Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

Matrix Factorization Techniques for Recommender Systems

Coronary heart disease

A survey on deep learning for big data

Development of technology in educational field brings the easier ways through the variety of facilitation for learning process, sharing files, giving assignment and assessment. Automated Essay Scoring (AES) is one of the development systems for determining a score automatically from text document source to facilitate the correction and scoring by utilizing applications that run on the computer. AES process is used to help the lecturers to score efficiently and effectively. Besides it can reduce the subjectivity scoring problem. However, implementation of AES depends on many factors and cases, such as language and mechanism of scoring process especially for essay scoring. A number of methods implemented for weighting the terms from document and reaching the solutions for handling comparative level between documents answer and expert's document still defined. In this research, we implemented the weighting of Term Frequency — Inverse Document Frequency (TF-IDF) method and Cosine Similarity with the measuring degree concept of similarity terms in a document. Tests carried out on a number of Indonesian text-based documents that have gone through the stage of pre-processing for data extraction purposes. This process results is in a ranking of the document weight that have closesness match level with expert's document.

Cosine similarity to determine similarity measure: Study case in online essay assessment

Heart disease is any disease that affects the normal condition and functionality of heart. Coronary Artery Disease (CAD) is the most common. It is caused by the accumulation of plaques within the walls of the coronary arteries that supply blood to the heart muscles. It may lead to continued temporary oxygen deprivation that will result in the damage of heart muscles. CAD caused more than 7,000,000 deaths every year in the worldwide. It is the second cause of death in Malaysia and the major cause of death in the world. To diagnose CAD, cardiologists usually perform many diagnostic steps. Unfortunately, the results of the diagnostic tests are difficult to interpret which do not always provide definite answer, but may lead to different opinion. To help cardiologists providing correct diagnosis of CAD in less expensive and non-invasive manner, many researchers had developed decision support system to diagnose CAD. 

A fuzzy decision support system for the diagnosis of coronary artery disease based on rough set theory is proposed in this thesis. The objective is to develop an evidence based fuzzy decision support system for the diagnosis of coronary artery disease. This proposed system is based on evidences or raw medical data sets, which are taken from University California Irvine (UCI) database. The proposed system is designed to be able to handle the uncertainty, incompleteness and heterogeneity of data sets. Artificial Neural Network with Rough Set Theory attribute reduction (ANNRST) is proposed is the imputation method to solve the incompleteness of data sets. Evaluations of ANNRST based on classifiers performance and rule filtering are proposed by comparing ANNRST and other methods using classifiers and during rule filtering process. RST rule induction is applied to ANNRST imputed data sets. Numerical values are discretized using Boolean reasoning method. Rule selection based on quality and importance is proposed. RST rule importance measure is used to select the most important high quality rules. The selected rules are used to build fuzzy decision support systems. Fuzzification based on discretization cuts and fuzzy rule weighing based on rule quality are proposed. Mamdani inference method is used to provide the decision with centroid defuzzification to give numerical results, which represent the possibility of blocking in coronary arteries. 

The results show that proposed ANNRST has similar performance to ANN and outperforms k-Nearest Neighbour (k-NN) and Concept Most Common attribute value Filling (CMCF). ANNRST is simpler than ANN because it has fewer input attributes and more suitable to be applied for missing data imputation problem. ANNRST also provides strong relationship between original and imputed data sets. It is shown that ANNRST provide better RST rule based classifier than CMCF and k-NN during rule filtering process. Proposed RST based rule selection also performs better than other filtering methods. Developed Fuzzy Decision Support System (FDSS) provides better performance compared to multi layer perceptron ANN, k-NN, rule induction method called C4.5 and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) applied on UCI CAD data sets and Ipoh Specialist Hospital’s patients. FDSS has transparent knowledge representation, heterogeneous and incomplete input data handling capability. FDSS is able to give the approximate percentage of blocking of coronary artery based on 13 standard attributes based on historical, simple blood test and ECG data, etc, where coronary angiography or cardiologist can not give the percentage. The results of FDSS were evaluated by three local cardiologists and considered to be efficient and useful.

Diagnosis of Coronary Artery Disease Using Artificial Intelligence Based Decision Support System

At recent time, the statistical based language model and neural based language model are still dominating the researches in the field of machine translation. The statistical based machine translation today is the fastest one but it has a weakness in term of accuracy. In contrast, the neural based network has higher accuracy but has a very slow computation process. In this research, a comparison between neural based network that adopts Recurrent Neural Network (RNN) and statistical based network with n-gram model for two-way English-Indonesian Machine Translation (MT) is conducted. The perplexity value evaluation of both models show that the use of RNN obtains a more excellent result. Meanwhile, Bilingual Evaluation Understudy (BLEU) and Rank-based Intuitive Bilingual Evaluation Score (RIBES) values increase by 1.1 and 1.6 higher than the results obtained using statistical based.

Recurrent neural network language model for English-Indonesian Machine Translation: Experimental study

In this research, artificial neural network (ANN) combined with rough set theory (RST), named as ANNRST, is proposed to predict missing values of attribute. The prediction of missing values of attribute is applied on heart disease data from UCI datasets. The ANN used is multilayer perceptron (MLP) with resilient back-propagation learning. RST can reduce the dimensionality of attributes through its reduct. Reduct is used as input of ANN combined with decision attribute. By simulating of missing values, the prediction accuracy of ANN is compared to ANNRST. The accuracy of ANNRST is also compared with missing data imputation ofk-Nearest Neighbor (k-NN), most common attribute value method and ANN with piecewise linear network-orthonormal least square feature selection (PLN-OLS). Simulation results show that ANNRST can predict the missing value with maximum accuracy close to ANN without dimensionality reduction (pure ANN) and outperform k-NN, most common attribute value method, and ANN with PLN-OLS.

Missing Attribute Value Prediction Based on Artificial Neural Network and Rough Set Theory

The growth of vehicles in Yogyakarta Province, Indonesia is not proportional to the growth of roads. This problem causes severe traffic jam in many main roads. Common traffic anomalies detection using surveillance camera requires manpower and costly, while traffic anomalies detection with crowdsourcing mobile applications are mostly owned by private. This research aims to develop a real-time traffic classification by harnessing the power of social network data, Twitter. In this study, Twitter data are processed to the stages of preprocessing, feature extraction, and tweet classification. This study compares classification performance of three machine learning algorithms, namely Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT). Experimental results show that SVM algorithm produced the best performance among the other algorithms with 99.77% and 99.87% of classification accuracy in balanced and imbalanced data, respectively. This research implies that social network service may be used as an alternative source for traffic anomalies detection by providing information of traffic flow condition in real-time.

Noor Akhmad Setiawan

Papers

Cosine similarity to determine similarity measure: Study case in online essay assessment

Diagnosis of Coronary Artery Disease Using Artificial Intelligence Based Decision Support System

Recurrent neural network language model for English-Indonesian Machine Translation: Experimental study

Missing Attribute Value Prediction Based on Artificial Neural Network and Rough Set Theory

Real-time traffic classification with Twitter data mining