scholarly journals Semi-supervised learning with the clustering and Decision Trees classifier for the task of cognitive workload study

2020 ◽  
Vol 15 ◽  
pp. 214-218
Author(s):  
Martyna Wawrzyk
Keyword(s):  
Supervised Learning ◽  
Clustering Algorithm ◽  
Cognitive Workload ◽  
Digit Symbol Substitution Test ◽  
Eye Tracker ◽  
Symbol Substitution ◽  
Decision Tress ◽  
High Level

The paper is focused on application of the clustering algorithm and Decision Tress classifier (DTs) as a semi-supervised method for the task of cognitive workload level classification. The analyzed data were collected during examination of Digit Symbol Substitution Test (DSST) with use of eye-tracker device. 26 participants took part in examination as volunteers. There were conducted three parts of DSST test with different levels of difficulty. As a results there were obtained three versions of data: low, middle and high level of cognitive workload. The case study covered clustering of collected data by using k-means algorithm to detect three clusters or more. The obtained clusters were evaluated by three internal indices to measure the quality of clustering. The David-Boudin index detected the best results in case of four clusters. Based on this information it is possible to formulate the hypothesis of the existence of four clusters. The obtained clusters were adopted as classes in supervised learning and have been subjected to classification. The DTs was applied in classification. There were obtained the 0.85 mean accuracy for three-class classification and 0.73 mean accuracy for four-class classification.  

scholarly journals Farmer Preference to High Elevation Rice Technological Packages for Accelerating Technological Dissemination (A case Study in Humbang Hasundutan Regency)

Agro Ekonomi ◽  
2021 ◽  
Vol 32 (2) ◽  
Author(s):  
Setia Sari Girsang ◽  
Agung B Santosa ◽  
Tommy Purba ◽  
Deddy R Siagian ◽  
Khadijah E Ramija
Keyword(s):  
Low Cost ◽  
High Elevation ◽  
Primary Data ◽  
Survey Method ◽  
User Friendliness ◽  
Level Of Satisfaction ◽  
High Level ◽  
Level Of Importance

Accelerating the introduction of a new technological package is needed to increase the productivity of high elevation puddled rice in Humbang Hasundutan. The objectives of the study are to find out the perception of the existence of technological packages and farmers' preference for a new technological package. The study used a survey method with primary data gathered using questionnaires. The criteria of locations and respondents were used to obtain relevant respondents and data concerning their knowledge of high elevation puddled rice cultivation.  The collected data were processed by using Importance Performance Analysis in order to find out the level of Importance and Satisfaction of the indicators and the valued aspects in the technological package components. The results of the study showed that the socio-economic aspects had to be heeded in organizing the technological package. Indicators having a high level of importance and a low level of satisfaction consisted of production cost, quality of seeds, farmer groups empowerment, technology information institution, capital cost, agricultural tools and machines, pest control, sales price, irrigation canals, and farm roads. On the other hand, introducing new superior seeds, productivity attribute and planting age were important indicators for local farmers as to improve the quality of existing seeds. Farmers group expected that the technological package had a high level of productivity, better access to input, low cost, and good user-friendliness in its application.

scholarly journals PENERAPAN DATA MINING DALAM MENGELOMPOKAN PRODUKSI JAGUNG MENURUT PROVINSI MENGGUNAKAN ALGORITMA K-MEANS

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Nanda Erlangga ◽  
Solikhun Solikhun ◽  
Irawan Irawan
Keyword(s):  
Data Mining ◽  
Clustering Algorithm ◽  
Rapid Development ◽  
Domestic Market ◽  
Corn Production ◽  
Low Level ◽  
High Level ◽  
Level Cluster ◽  
Central Statistics

Corn needs are currently experiencing a fairly rapid development can be seen in terms of the domestic market, here researchers want to increase the productivity and quality of corn production. The data that will be used is the data from the Central Statistics Agency. The method in this study is the K-means clustering algorithm and the application used is Rapidminer which will be grouped into 2 clustering, namely high and low. The results of this study are 2 high level cluster provinces, 32 low level cluster provincesKeywords: Corn, Data mining, K-means Clustering c

scholarly journals A Bayesian Best-Worst Method-Based Multicriteria Competence Analysis of Crowdsourcing Delivery Personnel

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-17 ◽  
Author(s):  
Longxiao Li ◽  
Xu Wang ◽  
Jafar Rezaei
Keyword(s):  
Customer Service ◽  
Value Function ◽  
Service Network ◽  
Core Elements ◽  
Delivery Platform ◽  
High Level ◽  
The Relationship ◽  
Best Worst Method

Crowdsourcing delivery is becoming a prevalent tool for tackling delivery problems by building a large labor-intensive service network. In this network, the delivery personnel consist of a large number of people with a complex composition and high level of mobility, creating enormous challenges for the quality of service and the management of a crowdsourcing platform. Hence, we attempt to conduct a competence analysis to determine whether they can provide promised services with high quality, i.e., they are competent for their job. To this end, the competence theory is introduced, and a multicriteria competence analysis (MCCA) approach is developed. To illustrate the MCCA approach, a real-world case study is conducted involving a Chinese takeaway delivery platform, where the Bayesian best-worst method is used to determine the weights of the criteria based on the data collected from managers of the platform company. Also, the competence scores of the personnel involved are collected through surveys and data sources of the company. Given the weights and the competence scores, we use additive value function to identify the overall competence scores of them, which reflects the level of competence for their job. The results show that Skills is the most important competence, while Knowledge is the least important of the four competence dimensions. In subcriteria, four core elements are identified such as punctuality, customer service awareness, responsible, and goods intact. In addition to the importance of criteria, a ranking of a sample of personnel is provided, and almost half of the crowdsourcing delivery personnel’s competence is below the average and vary significantly, while the relationship between the competence level and some other variables is also discussed. Moreover, the developed MCCA approach in this paper can be applied to analyze the competence of personnel in many other industries as well.

Co-evolutionary processes and positive feedbacks in the growth of the ultimate fighting championships

2015 ◽  
Vol 5 (1) ◽  
pp. 31-49 ◽  
Author(s):  
Simon James Ford
Keyword(s):  
Web Sites ◽  
Critical Mass ◽  
Growth Dynamics ◽  
Historical Case Study ◽  
Historical Case ◽  
Content Type ◽  
Positive Feedbacks ◽  
High Level

Purpose – In the late 2000s, the Ultimate Fighting Championships (UFC) emerged to become the dominant mixed martial arts (MMA) organisation, bringing the sport to mainstream acceptance. The purpose of this paper is to draw on theories of co-evolution and positive feedbacks to provide insights into how the UFC has assumed this dominant position. Design/methodology/approach – A single historical case study is compiled drawing on data from a number of sources, including the UFC, US State Athletic Commissions, MMA web sites and prior UFC-related academic literature. Findings – A number of significant growth dynamics are identified, including interconnections between the increase in free-to-air events and the generation of new UFC fans and revenues; the increased financial rewards to successful fighters that allows them to improve the quality of their training and the improved quality of UFC content; and the accumulation of a critical mass of high-level fighters that increases the reputation of the UFC and the increased attraction of new fighters to the organisation. Research limitations/implications – Further in depth studies are necessary to substantiate and quantify the interconnections identified in this paper. Practical implications – The paper provides insights for other non-mainstream sports organisations that are attempting to grow their participation and viewership. Originality/value – The emergence of new sports and sports organisations such as the UFC with global appeal and significant commercial returns is infrequent. This study contributes to the need for understanding of how new sports enter the mainstream and the role that governing organisations such as the UFC play in achieving this transition.

scholarly journals ACS Publications — Ensuring XML Quality

2012 ◽  
Author(s):  
Tamara Stoker ◽  
Keith Rose
Keyword(s):  
American Chemical Society ◽  
Chemical Society ◽  
Publication Time ◽  
High Level ◽  
Publication Workflow ◽  
Very High

The benefits of using XML in publishing are widely known but those benefits are more difficult to attain if the quality of the XML produced by the process is not consistently at a very high level. This case study outlines the steps that the American Chemical Society (“ACS”) has taken both in-house and in collaboration with the vendor to which we have outsourced portions of our publication workflow. In addition to producing predictable XML, these efforts have also improved our publication time.

scholarly journals Pemetaan Siswa Berprestasi Menggunakan Metode K-Means Clustring

JURTEKSI ◽  
2017 ◽  
Vol 4 (1) ◽  
pp. 85-92
Author(s):  
Mustika Larasati Sibuea ◽  
Andy Safta
Keyword(s):  
Data Mining ◽  
Student Achievement ◽  
Manhattan Distance ◽  
Data Set ◽  
Euclidian Distance ◽  
Student Failure ◽  
Human Resources Information Systems ◽  
High Level

Abstract: The high level of student success and the low level of student failure is a quality of the education world. The world of education is currently required to have the ability to compete by utilizing all resources owned. In addition to facilities, infrastructure and human resources, information systems are one of the resources that can be used to improve competency skills. Data mining is a process of data analysis to find a dataset of data set. Data mining is able to analyze large amounts of data into information that has meaning for decision supporters. One process of data mining is clustring. Attributes used in the grouping of student achievement are Name, Extracurricular, Value which include Task Value, Uts Value, Value of Uses, total absenteeism, and Attitude value. The case study of 20 students with distance calculation using manhattan distance, chbychep distance and euclidian distance yielded 67% accuracy. Keywords: data mining, clustering, k-means, student achievement Abstrak: Tingginya tingkat keberhasilan siswa dan rendahnya tingkat kegagalan siswa merupakan cemin kualitas dunia pendidikan.Dunia pendidikan saat ini dituntut untuk memiliki kemampuan bersaing dengan memanfaatkan semua sumber daya yang dimiliki. Selain sumber daya sarana, prasarana dan manusia, sistem informasi merupakan salah satu sumber daya yang dapat digunakan untuk meningkatkan kemampuan barsaing. Data mining merupakan proses analisa data untuk menemukan suatu pola dara kumpulan data. Data mining mampu menganalisa jumlah data yang besar menjadi informasi yang mempunyai arti bagi pendukung keputusan. Salah satu proses data mining adalah clustring. Atribut yang digunakan dalam pengelompokan prestasi siswa adalah Nama, Ekstrakulikuler, Nilai yang meliputi Nilai Tugas, Nilai Uts, Nilai Uas, jumlah ketidak hadiran siswa (absensi), dan Nilai sikap. Studi kasus pada 20 siswa dengan perhitungan jarak menggunakan manhattan distance, chbychep distance dan euclidian distance menghasilkan akurasi sebesar 67%. Kata kunci: data mining, clustering, k-means, prestasi siswa

Pupil diameter dynamics as an indicator of the respondent’s cognitive load: Methodological experiment comparing CASI and P&PSI

2021 ◽  
Vol 21 (1) ◽  
pp. 36-49
Author(s):  
I. F. Deviatko ◽  
M. B. Bogdanov ◽  
D. V. Lebedev
Keyword(s):  
Cognitive Load ◽  
Interpersonal Communication ◽  
Survey Data ◽  
Computer Literacy ◽  
Initial Assessment ◽  
General Interest ◽  
Computer Assisted ◽  
Eye Tracker ◽  
High Level

In recent years, the increase in general interest in methods for measuring cognitive load and subjectively perceived mental effort when solving various tasks and in the interpersonal communication was accompanied by an increase in the specific interest of social researchers in the multimodal assessment of the cognitive load of interviewers and respondents based on objective and subjective indicators, including paradata and webcam data, in order to control this loads impact on the quality of survey data. The authors argue that the possibilities of relatively new approaches to measuring cognitive load with neurophysiological methods (such as the use of wearable devices for oculography - eye tracking and pupillometry - which do not disrupt the natural course of respondents and interviewers activity) are still underestimated, although they allow an accurate time linkage of measured parameters dynamics (primarily the size of the pupil) to the question format, mode and phase of survey completion, external influences localized in time, etc. As a rule, quantitative studies of surveys cognitive load and its possible impact on the quality of survey data focus on computer-assisted (CAPI) or paper-based (PAPI) interviewing, while the specificity of the cognitive load in the self-completed computerized (CASI) and paper (PPSI) surveys was not studied. The article presents the results of the methodological experiment based on a modified version of the multimodal approach to the comparative assessment of the cognitive load of interviewers working with paper and computerized questionnaire. We expanded the range of methods for assessing cognitive load by using a wearable oculographic device (eye tracker) to measure the dynamics of pupil size when answering different survey questions. The results of the experiment confirmed the hypothesis about the approximate equivalence of the two modes of survey completion in terms of their cognitive load for younger respondents with a high level of functional computer literacy, and allowed an initial assessment of the technical and metrological capabilities and limitations of the use of pupil dynamics indicators, measured with a wearable oculographic device, to study the respondents cognitive load.

Analysis of Dynamics Competitiveness by Using Strategic Groups Maps

2018 ◽  
Vol 5 (3) ◽  
pp. 52-66
Author(s):  
Hamed Aboutorab ◽  
Alireza Aslani ◽  
Mohsen Nazari
Keyword(s):  
Market Analysis ◽  
Economic Conditions ◽  
Strategic Analysis ◽  
Furniture Industry ◽  
Strategic Group ◽  
The World ◽  
Analysis Of Dynamics ◽  
High Level

This chapter describes how in today's competitive world, the survival of businesses is highly dependent on satisfying the customers and responding to their demands. The furniture industry is one of the markets that consists high level of competition and customers in different groups. The industry has a rapid growth by improving the economic conditions and quality of life in the world. However, the capability and competitiveness of suppliers and retailers for domestic and imported products are a big challenge. This brings the importance of the strategic analysis approach to the industry. The aim of this article is to implement strategic group maps to understand the dynamics of the furniture market in a selected case study. The used method is the first in the furniture industry and the market analysis is based on the both suppliers/retailers and customers' viewpoints. The outputs show the furniture industry can be categorized in the five groups with specific required demand and strategy in each group.

scholarly journals Upstream to downstream: a multiple-assessment-point approach for targeting non-point-source priority management areas at large watershed scale

2014 ◽  
Vol 18 (4) ◽  
pp. 1265-1272 ◽  
Author(s):  
L. Chen ◽  
Y. Zhong ◽  
G. Wei ◽  
Z. Shen
Keyword(s):  
Point Source ◽  
Large Scale ◽  
Cost Effective ◽  
Small Scale ◽  
Nps Pollution ◽  
Specific Assessment ◽  
High Level ◽  
Multiple Assessment

Abstract. The identification of priority management areas (PMAs) is essential for the control of non-point-source (NPS) pollution, especially for a large-scale watershed. However, previous studies have typically focused on small-scale catchments adjacent to specific assessment points; thus, the interactions between multiple river points remain poorly understood. In this study, a multiple-assessment-point PMA (MAP-PMA) framework was proposed by integrating the upstream sources and the downstream transport aspects of NPS pollution. Daning River watershed was taken as a case study in this paper, which has demonstrated that the integration of the upstream input changes was vital for the final PMAs map, especially for downstream areas. Contrary to conventional wisdom, this research recommended that the NPS pollutants could be best controlled among the upstream high-level PMAs when protecting the water quality of the entire watershed. The MAP-PMA framework provided a more cost-effective tool for the establishment of conservation practices, especially for a large-scale watershed.

Sign in / Sign up

Export Citation Format

Share Document