• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.7
• /
• pp.1044-1051
• /
• 2019

Objective: Recent studies have implied that gene expression has high tissue-specificity, and therefore it is essential to investigate gene expression in a variety of tissues when performing the transcriptomic analysis. In addition, the gradual increase of long non-coding RNA (lncRNA) annotation database has increased the importance and proportion of mapped reads accordingly. Methods: We employed simple statistical models to detect the sexually biased/dimorphic genes and their conjugate lncRNAs in 40 RNA-seq samples across two factors: sex and tissue. We employed two quantification pipeline: mRNA annotation only and mRNA+lncRNA annotation. Results: As a result, the tissue-specific sexually dimorphic genes are affected by the addition of lncRNA annotation at a non-negligible level. In addition, many lncRNAs are expressed in a more tissue-specific fashion and with greater variation between tissues compared to protein-coding genes. Due to the genic region lncRNAs, the differentially expressed gene list changes, which results in certain sexually biased genes to become ambiguous across the tissues. Conclusion: In a past study, it has been reported that tissue-specific patterns can be seen throughout the differentially expressed genes between sexes in cattle. Using the same dataset, this study used a more recent reference, and the addition of conjugate lncRNA information, which revealed alterations of differentially expressed gene lists that result in an apparent distinction in the downstream analysis and interpretation. We firmly believe such misquantification of genic lncRNAs can be vital in both future and past studies.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1126-1126
• /
• 2001

The paper presented here is the initial part of a larger study, in which it was determined which quality parameters in cheese powder could already be predicted by NIR at an early stage in the process and which could only be predicted at the final stages of the process. This initial study was performed in order to establish the levels and nature of variation within and between batches such that the subsequent data collection could be tackled optimally. The perspectives evolved into more than was originally planned and revealed some interesting uses of NIR-technology. Cheese powder production starts as a batch process, where waste cheese from other dairies is melted down in a vat. The process then turns into a continual process as the vat is emptied and the melted cheese is then filtered, homogenized, pasteurized and finally spray dried. Between each batch the powder is to a greater or lesser degree a mixture of 2 batches. This paper is divided into 2 aspects, one regarding the optimization of sampling time and the other is a study of process dynamics. Optimizing sampling time This initial study included 9 powder samples from 9 different batches produced during one day. The raw materials for the batches were chosen with the aim of creating a relatively high level of variation in the data. The total of 81 samples were taken out at regular intervals and spectra were collected on a NIR-systems 6500 instrument. The subsequent reduction of the data by PCA to score values shows the power of NIR as a tool to determine not only when samples are representative of a certain batch, but also which batches are stable enough to include in a further study. Studying process dynamics To take this experiment a step further 1 of the 81 samples were sent to the laboratory for further analyses. The samples were chosen on the criteria that they covered the spectral variation in the dataset. These samples were analysed for 4 chemical components and 5 physical attributes, which are essential for describing the quality of the product. The latent structure of the 7 samples, using the chemical and physical variables, is totally comparable to the latent structure of the NIR spectra. This outcome makes it possible to describe the dynamics of one day's production both chemically and physically with relatively little resources. Additionally it raises the question as to whether reference values are needed, as the latent structure of the NIR-spectra appears to be sufficient in providing information on the quality of the product. To be able to use NIR in this way would require defining quality limits in the principal component space as opposed to each of the reference values. The potential of NIR applied in an explorative fashion with batch processes opens a whole new gateway for the use of this technology. This study explains yet again after so many years in the field “why I'm crazy about NIR!”.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.375-384
• /
• 2021

Deep learning techniques have been proven to have high performance in image processing and are applied in various fields. The most widely used methods for validating a deep learning model include a holdout verification method, a k-fold cross verification method, and a bootstrap method. These legacy methods consider the balance of the ratio between classes in the process of dividing the data set, but do not consider the ratio of various features that exist within the same class. If these features are not considered, verification results may be biased toward some features. Therefore, we propose a deep learning model validation method based on data feature coverage for image classification by improving the legacy methods. The proposed technique proposes a data feature coverage that can be measured numerically how much the training data set for training and validation of the deep learning model and the evaluation data set reflects the features of the entire data set. In this method, the data set can be divided by ensuring coverage to include all features of the entire data set, and the evaluation result of the model can be analyzed in units of feature clusters. As a result, by providing feature cluster information for the evaluation result of the trained model, feature information of data that affects the trained model can be provided.

• Asia-Pacific Journal of Business
• /
• v.14 no.4
• /
• pp.67-85
• /
• 2023

Purpose - This study seeks to investigate the determinants of global sourcing intention in clothing sewing industry, in particular with its focus on women's knit wear production. Design/methodology/approach - This study collected a unique set of qualitative data through 31 in-depth interviews with fashion brands, promotion agencies, and sewing factories between July 2023 and October 2023. In addition, it analyzed the dataset using the MAXQDA to complement the research findings. Findings - We have two findings. First, the interviewees commonly mentioned the following factors as reasons for considering global sourcing: the human factors(aging of skilled technicians and labor shortages), the financial factors(gap in production unit prices at home and abroad), the relational factors(lack of novelty), and the physical factors(loss of production infrastructure and network), while the human factors(skilled workforce), the production factors(delivery date and product quality), and the relational factors(timely communication and mutual trust) as reasons for continuing domestic sourcing. Additional code analysis of interview also supports this finding. On the other hand, there was also a subtle difference between buyers(brands) and suppliers(promotion agencies and processing plants), and buyers consider the exact delivery date critical so that they could see trend-sensitive women's knit wear on time, and suppliers took production costs, labor costs, and labor shortages, which are financial factors, more seriously. Research implications or Originality - This study provides a richer and more balanced view of existing literature, which has generally tended to introduce global sourcing across the clothing industry despite the existence of various diversity within the industry. In addition, through qualitative research, we introduce that the sewing industry is carried out according to complex factors, and by revealing and categorizing the determinants of global sourcing, we supplement the existing research on the clothing sewing industry centered on survey. On a practical note, this study introduces that there is a difference in view of domestic sourcing and global sourcing between buyers(brands) and suppliers(promotion agencies and sewing factories), suggesting practical implications for revitalizing networks and deriving win-win cooperation network models among members in the future.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.