Data-based Decision Research Articles

Success Driven: Student Motivation Actions in Teaching and Learning

The purpose of this topic is to add to the body of good teaching and learning that helps create the conditions for more critical thinking and practice skills that enable, keep students interested, and consistently motivate them. Teachers now have a greater focus on implementing motivational learning and studying strategies that are more relevant to the processes of teaching and learning thanks to new methodologies, which have further enhanced instructional strategies for teaching and learning. Positive school cultures that are long-lasting will result from these new methods and strategies. According to the authors, educators have been impacted by evidence-based practice and data-based decision making within the educational system. As a result, there is a growing need for educators to learn more about these resources that are relevant to students and can lead to greater success. These applicable interventions have a positive effect on students, and the information that helps them make decisions increases their response.

Role of inclusion for education

There has long been a need for all students, regardless of their requirements or the capacity of their teachers to satisfy those needs, to be included in public education. Despite substantial study on Each countryfies of data-based decision making, there is little empirical evidence to support complete inclusion for all students and much less information on the importance of data-based decision making in inclusive education especially. There is a lot of information on data-based decision making and how it may be used to assist decisions for children with reading impairments and people with intellectual disabilities who are moving into adulthood in this article. Evidence-based methods for boosting reading and transition are examined in connection to the reality of implementing these activities in inclusive educational environments. Data-based decision-making in inclusive environments is also highlighted.

Anaplasma ovis Prevalence Assessment and Cross Validation Using Multiparametric Screening Approach in Sheep from Central Tunisia.

We conducted a 5-month-long screening of Anaplasma spp. and Anaplasma ovis infection in sheep from central Tunisia. During this longitudinal study, we investigated the infection dynamics using both direct and indirect assessments validated with a polymerase chain reaction (PCR) as the gold standard method. The experimental design included 84 male lambs aged from 6 to 8 months, and 32 ewes, both chosen randomly from June to November with a periodicity of 2 weeks approximately between June and September, and 1 month between September and November. A total of 9 field visits were carried out in this period during which animals were clinically examined and biological samples were extracted. Thus, a total of 716 blood smears, 698 sera from the nine sampling dates, as well as 220 blood samples from the first and the ninth sampling dates were collected from apparently healthy lambs and ewes, respectively, and analyzed by competitive enzyme-linked immunosorbent assay (cELISA) and polymerase chain reaction (PCR) assay, for the detection of Anaplasma antibodies and A. ovis DNA, respectively. Sera were analyzed by competitive enzyme-linked immunosorbent assay (cELISA) and PCR, for the detection of Anaplasma antibodies and A. ovis DNA, respectively. The Anaplasma spp. initial seroprevalence rate was 33.3% in lambs and 100% in ewes, and it then flowed in an upward trend to reach a maximum of 52.6% in lambs, whereas in ewes, the Anaplasma spp. seroprevalence rate remained unchanged and equal to 100%. Meanwhile, the A. ovis initial molecular prevalence was 22.6% at the first visit and 26.3% at the last visit in lambs, whereas in ewes, the molecular prevalence rates of A. ovis were higher in both the first and the last visit estimated at 100% and 85.7%, respectively. The Kappa coefficient between cELISA and PCR indicated a moderate level of agreement on the first sampling date (0.67) and a low agreement level on the last (0.43). Furthermore, an exploratory data analysis using a multimodal machine learning approach highlighted the underlying pattern of each analytical technique used in this study. In this prospect, we were able to establish the performance of each technique at detecting Anaplasma spp. in sheep. The combination of these approaches should improve the field assessment while promoting a data-based decision in precision epidemiology. The genetic follow-up test relevant to A. ovis msp4 sequences revealed three different genotypes, two of which were previously described in Italy.

Logical coherence in Bayesian simultaneous three-way hypothesis tests

Hypothesis testing is a key component in Statistics. In practice, it is common for a practitioner to test several hypotheses, the so-called simultaneous hypothesis testing problem. Unfortunately, simultaneous hypothesis tests can be logically incoherent: for instance, if hypothesis H1 implies hypothesis H2, a procedure that rejects H2 should also reject H1, a property not always met by multiple test procedures. Indeed, previous results show that standard two-way hypothesis tests cannot be logically coherent. Three-way tests allow more nuanced data-based decisions. This paper studies whether Bayesian simultaneous three-way hypothesis tests can be logically coherent. Two types of results are obtained. First, under the standard error-wise constant loss, only for a limited set of models a Bayes simultaneous test can be logically coherent. Second, if more general loss functions are used, then it is possible to obtain Bayes simultaneous tests that are always logically coherent. An explicit example of such a loss function is provided. These results provide guidelines on how to build a logically coherent posterior probability three-way hypothesis test or more general Bayesian three-way hypothesis tests.

The Benefits of Learning Analytics for Education: An Analysis of the Experiences of Lithuanian General Education School Teachers

The article discusses the benefits of learning analytics for education: the theoretical part reveals the concept of learning analytics, discusses how learning analytics technologies help to improve the teaching / learning process. The focus is on the most important group of learning analytics beneficiaries - teachers. The benefits of learning analytics in teachers’ pedagogical work are discussed. The empirical part of the article presents the results of a qualitative study for the analysis of teachers’ experiences. The study involved 17 teachers from Lithuanian general education schools with experience in working with learning analytics tools. The semi-structured interview method allowed to gather the research participants’ insights into the use of learning analytics in Lithuanian schools from the perspective of teachers. Qualitative analysis of the content of the informants’ answers revealed teachers’ opinion on the benefits of learning analytics for teaching and learning, teachers’ competencies to work with learning analytics tools, empowering teachers to use learning analytics tools and to make data-based pedagogical decisions.

Multilevel and empirical reliability estimates of learning growth: A simulation study and empirical illustration

Reliable learning progress information is crucial for teachers’ interpretation and data-based decision making in everyday classrooms. Slope estimates obtained from simple regression modeling or more complex latent growth models are typically used in this context as indicators of learning progress. Research on progress monitoring has used mainly two ways to estimate reliability of learning progress, namely (a) split-half reliability and (b) multilevel reliability. In this work we introduce empirical reliability as another attractive alternative to quantify measurement precision of slope estimates (and intercepts) in learning progress monitoring research. Specifically, we extended previous work on slope reliability in two ways: (a) We evaluated in a simulation study how well multilevel reliability and empirical reliability work as estimates of slope reliability, and (b) we wanted to better understand reliability of slopes as a latent variable (by means of empirical reliability) vs. slopes as an observed variable (by means of multilevel reliability). Our simulation study demonstrates that reliability estimation works well over a variety of different simulation conditions, while at the same time conditions were identified in which reliability estimation was biased (i.e., with very poor data quality, eight measurement points, and when empirical reliability was estimated). Furthermore, we employ multilevel reliability and empirical reliability to estimate reliability of intercepts (i.e., initial level) and slopes for the quop-L2 test. Multilevel and empirical reliability estimates were comparable in size with only slight advantages for latent variable scores. Future avenues for research and practice are discussed.

Empty Houses, Loose Dogs, and Engaged Citizens: Lessons Learned From Community Participatory Data Collection in Rural Areas.

Rural surveys tend to oversample easy to reach populations, which can misrepresent community health needs. To achieve baseline data reflective of the communities served by the high obesity program (HOP), an innovative evaluation plan was created to prioritize equity and reflect the whole community. Principles of Community-Based Participatory Research (CBPR) were used to guide instrument development, research protocols, and data collection. A random sample of addresses created with United States Postal Service records provided a representative list of addresses in three HOP counties in Louisiana. Local data collectors were recruited to go door to door at the selected addresses to collect in-person surveys (N = 682; response rate of 84%). Over a quarter of participants reported using the charitable food system and walking for transportation at least weekly. Collecting door to door data in rural communities presents unique challenges, including abandoned properties, inaccurate address records, loose dogs, and at times, racial tensions and houses far removed from public roads. Lessons learned include the importance of local knowledge, adapting protocols to fit local conditions, and community awareness of the survey. Health practitioners need confidence when they are making data-based decisions about interventions, and one way to provide this confidence is to collect data from a true cross-section of the community. With a plan and in partnership with community members, a probability sample is feasible to collect in rural communities.

6.G. Workshop: The European Health Data Space 2: is Europe ready to maximise the re-use of health data?

Abstract The EU's Heads of State called in October 2020 to set up a European Health Data Space (EHDS): “The European Council welcomes the creation of common European data spaces in strategic sectors, and in particular invites the Commission to give priority to the health data space”. As a response, multiple initiatives were set-up to engage the views and expectations from EU member states in the development of the upcoming legislative proposal on the EHDS for primary (EHDS1) and secondary use of health data (EHDS2). One of these was the launch of the Joint Action (JA) Towards the European Health Data Space (TEHDAS) in February 2021. The aim of TEHDAS is to support the European Commission (EC) and Member States (MS), identifying the challenges and providing concepts and options for the EHDS2. It is built on the needs and expectations of national and international stakeholders, citizens’ engagement and existing infrastructure. The major expected outcome of this JA is a sustainable roadmap towards the EHDS2 implementation promoting the cross-border sharing of health data for secondary use. The EHDS2 will benefit population health by facilitating the timely exchange of and access to health data, improving not only the care of patients but also facilitating research, epidemiology, disease prevention and data-based policy decisions. This workshop aims to provide an overview of the preparedness of MS to join the EHDS for secondary use of health data, covering current state-of-play of health data management systems in the EU, barriers on the secondary use of health data, the ongoing work on the development and deployment of the EHDS2 infrastructure and finally, how population health research can benefit from the EHDS2. The workshop will begin with a short introduction on the TEHDAS JA, followed by a presentation on the outcomes of the TEHDAS country visits. In these country visits, the state-of-play of the health data management system and the preparedness to join the EHDS2 were mapped in 12 different EU MS. The next presentation will continue with the results from a study that collected more evidence on the barriers to cross-border sharing of health data for secondary use and options on how to overcome these. It will focus on the legal preparedness and barriers and will discuss how the options proposed by experts in the field align with the legislative proposal for the EHDS2. The audience will be able to give their opinion on the different options through an interactive voting poll during the session. Some of the options on how to overcome technical barriers will be taken further in the development of a pilot infrastructure for the EHDS2. Therefore, the last two presentations will focus on the development and deployment of this pilot infrastructure for the EHDS2 and the role and benefits that population health research will have in it. Throughout the workshop there will be discussion sessions between presentations to allow exchange of knowledge, experiences and opinions with the audience. Key messages • The main outputs will support EU countries to prepare their health data management system for the EHDS2 based on the best practices and actions presented. • The presentations will inform and align participants on the current work on the technical EHDS infrastructure that is being developed for secondary use of health data, the EHDS2.

Building “First Expire, First Out” models to predict food losses at retail due to cold chain disruption in the last mile

Current less-than-truckload (LTL) shipping practices allow for temperature abuse (TA) in the last segment (last mile) of the food supply chain. When this TA is combined with “First In, First Out” product rotation methods, it could lead to food spoilage and food waste; therefore, data-based decision models are needed to aid retail managers. An experiment was designed using pallets (4 layers/pallet × 5 boxes/layer) of commercially produced boneless chicken breast filet trays. The pallets were exposed to 24 h of simulated LTL TA (cyclic 2 h at 4°C, then 2 h at 23 ± 2°C). Filet temperatures were recorded for all 20 boxes using dataloggers with thermocouple wires. Additionally, microbiological sampling of filets [aerobic plate counts (APC) and psychrotrophic plate counts (PSY)] was conducted before (0 h of LTL TA) and after (24 h of LTL TA) the TA experiment for select boxes of the pallet and compared to control filets (maintained at 4°C). After TA, a shelf-life experiment was conducted by storing filets from predetermined boxes at 4°C until spoilage (7 log CFU/ml). Temperature and microbiological data were augmented using Monte Carlo simulations (MC) to build decision making models using two methods; (1) the risk of each box on the pallet reaching the bacterial “danger zone” (>4°C) was determined; and (2) the risk-of-loss (shelf-life < 4 days; minimum shelf-life required to prevent food waste) was determined. Temperature results indicated that boxes on the top and bottom layers reached 4°C faster than boxes comprising the middle layers while the perimeter boxes of each layer reached 4°C faster than centrally located boxes. Shelf-life results indicate simulated LTL TA reduced shelf-life by 2.25 and 1.5 days for APC and PSY, respectively. The first MC method showed the average risk of boxes reaching 4°C after 24 h of simulated LTL TA were 94.96%, 43.20%, 27.20%, and 75.12% for layers 1–4, respectively. The second MC method indicated that exposure at >4°C for 8 h results in a risk-of-loss of 43.8%. The findings indicate that LTL TA decreases shelf-life of chicken breast filets in a heterogenous manner according to location of boxes on the pallet. Therefore, predictive models are needed to make objective decisions so that a “First Expire, First Out” method can be implemented to reduce food wastes due to TA during the last mile.

Machine Learning to Predict the Interfacial Behavior of Pesticide Droplets on Hydrophobic Surfaces for Minimizing Environmental Risk

Achieving accurate and efficient target deposition of pesticide droplets is the principal factor in minimizing environmental risk. For hydrophobic surfaces, adding tank-mix adjuvants containing surfactants to modulate interfacial behavior is warranted, which lacks common laws to guide practical applications directly. Machine learning is developing rapidly and makes many data-based decisions in various industrial processes. Hence, according to machine learning-based analysis of fundamental physical quantities, proposing quantitative sustainability metrics to improve interface behavior is essential. Comparing the interfacial behavior of five adjuvants, the common denominator is that droplets in the Wenzel state with higher adhesion tension and lower contact angles can generate the pinning force that causes energy dissipation, reduces pesticide losses, and weakens environmental pollution. Simultaneously, the interfacial behavior of pesticide droplets including adjuvants on citrus leaves is verified, while the phytotoxicity experiment under high temperature and the laboratory bioassay are carried out. The results show that the eco-friendly alkyl polyglycoside (APG) as the glycosidic surfactant has nontarget biosafety and better mite control, which can be exploited as a commercial tank-mix adjuvant for promotion. This study provides a new insight into guiding adjuvants added to pesticides on account of quantitative sustainability metrics, which has important implications for food safety and agricultural green development.

Difficulties and Countermeasures of Game Localization Translation Based on the IoT and Big Data

With the development of international social facilitation brought about by the technological progress of various social media, games are spread internationally as a key application for entertainment and social interaction. At present, my country has introduced more than tens of thousands of games from abroad. There are cultural differences and grammatical differences between different countries. The introduced game dubbing and NPC subtitles are not completely the same as the meaning of the country of origin of the game. The result of the incomprehensible words usually makes the game player unable to understand part of the game in the game, while affecting the game experience; it also hinders international cultural exchanges and curbs the strategic expansion of game companies. Big data technology is an inevitable product of the rapid development of data science. It uses various data collection, data storage, and data analysis tools to provide data-based decision support for users in need. The data plane provides tool support for translation. IoT technology relies on various sensors and microdevices to collect status information of different things. IoT devices all have a central server. Currently, game companies translate overseas games through teamwork. Using IoT devices, teams can translate status and progress information, stored in the server to support the progress control of game localization translation. This paper firstly conducts a survey on the questionnaires issued by the translation team leaders of multinational game companies, conducts statistical processing on the collected data, analyzes and summarizes the difficulties existing in the current game localization translation, and finally designs a corresponding game based on big data and Internet of Things technology. In localization translation strategy, through follow-up investigations on companies that have adopted the strategy, it is found that the dilemma of game localization translation has been solved.

Data-based decision-making in schools: Examining the process and effects of teacher support.

Data-based decision-making in schools: Examining the process and effects of teacher support.

Developing an online system to support algebra progress monitoring: Teacher use and feedback

A brief overview of the development of an online system to support algebra progress monitoring across several years of an iterative process of development, feedback, and revision is provided. Online instructional modules addressed progress monitoring concepts and procedures; administration and scoring of three types of algebra measures, including teacher accuracy with scoring; and navigation and use of the online data management system, including data entry, graphing, and skills analyses. In the final year of this federally funded research project, a test of the functionality of the completed system as well as an evaluation of teachers’ knowledge, accuracy, and satisfaction with the online professional development was evaluated. Specifically, 29 general and special education secondary school teachers completed 11 fully developed online instructional modules independently and administered weekly two of three types of algebra measures across 10 weeks with one of their classes of students. Data analysis included teacher accuracy in the scoring of the measures; change in their knowledge of student progress monitoring and data-based decision making; and teacher satisfaction with the online system, including instructional content, feasibility, and usability for data-based decision making. Directions for future research and implications for classroom use of this online system are discussed.

Understanding and improving teachers’ graph literacy for data-based decision-making via video intervention

In the educational context, graph literacy describes the competence to read, comprehend, and interpret formative assessment data in terms of data-based decision-making (DBDM) in order to derive and justify individual adaptations of instruction based on them. Since misconceptions may arise in predicting a future learning progress due to the characteristics of the data base as well as the approach to graph literacy, effective supports are needed, especially for inexperienced teachers. We present two interrelated studies to broaden the field of support in graph literacy. In Study I, graph literacy procedures are collected fromN= 196 university student teachers using an online survey that includes six case vignettes with learning progress prediction tasks. Results show that both regular and special education student teachers intuitively neglect important data points in interpretation and they do not use a consistent strategy in prediction across the case vignettes (Fleiss’ κ = 0.071;p< 0.001). Building on the results of Study I, a 3-min video intervention for linear trend identification using Tukey Tri-Split was developed. Study II tested the efficacy of the video intervention on the accuracy of future learning progress among student teachers and in-service teachers (N= 198) using randomized group assignment compared to a brief text hint. With a large effect size of Cohens’f= 0.39, the video instruction shows high efficacy compared to the text hint. The increasing importance of DBDM in inclusive and special education is discussed.

Rapid Text Retrieval and Analysis Supporting Latent Dirichlet Allocation Based on Probabilistic Models

Text mining, also known as text analysis, is the process of converting unstructured text data into meaningful and functional information. Text mining uses different AI technologies to automate data and generate valuable insights, allowing enterprises to make data-based decisions. Text mining enables the user to extract important content from text data sets. Text analysis encourages machine learning ability for research areas such as medical and pharmaceutical innovation fields. Apart from this, text analysis converts inaccessible data into a structured format, which can be used for further analysis. Text analysis emphasizes facts and relationships from large data sets. This information is extracted and converted into structured data for visualization, analysis, and integration as structured data and refines the information using machine-learning methods. Like most things related to Natural Language Processing, text mining can seem like a difficult concept to understand. But the fact is, it does not have to be. This research article will go through the basics of text mining, clarify its different methods and techniques, and make it easier to understand how it works. We implemented Latent Dirichlet Allocation techniques for mining the data from the data set; it works properly and will be in future development data mining techniques.

Technical Features and Trends of Data Science in Financial Engineering

In the new financial era, the huge amount of data brings more challenges to the traditional financial business and creates unprecedented opportunities at the same time. In the financial industry, the use of data science by financial institutions has significantly deepened, from the traditional "data visualization presentation" to "data-based decision analysis". This paper analyzes the technical characteristics and development trend of data science in financial engineering against the background of rapid development of financial technology.

Individual, generalized, and moderated effects of the good behavior game on at-risk primary school students: A multilevel multiple baseline study using behavioral progress monitoring

The current study examined the impact of the Good Behavior Game (GBG) on the academic engagement (AE) and disruptive behavior (DB) of at-risk students’ in a German inclusive primary school sample using behavioral progress monitoring. A multiple baseline design across participants was employed to evaluate the effects of the GBG on 35 primary school students in seven classrooms from grade 1 to 3 (Mage = 8.01 years, SDage = 0.81 years). The implementation of the GBG was randomly staggered by 2 weeks across classrooms. Teacher-completed Direct Behavior Rating (DBR) was applied to measure AE and DB. We used piecewise regression and a multilevel extension to estimate the individual case-specific treatment effects as well as the generalized effects across cases. Piecewise regressions for each case showed significant immediate treatment effects for the majority of participants (82.86%) for one or both outcome measures. The multilevel approach revealed that the GBG improved at-risk students’ classroom behaviors generally with a significant immediate treatment effect across cases (for AE, B = 0.74, p < 0.001; for DB, B = –1.29, p < 0.001). The moderation between intervention effectiveness and teacher ratings of students’ risks for externalizing psychosocial problems was significant for DB (B = –0.07, p = 0.047) but not for AE. Findings are consistent with previous studies indicating that the GBG is an appropriate classroom-based intervention for at-risk students and expand the literature regarding differential effects for affected students. In addition, the study supports the relevance of behavioral progress monitoring and data-based decision-making in inclusive schools in order to evaluate the effectiveness of the GBG and, if necessary, to modify the intervention for individual students or the whole group.

지방교육청의 재정운용 유형화 연구

There are growing concerns about efficient fiscal management and expenditure structure due to the decline of the school-age population, the expansion of educational autonomy, and the increase of block grant in education finance. The local education financial analysis system has been developed to fulfill fiscal responsibility and evaluate the efficiency and performance of fiscal management, but research on the operational performance and development potential of this system is insufficient. This study analyzed the financial soundness and financial efficiency index of the local school district based on the financial index of the local education finance analysis system through cluster analysis, a machine learning unsupervised learning approach. A result of the analysis reveals that heterogeneous clustering by financial indicators of local education offices was found, and this offers implications on how policy can be improved such as simplification of financial analysis indicators and data-based decision-making was presented.

Evolved model for early fault detection and health tracking in marine diesel engine by means of machine learning techniques

The Coast Guard Command, which has a wide range of duties as saving human lives, protecting natural resources, preventing marine pollution and battle against smuggling, uses diesel main engines in its ships, as in other military and commercial ships. It is critical that the main engines operate smoothly at all times so that they can respond quickly while performing their duties, thus enabling fast and early detection of faults and preventing failures that are costly or take longer to repair. The aim of this study is to create and to develop a model based on current data, to select machine learning algorithms and ensemble methods, to develop and explain the most appropriate model for fast and accurate detection of malfunctions that may occur in 4-stroke high-speed diesel engines. Thus, it is aimed to be an exemplary study for a data-based decision support mechanism.

The power of local research to inform adverse childhood experiences in substance use prevention in adolescents and adults

BackgroundThe impact of adverse childhood experiences on substance use has been well reported, however, less well documented is looking at the comparison of youth and adult substance use and their respective adverse childhood experiences. This study leveraged local data sources to support prevention efforts inside a state-level working group and examined research questions that explored the relationship between reported adverse childhood experiences and substance use for youth and adult samples at the state level.MethodsThis study conducted a series of logistic regression models (95% CI) between substance use outcomes with different age group populations to investigate the relationship between adverse childhood experiences and substance use for each group. Adverse childhood experiences scores and substance use were examined using two Arizona datasets: 1) Arizona Youth Survey (n = 42,009) and 2) the Behavioral Risk Factor Surveillance System (n = 5328).ResultsThe results of youth and adult datasets were consistent: users with adverse childhood experiences scores of 4 to 6 had a positive association with more substance use. When the variables were examined, showing the entire sample of youth and adult groups compared to those subgroups with a score of zero, a score of 1 to 3, and a score of 4 to 6, the overall pattern was the same; the more frequent use of substances was directly associated to the group with higher scores. Additionally, findings support increased attention on prevention and intervention efforts with higher reports of adverse childhood experiences as well as substance use.ConclusionsThese findings demonstrate how local research can help prioritize prevention resources and increase the value of data-based decision-making. Policy-makers and providers can examine youth and adult data to compare priorities and assess for planning purposes. Specifically, it is possible to replicate known research findings, identify the most impacted subpopulations, and forecast the community’s future needs.