• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.211-218
• /
• 2022

Continuous wave (CW) radar has the advantage of reliability and accuracy compared to other sensors such as camera and lidar. In addition, binarized neural network (BNN) has a characteristic that dramatically reduces memory usage and complexity compared to other deep learning networks. Therefore, this paper proposes binarized neural network based human identification and motion classification system using CW radar. After receiving a signal from CW radar, a spectrogram is generated through a short-time Fourier transform (STFT). Based on this spectrogram, we propose an algorithm that detects whether a person approaches a radar. Also, we designed an optimized BNN model that can support the accuracy of 90.0% for human identification and 98.3% for motion classification. In order to accelerate BNN operation, we designed BNN hardware accelerator on field programmable gate array (FPGA). The accelerator was implemented with 1,030 logics, 836 registers, and 334.904 Kbit block memory, and it was confirmed that the real-time operation was possible with a total calculation time of 6 ms from inference to transferring result.

• Journal of Practical Engineering Education
• /
• v.13 no.3
• /
• pp.515-532
• /
• 2021

The purpose of this study was to analysis of PBL for Korean Apprenticeship Program in Mechanical Engineering. The details of the study were as follows: First, the perception related to the PBL of Korean apprenticeship program was investigated. Second, the utilization and the operational difficulties of PBL for Korean Apprenticeship Program were investigated. Third, the supporting system for PBL was suggested. Research methods were literature research, questionnaire survey and FGI. The survey was conducted online from July 15 to August 14, 2021. A total of 515 respondents responded. A total of 108 in 515 respondents were in Mechanical Engineering. FGI conducted a total of 25 people who actual use PBL in the field of Korean Apprenticeship Program. Conclusions and suggestions based upon the result of this study are as follows. First, It is necessary to improve the utilization of PBL for Korean Apprenticeship Program in Industry. Second, PBL is necessary to apply optionally according to the job and field situation. Third, it is necessary to support system of evaluation for PBL in Korean Apprenticeship Program. Finally, related operation model and guideline need to be prepared for best practice.

• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.28-34
• /
• 2022

This study analyzes the impact that accidents and near misses have on clients' and contractors' awareness of safety culture. Due to the unique characteristic of employment structure in Korea, the occurrence of accidents differs by company size, which has relevant implications for the establishment of safety culture. Attention has been drawn to the importance of the management of accidents and near misses, with safety awareness acting as a core factor. A positive effect on the prevention of accidents could be achieved by noting the difference in safety awareness between clients and contractors and suggesting an associated suitable safety management system. In support of this study, a survey was distributed to workers in the automobile manufacturing industry (May-August 2020), and data from a total of 574 workers was collected and analyzed, including 399 clients' worksers and 175 contractors' workers. The questionnaire addressed participants' experiences of accidents and near misses as well as 50 items from the Nordic Occupational Safety Climate Questionnaire. Analysis of the responses was conducted using the methods of frequency analysis, Fisher's exact test, t-test, correlation analysis, and regression analysis. The results demonstrated that clients had more experiences with accidents and near misses compared to contractors. Additional differences between clients and contractors were noted in terms of the safety culture factors of learning, communication, and trust. A correlation was observed between the experience of accidents and safety justice management: for clients and contractors who experienced accidents, safety justice management was 9.4 times higher. Furthermore, clients' and contractors' awareness of employees' commitment to safety was determined to be 28.5 times higher in those who had experienced near misses This study concludes that, in order to improve accident prevention through the management of accidents and near misses, clients must focus on overseeing safety justice management and aspects of safety culture factors, while contractors must focus efforts on managing employees' commitment to safety. In further applications, this study could provide baseline data for health and safety activities in terms of the safety culture of clients and contractors. Further study on the establishment of safety culture as related to employment structure is proposed for future research.

• KDI Journal of Economic Policy
• /
• v.13 no.4
• /
• pp.91-116
• /
• 1991

Market liberalization progressing simultaneously with high and rapidly rising domestic wages has created an adverse business environment for domestic firms. Korean firms are losing their international competitiveness in comparison to firms from LDC(Less Developed Countries) in low-tech industries. In high-tech industries, domestic firms without government protection (which is impossible due to the liberalization policy and the current international status of the Korean economy) are in a disadvantaged position relative to firms from advanced countries. This paper examines the division of roles between the private sector and the government in order to achieve a successful structural adjustment, which has become the impending industrial policy issue caused by high domestic wages, on the one hand, and the opening of domestic markets, on the other. The micro foundation of the economy-wide structural adjustment is actually the restructuring of business portfolios at the firm level. The firm-level business restructuring means that firms in low-value-added businesses or with declining market niches establish new major businesses in higher value-added segments or growing market niches. The adjustment of the business structure at the firm level can only be accomplished by accumulating firm-specific managerial assets necessary to establish a new business structure. This can be done through learning-by-doing in the whole system of management, including research and development, manufacturing, and marketing. Therefore, the voluntary cooperation among the people in the company is essential for making the cost of the learning process lower than that at the competing companies. Hence, firms that attempt to restructure their major businesses need to induce corporate-wide participation through innovations in organization and management, encourage innovative corporate culture, and maintain cooperative labor unions. Policy discussions on structural adjustments usually regard firms as a black box behind a few macro variables. But in reality, firm activities are not flows of materials but relationships among human resources. The growth potential of companies are embodied in the human resources of the firm; the balance of interest among stockholders, managers, and workers of the company' brings the accumulation of the company's core competencies. Therefore, policymakers and economists shoud change their old concept of the firm as a technological black box which produces a marketable commodities. Firms should be regarded as coalitions of interest groups such as stockholders, managers, and workers. Consequently the discussion on the structural adjustment both at the macroeconomic level and the firm level should be based on this new paradigm of understanding firms. The government's role in reducing the cost of structural adjustment and supporting should the creation of new industries emphasize the following: First, government must promote the competition in domestic markets by revising laws related to antitrust policy, bankruptcy, and the promotion of small and medium-sized companies. General consensus on the limitations of government intervention and the merit of deregulation should be sought among policymakers and people in the business world. In the age of internationalization, nation-specific competitive advantages cannot be exclusively in favor of domestic firms. The international competitiveness of a domestic firm derives from the firm-specific core competencies which can be accumulated by internal investment and organization of the firm. Second, government must build up a solid infrastructure of production factors including capital, technology, manpower, and information. Structural adjustment often entails bankruptcies and partial waste of resources. However, it is desirable for the government not to try to sustain marginal businesses, but to support the diversification or restructuring of businesses by assisting in factor creation. Institutional support for venture businesses needs to be improved, especially in the financing system since many investment projects in venture businesses are highly risky, even though they are very promising. The proportion of low-value added production processes and declining industries should be reduced by promoting foreign direct investment and factory automation. Moreover, one cannot over-emphasize the importance of future-oriented labor policies to be based on the new paradigm of understanding firm activities. The old laws and instititutions related to labor unions need to be reformed. Third, government must improve the regimes related to money, banking, and the tax system to change business practices dependent on government protection or undesirable in view of the evolution of the Korean economy as a whole. To prevent rational business decisions from contradicting to the interest of the economy as a whole, government should influence the business environment, not the business itself.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.83-105
• /
• 2016

Measuring an individual's subjective wellbeing in an accurate, unobtrusive, and cost-effective manner is a core success factor of the wellbeing support system, which is a type of medical IT service. However, measurements with a self-report questionnaire and wearable sensors are cost-intensive and obtrusive when the wellbeing support system should be running in real-time, despite being very accurate. Recently, reasoning the state of subjective wellbeing with conventional sentiment analysis and unstructured data has been proposed as an alternative to resolve the drawbacks of the self-report questionnaire and wearable sensors. However, this approach does not consider contextual polarity, which results in lower measurement accuracy. Moreover, there is no sentimental word net or ontology for the subjective wellbeing area. Hence, this paper proposes a method to extract keywords and their contextual polarity representing the subjective wellbeing state from the unstructured text in online websites in order to improve the reasoning accuracy of the sentiment analysis. The proposed method is as follows. First, a set of general sentimental words is proposed. SentiWordNet was adopted; this is the most widely used dictionary and contains about 100,000 words such as nouns, verbs, adjectives, and adverbs with polarities from -1.0 (extremely negative) to 1.0 (extremely positive). Second, corpora on subjective wellbeing (SWB corpora) were obtained by crawling online text. A survey was conducted to prepare a learning dataset that includes an individual's opinion and the level of self-report wellness, such as stress and depression. The participants were asked to respond with their feelings about online news on two topics. Next, three data sources were extracted from the SWB corpora: demographic information, psychographic information, and the structural characteristics of the text (e.g., the number of words used in the text, simple statistics on the special characters used). These were considered to adjust the level of a specific SWB. Finally, a set of reasoning rules was generated for each wellbeing factor to estimate the SWB of an individual based on the text written by the individual. The experimental results suggested that using contextual polarity for each SWB factor (e.g., stress, depression) significantly improved the estimation accuracy compared to conventional sentiment analysis methods incorporating SentiWordNet. Even though literature is available on Korean sentiment analysis, such studies only used only a limited set of sentimental words. Due to the small number of words, many sentences are overlooked and ignored when estimating the level of sentiment. However, the proposed method can identify multiple sentiment-neutral words as sentiment words in the context of a specific SWB factor. The results also suggest that a specific type of senti-word dictionary containing contextual polarity needs to be constructed along with a dictionary based on common sense such as SenticNet. These efforts will enrich and enlarge the application area of sentic computing. The study is helpful to practitioners and managers of wellness services in that a couple of characteristics of unstructured text have been identified for improving SWB. Consistent with the literature, the results showed that the gender and age affect the SWB state when the individual is exposed to an identical queue from the online text. In addition, the length of the textual response and usage pattern of special characters were found to indicate the individual's SWB. These imply that better SWB measurement should involve collecting the textual structure and the individual's demographic conditions. In the future, the proposed method should be improved by automated identification of the contextual polarity in order to enlarge the vocabulary in a cost-effective manner.

• Journal of Technology Innovation
• /
• v.20 no.2
• /
• pp.75-107
• /
• 2012

Previous researches on technological innovation have several limitations such as lack of general mechanism for technological innovation(inputs, throughputs and outputs of technological innovation), large company oriented studies, and ignoring importance of technology management capabilities. So, this study suggested a new model using resource-based theory and system theory, and empirically applied that to SMEs. Structural equation model analysis by using 223 SMEs in Daegu region provided a support for most of hypotheses. Research results showed that all of factors on technological innovation were significantly and positively related with each other: inputs(R&D leadership, innovation strategy, R&D investment, R&D human resource management, external network), throughputs(portfolio management, project management, technology commercialization) and output(technological innovation). In case of technological innovation inputs, R&D leadership influenced on innovation strategy positively and significantly. And R&D leadership and innovation strategy had positive and significant effects on R&D investment, R&D human resource management and external network. R&D human resource management and external network exerted positive and significant influences on technological innovation throughputs such as portfolio management and project management. But R&D investment did not significant impacts on technological innovation throughputs. Among technological innovation throughputs, both portfolio management and project management had positive and significant effect on technology commercialization. In addition, technology commercialization acted positively and significantly technological innovation output. This study suggests necessary of efforts to implement innovation strategy and manage R&D human resource effectively based on CEO's innovativeness and entrepreneurship. Also, if SMEs want to develop technology and commercialize it, they have to cooperate with external technology resources and informations. Research results revealed that proper level of R&D investment, internal and external communication, information sharing, and learning and cooperative culture were very important for improvement of technological innovation performance in SMEs. Especially, this research suggested that if SMEs manage technological innovation process effectively based on resource-based and system approaches, then they can overcome their resource limitations and gain high technological innovation performance. Also, useful policy support for technological innovation of central or regional government by this research model is important factor for SMEs' technological innovation performance.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.

• Sijohaknonchong
• /
• v.44
• /
• pp.105-138
• /
• 2016

Recently with the research function, "XML Digital collection of Sijo Texts in the Period of Modern Enlightenment" DB data is being provided through the Korean Research Memory (http://www.krm.or.kr) and the foundation for the constructing the contents of Sijo Texts in the Period of Modern Enlightenment has been laid. In this paper, by reviewing the characteristics and problems of Digital collection of Sijo Texts in the Period of Modern Enlightenment and searching for the improvement, I tried to find a way to make it into the content. This database has the primary meaning in the integrating and glancing at the vast amounts of Sijo in the Period of Modern Enlightenment to reaching 12,500 pieces. In addition, it is the first Sijo data base which is provide the variety of search features according to literature, name of poet, title of work, original text, per period, and etc. However, this database has the limits to verifying the overall aspects of the Sijo in the Period of Modern Enlightenment. The title and original text, which is written in the archaic word or Chinese character, could not be searched, because the standard type text of modern language is not formatted. And also the works and the individual Sijo works released after 1945 were missing in the database. It is inconvenient to extract the datum according to the poet, because poets are marked in the various ways such as one's real name, nom de plume and etc. To solve this kind of problems and improve the utilization of the database, I proposed the providing the standard type text of modern language, giving the index terms about content, providing the information on the work format and etc. Furthermore, if the Sijo database in the Period of Modern Enlightenment which is prepared the character of the Sijo Culture Information System could be built, it could be connected with the academic, educational contents. For the specific plan, I suggested as follow, - learning support materials for the Modern history and the national territory recognition on the Modern Age - source materials for studying indigenous animals and plants characters creating the commercial characters - applicability as the Sijo learning tool such as Sijo Game.