• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.199-230
• /
• 2021

Innovative new products and services are being launched through the convergence between heterogeneous industries, and social interest and investment in convergence industries such as AI, big data-based future cars, and robots are continuously increasing. However, in the process of commercialization of convergence new products and services, there are many cases where they do not conform to the existing regulatory and legal system, which causes many difficulties in companies launching their products and services into the market. In response to these industrial changes, the current government is promoting the improvement of existing regulatory mechanisms applied to the relevant industry along with the expansion of investment in new industries. This study, in these convergence industry trends, aimed to analysis the existing regulatory system that is an obstacle to market entry of innovative new products and services in order to preemptively predict regulatory issues that will arise in emerging industries. In addition, it was intended to establish a regulatory impact analysis system to evaluate adequacy and prepare improvement measures. The flow of this study is divided into three parts. In the first part, previous studies on regulatory impact analysis and evaluation systems are investigated. This was used as basic data for the development direction of the regulatory impact framework, indicators and items. In the second regulatory impact analysis framework development part, indicators and items are developed based on the previously investigated data, and these are applied to each stage of the framework. In the last part, a case study was presented to solve the regulatory issues faced by actual companies by applying the developed regulatory impact analysis framework. The case study included the autonomous/electric vehicle industry and the Internet of Things (IoT) industry, because it is one of the emerging industries that the Korean government is most interested in recently, and is judged to be most relevant to the realization of an intelligent information society. Specifically, the regulatory impact analysis framework proposed in this study consists of a total of five steps. The first step is to identify the industrial size of the target products and services, related policies, and regulatory issues. In the second stage, regulatory issues are discovered through review of regulatory improvement items for each stage of commercialization (planning, production, commercialization). In the next step, factors related to regulatory compliance costs are derived and costs incurred for existing regulatory compliance are calculated. In the fourth stage, an alternative is prepared by gathering opinions of the relevant industry and experts in the field, and the necessity, validity, and adequacy of the alternative are reviewed. Finally, in the final stage, the adopted alternatives are formulated so that they can be applied to the legislation, and the alternatives are reviewed by legal experts. The implications of this study are summarized as follows. From a theoretical point of view, it is meaningful in that it clearly presents a series of procedures for regulatory impact analysis as a framework. Although previous studies mainly discussed the importance and necessity of regulatory impact analysis, this study presented a systematic framework in consideration of the various factors required for regulatory impact analysis suggested by prior studies. From a practical point of view, this study has significance in that it was applied to actual regulatory issues based on the regulatory impact analysis framework proposed above. The results of this study show that proposals related to regulatory issues were submitted to government departments and finally the current law was revised, suggesting that the framework proposed in this study can be an effective way to resolve regulatory issues. It is expected that the regulatory impact analysis framework proposed in this study will be a meaningful guideline for technology policy researchers and policy makers in the future.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.

• Clinical and Experimental Pediatrics
• /
• v.52 no.3
• /
• pp.289-294
• /
• 2009

Purpose : To assess the usefulness of magnetic resonance imaging (MRI), karyotyping, brainstem auditory evoked potential (BAEP), electroencephalogram (EEG), tandem mass screening test, and newborn metabolic screening test in children with language delay for diagnosing underlying diseases. Methods : From January 2000 to June 2007, a retrospective chart review was performed for 122 children with language delay who visited the Child Neurology Clinic at Yeungnam University Hospital and who underwent neuropsychologic tests and other diagnostic evaluations for underlying diseases. They were grouped into phenomenological diagnostic categories, and test results were analyzed according to the underlying diseases. Results : Of 122 patients, 47 (38.5%) had mental retardation, 40 (32.8%) had developmental language disorders, 23 (18.9 %) had borderline IQ, and 12 (9.8%) had autism spectrum disorder. In 26 (21.3%) cases, the causes or relevant clinical findings to explain language delay were found. Eight (10.4%) of 77 MRIs, 6 (8.0%) of 75 EEGs, and 4 (5%) of 80 BAEPs showed abnormal results. Results directly attributed to diagnosing underlying diseases were 2 hearing defects in BAEPs and 1 bilateral perisylvian cortical dysplasia in MRIs. No abnormal results were found in karyotyping, tandem mass screening tests, and new-born screening tests. Conclusion : Commonly used tests to diagnose the cause of language delay are not very effective and should only be used selectively, according to patient characteristics. However, despite the low diagnostic yields from these tests, because many patients show abnormal results, these tests are useful when conducted in complete evaluation.

• Journal of The Korean Association For Science Education
• /
• v.41 no.6
• /
• pp.483-499
• /
• 2021

The curriculum localization policy is closely related to the decentralization and autonomy policy, which is a direction of the 2022 revised curriculum. In particular, considering the continuously expanding and changing environment and contents in science education, the localization of the science curriculum has the advantage of advancing to expertise through diversity. In this paper, through experts' perception of the science curriculum localization policy, the implications of the curriculum revision were confirmed, focusing on 'MPOE(Metropolitan and Provincial Offices of Education) curriculum arrangement and implementation guidelines(hereinafter referred to as 'guidelines')' and the achievement standards revision of science curriculum. In conclusion, study participants considered that the possibility of expanding the localization of the curriculum was high due to the unique characteristics of science practices. And they recognized the level of localization at the 'district office of education or village'-level between MPOE-level and school-level. When localization reaches the school-level in the future, it was considered necessary to discuss linkage with teacher policies such as teacher's competency, noting that the level of teachers could become the level of localization. In addition, there was a common perception that in order for the science 'guidelines' to be localized, 17 MPOE must be given the authority to autonomously organize some achievement standards in parallel. It was considered that 'restructuring or slimming of achievement standards' should precede localization of achievement standards in connection with this. On the other hand, it was predicted that the curriculum localization policy would enhance the aspect of diversification and autonomy of the science curriculum, and the establishment of achievement standards was directly related to evaluation, so it recognized the need to refine policies such as new description for evaluation clause in future science 'guidelines'. Finally, considering science and characteristics, it was mentioned that it is necessary to specify regional intensive science education policies in the 'guidelines' themselves beyond the localization of teaching materials.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.55-79
• /
• 2013

In this paper, we propose a hybrid genetic algorithm (HGA) approach to effectively solve the reverse logistics network with centralized centers (RLNCC). For the proposed HGA approach, genetic algorithm (GA) is used as a main algorithm. For implementing GA, a new bit-string representation scheme using 0 and 1 values is suggested, which can easily make initial population of GA. As genetic operators, the elitist strategy in enlarged sampling space developed by Gen and Chang (1997), a new two-point crossover operator, and a new random mutation operator are used for selection, crossover and mutation, respectively. For hybrid concept of GA, an iterative hill climbing method (IHCM) developed by Michalewicz (1994) is inserted into HGA search loop. The IHCM is one of local search techniques and precisely explores the space converged by GA search. The RLNCC is composed of collection centers, remanufacturing centers, redistribution centers, and secondary markets in reverse logistics networks. Of the centers and secondary markets, only one collection center, remanufacturing center, redistribution center, and secondary market should be opened in reverse logistics networks. Some assumptions are considered for effectively implementing the RLNCC The RLNCC is represented by a mixed integer programming (MIP) model using indexes, parameters and decision variables. The objective function of the MIP model is to minimize the total cost which is consisted of transportation cost, fixed cost, and handling cost. The transportation cost is obtained by transporting the returned products between each centers and secondary markets. The fixed cost is calculated by opening or closing decision at each center and secondary markets. That is, if there are three collection centers (the opening costs of collection center 1 2, and 3 are 10.5, 12.1, 8.9, respectively), and the collection center 1 is opened and the remainders are all closed, then the fixed cost is 10.5. The handling cost means the cost of treating the products returned from customers at each center and secondary markets which are opened at each RLNCC stage. The RLNCC is solved by the proposed HGA approach. In numerical experiment, the proposed HGA and a conventional competing approach is compared with each other using various measures of performance. For the conventional competing approach, the GA approach by Yun (2013) is used. The GA approach has not any local search technique such as the IHCM proposed the HGA approach. As measures of performance, CPU time, optimal solution, and optimal setting are used. Two types of the RLNCC with different numbers of customers, collection centers, remanufacturing centers, redistribution centers and secondary markets are presented for comparing the performances of the HGA and GA approaches. The MIP models using the two types of the RLNCC are programmed by Visual Basic Version 6.0, and the computer implementing environment is the IBM compatible PC with 3.06Ghz CPU speed and 1GB RAM on Windows XP. The parameters used in the HGA and GA approaches are that the total number of generations is 10,000, population size 20, crossover rate 0.5, mutation rate 0.1, and the search range for the IHCM is 2.0. Total 20 iterations are made for eliminating the randomness of the searches of the HGA and GA approaches. With performance comparisons, network representations by opening/closing decision, and convergence processes using two types of the RLNCCs, the experimental result shows that the HGA has significantly better performance in terms of the optimal solution than the GA, though the GA is slightly quicker than the HGA in terms of the CPU time. Finally, it has been proved that the proposed HGA approach is more efficient than conventional GA approach in two types of the RLNCC since the former has a GA search process as well as a local search process for additional search scheme, while the latter has a GA search process alone. For a future study, much more large-sized RLNCCs will be tested for robustness of our approach.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Clinical and Experimental Pediatrics
• /
• v.50 no.2
• /
• pp.182-189
• /
• 2007

Purpose : The primary purpose of this study was to evaluate the growth and neuropsychologic function following treatments for pediatric hematologic and oncologic diseases. Healthy monozygotic twins served as ideal controls for comparison to exclude possible confounding factors. Methods : Seven children treated with various hematologic and oncologic diseases were included in the study: acute lymphoblastic leukemia (ALL; n=2), Diamond-Blackfan anemia twins (n=2), and aplastic anemia (n=3). The median age at the diagnosis was 5.2 (0.3-15) years. The median duration of follow-up was 7.2 (4.9-10) years. Controls were healthy monozygotic twins. Growth was measured and the percentile channels were evaluated sequentially for patients. The K-WISC III was applied and compared in 5 pairs of patients and controls. Results : Similar growth profiles were noted for the twins. The percentiles at diagnosis was 3-10 in 3, 25-50 in 2, and 50-75 in 2 cases. All patients stayed in their growth percentiles through follow-up, except for 1 patient who became obese. For IQ tests, the mean behavioral, verbal and full scale IQ scores of patients were 88.0, 93.8, and 89.8, respectively, and those from their corresponding controls were 92.2, 97.0, and 91.7 (P>0.05). However, 2 children who were treated for ALL had lower IQ scores. Conclusion : Similar growth profiles were observed in the monozygotic twins in terms of height and weight. The IQ scores of patients were similar to those of monozygotic twins. However, prophylactic CNS-directed therapy for leukemia might adversely affect the IQ scores. A further prospective study on larger number of twins is warranted.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.