• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1653-1671
• /
• 2022

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and strawberry. Our study has three steps of species classification, disease detection, and disease classification, which is noteworthy for using captured images without additional processes. We designed deep learning approach of deep learning convolutional neural networks based on Mask R-CNN model to classify crop species. Inception and Resnet models were presented for disease detection and classification sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC whereas 0.940 and 0.988 for pepper and strawberry by Inception.

• The Journal of Information Systems
• /
• v.27 no.3
• /
• pp.63-80
• /
• 2018

Purpose The purpose of this study is to build a machine learning-based customer classification model to promote customer expansion effect of the free sample promotion. Specifically, the proposed model classifies potential target customers who are expected to purchase the products included in the free sample promotion after receiving the free samples. Design/methodology/approach This study proposes to build a customer classification model for determining customers suitable for providing free samples by using various machine learning techniques such as logistic regression, multiple discriminant analysis, case-based reasoning, decision tree, artificial neural network, and support vector machine. To validate the usefulness of the proposed model, we apply it to a real-world free sample-based target marketing case of a Korean major cosmetic retail company. Findings Experimental results show that a machine learning-based customer classification model presents satisfactory accuracy ranging from 70% to 75%. In particular, support vector machine is found to be the most effective machine learning technique for free sample-based target marketing model. Our study sheds a light on customer relationship management strategies using free sample promotions.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.471-478
• /
• 2012

Various studies on sentiment classification of documents have been performed. Recently, they have been applied to twitter sentiment classification. However, they did not show good performances because they did not consider the characteristics of tweets such as tweet structure, emoticons, spelling errors, and newly-coined words. In this paper, we perform experiments on various input features (emoticon polarity, retweet polarity, author polarity, and replacement words) which affect twitter sentiment classification model based on machine-learning techniques. In the experiments with a sentiment classification model based on a support vector machine, we found that the emoticon polarity features and the author polarity features can contribute to improve the performance of a twitter sentiment classification model. Then, we found that the retweet polarity features and the replacement words features do not affect the performance of a twitter sentiment classification model contrary to our expectations.

• Journal of Information Technology Services
• /
• v.16 no.3
• /
• pp.167-183
• /
• 2017

The rapid growth of information technology and mobile service platforms, i.e., internet, google, and facebook, etc. has led the abundance of data. Due to this environment, the world is now facing a revolution in the process that data is searched, collected, stored, and shared. Abundance of data gives us several opportunities to knowledge discovery and data mining techniques. In recent years, data mining methods as a solution to discovery and extraction of available knowledge in database has been more popular in e-commerce service fields such as, in particular, movie recommendation. However, most of the classification approaches for predicting the movie popularity have used only several types of information of the movie such as actor, director, rating score, language and countries etc. In this study, we propose a classification-based support vector machine (SVM) model for predicting the movie popularity based on movie's genre data and social network data. Social network analysis (SNA) is used for improving the classification accuracy. This study builds the movies' network (one mode network) based on initial data which is a two mode network as user-to-movie network. For the proposed method we computed degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality as centrality measures in movie's network. Those four centrality values and movies' genre data were used to classify the movie popularity in this study. The logistic regression, neural network, $na{\ddot{i}}ve$ Bayes classifier, and decision tree as benchmarking models for movie popularity classification were also used for comparison with the performance of our proposed model. To assess the classifier's performance accuracy this study used MovieLens data as an open database. Our empirical results indicate that our proposed model with movie's genre and centrality data has by approximately 0% higher accuracy than other classification models with only movie's genre data. The implications of our results show that our proposed model can be used for improving movie popularity classification accuracy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.36-41
• /
• 2010

An advanced form of Multistage Feature-based Classification Model(AMFCM), called AMFCM, is proposed in this paper. AMFCM like MFCM does not use the concatenated form of available feature vectors extracted from original data to classify each data, but uses only groups related to each feature vector to classify separately. The prpposed AMFCM improves the contribution rate used in MFCM and proposes a confusion table for each local classifier using a specific feature vector group. The confusion table for each local classifier contains accuracy information of each local classifier on each class of data. The proposed AMFCM is applied to the problem of music genre classification on a set of music data. The results demonstrate that the proposed AMFCM outperforms MFCM by 8% - 15% on average in terms of classification accuracy depending on the grouping algorithms used for local classifiers and the number of clusters.

• Journal of The Korean Association For Science Education
• /
• v.32 no.3
• /
• pp.524-531
• /
• 2012

Categorization is an important human function used to process different stimuli. It is also one of the most important factors affecting measurement of a person's classification ability. Explicit categorization, the representative system by which categorization ability is measured, can verbally describe the categorization rule. The purpose of this study was to develop a prediction model for categorization ability as it relates to the classification process of living organisms using fMRI. Fifty-five participants were divided into two groups: a model generation group, comprised of twenty-seven subjects, and a model verification group, made up of twenty-eight subjects. During prediction model generation, functional connectivity was used to analyze temporal correlations between brain activation regions. A classification ability quotient (CQ) was calculated to identify the verbal categorization ability distribution of each subject. Additionally, the connectivity coefficient (CC) was calculated to quantify the functional connectivity for each subject. Hence, it was possible to generate a prediction model through regression analysis based on participants' CQ and CC values. The resultant categorization ability regression model predictor was statistically significant; however, researchers proceeded to verify its predictive ability power. In order to verify the predictive power of the developed regression model, researchers used the regression model and subjects' CC values to predict CQ values for twenty-eight subjects. Correlation between the predicted CQ values and the observed CQ values was confirmed. Results of this study suggested that explicit categorization ability differs at the brain network level of individuals. Also, the finding suggested that differences in functional connectivity between individuals reflect differences in categorization ability. Last, researchers have provided a new method for predicting an individual's categorization ability by measuring brain activation.

• Economic and Environmental Geology
• /
• v.55 no.3
• /
• pp.309-316
• /
• 2022

In order to minimize the human and time consumption required for rock classification, research on rock classification using artificial intelligence (AI) has recently developed. In this study, basic volcanic rocks were subdivided by using polarizing microscope thin section images. A convolutional neural network (CNN) model based on Tensorflow and Keras libraries was self-producted for rock classification. A total of 720 images of olivine basalt, basaltic andesite, olivine tholeiite, trachytic olivine basalt reference specimens were mounted with open nicol, cross nicol, and adding gypsum plates, and trained at the training : test = 7 : 3 ratio. As a result of machine learning, the classification accuracy was over 80-90%. When we confirmed the classification accuracy of each AI model, it is expected that the rock classification method of this model will not be much different from the rock classification process of a geologist. Furthermore, if not only this model but also models that subdivide more diverse rock types are produced and integrated, the AI model that satisfies both the speed of data classification and the accessibility of non-experts can be developed, thereby providing a new framework for basic petrology research.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.1035-1046
• /
• 2015

Variance components models incorporate various random factors in the form of linear models. There are two experimental Layouts for the classification of factors under variance components models: nested classification and crossed classification. We consider two-way variance components models and investigate the effect of experimental Layout on the performance of model selection criteria AIC and BIC. The effect of experimental Layout is studied through a simulation study with various combinations of parameters in a systematic fashion. The simulation study shows differences in performance of model selection methods between the two classification. There is a particular tendency to prefer the smaller model than the true model when the variance component of a nested factor becomes relatively larger than a nesting factor that is persistent even when the sample size is not small.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.3
• /
• pp.265-276
• /
• 2019

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.