Downloads & Free Reading Options - Results

In a previous study, multiple regression techniques were applied to Flight Operations Quality Assurance-derived data to develop parsimonious model(s) for fuel consumption on the Boeing 757 airplane. The present study examined several data mining algorithms, including neural networks, on the fuel consumption problem and compared them to the multiple regression results obtained earlier. Using regression methods, parsimonious models were obtained that explained approximately 85% of the variation in fuel flow. In general data mining methods were more effective in predicting fuel consumption. Classification and Regression Tree methods reported correlation coefficients of .91 to .92, and General Linear Models and Multilayer Perceptron neural networks reported correlation coefficients of about .99. These data mining models show great promise for use in further examining large FOQA databases for operational and safety improvements.

In a previous study, multiple regression techniques were applied to Flight Operations Quality Assurance-derived data to develop parsimonious model(s) for fuel consumption on the Boeing 757 airplane. The present study examined several data mining algorithms, including neural networks, on the fuel consumption problem and compared them to the multiple regression results obtained earlier. Using regression methods, parsimonious models were obtained that explained approximately 85% of the variation in fuel flow. In general data mining methods were more effective in predicting fuel consumption. Classification and Regression Tree methods reported correlation coefficients of .91 to .92, and General Linear Models and Multilayer Perceptron neural networks reported correlation coefficients of about .99. These data mining models show great promise for use in further examining large FOQA databases for operational and safety improvements.

This article is from PLoS ONE , volume 9 . Abstract Introduction: For many organizations, limited budgets and phased funding restrict the development of digital health tools. This problem is often exacerbated by the ever-increasing sophistication of technology and costs related to programming and maintenance. Traditional development methods tend to be costly and inflexible and not client centered. The purpose of this study is to analyze the use of Agile software development and outcomes of a three-phase mHealth program designed to help young adult Quebecers quit smoking. Methods: In Phase I, literature reviews, focus groups, interviews, and behavior change theory were used in the adaption and re-launch of an existing evidence-based mHealth platform. Based on analysis of user comments and utilization data from Phase I, the second phase expanded the service to allow participants to live text-chat with counselors. Phase II evaluation led to the third and current phase, in which algorithms were introduced to target pregnant smokers, substance users, students, full-time workers, those affected by mood disorders and chronic disease. Results: Data collected throughout the three phases indicate that the incremental evolution of the intervention has led to increasing numbers of smokers being enrolled while making functional enhancements. In Phase I (240 days) 182 smokers registered with the service. 51% (n = 94) were male and 61.5% (n = 112) were between the ages of 18–24. In Phase II (300 days), 994 smokers registered with the service. 51% (n = 508) were male and 41% (n = 403) were between the ages of 18–24. At 174 days to date 873 smokers have registered in the third phase. 44% (n = 388) were male and 24% (n = 212) were between the ages of 18–24. Conclusions: Emerging technologies in behavioral science show potential, but do not have defined best practices for application development. In phased-based projects with limited funding, Agile appears to be a viable approach to building and expanding digital tools.

This paper presents a (semi-)automatic processing technique for GPR data analysis. Exploiting the generalization capabilities of artificial neural networks (ANN), it will be shown that it is possible to feed a Multi-Layer Perceptron (MLP) with a suitable set of input features in order to determine the permittivity of a ground layer. A detailed performance assessment have proven that the algorithm provides very promising results, reconstructing with high accuracy the dielectric properties of both planar and rough surfaces. Some critical issues have anyway emerged that limit the effectiveness of the method to lossless media.

Polygamy remains one of the interesting key topics in various society, especially Indonesia. P olygamy is the act of marrying multiple spouses that means having more one wife at the same time, is common case in worldwide. In this problem, the most of Muslim in Indonesia adopt Islamic l aw that let men to do the polygamy with certain requirements. In worldwide communities, this has been a prominent feature and has become the subject of numerous books, heated debates, journal articles, discussion papers , and so on. Furthermore, in Indonesia the polygamous marriage has recently become a heated topic. Despite controversy, Indonesia’s law, of recent, allows people for doing polygamy in certain conditions. Because the polygamy is often debated, this study focuses on assessment of Indonesian’s perceptions through s entiment a nalysis and would determine people’s perception about polygamy issue from 500 tweets on Twitter. T o conclude, it elucidates that the polygamy in Indonesia is a normal thing and few assume the case is as negative thing.

Advances in the fields of simulation and data mining are proving relevant to providing battlespace decision support. High performance computing, improved modeling techniques, and new decision support methodologies drive these advances. Combat simulations now generate behaviors at increasingly finer scales. Data mining provides a mechanism for uncovering key patterns in larger data sets such as those generated by modern combat simulations. The capability of simulating detailed courses of action (COAs) opens up the possibility of mining collected data for insights. Specifically, decision support systems could assist commanders in examining simulation data for relationships between the structure of the COA and various battle objectives. Our current experimentation centers on the use of complex or urban terrain for warfighting. The synergy of data mining tools, high performance computing, and high resolution simulation has the potential to assist battle planners in the improvement of battlefield assessments and the expedient modification of COAs.

The use of data mining and machine learning tools is becoming increasingly common. Their usefulness is mainly noticeable in the case of large datasets, when information to be found or new relationships are extracted from information noise. The development of these tools means that datasets with much fewer records are being explored, usually associated with specific phenomena. This specificity most often causes the impossibility of increasing the number of cases, and that can facilitate the search for dependences in the phenomena under study. The paper discusses the features of applying the selected tools to a small set of data. Attempts have been made to present methods of data preparation, methods for calculating the performance of tools, taking into account the specifics of databases with a small number of records. The techniques selected by the author are proposed, which helped to break the deadlock in calculations, i.e., to get results much worse than expected. The need to apply methods to improve the accuracy of forecasts and the accuracy of classification was caused by a small amount of analysed data. This paper is not a review of popular methods of machine learning and data mining; nevertheless, the collected and presented material will help the reader to shorten the path to obtaining satisfactory results when using the described computational methods.

Indonesian people prefer private schools with high prices, which is one of the exciting things to study. In fact, in the modern era, public schools have competed with private schools with international categories. The problem in public schools is the parent's perspective on the quality of education in public schools, especially public madrasahs. In addition, cases such as bullying and violence between schools. People on Twitter also have various perceptions of public madrasas, which are considered to have religiosity. This research uses the keywords public madrasah, quality management, and quality taken from Twitter using the Orange application. The amount of data in this research is 300 tweets from Twitter. As a result, there are both negative and positive sentiments toward public madrasas. However, the negative sentiment is higher than the positive sentiment. This means parents have more trust in private schools than in public madrasahs.

Data mining seems to be a promising way to tackle the problem of unpredictability in MRO organizations. The Amsterdam University of Applied Sciences therefore cooperated with the aviation industry for a two-year applied research project exploring the possibilities of data mining in this area. Researchers studied more than 25 cases at eight different MRO enterprises, applying a CRISP-DM methodology as a structural guideline throughout the project. They explored, prepared and combined MRO data, flight data and external data, and used statistical and machine learning methods to visualize, analyse and predict maintenance. They also used the individual case studies to make predictions about the duration and costs of planned maintenance tasks, turnaround time and useful life of parts. Challenges presented by the case studies included time-consuming data preparation, access restrictions to external data-sources and the still-limited data science skills in companies. Recommendations were made in terms of ways to implement data mining – and ways to overcome the related challenges – in MRO. Overall, the research project has delivered promising proofs of concept and pilot implementations

110 Applied Data Mining