• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Korean Journal of Community Nutrition
• /
• v.26 no.3
• /
• pp.188-199
• /
• 2021

Objectives: The purpose was to identify the ingredients that are usually surveyed for assessing real prices and to present the demand for such surveys by nutrition teachers and dietitians for ingredients used by school foodservice. Methods: A survey was conducted online from December 2019 to January 2020. The survey questionnaire was distributed to 1,158 nutrition teachers and dietitians from elementary, middle, and high schools nationwide, and 439 (37.9% return rate) of the 1,158 were collected and used for data analysis. Results: The ingredients which were investigated for price realities directly by schools were industrial products in 228 schools (51.8%), fruits in 169 schools (38.4%), and specialty crops in 166 schools (37.7%). Moreover, nutrition teachers and dietitians in elementary, middle, and high schools searched in different ways for the real prices of ingredients. In elementary schools, there was a high demand for price information about grains, vegetables or root and tuber crops, special crops, fruits, eggs, fishes, and organic and locally grown ingredients by the School Foodservice Support Centers. Real price information about meats, industrial products, and pickled processed products were sought from the external specialized institutions. In addition, nutrition teachers and dietitians in middle and high schools wanted to obtain prices of all of the ingredients from the Offices of Education or the District Office of Education. Conclusions: Schools want to efficiently use the time or money spent on research for the real prices of ingredients through reputable organizations or to co-work with other nutrition teachers and dietitians. The results of this study will be useful in understanding the current status of the surveys carried out to determine the real price information for ingredients used by the school foodservice.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.26 no.2
• /
• pp.43-47
• /
• 2022

Purpose Radioimmunoassay implement quality control by systematizing the internal quality control system for quality assurance of test results. This study aims to contribute to the quality assurance of radioimmunoassay results and to implement systematic quality control by measuring the average CV of internal quality control and external quality control by plenty of institutions for reference when setting the laboratory's own acceptable range. Materials and Methods We measured the average CV of internal quality control and the bounce rate of more than 10.0% for a total of 42 items from October 2020 to December 2021. According to the CV result, we classified and compared the upper group (5.0% or less), the middle group (5.0~10.0%) and the lower group (10.0% or more). The bounce rate of 10.0% or more was compared by classifying the item of five or more institutions into tumor markers, thyroid hormones and other hormones. The average CV was measured by the overall average and standard deviation of the external quality control results for 28 items from the first quarter to the fourth quarter of 2021. In addition, the average CV was measured by the overall average and standard deviation of the proficiency results between institutions for 13 items in the first half and the second half of 2021. The average CV of internal quality control and external quality control was compared by item so we compared and analyzed the items that implement well to quality control and the items that require attention to quality control. Results As a result of measuring the precision average of internal quality control for 42 items of six institutions, the top group (5.0% or less) are Ferritin, HGH, SHBG, and 25-OH-VitD, while the bottom group (≤10.0%) are cortisol, ATA, AMA, renin, and estradiol. When comparing more than 10.0% bounce rate of CV for tumor markers, CA-125 (6.7%), CA-19-9 (9.8%) implemented well, while SCC-Ag (24.3%), CA-15-3 (26.7%) were among the items that require attention to control. As a result of comparing the bounce rate of more than 10.0% of CV for thyroid hormones examination, free T4 (2.1%), T3 (9.3%) showed excellent performance and AMA (39.6%), ATA (51.6%) required attention to control. When comparing the bounce rate of 10.0% or more of CV for other hormones, IGF-1 (8.8%), FSH (9.1%), prolactin (9.2%) showed excellent performance, however estradiol (37.3%), testosterone (37.7%), cortisol (44.4%) required attention to control. As a result of measuring the average CV of the whole institutions participating at external quality control for 28 items, HGH and SCC-Ag were included in the top group (≤10.0%), however ATA, estradiol, TSI, and thyroglobulin included in bottom group (≥30.0%). Conclusion As a result of evaluating 42 items of six institutions, the average CV was 3.7~12.2% showing a 3.3 times difference between the upper group and the lower group. Cortisol, ATA, AMA, Renin and estradiol tests with high CV will require continuous improvement activities to improve precision. In addition, we measured and compared the overall average CV of the internal quality control, the external quality control and the proficiency between institutions participating of six institutions for 41 items excluding HBs-Ab. As a result, ATA, AMA, Renin and estradiol belong to the same subgroup so we require attention to control and consider setting a higher acceptable range. It is recommended to set and control the acceptable range standard of internal quality control CV in consideration of many things in the laboratory due to the different reagents and instruments, and the results vary depending on the test's proficiency and quality control materials. It is thought that the accuracy and reliability of radioimmunoassay results can be improved if systematic quality control is implemented based on the set acceptable range.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.175-196
• /
• 2022

Information and communication and home appliance industries, which were one of South Korea's main industries, are gradually losing their export share as their export competitiveness is weakening. This study objectively analyzed export competitiveness and suggested export-promising countries in order to help South Korea's information communication and home appliance industries improve exports. In this study, network properties, centrality, and structural hole analysis were performed during network analysis to evaluate export competitiveness. In order to select promising export countries, we proposed a new variable that can take into account the characteristics of an already established International Trade Network (ITN), that is, the Global Value Chain (GVC), in addition to the existing economic factors. The conditional log-odds for individual links derived from the Exponential Random Graph Model (ERGM) in the analysis of the cross-border trade network were assumed as a proxy variable that can indicate the export potential. In consideration of the possibility of ERGM linkage, a parametric approach and a non-parametric approach were used to recommend export-promising countries, respectively. In the parametric method, a regression analysis model was developed to predict the export value of the information and communication and home appliance industries in South Korea by additionally considering the link-specific characteristics of the network derived from the ERGM to the existing economic factors. Also, in the non-parametric approach, an abnormality detection algorithm based on the clustering method was used, and a promising export country was proposed as a method of finding outliers that deviate from two peers. According to the research results, the structural characteristic of the export network of the industry was a network with high transferability. Also, according to the centrality analysis result, South Korea's influence on exports was weak compared to its size, and the structural hole analysis result showed that export efficiency was weak. According to the model for recommending promising exporting countries proposed by this study, in parametric analysis, Iran, Ireland, North Macedonia, Angola, and Pakistan were promising exporting countries, and in nonparametric analysis, Qatar, Luxembourg, Ireland, North Macedonia and Pakistan were analyzed as promising exporting countries. There were differences in some countries in the two models. The results of this study revealed that the export competitiveness of South Korea's information and communication and home appliance industries in GVC was not high compared to the size of exports, and thus showed that exports could be further reduced. In addition, this study is meaningful in that it proposed a method to find promising export countries by considering GVC networks with other countries as a way to increase export competitiveness. This study showed that, from a policy point of view, the international trade network of the information communication and home appliance industries has an important mutual relationship, and although transferability is high, it may not be easily expanded to a three-party relationship. In addition, it was confirmed that South Korea's export competitiveness or status was lower than the export size ranking. This paper suggested that in order to improve the low out-degree centrality, it is necessary to increase exports to Italy or Poland, which had significantly higher in-degrees. In addition, we argued that in order to improve the centrality of out-closeness, it is necessary to increase exports to countries with particularly high in-closeness. In particular, it was analyzed that Morocco, UAE, Argentina, Russia, and Canada should pay attention as export countries. This study also provided practical implications for companies expecting to expand exports. The results of this study argue that companies expecting export expansion need to pay attention to countries with a relatively high potential for export expansion compared to the existing export volume by country. In particular, for companies that export daily necessities, countries that should pay attention to the population are presented, and for companies that export high-end or durable products, countries with high GDP, or purchasing power, relatively low exports are presented. Since the process and results of this study can be easily extended and applied to other industries, it is also expected to develop services that utilize the results of this study in the public sector.

• Journal of Venture Innovation
• /
• v.5 no.1
• /
• pp.107-127
• /
• 2022

Global challenges such as the corona pandemic, climate change and the war-on-tech ensure that the demand who the technologies of the future develops and monitors prominently for will be on the agenda. Development of, and applications in, agrifood, biotech, high-tech, medtech, quantum, AI and photonics are the basis of the future earning capacity of the Netherlands and contribute to solving societal challenges, close to home and worldwide. To be like the Netherlands and Europe a strategic position in the to obtain knowledge and innovation chain, and with it our autonomy in relation to from China and the United States insurance, clear choices are needed. Brainport Eindhoven: Building on Philips' knowledge base, there is create an innovative ecosystem where more than 7,000 companies in the High-tech Systems & Materials (HTSM) collaborate on new technologies, future earning potential and international value chains. Nearly 20,000 private R&D employees work in 5 regional high-end campuses and for companies such as ASML, NXP, DAF, Prodrive Technologies, Lightyear and many others. Brainport Eindhoven has a internationally leading position in the field of system engineering, semicon, micro and nanoelectronics, AI, integrated photonics and additive manufacturing. What is being developed in Brainport leads to the growth of the manufacturing industry far beyond the region thanks to chain cooperation between large companies and SMEs. South-Holland: The South Holland ecosystem includes companies as KPN, Shell, DSM and Janssen Pharmaceutical, large and innovative SMEs and leading educational and knowledge institutions that have more than Invest €3.3 billion in R&D. Bearing Cores are formed by the top campuses of Leiden and Delft, good for more than 40,000 innovative jobs, the port-industrial complex (logistics & energy), the manufacturing industry cluster on maritime and aerospace and the horticultural cluster in the Westland. South Holland trains thematically key technologies such as biotech, quantum technology and AI. Twente: The green, technological top region of Twente has a long tradition of collaboration in triple helix bandage. Technological innovations from Twente offer worldwide solutions for the large social issues. Work is in progress to key technologies such as AI, photonics, robotics and nanotechnology. New technology is applied in sectors such as medtech, the manufacturing industry, agriculture and circular value chains, such as textiles and construction. Being for Twente start-ups and SMEs of great importance to the jobs of tomorrow. Connect these companies technology from Twente with knowledge regions and OEMs, at home and abroad. Wageningen in FoodValley: Wageningen Campus is a global agri-food magnet for startups and corporates by the national accelerator StartLife and student incubator StartHub. FoodvalleyNL also connects with an ambitious 2030 programme, the versatile ecosystem regional, national and international - including through the WEF European food innovation hub. The campus offers guests and the 3,000 private R&D put in an interesting programming science, innovation and social dialogue around the challenges in agro production, food processing, biobased/circular, climate and biodiversity. The Netherlands succeeded in industrializing in logistics countries, but it is striving for sustainable growth by creating an innovative ecosystem through a regional industry-academic research model. In particular, the Brainport Cluster, centered on the high-tech industry, pursues regional innovation and is opening a new horizon for existing industry-academic models. Brainport is a state-of-the-art forward base that leads the innovation ecosystem of Dutch manufacturing. The history of ports in the Netherlands is transforming from a logistics-oriented port symbolized by Rotterdam into a "port of digital knowledge" centered on Brainport. On the basis of this, it can be seen that the industry-academic cluster model linking the central government's vision to create an innovative ecosystem and the specialized industry in the region serves as the biggest stepping stone. The Netherlands' innovation policy is expected to be more faithful to its role as Europe's "digital gateway" through regional development centered on the innovation cluster ecosystem and investment in job creation and new industries.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.1-33
• /
• 2019

The small and medium sized enterprises (hereinafter SMEs) are already at a competitive disadvantaged when compared to large companies with more abundant resources. Manufacturing SMEs not only need a lot of information needed for new product development for sustainable growth and survival, but also seek networking to overcome the limitations of resources, but they are faced with limitations due to their size limitations. In a new era in which connectivity increases the complexity and uncertainty of the business environment, SMEs are increasingly urged to find information and solve networking problems. In order to solve these problems, the government funded research institutes plays an important role and duty to solve the information asymmetry problem of SMEs. The purpose of this study is to identify the differentiating characteristics of SMEs that utilize the public information support infrastructure provided by SMEs to enhance the innovation capacity of SMEs, and how they contribute to corporate performance. We argue that we need an infrastructure for providing information support to SMEs as part of this effort to strengthen of the role of government funded institutions; in this study, we specifically identify the target of such a policy and furthermore empirically demonstrate the effects of such policy-based efforts. Our goal is to help establish the strategies for building the information supporting infrastructure. To achieve this purpose, we first classified the characteristics of SMEs that have been found to utilize the information supporting infrastructure provided by government funded institutions. This allows us to verify whether selection bias appears in the analyzed group, which helps us clarify the interpretative limits of our study results. Next, we performed mediator and moderator effect analysis for multiple variables to analyze the process through which the use of information supporting infrastructure led to an improvement in external networking capabilities and resulted in enhancing product competitiveness. This analysis helps identify the key factors we should focus on when offering indirect support to SMEs through the information supporting infrastructure, which in turn helps us more efficiently manage research related to SME supporting policies implemented by government funded institutions. The results of this study showed the following. First, SMEs that used the information supporting infrastructure were found to have a significant difference in size in comparison to domestic R&D SMEs, but on the other hand, there was no significant difference in the cluster analysis that considered various variables. Based on these findings, we confirmed that SMEs that use the information supporting infrastructure are superior in size, and had a relatively higher distribution of companies that transact to a greater degree with large companies, when compared to the SMEs composing the general group of SMEs. Also, we found that companies that already receive support from the information infrastructure have a high concentration of companies that need collaboration with government funded institution. Secondly, among the SMEs that use the information supporting infrastructure, we found that increasing external networking capabilities contributed to enhancing product competitiveness, and while this was no the effect of direct assistance, we also found that indirect contributions were made by increasing the open marketing capabilities: in other words, this was the result of an indirect-only mediator effect. Also, the number of times the company received additional support in this process through mentoring related to information utilization was found to have a mediated moderator effect on improving external networking capabilities and in turn strengthening product competitiveness. The results of this study provide several insights that will help establish policies. KISTI's information support infrastructure may lead to the conclusion that marketing is already well underway, but it intentionally supports groups that enable to achieve good performance. As a result, the government should provide clear priorities whether to support the companies in the underdevelopment or to aid better performance. Through our research, we have identified how public information infrastructure contributes to product competitiveness. Here, we can draw some policy implications. First, the public information support infrastructure should have the capability to enhance the ability to interact with or to find the expert that provides required information. Second, if the utilization of public information support (online) infrastructure is effective, it is not necessary to continuously provide informational mentoring, which is a parallel offline support. Rather, offline support such as mentoring should be used as an appropriate device for abnormal symptom monitoring. Third, it is required that SMEs should improve their ability to utilize, because the effect of enhancing networking capacity through public information support infrastructure and enhancing product competitiveness through such infrastructure appears in most types of companies rather than in specific SMEs.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of Agricultural Extension & Community Development
• /
• v.7 no.1
• /
• pp.155-166
• /
• 2000

When the marcher visited Korea in fall 1994, he was shocked to see high rise apartment buildings around the capitol region including Seoul and Suwon, resulting from rising demand of housing because of urban migration followed by second and third industrial development. After 6 years in March 2000, the researcher witnessed more apartment buildings and vinyl house complexes, one of the evidences of continued economic progress in Korea. Korea had to receive the rescue finance from International Monetary Fund (IMF) because of financial crisis in 1997. However, the sign of recovery was seen in a year, and the growth rate of Gross Domestic Products (GDP) in 1999 recorded as high as 10.7 percent. During this period, the Korean government has been working on restructuring of banks, enterprises, labour and public sectors. The major directions of government were; localization, reducing administrative manpower, limiting agricultural budgets, privatization of public enterprises, integration of agricultural organization, and easing of various regulations. Thus, the power of central government shifted to local government resulting in a power increase for city mayors and county chiefs. Agricultural extension services was one of targets of government restructuring, transferred to local governments from central government. At the same time, the number of extension offices was reduced by 64 percent, extension personnel reduced by 24 percent, and extension budgets reduced. During the process of restructuring, the basic direction of extension services was set by central Rural Development Administration Personnel management, technology development and supports were transferred to provincial Rural Development Administrations, and operational responsibilities transferred to city/county governments. Agricultural extension services at the local levels changed the name to Agricultural Technology Extension Center, established under jurisdiction of city mayor or county chief. The function of technology development works were added, at the same time reducing the number of educators for agriculture and rural life. As a result of observations of rural areas and agricultural extension services at various levels, functional responsibilities of extension were not well recognized throughout the central, provincial, and local levels. Central agricultural extension services should be more concerned about effective rural development by monitoring provincial and local level extension activities more throughly. At county level extension services, it may be desirable to add a research function to reflect local agricultural technological needs. Sometimes, adding administrative tasks for extension educators may be helpful far farmers. However, tasks such as inspection and investigation should be avoided, since it may hinder the effectiveness of extension educational activities. It appeared that major contents of the agricultural extension service in Korea were focused on saving agricultural materials, developing new agricultural technology, enhancing agricultural export, increasing production and establishing market oriented farming. However these kinds of efforts may lead to non-sustainable agriculture. It would be better to put more emphasis on sustainable agriculture in the future. Agricultural extension methods in Korea may be better classified into two approaches or functions; consultation function for advanced farmers and technology transfer or educational function for small farmers. Advanced farmers were more interested in technology and management information, while small farmers were more concerned about information for farm management directions and timely diffusion of agricultural technology information. Agricultural extension service should put more emphasis on small farmer groups and active participation of farmers in these groups. Providing information and moderate advice in selecting alternatives should be the major activities for consultation for advanced farmers, while problem solving processes may be the major educational function for small farmers. Systems such as internet and e-mail should be utilized for functions of information exchange. These activities may not be an easy task for decreased numbers of extension educators along with increased administrative tasks. It may be difficult to practice a one-to-one approach However group guidance may improve the task to a certain degree.