The equivalency between a decision tree for classification and a feedback neural network

For a university student, the main measure of success is whether or not they pass the modules for which they are enrolled. It is not always easy for a lecturer to determine whether or not a student will be successful as there may be various factors on which the final result of a student depends. Applying rules or common insights might aid a lecturer in identifying students who are struggling in a specific module. This may afford the lecturer the opportunity to devise an intervention; so as to enhance the chances of the student passing the module. To facilitate the gathering of information on which to base possible student academic interventions, this study makes use of an artificial neural network and decision tree to derive a series of insights and rules which a lecturer may use to identify struggling students. The artificial neural network and decision tree are both trained using supervised learning techniques. Individually, both the neural network and decision tree have an accuracy in excess of 77% and a sensitivity in excess of 83% on a test data set. Both models show a moderate level of agreement with a pre-labelled dataset.

Machine learning algorithms are used to analyze medical data sets effectively in present. Today machine learning gives us several necessary tools for intelligent data analysis and research. Especially in very recent years, the digital world has provided relatively inexpensive and available means to collect and store the data. The main aim is to implement supervised machine learning concept by using datasets regarding blood cells collected from blood cells detecting and counting sensors, of a human as the input which is trained by artificial neural network algorithm and apply decision tree classification learning algorithm to perform classification which results in recognizing and also possibly predict the disease based on the nature of blood cells and classify accordingly. Artificial Neural network algorithm seems to avoid pruning problem and has higher efficiency and accuracy in training the datasets. Also the using of Decision tree is because they are easy to interpret, understand and also possess non-linear characteristics between values. This holds well the performance of the tree constructed which gives better outputs. Beside all the application developed using machine learning in day today life, the use of such learning algorithm in such medical application will enhance and benefit the medical field.

Predictive systems use historical and other available data to predict an event. In this paper we tries to compare the power of Artificial Neural Network (ANN) and Decision Tree (DT) in prediction of aerology events with time series streams and events stream using combination of K-means clustering algorithm and Decision Tree C5 algorithm and ANN. We try to find the effective parameters on events occurrences. Firstly, we find the closest time series record for any events; therefore, we have gathered different parameters value when an event is occurring. Using K-means we add a field to dataset which determines the cluster of each record and after that we predict the events using C5 algorithm and ANN. This framework and time series model can predict future events efficiently. We gathered 1961 until 2005 data of aerology organization for Tehran Mehrabad Station. This data contains some fields such as wet bulb, relative humidity, amount of cloud, wind speed and etc. This dataset includes 17 types of events. Using this framework the closest event can be predicted. The C5 method is able to predict events with 79.55% accuracy and ANN with 72.87% accuracy. Applying K-means clustering algorithm the prediction increase to 94.59% for C5 and 92.66% accuracies for ANN. We use 10-fold cross validation to evaluate our prediction rate. This framework is the first estimation in the area of event prediction for a huge dataset of aerology and can be extended in many different datasets in any other environments.

The county level of urbanization quality analysis and classification play an important role in county economic growth and improve benefit of healthy development of urbanization in China. According to the county level of urbanization quality data which is large scale and imbalance, this paper presented a support vector machine model to classify the county level of urbanization quality. The method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding the county level of urbanization quality classification for Guanzhong urban agglomeration. It is found that the method has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for county level of urbanization quality classification and prediction.

Coordinated development degree of county socio-economic system analysis and prediction play an important role in urban agglomeration coordinated development and improve benefit of regional coordinated development in China. According to the county socio-economic system data which is large scale and imbalance, this paper presented a support vector machine (SVM) model to predict coordinated development degree of county socio-economic system. In order to improve the discrimination precision of SVM in classification, a Genetic Algorithm (GA) was used to optimize SVM parameters in the solution space. The method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding coordinated development degree of county socio-economic system prediction for Guanzhong urban agglomeration. It is found that the method has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for coordinated development degree of county socio-economic system classification and prediction.

In this paper, we have compared the classifier algorithms including C4.5 decision tree, le artificial neural network (ANN), artificial immune recognition system (AIRS), and adaptive neuro-fuzzy inference system (ANFIS) in the diagnosis of obstructive sleep apnea syndrome (OSAS), which is an important disease that affects both the right and the left cardiac ventricle. The goal of this study was to find the best classifier model on the diagnosis of OSAS. The clinical features were obtained from Polysomnography device as a diagnostic tool for obstructive sleep apnea in patients clinically suspected of suffering this disease in this study. The clinical features are arousals index, apneahypopnea index (AHI), SaO2 minimum value in stage of rapid eye movement, and percent sleep time in stage of SaO2 intervals bigger than 89%. In our experiments, a total of 83 patients (58 with a positive OSAS (AHI>5) and 25 with a negative OSAS such that normal subjects) were examined. The decision support systems can help to physicians in the diagnosing of any disorder or disease using clues obtained from signal or images taken from subject having any disorder. In order to compare the used classifier algorithms, the mean square error, classification accuracy, area under the receiver operating characteristics curve (AUC), and sensitivity and specificity analysis have been used. The obtained AUC values of C4.5 decision tree, ANN, AIRS, and ANFIS classifiers are 0.971, 0.96, 0.96, and 0.922, respectively. These results have shown that the best classifier system is C4.5 decision tree classifier on the diagnosis of obstructive sleep apnea syndrome.

Intrusion detection is a major challenge for security experts in the cyber world. Traditional IDS failed to detect complex and unknown cyber-attacks. Machine learning has become a vibrant technology for cybersecurity. There exists several machine learning algorithms to detect intrusion. Most classifiers are well suited to detect the attacks. However, improving accuracy and detecting unknown attacks in existing IDSs is a great challenge. Therefore, the detailed comparative study of various machine learning approaches such as artificial neural networks, support vector machine, decision tree, and hybrid classifiers used by researchers for intrusion detection are done. Deep learning is an emerging approach which suits well for large data. Deep learning techniques find optimal feature set and classify low-frequency attacks better than other techniques. This study also summarizes literatures in deep learning approaches such as deep auto-encoder, Boltzmann machine, recurrent neural networks, convolutional neural networks, and deep neural networks. Moreover, the datasets used in various literatures and the analysis of deep learning approaches based on the performance metrics are also done. Future directions to detect intrusion are also provided. This study in fact will be helpful to develop IDS based on artificial intelligence approaches such as machine learning and deep learning.KeywordsMachine learningIntrusion detectionFeature selectionDeep learningCyber securityClassifier

Heart disease is one of the leading cause deaths of worldwide. Prediction of cardiovascular infection is a critical challenge in the area of clinical data analysis. Data mining techniques are providing an effective decision and significant results on data that are used widely for predicting. The purpose of this paper is to propose a novel approach with aims to find a noteworthy method to diagnose heart disease prediction. In this research, a unique dataset was created by combining the Cleveland dataset and Stalog heart disease datasets collected from the UCI ML repository. The new dataset contains 14 medical parameters such as age, sex, blood pressure, and 568 instances for training and prediction heart disease. This paper offers a novel methodology of NNDT (Neural Network and Decision Tree) that uses Neural Network for training model and Decision Tree to test classification for better heart disease prediction. The performance of the proposed approach have been compared with Naive Bayes, Support Vector Machine, Neural Network, Voted Perceptron, and Decision Tree algorithms. The results showed that the accuracy and performance improved as compared to other techniques and methods. This study enables the researchers to analyze the heart disease data with a new approach to predict heart diseases to maintain human health.

Machine learning models are frequently gaining wide applications in different fields with an emphasis on supervised machine learning for data exploration as in healthcare provision. With an increase in demand for outpatient health care services in Kenya, the Government is faced with the problem of forecasting this type of demand. Its in this regard that this research develops a supervised machine learning model for the modeling and prediction of demand for outpatient health-care services in Kenya using artificial neural networks, Linear Regression analysis and Decision trees. The objectives of this research were to analyze, develop and evaluate machine learning models in the modeling of outpatient healthcare data. Model evaluation was via the deviance residuals and mean squared error. Data used in this research was secondary data obtained from the Kenya Household Health Expenditure Utilization Survey, 2017 in which the R statistical software was used to aid the analysis. A total of nine thousand one hundred and fifty-nine outpatients were used in the research and data attributes were age, gender, cost of outpatient health care sought and number of visits made by the outpatients. Experiment results showed that age and gender of an outpatient were significant factors in the estimation and forecasting of demand for outpatient healthcare services for which the neural network architecture was used in the data training. Cost and Visits were used as primary variables in decision tree construction for the classification and regression decision trees respectively.

Tumors that have migrated to other regions of the body, particularly the breast, lung, bowel, or prostate, usually develop secondary tumors in the eyes. Retinoblastoma in children and melanoma in adults are two forms of primary cancers that develop within the eye. In this paper, we review the recent works of the artificial intelligence techniques that are applied for classification of ophthalmology tumors. The researchers had proposed different diagnosis systems of eye cancer; iris tumor, iris nevus, uveal melanoma and metastatic, malignant choroidal melanoma and retinoblastoma. The techniques used in these papers can be divided into three main methodologies. The main methodology depends on the Artificial Neural Network (ANN) and deep learning; Back Propagation Neural Networks (BPNN), Radial Basis Function Networks (RBFN), Auto Encoder (AE) Neural Network, hybrid Stacked Auto Encoder (SAE) Network, Deep Belief Network (DBN),Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM). The second methodology depends on the Machine Learning (ML) approaches; decision tree, Fuzzy C-Means (FCM), Alternative Fuzzy C-Mean (AFCM), Support Vector Machine (SVM) and Decision Tree classifier. The third one depends on different image processing techniques and Apriori based algorithm. The highest recognition rate is achieved by applying different image processing techniques and BPNN with 98.5% and 95%, respectively.

Nowadays, expert systems being used in various fields have received a great deal of attention. Auditing is one such field, along with determining the audit opinion type. An expert system consists of a knowledge database and an inference engine. The objective of this research is to make an expert system that will be of help to auditors in predicting and determining the different types of audit reports. The expert system receives data or knowledge from financial reports and determines the types of audit opinions by using an artificial neural network and a decision tree as an inference engine. An expert system should be able to explain the solution, but presenting the reason for the results obtained with a neural network is difficult. This study attempts to provide a method that will present simple and understandable reasons for the results obtained with neural networks.

At present, patients whose have suffered from stroke in Thailand are increasing every year. Stroke impairments relate to many functions such as sensory, motor function, communication, visual and emotional function which depend on brain's lesion. Physical examinations and assessments are important for planning the rehabilitation programs. For this reason, there are several information for medical decision making. Missing some data for treatment planning may occur. To solve this problem, the proposed study used two algorithms to determine the proper rehabilitation treatment program. Artificial Neural Networks and Decision Trees models were considered. Sensitivity, specificity and accuracy values were computed to define the performance of both algorithms. The results of this study indicated that both techniques can apply for data classification and define the proper treatment programs. However, the results were shown that the specificity and accuracy of decision trees model were higher than neural network model.

Smart cities integrate data collection and communication technologies to operate more efficiently in order to provide better services to citizens, improved road traffic situation, better economic development, etc. However, safety still a main concern of road traffic as road crashes pose serious threats to road users causing death and injury all over the world. Road traffic safety is the process of implementing measures to reduce the number of crashes, death and severe injuries. In this paper, using Machine Learning (ML) algorithms, Off-line, we train and test the Intelligent and Dynamic Adaptation Model (IDAM) on the road traffic data collected for 14 years of car crashes in United Kingdom (UK). IDAM then on-line determines the optimal speed limit for each road segment based on many predictors such as weather, road type, light condition, and many others, stated later. We train and test IDAM using three different machine learning algorithms: Artificial Neural Network (ANN), Decision Tree (DT), and Linear Regression (LR) with Stochastic Gradient Descent (SGD). Using the testing dataset, IDAM achieves prediction accuracy of around 96%. Implemented in an operation algorithm, IDAM can continuously adapt the road speed limit to an optimal value as the predictors change on-line.

The leading treads towards social networking services had drawn massive public attention from last one and half decade. The amount of data that is uploaded to these social networking services is increasing day by day. So, their is massive requirement to study the highly dynamic behavior of users towards these services. This is a preliminary work to model the user patterns and to study the effectiveness of machine learning predictive modeling approaches on leading social networking service Facebook. We modeled the user comment patters, over the posts on Facebook Pages and predicted that how many comments a post is expected to receive in next H hrs. To automate the process, we developed a software prototype consisting of the crawler, Information extractor, information processor and knowledge discovery module. We used Neural Networks and Decision Trees, predictive modeling techniques on different data-set variants and evaluated them under Hits@10(custom measure), Area Under Curve, Evaluation Time and Mean Absolute error evaluation metrics. We concluded that the Decision trees performed better than the Neural Networks under light of all evaluation metrics.

Machine learning based algorithms, such as a decision tree (DT) classifier, have been applied to automated process monitoring and fault identification in manufacturing processes, however the current DT-based process control models employ a single DT classifier for both mean shift detection and fault identification. As many manufacturing processes use automated data collection for multiple process parameters, a DT classifier would have to handle a large number of classes. Previous research shows that a large number of classes can degrade the accuracy of a DT multiclass classifier. In this study we propose a new process monitoring model using multiple DT classifiers with each handling a small number of classes. Moreover, we not only detect mean shifts but also identify process variability levels that may cause out-of-control signals. Experimental results show that our proposed model achieves satisfactory performance in process monitoring and fault identification with various parameter settings. It achieves better ARL performance compared with the baseline method based on a single DT classifier.