Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

When is nearest neighbor meaningful

3. Classes should hide their data, we call this encapsulation, only providing a small number of controlled methods or functions in the interface for accessing that data. These factors taken together enable separation of interface from implementation. The actual designs of the algorithms employed inside the classes can be changed as better, more efficient algorithms are found. After a design is complete, changes in a class implementation must not affect its interface. The effect on current and future users is then only in terms of efficiency: their applications need not be recoded to take advantage of the new class implementation. The advantages of separation of interface from implementation include rapid prototyping and graceful refinement. See Fig. 3.

Object-Oriented Analysis and Design.

This paper introduces a web image search reranking approach that explores multiple modalities in a graph-based learning scheme. Different from the conventional methods that usually adopt a single modality or integrate multiple modalities into a long feature vector, our approach can effectively integrate the learning of relevance scores, weights of modalities, and the distance metric and its scaling for each modality into a unified scheme. In this way, the effects of different modalities can be adaptively modulated and better reranking performance can be achieved. We conduct experiments on a large dataset that contains more than 1000 queries and 1 million images to evaluate our approach. Experimental results demonstrate that the proposed reranking approach is more robust than using each individual modality, and it also performs better than many existing methods.

Multimodal Graph-Based Reranking for Web Image Search

Social networking sites such as Twitter and Facebook attracts millions of users across the world and their interaction with social networking has affected their life. This popularity in social networking has led to different problems including the possibility of exposing incorrect information to their users through fake accounts which results to the spread of malicious content. This situation can result to a huge damage in the real world to the society. In our study, we present a classification method for detecting the fake accounts on Twitter. We have preprocessed our dataset using a supervised discretization technique named Entropy Minimization Discretization (EMD) on numerical features and analyzed the results of the Naive Bayes algorithm.

Twitter fake account detection

Owing to the rapid growth of the World Wide Web, the number of documents that can be accessed via the Internet explosively increases with each passing day. Considering news portals in particular, sometimes documents related to categories such as technology, sports and politics seem to be in the wrong category or documents are located in a generic category called others. At this point, text categorization TC, which is generally addressed as a supervised learning task is needed. Although there are substantial number of studies conducted on TC in other languages, the number of studies conducted in Turkish is very limited owing to the lack of accessibility and usability of datasets created. In this paper, a new dataset named TTC-3600, which can be widely used in studies of TC of Turkish news and articles, is created. TTC-3600 is a well-documented dataset and its file formats are compatible with well-known text mining tools. Five widely used classifiers within the field of TC and two feature selection methods are evaluated on TTC-3600. The experimental results indicate that the best accuracy criterion value 91.03% is obtained with the combination of Random Forest classifier and attribute ranking-based feature selection method in all comparisons performed after pre-processing and feature selection steps. The publicly available TTC-3600 dataset and the experimental results of this study can be utilized in comparative experiments by other researchers.

Ttc-3600

This article investigates the competence of ensemble learning techniques in solar irradiance prediction. It was seen from the literature survey, an ensemble tree model, random forests is studied more frequently as ensemble models. However, ensemble of support vector regression (SVR) and artificial neural networks (ANN) is also possible. So, this study is the first detailed evaluation of ensemble models in solar irradiance estimation domain. Boosting and bagging ensembles of SVR, ANN and decision tree (DT), are developed to estimate solar irradiance in hourly basis in five cities in Turkey. First frequently used base models (SVR, ANN, and DT) are created and tested with the use of 5 years meteorological data. Then boosting and bagging ensembles of the base models are developed and tested with the same data. The base models are compared with their ensemble counterparts in terms of average coefficient of determination (R2) and root mean squared error (RMSE). The comparative results show that boosting and bagging ensemble models improve SVR, ANN, and DT in terms of RMSE between 4.6 and 14.6% in average. The results show empirically that ensemble models improve prediction accuracies of various base regression models and it can be applied to other machine learning models used in solar irradiance prediction.

A New Approach for Prediction of Solar Radiation with Using Ensemble Learning Algorithm

Multiple-classifiers in software quality engineering: Combining predictors to improve software fault prediction ability

This paper presents a hybrid methodology for Turkish sentiment analysis, which combines the lexicon-based and machine learning (ML)-based approaches. On the lexicon-based side, we use a sentiment dictionary that is extended with a synonyms lexicon. Besides this, we tackle the classification problem with three supervised classifiers, naive Bayes, support vector machines, and J48, on the ML side. Our hybrid methodology combines these two approaches by generating a new lexicon-based value according to our feature generation algorithm and feeds it as one of the features to machine learning classifiers. Despite the linguistic challenges caused by the morphological structure of Turkish, the experimental results show that it improves the accuracy by 7 % on average.

/pdf/a-hybrid-sentiment-analysis-method-for-turkish-3rs6dk1qxv.pdf

Deniz Kilinç

Papers

Twitter fake account detection

Ttc-3600

A New Approach for Prediction of Solar Radiation with Using Ensemble Learning Algorithm

Multiple-classifiers in software quality engineering: Combining predictors to improve software fault prediction ability

A hybrid sentiment analysis method for Turkish