Information Gain Method Research Articles

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning.

Drug-induced immune thrombocytopenia (DITP) often occurs in patients receiving many drug treatments simultaneously. However, clinicians usually fail to accurately distinguish which drugs can be plausible culprits. Despite significant advances in laboratory-based DITP testing, in vitro experimental assays have been expensive and, in certain cases, cannot provide a timely diagnosis to patients. To address these shortcomings, this paper proposes an efficient machine learning-based method for DITP toxicity prediction. A small dataset consisting of 225 molecules was constructed. The molecules were represented by six fingerprints, three descriptors, and their combinations. Seven classical machine learning-based models were examined to determine an optimal model. The results show that the RDMD + PubChem-k-NN model provides the best prediction performance among all the models, achieving an area under the curve of 76.9% and overall accuracy of 75.6% on the external validation set. The application domain (AD) analysis demonstrates the prediction reliability of the RDMD + PubChem-k-NN model. Five structural fragments related to the DITP toxicity are identified through information gain (IG) method along with fragment frequency analysis. Overall, as far as known, it is the first machine learning-based classification model for recognizing chemicals with DITP toxicity and can be used as an efficient tool in drug design and clinical therapy.

Feature Selection using Information Gain Method for Building Classification Model DDoS Attack at Application Layer

Distributed Denial of Services (DDoS) is one of the digital attacks that often occurred, the record for DDoS attacks in the second quartal of 2018 reaches 5.7Gbps. The application layer becomes one of the targets for this attack type; this type of DDoS attack always mimicks the user's request, making it harder to detect than DDoS attack at the network and transport layer. The classification has been offered as one method to overcome this problem. Before classification, the selection feature becomes important due to some features that lead to error classification and make the process classification longer. This research uses information gain as a selection feature method and using CICIDS 2017 as the dataset. The CICIDS2017 has 692.704 records consist of 78 features and five classes. The result of feature selection using the information gain method reduces the numbers of features from 78 to 5. To prove that these five features can classify DDoS attacks correctly, we use a randomForest method as a classification method. The randomForest was used to classify the data into five classes: normal, DDoS Goldeneye, DDoS Hulk, DDoS Slowhttptest, and DDoS Slowloris. The result of performance for accuracy is 99.43%, for recall of each class are 99.48%, 99.81%, 99.41%, 96.01%, 99.97% respectively. Besides the result of performance for precision each class are 99.65%, 96.04%, 99.90%, 98.63%, 71.37%, respectively. The results of performance for classification time using five features are decreasing execution time 3.1 seconds.

Evaluation of landslide susceptibility of the Ya’an–Linzhi section of the Sichuan–Tibet Railway based on deep learning

The Qinghai–Tibet Plateau is an area with frequent landslide hazards due to its unique geology, topography, and climate conditions, posing severe threats to engineering construction and human settlements. The primary purpose of this paper is to map the landslide susceptibility of the Ya’an–Lin branch of the Sichuan–Tibet Railway using two deep learning (DL) algorithms, convolutional neural network (CNN) and deep neural network (DNN). Initially, a geospatial database was generated based on 587 landslide hazards determined by Interferometric Synthetic Aperture Radar (InSAR) Stacking technology and field geological hazard surveys; thus, 18 landslide-influencing factors were selected. Subsequently, the landslides were randomly divided into training (70%) and validation data (30%) for model training and testing. Next, a Pearson correlation coefficient and information gain (IG) method were used to perform the correlation analysis and feature selection of the 18 influencing factors. Afterward, landslide susceptibility maps were generated for the two models. Finally, the performance of the model is validated using the receiver-operating characteristic (ROC) curve and confusion matrix. The results show that the CNN model (AUC = 0.88) provided better performance in both the training and testing phases compared to the DNN model (AUC = 0.84). In addition, the high landslide susceptibility is primarily distributed in the Jinsha, Lancang and Nu River basins along the railway. The slope, altitude and rainfall are the main factors for the formation of the landslides. Furthermore, the two deep learning models can accurately map the landslide susceptibility, providing important information for landslide risk reduction and prevention.

Feature Selection with IG-R for Improving Performance of Intrusion Detection System

As the popularity of the internet computer continued to grow and become an indispensable in human life, the security of computer network has become an important issue in computer security field. The Intrusion Detection System (IDS) is a system used in computer security for network security. The feature selection stage of IDS is considered to be the most critical stage in IDS. This stage is very costly both in efforts and time. However, many machine learning approaches have been presented to improve this stage in order to improve the performance of an IDS. However, these approaches did not give desirable results with respect to the detection accuracy in the IDS. A novel technique is proposed in this paper combining the Information Gain and Ranker (IG+R) method as the feature selection strategy with Naïve Bayes (NB), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) as the classifiers. The performance of these IG+R-NB, IG+R-SVM, and IG+R-KNN was evaluated on NSLKDD dataset. The experimental results of our proposed method gave high accuracy and low false alarm rate. The results obtained was compared and benchmarked with existing works. The results of this paper outperformed the existing approaches in terms of the detection accuracy.

Improving Health Literacy of TB Patients at Bandarharjo Health Center through TB Literacy Book Media (BuLit TB)

Objective and Background: The Bandarharjo Health Center reported in 2019 that the number of cases of Multidrug-Resistant Tuberculosis had increased to four. The current program to increase patient TB literacy is only education delivered by TB officers, and no specific media is used to increase patient TB literacy. The purpose of this study was to create literacy media in the form of TB literacy books (BuLit TB) in order to improve the literacy of TB patients at the Bandarharjo Health Center.
 Methods: This study included 50 tuberculosis patients whose literacy levels were assessed both before and after the intervention media was administered. In this study, the information gain method is used to determine the level of importance of a variable based on its target value. In addition, non-parametric tests were used in this study to determine the effect of the intervention on respondents' TB knowledge and Health Literacy levels.
 Results: According to the findings of this study, testing using a weighting algorithm reveals that education and age variables are important on the level of TB knowledge, with weights of 0.221 and 0.155, respectively. Furthermore, the education and address variables have a weighted score of 0.205 and 0.198, respectively, on the respondent's health literacy level. Non-parametric statistical tests revealed that BuLit TB media was effective in increasing the literacy of TB patients at the Bandarharjo Health Center.
 Conclusion: The BuLit TB media can be used by Health Center officers to help TB patients with literacy and education.

Bank Financial Risk Prediction Model Based on Big Data

Financial risk prediction is an important technique to systematically predict the unforeseeable risks in banking systems. The issues involving ill-timing and low accuracy in the current risks prediction methods necessitate an effective risk prediction method. Akin to the use of big data in various domains, the technology has a significant role in financial services and can be used to accurately and timely predict the possibilities of risks. In this paper, an effective hybrid method is proposed to aptly and effectively predict financial risks in the banking systems. The method utilizes the Lasso and linear regression algorithms via the big data features and framework technologies. By proper formalization of the bank financial risk problems, the risk data is obtained and processed. To filter the initial text features and preprocess the annual report text data, the information gain method is used. With the Bag-of-Words (BoW) and the word frequency reverse document frequency weighting method, the text features of financial risk prediction are extracted. The bank financial risk prediction model is constructed based on weighted fusion adaptive random subspace algorithm. The prediction results obtained are integrated so as to realize the bank financial risks in a seamless way. The experimental results show that the proposed method can effectively improve the prediction accuracy and consumes comparatively lesser time in risk prediction.

IMPROVING MULTI-LABEL TEXT CLASSIFICATION USING WEIGHTED INFORMATION GAIN AND CO-TRAINED MULTINOMIAL NAÏVE BAYES CLASSIFIER

Over recent years, the emergence of electronic text processing systems has generated a vast amount of structured and unstructured data, thus creating a challenging situation for users to rummage through irrelevant information. Therefore, studies are continually looking to improve the classification process to produce more accurate results that would benefit users. This paper looks into the weighted information gain method that re-assigns wrongly classified features with new weights to provide better classification. The method focuses on the weights of the frequency bins, assuming every time a certain word frequency bin is iterated, it provides information on the target word feature. Therefore, the more iteration and re-assigning of weight occur within the bin, the more important the bin becomes, eventually providing better classification. The proposed algorithm was trained and tested using a corpus extracted from dedicated Facebook pages related to diabetes. The weighted information gain feature selection technique is then fed into a co-trained Multinomial Naïve Bayes classification algorithm that captures the labels' dependencies. The algorithm incorporates class value dependencies since the dataset used multi-label data before converting string vectors that allow the sparse distribution between features to be minimised, thus producing more accurate results. The results of this study show an improvement in classification to 61%.

Machine Learning Approach for Intrusion Detection Systems as a Cyber Security Strategy for Small and Medium Enterprises

Small and medium enterprises (SMEs) are businesses that account for a large percentage of the economy in many countries, but they lack cyber security. The present study examines different supervised machine learning methods with a focus on intrusion detection systems (IDSs) that will help in improving SMEs’ security. The algorithms that are tested through a real dataset, are Naïve Bayes, Sequential minimal optimization (SMO), C4.5 decision tree, and Random Forest. The experiments are run using the Waikato Environment for Knowledge Analyses (WEKA) 3.8.4 tools and the metrics used to evaluate the results were: accuracy, false-positive rate (FPR), and total time to train and build a classification model. The results obtained from the original dataset with 130 features show a high value of accuracy, but the computation time to build the classification model was notably high for the cases of C4.5 (1 hr. and 20 mins) and SMO algorithm (4 hrs. and 20 mins). the Information Gain (IG) method was used and the result was impressive. The time needed to train the model was reduced in the order of a few minutes and the accuracy was high (above 95%). In the end, challenges that SMEs can have for choosing an IDS such as lack of scalability and autonomic self-adaptation, can be solved by using a correct methodology with machine learning techniques.

Feature extraction of public English vocabulary text based on wavelet transform

Aiming at the problems of low extraction accuracy and long time-consuming in the existing public English vocabulary text feature extraction methods, a public English vocabulary text feature extraction method based on wavelet transform is proposed. Set the existence space of public English vocabulary text, convert the text into vector mode, and cluster the text vector by clustering and fusion method. The distance between lexical text vectors in space is calculated, the similarity between vectors is determined, and the noise in text data is removed by information gain method; divide several small bands of different sizes, determine the change frequency of small band vocabulary text data, integrate the eigenvalues of different bands of text, and carry out wavelet transform on the integrated data features to obtain the transformation result, which is the text feature. The results show that the accuracy of the proposed method is 96%.

A Novel Learning Model of Driver Fatigue Features Representation for Steering Wheel Angle

In the field of advanced driver assistance systems (ADAS), effective learning of driver fatigue characteristics representation is a major challenge due to uncertainties of both real roads and drivers. To tackle this problem, this paper proposes a novel model of learning interpretable representations for fatigue features, so as to improve the performance of the monitoring system on real roads through the learned features. First, the approximate entropy of the Steering Wheel Angle (SWA)sequence is used to crop adaptive lengths of the Recurrent Neural Network (RNN) input data. Then, it will learn statistical indexes to discover the random steering characteristics. The Long Short-Term Memory (LSTM) unit can memorize drivers’ long-term operating characteristics and instantaneous change patterns, and mine their fatigue characteristics. Finally, the information gain method is used to discover the strong correlation between potential characteristics and fatigue levels, thereby obtaining the best feature representation for driver fatigue. The proposed method makes use of the advantages of recurrent neural network learning to explicitly capture various potential characteristics of fatigue driving and interactions between non-linear characteristics in driving. Experimental results on real driving data validate the effectiveness of our proposed method.

Interpretable machine learning models to support differential diagnosis between Ischemic Heart Disease and Dilated Cardiomyopathy

The differential diagnosis between Ischemic Heart Disease (IHD) and Dilated Cardiomyopathy (DCM), particularly in the early stages of the diseases, can often be difficult. Left ventricular ejection fraction (LVEF) and heart rate variability (HRV) analysis are shown to be helpful tools for diagnosing several cardiac diseases. There is a growing interest in application of machine learning techniques to guide the diagnosis. However, often black-box machine learning models create dissatisfaction among clinicians due to the lack of a model interpretability. The aim of our study was to compare the classification performance of interpretable and clinically plausible models applied for early differential diagnosis between DCM and IHD (NYHA ≤ 1) based on LVEF and HRV features. The study encompassed 196 IHD and 117 DCM subjects. The models were produced by classification tree, logistic regression and naïve Bayes algorithms considering the set of selected HRV and LVEF features, chosen with the information gain method. The results showed that the most informative features for classification between IHD and DCM were LVEF, LF, NN50, pNN50, and meanRR. The naive Bayes model with classification accuracy of 73.5% outperformed classification tree and logistic regression models with 67.4% and 67.1% accuracies, respectively. We also demonstrated that the produced models together with nomograms allow probabilistic interpretation of the classification output between IHD and DCM, which is an important factor to guide the clinical decision making in differential diagnosis.

Comprehensive DDoS Attack Classification Using Machine Learning Algorithms

The fast development of Internet technologies ignited the growth of techniques for information security that protect data, networks, systems, and applications from various threats. There are many types of threats. The dedicated denial of service attack (DDoS) is one of the most serious and widespread attacks on Internet resources. This attack is intended to paralyze the victim's system and cause the service to fail. This work is devoted to the classification of DDoS attacks in the special network environment called Software-Defined Networking (SDN) using machine learning algorithms. The analyzed dataset included instances of two classes: benign and malicious. As the dataset contained twenty-two features, the feature selection techniques were required for dimensionality reduction. In these experiments, the Information gain, the Chi-square, and the F-test were applied to decrease the number of features to ten. The classes were also not completely balanced, so undersampling, oversampling, and synthetic minority oversampling (SMOTE) techniques were used to balance classes equally. The previous research works observed the classification of DDoS attacks applying various feature selection techniques and one or more machine learning algorithms. Still, they did not pay much attention to classifying the combinations of feature selection and balancing methods with different machine learning algorithms. This work is devoted to the classification of datasets with eight machine learning algorithms: naïve Bayes, logistic regression, support vector machine, k-nearest neighbors, decision tree, random forest, XGBoost, and CatBoost. In the experimental results, the Information gain and F-test feature selection methods achieved better performance with all eight ML algorithms than with the Chi-square technique. Furthermore, the accuracy values of the oversampled and SMOTE datasets were higher than that of the undersampled and imbalanced datasets. Among machine learning algorithms, the accuracy of support vector machine, logistic regression, and naïve Bayes fluctuates between 0.59 and 0.75, while decision tree, random forest, XGBoost, and CatBoost allowed achieving values around 0.99 and 1.00 with all feature selection and class balancing techniques among all the algorithms.

Investigation of Information gain and Chi test feature selection methods in dimensionality reduction using Machine learning for drug discovery

Investigation of Information gain and Chi test feature selection methods in dimensionality reduction using Machine learning for drug discovery

Feature Selection Approach to Detect DDoS Attack Using Machine Learning Algorithms

Distributed Denial of Service (DDoS) attacks are dangerous attacks that can cause disruption to server, system or application layer. It will flood the target server with the amount of Internet traffic that the server could not afford at one time. Therefore, it is possible that the server will not work if it is affected by this DDoS attack. Due to this attack, the network security environment becomes insecure with the possibility of this attack. In recent years, the cases related to DDoS attacks have increased. Although previously there has been a lot of research on DDoS attacks, cases of DDoS attacks still exist. Therefore, the research on feature selection approach has been done in effort to detect the DDoS attacks by using machine learning techniques. In this paper, to detect DDoS attacks, features have been selected from the UNSW-NB 15 dataset by using Information Gain and Data Reduction method. To classify the selected features, ANN, Naïve Bayes, and Decision Table algorithms were used to test the dataset. To evaluate the result of the experiment, the parameters of Accuracy, Precision, True Positive and False Positive evaluated the results and classed the data into attacks and normal class. Hence, the good features have been obtained based on the experiments. To ensure the selected features are good or not, the results of classification have been compared with the past research that used the same UNSW-NB 15 dataset. To conclude, the accuracy of ANN, Naïve Bayes and Decision Table classifiers has been increased by using this feature selection approach compared to the past research.

Application of Information Gain to Select Attributes in Improving Naïve Bayes Accuracy in Predicting Customer's Payment Capability

The customer is the main factor in the running of PT. XYZ. A good understanding of customers is very important for predicting the capability of customers to pay. The implementation of credit collectibility is used to determine the quality of customer credit, one of which is the customer's capability to pay interest and principal on time. While manually, it is very difficult to accurately predict the capability of customer credit payments. Data mining techniques with the Naïve Bayes algorithm were chosen to classify customers to be able to find patterns, analyze and predict, because they have good performance, are efficient, and simple. The Naïve Bayes algorithm has a weakness in terms of sensitivity to many attributes, so the accuracy is low. Based on the problem stated, his study will apply the Information Gain method to select the most influential attribute on the label in order to increase the accuracy of the Naïve Bayes algorithm. This research produces a new dataset with seven attributes: TENOR, SALARY, DOWN PAYMENT, INSTALLMENT, APPROVAL, OTR CLASS, AGE with Labels: Status and Id: Id number based on the Information Gain method. The dataset comparison process with 995 data records showed an increase in accuracy, precision, and AUC using the new dataset compared to the old dataset, but in the t-Test test with an alpha value = 0.05 there is a difference but not significant. In the evaluation process, performance experienced a significant increase in the use of new datasets with the following percentages of performance improvement: accuracy = 8%, precision = 18.42%, recall = 17.65% and AUC= 0.057%. The results of this study obtained AUC of 0.876, accuracy of 87.88%, precision of 61.90%, and recall of 76.47%, and classified into good classification.

Enriched Optimization Algorithm for Effective Skin Disease Prediction Using Soft Computing Techniques

In recent years, a usual worldwide problem is a skin disease—the diagnostics of infection and skin disease prediction based on the data mining techniques. The precise and cost-effective treatments obtain a technologybased data mining system that can consider making the right decision. Depends on data, there are 34 UCI datasets have in the skin disease prediction. All of the datasets are not much important when predicting the skin disease problem. In this study, the essential datasets to be analyzed because they only give the best accuracy in skin disease prediction. For an outstanding selection of allocation, to propose a novel feature selection approaches, Enriched Fruitfly Optimization Algorithm (EFOA), and Ensemble Classifiers that are helps for an early stage of skin disease prediction. A hybrid technique through the three essential hybrid feature selection approaches such as Chi-Square method, Information Gain method, and Principal Component Analysis (PCA) methods that are combined for better feature selection results. Based on the skin disease dataset, the resultant feature selection approach generated the reduced data subset. Then, the Enriched Fruitfly Optimization Algorithm (EFOA) offers the optimization of reduced data subset. Here, the accuracy estimation is the vital factor to optimize the effective and best prediction of skin disease affected regions. Afterward, the classification performs to classify the EFOA based optimized result by using the six different classification methods. Where, the classification helps to analyze the optimized results, which offers the better classification procedure. To predict the base learner’s performance, to utilize the Naive Bayesian, K-Nearest Neighbour, Decision Tree, Support Vector Machine, Random Forest, and Multilayer Perceptron (MLP) to classify the optimized result. Then, the ensemble techniques used to analyze the classifier’s results through the 3 different methods like Bagging, Boosting, Stacking, added on the base learners to improve the proposed work. Based on the performance, the base learners’ performance is larger than the input dataset. The base learner’s parameters are essential to calculate the accuracy of skin disease prediction performance. The performance of the proposed method will take and compare to each base learner, and the performance shows the accurate skin disease prediction improvement with other existing methods.

A Modeling of an Intelligent System for Learning Result Prediction to Reduce Drop-Out of Undergraduate Students

The objectives of this research were to; 1) analyze the factors of an intelligent system for learning result prediction to reduce drop-out of undergraduate students. 2) construct a modeling of an intelligent system for learning result prediction to reduce drop-out of undergraduate students. The samples were 141 undergraduate students who study English Education program in Academic year 2012-2014 at Kanchanaburi Rajabhat University by purposive sampling. The research results were as follows 1) the factors analysis was based on the attribute weight indexing technique using the Information Gain method. The learning results prediction factors had 14 factors, for example, mean of GPA from semester 1 to 5 and learning results about 9 subjects, 2) constructing a modeling of an intelligent system for learning result prediction to reduce drop-out of undergraduate students by measuring the quality with Cross-validation Test; 10-fold cross-validation and Naïve Bayes technique, the highest accuracy index is 84.33 percent, and followed by the creation of student's learning result prediction by using Decision Tree technique, 73.86 percent of accuracy index.

Combination of TOPSIS Method with Attribute Weighting of Information Gain in Decision-Making

In this research, a combination of the Technique for Order Preference by Similarity lto Ideal Solution (TOPSIS) lalgorithm was carried out with the attribute weighting of the Information Gain method to obtain better decision support results. The data processed in this study is the Indian Liver Patient Dataset (ILPD) dataset obtained lfrom UCI Machine Learning Repository which has 583 instances, 11 attributes and 1 class label. The class label is a text type that consists of two values, namely a liver patient and a non-liver patient. The experimental results show that TOPSIS’ running time and information gain combination algorithm is 1.13 seconds. The result of the accuracy value obtained with a final threshold value greater than 0.5 is 91.25%. In this research, a combination of l the l Technique l for l Order l Preference l by Similarity l to l Ideal l Solution (TOPSIS) l algorithm was carried out with the attribute weighting of the Information Gain method to obtain better decision support results. The data processed in this study is the Indian l Liver l Patient l Dataset (ILPD) dataset obtained l from UCI l Machine Learning l Repository which has 583 instances, 11 attributes and 1 class label. The class label is a text type that consists of two values, namely a liver patient and a non-liver patient. The experimental results show that TOPSIS’ running time and information gain combination algorithm is 1.13 seconds. The result of the accuracy value obtained with a final threshold value greater than 0.5 is 91.25%

On Combining Feature Selection and Over-Sampling Techniques for Breast Cancer Prediction

Breast cancer prediction datasets are usually class imbalanced, where the number of data samples in the malignant and benign patient classes are significantly different. Over-sampling techniques can be used to re-balance the datasets to construct more effective prediction models. Moreover, some related studies have considered feature selection to remove irrelevant features from the datasets for further performance improvement. However, since the order of combining feature selection and over-sampling can result in different training sets to construct the prediction model, it is unknown which order performs better. In this paper, the information gain (IG) and genetic algorithm (GA) feature selection methods and the synthetic minority over-sampling technique (SMOTE) are used for different combinations. The experimental results based on two breast cancer datasets show that the combination of feature selection and over-sampling outperform the single usage of either feature selection and over-sampling for the highly class imbalanced datasets. In particular, performing IG first and SMOTE second is the better choice. For other datasets with a small class imbalance ratio and a smaller number of features, performing SMOTE is enough to construct an effective prediction model.

CWLy-RF: A novel approach for identifying cell wall lyases based on random forest classifier

Drug resistance of pathogenic bacteria has become increasingly serious due to the abuse of antibiotics in recent years. Researchers have found that cell wall lyases are effective antibacterial agents that can specifically recognize target bacteria and degrade bacterial peptidoglycan. Traditional wet experiments are usually expensive, time-consuming and laborious for the identification of lyases. Therefore, there is an urgent need to develop prediction tools based on computer methods to identify lyases quickly and accurately. In this paper, a new predictor, CWLy-RF, is proposed based on the random forest (RF) algorithm to identify cell wall lyases. In this method, we combined three features, namely, 400D, 188D and the composition of k-spaced amino acid group pairs, using mixed-feature representation methods. Afterward, we improved the feature representation ability with the selected top 100 features by using the information gain method and trained a predictive model using RF. The constructed prediction model is evaluated by using 10-fold cross-validation. The accuracy obtained was 96.09%, the AUC was 0.993, the MCC was 0.922, the sensitivity was 94.92%, and the specificity was 97.32%. We have proved that the proposed predictor CWLy-RF is superior to other latest models, and it will hopefully become an effective and useful tool for identifying lyases.