1 |
資料挖掘在房地產價格上之運用 / Data Mining Technique with an Application to the Real Estate Price Estimation高健維 Unknown Date (has links)
在現今資訊潮流中,企業的龐大資料庫可藉由統計及人工智慧的科學技術尋找出有價值的隱藏事件。利用資料做深入分析,找出其中的知識,並根據企業的問題,建立不同的模型,進而提供企業進行決策時的參考依據。資料挖掘的工作是近年來資料庫應用領域中相當熱門的議題。它雖是個神奇又時髦的技術,卻不是一門創新的學問。美國政府在第二次世界大戰前,就於人口普查以及軍事方面使用資料挖掘的分析方法。隨著資訊科技的進展,新工具的出現,以及網路通訊技術的發展,常常能超越歸納範圍的關係來執行資料挖掘,而由資料堆中挖掘寶藏,使資料挖掘成為企業智慧的一部份。在本篇論文當中,將資料挖掘技術中的關聯法則 ( Association Rule ) 運用至房地產的價格分析,進而提供有效的關聯法則,對於複雜之房價與週邊環境因素作一整合探討。購屋者將有一適當依循的投資計畫,房產業者亦可針對適當的族群做出適當的銷售企畫。 / At this technological stream of time, it is able to extract the value of corporations’ large data sets by applying the knowledge of statistics and the scientific techniques from artificial intelligence. Through the use of these algorithms, the database will be analyzed and its knowledge will be generated. In addition to these, data models will be sorted by different corporation issues resulting in the reference for any strategic decision processes. More advantages are the predictions of future events and how much public is willing to contribute and feedback to new products or promotions. The probability of outcomes will be helpful as references since this information is referable to ensure companies providing quality services at the right time. In another words, companies will have clues in attempts to understand and familiarize their customers’ needs, wants and behaviors, as a result of delivering best services for customers’ satisfactions. Data mining is such a new knowledge that is commonly discussed in the field of database applications. Although it is a relatively new term, the technology is not exactly due to the analysis methods used. Before World War II, the analysis techniques were used in particular to the statistics in census or cases related to military affairs by the US government. Knowledge discovery has been one part of business intelligence in current corporations because these new techniques are inherently geared towards explicit information, rather than just simple analysis. By applying association rules from knowledge discovery technology, this dissertation will provide a discussion of price estimation in real estates. This discussion is involved in investigations into diverse housing prices resulting from the factors of surrounding environment. By referring to this association rule, buyers will acquire information about investment plans while housing agents will gain knowledge for their plans or projects in particular to their target markets.
|
2 |
英文文法關係之型態探勘 / Pattern Mining on English Grammatical Relations蔡吉章, Tsai, Chi Chang Unknown Date (has links)
一些研究發現常見的ESL(English as a Second Language)學習者在英語寫作時的錯誤為:用字不適當、動詞的形式不正確、句子缺少主詞、以及動詞時態錯誤。這些錯誤主要是起因於:字彙之不足、不清楚文法概念、本身母語的干擾。為了改善ESL學習者的寫作。我們希望能從文法關係的資訊來提供協助。目前,研究文法關係大多著重於字詞構成的單一文法關係,然而字詞在句中可能同時具備了不只一種文法關係。在我們的研究中,我們先發展文法關係樣式辨識系統。從句子中利用此系統提供使用者可搭配的文法關係,以了解可供使用的對應字詞。對應字詞可以輔助學習者適當地使用此關鍵字。此外設計使用者介面供查詢文法關係。以上,我們利用文法關係與搭配字詞來提供使用者英語寫作上的協助。而找尋樣式的做法,我們提出關聯法則和LSA(Latent Semantic Analysis)來實作。 / Some study found some common ESL (English as a Second Language) learners English Writing Error: improper use of the word, the verb form is not correct, the sentence lack of subject and verb tense errors. These errors are mainly due to: lack of vocabulary, grammar concept is not clear, the mother-tongue interference. In order to improve the ESL writing, we hope that the information from the grammatical relation to provide assistance. At present, the studies of grammatical relation mostly emphasize the word consisting of a single grammatical relation. However, words in the sentence may also have more than one grammatical relation. In our study, we first develop grammatical relation pattern recognition system. From the sentence using the system provides users with the grammatical relation, in order to understand the availability of the corresponding words. The corresponding words can help learners make appropriate use of this keyword. In addition the design of the user interface provides querying grammatical relation. This work makes use of grammatical relation and collocation in order to provide users with the assistance of English writing. And look for patterns of practice, we have proposed association rules and LSA (Latent Semantic Analysis) to implement.
|
3 |
高效率常見超集合探勘演算法之研究 / Efficient Algorithms for the Discovery of Frequent Superset廖忠訓, Liao, Zhung-Xun Unknown Date (has links)
過去對於探勘常見項目集的研究僅限於找出資料庫中交易紀錄的子集合,在這篇論文中,我們提出一個新的探勘主題:常見超集合探勘。常見超集合意指它包含資料庫中各筆紀錄的筆數多於最小門檻值,而原本用來探勘常見子集合的演算法並無法直接套用,因此我們以補集合的角度,提出了三個快速的演算法來解決這個新的問題。首先為Apriori-C:此為使用先廣後深搜尋的演算法,並且以掃描資料庫的方式來決定具有相同長度之候選超集合的支持度,第二個方法是Eclat-C:此為採用先深後廣搜尋的演算法,並且搭配交集法來計算倏選超集合的支持度,最後是DCT:此方法可利用過去常見子集合探勘的演算法來進行探勘,如此可以省下開發新系統的成本。
常見超集合的探勘可以應用在電子化的遠距學習系統,生物資訊及工作排程的問題上。尤其在線上學習系統,我們可以利用常見超集合來代表一群學生的學習行為,並且藉以預測學生的學習成就,使得老師可以及時發現學生的學習迷失等行為;此外,透過常見超集合的探勘,我們也可以為學生推薦個人化的課程,以達到因材施教的教學目標。
在實驗的部份,我們比較了各演算法的效率,並且分別改變實驗資料庫的下列四種變因:1) 交易資料的筆數、2) 每筆交易資料的平均長度、3) 資料庫中項目的總數和4) 最小門檻值。在最後的分析當中,可以清楚地看出我們提出的各種方法皆十分有效率並且具有可延伸性。 / The algorithms for the discovery of frequent itemset have been investigated widely. These frequent itemsets are subsets of database. In this thesis, we propose a novel mining task: mining frequent superset from the database of itemsets that is useful in bioinformatics, E-learning systems, jobshop scheduling, and so on. A frequent superset means that the number of transactions contained in it is not less than minimum support threshold. Intuitively, according to the Apriori algorithm, the level-wise discovering starts from 1-itemset, 2-itemset, and so forth. However, such steps cannot utilize the property of Apriori to reduce search space, because if an itemset is not frequent, its superset maybe frequent. In order to solve this problem, we propose three methods. The first is the Apriori-based approach, called Apriori-C. The second is the Eclat-based approach, called Eclat-C, which is a depth-first approach. The last is the proposed data complement technique (DCT) that we utilize original frequent itemset mining approach to discover frequent superset.
The experimental studies compare the performance of the proposed three methods by considering the effect of the number of transactions, the average length of transactions, the number of different items, and minimum support. The analysis shows that the proposed algorithms are time efficient and scalable.
|
Page generated in 0.0192 seconds