Proposed Feature Extraction Method Research Articles

ABILITY CONVOLUTIONAL FEATURE EXTRACTION FOR CHILI LEAF DISEASE USING SUPPORT VECTOR MACHINE CLASSIFICATION

Chili plants are among the most commonly used food ingredients in various dishes in Indonesia. Leaves on chili plants are often affected by disease; if the disease is not treated immediately, it can damage the plant and cause crop failure. Early detection of chili plant diseases is important to reduce the risk of crop failure. The development of technology and the application of machine-learning algorithms can automatically monitor chili plants using a computer system. Using this algorithm, the system analyzes and identifies diseases that a camera can observe and record. In this study, the proposed method for feature extraction uses a convolutional neural network (CNN) algorithm with transfer learning using VGG19. For classification using SVM for training data, accuracy generated 95%, precision 95%, recall 95%, and F1-Score 95%, and testing data accuracy generated 90%, precision 89%, recall 90%, and F1-Score 89%, proving that the convolutional process with architecture VGG19 and SVM algorithm is acceptable for classification. In future research, other architectures or extraction fusions can be used to maximize the results.

Pattern recognition for EMG based forearm orientation and contraction in myoelectric prosthetic hand

Communication is an essential component of human nature. It connects humans, allowing them to learn, grow, col-laborate, and resolve conflicts. Several aspects of human society, relationships, and growth would be significantly hampered in the absence of efficient communication. Hand gesture recognition is a way to interact with technology that can be particularly useful for individuals with disabilities. This hand gesture recognition is mainly employed in sign language translation, healthcare, rehabilitation, prosthesis, and Human-Computer Interaction (HCI). The high degree of dexterity is a main challenge for prosthetic limbs. In order to meet this challenge, hand gesture recognition is employed for the prosthetic limb, which can be used for rehabilitation. The objective of this article is to show the methodology for the recognition of hand gestures using Electromyography (EMG) signals. This article uses the pro-posed time domain feature extraction method called Absolute Fluctuation Analysis (AFA) along with the Root Mean Square (RMS) for the feature extraction method. Along with these feature extraction methods, repeated stratified K-fold cross validation is used for the validation of the classifiers such as the XGB classifier, the K-Nearest Neighbour (KNN) classifier, the Decision Tree classifier, the Random Forest classifier, and the SVM classifier, whose mean recognition accuracy is given by 93.26%, 87.42%, 85.26%, 92.23%, and 91.78%, respectively. The recognition accuracy of machine learning classifiers is being compared with state-of-the-art networks such as artificial neural net-works (ANN), long short-term memory (LSTM), bidirectional LSTM, gated recurrent units (GRU), and convolution-al neural networks (CNN), which provide recognition accuracy of 96.65%, 99.16%, 99.94%, and 99.99%, respectively.

Multiscale Hjorth Descriptor on Epileptic EEG Classification

The electroencephalogram (EEG) examination provides information on the brain’s electricity, especially in cases of epilepsy. Since the characteristics of EEG signals are nonlinear and nonstationary, visual inspection becomes very difficult. To overcome this problem, digital EEG signal processing was developed. Automatic epileptic EEG recognition is an area of interest on which much research focuses. The complexity approach to EEG signal analysis is interesting to be used as feature extraction, referring to the nonlinear characteristics of the signal. This study proposed an automatic epileptic EEG classification method based on the multiscale Hjorth descriptor measurement. EEG signals consisting of normal, interictal, and seizure (ictal) were simulated. The signal is scaled into new signals using the coarse-grained procedure on a scale of 1–20. Then, the Hjorth parameter which consists of activity, mobility, and complexity is calculated on the new signal. This process produces a feature vector that is used in the classification stage. Support vector machine (SVM) is used to evaluate the proposed feature extraction method. Simulation results showed that the Hjorth parameter on a scale of 1–15 yields 99.5% accuracy. The proposed method is expected to be applied to digital EEG for seizure detection and prediction.

Fault Feature Extraction Method for Rolling Bearings Based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Variational Mode Decomposition

Due to the difficulty in dealing with non-stationary and nonlinear vibration signals using the single decomposition method, it is difficult to extract weak fault features from complex noise; therefore, this paper proposes a fault feature extraction method for rolling bearings based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD) methods. CEEMDAN was used to decompose the signal, and the signal was then screened and reconstructed according to the component envelope kurtosis. Based on the kurtosis of the maximum envelope spectrum as the fitness function, the sparrow search algorithm (SSA) was used to perform adaptive parameter optimization for VMD, which decomposed the reconstructed signal into several IMF components. According to the kurtosis value of the envelope spectrum, the optimal component was selected for an envelope demodulation analysis to realize fault feature extraction for rolling bearings. Finally, by using open data sets and experimental data, the accuracy of envelope kurtosis and envelope spectrum kurtosis as a component selection index was verified, and the superiority of the proposed feature extraction method for rolling bearings was confirmed by comparing it with other methods.

Real-Time Feature Extraction from Electrocochleography with Impedance Measurements during Cochlear Implantation using Linear State-Space Models.

Electrocochleography (ECochG) is increasingly used to monitor the inner ear function of cochlear implant (CI) patients during surgery. Current ECochG-based trauma detection shows low sensitivity and specificity and depends on visual analysis by experts. Trauma detection could be improved by including electric impedance data recorded simultaneously with the ECochG. However, combined recordings are rarely used because the impedance measurements produce artifacts in the ECochG. In this study, we propose a framework for automated real-time analysis of intraoperative ECochG signals using Autonomous Linear State-Space Models (ALSSMs). We developed ALSSM based algorithms for noise reduction, artifact removal, and feature extraction in ECochG. Feature extraction includes local amplitude and phase estimations and a confidence metric over the presence of a physiological response in a recording. We tested the algorithms in a controlled sensitivity analysis using simulations and validated them with real patient data recorded during surgeries. The results from simulation data show that the ALSSM method provides improved accuracy in the amplitude estimation together with a more robust confidence metric of ECochG signals compared to the state-of-the-art methods based on the fast Fourier transform (FFT). Tests with patient data showed promising clinical applicability and consistency with the findings from the simulations. We showed that ALSSMs are a valid tool for real-time analysis of ECochG recordings. Removal of artifacts using ALSSMs enables simultaneous recording of ECochG and impedance data. The proposed feature extraction method provides the means to automate the assessment of ECochG. Further validation of the algorithms in clinical data is needed.

Feature extraction and fault diagnosis of photovoltaic array based on current–voltage conversion

Fault diagnosis plays a crucial role in the operation and maintenance (O&M) of photovoltaic (PV) arrays, and reasonable feature extraction is a prerequisite for effective fault diagnosis. In this paper, a feature extraction and fault diagnosis method based on current–voltage (I–V) conversion is proposed. First, the PV array modeling method based on the double diode model (DDM) and the reverse bias model (RBM) is proposed. This modeling method can simulate the I–V curves under different states and provide data foundation for feature extraction and fault diagnosis. Next, three procedures for correcting I–V curves and three feature enhancement methods are compared to select the optimal program for I–V conversion. The converted feature matrix is dimensionalized using T-distributed stochastic neighbor embedding (T-SNE) to achieve feature extraction. Finally, ten classification models for fault diagnosis are adopted to verify the effectiveness of the proposed feature extraction method. Experimental results demonstrate that the proposed methods perform well on simulation data and provide satisfactory fault diagnosis results for the measured I–V curves. Among the classification models tested, the variable prediction model (VPM) shows the optimal comprehensive performance, with the computational time of 0.17 s and the accuracy of 99.4%.

Deep Autoencoder-Based Integrated Model for Anomaly Detection and Efficient Feature Extraction in IoT Networks

The intrusion detection system (IDS) is a promising technology for ensuring security against cyber-attacks in internet-of-things networks. In conventional IDS, anomaly detection and feature extraction are performed by two different models. In this paper, we propose a new integrated model based on deep autoencoder (AE) for anomaly detection and feature extraction. Firstly, AE is trained based on normal network traffic and used later to detect anomalies. Then, the trained AE model is employed again to extract useful low-dimensional features for anomalous data without the need for a feature extraction training stage, which is required by other methods such as principal components analysis (PCA) and linear discriminant analysis (LDA). After that, the extracted features are used by a machine learning (ML) or deep learning (DL) classifier to determine the type of attack (multi-classification). The performance of the proposed unified approach was evaluated on real IoT datasets called N-BaIoT and MQTTset, which contain normal and malicious network traffics. The proposed AE was compared with other popular anomaly detection techniques such as one-class support vector machine (OC-SVM) and isolation forest (iForest), in terms of performance metrics (accuracy, precision, recall, and F1-score), and execution time. AE was found to identify attacks better than OC-SVM and iForest with fast detection time. The proposed feature extraction method aims to reduce the computation complexity while maintaining the performance metrics of the multi-classifier models as much as possible compared to their counterparts. We tested the model with different ML/DL classifiers such as decision tree, random forest, deep neural network (DNN), conventional neural network (CNN), and hybrid CNN with long short-term memory (LSTM). The experiment results showed the capability of the proposed model to simultaneously detect anomalous events and reduce the dimensionality of the data.

Cluster-based phase space density feature in multichannel scalp EEG for seizure prediction by deep learning

The electroencephalogram (EEG) is one of the most common methods for studying epileptic seizures. Seizure detection has been a well-known subject in neuroscience. According to previous research projects, it is more effective to extract features from the EEG to detect seizures rather than analyzing the raw EEG signals. Therefore, a new feature extraction method is suggested in this work.In this paper, new features are proposed to classify different brain states in EEG records of patients with epilepsy disorder. In previous works, some of the proposed features were based on the ellipses’ data density in phase space which is the motivation of this paper. The innovation here is to use clusters with no specific shapes instead of ellipses to extract improved features. A clustering method is performed on EEG signals in phase space. The densities of data in each cluster are considered as features, and these features are given to a classifier as inputs to classify different brain signals.The investigation is performed on the CHB-MIT scalp EEG dataset. In the binary classification scenario, the achieved results include a sensitivity of 94.94%, a specificity of 94.94%, and a FPR of 0.051 per hour. On the other hand, for the multiclass classification, the specificity is 92.33% and the FPR is 0.077 per hour. These performance metrics highlight the effectiveness of the proposed feature extraction method in generating robust features for classifying brain states. The achieved results demonstrate its superiority over the methods used in previous studies. By extracting meaningful and discriminative features from the EEG signals, the classification model can accurately differentiate between different brain states. This suggests that the proposed method holds promise for improving the accuracy and reliability of brain state classification.The proposed technique can assist neuroscientists in easily distinguishing different states of the brain before the seizure onset.

A novel feature extraction method for recognition of coal and gangue under wetting conditions

Aiming at the problem of low recognition accuracy of coal and gangue under wetting conditions, a new idea of feature extraction for recognition of coal and gangue was proposed based on grayscale distribution morphology. The surface imaging experiments under wetting conditions were carried out and three features such as zone brightness varying with location, bright irregular zones and bright curve zones were found in the obtained images. By studying the causes of these features, the distribution morphology of great grayscale value was selected as features for recognition of coal and gangue. The sub-image was sampled from the whole image by the algorithm of sliding window traversal and its occupied degree by great grayscale value was used to quantify distribution morphology. The maximum width of the sliding window, which was full of great grayscale value, was extracted as feature value of distribution morphology of great grayscale value, which was expressed as A. The recognition experiments of coal and gangue were carried out based on the statistical features of grayscale, the deep learning algorithm (Alex-Net) and A, respectively. The results showed that the maximum recognition accuracy was only 46.26% based on the statistical features of grayscale and the recognition accuracy was 83.0% based on the deep learning algorithm (Alex-Net), while the recognition accuracy reached 97.5% based on A. Such result demonstrates that the proposed feature extraction method can effectively improve the recognition accuracy of coal and gangue under wetting conditions.

A novel feature extraction method for ship-radiated noise based on hierarchical refined composite multi-scale dispersion entropy-based Lempel-Ziv complexity

Accurate recognition of ship-radiated noise (SRN) is particularly important for coastal defense, where feature extraction is the key technology. As a recently proposed nonlinear dynamics index, dispersion entropy-based Lempel-Ziv complexity (DELZC) can effectively quantify the information contained in SRN. However, DELZC characterizes inadequately the complexity feature of SRN with the ignorance of the information under different scales and information hidden in high frequency. To correct these drawbacks, the refined composite coarse-graining operation is integrated into DELZC, and the refined composite multi-scale DELZC (RCMDELZC) is put forward and adequately reflects the scale information, subsequently the technology of hierarchical decomposition is introduced and proposed the hierarchical RCMDELZC (HRCMDELZC), which takes into account the abundant feature information of the signal contained in the time scale and different frequency bands. Then, on the basis of HRCMDELZC, a feature extraction method for SRN by combining with maximum relevance minimum redundancy (mRMR) is proposed. The simulation results show that HRCMDELZC can effectively classify different noise and chaotic signals; the realistic experimental results deliver that the HRCMDELZC features of SRNs have more excellent separability compared with the other seven categories of complexity features, and the proposed feature extraction method has the highest classification accuracy for various SRNs.

Joint filter combination-based central difference feature extraction and attention-enhanced Dense-Res2Block network for short-utterance speaker recognition

Speech authentication in smart services typically involves short utterances. However, due to the short duration of these utterances (e.g. less than 3 s) and the limited enrolment and/or test data available, it is difficult to learn enough information to accurately distinguish the person. As a result, speaker recognition from short utterances is very challenging. In this paper, in the acoustic end. we propose a novel Bark-scaled Gaussian and linear filter bank cepstral coefficients (BGLCC) and multi-dimensional central difference (MDCD) acoustic features extraction method. Also, to enhance the discriminative embedding, in the network end, a novel attention-enhanced Dense-Res2Block network is proposed. First, the rich low-frequency information is extracted based on the high distribution density of the Bark-scaled Gaussian filter bank in the low-frequency domain, and more high-frequency information is extracted based on the linear filter bank uniformly distributed in the high-frequency domain. This means that the combined filters can produce more discriminative and richer acoustic features from short-duration audio signals. In addition, the multi-dimensional central difference method captures better speaker dynamic features in the relative BGLCC domain to improve the performance of short utterance speaker recognition. Finally, an attention-enhanced Dense-Res2Block architecture can obtain a variety of feature expressions of different scale combinations to enhance features. Extensive analysis of a variety of datasets, which speech samples of different types, diverse lengths, etc., demonstrate the superiority of the proposed feature extraction method and model over existing acoustic feature extraction methods and speaker recognition models, including those based on MFCCs, LPCCs, and fusion features, and X-vector-PLDA, BLSTM-ResNet, ResNet34-SP, ECAPA-TDNN respectively. The experimental results show that the proposed method achieves the best performance compared to the existing approach.

Hybrid feature extraction method of MFCC+GFCC helicopter noise based on wavelet decomposition

Aiming at the issue that the recognition accuracy of traditional acoustic signal features is low for helicopter acoustic signals with wind noise in the near field, a method of extracting mixed noise features of MFCC+GFCC based on wavelet decomposition is proposed. Firstly, the three-layer wavelet decomposition and reconstruction are applied to the helicopter acoustic signals; then, the Mel-Frequency Cepstral Coefficients (MFCC) and Gammatone-Frequency Cepstrum Coefficient (GFCC) are respectively extracted for the approximation and detail components; next, the coefficients of detail components which are averaged are combined with those of approximation components to form the hybrid feature parameters; finally, the convolutional neural network is used to classify the signal, to realize the correct recognition of helicopter acoustic signals. Experimental results show that the recognition accuracy is improved by almost 40% in contrast with other traditional methods, such as MFCC and GFCC, when the SNR is equal to -5dB. Further, When the SNR is -10dB, the recognition accuracy is more than 49%, while the traditional methods cannot effectively recognize the helicopter acoustic targets. The proposed feature extraction method can significantly improve the recognition accuracy in the low SNR environment, and provide a reference for near-field detection and recognition of helicopter acoustic targets.

English

EEG is a non-invasive method of recording evoked and induced electrical activity in the brain from the scalp. EEG data is increasingly used in artificial intelligence (A.I.) applications, including pattern recognition, group membership categorization, and brain-computer interface resolutions. This study presents unique EEG data approaches for emotion detection, feature extraction, and classification utilizing fuzzy-based deep learning techniques. This step has analyzed and separated The incoming EEG data as signal fragments. This signal has been pre-processed to remove and normalize noise for feature extraction. The processed signal was retrieved using a fuzzy neural network (FNN) for features. A deep Q neural network was used to classify these retrieved features. Four performance indicators, namely accuracy of 96%, Precision of 90%, Sensitivity of 92%, Specificity of 90% RMSE of 88% for 500 epochs, were used to assess the performance of four distinct classifiers. This investigation indicated that the proposed feature extraction method could accurately identify EEG data recorded during a demanding task. As a result, the suggested feature selection and optimization approach can potentially enhance classification accuracy.

Feature Extraction of Motor Imagery EEG via Discrete Wavelet Transform and Generalized Maximum Fuzzy Membership Difference Entropy: A Comparative Study

Identifying motor imagery (MI) electroencephalogram (EEG) is an important way to achieve brain–computer interface (BCI), but its applicability is heavily dependent on the performance of feature extraction procedure. In this paper, a feature extraction method based on generalized maximum fuzzy membership difference entropy (GMFMDE) and discrete wavelet transform (DWT) was proposed for the feature extraction of EEG signals. The influence of different distance calculation methods, embedding dimensions and tolerances were studied to find the best configuration of GMFMDE for the feature extraction of MI–EEG. The gradient boosting decision tree (GBDT) classifier was used to classify the features extracted from GMFMDE and DWT. The average classification accuracy of 93.71% and the maximum classification accuracy of 96.96% were obtained, which proved the effectiveness of the proposed feature extraction method for EEG signal feature extraction.

Regime independent flow rate prediction in a gas-liquid two-phase facility based on gamma ray technique and one detector using multi-feature extraction

One of the key challenges in petroleum related industries is how to precisely measure the flow rates of individual phases in a pipeline. To address this challenge, in the present study, an automated two-phase test loop capable of generating different flow patterns in horizontal pathway is used to perform experiments on the flow rates. The measuring package set-up consists of a Cs-137 radiation source with photon energy of 662 keV and one NaI (Tl) scintillation detector to register transmission counts. Multi-layer perceptron (MLP) is the selected processing element. Distinguished property of this paper is considering a feature vector with diverse-nature elements as input and the flow rate values of water and air as the target elements. Several combinations of features were investigated to determine the feature vector which shows the best quality to predict the flow rates. Moreover, two structures of MLP with different scenarios of hidden layers were utilized for examining every feature vector set. Numerous experiments were performed to collect adequate data to train and test the ANN in a wide range of air and water flow rates. The results indicate that the proposed model achieved MAE of less than 1 and 5.9 L/min and MRE% of 1.09% and 1.45% to predict water and air flow rates, respectively. The results show that the presented ANN model outperforms existing methods on multiphase flow rates measurements. Therefore, the proposed feature extraction method is applicable to estimate phase flow rates in a two-phase flow for industrial goals.

Transformer Vibration Signal Feature Extraction Based on Compressed Sensing and Wavelet Packet

Transformers are important equipment in the power system. Aiming at the collection, transmission, storage, and processing of massive high-dimensional vibration data in the process of transformer vibration online monitoring, this paper proposes a transformer vibration signal feature extraction method based on compressed sensing and wavelet packets. Firstly, the PartHadamard measurement matrix is used to compress the transformer vibration signal, and then the characteristics of the transformer vibration signal are extracted based on the wavelet packet decomposition and normalized wavelet information entropy. The proposed method completes feature extraction on the measured vibration data of the transformer, and three classification algorithms are applied to carry out simulation experiments. The results show that the proposed feature extraction method can effectively extract the vibration characteristics reflecting the operating state of the transformer while greatly reducing the dimension of vibration data, which provides a reference for the online monitoring of transformer vibration.

Automatic classification of weld defects from ultrasonic signals using WPEE-KPCA feature extraction and an ABC-SVM approach

The classification of weld defects is very important for the safety assessment of welded structures and feature extraction of ultrasonic defect signals is vital for defect classification. A novel approach based on wavelet packet energy entropy (WPEE) and kernel principal component analysis (KPCA) feature extraction and an artificial bee colony optimisation support vector machine (ABC-SVM) classifier is proposed in this paper. Firstly, the WPEE method is adopted to extract ultrasonic signal features of weld defects and KPCA is used for feature selection. Secondly, an ABC-SVM classifier is employed to perform defect classification. Finally, experiments involving defect feature extraction, selection and classification are carried out using four types of weld defect. The results demonstrate that the performance of the proposed feature extraction method based on WPEE is superior to that of wavelet packet energy (WPE). In addition, the WPEE-KPCA method achieved a higher accuracy rate of defect classification than WPEE.

Effect of Local Network Characteristics on the Performance of the SSVEP Brain-Computer Interface

ObjectiveFor decades, a great deal of interest in investigating brain network functional connective features has arisen in brain-computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEPs). Traditional decoding algorithms, for example, canonical correlation analysis (CCA), only consider the inherent properties of each channel in terms of feature extraction for the single channel electroencephalogram (EEG) signal, with inadequate features that cannot fully utilize the information transmitted by the brain. Material and methodsThis paper proposes a fused feature extraction method, CCA-DTF, which combines CCA with a direct transfer function (DTF) to construct local brain network features with seven leads in the occipital region. First, the features extracted by the CCA algorithm were combined with these features extracted by DTF to analyze the EEG data from 20 subjects. Then, two methods, support vector machine (SVM) and random forest (RF), were used in constructing the classifiers for the four tasks classification of the SSVEP-BCI. ResultsThe experimental results showed that incorporating local network features (extracted from DTF or Pearson correlation coefficient) can effectively improve the classification average accuracy and the information transfer rate (ITR) of SSVEP, not only for SVM but also for the ensemble method RF. In particular, CCA-DTF plus SVM obtained a 94.52% classification average accuracy and a 49.23 bits/min ITR in a time window of 2 seconds. The performance was 5.57% and 8.01 bits/min higher than those of traditional CCA plus SVM, respectively. ConclusionThe proposed feature extraction method based on local network features is robust for improving the performance of SSVEP-BCI significantly, which has a perspective of being used in neural rehabilitation engineering field.

Automatic detection of microaneurysms in fundus images based on multiple preprocessing fusion to extract features

Diabetic retinopathy (DR) is the main cause of new cases of blindness, and retinal microaneurysm (MA) is one of the early clinical manifestations of DR. However, it is difficult to directly observe MA with naked eyes because of their small size and poor contrast with the surrounding background. This paper presents a new method for automatic detection of MAs from fundus images. It mainly includes four steps: image preprocessing, candidate region extraction, feature extraction and classification. At the stage of feature extraction, different from traditional methods, we propose a feature extraction method based on multi-preprocessing fusion. In this paper, features are extracted from the original green channel image and the original gray image respectively, and then different processing methods are used to extract the same features from multiple pre-processed images. Finally, the extracted features are classified by multi-layer perceptron (MLP) classifier to determine whether the candidate object is microaneurysm (MA). The method is evaluated on e-ophtha-MA database and achieved high sensitivity. Using the FROC (free-response ROC) indicator, the detection achieves the F-score, accuracy, sensitivity, specificity and AUC (area under the curve) of 0.507, 0.940, 0.870, 0.938 and 0.9821, respectively, compared to the most advanced methods available. The proposed method of multi-preprocessing and fusion feature extraction is beneficial to classification and improves the detection performance.

A generic methodology for the statistically uniform & comparable evaluation of Automated Trading Platform components

Introduction:Although machine learning approaches have been widely used in the field of finance, to very successful degrees, these approaches remain bespoke to specific investigations and opaque in terms of explainability, comparability, and reproducibility. Objectives:The primary objective of this research was to shed light upon this field by providing a generic methodology that was investigation-agnostic and interpretable to a financial markets’ practitioner, thus enhancing their efficiency, reducing barriers to entry, and increasing the reproducibility of experiments. The proposed methodology is showcased on two automated trading platform components. Namely, price levels, a well-known trading pattern, and a novel 2-step feature extraction method. Methods:This proposed a generic methodology, useable across markets, the methodology relies on hypothesis testing, which is widely applied in other social and scientific disciplines to effectively evaluate the concrete results beyond simple classification accuracy. The first hypothesis was formulated to evaluate whether the selected trading pattern is suitable for use in the machine learning setting. The second hypothesis allows us to systematically assess whether the proposed feature extraction method leads to any statistically significant improvement in the automated trading platform performance. Results:Experiments were conducted across, 10 contracts, 3 feature spaces, and 3 rebound configurations (for feature extraction), resulting in 90 experiments. Across the experiments we found that the use of the considered trading pattern in the machine learning setting is only partially supported by statistics, resulting in insignificant effect sizes (Rebound 7 - 0.64±1.02, Rebound 11 0.38±0.98, and rebound 15 - 1.05±1.16), but allowed the rejection of the null hypothesis based on the outcome of the statistical test. While the results of the proposed 2-step feature extraction looked promising at first sight, statistics did not support this, this demonstrated the usefulness of the proposed methodology. Additionally, we obtained SHAP values for the considered models, providing insights for adjustments to the feature space. Conclusion:We showcased the generic methodology on a US futures market instrument and provided evidence that with this methodology we could easily obtain informative metrics beyond the more traditional performance and profitability metrics. The interpretability of these results allows the practitioner to construct more effective automated trading pipelines by analysing their strategies using an intuitive and statistically sound methodology. This work is one of the first in applying this rigorous statistically-backed approach to the field of financial markets and we hope this may be a springboard for more research. A full reproducibility package is shared.