 |
|
 หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Comparison of Clustering Techniques for Cluster Analysis) ผู้เขียน: ปิยธิดา รุจะศิริ,  ดร.บุญอ้อม โฉมที, รองศาสตราจารย์ สื่อสิ่งพิมพ์:pdf AbstractCluster analysis is important for analyzing the number of clusters of natural data in several domains. Various clustering methods have been proposed. However, it is very difficult to choose the method best suited to the type of data. Therefore, the objective of this research was to compare the effectiveness of five clustering techniques with multivariate data. The techniques were: hierarchical clustering method; K-means clustering algorithm; Kohonen’s Self-Organizing Maps method (SOM); K-medoids method; and K-medoids method integrated with Dynamic Time Warping distance measure (DTW). To evaluate these five techniques, the root mean square standard deviation (RMSSTD) and r2 (RS) were used. For RMSSTD, a lower value indicates a better technique and for RS, a higher value indicates a better technique. These approaches were evaluated using both real and simulated data which were multivariate normally distributed. Each dataset was generated by a Monte Carlo technique with 100 sample sizes and repeated 1,000 times for 3, 5 and 7 variables. In this research, 2, 3, 4, 5, 6, 7 and 8 clusters were studied. Both real and simulated datasets provided the same result, with the K-means clustering method having the closest RMSSTD and RS results to the SOM method. These two methods yielded the lowest RMSSTD and highest RS in all simulations. Hence, both K-means and SOM were considered to be the most suitable techniques for cluster analysis. |
 ที่มา:การประชุมทางวิชาการของมหาวิทยาลัยเกษตรศาสตร์ ครั้งที่ 49 : สาขาอุตสาหกรรมเกษตรหัวเรื่อง:การศึกษาพฤติกรรมและทัศนคติการบริโภคผลิตภัณฑ์ไส้พายผลไม้และจาแนกกลุ่มโดยใช้เทคนิคจัดกลุ่มตามลาดับขั้น |
|
 หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Selecting Stocks Using A Genetic Algorithm: A Case of Real Estate Investment Trusts (REITs)) ผู้เขียน:Kaveepong Lertwachara สื่อสิ่งพิมพ์:pdf AbstractMany investors invest according to analysts' recommendations, but some studies detect sizable abnormal returns associated with those recommendations. A tool that imitates the mechanism of the recommendation process should enable individual investors to formulate a profitable investment strategy and to select stocks that analysts have not covered. This paper presents a genetic algorithm (GA) method for identifying attractive stocks. The GA method has shown promising performance as a tool with which investors can develop a profitable investment strategy. GA is able to pick stocks with a "buy" rating at 62.50%, compared to 36.45% for stocks picked at random. |
ที่มา:Australian Journal of Crop Scienceหัวเรื่อง:- |
|
หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Variation of small erect-fruited chili in Thailand) ผู้เขียน:Nongluck Milerue, ดร.จุลภาค คุ้นวงศ์, รองศาสตราจารย์ , Darush Struss, ดร.สิริกุล วะสี สื่อสิ่งพิมพ์:pdf AbstractSingle cross varieties of small, erect-fruited chili (Prik-khee-noo in Thai) are required because of their high yield and high quality. Production of a single cross needs superior parental lines. This study was conducted to screen for parental lines which could be used for the production of superior single cross. To develop new varieties, high variation of the parental lines is required. Twenty-eight chili accessions (Capsicum annuum L.) cultivated in Thailand were collected and evaluated for variation with 343 single nucleotide polymorphic (SNP) markers at the Molecular Marker Laboratory at Hortigenetic Research (S.E. Asia) Ltd., Chiang Mai, Thailand. The results showed low variation among the 28 chili accessions with the polymorphism information content varying from 0.45 to 0.49 with an average of 0.46. The average genetic distance estimated from the SNP markers based on Jaccard's coefficient was 0.29 (ranging from 0.03 to 0.55). However, based on SNP analysis, the unweighted pair-group method with arithmetic averages divided the 28 chili accessions into two main groups and four subgroups. The first group consisted of 23 accessions mostly collected from varieties cultivated in Northeastern Thailand. The second group contained five accessions collected from different locations in other regions of Thailand. |
 Researcherดร. อัจฉรา เกษสุวรรณ, ผู้ช่วยศาสตราจารย์ที่ทำงาน:ภาควิชาเทคโนโลยีอุตสาหกรรมเกษตร คณะอุตสาหกรรมเกษตร สาขาที่สนใจ:กลยุทธ์การตลาดธุรกิจเกษตรและอุตสาหกรรมเกษตร, การวิจัยทางการตลาดและการวิจัยผู้บริโภคสำหรับสินค้าเกษตรและอุตสาหกรรมเกษตร, การตลาดระหว่างประเทศสำหรับสินค้าเกษตรและอุตสาหกรรมเกษตร Resume |
 |
 |
หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : The Effect of Genotypes and GE Interaction on Starch Content of Cassava) ผู้เขียน:ดร.ประเสริฐ ฉัตรวชิระวงษ์, รองศาสตราจารย์ , Opas Boonseng, Anusart Summatraya สื่อสิ่งพิมพ์:pdf AbstractThe objective of this study is to explore the effect of genotype and genotype x environment on starch content percentage of 5 cassava genotypes grown under several environments in early and late rainy seasons. The results indicated that there was less seasonal effect on genotypic performance. There was more GE interaction in late rainy season. The sum of squares of GE interaction was partitioned using 3 techniques, viz. linear regression (REG), using Eberhart and Russell (1966) stability, and Additive Main effects and the Multiplicative Interaction (AMMI) model in 2 principal component axes. The AMMI model can explain a large portion of sum of squares, and thus more effective in partitioning the GE interaction SS than the REG technique. Grouping of homogeneous environments using cluster analysis resulted in almost the same genotype ranking in each group. Environmental grouping can then be used to reduce the reversal GE interaction. |
|
ที่มา:การประชุมวิชาการของมหาวิทยาลัยเกษตรศาสตร์ ครั้งที่ ๔๙ สาขาพืชหัวเรื่อง:การวิเคราะห์จัดกลุ่มความต้านทานเชื้อโรคไหม้ของข้าวพันธุ์ปรับปรุงด้วยเชื้อที่เก็บรวบรวมใหม่ |
ที่มา:FEMS Yeast Researchหัวเรื่อง:Candida nonsorbophila sp. nov., a new ascomycetous yeast species isolated in Thailand |
ที่มา:FEMS Yeast Researchหัวเรื่อง:Candida siamensis sp. nov., an anamorphic yeast species in the Saturnispora clade isolated in Thailand |
|
|
หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Categorization of Coconut Milk Products by Their Sensory Characteristics) ผู้เขียน:เสาวภาคย์ วัฒนพาหุ, ดร.ธงชัย สุวรรณสิชณน์, รองศาสตราจารย์ , ดร.วรรณี จิรภาคย์กุล, รองศาสตราจารย์ , Sumaporn Kasermsumran สื่อสิ่งพิมพ์:pdf AbstractCoconut milk is extensively used as a major ingredient of savory foods and desserts in many countries. The sensory characteristics of coconut milk have a substantial effect on consumer acceptance. The objectives of this investigation were to develop a lexicon of coconut milk products produced by different tempering processes and to categorize coconut milk products based on their sensory properties. Twelve samples consisting of two unheated, four pasteurized, three UHT, one sterilized and two spray dried were collected and determined. Eight highly trained panelists described the sensory characteristics of the coconut milk samples. The results demonstrated that there were 17 attributes: smoothness, overall coconut milk odor, sweetness of coconut milk odor, freshness odor, coconut oil odor, cooked odor nutty odor, overall coconut milk fl avor, freshness fl avor, oily fl avor, cooked fl avor, sweet fl avor, nutty fl avor, viscosity, fat feel, dryness, lip and mouth feel. All 17 sensory attributes were signifi cantly different (P < 0.05) among coconut milk samples. The results of hierarchical cluster analysis (HCA) and principal component analysis (PCA) demonstrated that PCA reduced the 17 sensory attributes into two independent principal components (PCs), which accounted for 87.30% of the explained variance. These two PCs with HCA could classify the 12 samples into fi ve groups related to their tempering processes. |