Search results for: Text Data Mining

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

By the evolvement in technology, the way of expressing opinions switched direction to the digital world. The domain of politics, as one of the hottest topics of opinion mining research, merged together with the behavior analysis for affiliation determination in texts, which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 were constituted by Linguistic Inquiry and Word Count (LIWC) features were tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that the “Decision Tree”, “Rule Induction” and “M5 Rule” classifiers when used with “SVM” and “IGR” feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “Function”, as an aggregate feature of the linguistic category, was found as the most differentiating feature among the 68 features with the accuracy of 81% in classifying articles either as Republican or Democrat.

Keywords: Politics, machine learning, feature selection, LIWC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2369

Authors: Monika Chuchro

Abstract:

This paper presents a preliminary attempt to apply classification of time series using meta-clusters in order to improve the quality of regression models. In this case, clustering was performed as a method to obtain subgroups of time series data with normal distribution from the inflow into wastewater treatment plant data, composed of several groups differing by mean value. Two simple algorithms, K-mean and EM, were chosen as a clustering method. The Rand index was used to measure the similarity. After simple meta-clustering, a regression model was performed for each subgroups. The final model was a sum of the subgroups models. The quality of the obtained model was compared with the regression model made using the same explanatory variables, but with no clustering of data. Results were compared using determination coefficient (R2), measure of prediction accuracy- mean absolute percentage error (MAPE) and comparison on a linear chart. Preliminary results allow us to foresee the potential of the presented technique.

Keywords: Clustering, Data analysis, Data mining, Predictive models.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1951

Authors: Irina Pyrlina

Abstract:

This article presents the results of a study conducted to identify operational risks for information systems (IS) with service-oriented architecture (SOA). Analysis of current approaches to risk and system error classifications revealed that the system error classes were never used for SOA risk estimation. Additionally system error classes are not normallyexperimentally supported with realenterprise error data. Through the study several categories of various existing error classifications systems are applied and three new error categories with sub-categories are identified. As a part of operational risks a new error classification scheme is proposed for SOA applications. It is based on errors of real information systems which are service providers for application with service-oriented architecture. The proposed classification approach has been used to classify SOA system errors for two different enterprises (oil and gas industry, metal and mining industry). In addition we have conducted a research to identify possible losses from operational risks.

Keywords: Enterprise architecture, Error classification, Oil&Gas and Metal&Mining industries, Operational risks, Serviceoriented architecture

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1605

Authors: Chen Wu, Jingyu Yang

Abstract:

Using maximal consistent blocks of tolerance relation on the universe in incomplete decision table, the concepts of join block and meet block are introduced and studied. Including tolerance class, other blocks such as tolerant kernel and compatible kernel of an object are also discussed at the same time. Upper and lower approximations based on those blocks are also defined. Default definite decision rules acquired from incomplete decision table are proposed in the paper. An incremental algorithm to update default definite decision rules is suggested for effective mining tasks from incomplete decision table into which data is appended. Through an example, we demonstrate how default definite decision rules based on maximal consistent blocks, join blocks and meet blocks are acquired and how optimization is done in support of discernibility matrix and discernibility function in the incomplete decision table.

Keywords: rough set, incomplete decision table, maximalconsistent block, default definite decision rule, join and meet block.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1289

Authors: Farshideh Einsele, Rolf Ingold

Abstract:

Current OCR technology does not allow to accurately recognizing small text images, such as those found in web images. Our goal is to investigate new approaches to recognize very low resolution text images containing antialiased character shapes. This paper presents a preliminary study on the variability of such characters and the feasibility to discriminate them by using geometrical features. In a first stage we analyze the distribution of these features. In a second stage we present a study on the discriminative power for recognizing isolated characters, using various rendering methods and font properties. Finally we present interesting results of our evaluation tests leading to our conclusion and future focus.

Keywords: World Wide Web, document analysis, pattern recognition, Optical Character Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1372

Authors: Jawad H AlKhateeb, Jianmin Jiang, Jinchang Ren, Stan S Ipson

Abstract:

Efficient preprocessing is very essential for automatic recognition of handwritten documents. In this paper, techniques on segmenting words in handwritten Arabic text are presented. Firstly, connected components (ccs) are extracted, and distances among different components are analyzed. The statistical distribution of this distance is then obtained to determine an optimal threshold for words segmentation. Meanwhile, an improved projection based method is also employed for baseline detection. The proposed method has been successfully tested on IFN/ENIT database consisting of 26459 Arabic words handwritten by 411 different writers, and the results were promising and very encouraging in more accurate detection of the baseline and segmentation of words for further recognition.

Keywords: Arabic OCR, off-line recognition, Baseline estimation, Word segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2207

Authors: Preeti Kumari, Ridhi Kapoor

Abstract:

 In any communication, security is the most important issue in today’s world. In this paper, steganography is the process of hiding the important data into other data, such as text, audio, video, and image. The interest in this topic is to provide availability, confidentiality, integrity, and authenticity of data. The steganographic technique that embeds hides content with unremarkable cover media so as not to provoke eavesdropper’s suspicion or third party and hackers. In which many applications of compression, encryption, decryption, and embedding methods are used for digital image steganography. Due to compression, the nose produces in the image. To sustain noise in the image, the LSB insertion technique is used. The performance of the proposed embedding system with respect to providing security to secret message and robustness is discussed. We also demonstrate the maximum steganography capacity and visual distortion.

Keywords: Steganography, LSB, encoding, information hiding, color image.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1093

Authors: Nadeem Iftikhar, Zouhaib Zafar, Shaukat Ali

Abstract:

Efficient retrieval of multimedia objects has gained enormous focus in recent years. A number of techniques have been suggested for retrieval of textual information; however, relatively little has been suggested for efficient retrieval of multimedia objects. In this paper we have proposed a generic architecture for contextaware retrieval of multimedia objects. The proposed framework combines the well-known approaches of text-based retrieval and context-aware retrieval to formulate architecture for accurate retrieval of multimedia data.

Keywords: Context-aware retrieval, information retrieval, multimedia databases, multimedia data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1538

Authors: García López

Abstract:

The Government Departments of Health have the task of informing and educating citizens about public health issues. For this, they use channels like Twitter, key in the search for health information and the propagation of content. The tweets, important in the virality of the content, may contain emotions that influence the contagion and exchange of knowledge. The goal of this study is to perform an analysis of the emotional projection of health information shared on Twitter by official American accounts: the disease control account CDCgov, National Institutes of Health, NIH, the government agency HHSGov, and the professional organization PublicHealth. For this, we used Tone Analyzer, an International Business Machines Corporation (IBM) tool specialized in emotion detection in text, corresponding to the categorical model of emotion representation. For 15 days, all tweets from these accounts were analyzed with the emotional analysis tool in text. The results showed that their tweets contain an important emotional load, a determining factor in the success of their communications. This exposes that official accounts also use subjective language and contain emotions. The predominance of emotion joy over sadness and the strong presence of emotions in their tweets stimulate the virality of content, a key in the work of informing that government health departments have.

Keywords: Emotions in tweets emotion detection in text, health information on Twitter, American health official accounts, emotions on Twitter, emotions and content.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 699

Authors: Mohamed Lahcen BenSaad, Sun XingMing

Abstract:

Information hiding, especially watermarking is a promising technique for the protection of intellectual property rights. This technology is mainly advanced for multimedia but the same has not been done for text. Web pages, like other documents, need a protection against piracy. In this paper, some techniques are proposed to show how to hide information in web pages using some features of the markup language used to describe these pages. Most of the techniques proposed here use the white space to hide information or some varieties of the language in representing elements. Experiments on a very small page and analysis of five thousands web pages show that these techniques have a wide bandwidth available for information hiding, and they might form a solid base to develop a robust algorithm for web page watermarking.

Keywords: Digital Watermarking, Information Hiding, Markup Language, Text watermarking, Software Watermarking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1795

Authors: Kitti Koonsanit, Chuleerat Jaruskulchai, Poonsak Miphokasap, Apisit Eiumnoh

Abstract:

In the end of the day, meteorological data and environmental data becomes widely used such as plant varieties selection system. Variety plant selection for planted area is of almost importance for all crops, including varieties of sugarcane. Since sugarcane have many varieties. Variety plant non selection for planting may not be adapted to the climate or soil conditions for planted area. Poor growth, bloom drop, poor fruit, and low price are to be from varieties which were not recommended for those planted area. This paper presents plant varieties selection system for planted areas in Thailand from meteorological data and environmental data by the use of decision tree techniques. With this software developed as an environmental data analysis tool, it can analyze resulting easier and faster. Our software is a front end of WEKA that provides fundamental data mining functions such as classify, clustering, and analysis functions. It also supports pre-processing, analysis, and decision tree output with exporting result. After that, our software can export and display data result to Google maps API in order to display result and plot plant icons effectively.

Keywords: Plant varieties selection system, decision tree, expert recommendation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1794

Authors: Xiaohua Liu, Juan F. Beltran, Nishant Mohanchandra, Godfried T. Toussaint

Abstract:

Support vector machines (SVMs) are considered to be the best machine learning algorithms for minimizing the predictive probability of misclassification. However, their drawback is that for large data sets the computation of the optimal decision boundary is a time consuming function of the size of the training set. Hence several methods have been proposed to speed up the SVM algorithm. Here three methods used to speed up the computation of the SVM classifiers are compared experimentally using a musical genre classification problem. The simplest method pre-selects a random sample of the data before the application of the SVM algorithm. Two additional methods use proximity graphs to pre-select data that are near the decision boundary. One uses k-Nearest Neighbor graphs and the other Relative Neighborhood Graphs to accomplish the task.

Keywords: Machine learning, data mining, support vector machines, proximity graphs, relative-neighborhood graphs, k-nearestneighbor graphs, random sampling, training data condensation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1919

Authors: E. Khorram, S.M. Mirzababaei

Abstract:

Everyday the usages of the Internet increase and simply a world of the data become accessible. Network providers do not want to let the provided services to be used in harmful or terrorist affairs, so they used a variety of methods to protect the special regions from the harmful data. One of the most important methods is supposed to be the firewall. Firewall stops the transfer of such packets through several ways, but in some cases they do not use firewall because of its blind packet stopping, high process power needed and expensive prices. Here we have proposed a method to find a discriminate function to distinguish between usual packets and harmful ones by the statistical processing on the network router logs. So an administrator can alarm to the user. This method is very fast and can be used simply in adjacent with the Internet routers.

Keywords: Data Mining, Firewall, Optimization, Packetclassification, Statistical Pattern Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1410

Authors: Kazunari Meguro, Daisuke Yamamoto, Shinichi Motomura, Toshihiko Sasama, Takao Kawamura, Kazunori Sugahara

Abstract:

We have developed a distributed asynchronous Web based training system. In order to improve the scalability and robustness of this system, all contents and functions are realized on mobile agents. These agents are distributed to computers, and they can use a Peer to Peer network that modified Content-Addressable Network. In the proposed system, only text data can be included in a exercise. To make our proposed system more useful, the mechanism that it not only adapts to multimedia data but also it doesn-t influence the user-s learning even if the size of exercise becomes large is necessary.

Keywords: e-Learning, multimedia, Mobile Agent.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1492

Authors: Leo Galambos, Jan Lansky, Katsiaryna Chernik

Abstract:

EGOTHOR is a search engine that indexes the Web and allows us to search the Web documents. Its hit list contains URL and title of the hits, and also some snippet which tries to shortly show a match. The snippet can be almost always assembled by an algorithm that has a full knowledge of the original document (mostly HTML page). It implies that the search engine is required to store the full text of the documents as a part of the index. Such a requirement leads us to pick up an appropriate compression algorithm which would reduce the space demand. One of the solutions could be to use common compression methods, for instance gzip or bzip2, but it might be preferable if we develop a new method which would take advantage of the document structure, or rather, the textual character of the documents. There already exist a special compression text algorithms and methods for a compression of XML documents. The aim of this paper is an integration of the two approaches to achieve an optimal level of the compression ratio

Keywords: Compression, search engine, HTML, XML.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1578

Authors: Farooq A. Al-Sheikh, Carol Moralejo, Mark Pritzker, William A. Anderson, Ali Elkamel

Abstract:

Ammonia in mining wastewater is a significant problem, and treatment can be especially difficult in cold climates where biological treatment is not feasible. An adsorption process is one of the alternative processes that can be used to reduce ammonia concentrations to acceptable limits, and therefore a LEWATIT resin strongly acidic H+ form ion exchange resin and a Bowie Chabazite Na form AZLB-Na zeolite were tested to assess their effectiveness. For these adsorption tests, two packed bed columns (a mini-column constructed from a 32-cm long x 1-cm diameter piece of glass tubing, and a 60-cm long x 2.5-cm diameter Ace Glass chromatography column) were used containing varying quantities of the adsorbents. A mining wastewater with ammonia concentrations of 22.7 mg/L was fed through the columns at controlled flowrates. In the experimental work, maximum capacities of the LEWATIT ion exchange resin were 0.438, 0.448, and 1.472 mg/g for 3, 6, and 9 g respectively in a mini column and 1.739 mg/g for 141.5 g in a larger Ace column while the capacities for the AZLB-Na zeolite were 0.424, and 0.784 mg/g for 3, and 6 g respectively in the mini column and 1.1636 mg/g for 38.5 g in the Ace column. In the theoretical work, Thomas, Adams-Bohart, and Yoon-Nelson models were constructed to describe a breakthrough curve of the adsorption process and find the constants of the above-mentioned models. In the regeneration tests, 5% hydrochloric acid, HCl (v/v) and 10% sodium hydroxide, NaOH (w/v) were used to regenerate the LEWATIT resin and AZLB-Na zeolite with 44 and 63.8% recovery, respectively. In conclusion, continuous flow adsorption using a LEWATIT ion exchange resin and an AZLB-Na zeolite is efficient when using a co-flow technique for removal of the ammonia from wastewater. Thomas, Adams-Bohart, and Yoon-Nelson models satisfactorily fit the data with R² closer to 1 in all cases.

Keywords: AZLB-Na zeolite, continuous adsorption, LEWATIT resin, models, regeneration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1237

Authors: K. Jahani, J. Razavi

Abstract:

Nowadays, to decrease the number of downtimes in the industries such as metal mining, petroleum and chemical industries, predictive maintenance is crucial. In order to have efficient predictive maintenance, knowing the performance of critical equipment of production line such as pumps and hydro-cyclones under variable operating parameters, selecting best indicators of this equipment health situations, best locations for instrumentation, and also measuring of these indicators are very important. In this paper, computer aided engineering (CAE) tools are implemented to study some important elements of copper process line, namely slurry pumps and cyclone to predict the performance of these components under different working conditions. These modeling and simulations can be used in predicting, for example, the damage tolerance of the main shaft of the slurry pump or wear rate and location of cyclone wall or pump case and impeller. Also, the simulations can suggest best-measuring parameters, measuring intervals, and their locations.

Keywords: Computer aided engineering, predictive maintenance, fault detection, mining process line, slurry pump, hydrocyclone.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1834

Authors: Shaukat Wasi, Zubair A. Shaikh, Sajid Qasmi, Hussain Sachwani, Rehman Lalani, Aamir Chagani

Abstract:

Automatic Extraction of Event information from social text stream (emails, social network sites, blogs etc) is a vital requirement for many applications like Event Planning and Management systems and security applications. The key information components needed from Event related text are Event title, location, participants, date and time. Emails have very unique distinctions over other social text streams from the perspective of layout and format and conversation style and are the most commonly used communication channel for broadcasting and planning events. Therefore we have chosen emails as our dataset. In our work, we have employed two statistical NLP methods, named as Finite State Machines (FSM) and Hidden Markov Model (HMM) for the extraction of event related contextual information. An application has been developed providing a comparison among the two methods over the event extraction task. It comprises of two modules, one for each method, and works for both bulk as well as direct user input. The results are evaluated using Precision, Recall and F-Score. Experiments show that both methods produce high performance and accuracy, however HMM was good enough over Title extraction and FSM proved to be better for Venue, Date, and time.

Keywords: Emails, Event Extraction, Event Detection, Finite state machines, Hidden Markov Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2319

Authors: C. Rajan, K. Geetha, S. Geetha

Abstract:

The motivation of image compression technique is to reduce the irrelevance and redundancy of the image data in order to store or pass data in an efficient way from one place to another place. There are several types of compression methods available. Without the help of compression technique, the file size is knowingly larger, usually several megabytes, but by doing the compression technique, it is possible to reduce file size up to 10% as of the original without noticeable loss in quality. Image compression can be lossless or lossy. The compression technique can be applied to images, audio, video and text data. This research work mainly concentrates on methods of encoding, DCT, compression methods, security, etc. Different methodologies and network simulations have been analyzed here. Various methods of compression methodologies and its performance metrics has been investigated and presented in a table manner.

Keywords: Image compression techniques, encoding, DCT, lossy compression, lossless compression, JPEG.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1189

Authors: Safa Adi

Abstract:

This paper will consider the problem of sequential mining patterns embedded in a database by handling the time constraints as defined in the GSP algorithm (level wise algorithms). We will compare two previous approaches GTC and PSP, that resumes the general principles of GSP. Furthermore this paper will discuss PG-hybrid algorithm, that using PSP and GTC. The results show that PSP and GTC are more efficient than GSP. On the other hand, the GTC algorithm performs better than PSP. The PG-hybrid algorithm use PSP algorithm for the two first passes on the database, and GTC approach for the following scans. Experiments show that the hybrid approach is very efficient for short, frequent sequences.

Keywords: Database, GTC algorithm, PSP algorithm, sequential patterns, time constraints.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 700

Authors: Damith Senanayake, Lakmal Muthugama, Laksheen Mendis, Tiroshan Madushanka

Abstract:

Customer churn prediction is one of the most useful areas of study in customer analytics. Due to the enormous amount of data available for such predictions, machine learning and data mining have been heavily used in this domain. There exist many machine learning algorithms directly applicable for the problem of customer churn prediction, and here, we attempt to experiment on a novel approach by using a cognitive learning based technique in an attempt to improve the results obtained by using a combination of supervised learning methods, with cognitive unsupervised learning methods.

Keywords: Growing Self Organizing Maps, Kernel Methods, Churn Prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2563

Authors: V. Salajka, Z. Kaláb, J. Kala, P. Hradil

Abstract:

In the territories where high-intensity earthquakes are frequent is paid attention to the solving of the seismic problems. In the paper are described two computational model variants based on finite element method of the construction with different subsoil simulation (rigid or elastic subsoil) is used. For simulation and calculations program system based on method final elements ANSYS was used. Seismic responses calculations of residential building structure were effected on loading characterized by accelerogram for comparing with the responses spectra method.

Keywords: Accelerogram, ANSYS, mining induced seismic, residential building structure, spectra, subsoil.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1538

Authors: Roman Graf, Sergiu Gordea, Heather M. Ryan

Abstract:

This paper presents an approach for easy creation and classification of institutional risk profiles supporting endangerment analysis of file formats. The main contribution of this work is the employment of data mining techniques to support set up of the most important risk factors. Subsequently, risk profiles employ risk factors classifier and associated configurations to support digital preservation experts with a semi-automatic estimation of endangerment group for file format risk profiles. Our goal is to make use of an expert knowledge base, accuired through a digital preservation survey in order to detect preservation risks for a particular institution. Another contribution is support for visualisation of risk factors for a requried dimension for analysis. Using the naive Bayes method, the decision support system recommends to an expert the matching risk profile group for the previously selected institutional risk profile. The proposed methods improve the visibility of risk factor values and the quality of a digital preservation process. The presented approach is designed to facilitate decision making for the preservation of digital content in libraries and archives using domain expert knowledge and values of file format risk profiles. To facilitate decision-making, the aggregated information about the risk factors is presented as a multidimensional vector. The goal is to visualise particular dimensions of this vector for analysis by an expert and to define its profile group. The sample risk profile calculation and the visualisation of some risk factor dimensions is presented in the evaluation section.

Keywords: linked open data, information integration, digital libraries, data mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 730

Authors: Zaheer Ahmad, Jehanzeb Khan Orakzai, Inam Shamsher, Awais Adnan

Abstract:

This paper discusses the Urdu script characteristics, Urdu Nastaleeq and a simple but a novel and robust technique to recognize the printed Urdu script without a lexicon. Urdu being a family of Arabic script is cursive and complex script in its nature, the main complexity of Urdu compound/connected text is not its connections but the forms/shapes the characters change when it is placed at initial, middle or at the end of a word. The characters recognition technique presented here is using the inherited complexity of Urdu script to solve the problem. A word is scanned and analyzed for the level of its complexity, the point where the level of complexity changes is marked for a character, segmented and feeded to Neural Networks. A prototype of the system has been tested on Urdu text and currently achieves 93.4% accuracy on the average.

Keywords: Cursive Script, OCR, Urdu.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2780

Authors: Surat Srinoy, Werasak Kurutach, Witcha Chimphlee, Siriporn Chimphlee

Abstract:

One main drawback of intrusion detection system is the inability of detecting new attacks which do not have known signatures. In this paper we discuss an intrusion detection method that proposes independent component analysis (ICA) based feature selection heuristics and using rough fuzzy for clustering data. ICA is to separate these independent components (ICs) from the monitored variables. Rough set has to decrease the amount of data and get rid of redundancy and Fuzzy methods allow objects to belong to several clusters simultaneously, with different degrees of membership. Our approach allows us to recognize not only known attacks but also to detect activity that may be the result of a new, unknown attack. The experimental results on Knowledge Discovery and Data Mining- (KDDCup 1999) dataset.

Keywords: Network security, intrusion detection, rough set, ICA, anomaly detection, independent component analysis, rough fuzzy .

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1956

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: Deep learning, data mining, gender predication, MOOCs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1365

Authors: Daniel Morariu, Lucian N. Vintan, Volker Tresp

Abstract:

Text categorization is the problem of classifying text documents into a set of predefined classes. After a preprocessing step, the documents are typically represented as large sparse vectors. When training classifiers on large collections of documents, both the time and memory restrictions can be quite prohibitive. This justifies the application of feature selection methods to reduce the dimensionality of the document-representation vector. In this paper, three feature selection methods are evaluated: Random Selection, Information Gain (IG) and Support Vector Machine feature selection (called SVM_FS). We show that the best results were obtained with SVM_FS method for a relatively small dimension of the feature vector. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).

Keywords: Feature Selection, Learning with Kernels, SupportVector Machine, and Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1830

Authors: Kamal K.Bharadwaj, Rekha Kandwal

Abstract:

An important structuring mechanism for knowledge bases is building clusters based on the content of their knowledge objects. The objects are clustered based on the principle of maximizing the intraclass similarity and minimizing the interclass similarity. Clustering can also facilitate taxonomy formation, that is, the organization of observations into a hierarchy of classes that group similar events together. Hierarchical representation allows us to easily manage the complexity of knowledge, to view the knowledge at different levels of details, and to focus our attention on the interesting aspects only. One of such efficient and easy to understand systems is Hierarchical Production rule (HPRs) system. A HPR, a standard production rule augmented with generality and specificity information, is of the following form Decision If < condition> Generality Specificity . HPRs systems are capable of handling taxonomical structures inherent in the knowledge about the real world. In this paper, a set of related HPRs is called a cluster and is represented by a HPR-tree. This paper discusses an algorithm based on cumulative learning scenario for dynamic structuring of clusters. The proposed scheme incrementally incorporates new knowledge into the set of clusters from the previous episodes and also maintains summary of clusters as Synopsis to be used in the future episodes. Examples are given to demonstrate the behaviour of the proposed scheme. The suggested incremental structuring of clusters would be useful in mining data streams.

Keywords: Cumulative learning, clustering, data mining, hierarchical production rules.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1439

Authors: Hong Choon Ong

Abstract:

Naïve Bayes classifiers are simple probabilistic classifiers. Classification extracts patterns by using data file with a set of labeled training examples and is currently one of the most significant areas in data mining. However, Naïve Bayes assumes the independence among the features. Structural learning among the features thus helps in the classification problem. In this study, the use of structural learning in Bayesian Network is proposed to be applied where there are relationships between the features when using the Naïve Bayes. The improvement in the classification using structural learning is shown if there exist relationship between the features or when they are not independent.

Keywords: Bayesian Network, Classification, Naïve Bayes, Structural Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2600

Authors: Philip T. Broughton, Mark P. Bettney, Isla L. Smail

Abstract:

Effective treatment of ground instability is essential when managing the impacts associated with historic mining. A field trial was undertaken by the Coal Authority to investigate the geotechnical performance and potential use of composite materials comprising resin and fill or stone to safely treat surface collapses, such as crown-holes, associated with shallow mining. Test pits were loosely filled with various granular fill materials. The fill material was injected with commercially available silicate and polyurethane resin foam products. In situ and laboratory testing was undertaken to assess the geotechnical properties of the resultant composite materials. The test pits were subsequently excavated to assess resin permeation. Drilling and resin injection was easiest through clean limestone fill materials. Recycled building waste fill material proved difficult to inject with resin; this material is thus considered unsuitable for use in resin composites. Incomplete resin permeation in several of the test pits created irregular ‘blocks’ of composite. Injected resin foams significantly improve the stiffness and resistance (strength) of the un-compacted fill material. The stiffness of the treated fill material appears to be a function of the stone particle size, its associated compaction characteristics (under loose tipping) and the proportion of resin foam matrix. The type of fill material is more critical than the type of resin to the geotechnical properties of the composite materials. Resin composites can effectively support typical design imposed loads. Compared to other traditional treatment options, such as cement grouting, the use of resin composites is potentially less disruptive, particularly for sites with limited access, and thus likely to achieve significant reinstatement cost savings. The use of resin composites is considered a suitable option for the future treatment of shallow mining collapses.

Keywords: Composite material, ground improvement, mining legacy, resin.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1541