Search results for: Text mining.
695 Generating Concept Trees from Dynamic Self-organizing Map
Authors: Norashikin Ahmad, Damminda Alahakoon
Abstract:
Self-organizing map (SOM) provides both clustering and visualization capabilities in mining data. Dynamic self-organizing maps such as Growing Self-organizing Map (GSOM) has been developed to overcome the problem of fixed structure in SOM to enable better representation of the discovered patterns. However, in mining large datasets or historical data the hierarchical structure of the data is also useful to view the cluster formation at different levels of abstraction. In this paper, we present a technique to generate concept trees from the GSOM. The formation of tree from different spread factor values of GSOM is also investigated and the quality of the trees analyzed. The results show that concept trees can be generated from GSOM, thus, eliminating the need for re-clustering of the data from scratch to obtain a hierarchical view of the data under study.
Keywords: dynamic self-organizing map, concept formation, clustering.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1445694 Segmentation of Korean Words on Korean Road Signs
Authors: Lae-Jeong Park, Kyusoo Chung, Jungho Moon
Abstract:
This paper introduces an effective method of segmenting Korean text (place names in Korean) from a Korean road sign image. A Korean advanced directional road sign is composed of several types of visual information such as arrows, place names in Korean and English, and route numbers. Automatic classification of the visual information and extraction of Korean place names from the road sign images make it possible to avoid a lot of manual inputs to a database system for management of road signs nationwide. We propose a series of problem-specific heuristics that correctly segments Korean place names, which is the most crucial information, from the other information by leaving out non-text information effectively. The experimental results with a dataset of 368 road sign images show 96% of the detection rate per Korean place name and 84% per road sign image.Keywords: Segmentation, road signs, characters, classification.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2731693 Decision Support System Based on Data Warehouse
Authors: Yang Bao, LuJing Zhang
Abstract:
Typical Intelligent Decision Support System is 4-based, its design composes of Data Warehouse, Online Analytical Processing, Data Mining and Decision Supporting based on models, which is called Decision Support System Based on Data Warehouse (DSSBDW). This way takes ETL,OLAP and DM as its implementing means, and integrates traditional model-driving DSS and data-driving DSS into a whole. For this kind of problem, this paper analyzes the DSSBDW architecture and DW model, and discusses the following key issues: ETL designing and Realization; metadata managing technology using XML; SQL implementing, optimizing performance, data mapping in OLAP; lastly, it illustrates the designing principle and method of DW in DSSBDW.
Keywords: Decision Support System, Data Warehouse, Data Mining.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3845692 Hydrogeological Risk and Mining Tunnels: the Fontane-Rodoretto Mine Turin (Italy)
Authors: Paola Gattinoni, Laura Scesi, Elena Cerino Adbin, Daniele Cremonesi
Abstract:
The interaction of tunneling or mining with groundwater has become a very relevant problem not only due to the need to guarantee the safety of workers and to assure the efficiency of the tunnel drainage systems, but also to safeguard water resources from impoverishment and pollution risk. Therefore it is very important to forecast the drainage processes (i.e., the evaluation of drained discharge and drawdown caused by the excavation). The aim of this study was to know better the system and to quantify the flow drained from the Fontane mines, located in Val Germanasca (Turin, Italy). This allowed to understand the hydrogeological local changes in time. The work has therefore been structured as follows: the reconstruction of the conceptual model with the geological, hydrogeological and geological-structural study; the calculation of the tunnel inflows (through the use of structural methods) and the comparison with the measured flow rates; the water balance at the basin scale. In this way it was possible to understand what are the relationships between rainfall, groundwater level variations and the effect of the presence of tunnels as a means of draining water. Subsequently, it the effects produced by the excavation of the mining tunnels was quantified, through numerical modeling. In particular, the modeling made it possible to observe the drawdown variation as a function of number, excavation depth and different mines linings.Keywords: Groundwater, Italy, numerical model, tunneling.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1909691 Utilization of Process Mapping Tool to Enhance Production Drilling in Underground Metal Mining Operations
Authors: Sidharth Talan, Sanjay Kumar Sharma, Eoin Joseph Wallace, Nikita Agrawal
Abstract:
Underground mining is at the core of rapidly evolving metals and minerals sector due to the increasing mineral consumption globally. Even though the surface mines are still more abundant on earth, the scales of industry are slowly tipping towards underground mining due to rising depth and complexities of orebodies. Thus, the efficient and productive functioning of underground operations depends significantly on the synchronized performance of key elements such as operating site, mining equipment, manpower and mine services. Production drilling is the process of conducting long hole drilling for the purpose of charging and blasting these holes for the production of ore in underground metal mines. Thus, production drilling is the crucial segment in the underground metal mining value chain. This paper presents the process mapping tool to evaluate the production drilling process in the underground metal mining operation by dividing the given process into three segments namely Input, Process and Output. The three segments are further segregated into factors and sub-factors. As per the study, the major input factors crucial for the efficient functioning of production drilling process are power, drilling water, geotechnical support of the drilling site, skilled drilling operators, services installation crew, oils and drill accessories for drilling machine, survey markings at drill site, proper housekeeping, regular maintenance of drill machine, suitable transportation for reaching the drilling site and finally proper ventilation. The major outputs for the production drilling process are ore, waste as a result of dilution, timely reporting and investigation of unsafe practices, optimized process time and finally well fragmented blasted material within specifications set by the mining company. The paper also exhibits the drilling loss matrix, which is utilized to appraise the loss in planned production meters per day in a mine on account of availability loss in the machine due to breakdowns, underutilization of the machine and productivity loss in the machine measured in drilling meters per unit of percussion hour with respect to its planned productivity for the day. The given three losses would be essential to detect the bottlenecks in the process map of production drilling operation so as to instigate the action plan to suppress or prevent the causes leading to the operational performance deficiency. The given tool is beneficial to mine management to focus on the critical factors negatively impacting the production drilling operation and design necessary operational and maintenance strategies to mitigate them.
Keywords: Process map, drilling loss matrix, availability, utilization, productivity, percussion rate.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1068690 Appreciating, Interpreting and Understanding Posters via Levels of Visual Literacy
Authors: Mona Masood, Zakiah Zain
Abstract:
This study was conducted in Malaysia to discover how meaning and appreciation were construed among 35 Form Five students. Panofsky-s theory was employed to discover the levels of reasoning among students when various types of posters were displayed. The independent variables used were posters that carried explicit and implicit meanings; the moderating variable was students- visual literacy levels while the dependent variable was the implicit interpretation level. One-way ANOVA was applied for the data analysis. The data showed that before students were exposed to Panofsky-s theory, there were differences in thinking between boys, who did not think abstractly or implicit in comparison to girls. The study showed that students- visual literacy in posters depended on the use of visual texts and illustration. This paper discuss further on posters with text only have a tendency to be too abstract as opposed to posters with visuals plus text.Keywords: explicit visual, implicit visual, visual interpretation, visual literacy
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2386689 Words Reordering based on Statistical Language Model
Authors: Theologos Athanaselis, Stelios Bakamidis, Ioannis Dologlou
Abstract:
There are multiple reasons to expect that detecting the word order errors in a text will be a difficult problem, and detection rates reported in the literature are in fact low. Although grammatical rules constructed by computer linguists improve the performance of grammar checker in word order diagnosis, the repairing task is still very difficult. This paper presents an approach for repairing word order errors in English text by reordering words in a sentence and choosing the version that maximizes the number of trigram hits according to a language model. The novelty of this method concerns the use of an efficient confusion matrix technique for reordering the words. The comparative advantage of this method is that works with a large set of words, and avoids the laborious and costly process of collecting word order errors for creating error patterns.Keywords: Permutations filtering, Statistical languagemodel N-grams, Word order errors
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1572688 Labeling Method in Steganography
Authors: H. Motameni, M. Norouzi, M. Jahandar, A. Hatami
Abstract:
In this paper a way of hiding text message (Steganography) in the gray image has been presented. In this method tried to find binary value of each character of text message and then in the next stage, tried to find dark places of gray image (black) by converting the original image to binary image for labeling each object of image by considering on 8 connectivity. Then these images have been converted to RGB image in order to find dark places. Because in this way each sequence of gray color turns into RGB color and dark level of grey image is found by this way if the Gary image is very light the histogram must be changed manually to find just dark places. In the final stage each 8 pixels of dark places has been considered as a byte and binary value of each character has been put in low bit of each byte that was created manually by dark places pixels for increasing security of the main way of steganography (LSB).
Keywords: Binary image, labeling, low bit, neighborhood, RGB image, steganography, threshold.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2120687 Evaluation of the Urban Regeneration Project: Land Use Transformation and SNS Big Data Analysis
Authors: Ju-Young Kim, Tae-Heon Moon, Jung-Hun Cho
Abstract:
Urban regeneration projects have been actively promoted in Korea. In particular, Jeonju Hanok Village is evaluated as one of representative cases in terms of utilizing local cultural heritage sits in the urban regeneration project. However, recently, there has been a growing concern in this area, due to the ‘gentrification’, caused by the excessive commercialization and surging tourists. This trend was changing land and building use and resulted in the loss of identity of the region. In this regard, this study analyzed the land use transformation between 2010 and 2016 to identify the commercialization trend in Jeonju Hanok Village. In addition, it conducted SNS big data analysis on Jeonju Hanok Village from February 14th, 2016 to March 31st, 2016 to identify visitors’ awareness of the village. The study results demonstrate that rapid commercialization was underway, unlikely the initial intention, so that planners and officials in city government should reconsider the project direction and rebuild deliberate management strategies. This study is meaningful in that it analyzed the land use transformation and SNS big data to identify the current situation in urban regeneration area. Furthermore, it is expected that the study results will contribute to the vitalization of regeneration area.
Keywords: Land use, SNS, text mining, urban regeneration.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1198686 Discovering Complex Regularities: from Tree to Semi-Lattice Classifications
Authors: A. Faro, D. Giordano, F. Maiorana
Abstract:
Data mining uses a variety of techniques each of which is useful for some particular task. It is important to have a deep understanding of each technique and be able to perform sophisticated analysis. In this article we describe a tool built to simulate a variation of the Kohonen network to perform unsupervised clustering and support the entire data mining process up to results visualization. A graphical representation helps the user to find out a strategy to optimize classification by adding, moving or delete a neuron in order to change the number of classes. The tool is able to automatically suggest a strategy to optimize the number of classes optimization, but also support both tree classifications and semi-lattice organizations of the classes to give to the users the possibility of passing from one class to the ones with which it has some aspects in common. Examples of using tree and semi-lattice classifications are given to illustrate advantages and problems. The tool is applied to classify macroeconomic data that report the most developed countries- import and export. It is possible to classify the countries based on their economic behaviour and use the tool to characterize the commercial behaviour of a country in a selected class from the analysis of positive and negative features that contribute to classes formation. Possible interrelationships between the classes and their meaning are also discussed.Keywords: Unsupervised classification, Kohonen networks, macroeconomics, Visual data mining, Cluster interpretation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1529685 Influenza Pattern Analysis System through Mining Weblogs
Authors: Pei Lin Khoo, Yunli Lee
Abstract:
Weblogs are resource of social structure to discover and track the various type of information written by blogger. In this paper, we proposed to use mining weblogs technique for identifying the trends of influenza where blogger had disseminated their opinion for the anomaly disease. In order to identify the trends, web crawler is applied to perform a search and generated a list of visited links based on a set of influenza keywords. This information is used to implement the analytics report system for monitoring and analyzing the pattern and trends of influenza (H1N1). Statistical and graphical analysis reports are generated. Both types of the report have shown satisfactory reports that reflect the awareness of Malaysian on the issue of influenza outbreak through blogs.
Keywords: H1N1, Weblogs, Web Crawler, Analytics Report System.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2455684 Analysis of Road Repairs in Undermined Areas
Authors: Tomáš Seidler, Marek Mihola, Denisa Cihlarova
Abstract:
The article presents analysis results of maps of expected subsidence in undermined areas for road repair management. The analysis was done in the area of Karvina district in the Czech Republic, including undermined areas with ongoing deep mining activities or finished deep mining in years 2003 - 2009. The article discusses the possibilities of local road maintenance authorities to determine areas that will need most repairs in the future with limited data available. Using the expected subsidence maps new map of surface curvature was calculated. Combined with road maps and historical data about repairs the result came for five main categories of undermined areas, proving very simple tool for management.Keywords: GIS, Map of Subsidence, Road, Undermined Area
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1300683 MHD Stagnation Point Flow towards a Shrinking Sheet with Suction in an Upper-Convected Maxwell (UCM) Fluid
Authors: K. Jafar, R. Nazar, A. Ishak, I. Pop
Abstract:
The present analysis considers the steady stagnation point flow and heat transfer towards a permeable shrinking sheet in an upper-convected Maxwell (UCM) electrically conducting fluid, with a constant magnetic field applied in the transverse direction to flow and a local heat generation within the boundary layer, with a heat generation rate proportional to (T-T)p Using a similarity transformation, the governing system of partial differential equations is first transformed into a system of ordinary differential equations, which is then solved numerically using a finite-difference scheme known as the Keller-box method. Numerical results are obtained for the flow and thermal fields for various values of the stretching/shrinking parameter λ, the magnetic parameter M, the elastic parameter K, the Prandtl number Pr, the suction parameter s, the heat generation parameter Q, and the exponent p. The results indicate the existence of dual solutions for the shrinking sheet up to a critical value λc whose value depends on the value of M, K, and s. In the presence of internal heat absorption (Q<0) the surface heat transfer rate decreases with increasing p but increases with parameters Q and s when the sheet is either stretched or shrunk.
Keywords: Magnetohydrodynamic (MHD), boundary layer flow, UCM fluid, stagnation point, shrinking sheet.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2052682 Impact of Coal Mining on River Sediment Quality in the Sydney Basin, Australia
Authors: A. Ali, V. Strezov, P. Davies, I. Wright, T. Kan
Abstract:
The environmental impacts arising from mining activities affect the air, water, and soil quality. Impacts may result in unexpected and adverse environmental outcomes. This study reports on the impact of coal production on sediment in Sydney region of Australia. The sediment samples upstream and downstream from the discharge points from three mines were taken, and 80 parameters were tested. The results were assessed against sediment quality based on presence of metals. The study revealed the increment of metal content in the sediment downstream of the reference locations. In many cases, the sediment was above the Australia and New Zealand Environment Conservation Council and international sediment quality guidelines value (SQGV). The major outliers to the guidelines were nickel (Ni) and zinc (Zn).Keywords: Coal mine, environmental impact, produced water, sediment quality guidelines value.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1395681 Examining the Dubbing Strategies Used in the Egyptian Dubbed Version of Mulan (1998)
Authors: Shaza Melies, Saadeya Salem, Seham Kareh
Abstract:
Cartoon films are multisemiotic as various modes integrate in the production of meaning. This study aims to examine the cultural and linguistic specific references in the Egyptian dubbed cartoon film Mulan. The study examines the translation strategies implemented in the Egyptian dubbed version of Mulan to meet the cultural preferences of the audience. The study reached the following findings: Using the traditional translation strategies does not deliver the intended meaning of the source text and causes loss in the intended humor. As a result, the findings showed that in the dubbed version, translators tend to omit, change, or add information to the target text to be accepted by the audience. The contrastive analysis of the Mulan (English and dubbed versions) proves the connotations that the dubbing has taken to be accepted by the target audience. Cartoon films are multisemiotic as various modes integrate in the production of meaning. This study aims to examine the cultural and linguistic specific references in the Egyptian dubbed cartoon film Mulan. The study examines the translation strategies implemented in the Egyptian dubbed version of Mulan to meet the cultural preferences of the audience. The study reached the following findings: Using the traditional translation strategies does not deliver the intended meaning of the source text and causes loss in the intended humor. As a result, the findings showed that in the dubbed version, translators tend to omit, change, or add information to the target text to be accepted by the audience. The contrastive analysis of the Mulan (English and dubbed versions) proves the connotations that the dubbing has taken to be accepted by the target audience.Keywords: Domestication, dubbing, Mulan, translation theories.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 698680 Using Data Mining Techniques for Finding Cardiac Outlier Patients
Authors: Farhan Ismaeel Dakheel, Raoof Smko, K. Negrat, Abdelsalam Almarimi
Abstract:
In this paper we used data mining techniques to identify outlier patients who are using large amount of drugs over a long period of time. Any healthcare or health insurance system should deal with the quantities of drugs utilized by chronic diseases patients. In Kingdom of Bahrain, about 20% of health budget is spent on medications. For the managers of healthcare systems, there is no enough information about the ways of drug utilization by chronic diseases patients, is there any misuse or is there outliers patients. In this work, which has been done in cooperation with information department in the Bahrain Defence Force hospital; we select the data for Cardiac patients in the period starting from 1/1/2008 to December 31/12/2008 to be the data for the model in this paper. We used three techniques for finding the drug utilization for cardiac patients. First we applied a clustering technique, followed by measuring of clustering validity, and finally we applied a decision tree as classification algorithm. The clustering results is divided into three clusters according to the drug utilization, for 1603 patients, who received 15,806 prescriptions during this period can be partitioned into three groups, where 23 patients (2.59%) who received 1316 prescriptions (8.32%) are classified to be outliers. The classification algorithm shows that the use of average drug utilization and the age, and the gender of the patient can be considered to be the main predictive factors in the induced model.Keywords: Data Mining, Clustering, Classification, Drug Utilization..
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1883679 Implementation of an IoT Sensor Data Collection and Analysis Library
Authors: Jihyun Song, Kyeongjoo Kim, Minsoo Lee
Abstract:
Due to the development of information technology and wireless Internet technology, various data are being generated in various fields. These data are advantageous in that they provide real-time information to the users themselves. However, when the data are accumulated and analyzed, more various information can be extracted. In addition, development and dissemination of boards such as Arduino and Raspberry Pie have made it possible to easily test various sensors, and it is possible to collect sensor data directly by using database application tools such as MySQL. These directly collected data can be used for various research and can be useful as data for data mining. However, there are many difficulties in using the board to collect data, and there are many difficulties in using it when the user is not a computer programmer, or when using it for the first time. Even if data are collected, lack of expert knowledge or experience may cause difficulties in data analysis and visualization. In this paper, we aim to construct a library for sensor data collection and analysis to overcome these problems.
Keywords: Clustering, data mining, DBSCAN, k-means, k-medoids, sensor data.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1990678 A Novel Approach to Optimal Cutting Tool Replacement
Authors: Cem Karacal, Sohyung Cho, William Yu
Abstract:
In metal cutting industries, mathematical/statistical models are typically used to predict tool replacement time. These off-line methods usually result in less than optimum replacement time thereby either wasting resources or causing quality problems. The few online real-time methods proposed use indirect measurement techniques and are prone to similar errors. Our idea is based on identifying the optimal replacement time using an electronic nose to detect the airborne compounds released when the tool wear reaches to a chemical substrate doped into tool material during the fabrication. The study investigates the feasibility of the idea, possible doping materials and methods along with data stream mining techniques for detection and monitoring different phases of tool wear.Keywords: Tool condition monitoring, cutting tool replacement, data stream mining, e-Nose.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1869677 Road Traffic Accidents Analysis in Mexico City through Crowdsourcing Data and Data Mining Techniques
Authors: Gabriela V. Angeles Perez, Jose Castillejos Lopez, Araceli L. Reyes Cabello, Emilio Bravo Grajales, Adriana Perez Espinosa, Jose L. Quiroz Fabian
Abstract:
Road traffic accidents are among the principal causes of traffic congestion, causing human losses, damages to health and the environment, economic losses and material damages. Studies about traditional road traffic accidents in urban zones represents very high inversion of time and money, additionally, the result are not current. However, nowadays in many countries, the crowdsourced GPS based traffic and navigation apps have emerged as an important source of information to low cost to studies of road traffic accidents and urban congestion caused by them. In this article we identified the zones, roads and specific time in the CDMX in which the largest number of road traffic accidents are concentrated during 2016. We built a database compiling information obtained from the social network known as Waze. The methodology employed was Discovery of knowledge in the database (KDD) for the discovery of patterns in the accidents reports. Furthermore, using data mining techniques with the help of Weka. The selected algorithms was the Maximization of Expectations (EM) to obtain the number ideal of clusters for the data and k-means as a grouping method. Finally, the results were visualized with the Geographic Information System QGIS.Keywords: Data mining, K-means, road traffic accidents, Waze, Weka.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1188676 Design of Personal Job Recommendation Framework on Smartphone Platform
Authors: Chayaporn Kaensar
Abstract:
Recently, Job Recommender Systems have gained much attention in industries since they solve the problem of information overload on the recruiting website. Therefore, we proposed Extended Personalized Job System that has the capability of providing the appropriate jobs for job seeker and recommending some suitable information for them using Data Mining Techniques and Dynamic User Profile. On the other hands, company can also interact to the system for publishing and updating job information. This system have emerged and supported various platforms such as web application and android mobile application. In this paper, User profiles, Implicit User Action, User Feedback, and Clustering Techniques in WEKA libraries were applied and implemented. In additions, open source tools like Yii Web Application Framework, Bootstrap Front End Framework and Android Mobile Technology were also applied.Keywords: Recommendation, user profile, data mining, web technology, mobile technology.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2137675 Graphical Password Security Evaluation by Fuzzy AHP
Authors: Arash Habibi Lashkari, Azizah Abdul Manaf, Maslin Masrom
Abstract:
In today's day and age, one of the important topics in information security is authentication. There are several alternatives to text-based authentication of which includes Graphical Password (GP) or Graphical User Authentication (GUA). These methods stems from the fact that humans recognized and remembers images better than alphanumerical text characters. This paper will focus on the security aspect of GP algorithms and what most researchers have been working on trying to define these security features and attributes. The goal of this study is to develop a fuzzy decision model that allows automatic selection of available GP algorithms by taking into considerations the subjective judgments of the decision makers who are more than 50 postgraduate students of computer science. The approach that is being proposed is based on the Fuzzy Analytic Hierarchy Process (FAHP) which determines the criteria weight as a linear formula.Keywords: Graphical Password, Authentication Security, Attack Patterns, Brute force attack, Dictionary attack, Guessing Attack, Spyware attack, Shoulder surfing attack, Social engineering Attack, Password Entropy, Password Space.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1922674 Evaluating some Feature Selection Methods for an Improved SVM Classifier
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 features selection methods to reduce the dimensionality of the document-representation vector. Four feature selection methods are evaluated: Random Selection, Information Gain (IG), Support Vector Machine (called SVM_FS) and Genetic Algorithm with SVM (GA_FS). We showed that the best results were obtained with SVM_FS and GA_FS methods for a relatively small dimension of the features vector comparative with the IG method that involves longer vectors, for quite similar classification accuracies. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).
Keywords: Features selection, learning with kernels, support vector machine, genetic algorithms and classification.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1522673 Fuzzy Relatives of the CLARANS Algorithm With Application to Text Clustering
Authors: Mohamed A. Mahfouz, M. A. Ismail
Abstract:
This paper introduces new algorithms (Fuzzy relative of the CLARANS algorithm FCLARANS and Fuzzy c Medoids based on randomized search FCMRANS) for fuzzy clustering of relational data. Unlike existing fuzzy c-medoids algorithm (FCMdd) in which the within cluster dissimilarity of each cluster is minimized in each iteration by recomputing new medoids given current memberships, FCLARANS minimizes the same objective function minimized by FCMdd by changing current medoids in such away that that the sum of the within cluster dissimilarities is minimized. Computing new medoids may be effected by noise because outliers may join the computation of medoids while the choice of medoids in FCLARANS is dictated by the location of a predominant fraction of points inside a cluster and, therefore, it is less sensitive to the presence of outliers. In FCMRANS the step of computing new medoids in FCMdd is modified to be based on randomized search. Furthermore, a new initialization procedure is developed that add randomness to the initialization procedure used with FCMdd. Both FCLARANS and FCMRANS are compared with the robust and linearized version of fuzzy c-medoids (RFCMdd). Experimental results with different samples of the Reuter-21578, Newsgroups (20NG) and generated datasets with noise show that FCLARANS is more robust than both RFCMdd and FCMRANS. Finally, both FCMRANS and FCLARANS are more efficient and their outputs are almost the same as that of RFCMdd in terms of classification rate.Keywords: Data Mining, Fuzzy Clustering, Relational Clustering, Medoid-Based Clustering, Cluster Analysis, Unsupervised Learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2386672 Finding Fuzzy Association Rules Using FWFP-Growth with Linguistic Supports and Confidences
Authors: Chien-Hua Wang, Chin-Tzong Pang
Abstract:
In data mining, the association rules are used to search for the relations of items of the transactions database. Following the data is collected and stored, it can find rules of value through association rules, and assist manager to proceed marketing strategy and plan market framework. In this paper, we attempt fuzzy partition methods and decide membership function of quantitative values of each transaction item. Also, by managers we can reflect the importance of items as linguistic terms, which are transformed as fuzzy sets of weights. Next, fuzzy weighted frequent pattern growth (FWFP-Growth) is used to complete the process of data mining. The method above is expected to improve Apriori algorithm for its better efficiency of the whole association rules. An example is given to clearly illustrate the proposed approach.Keywords: Association Rule, Fuzzy Partition Methods, FWFP-Growth, Apiroir algorithm
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1639671 AniMoveMineR: Animal Behavior Exploratory Analysis Using Association Rules Mining
Authors: Suelane Garcia Fontes, Silvio Luiz Stanzani, Pedro L. Pizzigatti Corrła Ronaldo G. Morato
Abstract:
Environmental changes and major natural disasters are most prevalent in the world due to the damage that humanity has caused to nature and these damages directly affect the lives of animals. Thus, the study of animal behavior and their interactions with the environment can provide knowledge that guides researchers and public agencies in preservation and conservation actions. Exploratory analysis of animal movement can determine the patterns of animal behavior and with technological advances the ability of animals to be tracked and, consequently, behavioral studies have been expanded. There is a lot of research on animal movement and behavior, but we note that a proposal that combines resources and allows for exploratory analysis of animal movement and provide statistical measures on individual animal behavior and its interaction with the environment is missing. The contribution of this paper is to present the framework AniMoveMineR, a unified solution that aggregates trajectory analysis and data mining techniques to explore animal movement data and provide a first step in responding questions about the animal individual behavior and their interactions with other animals over time and space. We evaluated the framework through the use of monitored jaguar data in the city of Miranda Pantanal, Brazil, in order to verify if the use of AniMoveMineR allows to identify the interaction level between these jaguars. The results were positive and provided indications about the individual behavior of jaguars and about which jaguars have the highest or lowest correlation.Keywords: Data mining, data science, trajectory, animal behavior.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 884670 Feature Selection Approaches with Missing Values Handling for Data Mining - A Case Study of Heart Failure Dataset
Authors: N.Poolsawad, C.Kambhampati, J. G. F. Cleland
Abstract:
In this paper, we investigated the characteristic of a clinical dataseton the feature selection and classification measurements which deal with missing values problem.And also posed the appropriated techniques to achieve the aim of the activity; in this research aims to find features that have high effect to mortality and mortality time frame. We quantify the complexity of a clinical dataset. According to the complexity of the dataset, we proposed the data mining processto cope their complexity; missing values, high dimensionality, and the prediction problem by using the methods of missing value replacement, feature selection, and classification.The experimental results will extend to develop the prediction model for cardiology.Keywords: feature selection, missing values, classification, clinical dataset, heart failure.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3200669 Seasonal Variation of the Impact of Mining Activities on Ga-Selati River in Limpopo Province, South Africa
Authors: Joshua N. Edokpayi, John O. Odiyo, Patience P. Shikwambana
Abstract:
Water is a very rare natural resource in South Africa. Ga-Selati River is used for both domestic and industrial purposes. This study was carried out in order to assess the quality of Ga-Selati River in a mining area of Limpopo Province-Phalaborwa. The pH, Electrical Conductivity (EC) and Total Dissolved Solids (TDS) were determined using a Crinson multimeter while turbidity was measured using a Labcon Turbidimeter. The concentrations of Al, Ca, Cd, Cr, Fe, K, Mg, Mn, Na and Pb were analysed in triplicate using a Varian 520 flame atomic absorption spectrometer (AAS) supplied by PerkinElmer, after acid digestion with nitric acid in a fume cupboard. The average pH of the river from eight different sampling sites was 8.00 and 9.38 in wet and dry season respectively. Higher EC values were determined in the dry season (138.7 mS/m) than in the wet season (96.93 mS/m). Similarly, TDS values were higher in dry (929.29 mg/L) than in the wet season (640.72 mg/L) season. These values exceeded the recommended guideline of South Africa Department of Water Affairs and Forestry (DWAF) for domestic water use (70 mS/m) and that of the World Health Organization (WHO) (600 mS/m), respectively. Turbidity varied between 1.78-5.20 and 0.95-2.37 NTU in both wet and dry seasons. Total hardness of 312.50 mg/L and 297.75 mg/L as the concentration of CaCO3 was computed for the river in both the wet and the dry seasons and the river water was categorised as very hard. Mean concentration of the metals studied in both the wet and the dry seasons are: Na (94.06 mg/L and 196.3 mg/L), K (11.79 mg/L and 13.62 mg/L), Ca (45.60 mg/L and 41.30 mg/L), Mg (48.41 mg/L and 44.71 mg/L), Al (0.31 mg/L and 0.38 mg/L), Cd (0.01 mg/L and 0.01 mg/L), Cr (0.02 mg/L and 0.09 mg/L), Pb (0.05 mg/L and 0.06 mg/L), Mn (0.31 mg/L and 0.11 mg/L) and Fe (0.76 mg/L and 0.69 mg/L). Results from this study reveal that most of the metals were present in concentrations higher than the recommended guidelines of DWAF and WHO for domestic use and the protection of aquatic life.Keywords: Contamination, mining activities, surface water, trace metals.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1962668 Skin Effect: A Natural Phenomenon for Minimization of Ground Bounce in VLSI RC Interconnect
Authors: Shilpi Lavania
Abstract:
As the frequency of operation has attained a range of GHz and signal rise time continues to increase interconnect technology is suffering due to various high frequency effects as well as ground bounce problem. In some recent studies a high frequency effect i.e. skin effect has been modeled and its drawbacks have been discussed. This paper strives to make an impression on the advantage side of modeling skin effect for interconnect line. The proposed method has considered a CMOS with RC interconnect. Delay and noise considering ground bounce problem and with skin effect are discussed. The simulation results reveal an advantage of considering skin effect for minimization of ground bounce problem during the working of the model. Noise and delay variations with temperature are also presented.
Keywords: Interconnect, Skin effect, Ground Bounce, Delay, Noise.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3125667 Future Logistics - Challenges, Requirements and Solutions for Logistics Networks
Authors: Martin Roth, Axel Klarmann, Bogdan Franczyk
Abstract:
The importance of logistics has changed enormously in the last few decades. While logistics was formerly one of the core functions of most companies, logistics or at least parts of their functions are nowadays outsourced to external logistic service providers in terms of contracts. As a result of this shift new business models like the fourth party logistics provider emerged, which designs, plans and monitors the resulting logistics networks. This new business model and topics such as Synchromodality or Big Data impose new requirements on the underlying IT, which cannot be met with conventional concepts and approaches. In this paper, the challenges of logistics network monitoring are outlined by using a scenario. The most common layers in a logical multilayered architecture for an information system are used to point out the arising challenges for IT. In addition, first appropriate solution approaches are introduced.
Keywords: Complex Event Processing, Fourth Party Logistics Service Provider, Logistics monitoring, Synchromodality.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3361666 Efficient Implementation of Serial and Parallel Support Vector Machine Training with a Multi-Parameter Kernel for Large-Scale Data Mining
Authors: Tatjana Eitrich, Bruno Lang
Abstract:
This work deals with aspects of support vector learning for large-scale data mining tasks. Based on a decomposition algorithm that can be run in serial and parallel mode we introduce a data transformation that allows for the usage of an expensive generalized kernel without additional costs. In order to speed up the decomposition algorithm we analyze the problem of working set selection for large data sets and analyze the influence of the working set sizes onto the scalability of the parallel decomposition scheme. Our modifications and settings lead to improvement of support vector learning performance and thus allow using extensive parameter search methods to optimize classification accuracy.
Keywords: Support Vector Machines, Shared Memory Parallel Computing, Large Data
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1568