• Korean Journal of Culture and Social Issue
• /
• v.12 no.5_spc
• /
• pp.149-167
• /
• 2006

Korean society is rapidly changing to aging society comparing the other industrialized countries, however, the studies of elderly driver's driving behavior and accidents are not enough in Korea for elderly driver's accident prevention. This study focused on the elderly driver's psychological effects on elderly driver's driving behavior and traffic accidents; carefulness and aberrant driving behavior. - Elderly driver's traffic accidents The high percentage of elderly driver's accidents occurs in intersections and when turning left. There was a significant difference of the opponent vehicle's speed when left turn, between elderly driver and young driver; the elderly driver choose the higher speed of opponent vehicle than young driver when left turning. This result means that elderly driver has some problems with deciding the vehicle's speed and gap acceptance(Sunyeol Lee, Soonchul Lee, and Inseok Kim, 2006)(Table 1). - Carefulness and driving confidence In order to understand elderly driver's carefulness, this study compared the elderly driver's driving confidence. Driving confidence was consisted of 4 factors; environment of traffic condition, safe driving, driving ability and attention. Elderly driver's confidence was lower than young driver's. Elderly driver in high driving confidence group, showed longer driving history and they were tend to commit violations more frequently than elerly driver in low driving confidence group. Young driver, whose driving confidence level was high answered more driving history, annual mileage, the frequency of committing traffic violation and the experience of accident within lats 5 years(Soonchul Lee, Juseok Oh, Sunjin Park, Soonyeol Lee and Inseok Kim, 2006)(Table 2). This study examined the total time required until deciding to turn left in the no traffic signal intersection between elderly driver and young driver. The result showed that the time of elderly driver was significant longer than young driver(Sunyeol Lee et al, 2006)(Table 3). - Elderly driver's aberrant behavior Driver behavior Questionnaire(DBQ) was measured to understand the aberrant behavior; violation, error and lapse. The tend of aberrant behavior was observed by aging(Sunjin Park, Soonchul Lee, Jonghoi, Kim and Inseok Kim, 2006). Elderly driver's DBQ score was lower than young driver's(Table 4). Elderly and young driver showing longer driving history were in low DBQ score group. Elderly driver had high error score and young driver had high violation score. Young driver's aberrant driving behaviour was associated with annual mileage and the frequency of committing traffic violation. Elderly driver's aberrant driving behaviour was associated with annual mileage and experience of accident. Especially elderly driver whose violation, error and lapse score was high answered more committing experience of accident within last 5 years.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.49-71
• /
• 2021

Users who intend to utilize knowledge to actively solve given problems proceed their jobs with cross- and sequential exploration of associated knowledge related each other in terms of certain criteria, such as content relevance. A knowledge map is the diagram or taxonomy overviewing status of currently managed knowledge in a knowledge-base, and supports users' knowledge exploration based on certain relationships between knowledge. A knowledge map, therefore, must be expressed in a networked form by linking related knowledge based on certain types of relationships, and should be implemented by deploying proper technologies or tools specialized in defining and inferring them. To meet this end, this study suggests a methodology for developing the knowledge graph-based knowledge map using the Graph DB known to exhibit proper functionality in expressing and inferring relationships between entities and their relationships stored in a knowledge-base. Procedures of the proposed methodology are modeling graph data, creating nodes, properties, relationships, and composing knowledge networks by combining identified links between knowledge. Among various Graph DBs, the Neo4j is used in this study for its high credibility and applicability through wide and various application cases. To examine the validity of the proposed methodology, a knowledge graph-based knowledge map is implemented deploying the Graph DB, and a performance comparison test is performed, by applying previous research's data to check whether this study's knowledge map can yield the same level of performance as the previous one did. Previous research's case is concerned with building a process-based knowledge map using the ontology technology, which identifies links between related knowledge based on the sequences of tasks producing or being activated by knowledge. In other words, since a task not only is activated by knowledge as an input but also produces knowledge as an output, input and output knowledge are linked as a flow by the task. Also since a business process is composed of affiliated tasks to fulfill the purpose of the process, the knowledge networks within a business process can be concluded by the sequences of the tasks composing the process. Therefore, using the Neo4j, considered process, task, and knowledge as well as the relationships among them are defined as nodes and relationships so that knowledge links can be identified based on the sequences of tasks. The resultant knowledge network by aggregating identified knowledge links is the knowledge map equipping functionality as a knowledge graph, and therefore its performance needs to be tested whether it meets the level of previous research's validation results. The performance test examines two aspects, the correctness of knowledge links and the possibility of inferring new types of knowledge: the former is examined using 7 questions, and the latter is checked by extracting two new-typed knowledge. As a result, the knowledge map constructed through the proposed methodology has showed the same level of performance as the previous one, and processed knowledge definition as well as knowledge relationship inference in a more efficient manner. Furthermore, comparing to the previous research's ontology-based approach, this study's Graph DB-based approach has also showed more beneficial functionality in intensively managing only the knowledge of interest, dynamically defining knowledge and relationships by reflecting various meanings from situations to purposes, agilely inferring knowledge and relationships through Cypher-based query, and easily creating a new relationship by aggregating existing ones, etc. This study's artifacts can be applied to implement the user-friendly function of knowledge exploration reflecting user's cognitive process toward associated knowledge, and can further underpin the development of an intelligent knowledge-base expanding autonomously through the discovery of new knowledge and their relationships by inference. This study, moreover than these, has an instant effect on implementing the networked knowledge map essential to satisfying contemporary users eagerly excavating the way to find proper knowledge to use.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.2
• /
• pp.82-100
• /
• 2022

With the crisis of the COVID-19 pandemic and the era of the 4th industrial revolution, archaeological heritage education has entered a new phase. This article responds to the trends in the post-COVID-19 era, seeking ways to develop archaeological heritage education and sustainable strategies necessary in the era of the 4th industrial revolution. The program of archaeological heritage education required in the era of the 4th industrial revolution must cultivate creative talent, solve problems, and improve self-efficacy. It should also draw attention to archaeological heritage maker education. Such maker education should be delivered based on constructivism and be designed by setting specific learning goals in consideration of various age-specific characteristics. Moreover, various ICT-based contents applying VR, AR, cloud, and drone imaging technologies should be developed and expanded, and, above all, ontact digital education(real-time virtual learning) should seek ways to revitalize communities capable of interactive communication in non-face-to-face situations. The development of such ancient heritage content needs to add AI functions that consider learners' interests, learning abilities, and learning purposes while producing various convergent contents from the standpoint of "cultural collage." Online archaeological heritage content education should be delivered following prior learning or with supplementary learning in consideration of motivation or field learning to access the real thing in the future. Ultimately, archaeological ontact education will be delivered using cutting-edge technologies that reflect the current trends. In conjunction with this, continuous efforts are needed for constructive learning that enables discovery and question-exploration.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.41-59
• /
• 2022

The timely procurement of military supplies is essential to maintain the military's operational capabilities, and contract work is the first step toward timely procurement. In addition, rapid signing of a contract enables consumers to set a leisurely delivery date and increases the possibility of budget execution, so it is essential to improve the contract process to prevent early execution of the budget and transfer or disuse. Recently, research using big data has been actively conducted in various fields, and process analysis using big data and process mining, an improvement technique, are also widely used in the private sector. However, the analysis of contract work in the military is limited to the level of individual analysis such as identifying the cause of each problem case of budget transfer and disuse contracts using the experience and fragmentary information of the person in charge. In order to improve the contract process, this study analyzed using the process mining technique with data on a total of 560 contract tasks directly contracted by the Department of Finance of the Air Force Logistics Command for about one year from November 2019. Process maps were derived by synthesizing distributed data, and process flow, execution time analysis, bottleneck analysis, and additional detailed analysis were conducted. As a result of the analysis, it was found that review/modification occurred repeatedly after request in a number of contracts. Repeated reviews/modifications have a significant impact on the delay in the number of days to complete the cost calculation, which has also been clearly revealed through bottleneck visualization. Review/modification occurs in more than 60% of the top 5 departments with many contract requests, and it usually occurs in the first half of the year when requests are concentrated, which means that a thorough review is required before requesting contracts from the required departments. In addition, the contract work of the Department of Finance was carried out in accordance with the procedures according to laws and regulations, but it was found that it was necessary to adjust the order of some tasks. This study is the first case of using process mining for the analysis of contract work in the military. Based on this, if further research is conducted to apply process mining to various tasks in the military, it is expected that the efficiency of various tasks can be derived.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.13 no.1
• /
• pp.139-152
• /
• 2002

Objectives：This study was conducted to compare the clinical and neuropsychological characteristics by DSM-IV subtypes of attention deficit hyperactivity disorder(ADHD) patients who did not have comorbid psychiatric disorders. Methods：5-15 year old children with ADHD were recruited at psychiatric outpatient clinic of Yeungnam University hospital and the patients with comorbidity or neurological abnormalities were excluded. Finally, total 404 children with ADHD were selected for this study. There were 234 subjects of ADHD-C(57.9%), 156 subjects of ADHD-I(38.6%) and 14 subjects of ADHD-HI(3.5%), who fulfilled the DSM-IV diagnostic criteria. The mean age of the total subjects was 9.63±2.49 years old. The psychopathology, IQ, behavioral problems, neuropsychological executive function were evaluated before pharmacological treatment. The measures were Korean Personality Inventory of Child(K-PIC) for psychopathology, 4 behavioral check lists(ADDES-HV, ACTeRS, CAP, SNAP) for behavioral symptoms of ADHD, K-ABC and KEDI-WISC for IQ and Conner's CPT, WCST, SST for neuropsychological executive functions. Results：1) The prevalence of subtypes was ADHD-C, ADHD-I, ADHD-HI in decreasing order. There was no sex difference of prevalence among three subtypes. The mean age of ADHD-I was older than other subtypes. 2) There was significant differences of psychopathology among subtypes, the ADHD-C and ADHD-HI had higher than the ADHD-I in the scores of delinquent, hyperactivity and psychosis；the ADHD-C had higher than the ADHD-I in the scores of family relation and autism, the scores of ego resilience were lower than the ADHD-I. However, there was no difference in anxiety, depression and somatization scores among them. 3) The results of behavioral symptom check lists, the ADHD-C had higher the score of inattention, hyperactivity and impulsivity than the ADHD-I. Meanwhile the results of ACTeRs, which rated by the teachers, were different. 4) There were significant differences of sequential processing scale and arithmetics among subtypes in IQ using K-ABC, but there was no significant difference between the ADHD-C and the ADHD-I after excluding the ADHD-HI due to small numbers. 5) There was numerical difference among subtypes but did not reach statistical significance in three neuropsychological executive function tests. Conclusion：In conclusion, our results revealed that there was significant difference in clinical features among three subtypes but, no significant difference in executive functions.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.