• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.287-310
• /
• 2022

Companies' interest in developing AI-based intelligent new products is increasing. Recently, the main concern of companies is to innovate customer experience and create new values by developing new products through the effective use of Artificial intelligence technology. However, due to the nature of products based on radical technologies such as artificial intelligence, intelligent products differ from existing products and development methods, so it is clear that there is a limitation to applying the existing development methodology as it is. This study proposes a new research method based on KANO-TOPSIS for the successful development of AI-based intelligent new products by using car voice assistants as an example. Using the KANO model, select and evaluate functions that customers think are necessary for new products, and use the TOPSIS method to derives priorities by finding the importance of functions that customers need. For the analysis, major categories such as vehicle condition check and function control elements, driving-related elements, characteristics of voice assistant itself, infotainment elements, and daily life support elements were selected and customer demand attributes were subdivided. As a result of the analysis, high recognition accuracy should be considered as a top priority in the development of car voice assistants. Infotainment elements that provide customized content based on driver's biometric information and usage habits showed lower priorities than expected, while functions related to driver safety such as vehicle condition notification, driving assistance, and security, also showed as the functions that should be developed preferentially. This study is meaningful in that it presented a new product development methodology suitable for the characteristics of AI-based intelligent new products with innovative characteristics through an excellent model combining KANO and TOPSIS.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Korea Science and Art Forum
• /
• v.30
• /
• pp.151-161
• /
• 2017

In the fields of science and engineering, multidisciplinary research is common, and researchers with a diverse range of expertise collaborate to achieve common goals. As the 4th industrial revolution gains currency in society, there is growing demand on talented personnel both with technical knowledge and skills and with communicative skills. That is, future engineers are expected to possess competence in social and artistic skills in addition to specialized knowledge and skills in engineering. In this paper we introduce an emerging field of 3D bioprinting as an exemplary case of interdisciplinary research. We have chosen the case to demonstrate the possibility of cultivating engineers with π-shaped expertise. Building on the concept of T-shaped talent, we define π-shaped expertise as having both technical skills in more than one specialized field and interpersonal/communicative skills. Wtih references to such concepts as trading zones and interactional expertise, we suggest that π-shaped expertise can be cultivated via the creation of multi-level trading zones. Trading zones are referred to as the physical, conceptual, or metaphorical spaces in which experts with different world views trade ideas, objects, and the like. Interactional expertise is cultivated, as interactions between researches are under way, with growing understanding of each other's expertise. Under the support of the university and the government, two researchers with expertise in printing technology and life sciences cooperate to develop a 3D bioprinting system. And the primary investigator of the research laboratory under study has aimed to create multiple dimensions of trading zones where researchers with different educational and cultural backgrounds can exchange ideas and interact with each other. As 3D bioprinting has taken shape, we have found that a new form of expertise, namely π-shaped expertise is formed.

• Health Policy and Management
• /
• v.33 no.2
• /
• pp.185-193
• /
• 2023

Background: This study focuses on the establishment and operation of a stroke patient hotline program to help patients and their caregivers determine when acute neurological changes require emergency attention. Method: The stroke hotline was established at the Gyeonggi Regional Cerebrovascular Center, Seoul National University Bundang Hospital, in June 2016. Patients diagnosed with stroke during admission or in outpatient clinics were registered and provided with stroke education. Consulting nurses managed hotline calls and made decisions about outpatient schedules or emergency room referrals, consulting physicians when necessary. The study analyzed consultation records from June 2016 to December 2020, assessing consultation volumes and types. Outcomes and hotline satisfaction were also evaluated. Results: Over this period, 6,851 patients were registered, with 1,173 patients (18%) undergoing 3,356 hotline consultations. The average monthly consultation volume increased from 29.2 cases in 2016 to 92.3 cases in 2020. Common consultation types included stroke symptoms (22.3%), blood pressure/glucose inquiries (12.8%), and surgery/procedure questions (12.6%). Unexpected outpatient visits decreased from 103 cases before the hotline to 81 cases after. Among the 2,244 consultations between January 2019 and December 2020, 9.6% were recommended hospital visits, with two cases requiring intra-arterial thrombectomy. Patient satisfaction ratings of 9-10 points increased from 64% in 2019 to 69% in 2020. Conclusion: The stroke hotline program effectively reduced unexpected outpatient visits and achieved high patient satisfaction. Expanding the program could enhance the management of stroke-related neurological symptoms and minimize unnecessary healthcare resource utilization.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.57-84
• /
• 2023

With the development of information and communications technology (ICT) and big data technology, anyone can easily obtain and utilize vast amounts of data through the Internet. Therefore, the capability of selecting high-quality data from a large amount of information is becoming more important than the capability of just collecting them. This trend continues in academia; literature reviews, such as systematic and non-systematic reviews, have been conducted in various research fields to construct a healthy knowledge structure by selecting high-quality research from accumulated research materials. Meanwhile, after the COVID-19 pandemic, remote healthcare services, which have not been agreed upon, are allowed to a limited extent, and new healthcare services such as health recommender systems (HRS) equipped with artificial intelligence (AI) and big data technologies are in the spotlight. Although, in practice, HRS are considered one of the most important technologies to lead the future healthcare industry, literature review on HRS is relatively rare compared to other fields. In addition, although HRS are fields of convergence with a strong interdisciplinary nature, prior literature review studies have mainly applied either systematic or non-systematic review methods; hence, there are limitations in analyzing interactions or dynamic relationships with other research fields. Therefore, in this study, the overall network structure of HRS and surrounding research fields were identified using citation network analysis (CNA). Additionally, in this process, in order to address the problem that the latest papers are underestimated in their citation relationships, the GraphSAGE algorithm was applied. As a result, this study identified 'recommender system', 'wireless & IoT', 'computer vision', and 'text mining' as increasingly important research fields related to HRS research, and confirmed that 'personalization' and 'privacy' are emerging issues in HRS research. The study findings would provide both academic and practical insights into identifying the structure of the HRS research community, examining related research trends, and designing future HRS research directions.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.101-114
• /
• 2023

In the wartime, aircraft carrying out a mission to strike the enemy deep in the depth are exposed to the risk of being shoot down. As a key combat force in mordern warfare, it takes a lot of time, effot and national budget to train military flight personnel who operate high-tech weapon systems. Therefore, this study studied the path problem of predicting the route of emergency escape from enemy territory to the target point to avoid obstacles, and through this, the possibility of safe recovery of emergency escape military flight personnel was increased. based problem, transforming the problem into a TSP, VRP, and Dijkstra algorithm, and approaching it with an optimization technique. However, if this problem is approached in a network problem, it is difficult to reflect the dynamic factors and uncertainties of the battlefield environment that military flight personnel in distress will face. So, MDP suitable for modeling dynamic environments was applied and studied. In addition, GIS was used to obtain topographic information data, and in the process of designing the reward structure of MDP, topographic information was reflected in more detail so that the model could be more realistic than previous studies. In this study, value iteration algorithms and deterministic methods were used to derive a path that allows the military flight personnel in distress to move to the shortest distance while making the most of the topographical advantages. In addition, it was intended to add the reality of the model by adding actual topographic information and obstacles that the military flight personnel in distress can meet in the process of escape and escape. Through this, it was possible to predict through which route the military flight personnel would escape and escape in the actual situation. The model presented in this study can be applied to various operational situations through redesign of the reward structure. In actual situations, decision support based on scientific techniques that reflect various factors in predicting the escape route of the military flight personnel in distress and conducting combat search and rescue operations will be possible.

• Knowledge Management Research
• /
• v.24 no.2
• /
• pp.241-262
• /
• 2023

The phenomena and game records that occur in sports matches are being analyzed in the field of sports game analysis, utilizing advanced technologies and various scientific analysis methods. Among these methods, social network analysis is actively employed in analyzing pass networks. As football is a representative sport in which the game unfolds through player interactions, efforts are being made to provide new insights into the game using social network analysis, which were previously unattainable. Consequently, this study aims to analyze the changes in pass networks over time for a specific football team and compare them in different scenarios, including variations in the game's nature (Qatar World Cup games vs. A match games) and alterations in the opposing team (higher FIFA rankers vs. lower FIFA rankers). To elaborate, we selected ten matches from the games of the Korean national football team following Coach Bento's appointment, extracted network indicators for these matches, and applied four indicators (efficiency, cohesion, vulnerability, and activity/leadership) from a football team's performance evaluation model to the extracted data for analysis under different circumstances. The research findings revealed a significant increase in cohesion and a substantial decrease in vulnerability during the analysis of game performance over time. In the comparative analysis based on changes in the game's nature, Qatar World Cup matches exhibited superior performance across all aspects of the evaluation model compared to A matches. Lastly, in the comparative analysis considering the variations in the opposing team, matches against lower FIFA rankers displayed superior performance in all aspects of the evaluation model in comparison to matches against top FIFA rankers. We hope that the outcomes of this study can serve as essential foundational data for the selection of football team coaches and the development of game strategies, thereby contributing to the enhancement of the team's performance.

• Korean Journal of Environment and Ecology
• /
• v.37 no.2
• /
• pp.100-139
• /
• 2023

This study was intended to identify the distribution and characteristics of plants such as native plants, rare plants, and endemic plants through a flora survey in Sangwangsan Mt. (644m), Wando-gun, Jeollanam-do, a group habitat of warm temperate forests in Korea, and use the data for the conservation of plant species diversity and the study of climate and distribution changes in warm-temperate forests. A total of 32 field surveys were conducted from 2018 to 2022. The survey identified 785 taxa, including 8 forms, 53 varieties, 16 subspecies, 708 species, 473 genera, and 132 families. The endangered wild plants designated by the Ministry of Environment included 6 taxa: Woodwardia japonica, Metanarthecium luteoviride, Bulbophyllum inconspicuum, Dendrobium moniliforme, Pelatantheria scolopendrifolia, and Cymbidium macrorhizon. Rare plants designated by the Korea Forest Service were identified as 26 taxa. The red list designated by the Korea National Arboretum was identified as 7 taxa, the red list designated by the Ministry of Environment was identified as 29 taxa, and endemic plants in Korea were identified as 17 taxa. Floristic target species in Korea were identified as 200 taxa, specifically 6 taxa of grade V, 13 taxa of grade IV, 73 taxa of grade III, 29 taxa of grade II, and 79 taxa of grade I. Naturalized plants were identified as 73 taxa, and invasive alien plants were identified as 6 taxa. Target plants adaptable to climate change in Korea were identified as 55 taxa, specifically 8 taxa of endemic plants, 46 taxa of southern plants, and 1 taxon of northern plants.

• Journal of Food Hygiene and Safety
• /
• v.38 no.3
• /
• pp.123-130
• /
• 2023

Salmonella spp. are prevalent foodborne pathogens that are infective at relatively low concentrations, thus posing a serious health threat, especially to young children and the elderly. In several countries, the management and regulation of Salmonella spp. in food, including seafood, adhere to a negative detection standard. The risk of infection is particularly high when seafood is consumed raw, which underscores the importance of timely detection of pathogenic microorganisms, such as Salmonella. Accordingly, this study aimed to develop a combined pre-treatment and detection method that includes pre-culture and DNA extraction in order to detect five species of Salmonella at concentrations below 10 CFU/mL in seafood. The effectiveness of the proposed method was assessed in terms of the composition of the enrichment (pre-culture) medium, minimum incubation time, and minimum cell concentration for pathogen detection. Furthermore, a practical DNA extraction method capable of effectively handling high salt conditions was tested and found to be successful. Through polymerase chain reaction, Salmonella spp. Were detected and positively identified in shellfish samples at cell concentrations below 10 CFU/g. Thus, the proposed method, combining sample pre-treatment and cell culture with DNA extraction, was shown to be an effective strategy for detecting low cellular concentrations of harmful bacteria. The proposed methodology is suitable as an economical and practical in situ pre-treatment for effective detection of Salmonella spp. in seafood.

• Journal of the Korean Society of International Agriculture
• /
• v.23 no.5
• /
• pp.475-484
• /
• 2011

International price of cereal has been dramatically increasing for the past few years. This price hike amplified the importance of food self-sufficiency in numerous countries due to the fact that food security is directly proportional to food self-sufficiency. In this study, we conducted a survey to provide useful information of Cambodia's agricultural environment to possible Korean agricultural investors and as to highlight Cambodia as a strong candidate for the establishment of Korea's foreign base for cereal production. The survey conducted includes information regarding Cambodia's agricultural environment and investment circumstances including the political, economical and other contributing factors affecting agricultural investment in Cambodia. Seventy percent of the Cambodia's total population engage in agriculture and this comprises about 30% of the country's GDP. This statistics reflects the possibility of Cambodia's poverty alleviation which proves that agriculture in Cambodia is the driving force for the improvement of the country's economy. In addition, low labor cost, fertile land, abundant water resources, like the Tonle sap lake and the Mekong river, and unreclaimed lands are the strong points that could attract agricultural investors to Cambodia. Poor infrastructure, irrigation systems, law reforms, including social and cultural differences may be the biggest setbacks for the acceleration of Cambodia's agriculture development. However, the Cambodian government is open and willing to make adjustments for Cambodia to be both foreign and domestic agricultural investor-friendly, expecting that it will boost its country's agricultural development. Making the best out of this opportunity, the coordination of KOICA with Korean agricultural investors in building infrastructures and with the help of the KOPIA program for the transfer of agricultural technology will benefit both countries and will play an important role in Cambodia's agriculture.