• Title/Summary/Keyword: school selection

Search Result 3,301, Processing Time 0.028 seconds

Landslide susceptibility assessment using feature selection-based machine learning models

  • Liu, Lei-Lei;Yang, Can;Wang, Xiao-Mi
    • Geomechanics and Engineering
    • /
    • v.25 no.1
    • /
    • pp.1-16
    • /
    • 2021
  • Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

A Novel Action Selection Mechanism for Intelligent Service Robots

  • Suh, Il-Hong;Kwon, Woo-Young;Lee, Sang-Hoon
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.2027-2032
    • /
    • 2003
  • For action selection as well as learning, simple associations between stimulus and response have been employed in most of literatures. But, for a successful task accomplishment, it is required that an animat can learn and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with sequential behaviors. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a network with behavioral motivations. The vertical path of the network represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.

  • PDF

A Study on the Clothing Practices of Korean Girl's Junior High School & University Students (청소년 의생활의 실태조사 -서울지역 여자 중.고.대학생을 중심으로-)

  • 조진숙
    • The Research Journal of the Costume Culture
    • /
    • v.2 no.2
    • /
    • pp.337-354
    • /
    • 1994
  • The main purpose of the study were to investigate a selection motive of clothing and feeling of wearing of Korean junior, high school & university students. The results were as follows; 1. For underwear, the body appearance and hygienical aspect were shown as important factors in a selection motive of clothing. And the property matter and hygienical aspect were shown as important factors in the feeling of wearing. 2. For outwear, a functionality and the psychological aspect were shown as important factors in a selection motive of clothing. And a exercise and psychological aspect were shown as important factors in the feeling of wearing. 3. For pants, the functionality was shown as an important factor in a selection motive of clothing and the exercise aspect was shown as an important factors in the feeling of wearing. For skirt. the psychological aspect was shown as an important factor in a selection motive of clothing and feeling of wearing. 4. The hygienical aspect was shown as an important factor in a selection motive and the feeling of wearing of clothing for comfort.

  • PDF

TOUSE: A Fair User Selection Mechanism Based on Dynamic Time Warping for MU-MIMO Networks

  • Tang, Zhaoshu;Qin, Zhenquan;Zhu, Ming;Fang, Jian;Wang, Lei;Ma, Honglian
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.11 no.9
    • /
    • pp.4398-4417
    • /
    • 2017
  • Multi-user Multiple-Input and Multiple-Output (MU-MIMO) has potential for prominently enhancing the capacity of wireless network by simultaneously transmitting to multiple users. User selection is an unavoidable problem which bottlenecks the gain of MU-MIMO to a great extent. Major state-of-the-art works are focusing on improving network throughput by using Channel State Information (CSI), however, the overhead of CSI feedback becomes unacceptable when the number of users is large. Some work does well in balancing tradeoff between complexity and achievable throughput but is lack of consideration of fairness. Current works universally ignore the rational utilizing of time resources, which may lead the improvements of network throughput to a standstill. In this paper, we propose TOUSE, a scalable and fair user selection scheme for MU-MIMO. The core design is dynamic-time-warping-based user selection mechanism for downlink MU-MIMO, which could make full use of concurrent transmitting time. TOUSE also presents a novel data-rate estimation method without any CSI feedback, providing supports for user selections. Simulation result shows that TOUSE significantly outperforms traditional contention-based user selection schemes in both throughput and fairness in an indoor condition.

Development of CTP Selection Methodology of Semiconductor Equipment Line Using AHP and Fuzzy Decision Model (AHP 및 Fuzzy 의사결정 모형을 활용한 반도체 장치라인의 CTP 선정 방법론 개발)

  • Jeong, Jaehwan;Kim, Jungseop;Kim, Yeojin;Lee, Jonghwan
    • Journal of the Semiconductor & Display Technology
    • /
    • v.20 no.2
    • /
    • pp.6-13
    • /
    • 2021
  • Cases and studies on the selection method of CTQ are relatively active, but there are few cases or studies on the selection method of CTP which is important in the device industry. In fact, many companies simply select and manage CTP from the point of contact based on their experience and intuition. The purpose of this study is to present an evaluation model and a mathematical decision model for rational and systematic CTP selection to improve the process quality of semiconductor equipment lines. In the evaluation model, AHP (Analytic Hierarchy Process) analysis technique was applied to show objective and quantitative figures, and Fuzzy decision-making model was used to solve the ambiguity and uncertainty in the decision-making process. Decision Value (DV) was presented. The subjects were 22 process factors managed in the Plating Process that the representative equipment line can do. As a result, the evaluation model proposed in this study can support more efficient and effective decision-making for process quality improvement by more objectively measuring the problem of subjective CTP selection in manufacturing sites.

Analysis on Tower Crane Selection in Precast Concretes Structures and its Connection with Precast Rate

  • Guo, Jingjing;Fu, Yan;Wang, Kang;Peng, Zhenyu
    • International conference on construction engineering and project management
    • /
    • 2017.10a
    • /
    • pp.192-200
    • /
    • 2017
  • With the acceleration of construction industrialization, the buildings that China has adopted the construction of industrialization technology are increasing day by day, and Precast Concrete (PC) Structure technology is one of the main technologies of construction industrialization. Compared with the traditional cast-in-place concrete structure, PC structure is more conducive to shorten the construction period, reduce the number of construction workers and the site construction waste. Nevertheless, PC structure improves the requirements of hoisting machinery in the construction site, and the lay-out and selection of hoisting machinery become an important factor influencing the construction cost. The paper regards the typical tower crane in China as the research object, and establishes the time optimization model for the lifting scheme. The influence of the different precast rate on the selection of the tower crane is analyzed. This paper obtains the time variation of the tower crane under different precast rate, provides a theoretical basis for the design of precast concrete structures under the influence of assembly construction, and lays the foundation for the selection of tower crane under the precast rate.

  • PDF

Examination of Students' Perceptions of the Selection of Science Subjects in High School Credit System and Their Reasons for Selection

  • Dong-Seon Shin;Jong Keun Park
    • International Journal of Advanced Culture Technology
    • /
    • v.11 no.4
    • /
    • pp.263-272
    • /
    • 2023
  • We investigated and analyzed students' perceptions of their choice of science subjects in the high school credit system and the reasons for their choice. To achieve this, the selection of science subjects was investigated for the second year of S high school over the past three years. Students selected an average of 1.54 science subjects, and it was found that the rate of selection of science subjects was gradually increasing by year. Students chose high in the order of life science I, earth science I, chemistry I, physics I, etc. in the science subject group. Students who wish to enter the natural and engineering fields chose life science I, chemistry I, physics I, etc., while, students who wish to enter the humanities society chose society and culture, life science I, ethics and thought, etc. On the other hand, the reason for choosing science subjects was 'related to college admission', followed by 'aptitude and interest', 'career and real life help', etc. physics I, chemistry I, etc., were high in the subjects selected according to the 'related to college admission'. The subjects selected according to 'aptitude and interest' were high in life science I, earth science I, etc. Physics I, chemistry I, etc. are recognized as subjects necessary for college entrance, and life science I, earth science I, etc., are found to be related to their interests and aptitudes.

Noise-Robust Speaker Recognition Using Subband Likelihoods and Reliable-Feature Selection

  • Kim, Sung-Tak;Ji, Mi-Kyong;Kim, Hoi-Rin
    • ETRI Journal
    • /
    • v.30 no.1
    • /
    • pp.89-100
    • /
    • 2008
  • We consider the feature recombination technique in a multiband approach to speaker identification and verification. To overcome the ineffectiveness of conventional feature recombination in broadband noisy environments, we propose a new subband feature recombination which uses subband likelihoods and a subband reliable-feature selection technique with an adaptive noise model. In the decision step of speaker recognition, a few very low unreliable feature likelihood scores can cause a speaker recognition system to make an incorrect decision. To overcome this problem, reliable-feature selection adjusts the likelihood scores of an unreliable feature by comparison with those of an adaptive noise model, which is estimated by the maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. To evaluate the effectiveness of the proposed methods in noisy environments, we use the TIMIT database and the NTIMIT database, which is the corresponding telephone version of TIMIT database. The proposed subband feature recombination with subband reliable-feature selection achieves better performance than the conventional feature recombination system with reliable-feature selection.

  • PDF

A Study on the Selection Criteria for Home Economics Textbook in the Middle School (중학교 가정 교과서 선정 기준에 관한 연구)

  • 권리라;윤인경
    • Journal of Korean Home Economics Education Association
    • /
    • v.10 no.1
    • /
    • pp.41-57
    • /
    • 1998
  • The purpose of this study was to make a selection criteria for Home Economics textbooks in the middle school. For this purpose, first, the criteria were out by collecting, analyzing and synthesizing the literature. Second, questionnaire survey of the 6 selection criteria was performed. Questionnaire sent to Home Economics teachers of 401 middle school selected by systematic random sapling, 233 questionnaire were received and 220 questionnaire were analyzed for this study. As a statistical tool, SPSSWIN was used to analyze frequency, mean, standard deviation, and factor analysis. The research findings were as follows ; 1. Now for kinds of Home Economics textbooks are mainly used. At that time when textbooks were selected, these selections were made upon deliberation with the teachers in charge and in future this method will be desirable. Most home economics teachers realize that the selection criteria is needed to improve the objectivity of textbook selection. 2. As a result of making factor analysis, the selection criteria were revised that 52 items in 7 categories were chosen as textbook criteria plan. They consist of 5 items related to the outward form of textbook, 5 items related to the learning materials in textbook, 10 items related to the composition of textbook units, 11 items related to the guiding contents of textbook, 7 items related to the subject of experiment.practice, 9 items related to the composition of picture, photograph and diagram. and 7 items related to the use of instructional-learning method.

  • PDF

An Analysis on the Priority of Selection of Supplier for School Food Service Materials (학교급식 식자재 공급업체 선정요인의 우선순위에 관한 연구)

  • Park, Myung-Joo;Kim, Suk-Whan;Lee, Joung-Sil
    • Korean Journal of Community Nutrition
    • /
    • v.13 no.4
    • /
    • pp.531-539
    • /
    • 2008
  • The purpose of this study is to examine how nutritionists, principals and parents evaluated the importance and priorities of different selection factors for food materials suppliers in an attempt to suggest how to ensure the best supplier choice, since the selection of the best supplier was mandatory for the successful TQM of school food services. This study especially aims to develop priority alternatives based on relative rather than absolute assignments on selection of suppliers for school food service materials. To apply AHP, the selection factors of a food materials suppliers were grouped into five categories, which included quality, service, reliability, hygiene and price. And the five categories involved 28 elements. As the result, quality was considered most crucial on the whole, followed by service, reliability, hygiene and price; and food labeling in the category of quality evaluated as that of first priority in the totality evaluation elements.