Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining Practical Machine Learning Tools and Techniques

Abstract Nowadays, being in digital era the data generated by various applications are increasing drastically both row-wise and column wise; this creates a bottleneck for analytics and also increases the burden of machine learning algorithms that work for pattern recognition. This cause of dimensionality can be handled through reduction techniques. The Dimensionality Reduction (DR) can be handled in two ways namely Feature Selection (FS) and Feature Extraction (FE). This paper focuses on a survey of feature selection methods, from this extensive survey we can conclude that most of the FS methods use static data. However, after the emergence of IoT and web-based applications, the data are generated dynamically and grow in a fast rate, so it is likely to have noisy data, it also hinders the performance of the algorithm. With the increase in the size of the data set, the scalability of the FS methods becomes jeopardized. So the existing DR algorithms do not address the issues with the dynamic data. Using FS methods not only reduces the burden of the data but also avoids overfitting of the model.

/pdf/a-review-of-feature-selection-and-its-methods-172ufuz4e8.pdf

A Review of Feature Selection and Its Methods

Review: Personalizing recommendations for tourists

A deep learning method with wrapper based feature extraction for wireless intrusion detection system

Liver cancer data always consist of a large number of multidimensional datasets. A dataset that has huge features and multiple classes may be irrelevant to the pattern classification in machine learning. Hence, feature selection improves the performance of the classification model to achieve maximum classification accuracy. The aims of the present study were to find the best feature subset and to evaluate the classification performance of the predictive model. This paper proposed a hybrid feature selection approach by combining information gain and sequential forward selection based on the class-dependent technique (IGSFS-CD) for the liver cancer classification model. Two different classifiers (decision tree and naive Bayes) were used to evaluate feature subsets. The liver cancer datasets were obtained from the Cancer Hospital Thailand database. Three ensemble methods (ensemble classifiers, bagging, and AdaBoost) were applied to improve the performance of classification. The IGSFS-CD method provided good accuracy of 78.36% (sensitivity 0.7841 and specificity 0.9159) on LC_dataset-1. In addition, LC_dataset II delivered the best performance with an accuracy of 84.82% (sensitivity 0.8481 and specificity 0.9437). The IGSFS-CD method achieved better classification performance compared to the class-independent method. Furthermore, the best feature subset selection could help reduce the complexity of the predictive model.

/pdf/liver-cancer-classification-model-using-hybrid-feature-4hrkvukqpr.pdf

Liver Cancer Classification Model Using Hybrid Feature Selection Based on Class-Dependent Technique for the Central Region of Thailand

It is commonly accepted nowadays that knowing the customers is important for running successful business. Customer Relationship Management (CRM) is a relatively new approach for enterprises to manage and understand their customers in order to provide better quality of products and services. The successful implementation of CRM applications describes the CRM models of interaction between companies and their customers, both locally and globally. It is considered as a basis for company competitive advantage because it enables organizations to understand and apply the knowledge about their customers and to bring up profitable and long-lasting personalization customer relationships. This study is based on a survey of CRM adoption by the Thai SME, showing some good CRM practices. It also investigates the existing CRM tools functionalities and analyzes their applicability to the process of running the Thai SME as well as the communication among them. The overall conclusion is that currently CRM implementation in Thai SME is still far from what should be and development of respective intelligent advisory system is necessary.

Analysis of the Readiness of Thai SME for Applying CRM

Class imbalance problems have been found in many medical data in recent years. Data are imbalanced when the distributions of classes are highly imbalanced that means the number of instances of one class is very different to the other classes. Feature selection combined with over-sampling technique (FOT) is proposed to preprocess data before classifying our dataset, imbalanced breast cancer. We used feature selection techniques, Consistency Subset Evaluation, at the beginning to remove insignificant attributes of data. The remaining attributes were fed into over-sampling phase to adjust instances in the minority class. After preprocessed the dataset, we classified data using three classification algorithms, decision tree, BayesNet, and OneR. The f-values of classification data using FOT are 0.76, 0.638, and 0.64, respectively. These are greater than the f-values of three above classifications without FOT as, 0.561, 0.518, and 0.512, respectively. The experimental results indicated that FOT achieves better f-values than non-FOT preprocessing and have performed well in improving the performance of classifiers on this dataset, especially, decision tree.

Preprocessing of imbalanced breast cancer data using feature selection combined with over-sampling technique for classification

The trend of industry tourism GDP is increasing in every year that speculates from statistics of the World Travel & Tourism Council (2018). Moreover, travel industry not only considered as the most dynamic sector but also the most importance generator of income and jobs in the country. Thus, the prototype for tourism plans are needed for strategic planning. Currently, social web is a great tool for providing useful insights about tourist behaviors especially with the text data that comes from travelers' opinions. In this work, we use sequential patterns of users' behavior which are ordered by time from tourist including opinions, reviews as our input data. Then, we use Convolutional Long Short-Term Deep Learning (CLSTDL) which is a deep learning technique that combines Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) to predict the expected location. During the process, the output of CNN will be fed into LSTM to learn the sequence pattern behavior of traveler. The model output is then used to predict the next location that particular travelers are likely to go. The experimental results have shown that CLSTDL outperforms other models when evaluating with the accuracy and loss metrics.

Prediction of Tourist Behaviour: Tourist Visiting Places by Adapting Convolutional Long Short-Term Deep Learning

Tourism is one of the main industries which bring about monetary to its country. To survive in the competitive industries these tourism organizations must have innovative strategies to carry on their business. One of the tools is tourism market segmentation which is used for strategic planning. This study presents inbound tourist market segmentation with combined algorithms using K-Means and Decision Tree. The study was divided into two phases. In the clustering phase, the segmentation was performed by Self Organizing Map (SOM) and K-Means. SOM used for determining the appropriate number of cluster. Then, K-Means used for refined the tourist clusters. The results of clustering phase were analyzed. In the classification phase, three classifiers were compared the performances of predictability by using the output provided by K-Means, i.e. Decision Tree, NaYve Bayes and Multilayer Perceptron (MLP). The experimental results indicated that SOM provided 6 clusters and K-Means gave better performance than SOM guided by Silhouette, Root Means Square Standard Deviation (RMSSTD) and R Square (RS). The predictive ability of J48 Decision Tree outperformed both of MLP and NaYve Bayes based on the tourist variables. J48 Decision Tree indicated the accuracy as 99.54%. The results of this study can be used for tourism management products and services.

Anongnart Srivihok

Papers

Liver Cancer Classification Model Using Hybrid Feature Selection Based on Class-Dependent Technique for the Central Region of Thailand

Analysis of the Readiness of Thai SME for Applying CRM

Preprocessing of imbalanced breast cancer data using feature selection combined with over-sampling technique for classification

Prediction of Tourist Behaviour: Tourist Visiting Places by Adapting Convolutional Long Short-Term Deep Learning

Inbound tourists segmentation with combined algorithms using K-Means and Decision Tree