Feature Analysis for Gear Growl in Electrified Powertrains

Text mining is a special case of data mining which explore unstructured or semi-structured text documents, to establish valuable patterns and rules that indicate trends and significant features about specific topics. Text mining has been in pattern recognition, predictive studies, sentiment analysis and statistical theories in many areas of research, medicine, financial analysis, social life analysis, and business intelligence. Text mining uses concept of natural language processing and machine learning. Machine learning algorithms have been used and reported to give great results, but their performance of machine learning algorithms is affected by factors such as dataset domain, number of classes, length of the corpus, and feature selection techniques used. Redundant attribute affects the performance of the classification algorithm, but this can be reduced by using different feature selection techniques and dimensionality reduction techniques. Feature selection is a data preprocessing step that chooses a subset of input variable while eliminating features with little or no predictive information. Feature selection techniques are Information gain, Term Frequency, Term Frequency-Inverse document frequency, Mutual Information, and Chi-Square, which can use a filters, wrappers, or embedded approaches. To get the most value from machine learning, pairing the best algorithms with the right tools and processes is necessary. Little research has been done on the effect of feature selection techniques on classification accuracy for pairing of these algorithms with the best feature selection techniques for optimal results. In this research, a text classification experiment was conducted using incident management dataset, where incidents were classified into their resolver groups. Support vector machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes (NB) and Decision tree (DT) machine learning algorithms were examined. Filtering approach was used on the feature selection techniques, with different ranking indices applied for optimal feature set and classification accuracy results analyzed. The classification accuracy results obtained using TF were, 88% for SVM, 70% for NB, 79% for Decision tree, and KNN had 55%, while Boolean registered 90%, 83%, 82% and 75%, for SVM, NB, DT, and KNN respectively. TF-IDF, had 91%, 83%, 76%, and 56% for SVM, NB, DT, and KNN respectively. The results showed that algorithm performance is affected by feature selection technique applied. SVM performed best, followed by DT, KNN and finally NB. In conclusion, presence of noisy data leads to poor learning performance and increases the computational time. The classifiers performed differently depending on the feature selection technique applied. For optimal results, the classifier that performed best together with the feature selection technique with the best feature subset should be applied for all types of data for accurate classification performance. Keywords: Text Classification, Supervised Machine Learning, Feature Selection DOI : 10.7176/JIEA/9-3-06 Publication date :May 31 st 2019

The non-contact measurement of engine speed can be realized by analyzing engine vibration frequency. However, the vibration signal is distorted by harmonics and noise in the measurement. This paper presents a novel method for the measurement of engine rotation speed by using the cross-correlation of vibration and acoustic signals. This method can enhance the same frequency components in engine vibration and acoustic signal. After cross-correlation processing, the energy centrobaric correction method is applied to estimate the accurate frequency of the engine’s vibration. This method can be implemented with a low-cost embedded system estimating the cross-correlation. Test results showed that this method outperformed the traditional vibration-based measurement method.

Scale abbreviation is a crucial task for researchers aiming to reduce response burden and optimize data collection when using self-report instruments such as online surveys and questionnaires. Among various data-driven strategies available for scale abbreviation, supervised machine learning (SML) algorithms have emerged as a prominent approach due to their accuracy in predicting total scores from the original instrument. However, previous studies offer limited insights into how SML-abbreviated scales can be evaluated using both SML and psychometric metrics across different feature selection techniques. To address this gap, the current study aims to evaluate the effectiveness of seven feature selection methods: item-total-correlation-based filters (ITC), Minimum-Redundancy-Maximum-Relevance (MRMR), Lasso, Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Genetic Algorithms (GA), and Non-dominated Sorting Genetic Algorithms-II (NSGA-II), all used in conjunction with SML. Additionally, the psychometric properties of these SML methods are compared with two non-SML approaches. Using simulated datasets varying in sample size, model error, and factorial correlations, the study examines predictive accuracy, reliability, and the ability to recover both inter-subscale correlations and external criterion correlations. The findings indicate that no single method consistently excels across all conditions, with specific feature selection techniques performing better under certain circumstances. Key insights are provided to guide researchers in selecting appropriate feature selection methods based on their specific dataset characteristics and goals.

Introduction: The early and accurate detection of COVID-19 remains a life-threatening challenge in medical analysis. Machine learning is used for predicting disease outcomes based on clinical parameters. This analysis proposes a comparative analysis of feature selection method and classification techniques to enhance COVID-19 detection accuracy using blood biomarkers. We used a pensourse dataset of 1,724 cases, including 35 features. To improve the model performance data preprocessing process included outlier handling, normalization, and transformation techniques to improve model performance. To identify the relevant features, we employed the three-feature selection methods Chi-Square test, Pearson correlation coefficient, and Random Forest. The model prediction accuracy was enhanced using a stacking ensemble classication techniques. The machine learning based classification models effectively predicted COVID-19 infectious disease using blood biomarkers with optimized feature selection techniques. Objectives: To enhance the accuracy of COVID-19 prediction using machine learning techniques by applying feature selection and classification techniques on blood biomarkers. Methods: The comparative analysis utilized a publicly available dataset containing 1,724 cases with 35 attributes. Data preprocessing involved outlier handling, normalization, and transformation techniques. Employed Chi-Square test, Pearson correlation coefficient, and Random Forest feature selection techniques. Stacking ensemble classification algorithm was utilized for the better performance of a model. Results: The classification models demonstrated efficiency in predicting COVID-19 using blood biomarkers. Optimized feature selection significantly improved predictive accuracy, highlighting the importance of selecting relevant features for model performance enhancement. Conclusions: This study showcases the potential of ML-driven approaches for COVID-19 detection, emphasizing the role of feature selection in improving classification accuracy. The findings contribute to the advancement of diagnostic tools, offering a data-driven solution for rapid and reliable COVID-19 screening.

Credit risk assessment is an essential task for financial institutions, as it evaluates the likelihood of loan defaults. Misclassifying loan applications can result in substantial economic losses. However, accurately predicting customers' creditworthiness presents challenges for machine learning models due to high dimensionality and imbalanced class distributions, which can severely impact overall model performance. This implements three feature selection (FS) techniques, such as Random Forest with Highly Correlated features (RFHC), Information Gain, and Chi-Square to address the high dimensional problem. Additionally, SMOTE is implemented to address the imbalanced dataset. The model performance is analyzed using three different approaches. First, employing only feature selection techniques, in the second approach, we employed feature selection followed by oversampling, and in the final approach, oversampling prior to feature selection is employed. The experimental results indicate that implementing feature selection followed by oversampling gives better performance compared to the other two approaches. Among the feature selection techniques, RFHC outperforms the others, achieving a highest F1-score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{95.12 \%}$</tex> and an AUC value of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{85.76 \%}$</tex>.

Monitoring of progressive wear and early diagnosis of damage are critical to a rotating machine to avoid dangerous, costly, time consuming failures. A common symptom of wear in rotating machines is characterized by an increase in noise and /or vibration levels. It is usually monitored by either accelerometers or acoustic emission sensors, both of which are required to be mounted on the machine. Acoustics measurement using microphones has its unique non-contact advantage of monitoring the sound that caused by the wearing. Some work has been done on investigating the power of the acoustic signals of wearing machines; however, the principal indicator of failure onset and the relation between the spectra of the vibration signal and the non-contact acoustic signal is unclear. In this project, both acoustic and vibration signals were measured to investigate a machine with bearings of different degrees of wear. Acoustic signal were recorded at various azimuth settings and compared to the vibration signal. Frequency analysis and signal processing techniques were applied to compare the information contents and sensitivities of those two measurements.

Internal combustion engines are frequently used in transportation, power plants, and in many other applications for industrial purposes. For this reason, it is very important that the maintenance is done systematically and that the faults are detected correctly. In this study, two different methods were used for the detection of the healthy internal combustion engine (H) and faulty internal combustion engines (single-cylinder misfire-F1, two-cylinder misfire-F2). In the first method, classical signal features were extracted from engine vibration measurements and used in the training of artificial neural networks (ANNs) and support vector machine (SVM). In the second method, convolutional neural networks (CNNs), a deep learning method in which features are extracted automatically, are used. Spectrograms of engine vibration signals were used to train pre-trained CNNs with different structures. Spectrograms were obtained by applying short-time Fourier transform (STFT) to vibration signals. The results of GoogleNet and ResNet-50 models trained with spectrograms were compared with the results obtained from models based on ANNs and SVM.

Prediction of the stage of cancer plays an important role in planning the course of treatment and has been largely reliant on imaging tools which do not capture molecular events that cause cancer progression. Gene-expression data-based analyses are able to identify these events, allowing RNA-sequence and microarray cancer data to be used for cancer analyses. Breast cancer is the most common cancer worldwide, and is classified into four stages - stages 1, 2, 3, and 4 [2]. While machine learning models have previously been explored to perform stage classification with limited success, multi-class stage classification has not had significant progress. There is a need for improved multi-class classification models, such as by investigating deep learning models. Gene-expression-based cancer data is characterised by the small size of available datasets, class imbalance, and high dimensionality. Class balancing methods must be applied to the dataset. Since all the genes are not necessary for stage prediction, retaining only the necessary genes can improve classification accuracy. The breast cancer samples are to be classified into 4 classes of stages 1 to 4. Invasive ductal carcinoma breast cancer samples are obtained from The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets and combined. Two class balancing techniques are explored, synthetic minority oversampling technique (SMOTE) and SMOTE followed by random undersampling. A hybrid feature selection pipeline is proposed, with three pipelines explored involving combinations of filter and embedded feature selection methods: Pipeline 1 - minimum-redundancy maximum-relevancy (mRMR) and correlation feature selection (CFS), Pipeline 2 - mRMR, mutual information (MI) and CFS, and Pipeline 3 - mRMR and support vector machine-recursive feature elimination (SVM-RFE). The classification is done using deep learning models, namely deep neural network, convolutional neural network, recurrent neural network, a modified deep neural network, and an AutoKeras generated model. Classification performance post class-balancing and various feature selection techniques show marked improvement over classification prior to feature selection. The best multiclass classification was found to be by a deep neural network post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with a Cohen-Kappa score of 0.303 and a classification accuracy of 53.1%. For binary classification into early and late-stage cancer, the best performance is obtained by a modified deep neural network (DNN) post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with an accuracy of 81.0% and a Cohen-Kappa score (CKS) of 0.280. This pipeline also showed improved multiclass classification performance on neuroblastoma cancer data, with a best area under the receiver operating characteristic (auROC) curve score of 0.872, as compared to 0.71 obtained in previous work, an improvement of 22.81%. The results and analysis reveal that feature selection techniques play a vital role in gene-expression data-based classification, and the proposed hybrid feature selection pipeline improves classification performance. Multi-class classification is possible using deep learning models, though further improvement particularly in late-stage classification is necessary and should be explored further.

Text clustering involves data that are of very high dimension. Feature selection techniques find subsets of relevant features from the original feature space that help in efficient and effective clustering. Selection of relevant features merely on ranking scores without considering correlation interferes with the clustering performance. An efficient feature selection technique should be capable of preserving the multi-cluster structure of the data. The purpose of the present work is to demonstrate that feature selection techniques which take into consideration the correlation among features in multi-cluster scenario show better clustering results than those techniques that simply rank features independent of each other. This paper compares two feature selection techniques in this regard viz. the traditional Tf-Idf and the Multi-Cluster Feature Selection (MCFS) technique. The experimental results over the TDT2 and Reuters-21,578 datasets show the superior clustering results of MCFS over traditional Tf-Idf.

Rotating machinery is one of the most common and critical types of machinery in engineering. This type of machinery often operates under harsh conditions for extended periods, which makes it prone to failure during use. Therefore, condition monitoring and fault diagnosis can help address issues promptly and reduce the risk of accidents in rotating machinery. Currently, vibration signals are the predominant single modality used for mechanical fault diagnosis. However, unimodal approaches often lack robustness and struggle to provide reliable diagnostics in practical industrial environments. Complementary data sources can provide unique insights into different aspects of physical degradation. To address these limitations, this paper proposes a multimodal domain generalization diagnostic method based on vibration and acoustic signals. First, the method extracts and fuses features using a feature extraction and fusion model. Then, it employs ensemble learning to achieve transfer diagnosis across different operating conditions. This approach effectively resolves issues of insufficient robustness in single-modal diagnosis and diagnosis under varying operating conditions.

In a machining system, tool condition monitoring systems are required to get a high-quality product and to prevent the downtime of machine tools due to tool failures. For this purpose, tool condition monitoring systems have become very important during the years since the mechanical faults can cause high cost. This study introduces a multistage cutting tool fault diagnosis method to detect the presence and level of the involute form cutter faults on the by the cutting force and vibration signal analysis. Therefore, different fault levels (low, medium and high) were generated on the involute form cutter as a tool breakage. During the experiments, the cutting force, vibration and acoustic signals were gathered with three different feed rates for each fault level. The gathered signals were processed by a multistage signal processing algorithm developed in the MATLAB environment. As an initial step, the continuous wavelet transform of the obtained signals was taken and saved as an image by the developed algorithm. After that, a convolutional neural network model is trained and tested by using the obtained images. The developed algorithm firstly checks the presence of the cutting tool fault. Once the algorithm labels the cutting tool is damaged, it then checks the damage level of the cutting tool fault. It is observed from the results, cutting force analysis is sufficient for the detection of cutting tool fault. On the other hand, the cutting force signal analysis is insufficient to detect the damage level of the cutting tool. Therefore, the vibration signal analysis is required to detect the damage level of the cutting tool. Results prove that, by the vibration analysis, the developed algorithm could detect not only the presence of the damage on the cutting tool but also the damage level. The results of the algorithm for each stage and signal are given in the results section.

Non-Intrusive Load Monitoring (NILM) aids in estimating the individual energy consumed by different appliances using aggregate signals measured at point of common connection. This paper explores various unexplored aspects concerning load classification in NILM. Rich feature sets are extracted from load signatures using auto-correlogram, Variational Mode Decomposition (VMD), and Wavelet Packet Tree (WPT) decomposition. Typically, previous works employ a single Feature Selection (FS) technique to earmark the relevant features for improved performance of NILM. However, each FS technique behaves uniquely, and the effects of using different FS techniques or their combinations have yet to be explored for NILM. Hence, Combinatorial Fusion Analysis (CFA), which surpasses the performance of a single FS technique by considering an optimal combination of multiple FS techniques, is used in this paper. The final selected features are fused and provided to a classifier. Rather than manually tuning or performing an exhaustive search for setting the classifier’s hyper-parameters, as prevalent in previous works, the present work utilizes Bayesian Optimization (BO) comprising surrogate and acquisition functions. The proposed work’s efficacy is validated on publicly available data-sets in a host computer and an embedded device, namely, R-Pi, via comparison with previous works.

Existing studies have attempted to determine the tool chipping condition using the indirect method of data capture and intelligent analysis techniques considering machine parameters, and tool conditions using signal processing techniques. Due to the obstructive nature of the machining operation, however, it is daunting to use signal capturing to intelligently capture the condition of the tool as well as that of the workpiece. This study aimed to apply some advanced signal processing techniques to the vibration signals captured experimentally during machining operation for the decision making and analysis of tool and workpiece conditions. Vibration signals were captured during turning operations while using four (4) classes of tools, based on their flank wear. The signals were first pre-processed and decomposed using the Empirical Mode Decomposition (EMD) method. The Hilbert–Huang transform (HHT) was applied to the resulting IMFs obtained to compute the feature vectors used to classify the condition of the tool and workpiece. A total of 12 features, consisting of instantaneous properties such as instantaneous energy, instantaneous frequencies, and amplitudes, were obtained for data training and classification of tool conditions. To optimize the classification process, feature selection was performed using a genetic algorithm (GA) to reduce the number of features from 12 to 4 for data training and classification. The feature vectors were first trained for tool classification with a neural network scaled conjugate gradient (SCG) algorithm. The result showed that the model classification error was 0.102. Two other machine learning models, support vector machine (SVM) and K-Nearest Neighbors (KNN), were also implemented for classifying the tool conditions, from the feature vector, to determine the model that most accurately predicted the condition of the tool. To avoid bias and reduce misclassification errors, the k-fold cross-validation technique was applied with ‘k’ taken as 5 and 10. The computed feature vectors were used as inputs to train the machine learning model using both SVM and KNN models to classify the tool and workpiece condition during machining. The error loss of each model was evaluated and plotted to review the performance. The average overall error loss of 0.5031 was observed for the SVM model with 5-fold cross-validation, whereas the error loss of 0.0318 was observed for the KNN model with 5-fold cross-validation. The average overall error loss of 0.5009 was observed for the SVM model with 10-fold cross-validation when trained using the features selected by a genetic algorithm (GA), while the average overall error loss of 0.0343 was observed for the KNN model. The optimal performance of the SVM model was obtained when all features were used for the training, whereas the KNN model performed better when feature selection was implemented. The error losses of the models were evaluated to be less in KNN models, compared to SVM and SCG. The obtained results also showed that the developed KNN models performed 10 times better than the SVM model in predicting the tool condition from the captured vibration signal during the machining process.

Identifying important biomarkers to improve disease diagnosis and treatment is a significant topic of research in bioinformatics. However, bioinformatics datasets frequently have a large number of features per sample or instance. This problem, known as “high dimensionality,” can be alleviated through the use of dimension reducing techniques such as feature (gene) selection which remove unnecessary features. There are many versions of feature selection, with varying biases and predictive abilities. However, predictive power is but one factor to consider when choosing a feature selection technique: one must also consider the technique's stability, that is, its ability to create feature subsets which remain valid in the face of changes to the data. While there has been work in determining the relative stability of different feature selection techniques, this does not always help determine whether a chosen feature selection technique will give stable feature subsets for a specific dataset. Factors such as difficulty of learning (e.g., dataset difficulty) may also influence feature selection stability, making generally-true facts about different techniques not applicable to a given dataset. In this work, we study how dataset difficulty can affect the stability of feature selection techniques, leading to good performance from bad techniques and vice versa. We use a set of twenty-six DNA microarray datasets with varying levels of difficulty of learning, along with four levels of dataset perturbation, six feature selection techniques with various levels of stability, and twelve feature subset sizes. The results show that as the dataset difficulty increases, the stability decreases. However, the relative stability between the techniques remains the same. Additionally, the more difficult the dataset, the more the stability is affected by changes to the data. We also found that unstable rankers are more affected by the transition between Easy and Moderate datasets, whereas the stable techniques are more affected by the change between Moderate and Hard datasets. Lastly, as the feature subset size increases, the stability increases and the difference between the levels of dataset difficulty decreases. Overall, we conclude that difficulty of learning must be taken into account before interpreting stability results.

Today, video data, as a powerful multimedia component, is accompanied by some problems with increasing usage in communication, health, education, and social media in particular. Classification and detection of concepts in video data by automatic methods are some of these challenging problems. In this study, we propose a video classification system, which incorporates deep convolutional neural networks (CNNs) by leveraging feature selection and data fusion techniques to improve the accuracy of the classification. Principal Component Analysis (PCA) as a feature selection method and Discriminant Correlation Analysis (DCA) technique, which incorporates class associations into the correlation analysis of feature sets for data fusion, are applied to the problem at the feature level. Support Vector Machines (SVMs) have been trained with new feature vectors obtained from different deep convolutional neural networks by feature selection and data fusion methods. The proposed method is tested for 38 concepts on TRECVID 2013 SIN video task dataset and the results are evaluated. Our results show that the classification accuracy is improved by 4% with an accuracy of 50.27% when the proposed data fusion and feature selection techniques are used.