Data Mining Practical Machine Learning Tools and Techniques

C4.5: Programs for Machine Learning (書評)

In the recent years, the emergence of data mining techniques in the research industries makes it possible to extract valuable information from huge volume of data. Good understanding of data mining...

Mining gene expression data using data mining techniques: A critical review

Objective: In this study, a systematic effort was employed to identify and review data mining concept, tasks and model evaluation techniques, Knowledge Discovery and Data mining process Model (KDDM) model process and research articles published with reputable journal publishers that employed data mining techniques for diagnosis of Diabetes Mellitus. Method/Analysis: The findings from this work have been drawn from the published articles reviewed and the frequency analysis was used for the analysis of the reviewed works. Finding: The result of the study showed that, classification data mining task has been the most successfully and most frequently used data mining tasks for diagnosis of DM and the mostly commonly used classification data mining algorithms are Support Vector Machine and decision tree algorithms. Novelty/Improvement: In the study Support Vector Machine was realized to be most efficient data mining algorithm for diagnosis of Diabetes Mellitus using either clinical or biological and clinical dataset of Diabetes Mellitus. Despite its popularity, SVM algorithm should be further improved in the future work so as to further improve its efficiency.
Keywords: Algorithm, Data Mining, Diabetes; Diagnosis, Knowledge, Pattern

/pdf/data-mining-driven-models-for-diagnosis-of-diabetes-mellitus-1ftsshhtkt.pdf

Data Mining Driven Models for Diagnosis of Diabetes Mellitus: A Survey

Risk prediction model estimates event occurrence based on related data. Conventional statistical metrics that utilized primary data generates simple descriptive analysis that often provide insufficient knowledge for decision making. In contrast, data mining techniques that have the capability to find hidden pattern from the secondary data in large databases and create prediction for de- sired output has become a popular approach to develop any risk prediction model. In healthcare particularly, data mining techniques can be applied in disease risk prediction model to provide reliable prediction on the possibility of acquiring the disease based on individual’s clinical and non-clinical data. Due to the increased use of data mining in healthcare, this study aims at identifying the data mining techniques and algorithms that are commonly implemented in studies related to various disease risk prediction model as well as finding the accuracy of the algorithms. The accuracy evaluation consists of various method, but this paper is focusing on overall accuracy which is measured by the total number of correctly predicted output over the total number of prediction. A systematic literature review approach that search across five databases found 170 articles, of which 7 articles were selected in the final process. This review found that most prediction model used classification technique, with a focus on decision tree, neural network, support vector machines, and Naive Bayes algorithms where heart-related disease is commonly studied. Further research can apply similar algorithms to develop risk prediction model for other types of diseases, such as infectious disease prediction.

Data mining techniques for disease risk prediction model: A systematic literature review

Data Mining (sometimes called data or knowledge discovery) is the process of analyzing data from different perspectives and summarizing it into useful information – making it more accurate, reliable, efficient and beneficial. In data mining various techniques are usedclassification, clustering, regression, association mining. These techniques can be used on various types of data; it may be stream data, one dimensional, two dimensional or multi-dimensional data. In this paper we analyze the data mining techniques based on various parameters. All data mining techniques used in various fields for prediction and extraction of useful data or knowledge from a large data base is analyzed and each data mining technique has different performance. General Terms Data mining (sometimes called data or knowledge discovery) is the process of analyzing data from different perspectives and summarizing it into useful information. classification is a general process related to categorization, the process in which ideas and objects are recognized, differentiated, and understood. A classification system is an approach to accomplishing classification.

/pdf/analysis-of-prediction-techniques-based-on-classification-4d60fztucv.pdf

Analysis of Prediction Techniques based on Classification and Regression

A leading cause of death from natural disasters over the last 50years is witnessed by none other than earthquake occurrences which have a negative economic impact on the world and claimed thousands of lives over the years, causing devastation to properties. In this paper, a novel Ensemble Earthquake Prediction Method (EEPM) is proposed and implemented to produce a strong learner (ensemble method) having better accuracy in prediction, less variance, and less errors. Data (parameters) which is continuous in nature is collected from two countries, India and Nepal, for five years, and surveyor’s data (precursor) which is categorical in nature is collected from three countries India, Nepal, and Kenya for five years on the specific earthquake-prone regions. The preprocessed data is generated by combining parameters and precursor data. EEPM focuses on detecting the accurate and better early signs of an earthquake and finding the probability of occurrence of an earthquake in the specified region, i.e., better prediction and robustness. The results of EEPM produced better 
 
 
 
 R
 
 
 2
 
 
 
 and less variance and less error in comparison to individual machine learning methods as well as better accuracy 87.8%, compared to state-of-the-art ensemble methods. The prediction of earthquake will alarm not only the people of the society but also the different organizations to explain the appropriate range of magnitude and dynamics of occurrence of earthquake.

/pdf/a-novel-ensemble-earthquake-prediction-method-eepm-by-2aq1od0d.pdf

A Novel Ensemble Earthquake Prediction Method (EEPM) by Combining Parameters and Precursors

Stock market prediction is a technique recently used to predict the future price of the stock. This research study mainly focuses on comparing the performance of Support vector machine and Long Short Term Memory (LS TM) in stock prediction. However, LS TM faces two challenges during the prediction of the stock market: Overfitting and Feature Engineering, when it is trained on the existing data it cannot be reflect on the current market trends. It requires a lot of training data to impact the performance. To overcome these limitations and improve accuracy, SVM has been selected to predict stock market prices. By comparing both of them respectively to each other helps to measure the performance of various algorithms. Here, the accuracy is used as a metric for evaluation of the efficiency of algorithms. To achieve this, supervised machine learning techniques like Support Vector Machine(S VM), Linear Regression and Decision Trees are used to forecast the stock value of a company. Then, the data is preprocessed and split into training and testing sets. Then, a collection of supervised machine learning mechanisms like SVM are employed. The results show that Support Vector Machine delivers better performance with an accuracy of 91%.

An Evaluation of Stock Market Prediction using Supervised Machine Learning Techniques

Augmented Reality interfaces have been extensively researched throughout the past few decades, with many user studies being conducted. This paper examines the landscape of research on augmented reality. We summarise the overall contribution of each field and will then present examples of influential user studies. We identify other areas of research that would be advantageous to possible future studies. There is a trend toward hands-free applications and most user testing is carried out in the laboratory. This research will also help researchers learning the best practices when conducting AR user studies.

Pinki Sagar

Papers

Analysis of Prediction Techniques based on Classification and Regression

A Novel Ensemble Earthquake Prediction Method (EEPM) by Combining Parameters and Precursors

An Evaluation of Stock Market Prediction using Supervised Machine Learning Techniques

A Systematic Review of Tools Available in the Field of Augmented Reality