• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.

• Korean Journal of Heritage: History & Science
• /
• v.42 no.1
• /
• pp.122-142
• /
• 2009

This study explored all domestic and international theories for maintenance and health enhancement of an old and big tree, and carried out the anatomical survey of the operation part of the tree toward he current status of domestic surgery and the perception survey of an expert group, and drew out following conclusion through the process of suggesting its reform plan. First, as a result of analyzing the correlation of the 67 subject trees with their ages, growth status. surroundings, it revealed that they were closely related to positional characteristic, damage size, whereas were little related to materials by fillers. Second, the size of the affected part was the most frequent at the bough sheared part under $0.09m^2$, and the hollow size by position(part) was the biggest at 'root + stem' starting from the behind of the main root and stem As a result of analyzing the correlation, the same result was elicited at the group with low correlation. Third, the problem was serious in charging the fillers (especially urethane) in the big hollow or exposed root produced at the behind of the root and stem part, or surface-processing it. The benefit by charging the hollow part was analyzed as not so much. Fourth, the surface-processing of fillers currently used (artificial bark) is mainly 'epoxy+woven fabric+cork', but it is not flexible, so it has brought forth problems of frequent cracks and cracked surface at the joint part with the treetextured part. Fifth, the correlation with the external status of the operated part was very high with the closeness, surface condition, formation of adhesive tissue and internal survey result. Sixth, the most influential thing on flushing by the wrong management of an old and big tree was banking, and a wrong pruning was the source of the ground part damage. In pruning a small bough can easily recover itself from its damage as its formation of adhesive tissue when it is cut by a standard method. Seventh, the parameters affecting the times of related business handling of an old and big tree are 'the need of the conscious reform of the manager and related business'. Eighth, a reform plan in an institutional aspect can include the arrangement of the law and organization of the old and big tree management and preservation at an institutional aspect. This study for preparing a reform plan through the status survey of the designated old and big tree, has a limit inducing a reform plan based on the status survey through individual research, and a weak point suggesting grounds by any statistical data. This can be complemented by subsequent studies.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.1
• /
• pp.69-74
• /
• 2019

Purpose $^{18}F$-FDOPA using amino acid is particularly attractive for imaging of brain tumors because of the high uptake in tumor tissue and the low uptake in normal brain tissue. But, on the other hand, $^{18}F$-FDG is highly uptake in both tumor tissue and normal brain tissue. The purpose of study is to evaluate comparison of contrasts in $^{18}F$-FDOPA Brain PET/CT and $^{18}F$-FDG Brain PET/CT and to find out optimal scan time by analysis of variation in SUV with the passage of uptake time. Materials and Methods A region of interest of approximately $350mm^2$ at the center of the tumor and cerebellum in 12 patients ($51.4{\pm}12.8yrs$) who $^{18}F$-FDG Brain PET/CT and $^{18}F$-FDOPA Brain PET/CT were examined more than once each. The $SUV_{max}$ was measured, and the $SUV_{max}$ ratio (T/C ratio) of the tumor cerebellum was calculated. In the analysis of SUV, T/C ratio was calculated for each frame after dividing into 15 frames of 2 minutes each using List mode data in 25 patients ($49.{\pm}10.3yrs$). SPSS 21 was used to compare T/C ratio of $^{18}F$-FDOPA and T/C ratio of $^{18}F$-FDG. Results The T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than the T/C ratio of $^{18}F$-FDG Brain, and show a significant difference according to a paired t-test(t=-5.214, p=0.000). As a result of analyzing changes in $SUV_{max}$ and T/C ratio, the peak point of $SUV_{max}$ was $5.6{\pm}2.9$ and appeared in the fourth frame (6 to 8 minutes), and the peak of T/C ratio also appeared in the fourth frame (6 to 8 minutes). Taking this into consideration and comparing the existing 10 to 30 minutes image and 6 to 26 minutes image, the $SUV_{max}$ and T/C ratio increased by 0.2 and 0.1 each, compared to the 10 to 30 minutes image for 6 to 26 minutes image. Conclusion From this study, $^{18}F$-FDOPA Brain PET/CT is effective when reading the image, because the T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than T/C ratio of $^{18}F$-FDG Brain PET/CT. In addition, in the case of $^{18}F$-FDOPA Brain PET/CT, there was no difference between the existing 10 to 30 minutes image and 6 to 26 minutes image. Through continuous research, we can find possibility of shortening examination time in $^{18}F$-FDOPA Brain PET/CT. Also, we can help physician to accurate reading using additional scan data.

• Journal of the Korean Society of Radiology
• /
• v.13 no.3
• /
• pp.371-379
• /
• 2019

The purpose of this study was to investigate the effect of the change in the X-ray condition on the entrance surface dose (ESD) and dose area product (DAP) in the cine imaging of coronary angiography (CAG), and to analyze the usefulness of the condition change on the dose relation and image quality by measuring and analyzing the Signal to Noise Radio (SNR) and Contrast to Nois Ratio (CNR) of the angiographic images taken by the Image J program. Data were collected from 33 patients (24 males and 9 females) who underwent CAG at this hospital from November 2017 to March 2018. In terms of imaging condition and data acquisition, the ESD and DAP of group A with a high tube current of 397.2 mA and group B with a low tube current of 370.7 mA were retrospectively obtained for comparison and analysis. For the SNR and CNR measurement and analysis via Image J, the result values were derived by substituting the obtained data into the formula. The correlations among ESD and DAP according to the change in the imaging condition, SNR, and CNR were analyzed by using the SPSS statistical analysis software. The relationships of groups A and B, having a difference in the imaging condition, mA, with ESD ($A:483.5{\pm}60.1$; $B: 464.4{\pm}39.9$) and DAP ($A:84.3{\pm}10.7$; $B:81.5{\pm}7$) were not statistically significant (p>0.05). In the relationships with SNR and CNR based on Image J, the SNR ($5.451{\pm}0.529$) and CNR ($0.411{\pm}0.0432$) of the images obtained via the left coronary artery (LCA) imaging of group B showed differences of $0.475{\pm}0.096$ and $-0.048{\pm}0.0$, respectively, from the SNR ($4.976{\pm}0.433$) and CNR ($0.459{\pm}0.0431$) of the LCA of group A. However, the differences were not statistically significant (p<0.05). In the SNR and CNR obtained via the right coronary artery (RCA) imaging, the SNR ($4.731{\pm}0.773$) and CNR ($0.354{\pm}0.083$) of group A showed increased values of $1.491{\pm}0.405$ and $0.188{\pm}0.005$, respectively, from the SNR ($3.24{\pm}0.368$) and CNR ($0.166{\pm}0.033$) of group B. Among these, CNR was statistically significant (p<0.05). In the correlation analysis, statistically significant results were shown in SNR (LCA) and CNR (LCA); SNR (RCA) and CNR (RCA); ESD and DAP; ESD and sec; DAP and CNR (RCA); and DAP and sec (p<0.05). As a result of the analyses on the image quality evaluation and usefulness of the dose change, the SNR and CNR were increased in the RCA images of the CAG obtained by increasing the mA. Based on the result that CNR showed a statistically significant difference, it is believed that the contrast in the image quality can be further improved by increasing the mA in RCA imaging.

• Korean Journal of Heritage: History & Science
• /
• v.49 no.2
• /
• pp.86-103
• /
• 2016

'Sukchunjeahdo' illustration-book, which was left by Han, Pil-gyo(韓弼敎 : 1807~1878)in the late Joseon Dynasty, includes pictorial record paintings containing government offices, Eupchi, and Feng Shui condition drawn by Gyehwa(界畵) method Sabangjeondomyobeop(四方顚倒描法) and is the rare historical material that help to understand spatial structure and landscape characteristics. Youngyuhyun(永柔縣) and Sincheongun(信川郡) town, the case sites of this study, show Feng Shui foundation structure and placement rules of government offices in the Joseon Period are applied such as 3Dan 1Myo(三壇一廟 : Sajikdan, Yeodan, Seonghwangdan, Hyanggyo), 3Mun 3Jo(三門三朝 : Oeah, Dongheon, Naeah) and Jeonjohuchim(前朝後寢) etc. by setting the upper and lower hierarchy of the north south central axis. The circulation system is the pattern that roads are segmented around the marketplace of the entrance of the town and the structure is that heading to the north along the internal way leads to the government office and going out to the main street leads to the major city. Baesanimsu(背山臨水 : Mountain in backward and water in front) foundation, back hill pine forest, intentionally created low mountains and town forest etc. showed landscape aesthetics well suited for the environmental comfort condition such as microclimate control, natural disaster prevention, psychological stability reflecting color constancy principle etc. and tower pavilions were built throughout the scenic spot, reflecting life philosophy and thoughts of contemporaries such as physical and mental discipline, satisfied at the reality of poverty, returning to nature etc. For government office landscape, shielding and buffer planting, landscape planting etc. were considered around Gaeksa(客舍), Dongheon(東軒), Naeah(內衙) backyard and deciduous tree s and flowering trees were cultivated as main species and in case of Gaeksa, tiled pavilions and pavilions topped with poke weed in tetragonal pond were introduced to Dongheon and Naeah and separate pavilions were built for the purpose of physical and mental discipline and military training such as archery. Back hill pine tree forest formed back landscape and zelkova, pear trees, willow trees, old pine trees, lotus, flowering trees etc. were cultivated as gardening trees and Feng-Shui forest with willow trees as its main species was created for landscape and practical purposes. On the other hand, various cultural landscape elements etc. were introduced such as pavilions, pond serving as fire protection water(square and circle), stone pagoda and stone Buddha, fountains and wells, monument houses, flagpoles etc. In case of Sincheongun town forest(邑藪), Manhagwan(挽河觀), Moonmujeong(文武井), Sangjangdae(上場岱) and Hajangdae(下場岱) Market place, Josanshup<(造山藪 : Dongseojanglim(東西長林)>, Namcheon(南川) etc. were combined and community cultural park with the nature of modern urban park was operated. In this context, government office landscape shows the garden management aspect where square pond and pavilions, flowering trees are harmonized around side pavilion and backyard. Also, environmental design technique not biased to aesthetics and ideological moral philosophy and comprehensively considering functionality (shielding and fire prevention, microclimate control, etc.) and environmental soundness etc. is working.

• 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.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.6
• /
• pp.49-59
• /
• 2018

The purpose of this study was to analyze the importance and satisfaction of resources in the mouth of Nakdong River. A Pearson's chi-square test was performed in SPSS 24.0 for statistical analysis and the result of the study was summarized by three points. First, the results of importance analysis on resources in Nakdong estuary found that the importance of ecology resources was the highest with 27.1%, followed by landscape resources (18.5%), waterside leisure resources (6.5%), complex cultural resources (5.4%), and historic and cultural resources (3.3%). The probability values (p-value) of each group had shown significant differences depending on gender, age, and the location of the survey. For instance, women respondents reported a higher preference to ecology resources and complex cultural resources such as museums than men respondents as much as two times and three times, respectively. Meanwhile, men respondents showed a higher preference to waterside leisure resources in three times as much as women respondents. As for the analysis by age, the respondents in their 20s and 30s recorded a higher value than those in other age groups, and people in their 30s reported a higher preference to waterside leisure resources than those in different age groups by three times. Lastly, no significant differences were found in the preference analysis by occupation (p>.05). With regard to the results of satisfaction analysis, the average level of satisfaction on landscape resources was 6.01, and that of ecology resources and complex cultural resource were 5.65 and 5.15, respectively. Also, significant differences were found between landscape and ecology resources in the satisfaction analysis by age, landscape resources by age, ecology resources by region, and between landscape resources and ecology resources by occupation. The p-value of complex cultural resources was p=0.012, although the satisfaction level of landscape resources and ecology resources were reported to have no significant differences by age. As for the level of satisfaction in landscape resources, respondents in their 40s and 50s showed a high level of satisfaction. However, those in their 20s showed a relatively low level of satisfaction in the same category. The survey respondents living in Busan and South Gyeongsang Province and those living outside the regions revealed no significant differences in terms of satisfaction in landscape resources and complex cultural resources. However, the two same groups were found to show significant differences in the satisfaction analysis on ecology resources. In the satisfaction analysis of landscape resources and ecology resources by occupation, significant differences were found among college students, government employees, ordinary citizens, and expert groups. However, they showed no significant differences in the level of satisfaction to complex cultural resources. Third, the results of importance-satisfaction analysis on Nakdong estuary found that the average levels of satisfaction to landscape resources for each group of respondents who considered landscape, ecology, and cultural resources as important was 6.19, 6.08, and 5.67, respectively. Their levels of satisfaction on ecology resources were 5.95, 5.57, and 5.41 for each. Its correlation to the importance was insignificant. However, it was confirmed that the correlation to the level of satisfaction on complex cultural resources had a significant difference (p=0.025). In addition, the results of the analysis on 15 detailed items that was carried out with the aim to improving values and vitalizing resources in the mouth of Nakdong River found that respondents considered that the vitalization of eco-tourism (49.5%) and restoration of reed marsh (47.5%) were important. The results of detailed analysis revealed respondents' high awareness on the need of enhancing values on ecology resources. Also, improving infrastructure nearby the mouth, creating cycling routes, walkways, waterside leisure facilities, and others were considered as the requirements for the vitalization of Nakdong estuary.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.231-252
• /
• 2021

Artificial intelligence (AI) is a key technology that will change the future the most. It affects the industry as a whole and daily life in various ways. As data availability increases, artificial intelligence finds an optimal solution and infers/predicts through self-learning. Research and investment related to automation that discovers and solves problems on its own are ongoing continuously. Automation of artificial intelligence has benefits such as cost reduction, minimization of human intervention and the difference of human capability. However, there are side effects, such as limiting the artificial intelligence's autonomy and erroneous results due to algorithmic bias. In the labor market, it raises the fear of job replacement. Prior studies on the utilization of artificial intelligence have shown that individuals do not necessarily use the information (or advice) it provides. Algorithm error is more sensitive than human error; so, people avoid algorithms after seeing errors, which is called "algorithm aversion." Recently, artificial intelligence has begun to be understood from the perspective of the augmentation of human intelligence. We have started to be interested in Human-AI collaboration rather than AI alone without human. A study of 1500 companies in various industries found that human-AI collaboration outperformed AI alone. In the medicine area, pathologist-deep learning collaboration dropped the pathologist cancer diagnosis error rate by 85%. Leading AI companies, such as IBM and Microsoft, are starting to adopt the direction of AI as augmented intelligence. Human-AI collaboration is emphasized in the decision-making process, because artificial intelligence is superior in analysis ability based on information. Intuition is a unique human capability so that human-AI collaboration can make optimal decisions. In an environment where change is getting faster and uncertainty increases, the need for artificial intelligence in decision-making will increase. In addition, active discussions are expected on approaches that utilize artificial intelligence for rational decision-making. This study investigates the impact of artificial intelligence on decision-making focuses on human-AI collaboration and the interaction between the decision maker personal traits and advisor type. The advisors were classified into three types: human, artificial intelligence, and human-AI collaboration. We investigated perceived usefulness of advice and the utilization of advice in decision making and whether the decision-maker's personal traits are influencing factors. Three hundred and eleven adult male and female experimenters conducted a task that predicts the age of faces in photos and the results showed that the advisor type does not directly affect the utilization of advice. The decision-maker utilizes it only when they believed advice can improve prediction performance. In the case of human-AI collaboration, decision-makers higher evaluated the perceived usefulness of advice, regardless of the decision maker's personal traits and the advice was more actively utilized. If the type of advisor was artificial intelligence alone, decision-makers who scored high in conscientiousness, high in extroversion, or low in neuroticism, high evaluated the perceived usefulness of the advice so they utilized advice actively. This study has academic significance in that it focuses on human-AI collaboration that the recent growing interest in artificial intelligence roles. It has expanded the relevant research area by considering the role of artificial intelligence as an advisor of decision-making and judgment research, and in aspects of practical significance, suggested views that companies should consider in order to enhance AI capability. To improve the effectiveness of AI-based systems, companies not only must introduce high-performance systems, but also need employees who properly understand digital information presented by AI, and can add non-digital information to make decisions. Moreover, to increase utilization in AI-based systems, task-oriented competencies, such as analytical skills and information technology capabilities, are important. in addition, it is expected that greater performance will be achieved if employee's personal traits are considered.