors, to increase forecast accuracy, and through analysis of selected gray factor, and then through the Institute of Construction The credit rating model simulation training and testing can be a specific objective and efficient model to provide a bank or investor credit rating methods.
In this study, the genetic algorithm for the particle swarm algorithm model, the degree of convergence and the convergence of a single genetic algorithm relatively more radical convergence process, the results of this study to the number of nine ratings, a gene model has the best results.