Predicting Tuberculosis Treatment Relapse: A Decision Tree Analysis of J48 for Data Mining

Tuberculosis remains an important problem in public health that threatens the world, including the Philippines. Treatment relapse continues to place a severe problem on patients and TB programs worldwide. A significant reason for the development of decline is poor compliance with medical treatments. The objectives of this research are to generate a predictive data mining model to classify the treatment relapse of TB patients and to identify the features influencing the category of treatment relapse. The TB patient dataset is applied and tested in decision tree J48 algorithm using WEKA. The J48 model identified the three (3) significant independent variables (DSSM Result, Age, and Sex) as predictors of category treatment relapse.

Visualization of the Machine Learning Process Using J48 Decision Tree for Biometrics through ECG Signal

The inherently unique qualities of the heart infer the candidacy for the domain of biometrics, which applies physiological attributes to establish the recognition of a person’s identity. The heart’s characteristics can be ascertained by recording the electrical signal activity of the heart through the acquisition of an electrocardiogram (ECG). With the application of machine learning the subject specific ECG signal can be differentiated. However, the process of distinguishing subjects through machine learning may be considered esoteric, especially for contributing subject matter experts external to the domain of machine learning. A resolution to this dilemma is the application of the J48 decision tree available through the Waikato Environment for Knowledge Analysis (WEKA). The J48 decision tree elucidates the machine learning process through a visualized decision tree that attains classification accuracy through the application of thresholds applied to the numeric attributes of the feature set. Additionally, the numeric attributes of the feature set for the application of the J48 decision tree are derived from the temporal organization of the ECG signal maxima and minima for the respective P, Q, R, S, and T waves. The J48 decision tree achieves considerable classification accuracy for the distinction of subjects based on their ECG signal, for which the machine learning model is briskly composed.

Vibration Based Tool Insert Health Monitoring Using Decision Tree and Fuzzy Logic

The productivity and quality in the turning process can be improved by utilizing the predicted performance of the cutting tools.This research incorporates condition monitoring of a non-carbide tool insert using vibration analysis along with machine learning and fuzzy logic approach.A non-carbide tool insert is considered for the process of cutting operation in a semi-automatic lathe,where the condition of tool is monitored using vibration characteristics.The vibration signals for conditions such as heathy,damaged,thermal and flank were acquired with the help of piezoelectric transducer and data acquisition system.The descriptive statistical features were extracted from the acquired vibration signal using the feature extraction techniques.The extracted statistical features were selected using a feature selection process through J48 decision tree algorithm.The selected features were classified using J48 decision tree and fuzzy to develop the fault diagnosis model for the improved predictive analysis.The decision tree model produced the classification accuracy as 94.78%with five selected features.The developed fuzzy model produced the classification accuracy as 94.02%with five membership functions.Hence,the decision tree has been proposed as a suitable fault diagnosis model for predicting the tool insert health condition under different fault conditions.

Can We Predict the Change in Code in a Software Product Line Project?

Software programs are always prone to change for several reasons. In a software product line, the change is more often as many software units are carried from one release to another. Also, other new files are added to the reused files. In this work, we explore the possibility of building a model that can predict files with a high chance of experiencing the change from one release to another. Knowing the files that are likely to face a change is vital because it will help to improve the planning, managing resources, and reducing the cost. This also helps to improve the software process, which should lead to better software quality. Also, we explore how different learners perform in this context, and if the learning improves as the software evolved. Predicting change from a release to the next release was successful using logistic regression, J48, and random forest with accuracy and precision scored between 72% to 100%, recall scored between 74% to 100%, and F-score scored between 80% to 100%. We also found that there was no clear evidence regarding if the prediction performance will ever improve as the project evolved.

基于WorldView-2影像数据对杭州西湖区绿地信息提取研究

以杭州市西湖区为例,根据研究区域地物在World View-2遥感影像的特征差异进行区域划分。在每个分区内采用不同的多尺度和方式进行分割,构建多层次结构,综合利用光谱、形状、纹理等特征变量;采用CART决策树分类算法,选择最优特征及节点阈值分区域对杭州市西湖区的植被绿地信息进行提取;采用Jeffries-Matusita(J-M)距离法,确定纹理窗口尺度并筛选纹理特征。结果表明:本研究利用可分离指数J-M距离法得到影像地物草地、农用地、灌木、乔木最佳纹理窗口尺寸分别为5×5、11×11、13×13、13×13,对纹理尺度的选择和纹理特征的降维极大地提高了信息提取的精度及效率;基于面向对象的CART决策树分类法的总体分类精度相比基于像元的最大似然法的精度从76.53%提高到88.56%,Kappa系数从0.711 7提高到0.862 3,绿地平均用户精度从72.73%提高到84.63%;同时比常规的面向对象的方法更快速灵活地确定分类特征及阈值,大幅度地提高了提取效率及精度。

Intelligent Sound-Based Early Fault Detection System for Vehicles

An intelligent sound-based early fault detection system has been proposed for vehicles using machine learning.The system is designed to detect faults in vehicles at an early stage by analyzing the sound emitted by the car.Early detection and correction of defects can improve the efficiency and life of the engine and other mechanical parts.The system uses a microphone to capture the sound emitted by the vehicle and a machine-learning algorithm to analyze the sound and detect faults.A possible fault is determined in the vehicle based on this processed sound.Binary classification is done at the first stage to differentiate between faulty and healthy cars.We collected noisy and normal sound samples of the car engine under normal and different abnormal conditions from multiple workshops and verified the data from experts.We used the time domain,frequency domain,and time-frequency domain features to detect the normal and abnormal conditions of the vehicle correctly.We used abnormal car data to classify it into fifteen other classical vehicle problems.We experimented with various signal processing techniques and presented the comparison results.In the detection and further problem classification,random forest showed the highest results of 97%and 92%with time-frequency features.

Condition Monitoring of Roller Bearing by K-star Classifier andK-nearest Neighborhood Classifier Using Sound Signal

Most of the machineries in small or large-scale industry have rotating elementsupported by bearings for rigid support and accurate movement. For proper functioning ofmachinery, condition monitoring of the bearing is very important. In present study soundsignal is used to continuously monitor bearing health as sound signals of rotatingmachineries carry dynamic information of components. There are numerous studies inliterature that are reporting superiority of vibration signal of bearing fault diagnosis.However, there are very few studies done using sound signal. The cost associated withcondition monitoring using sound signal (Microphone) is less than the cost of transducerused to acquire vibration signal (Accelerometer). This paper employs sound signal forcondition monitoring of roller bearing by K-star classifier and k-nearest neighborhoodclassifier. The statistical feature extraction is performed from acquired sound signals. Thentwo-layer feature selection is done using J48 decision tree algorithm and random treealgorithm. These selected features were classified using K-star classifier and k-nearestneighborhood classifier and parametric optimization is performed to achieve the maximumclassification accuracy. The classification results for both K-star classifier and k-nearestneighborhood classifier for condition monitoring of roller bearing using sound signals werecompared.

Electroacupuncture at jiājǐ(夹脊 EX-B2) for lumbar intervertebral disc herniation:A randomized controlled trial

Objective： To compare the effect differences of electroacupuncture（EA） at Jiajǐ（夹脊 EX-B2） and conventional acupoints for lumbar intervertebral disc herniation（LIDH） and the factors influenced the effect during the way of data mining.Methods： A total of 160 patients of LIDH were randomly assigned into the EX-B2 group and the conventional acupoints group, 80 cases in each one. The patients in the EX-B2 group received EA at the symmetrical 2 acupoints of the bilateral EX-B2 on the lesion part. The patients in the conventional acupoints group received EA at the tender point of the lesion part, Zhibian（ 秩边BL54）, Huantiao（环跳 GB30）,weǐzhōng（委中BL40）, Chéngshān（承山BL57） and Fúyáng（跗阳BL59） on the affected side. The retain time of the needles is both 45 min. The treatment of the two groups is 3 times a week and for a connective 20 times. The modified Assessment Criteria for Low Lumbar Pain of Japanese Orthopedic Association（JOA）,Visual Analogue Scale（VAS） were evaluated before and after the treatment and at the 6-month follow up.Results：（1） Effective outcomes. JOA score： The JOA score of the patients in the EX-B2 group after treatment was（20.89 士 3.43）, and was（19.35 ±4.02） on the follow-up. Compared with the JOA score（12.35 ±4.42） in the same group before the treatment, there were statistical significant higher（both P0.05）. The JOA score in the EX-B2 group after treatment and on the follow-up were both higher than that of the conventional acupoints group at the same time point（both P0.05）. VAS score： The VAS score of the patients in the EX-B2 group on the 24 h after the first treatment was（4.09 ± 1.81）, and was（2.11 ± 1.30） after the treatment. Compared with the VAS score（4.09 ± 1.81） in the same group before the treatment, there were statistical significant lower（both P0.05）. The VAS score in the EX-B2 group on the 24 h after the first treatment and after treatment showed no statistical differences than that of the conventional acupoints group at the same time point（both P0.05）.（2）Related results from data mining： The middle-aged people and disease duration less than six months, their effect of the immediate treatment was the best. According to JOA score, EA at EX-B2 was better than EA conventional acupoints,either in the process of treatment effect, or in pertinence of the treatment, which were superior to EA conventional acupoints therapy; The best curative effect time of EA at EX-B2 was the first treatment after24 h, and the best curative effect of the conventional acupoints was after the first treatment. The age and disease duration also affected curative effect.Conclusion： The effect of EA at EX-B2 was superior to the conventional acupoints in treating LIDH.

Data mining for classification of power quality problems using WEKA and the effect of attributes on classification accuracy

There is growing interest in power quality issues due to wider developments in power delivery engineering.In order to maintain good power quality,it is necessary to detect and monitor power quality problems.The power quality monitoring requires storing large amount of data for analysis.This rapid increase in the size of databases has demanded new technique such as data mining to assist in the analysis and understanding of the data.This paper presents the classification of power quality problems such as voltage sag,swell,interruption and unbalance using data mining algorithms:J48,Random Tree and Random Forest decision trees.These algorithms are implemented on two sets of voltage data using WEKA software.The numeric attributes in first data set include 3-phase RMS voltages at the point of common coupling.In second data set,three more numeric attributes such as minimum,maximum and average voltages,are added along with 3-phase RMS voltages.The performance of the algorithms is evaluated in both the cases to determine the best classification algorithm,and the effect of addition of the three attributes in the second case is studied,which depicts the advantages in terms of classification accuracy and training time of the decision trees.