• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.145-154
• /
• 2022

Automatic Target Recognition (ATR) technology is emerging as a core technology of Future Combat Systems (FCS). Conventional ATR is performed based on IMINT (image information) collected from the SAR sensor, and various image-based deep learning models are used. However, with the development of IT and sensing technology, even though data/information related to ATR is expanding to HUMINT (human information) and SIGINT (signal information), ATR still contains image oriented IMINT data only is being used. In complex and diversified battlefield situations, it is difficult to guarantee high-level ATR accuracy and generalization performance with image data alone. Therefore, we propose a knowledge graph-based ATR method that can utilize image and text data simultaneously in this paper. The main idea of the knowledge graph and deep model-based ATR method is to convert the ATR image and text into graphs according to the characteristics of each data, align it to the knowledge graph, and connect the heterogeneous ATR data through the knowledge graph. In order to convert the ATR image into a graph, an object-tag graph consisting of object tags as nodes is generated from the image by using the pre-trained image object recognition model and the vocabulary of the knowledge graph. On the other hand, the ATR text uses the pre-trained language model, TF-IDF, co-occurrence word graph, and the vocabulary of knowledge graph to generate a word graph composed of nodes with key vocabulary for the ATR. The generated two types of graphs are connected to the knowledge graph using the entity alignment model for improvement of the ATR performance from images and texts. To prove the superiority of the proposed method, 227 documents from web documents and 61,714 RDF triples from dbpedia were collected, and comparison experiments were performed on precision, recall, and f1-score in a perspective of the entity alignment..

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• Information Systems Review
• /
• v.25 no.2
• /
• pp.145-162
• /
• 2023

Asset management is a complex and difficult field that requires insight into numerous variables and even human psychology. Thus, it has traditionally been the domain of professionals, and these services have been expensive to obtain. Changes are taking place in these markets, and the driving force is the digital revolution, so-called the fourth industrial revolution. Among them, the Robo-Advisor service using artificial intelligence technology is the highlight. The reason is that it is possible to popularize investment advisory services with convenient accessibility and low cost. This study aims to clarify what factors are critically important when selecting robo-advisors for service users and providers in Korea, and what perception differences exist in the selection factors between user and provider groups. The framework of the study was based on the marketing mix 4C model, and the design and analysis of the model used Delphi survey and AHP. Through the study design, 4 main criteria and 15 sub-criteria were derived, and the findings of the study are as follows. First, the importance of the four main criteria was in the order of customer needs > customer convenience > customer cost > customer communication for both groups. Second, looking at the 15 sub-criteria, it was found that investment purpose coverage, investment propensity coverage, fee level and accessibility factors were the most important. Third, when comparing between groups, the user group found that the fee level and accessibility factors were the most important, and the provider group recognized the investment purpose coverage and investment propensity coverage factors as important. This study derived useful implications in practice. First, when designing for the spread of the robo-advisor service, the basis for constructing a user-oriented system was prepared by considering the priority of importance according to the weight difference between the four main criteria and the 15 sub-criteria. In addition, the difference in priority of each sub-criteria shown in the group comparison and the cause of the sub-criteria with large weight differences were identified. In addition, it was suggested that it is very important to form a consensus to resolve the difference in perception of factors between those in charge of strategy and marketing and system development within the provider group. Academically, it is meaningful in that it is an early study that presented various perspectives and perspectives by deriving a number of robo-advisor selection factors. Through the findings of this study, it is expected that a successful user-oriented robo-advisor system can be built and spread in Korea to help users.

• Asia pacific journal of information systems
• /
• v.17 no.4
• /
• pp.31-59
• /
• 2007

We frequently use search engines to find relevant information in the Web but still end up with too much information. In order to solve this problem of information overload, ranking algorithms have been applied to various domains. As more information will be available in the future, effectively and efficiently ranking search results will become more critical. In this paper, we propose a ranking algorithm for the Semantic Web resources, specifically RDF resources. Traditionally, the importance of a particular Web page is estimated based on the number of key words found in the page, which is subject to manipulation. In contrast, link analysis methods such as Google's PageRank capitalize on the information which is inherent in the link structure of the Web graph. PageRank considers a certain page highly important if it is referred to by many other pages. The degree of the importance also increases if the importance of the referring pages is high. Kleinberg's algorithm is another link-structure based ranking algorithm for Web pages. Unlike PageRank, Kleinberg's algorithm utilizes two kinds of scores: the authority score and the hub score. If a page has a high authority score, it is an authority on a given topic and many pages refer to it. A page with a high hub score links to many authoritative pages. As mentioned above, the link-structure based ranking method has been playing an essential role in World Wide Web(WWW), and nowadays, many people recognize the effectiveness and efficiency of it. On the other hand, as Resource Description Framework(RDF) data model forms the foundation of the Semantic Web, any information in the Semantic Web can be expressed with RDF graph, making the ranking algorithm for RDF knowledge bases greatly important. The RDF graph consists of nodes and directional links similar to the Web graph. As a result, the link-structure based ranking method seems to be highly applicable to ranking the Semantic Web resources. However, the information space of the Semantic Web is more complex than that of WWW. For instance, WWW can be considered as one huge class, i.e., a collection of Web pages, which has only a recursive property, i.e., a 'refers to' property corresponding to the hyperlinks. However, the Semantic Web encompasses various kinds of classes and properties, and consequently, ranking methods used in WWW should be modified to reflect the complexity of the information space in the Semantic Web. Previous research addressed the ranking problem of query results retrieved from RDF knowledge bases. Mukherjea and Bamba modified Kleinberg's algorithm in order to apply their algorithm to rank the Semantic Web resources. They defined the objectivity score and the subjectivity score of a resource, which correspond to the authority score and the hub score of Kleinberg's, respectively. They concentrated on the diversity of properties and introduced property weights to control the influence of a resource on another resource depending on the characteristic of the property linking the two resources. A node with a high objectivity score becomes the object of many RDF triples, and a node with a high subjectivity score becomes the subject of many RDF triples. They developed several kinds of Semantic Web systems in order to validate their technique and showed some experimental results verifying the applicability of their method to the Semantic Web. Despite their efforts, however, there remained some limitations which they reported in their paper. First, their algorithm is useful only when a Semantic Web system represents most of the knowledge pertaining to a certain domain. In other words, the ratio of links to nodes should be high, or overall resources should be described in detail, to a certain degree for their algorithm to properly work. Second, a Tightly-Knit Community(TKC) effect, the phenomenon that pages which are less important but yet densely connected have higher scores than the ones that are more important but sparsely connected, remains as problematic. Third, a resource may have a high score, not because it is actually important, but simply because it is very common and as a consequence it has many links pointing to it. In this paper, we examine such ranking problems from a novel perspective and propose a new algorithm which can solve the problems under the previous studies. Our proposed method is based on a class-oriented approach. In contrast to the predicate-oriented approach entertained by the previous research, a user, under our approach, determines the weights of a property by comparing its relative significance to the other properties when evaluating the importance of resources in a specific class. This approach stems from the idea that most queries are supposed to find resources belonging to the same class in the Semantic Web, which consists of many heterogeneous classes in RDF Schema. This approach closely reflects the way that people, in the real world, evaluate something, and will turn out to be superior to the predicate-oriented approach for the Semantic Web. Our proposed algorithm can resolve the TKC(Tightly Knit Community) effect, and further can shed lights on other limitations posed by the previous research. In addition, we propose two ways to incorporate data-type properties which have not been employed even in the case when they have some significance on the resource importance. We designed an experiment to show the effectiveness of our proposed algorithm and the validity of ranking results, which was not tried ever in previous research. We also conducted a comprehensive mathematical analysis, which was overlooked in previous research. The mathematical analysis enabled us to simplify the calculation procedure. Finally, we summarize our experimental results and discuss further research issues.

• Korean Journal of Agricultural Science
• /
• v.3 no.1
• /
• pp.39-51
• /
• 1976

As an accempt to increase thc efficiency of land use and the food production to achieve the national goal in the food self-sufficiency, nine cropping systems on the upper-land were examined in pure-stand and in mixtures of soybean, corn, potato and radish. The important conclusions of this study were summarized as follows; 1. The flowering date of soybean was two or three days earlier in pure-stand than in the mixture with corn. The maturing date two days earlier in the pure-stand than in the mixture with corn. The flowering and maturing dates were not different among various cropping systems in corn. 2. The stem length of soybean was significantly different among various cropping systems. Soybean in pure-stand was shorter in stem length than with corn. 3. The number of pods per soybean plant did not give any significant differences among various cultivation methods. 4. The length of internode and the number of nodes per soybean plant in the mixture with corn were greater than in the pure-stand. In the number of branches per plant this was reversed. 5. The average stem dry weight of soybean per 10a was not significantly different among various cultivation methods. 6. The soybean yield per 10a in the pure-stand was obviously greater than the mixture and there were significant differences among cultivation method within the mixture with corn in soybean yield. 7. The 1,000-grain weight of soybean was significantly different and those in the pure-stand was heavier than those in the mixture with corn. 8. Grain weight per soybean plant and the stem diameter in the pure-stand were significantly lesser than those in the mixture with corn. 9. In the comparisons of corn in the pure-stand and in the mixture with soybean, plant height, number of ear per 10a, mean ear weight and remember of grain per plant, 100-grain weight, ear length, ear girth and number of ear pel plant were not significantly different among various cultivation methods except for the grain yield per 10a. 10. In the economic analysis, the mixture with soybean and corn gave the greatest gross income. The combination 7 was the best which was 47.6% increase income comparing with the soybean pure-stand. 11. As it can be assumed, soybean plant was influenced greatly than corn by various cropping system. It is necessary to study more complex cropping system finding and giving more desirable multiple cropping system for the farmer.

• Journal of Korean Home Economics Education Association
• /
• v.19 no.3
• /
• pp.149-168
• /
• 2007

The purpose of this study was to analyze the home economics education items in the teacher recruitment examination for secondary school. To achieve the purpose, all the home economics education items, which were carried out for seven times from the school year 2001 to the most recent year 2007, were compared and analyzed. The form of items was analyzed by frequency and rate. Behavioral domain of items was analyzed by content analysis. In this study, some recommendations were suggested for the quality of home economics education items through discussion of science education and society education items, which were abstracted from the school year 2001 to the most recent year 2007. The results of this study were as follows. First, the score ratio of home economics education items was fluid as 20-30% from the school year 2001 to 2004 but it fixed as 30-35% since the school year 2005. In subcategory of home economics education, curriculum items accounted for highest ratio(43%). In the next thing, items of teaching-learning method(35%), evaluation(19%) and philosophy(3%) related to home economics education were followed in order. Second, the form of home economics education items was coexistent form of single item and subordinate item from the school year 2001 to 2004. But it was changed into form of single item by 100% since the school year 2005. Third, regarding the content of home economics education items, most of the curriculum items were related to the content of the 7th National Curriculum. Teaching-learning method items were taken mostly from model of teaching-learning. Evaluation items were taken mostly from performance assessment. Philosophy items related to home economics education were taken only from Habermas's three systems of action on the school year 2005. Fourth, about behavioral domain of home economics education items, most of the curriculum items were level of 'simple knowledge or memory'. Therefore, it was suggested that behavioral domain of curriculum items had to be changed into 'complex knowledge or comprehension and application'. The behavioral domain of teaching-learning method items and education evaluation items was mostly 'complex knowledge or comprehension and application'. However, to bettering the items it was suggested that the behavioral domain of them has to be changed 'comprehension' into more 'application'. Fifth, regarding the coverage of home economics education items, curriculum items were limited only superficial content of the 7th National Curriculum. Therefore, it was suggested that coverage of curriculum items had to be extended to theoretical content, which was philosophical background and various principles of curriculum. It was suggested that coverage of teaching-learning method items had to be extended to the content including various teaching-learning theories and the practical reasoning home economics instruction proved effective as home economics instruction recently. Evaluation items were taken mostly from performance assessment. Therefore, it was suggested that coverage of evaluation items had to be extended to analysis of evaluation result, item validity and reliability, and evaluator's philosophical perspective.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Asia pacific journal of information systems
• /
• v.18 no.4
• /
• pp.27-55
• /
• 2008

Due to the increasing and intensifying competition in the Internet shopping market, it has been recognized as very important to develop an effective policy and strategy for acquiring loyal customers. For this reason, web site designers need to know if a new Internet shopping mall(ISM) will be accepted. Researchers have been working on identifying factors for explaining and predicting user acceptance of an ISM. Some studies, however, revealed inconsistent findings on the antecedents of user acceptance of a website. Lack of consideration for individual differences in user ability is believed to be one of the key reasons for the mixed findings. The elaboration likelihood model (ELM) and several studies have suggested that individual differences in ability plays an moderating role on the relationship between the antecedents and user acceptance. Despite the critical role of user ability, little research has examined the role of user ability in the Internet shopping mall context. The purpose of this study is to develop a user acceptance model that consider the moderating role of user ability in the context of Internet shopping. This study was initiated to see the ability of the technology acceptance model(TAM) to explain the acceptance of a specific ISM. According to TAM. which is one of the most influential models for explaining user acceptance of IT, an intention to use IT is determined by usefulness and ease of use. Given that interaction between user and website takes place through web interface, the decisions to accept and continue using an ISM depend on these beliefs. However, TAM neglects to consider the fact that many users would not stick to an ISM until they trust it although they may think it useful and easy to use. The importance of trust for user acceptance of ISM has been raised by the relational views. The relational view emphasizes the trust-building process between the user and ISM, and user's trust on the website is a major determinant of user acceptance. The proposed model extends and integrates the TAM and relational views on user acceptance of ISM by incorporating usefulness, ease of use, and trust. User acceptance is defined as a user's intention to reuse a specific ISM. And user ability is introduced into the model as moderating variable. Here, the user ability is defined as a degree of experiences, knowledge and skills regarding Internet shopping sites. The research model proposes that the ease of use, usefulness and trust of ISM are key determinants of user acceptance. In addition, this paper hypothesizes that the effects of the antecedents(i.e., ease of use, usefulness, and trust) on user acceptance may differ among users. In particular, this paper proposes a moderating effect of a user's ability on the relationship between antecedents with user's intention to reuse. The research model with eleven hypotheses was derived and tested through a survey that involved 470 university students. For each research variable, this paper used measurement items recognized for reliability and widely used in previous research. We slightly modified some items proper to the research context. The reliability and validity of the research variables were tested using the Crobnach's alpha and internal consistency reliability (ICR) values, standard factor loadings of the confirmative factor analysis, and average variance extracted (AVE) values. A LISREL method was used to test the suitability of the research model and its relating six hypotheses. Key findings of the results are summarized in the following. First, TAM's two constructs, ease of use and usefulness directly affect user acceptance. In addition, ease of use indirectly influences user acceptance by affecting trust. This implies that users tend to trust a shopping site and visit repeatedly when they perceive a specific ISM easy to use. Accordingly, designing a shopping site that allows users to navigate with heuristic and minimal clicks for finding information and products within the site is important for improving the site's trust and acceptance. Usefulness, however, was not found to influence trust. Second, among the three belief constructs(ease of use, usefulness, and trust), trust was empirically supported as the most important determinants of user acceptance. This implies that users require trustworthiness from an Internet shopping site to be repeat visitors of an ISM. Providing a sense of safety and eliminating the anxiety of online shoppers in relation to privacy, security, delivery, and product returns are critically important conditions for acquiring repeat visitors. Hence, in addition to usefulness and ease of use as in TAM, trust should be a fundamental determinants of user acceptance in the context of internet shopping. Third, the user's ability on using an Internet shopping site played a moderating role. For users with low ability, ease of use was found to be a more important factors in deciding to reuse the shopping mall, whereas usefulness and trust had more effects on users with high ability. Applying the EML theory to these findings, we can suggest that experienced and knowledgeable ISM users tend to elaborate on such usefulness aspects as efficient and effective shopping performance and trust factors as ability, benevolence, integrity, and predictability of a shopping site before they become repeat visitors of the site. In contrast, novice users tend to rely on the low elaborating features, such as the perceived ease of use. The existence of moderating effects suggests the fact that different individuals evaluate an ISM from different perspectives. The expert users are more interested in the outcome of the visit(usefulness) and trustworthiness(trust) than those novice visitors. The latter evaluate the ISM in a more superficial manner focusing on the novelty of the site and on other instrumental beliefs(ease of use). This is consistent with the insights proposed by the Heuristic-Systematic model. According to the Heuristic-Systematic model. a users act on the principle of minimum effort. Thus, the user considers an ISM heuristically, focusing on those aspects that are easy to process and evaluate(ease of use). When the user has sufficient experience and skills, the user will change to systematic processing, where they will evaluate more complex aspects of the site(its usefulness and trustworthiness). This implies that an ISM has to provide a minimum level of ease of use to make it possible for a user to evaluate its usefulness and trustworthiness. Ease of use is a necessary but not sufficient condition for the acceptance and use of an ISM. Overall, the empirical results generally support the proposed model and identify the moderating effect of the effects of user ability. More detailed interpretations and implications of the findings are discussed. The limitations of this study are also discussed to provide directions for future research.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.55-78
• /
• 2021

Tosolve complex and diverse social problems and ensure the quality of life of individuals, social robots that can interact with humans are attracting attention. In the past, robots were recognized as beings that provide labor force as they put into industrial sites on behalf of humans. However, the concept of today's robot has been extended to social robots that coexist with humans and enable social interaction with the advent of Smart technology, which is considered an important driver in most industries. Specifically, there are service robots that respond to customers, the robots that have the purpose of edutainment, and the emotionalrobots that can interact with humans intimately. However, popularization of robots is not felt despite the current information environment in the modern ICT service environment and the 4th industrial revolution. Considering social interaction with users which is an important function of social robots, not only the technology of the robots but also other factors should be considered. The design elements of the robot are more important than other factors tomake consumers purchase essentially a social robot. In fact, existing studies on social robots are at the level of proposing "robot development methodology" or testing the effects provided by social robots to users in pieces. On the other hand, consumer emotions felt from the robot's appearance has an important influence in the process of forming user's perception, reasoning, evaluation and expectation. Furthermore, it can affect attitude toward robots and good feeling and performance reasoning, etc. Therefore, this study aims to verify the effect of appearance of social robot and consumer emotions on consumer's attitude toward social robot. At this time, a social robot design evaluation model is constructed by combining heterogeneous data from different sources. Specifically, the three quantitative indicator data for the appearance of social robots from the ABOT Database is included in the model. The consumer emotions of social robot design has been collected through (1) the existing design evaluation literature and (2) online buzzsuch as product reviews and blogs, (3) qualitative interviews for social robot design. Later, we collected the score of consumer emotions and attitudes toward various social robots through a large-scale consumer survey. First, we have derived the six major dimensions of consumer emotions for 23 pieces of detailed emotions through dimension reduction methodology. Then, statistical analysis was performed to verify the effect of derived consumer emotionson attitude toward social robots. Finally, the moderated regression analysis was performed to verify the effect of quantitatively collected indicators of social robot appearance on the relationship between consumer emotions and attitudes toward social robots. Interestingly, several significant moderation effects were identified, these effects are visualized with two-way interaction effect to interpret them from multidisciplinary perspectives. This study has theoretical contributions from the perspective of empirically verifying all stages from technical properties to consumer's emotion and attitudes toward social robots by linking the data from heterogeneous sources. It has practical significance that the result helps to develop the design guidelines based on consumer emotions in the design stage of social robot development.