• Title/Summary/Keyword: RankBoost

Search Result 12, Processing Time 0.026 seconds

RankBoost Algorithm for Personalized Education of Chinese Characters on Smartphone (스마트폰 상에서의 개인화 학습을 위한 랭크부스트 알고리즘)

  • Kang, Dae-Ki;Chang, Won-Tae
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.14 no.1
    • /
    • pp.70-76
    • /
    • 2010
  • In this paper, we propose a personalized Chinese character education system using RankBoost algorithm on a smartphone. In a typical Chinese character education scenario, a trainee is supplied with a finite number of Chinese characters as an input set in the beginning. And, as the training session repeats, the trainee will notice her/his difficult characters in the set which she/he hardly answers. Those characters reflect their personalized degrees of difficulty. Our proposed system constructs these personalized degrees of difficulty using RankBoost algorithm. In the beginning, the algorithm start with the set of Chinese characters, of which each is associated with the same weight values. As the training sessions are repeated, the algorithm increase the weights of Chinese characters that the trainee mistakes, thereby eventually constructs the personalized difficulty degrees of Chinese characters. The proposed algorithm maximizes the educational effects by having the trainee exposed to difficult characters more than easy ones.

Composition and Structure of Himalayan Oak (Quercus leucotrichophora A. Camus) Forest under Various Degrees of Disturbance

  • Prasad, Sunil;Uniyal, Pooja;Chauhan, D.S.
    • Journal of Forest and Environmental Science
    • /
    • v.31 no.1
    • /
    • pp.7-13
    • /
    • 2015
  • Forest disturbance sometime considered as a tool of management as it believed that mid level disturbance constructs better micro-climatic conditions which ultimately boost up the plant diversity. The effect of different levels of disturbance on species composition and regeneration is very important. Present attempt was carried out in a temperate evergreen oak forest which was under various degree of disturbance. The study area is one of the large ranges of oak forest in Garhwal Himalaya and compensating various types of daily needs of local people. On the basis of IVI values Quercus leucotrichophora holds first position in all the disturbance zones whereas Myrica esculenta upgraded it's rank in highly disturbed zone and showed less impacted species by disturbance. Berberis aristata and Eupatorium adenophorum in shrub layer and Anaphalis adnata and Bidens pilosa in herb layer were found as disturbance friendly species because they attained higher rank in highly disturbed zone whereas Caryopteris foetida was found disturbance-sensitive in shrub layer. The banj oak regenerated well under mid disturbance as compared to no and high degree of disturbance and a sharp downfall in the species diversity was recorded with increasing magnitude of disturbance. Density-diameter curves showed a reverse trend of lower density in higher girth classes. The results of the study should be useful for the forest management strategies.

A Study on the Win-Loss Prediction Analysis of Korean Professional Baseball by Artificial Intelligence Model (인공지능 모델에 따른 한국 프로야구의 승패 예측 분석에 관한 연구)

  • Kim, Tae-Hun;Lim, Seong-Won;Koh, Jin-Gwang;Lee, Jae-Hak
    • The Journal of Bigdata
    • /
    • v.5 no.2
    • /
    • pp.77-84
    • /
    • 2020
  • In this study, we conducted a study on the win-loss predicton analysis of korean professional baseball by artificial intelligence models. Based on the model, we predicted the winner as well as each team's final rank in the league. Additionally, we developed a website for viewers' understanding. In each game's first, third, and fifth inning, we analyze to select the best model that performs the highest accuracy and minimizes errors. Based on the result, we generate the rankings. We used the predicted data started from May 5, the season's opening day, to August 30, 2020 to generate the rankings. In the games which Kia Tigers did not play, however, we used actual games' results in the data. KNN and AdaBoost selected the most optimized machine learning model. As a result, we observe a decreasing trend of the predicted results' ranking error as the season progresses. The deep learning model recorded 89% of the model accuracy. It provides the same result of decreasing ranking error trends of the predicted results that we observe in the machine learning model. We estimate that this study's result applies to future KBO predictions as well as other fields. We expect broadcasting enhancements by posting the predicted winning percentage per inning which is generated by AI algorism. We expect this will bring new interest to the KBO fans. Furthermore, the prediction generated at each inning would provide insights to teams so that they can analyze data and come up with successful strategies.

The Effect on Images of an Engineering Program Participate toward 'Engineering' and 'Technology' through Semantic Differential Method (공학캠프를 통한 공학과 기술에 대한 이미지 변화 연구)

  • Lim, Nha Young;Lee, Chang Hoon
    • Journal of Engineering Education Research
    • /
    • v.20 no.6
    • /
    • pp.68-75
    • /
    • 2017
  • This study has a purpose to analyse changes in perception and image about engineering and technology of students who participated in the engineering camp. To achieve this objective, the questions were as follows. 1) What about participants' image difference for engineering before and after participating the engineering camp 2) What about participants' image difference for technology before and after participating the engineering camp. For this study, the program was progressed from Aug in 2017 and the data was collected from 88 students, middle school seniors and high school freshmen. The results of this study were as follows: First, secondary students perceived 'valuable(6.74)', 'meaningful(6.73)', 'rich(6.40)', 'collaborative(6.42)', 'nice(6.22)' as high image rank of the positive response for engineering. On the other hand, 'complex(3.59)', 'labored(3.80)', 'hard(4.66)', 'dangerous(4.48)', 'cold(4.86)' were perceived as low image rank of the negative response for engineering. We can realize that they generally has the image that engineering is valuable, meaningful and nice but also labored, complex and hard. The students who participated in the engineering camp showed the greatest difference in 'complex - simple' and 'dangerous - safe' engineering categories before and after the camp, followed by 'cold - hot', 'labored - easy', and 'hard - soft', respectively. Second, secondary students perceived 'meaningful(6.58)', 'valuable(6.55)', 'wide(6.38)', 'nice(6.37)', 'strong(6.25)' as high image rank of the positive response for technology. On the other hand, 'complex(3.85)', 'labored(3.93)', 'hard(4.62)', 'dangerous(4.72)', 'cold(5.05)' were perceived as low image rank of the negative response for technology. The students who participated in the engineering camp had the big change in 'hard - soft' technology category before and after the camp, followed by 'complex - simple', 'labored - easy', 'theoretical - practical' and 'dangerous - safe', respectively. We can see that the negative images for technology which were complex, labored, dangerous, theoretical was improved with positive image such as simple, easy, safe and practical, after conducting the engineering camp. In conclusion, both image recognitions for engineering and technology have improved after the camp. It means that interesting and entertaining engineering-technology program can boost interests in engineering and technology which felt difficult, so that images about them can be turned out positive. Also, it is possible to reduce avoidance of natural science and engineering subjects, as part of the purpose of training creative talents in science and engineering, so it can be said that the engineering camp is highly meaningful because it can lead students into the field of science and engineering.

Analytical Study on Classification and Service Quality Improvement for Keyword & Blog Advertising Marketing Services (검색 광고 마케팅 서비스 유형 분석과 서비스 품질 개선방안)

  • Choi, Yoon-Ho;Lee, Jae-Won
    • The Journal of the Korea Contents Association
    • /
    • v.15 no.11
    • /
    • pp.456-466
    • /
    • 2015
  • This study is focusing to the keyword and blog advertising marketing services that are implementing a viral marketing utilizing keyword searches of the search portal and advertiser's blogs with convergent way. Through a case study for the company operating the service to pinpoint consumers to the advertisers site by indirect exposure via keyword advertising blog at the top of the search results, we analyzed the primitive service operation model on transactional relationship between the business players. We have a research purpose to generate improvement alternatives for the company's keyword advertising marketing services and operation solution using the survey study on the service quality perception and the perceptional gap between user groups. As results of study, we founded 4 types of the service solution and 4 models of service operating architecture on the transactional relations, and we recommended some improvements on the service and solution operation based on the SERVQUAL questionnaire analysis of the difference between the ads sponsor group and ads agency group.

SVD-LDA: A Combined Model for Text Classification

  • Hai, Nguyen Cao Truong;Kim, Kyung-Im;Park, Hyuk-Ro
    • Journal of Information Processing Systems
    • /
    • v.5 no.1
    • /
    • pp.5-10
    • /
    • 2009
  • Text data has always accounted for a major portion of the world's information. As the volume of information increases exponentially, the portion of text data also increases significantly. Text classification is therefore still an important area of research. LDA is an updated, probabilistic model which has been used in many applications in many other fields. As regards text data, LDA also has many applications, which has been applied various enhancements. However, it seems that no applications take care of the input for LDA. In this paper, we suggest a way to map the input space to a reduced space, which may avoid the unreliability, ambiguity and redundancy of individual terms as descriptors. The purpose of this paper is to show that LDA can be perfectly performed in a "clean and clear" space. Experiments are conducted on 20 News Groups data sets. The results show that the proposed method can boost the classification results when the appropriate choice of rank of the reduced space is determined.

A Study on the Trade Structures and International Competitiveness of the Korean Environmental Industry (우리나라 환경산업의 무역구조와 국제경쟁력에 관한 연구)

  • Park, Bok-Jae;Moon, Young-Soo
    • International Commerce and Information Review
    • /
    • v.15 no.2
    • /
    • pp.345-364
    • /
    • 2013
  • This paper analyzed the Trade Structure of environmental industry in Korea and some major countries in preparation for The Doha Development Agenda (DDA) Trade Liberalization Negotiation in the environmental goods. Based on 161 environmental goods list proposed by OECD, this paper examined the Trade Returns of worldwide environmental goods during the past 10 years from 2002 to 2011. The analysis showed that Korean environmental goods' International Market Share(IMS) in the world was 3.2%; trade specialization index(TSI) -0.128; Revealed Comparative Advantage(RCA) 1.002 in 2011. And Korea Export Similarity Index(ESI) to Japan was the highest rank in the world market. According to the results of investigation, it is clear that International Competitiveness of the Korean Environmental Industry was received a relatively poor evaluation compared with Korean trade scale. To strengthen the competitiveness, it is required that Korean government should make an effort to boost domestic environmental industry and promote systematically Trade Liberalization Negotiation including the enforcement of transient period for Korean environmental goods in the next DDA Negotiation.

  • PDF

A Distributed Vertex Rearrangement Algorithm for Compressing and Mining Big Graphs (대용량 그래프 압축과 마이닝을 위한 그래프 정점 재배치 분산 알고리즘)

  • Park, Namyong;Park, Chiwan;Kang, U
    • Journal of KIISE
    • /
    • v.43 no.10
    • /
    • pp.1131-1143
    • /
    • 2016
  • How can we effectively compress big graphs composed of billions of edges? By concentrating non-zeros in the adjacency matrix through vertex rearrangement, we can compress big graphs more efficiently. Also, we can boost the performance of several graph mining algorithms such as PageRank. SlashBurn is a state-of-the-art vertex rearrangement method. It processes real-world graphs effectively by utilizing the power-law characteristic of the real-world networks. However, the original SlashBurn algorithm displays a noticeable slowdown for large-scale graphs, and cannot be used at all when graphs are too large to fit in a single machine since it is designed to run on a single machine. In this paper, we propose a distributed SlashBurn algorithm to overcome these limitations. Distributed SlashBurn processes big graphs much faster than the original SlashBurn algorithm does. In addition, it scales up well by performing the large-scale vertex rearrangement process in a distributed fashion. In our experiments using real-world big graphs, the proposed distributed SlashBurn algorithm was found to run more than 45 times faster than the single machine counterpart, and process graphs that are 16 times bigger compared to the original method.

A Study on the State of Fashion Marketing Using the SNS -Focused on the Facebook- (SNS를 이용한 패션업체의 마케팅 실태 연구 -Facebook을 중심으로-)

  • Kim, Tae-Jin;Chin, Seong-Ah
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.13 no.5
    • /
    • pp.2305-2312
    • /
    • 2012
  • Rapid evolutions in recent years related to IT (information technology) which has been exceedingly developed make it possible to utilize its application in broad fields as providing a convenient way to gather and to reuse information. As smart phones have been sporadic nowadays which boost increase of SNS in real-time making more dynamic, it is becoming more worthful as a marketing tool in the field of fashion area. In this study, we have explored some case studies in which they are actively using Facebook. We have selected 10 fashion brands to compare their activities in boards containing 'notice', 'like this', 'people talking about this' and 'event'. We also conduct the correlation analysis between the indicators above, using Spearman's rank correlation coefficient. As a consequence, we can confirm that 'notice' highly correlates with 'like this', but we cannot find any other correlations between the other factors. As a reasult, marketing in Facebook is more efficient communication way between the companies and customers than using other current mass media, it shows that SNS in fashion marketing could be an innovative solution to overcome current limitations caused probably by lack of communications.

Breast Conservation Therapy Versus Mastectomy - Preliminary Results of Pattern of Failure and Survival Rate in Early Breast Cancer (조기유방암에서 유방보존치료와 유방전절제술의 치료결과 및 실패양상 비교)

  • Kim Yeon-Sil;Yoon Sei-Chul;Chung Su-Mi;Ryu Mi-Ryeong;Jung Sang-Sul;Choi Ihl-Bohng
    • Radiation Oncology Journal
    • /
    • v.22 no.2
    • /
    • pp.115-123
    • /
    • 2004
  • Purpose : This retrospective study was conducted to compare early preliminary results of breast conservation therapy (BCT) with mastectomy In early breast cancer. Materials and Methods : We evaluated 171 women with AJCC stage I and II breast cancer who had been treated at Kangnam St. Mary's Hospital from March 1989 to August 1996. Eighty-eight patients underwent mastectomy and 85 patients did conservative surgery with breast irradiation. in the BCT group, all patients received whole breast irradiation to a total dose of 45$\~$50 Gy/5$\~$6 wks, followed by a boost to the original tumor site at least 60 Gy. Chemotherapy was administered to 29 (34.1$\%$) patients in BCT and 40 (45.5$\%$) in mastectomy, with various sequencing of surgery and/or radiation. We compared survival rate, patterns of failure in each treatment group and the prognostic factors that had a significant effect on treatment failure. The median follow-up time was 63 months (19$\~$111 months). Log rank test was used to estimate the prognostic factors for treatment failure. Results : Overall survival, disease free survival, locoregional recurrence and distant metastasis rates were not significantly different between the two treatment groups. During the follow-up period, 11 patients (12.5$\%$)in the mastectomy group and 10 patients (11.8%$\%$ in the BCT group were failed. Six local recurrences occurred after mastectomy and 5 after BCT Five patients fatted at distant site in mastectomy and 4 in BCT. Of the local recurrence cases, five of 6 mastectomy patients and 3 of S BCT patients were alive with no evidence of disease after salvage surgery and/or chemoirradiation. Our results indicated that the major influence on survival was distant metastasis. Unfortunately, control of distant metastasisis was not frequently achieved. Even with salvage systemic therapy or radiotherapy, most of distant metastasis patients died or had uncontrolled disease in both treatment groups: only one of 4 BCT patients and none of mastectomy patients were alive without disease. There was no apparent difference in the incidence rate of contralateral breast cancer and non-breast 2$^{nd}$ primary tumor between the two treatment groups. Univariate Log-rank test identified the N stage and the involved axillary LN number as distinct prognostic factors that were highly predictive of treatment failure in both treatment groups. Additionally, marginal status in BCT and histologic nuclear grade In the mastectomy group were risk factors for treatment fallure (p < 0.05). Concousion : Although further careful follow-up is necessary to confirm the trends evident In this serles, it would appear that patterns of failure and survival rate following conservative surgery and radiotherapy in early breast cancer are similar to those following mastectomy. The great majority of patients with local recurrence had an exellent salvage rate in both treatment groups. Therefore, these preliminary short term results support BCT as an equally effective management for early breast cancer as an alternative to mastectomy.