• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.53-73
• /
• 2023

Although it is mandatory to wear a seat belt that can minimize human injury when traffic accident occurs, the number of traffic accident casualties not wearing seat belts still accounts for a significant proportion.The seat belt wearing detection system for all seats is a system that identifies whether all seat passengers wear a seat belt and encourages their usage, also it can be a useful technical countermeasure. Firstly, this study established the viability of system implementation by assessing the factors influencing the severity of injuries in traffic accidents through the development of an ordered probit model. Analysis results showed that the use of seat belts has statistically significant effects on the severity of traffic accidents, reducing the probability of death or serious injury by 0.054 times in the event of a traffic accident. Secondly, a meta-analysis was conducted based on prior research related to seat belts and injuries in traffic accidents to estimate the expected reduction in accident severity upon the implementation of the system.The analysis of the effect of accident severity reduction revealed that wearing seat belts would lead to a 63.3% decrease in fatal accidents, with the front seats showing a reduction of 75.7% and the rear seats showing a reduction of 58.1% in fatal accidents. Lastly, Using the results of the meta-analysis and traffic accident statistics, the expected decrease in the number of traffic accident casualties with the implementation of the system was derived to analyze the traffic safety effects of the proposed detection system. The analysis demonstrated that with an increase in the adoption rate of the system, the number of casualties in accidents where seat belts were not worn decreased. Specifically, at a system adoption rate of 60%, it is anticipated that the number of fatalities would decrease by more than three times compared to the current scenario. Based on the analysis results, operational strategies for the system were proposed to increase seat belt usage rates and reduce accident severity.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.123-138
• /
• 2024

This study described the utilization of ChatGPT in teaching and students' learning processes for the course "Introductory Mathematics for Artificial Intelligence (Math4AI)" at 'S' University. We developed a customized ChatGPT and presented a learning model in which students supplement their knowledge of the topic at hand by utilizing this model. More specifically, first, students learn the concepts and questions of the course textbook by themselves. Then, for any question they are unsure of, students may submit any questions (keywords or open problem numbers from the textbook) to our own ChatGPT at https://math4ai.solgitmath.com/ to get help. Notably, we optimized ChatGPT and minimized inaccurate information by fully utilizing various types of data related to the subject, such as textbooks, labs, discussion records, and codes at http://matrix.skku.ac.kr/Math4AI-ChatGPT/. In this model, when students have questions while studying the textbook by themselves, they can ask mathematical concepts, keywords, theorems, examples, and problems in natural language through the ChatGPT interface. Our customized ChatGPT then provides the relevant terms, concepts, and sample answers based on previous students' discussions and/or samples of Python or R code that have been used in the discussion. Furthermore, by providing students with real-time, optimized advice based on their level, we can provide personalized education not only for the Math4AI course, but also for any other courses in college math education. The present study, which incorporates our ChatGPT model into the teaching and learning process in the course, shows promising applicability of AI technology to other college math courses (for instance, calculus, linear algebra, discrete mathematics, engineering mathematics, and basic statistics) and in K-12 math education as well as the Lifespan Learning and Continuing Education.

• Journal of the Korean association of regional geographers
• /
• v.3 no.2
• /
• pp.163-193
• /
• 1997

Medical services are a fundamental and essential service in all urban areas. The location and accessibility of medical service facilities and institutions are critical to the diagnosis, control and prevention of illness and disease. The purpose of this paper is to present the results of a study on the location of medical facilities in Kwangju and the utilization of these facilities by the inhabitants. The following information is a summary of the findings: (1) Korea, like many countries, is now witnessing an increase in the age of its population as a result of higher living standards and better medical services. Korea is also experiencing a rapid increase in health care costs. To ensure easy access to medical consultation, diagnosis and treatment by individuals, the hierarchical efficient location of medical facilities, low medical costs, equalized medical services, preventive medical care is important. (2) In Korea, the quality of medical services has improved significantly as evident by the increased number of medical facilities and medical personnel. However, there is still a need for not only quantitative improvements but also for a more equitable distribution of and location of medical services. (3) There are 503 medical facilities in Kwangju each with a need to service 2,556 people. This is below the national average of 1,498 inhabitants per facility. The higher locational quotient and satisfactory population per medical facility showed at the civic center. On the other hand, problem regions such as the traditional residential area in Buk-Gu, Moo-deung mountain area and the outer areas of west Kwangju still maintain rural characteristics. (4) In the study area there are 86 general medicine clinics which provide basic medical services. i. e. one clinic per every 14,949 residents. As a basic service, its higher locational quotient showed in the residential area. The lower population concentration per clinic was found in the civic center and in the former town center, Songjeong-dong. In recently build residential areas and in the civic center, the lack of general medicine clinics is not a serious medical services issue because of the surplus of medical specialists in Korea. People are inclined to seek a consultation with a specialist in specific fields rather than consult a general practitioner. As a result of this phenomenon, there are 81 internal medicine facilities. Of these, 32.1% provide services to people who are not referred by a primary care physician but who self-diagnose then choose a medical facility specializing in what they believe to be their health problem. Areas in the city, called dongs, without any internal facilities make up 50% of the total 101 dongs. (5) There are 78 surgical facilities within the area, and there is little difference at the locational appearance from internal medicine facilities. There are also 71 pediatric health clinics for people under 15 years of age in this area, represents one clinic per 5,063 people. On the quantitative aspect, this is a positive situation. Accessibility is the most important facility choice factor, so it should be evenly located in proportion to demander distribution. However, 61% of 102 dongs have no pediatric clinics because of the uneven location. (6) There are 43 obstetrical and gynecological clinics in Kwangju, and the number of residents being served per clinic is 15,063. These services need to be given regularly so it should increase the numbers. There are 37 ENT clinics in the study area with the lower concentration in Dong-gu (32.4%) making no locational differences by dong. There are 23 dermatology clinics with the largest concentration in Dong-Gu. There are 17 ophthalmic clinics concentrated in the residential area because of the primary function of this type of specialization. (7) The use of general medicine clinics, internal medicine clinics, pediatric clinics, ENT clinics by the inhabitants indicate a trend toward primary or routine medical services. Obstetrics and gynecology clinics are used on a regular basis. In choosing a general medicine clinic, internal medicine clinic, pediatric clinic, and a ENT clinic, accessibility is the key factor while choice of a general hospital, surgery clinic, or an obstetrics and gynecology clinic, thes faith and trust in the medical practitioner is the priority consideration. (8) I considered the efficient use of medical facilities in the aspect of locational and management and suggest the following: First, primary care facilities should be evenly distributed in every area. In Kwangju, the number of medical facilities is the lowest among the six largest cities in Korea. Moreover, they are concentrated in Dong-gu and in newly developed areas. The desired number of medical facilities should be within 30 minutes of each person's home. For regional development there is a need to develop a plan to balance, for example, taxes and funds supporting personnel, equipment and facilities. Secondly, medical services should be co-ordinated to ensure consistent, appropriate, quality services. Primary medical facilities should take charge of out-patient activities, and every effort should be made to standardize and equalize equipment and facility resources and to ensure ongoing development and training in the primary services field. A few specialty medical facilities and general hospitals should establish a priority service for incurable and terminally ill patients. (9) The management scheme for the inhabitants' efficient use of medical service is as follows: The first task is to efficiently manage medical facilities and related services. Higher quality of medical services can be accomplished within the rapidly changing medical environment. A network of social, administrative and medical organizations within an area should be established to promote information gathering and sharing strategies to better assist the community. Statistics and trends on the rate or occurrence of diseases, births, deaths, medical and environment conditions of the poor or estranged people should be maintained and monitored. The second task is to increase resources in the area of disease prevention and health promotion. Currently the focus is on the treatment and care of individuals with illness or disease. A strong emphasis should also be placed on promoting prevention of illness and injury within the community through not only public health offices but also via medical service facilities. Home medical care should be established and medical testing centers should be located as an ordinary service level. Also, reduced medical costs for the physically handicapped, cardiac patients, and mentally ill or handicapped patients should be considered.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.1
• /
• pp.32-36
• /
• 2016

Purpose In nuclear medicine examination, $^{131}I$ is widely used in nuclear medicine examination such as diagnosis, treatment, and others of thyroid cancer and other diseases. $^{131}I$ conducts examination and treatment through emission of ${\gamma}$ ray and ${\beta}^-$ ray. Since $^{131}I$ (364 keV) contains more energy compared to $^{99m}Tc$ (140 keV) although it displays high integrated rate and enables quick discharge through kidney, the objective of this study lies in comparing the difference in exposure dose of $^{131}I$ before and after wearing apron when handling $^{131}I$ with focus on 3 elements of external exposure protection that are distance, time, and shield in order to reduce the exposure to technicians in comparison with $^{99m}Tc$ during the handling and administration process. When wearing apron (in general, Pb 0.5 mm), $^{99m}Tc$ presents shield of over 90% but shielding effect of $^{131}I$ is relatively low as it is of high energy and there may be even more exposure due to influence of scattered ray (secondary) and bremsstrahlung in case of high dose. However, there is no special report or guideline for low dose (74 MBq) high energy thus quantitative analysis on exposure dose of technicians will be conducted based on apron wearing during the handling of $^{131}I$. Materials and Methods With patients who visited Department of Nuclear Medicine of our hospital for low dose $^{131}I$ administration for thyroid cancer and diagnosis for 7 months from Jun 2014 to Dec 2014 as its subject, total 6 pieces of TLD was attached to interior and exterior of apron placed on thyroid, chest, and testicle from preparation to administration. Then, radiation exposure dose from $^{131}I$ examination to administration was measured. Total procedure time was set as within 5 min per person including 3 min of explanation, 1 min of distribution, and 1 min of administration. In regards to TLD location selection, chest at which exposure dose is generally measured and thyroid and testicle with high sensitivity were selected. For preparation, 74 MBq of $^{131}I$ shall be distributed with the use of $2m{\ell}$ syringe and then it shall be distributed after making it into dose of $2m{\ell}$ though dilution with normal saline. When distributing $^{131}I$ and administering it to the patient, $100m{\ell}$ of water shall be put into a cup, distributed $^{131}I$ shall be diluted, and then oral administration to patients shall be conducted with the distance of 1m from the patient. The process of withdrawing $2m{\ell}$ syringe and cup used for oral administration was conducted while wearing apron and TLD. Apron and TLD were stored at storage room without influence of radiation exposure and the exposure dose was measured with request to Seoul Radiology Services. Results With the result of monthly accumulated exposure dose of TLD worn inside and outside of apron placed on thyroid, chest, and testicle during low dose $^{131}I$ examination during the research period divided by number of people, statistics processing was conducted with Wilcoxon Signed Rank Test using SPSS Version. 12.0K. As a result, it was revealed that there was no significant difference since all of thyroid (p = 0.345), chest (p = 0.686), and testicle (p = 0.715) were presented to be p > 0.05. Also, when converting the change in total exposure dose during research period into percentage, it was revealed to be -23.5%, -8.3%, and 19.0% for thyroid, chest, and testicle respectively. Conclusion As a result of conducting Wilcoxon Signed Rank Test, it was revealed that there is no statistically significant difference (p > 0.05). Also, in case of calculating shielding rate with accumulate exposure dose during 7 months, it was revealed that there is irregular change in exposure dose for inside and outside of apron. Although the degree of change seems to be high when it is expressed in percentage, it cannot be considered a big change since the unit of accumulated exposure dose is in decimal points. Therefore, regardless of wearing apron during high energy low dose $^{131}I$ administration, placing certain distance and terminating the administration as soon as possible would be of great assistance in reducing the exposure dose. Although this study restricted $^{131}I$ administration time to be within 5 min per person and distance for oral administration to be 1m, there was a shortcoming to acquire accurate result as there was insufficient number of N for statistics and it could be processed only through non-parametric method. Also, exposure dose per person during lose dose $^{131}I$ administration was measured with accumulated exposure dose using TLD rather than through direct-reading exposure dose thus more accurate result could be acquired when measurement is conducted using electronic dosimeter and pocket dosimeter.

• Journal of Korean Society of Forest Science
• /
• v.20 no.1
• /
• pp.1-44
• /
• 1973

Needless to say, the management of national forest in all countries is very important in view of the national mission and management purposes. Korean national forest is also in particular significant in promoting national economy for the continuous increasing of the demand for wood, conservation of the land and social welfare. But there's no denying the fact that the leading aim of the Korean forest policy has been based upon the conservation of forest resources and recovery of land conservation function instead of improvement of the forest productive capacity. Therefore, the management of national forest should be aimed as an industry in the chain of the Korean national economy. And the increment of the forest productive capacity based on rationalized forest management is also urgently needed. Not only the increment of the timber production but also the establishment of the good forest in quality and quantity are to bring naturally many functions of conservation and other public benefits. In 1908 Korean national forest was historically established for the first time as a result of the notification for ownership, and was divided into two kinds in 1911-1924, such as indisposable national forest for land conservation, forest management, scientific research and public welfare, and the other national forest to be disposed. Indisposable forest is mostly under the jurisdiction of national forest stations (Chungbu, Tongbu, Nambu), and the tother national forests are under custody of respective cities and provinces, and under custody of the other government authorities. As of the end of 1971, national forest land is 19.5% (1,297,708 ha) of the total forest land area, but growing stock is 50.1% ($35,406,079m^3$) of the total forest growing stock, and timber production of national forest is 23.6% ($205,959m^3$) of the year production of total timber in Korea. Accordingly, it is the important fact that national forest occupies the major part of Korean forestry. The author positively affirms that success or failure of the management of national forest controls rise or fall of forestry in Korea. All functions of forest are very important, but among others the function of timber production is most important especially in Korea, that unavoidably imports a large quantity of foreign wood every year (in 1971 import of foreign wood-$3,756,000m^3$, 160,995,000 dollars). So, Korea urgently needs the improvement of forest productive capacity in national forest. But it is difficult that wood production meets the rapid increase of demand for wood to the development of economy, because production term of forestry is long, so national forest management should be rationalized by the effective investment and development of forestry techniques in the long view. Although Korean national forest business has many difficulties in the budget, techniques and the lack of labour due to outflow of rural village labour by development of national economy, and the increase of labour wages and administrative expenses etc. the development of national forest depends on adoption of the suitable forest techniques and management adapted for social and economical development. In this view point the writer has investigated and analyzed the status of the management of national forest in Korea to examine the irrational problems and suggest an improvement plan. The national forestry statistics cited in this study is based on the basic statistics and the statistics of the forest business as of the end of 1971 published by Office of Forestry, Republic of Korea, and the other depended on the data presented by the national forest stations. The writer wants to propose as follows (seemed to be helpful in improvement of Korean national forest management). 1) In the organization of national forest management, more national forest stations should be established to manage intensively, and the staff of working plan officials should be strengthened because of the importance of working plan. 2) By increasing the staff of protection officials, forest area assigned for each protection official should be decreased to 1,000-2,000 ha. 3) The frequent personnel changes of supervisor of national forest station(the responsible person on-the-spot) obstructs to accomplish the consistent management plan. 4) In the working plan drafting for national forest, basic investigations should be carefully practiced with sufficient expenditure and staff not to draft unreal working plan. 5) The area of working-unit should be decreased to less than 2,000 ha on the average for intensive management and the principle of a working-unit in a forest station should be realized as soon as possible. 6) Reforestation on open land should be completed in a short time with a debt of the special fund(a long term loan), and the land on which growing hardwood stands should be changed with conifers to increase productivity per unit area, and at the same time techical utilization method of hardwood should be developed. 7) Expenses of reforestation should be saved by mechanization and use of chemicals for reforestation and tree nursery operation providing against the lack of labour in future. 8) In forest protection, forest fire damage is enormous in comparison with foreign countries, accordingly prevention system and equipment should be improved, and also the minimum necessary budget should be counted up for establishment and manintenance of fire-lines. 9) Manufacture production should be enlarged to systematize protection, processing and circulation of forest business, and, by doing this, mich benefit is naturally given for rural people. 10) Establishment and arrangement of forest road networks and erosion control work are indispensable for the future development of national forest itself and local development. Therefore, these works should be promoted by the responsibility of general accounting instead of special accounting. 11) Mechanization of forest works should be realized for exploiting hinterlands to meet the demand for timber increased and for solving lack of labour, consequently it should promote import of forest machines, home production, training for operaters and careful adminitration. 12) Situation of labour in future will grow worse. Therefore, the countermeasure to maintain forest labourers and pay attention to public welfare facilities and works should be considered. 13) Although the condition of income and expenditure grows worse because of economical change, the regular expenditure should be fixed. So part of the surplus fund, as of the end of 1971, should be established for the fund, and used for enlarging reforestation and forest road networks(preceding investment in national forest).

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

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

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.29-44
• /
• 2017

In Internet commerce, consumers are heavily influenced by product reviews written by other users who have already purchased the product. However, as the product reviews accumulate, it takes a lot of time and effort for consumers to individually check the massive number of product reviews. Moreover, product reviews that are written carelessly actually inconvenience consumers. Thus many online vendors provide mechanisms to identify reviews that customers perceive as most helpful (Cao et al. 2011; Mudambi and Schuff 2010). For example, some online retailers, such as Amazon.com and TripAdvisor, allow users to rate the helpfulness of each review, and use this feedback information to rank and re-order them. However, many reviews have only a few feedbacks or no feedback at all, thus making it hard to identify their helpfulness. Also, it takes time to accumulate feedbacks, thus the newly authored reviews do not have enough ones. For example, only 20% of the reviews in Amazon Review Dataset (Mcauley and Leskovec, 2013) have more than 5 reviews (Yan et al, 2014). The purpose of this study is to analyze the factors affecting the usefulness of online product reviews and to derive a forecasting model that selectively provides product reviews that can be helpful to consumers. In order to do this, we extracted the various linguistic, psychological, and perceptual elements included in product reviews by using text-mining techniques and identifying the determinants among these elements that affect the usability of product reviews. In particular, considering that the characteristics of the product reviews and determinants of usability for apparel products (which are experiential products) and electronic products (which are search goods) can differ, the characteristics of the product reviews were compared within each product group and the determinants were established for each. This study used 7,498 apparel product reviews and 106,962 electronic product reviews from Amazon.com. In order to understand a review text, we first extract linguistic and psychological characteristics from review texts such as a word count, the level of emotional tone and analytical thinking embedded in review text using widely adopted text analysis software LIWC (Linguistic Inquiry and Word Count). After then, we explore the descriptive statistics of review text for each category and statistically compare their differences using t-test. Lastly, we regression analysis using the data mining software RapidMiner to find out determinant factors. As a result of comparing and analyzing product review characteristics of electronic products and apparel products, it was found that reviewers used more words as well as longer sentences when writing product reviews for electronic products. As for the content characteristics of the product reviews, it was found that these reviews included many analytic words, carried more clout, and related to the cognitive processes (CogProc) more so than the apparel product reviews, in addition to including many words expressing negative emotions (NegEmo). On the other hand, the apparel product reviews included more personal, authentic, positive emotions (PosEmo) and perceptual processes (Percept) compared to the electronic product reviews. Next, we analyzed the determinants toward the usefulness of the product reviews between the two product groups. As a result, it was found that product reviews with high product ratings from reviewers in both product groups that were perceived as being useful contained a larger number of total words, many expressions involving perceptual processes, and fewer negative emotions. In addition, apparel product reviews with a large number of comparative expressions, a low expertise index, and concise content with fewer words in each sentence were perceived to be useful. In the case of electronic product reviews, those that were analytical with a high expertise index, along with containing many authentic expressions, cognitive processes, and positive emotions (PosEmo) were perceived to be useful. These findings are expected to help consumers effectively identify useful product reviews in the future.

• Journal of Korean Society of Transportation
• /
• v.20 no.7
• /
• pp.155-166
• /
• 2002

Since 1990s. there has been an increasing number of traffic accidents at intersection. which requires more urgent measures to insure safety on intersection. This study set out to analyze the road conditions, traffic conditions and traffic operation conditions on signalized intersection. to identify the elements that would impose obstructions in safety, and to develop a traffic accident prediction model to evaluate the safety of an intersection using the cop relation between the elements and an accident. In addition, the focus was made on suggesting appropriate traffic safety policies by dealing with the danger elements in advance and on enhancing the safety on the intersection in developing a traffic accident prediction model fir a signalized intersection. The data for the study was collected at an intersection located in Wonju city from January to December 2001. It consisted of the number of accidents, the road conditions, the traffic conditions, and the traffic operation conditions at the intersection. The collected data was first statistically analyzed and then the results identified the elements that had close correlations with accidents. They included the area pattern, the use of land, the bus stopping activities, the parking and stopping activities on the road, the total volume, the turning volume, the number of lanes, the width of the road, the intersection area, the cycle, the sight distance, and the turning radius. These elements were used in the second correlation analysis. The significant level was 95% or higher in all of them. There were few correlations between independent variables. The variables that affected the accident rate were the number of lanes, the turning radius, the sight distance and the cycle, which were used to develop a traffic accident prediction model formula considering their distribution. The model formula was compared with a general linear regression model in accuracy. In addition, the statistics of domestic accidents were investigated to analyze the distribution of the accidents and to classify intersections according to the risk level. Finally, the results were applied to the Spearman-rank correlation coefficient to see if the model was appropriate. As a result, the coefficient of determination was highly significant with the value of 0.985 and the ranks among the intersections according to the risk level were appropriate too. The actual number of accidents and the predicted ones were compared in terms of the risk level and they were about the same in the risk level for 80% of the intersections.

• Journal of Preventive Medicine and Public Health
• /
• v.22 no.4 s.28
• /
• pp.506-517
• /
• 1989

Two hundred and fifty teachers of special school (for the disabled) and 414 elementary school teachers were selected for the targets in order to compare their degrees of fatigue symptoms and to find what kind of ralationship is between subjective symptoms of fatigue and pH is the saliva. It was 30 minutes before their closing hours on April 21th, 1989 that their physical, mental and neuro-sensory symptoms and salivary pH were examined. The test results are summarized as fallows : It is observed that an interrelation between subjective fatigue and pH in their saliva shows a significant relationship between physical and neuro-sensory symptoms in a sense of statistics. The rate of subjective fatigue complained by the special teachers is higher than that by the elementary teachers. In the case of salivary pH, the special teachers' is as a whole lower than the elementary teachers'. The complain rates in each item, checked, of special teachers are generally higher than those of the elementary teachers. It is in the mental symptom related item that there are many sub-items which show significant difference. According to the average of salivary pH based on the degrees of complained symptoms shown in the pH related items, the salivary pH of the group with complained symptoms is lower than that of the group without complained symptoms. In the rate of complaints, by sex, both sexes of the special teachers show high ones, but salivary pH is low. The complain rate of mental symptoms shown by female group from the special teacher Is significantly higher(p<0.05). By age, the group in their thirties from the special teachers show the higher complain rate of mental symptoms (29.3%) and the lower salivary pH (p<0.05) than that (15.1%) of the elementary teachers belonging to the same age catagory. However, the special teachers in their forties show the lower complain rate of physical symptoms that of the elementary teachers (p<0.05). From the viewpoint of their working years, the special teachers below 14 years and elementary teachers above 15 years in their career show high complain rates. Among those who belong to the catagory of 10-14 working years, the special teachers show the higher complain rate of mental symptoms than that of their counterparts. In the case of the salivary pH, the special teachers of all working-year catagories show the higher pH than that of the elementary teachers. But there is not significantly difference. From the viewpoint of sleeping hours in the previous night of the questionaire surveyed, among those who slept for over 7 hours, the special teachers show the higher complain rate of mental symptoms with a significant difference, but the lower salivary pH than that of their counterparts. From the viewpoint of their marital status, existence of disease history, the special teachers show the higher complain rate of subjective fatigue, but the lower salivary pH than that of the elementary teachers respectively. According to the above results, the special teachers generally show the higher complain rate of subjective fatigue, the lower salivary pH, and the higher complain rate of mental symptoms. To prevent the possible accumulation of mental fatigue of the special teachers, ways and means to make use of leisure time, recreational facilities are necessarily provided. Since the degree of fatigue and salivary pH have a correlation to some extent, it is necessary that further continuous studies on the correlation between the degrees of fatigue and salivary pH should be pursued.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.