Academic literature on the topic 'MACHINE LEARNING TOOL'

Uma das mudanças trazidas pela Web 2.0 é a maior participação dos usuários na produção do conteúdo, através de opiniões em redes sociais ou comentários nos próprios sites de produtos e serviços. Estes comentários são muito valiosos para seus sites pois fornecem feedback e incentivam a participação e divulgação do conteúdo. Porém excessos podem ocorrer através de comentários com palavrões indesejados ou spam. Enquanto para alguns sites a própria moderação da comunidade é suficiente, para outros as mensagens indesejadas podem comprometer o serviço. Para auxiliar na moderação dos comentários foi construída uma ferramenta que utiliza técnicas de aprendizado de máquina para auxiliar o moderador. Para testar os resultados, dois corpora de comentários produzidos na Globo.com foram utilizados, o primeiro com 657.405 comentários postados diretamente no site, e outro com 451.209 mensagens capturadas do Twitter. Nossos experimentos mostraram que o melhor resultado é obtido quando se separa o aprendizado dos comentários de acordo com o tema sobre o qual está sendo comentado.<br>One of the main changes brought by Web 2.0 is the increase of user participation in content generation mainly in social networks and comments in news and service sites. These comments are valuable to the sites because they bring feedback and motivate other people to participate and to spread the content. On the other hand these comments also bring some kind of abuse as bad words and spam. While for some sites their own community moderation is enough, for others this impropriate content may compromise its content. In order to help theses sites, a tool that uses machine learning techniques was built to mediate comments. As a test to compare results, two datasets captured from Globo.com were used: the first one with 657.405 comments posted through its site and the second with 451.209 messages captured from Twitter. Our experiments show that best result is achieved when comment learning is done according to the subject that is being commented.

In a fully automated manufacturing environment, instant detection of condition state of the cutting tool is essential to the improvement of productivity and cost effectiveness. In this paper, a tool condition monitoring system (TCM) via machine learning (ML) and machine ensemble (ME) approach was developed to investigate the effectiveness of multisensor fusion when machining 4340 steel with multi-layer coated and multi-flute carbide end mill cutter. Feature- and decision-level information fusion models utilizing assorted combinations of sensors were studied against selected ML algorithms and their majority vote ensemble to classify gradual and transient tool abnormalities. The criterion for selecting the best model does not only depend on classification accuracy but also on the simplicity of the implemented system where the number of features and sensors is kept to a minimum to enhance the efficiency of the online acquisition system. In this study, 135 different features were extracted from sensory signals of force, vibration, acoustic emission and spindle power in the time and frequency domain by using data acquisition and signal processing modules. Then, these features along with machining parameters were evaluated for significance by using different feature reduction techniques. Specifically, two feature extraction methods were investigated: independent component analysis (ICA), and principal component analysis (PCA) and two feature selection methods were studied, chi square and correlation-based feature selection (CFS). For various multi-sensor fusion models, an optimal feature subset is computed. Finally, ML algorithms using support vector machine (SVM), multilayer perceptron neural networks (MLP), radial basis function neural network (RBF) and their majority voting ensemble were studied for selected features to classify not only flank wear but also breakage and chipping. In this research, it has been found that utilizing the multisensor feature fusion technique under majority vote ensemble gives the highest classification performance. In addition, SVM outperformed other ML algorithms while CFS feature selection method surpassed other reduction techniques in improving classification performance and producing optimal feature sets for different models.

This thesis develops a method for using machine learning in a industrial pro-cess. The implementation of this machine learning model aimed to reduce costsand increase efficiency of train wheel overhaul in partnership with the AustrianFederal Railroads, Oebb. Different machine learning models as well as categoryencodings were tested to find which performed best on the data set. In addition,differently sized training sets were used to determine whether size of the trainingset affected the results. The implementation shows that Oebb can save moneyand increase efficiency of train wheel overhaul by using machine learning andthat continuous training of prediction models is necessary because of variationsin the data set.

This research is concerned with possible applications of e-Learning as an alternative to onsite training sessions when supporting the integration of machine learning into the product development process. Mainly, its aim was to study if e-learning approaches are viable for laying a foundation for making machine learning more accessible in integrated product development processes. This topic presents itself as interesting as advances in the general understanding of it enable better remote learning as well as general scalability of knowledge transfer. To achieve this two groups of employees belonging to the same corporate group but working in two very different geographical regions where asked to participate in a set of training session created by the authors. One group received the content via in-person workshops whereas the other was invited to a series of remote tele-conferences. After both groups had participated in the sessions, some member where asked to be interviewed. Additionally. The authors also arranged for interviews with some of the participants’ direct managers and project leaders to compare the participants’ responses with some stakeholders not participating in the workshops. A combination of a qualitative theoretical analysis together with the interview responses was used as the base for the presented results. Respondents indicated that they preferred the onsite training approach, however, further coding of interview responses showed that there was little difference in the participants ability to obtain knowledge. Interestingly, while results point towards e-learning as a technology with many benefits, it seems as though other shortcomings, mainly concerning the human interaction between learners, may hold back its full potential and thereby hinder its integration into product development processes.<br>Detta forskningsarbete fokuserar på tillämpningar av elektroniska utlärningsmetoder som alternativ till lokala lektioner vid integrering av maskininlärning i produktutvecklingsprocessen. Framförallt är syftet att undersöka om det går att använda elektroniska utlärningsmetoder för att göra maskininlärning mer tillgänglig i produktutvecklingsprocessen. Detta ämne presenterar sig som intressant då en djupare förståelse kring detta banar väg för att effektivisera lärande på distans samt skalbarheten av kunskapsspridning. För att uppnå detta bads två grupper av anställda hos samma företagsgrupp, men tillhörande olika geografiska områden att ta del i ett upplägg av lektioner som författarna hade tagit fram. En grupp fick ta del av materialet genom seminarier, medan den andra bjöds in till att delta i en serie tele-lektioner. När båda deltagargrupper hade genomgått lektionerna fick några deltagare förfrågningar om att bli intervjuade. Några av deltagarnas direkta chefer och projektledare intervjuades även för att kunna jämföra deltagarnas åsikter med icke-deltagande intressenter. En kombination av en kvalitativ teoretisk analys tillsammans med svaren från intervjuerna användes som bas för de presenterade resultaten. Svarande indikerade att de föredrog träningarna som hölls på plats, men vidare kodning av intervjusvaren visade på undervisningsmetoden inte hade större påverkningar på deltagarnas förmåga att ta till sig materialet. Trots att resultatet pekar på att elektroniskt lärande är en teknik med många fördelar verkar det som att brister i teknikens förmåga att integrera mänsklig interaktion hindrar den från att nå sitt fulla potential och därigenom även hindrar dess integration i produktutvecklingsprocessen.

In todays world, ontologies are being widely used for data integration tasks and solving information heterogeneity problems on the web because of their capability in providing explicit meaning to the information. The growing need to resolve the heterogeneities between different information systems within a domain of interest has led to the rapid development of individual ontologies by different organizations. These ontologies designed for a particular task could be a unique representation of their project needs. Thus, integrating distributed and heterogeneous ontologies by finding semantic correspondences between their concepts has become the key point to achieve interoperability among different representations. In this thesis, an advanced instance-based ontology matching algorithm has been proposed to enable data integration tasks in ocean sensor networks, whose data are highly heterogeneous in syntax, structure, and semantics. This provides a solution to the ontology mapping problem in such systems based on machine-learning methods and string-based methods.

Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2015.<br>This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.<br>Cataloged from student-submitted PDF version of thesis.<br>Includes bibliographical references (pages 71-74).<br>Critical discourse analysis (CDA) aims to understand the link "between language and the social" (Mautner and Baker, 2009), and attempts to demystify social construction and power relations (Gramsci, 1999). On the other hand, corpus linguistics deals with principles and practice of understanding the language produced within large amounts of textual data (Oostdijk, 1991). In my thesis, I have aimed to combine, using machine learning, the CDA approach with corpus linguistics with the intention of deconstructing dominant discourses that create, maintain and deepen fault lines between social groups and classes. As an instance of this technological framework, I have developed a tool for understanding and defining the discourse on Islam in the global mainstream media sources. My hypothesis is that the media coverage in several mainstream news sources tends to contextualize Muslims largely as a group embroiled in conflict at a disproportionately large level. My hypothesis is based on the assumption that discourse on Islam in mainstream global media tends to lean toward the dangerous "clash of civilizations" frame. To test this hypothesis, I have developed a prototype tool "Said-Huntington Discourse Analyzer" that machine classifies news articles on a normative scale -- a scale that measures "clash of civilization" polarization in an article on the basis of conflict. The tool also extracts semantically meaningful conversations for a media source using Latent Dirichlet Allocation (LDA) topic modeling, allowing the users to discover frames of conversations on the basis of Said-Huntington index classification. I evaluated the classifier on human-classified articles and found that the accuracy of the classifier was very high (99.03%). Generally, text analysis tools uncover patterns and trends in the data without delineating the 'ideology' that permeates the text. The machine learning tool presented here classifies media discourse on Islam in terms of conflict and non-conflict, and attempts to put light on the 'ideology' that permeates the text. In addition, the tool provides textual analysis of news articles based on the CDA methodologies.<br>by Muhammad Ali Hashmi.<br>S.M.

Digital currencies (cryptocurrencies) are rapidly becoming commonplace in the global market. Trading is performed similarly to the stock market or commodities, but stock market prediction algorithms are not necessarily well-suited for predicting digital currency prices. In this work, we analyzed tweets with both an existing sentiment analysis package and a manually tailored "objective analysis," resulting in one impact value for each analysis per 15-minute period. We then used evolutionary techniques to select the most appropriate training method and the best subset of the generated features to include, as well as other parameters. This resulted in implementation of predictors which yielded much more profit in four-week simulations than simply holding a digital currency for the same time period--the results ranged from 28% to 122% profit. Unlike stock exchanges, which shut down for several hours or days at a time, digital currency prediction and trading seems to be of a more consistent and predictable nature.

In this thesis will be showed the design and development of SpeechTab, a web application that collects structured speech data from different subjects and a technique that try to tell which one is affected of cognitive decline or not.