• Title/Summary/Keyword: 대표값

Search Result 1,855, Processing Time 0.025 seconds

Major Class Recommendation System based on Deep learning using Network Analysis (네트워크 분석을 활용한 딥러닝 기반 전공과목 추천 시스템)

  • Lee, Jae Kyu;Park, Heesung;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.27 no.3
    • /
    • pp.95-112
    • /
    • 2021
  • In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

The Development of the Korean Evaluation Scale for Hearing Handicap (KESHH) for the Geriatric Hearing Los (노인성난청을 위한 청각장애평가지수(KESHH)의 개발)

  • Ku, Ho-Lim;Kim, Jin-Sook
    • 한국노년학
    • /
    • v.30 no.3
    • /
    • pp.973-992
    • /
    • 2010
  • The hearing impairment is the representative disorder that affects the quality of the routine life of the aged period. This study was aimed to develop the Korean evaluation scale for hearing handicap(KESHH) with which we can evaluate social and psychological effects of the hearing impairment. Applying this scale clinically, we can analyze the geriatric hearing loss specifically and improve the quality of the aural rehabilitation that can help the hardness of the hearing impairment. Data were collected from 288 participants(176 hearing aid users and 112 non-hearing aid users) and the average age of the participants was 67.4 years old ( 60.15 for the hearing aids users and 78.9 for the non hearing users). The composition ratio of the male and female participants were 58.0% and 42.0% and extrovert and introvert personality were 49.3% and 50.7% showing balanced formation. The tentative draft of KESHH measurements were produced with 30 items and following 5 subscales. Using factor analysis, 6 items were erased and 4 subscales - social effect, psycho/emotional effect, interpersonal effect, and perception of hearing aids - were identified. As each subscale consisted of 6 items, 24 items were corrected and remained totally. Conclusively, the KESHH was developed with 24 items and 4 subscales including 6 items on each subscale. In addition, the KESHH was divided into type-1 and 2 depending on hearing aid users and non hearing aid users. The results of this study can be summarized as the following 5 parts. Firstly, the reliabilities of the KESHH were proved to be high because the subscales' Cronbach alpha values were from 0.723 through 0.895. Secondly, the KESHH showed systematically increasing score as the hearing impairment increased. The lowest score was 24 and the highest score was 117 and the average scores of the hearing impaired and non-hearing impaired are 72.06(SD=15.67) and 66.98(SD=20.94) showing 5.08 increased score for the hearing impaired. Depending on the degree of the hearing loss, the scores recorded 52.63 at the below of the mild hearing loss, 67.29 for the moderate hearing loss, 71.89 for the moderately severe hearing loss, and 75.57 for the severe hearing loss The comparison of the scores by hearing levels indicated that the higher the hearing levels were, the higher the scores of the KESHH with statistical significance(p<0.001). Thirdly, the correlation among 4 subscales was 0.384~0.880(p<0.001). Also, the pure tone average, personality, and the four subscales correlations showed statistical significance with 0.148~0.880 except for the pure tone average and personality and the pure tone average and perception of hearing aids. Fourthly, the total variances explained for the independent subscles were analyzed with multiple regression. The social effect was explained 17.4% with pure tone average, personality, and the status of hearing aid use variances. The psycho/emotional effect was explained 14.4% with puretone average, personality, and age variances. The interpersonal effect was explained 11.2% with pure tone average, personality, and the status of hearing aid use variances. The perception of hearing aids effect was explained 2.2% with only personality. Finally, test-retest reliability was proved to be high with 0.791(p<0.001). Conclusively, the KESHH that was developed considering Korean culture can be a useful instrument for expressing the hearing handicaps of the Korean aged hearing impaired in scores for both hearing aid users and non-users. Also, it is thought that the KESHH is useful clinically for identifying the changes of the hearing handicap scores before and after wearing hearing aids and aural rehabilitation at diverse situations.

Design and Implementation of MongoDB-based Unstructured Log Processing System over Cloud Computing Environment (클라우드 환경에서 MongoDB 기반의 비정형 로그 처리 시스템 설계 및 구현)

  • Kim, Myoungjin;Han, Seungho;Cui, Yun;Lee, Hanku
    • Journal of Internet Computing and Services
    • /
    • v.14 no.6
    • /
    • pp.71-84
    • /
    • 2013
  • Log data, which record the multitude of information created when operating computer systems, are utilized in many processes, from carrying out computer system inspection and process optimization to providing customized user optimization. In this paper, we propose a MongoDB-based unstructured log processing system in a cloud environment for processing the massive amount of log data of banks. Most of the log data generated during banking operations come from handling a client's business. Therefore, in order to gather, store, categorize, and analyze the log data generated while processing the client's business, a separate log data processing system needs to be established. However, the realization of flexible storage expansion functions for processing a massive amount of unstructured log data and executing a considerable number of functions to categorize and analyze the stored unstructured log data is difficult in existing computer environments. Thus, in this study, we use cloud computing technology to realize a cloud-based log data processing system for processing unstructured log data that are difficult to process using the existing computing infrastructure's analysis tools and management system. The proposed system uses the IaaS (Infrastructure as a Service) cloud environment to provide a flexible expansion of computing resources and includes the ability to flexibly expand resources such as storage space and memory under conditions such as extended storage or rapid increase in log data. Moreover, to overcome the processing limits of the existing analysis tool when a real-time analysis of the aggregated unstructured log data is required, the proposed system includes a Hadoop-based analysis module for quick and reliable parallel-distributed processing of the massive amount of log data. Furthermore, because the HDFS (Hadoop Distributed File System) stores data by generating copies of the block units of the aggregated log data, the proposed system offers automatic restore functions for the system to continually operate after it recovers from a malfunction. Finally, by establishing a distributed database using the NoSQL-based Mongo DB, the proposed system provides methods of effectively processing unstructured log data. Relational databases such as the MySQL databases have complex schemas that are inappropriate for processing unstructured log data. Further, strict schemas like those of relational databases cannot expand nodes in the case wherein the stored data are distributed to various nodes when the amount of data rapidly increases. NoSQL does not provide the complex computations that relational databases may provide but can easily expand the database through node dispersion when the amount of data increases rapidly; it is a non-relational database with an appropriate structure for processing unstructured data. The data models of the NoSQL are usually classified as Key-Value, column-oriented, and document-oriented types. Of these, the representative document-oriented data model, MongoDB, which has a free schema structure, is used in the proposed system. MongoDB is introduced to the proposed system because it makes it easy to process unstructured log data through a flexible schema structure, facilitates flexible node expansion when the amount of data is rapidly increasing, and provides an Auto-Sharding function that automatically expands storage. The proposed system is composed of a log collector module, a log graph generator module, a MongoDB module, a Hadoop-based analysis module, and a MySQL module. When the log data generated over the entire client business process of each bank are sent to the cloud server, the log collector module collects and classifies data according to the type of log data and distributes it to the MongoDB module and the MySQL module. The log graph generator module generates the results of the log analysis of the MongoDB module, Hadoop-based analysis module, and the MySQL module per analysis time and type of the aggregated log data, and provides them to the user through a web interface. Log data that require a real-time log data analysis are stored in the MySQL module and provided real-time by the log graph generator module. The aggregated log data per unit time are stored in the MongoDB module and plotted in a graph according to the user's various analysis conditions. The aggregated log data in the MongoDB module are parallel-distributed and processed by the Hadoop-based analysis module. A comparative evaluation is carried out against a log data processing system that uses only MySQL for inserting log data and estimating query performance; this evaluation proves the proposed system's superiority. Moreover, an optimal chunk size is confirmed through the log data insert performance evaluation of MongoDB for various chunk sizes.

Packing effects on the intracavitary radiation Therapy 3-Dimension plan of the uterine cervix cancer (자궁경부암 강내조사 3차원 치료계획 시 Packing의 유용성 분석)

  • Si, Chang-Keun;Jo, Jung-Kun;Lee, Du-Hyun;Kim, Sun-Yeung;Kim, Tae-Yoon
    • The Journal of Korean Society for Radiation Therapy
    • /
    • v.17 no.1
    • /
    • pp.1-8
    • /
    • 2005
  • Purpose : An effect of a packing to uterine treatment of a cervical cancer using a dose-volume histogram for a point dose and a volume dose of the bladder and the rectum was analyzed by establishing a three-dimensional treatment plan using a CT image. Materials and methods : Reference points of the bladder and the rectum were marked, respectively at a treatment plan device (plato brachytherapy V14.2.4) by photographing CT(marconi, USA) when the packing was used and removed under the same condition and a treatment plan was performed to Apoint depending on ICRU38. However, in case of the rectum, a maximum point was looked up and compared with the above point because the point presented from the ICRU is not proper as a representative value of a rectum point dose. Further, the volume dose depending on volume of $50\%,\;80\%,\;and\;100\%$ point doses of the rectum and the bladder was measured. The measured values were used to analyze the effect of the packing through a Wilcoxon Signed Rank Test (a SAS statistical analysis process program). Result : The reference points at the bladder and rectum doses when the packing was removed were $116.94\;35.42\%$ and $117.59\;21.08\%$, respectively. The points when the packing was used were $107.08\;38.12\%$ and $95.19\;21.32\%$, respectively. After the packing was used, the reference points at the bladder and the rectum were decreased by $9.86\%$ and $22.4\%$, respectively. When the packing was removed, the maximum points at the bladder and the rectum were $164.51\;50.89\%,\;128.81\;33.05\%$, respectively. When the packing was used, the maximum points at the bladder and the rectum were $142.31\;44.79,\;110.08\;37.03\%$, respectively. After the packing was used, the maximum points at the bladder and the rectum were decreased by $22.2\%$ and $18.73\%$, respectively. When the packing was removed, the bladder volume at $50\%,\;80\%,\;and\;100\%$ point doses of the rectum and the bladder were $48.62{\pm}18.09\%,\;16.12{\pm}11.15\%,\;and\;7.51{\pm}6.63\%$, respectively and its rectum volume were $23.41{\pm}14.44\%,\;6.27{\pm}4.28\%,\;2.79{\pm}2.27\%$, respectively. When the packing was used, the bladder volume at $50\%,\;80\%,\;and\;100\%$ point doses of the rectum and the bladder were $40.33{\pm}16.72,\;11.63{\pm}8.72,\;and\;4.87{\pm}4.75\%$, respectively and its rectum volume were $18.96{\pm}8.37\%,\;4.75{\pm}2.58\%,\;and\;1.58{\pm}1.06\%$, respectively. After the packing was used, the bladder volume at $50\%,\;80\%,\;and\;100\%$ point doses of the rectum and the bladder were decreased by $8.29\%,\;4.49\%,\;and\;2.64\%$, respectively and its bladder volume were decreased by $4.45\%,\;1.52\%,\;and\;1.21\%$, respectively. Conclusion : Values at Reference point doses of the bladder and the rectum recommended from the ICRU 38 were 0.0781 and 0.0781, respectively and values of their maximum point doses were 0.0156 and 0.0156, respectively, as a result of which an effect of the packing using at the uterine intracavitary treatment of an uterine cervical cancer through the three-dimensional treatment plan used CT were measured. That is, the values at reference point doses and the values at maximum point doses show similar difference. However, P value was 0.15 at over $50\%,\;80\%,\;and\;100\%$ volume doses and the value shows no similar difference. In other words, the effect of the packing looks like having a difference at the point dose, but actually shows no difference at the volume dose. The reason is that the volume of the bladder and the rectum are wide but the volume of the packing is only a portion. Therefore, the effect of decreasing the point dose was not great. Further, the farer the distance is, the more weak the intensity of radiation is because the intensity of radiation is proportional to inverse square of a distance. Therefore, the effort to minimize an obstacle of the bladder and the rectum by using the packing should be made.

  • PDF

The Study in Objectification of the diagnosis of Sasang Constitution(According to Analysis of the Past Questionnaires) (사상체질진단(四象體質診斷)의 객관화(客觀化)에 관한 연구(硏究)(기존(旣存) 설문지(說問紙)의 분석(分析)을 중심(中心)으로))

  • Kim, Young-woo;Kim, Jong-won
    • Journal of Sasang Constitutional Medicine
    • /
    • v.11 no.2
    • /
    • pp.151-183
    • /
    • 1999
  • The object of this study was 200 patients who had been treated in the Oriental Medical Hospital at Dong Eui Medical Center during 9 months from Jan. 1999 to sept. 1999. We proceeded the judgment of Sasang Constitution according to 'Questionnaire of Sasang Constitution Classification (I)', and 'Questionnaire of Sasang Constitution Classification II(QSCCII)' and the diagnosis by a medical specialist. The following conclusion were made in comparison with Sasang Constitution and Questionnaire. 1. We selected the 84 subjects what had the statistical value out of the 196 subjects('Questionnaire of Sasang Constitution Classification (I)' had the 71 subjects and 'Questionnaire of Sasang Constitution Classification II(QSCCII)', had the 121 subjects). And we selected again the 73 subjects('Questionnaire of Sasang Constitution Classification (I)', had the 33 subjects and 'Questionnaire of Sasang Constitution Classification II (QSCC II)' had the 40 subjects) out of the 84 subjects, because it had a repeated subjects. 2. We made the Questionnaire what has the 85 subjects, including the subjects what was approved its statistical value by 'A CLINICAL STUDY OF THE JUDGMENT OF SASANG CONSTITUTION ACCORDING TO QUESTIONNAIRE' and 'A CLINICAL STUDY OF THE TYPE OF DISEASE AND SYMPTOM ACCORDING TO SASANG CONSTITUTION CLASSIFICATION'. The subject what ask the physique and the body form was 7, the subject what ask the external appearance and the posture was 7, the subject what ask the habit and the character was 3, the subject what ask the physiology and the pathology was 3, the subject what ask the phenomenon that he has frequency was 4, the subject what ask the eating was 3, the subject what ask the symptom that he has frequency was 14, the subject what ask the work and the qualities-defects was 6, the subject what ask the friendly intercourse was 7, the subject what ask the usual mind was 5, the subject what ask the emotional inclination was I, the subject what ask the behavioral inclination was 10, the subject what ask the character was 15. 3. In the new Questionnaire, the subject what has relevance to Soyang was 84, the subject what has relevance to Soeum was 87, the subject what has relevance to Taeeum was 70. And we made the point of subject with the statistical ratio. The total point of Soyang was 7785.04, the total point of Soeum was 7742.80, the total point of Taeeum was 7746.60. 4. As a result of judgment of Sasang Constitution between the clinical diagnosis by a medical specialist and the new Questionnaire, the diagnostic accuracy of new Questionnaire was 73.33%. The diagnostic accuracy of Soyang was low, the others was high. And the Taeyang was excepted.

  • PDF