Cumulative Features Research Articles

Analyzing Resampling Techniques for Addressing the Class Imbalance in NIDS using SVM with Random Forest Feature Selection

The purpose of Network Intrusion Detection Systems (NIDS) is to ensure and protect computer networks from harmful actions. A major concern in NIDS development is the class imbalance problem, i.e., normal traffic dominates the communication data plane more than intrusion attempts. Such a state of affairs can pose certain hazards to the effectiveness of detection algorithms, including those useful for detecting less frequent but still highly dangerous intrusions. This paper aims to utilize resampling techniques to tackle this problem of class imbalance in NIDS using a Support Vector Machine (SVM) classifier alongside utilizing features selected by Random Forest to improve the feature subset selection process. The analysis highlights the combativeness of each sampling method, offering insights into their efficiency and practicality for real-world applications. Four resampling techniques are analyzed. Such techniques include Synthetic Minority Over-sampling Technique (SMOTE), Random Under-sampling (RUS), Random Over-sampling (ROS) and SMOTE with two different combinations i.e., RUS SMOTE and RUS ROS. Feature selection was done using Random Forest, which was improved by Bayesian methods to create subsets of features with feature rankings determined by Cumulative Feature Importance Score (CFIS). The CIDDS-2017 dataset is used for the performance evaluation, and the metrics used include accuracy, precision, recall, F-measure and CPU time. The algorithm that performs best overall in the CFIS feature subsets is SMOTE, and the features that give the best result are selected at the 90% level with 25 features. This subset accomplishes a relative accuracy enhancement of 0.08% than the other approaches. The RUS+ROS technique is also fine but somehow slower than SMOTE. On the other hand, RUS+SMOTE shows relatively poor results although it consumes less time in terms of computational time compared to other methods, giving about 50% of the performance shown by the other methods. This paper's novelty is adapting the RUS method as a standalone test for screening new and potentially contaminated datasets. The standalone RUS method is more efficient in terms of computations; the algorithm returned the best result of 98.13% accuracy at 85% at the CFIS level of 34 features with a computation time of 137.812 s. It is also noted that SMOTE is considered to be proficient among all resampling techniques used for handling the problem of class imbalance in NIDS, vice 90% CFIS feature subset. Future research directions could include using these techniques in different data sets and other machine learning and deep learning methods together with ROC curve analysis to provide useful pointers to NIDS designers on how to select the right data mining tools and strategies for their projects.

A Gaussian process embedded feature selection method based on automatic relevance determination

In Gaussian Process, feature importance is inversely proportional to the corresponding length scale when applying the Automatic Relevance Determination (ARD) structured kernel function. Features can be selected by ranking them according to their importance. Among the ARD-based feature selection methods, no uniform score exists for quantifying the output variation explained by feature subsets. This study proposes two feature selection approaches using two cumulative feature importance scores, one titled derivative decomposition ratio and the other normalized sensitivity, to determine the optimal feature subset. The performance of the approaches is assessed to test if irrelevant features are accurately identified and if the feature rankings are correct. The approaches are applied to identify relevant dimensionless inputs for a hybrid model estimating liquid entrainment fraction in two-phase flow. The results reveal that the proposed methods can identify the optimal feature subset for the hybrid model without significantly worsening its Root Mean Squared Error.

Explainable Feature Engineering for Multi-Modal Tissue State Monitoring Based on Impedance Spectroscopy.

One of the most promising approaches to food quality assessments is the use of impedance spectroscopy combined with machine learning. Thereby, feature selection is decisive for a high classification accuracy. Physically based features have particularly significant advantages because they are able to consider prior knowledge and to concentrate the data into pertinent understandable information, building a solid basis for classification. In this study, we aim to identify physically based measurable features for muscle type and freshness classifications of bovine meat based on impedance spectroscopy measurements. We carry out a combined study where features are ranked based on their F1-score, cumulative feature selection, and t-distributed Stochastic Neighbor Embedding (t-SNE). In terms of features, we analyze the characteristic points (CPs) of the impedance spectrum and the model parameters (MPs) obtained by fitting a physical model to the measurements. The results show that either MPs or CPs alone are sufficient for detecting muscle type. Combining capacitance (C) and extracellular resistance (Rex) or the modulus of the characteristic point Z1 and the phase at the characteristic frequency of the beta dispersion (Phi2) leads to accurate separation. In contrast, the detection of freshness is more challenging. It requires more distinct features. We achieved a 90% freshness separation using the MPs describing intracellular resistance (Rin) and capacitance (C). A 95.5% freshness separation was achieved by considering the phase at the end of the beta dispersion (Phi3) and Rin. Including additional features related to muscle type improves the separability of samples; ultimately, a 99.6% separation can be achieved by selecting the appropriate features.

Digital technologies for signal radio vision and radio monitoring

Objectives. Radiophysical processes involving the electrodynamic formation of signal radio images diffusely scattered by the signature of small-sized objects or induced by the near field of radio devices are relevant for identifying radiogenomic (cumulant) features of objects in the microwave range in the development of neuroimaging ultra-short pulse (USP) signal radio vision systems, telemonitoring, and near-radio detection. The paper sets out to develop methods and algorithms for vector analysis of radio wave deformation of nonstationary fields forming a signal radio image based on radiophysical and topological characteristics of small-sized objects; to develop software and hardware for registration and neural network recognition of signal radio images, including methods for the synthesis and extraction of signal radiogenomes using digital twins of objects obtained through vector electrodynamic modeling; and to analyze signal radio images induced by elements of printed topology of electronic devices.Methods. The study is based on statistical radiophysics methods, time-frequency approaches for wavelet transformation of USP radio images, numerical electrodynamic methods for creating digital twins of small-sized objects, as well as neural network authentication algorithms based on the cumulant theory of pole-genetic and resonant physically unclonable functions used in identifying signal radio images.Results. The results of fundamental research on electrodynamic effects of vector-wave deformation of nonstationary fields of sub-nanosecond configuration are presented as a means of identifying and authenticating signal radio images. Neural network techniques for cumulant formation of radio genomes of signal radio images are proposed on the basis of pole-genetic and resonant functions.Conclusions. A radiogenome, representing the unique authenticator of a radio image, is shown to be formed on the basis of physically unclonable functions determined by the structure and set of radiophysical parameters of the image. Cumulant features of signal radio images identified on the basis of pole-genetic and physically unclonable resonant functions of small-sized objects are revealed.

Edge-preserving image deraining network using cumulative feature aggregation

This study proposes an edge-preserving image deraining network using a wavelet feature aggregation method. Wavelet subbands re correlated with each other, and the high-frequency subband in the horizontal direction is the least affected by rain streak contamination. On this basis, we introduce a single image deraining network that cumulatively aggregates wavelet subband features according to their importance. The network architecture primarily comprises a wavelet feature aggregation block and a residue channel guide block. The aggregation of features with the cumulative wavelet feature aggregation block moves downward and upward, and a long short-term memory-based multiscale attentive rain streak removal block is developed to serve as the backbone for rain streak removal. We use a residual channel map based on the low-frequency subband to construct guide features that assist in rain streak removal. A repetitive image restoration framework that incorporates two proposed blocks is used to iteratively improve rainy images. We test the proposed network on various image datasets and compare the deraining performance with those of existing methods The experimental results demonstrate that the performance of the proposed scheme is superior to that of other tested deraining methods. https://github.com/SYChoi98/CWFANet/

Prediction of Individual Gas Yields of Supercritical Water Gasification of Lignocellulosic Biomass by Machine Learning Models.

Supercritical water gasification (SCWG) of lignocellulosic biomass is a promising pathway for the production of hydrogen. However, SCWG is a complex thermochemical process, the modeling of which is challenging via conventional methodologies. Therefore, eight machine learning models (linear regression (LR), Gaussian process regression (GPR), artificial neural network (ANN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGB), and categorical boosting regressor (CatBoost)) with particle swarm optimization (PSO) and a genetic algorithm (GA) optimizer were developed and evaluated for prediction of H2, CO, CO2, and CH4 gas yields from SCWG of lignocellulosic biomass. A total of 12 input features of SCWG process conditions (temperature, time, concentration, pressure) and biomass properties (C, H, N, S, VM, moisture, ash, real feed) were utilized for the prediction of gas yields using 166 data points. Among machine learning models, boosting ensemble tree models such as XGB and CatBoost demonstrated the highest power for the prediction of gas yields. PSO-optimized XGB was the best performing model for H2 yield with a test R2 of 0.84 and PSO-optimized CatBoost was best for prediction of yields of CH4, CO, and CO2, with test R2 values of 0.83, 0.94, and 0.92, respectively. The effectiveness of the PSO optimizer in improving the prediction ability of the unoptimized machine learning model was higher compared to the GA optimizer for all gas yields. Feature analysis using Shapley additive explanation (SHAP) based on best performing models showed that (21.93%) temperature, (24.85%) C, (16.93%) ash, and (29.73%) C were the most dominant features for the prediction of H2, CH4, CO, and CO2 gas yields, respectively. Even though temperature was the most dominant feature, the cumulative feature importance of biomass characteristics variables (C, H, N, S, VM, moisture, ash, real feed) as a group was higher than that of the SCWG process condition variables (temperature, time, concentration, pressure) for the prediction of all gas yields. SHAP two-way analysis confirmed the strong interactive behavior of input features on the prediction of gas yields.

On the generalization of cognitive optical networking applications using composable machine learning

Model generalization characterizes the sustainability of machine learning (ML) designs applied to novel system states and therefore plays a vital role toward the realization of cognitive networking. In this paper, we present a composable ML framework (namely, CompML), aiming at generalizing ML-aided cognitive applications for optical networks. CompML makes use of three basic functional modules, i.e., the Loading, Recursion, and Readout modules, to model the loading/initialization processes (e.g., the launch of a signal), extract cumulative features by recursive operations, and produce model inferences, respectively. By the composition of the three modules and adoption of an end-to-end training mechanism, CompML allows for generalizing multiple tasks of the same domain [e.g., quality-of-transmission (QoT) estimation for different lightpaths]. We perform case studies of CompML on QoT estimation and nonlinearity compensation using both simulation and experimental data. Results show the superior generalization ability of CompML compared with the baselines, achieving mean absolute error (MAE) for generalized signal-to-noise ratio (GSNR) prediction error of below 1.06 dB for unseen lightpaths and up to 3 dB Q-factor improvement for nonlinearity compensation.

Quasi-phase-matched nonlinear Lamb waves in composite laminates for material degradation monitoring

Monitoring material degradation and in-service damage in fibrous composites at an early stage is challenging, yet critical for many industrial applications. Second harmonic Lamb waves, which result from the interaction of fundamental waves with material microstructural defects, have great potential for Structural Health Monitoring (SHM) applications. However, understanding of the second harmonic generation in composite laminates remains largely insufficient, which hinders practical SHM applications. This issue is investigated in this study to highlight the quasi-cumulative second harmonic B2 mode Lamb wave in the low frequency range. Theoretical analyses are conducted to ascertain how anisotropy affects the quasi-cumulative effect, followed and validated by numerical simulations and analyses considering different wave propagation angles. The characteristics of the second harmonic B2 mode Lamb waves are further explored in terms of the cumulative feature, robustness to wave beam divergence, and excitability. Experiments are finally carried out to monitor material degradation during the thermal aging of a carbon fiber reinforced panel. The results confirm the omnidirectional cumulative effect of quasi-phase-matched second harmonic B2 mode Lamb waves. It is revealed that the 0° propagating Lamb waves exhibit superior cumulative effect, high robustness to wave beam divergence, and good excitability, rendering them an ideal tool for SHM applications. Furthermore, the high sensitivity of the second harmonic B2 mode waves to material degradation is demonstrated, confirming their promise for material degradation monitoring applications in composite structures.

Seeing Beyond Words: An Investigation of Students' Opinions on Interactive Murals for Vocabulary Teaching

This study investigates the ways in which students view interactive murals as part of the vocabulary teaching and learning process in the classroom. A qualitative methodology and survey were administered to 22 elementary school students. The three components of the questionnaire were as follows: the pedagogical content of the feature of interactive mural, and motivation in using the murals. The questionnaire was administered to a research sample of 22 students who were specifically selected for the study. With a coefficient of scalability (CS) of at least 0.60 and a coefficient of reproducibility (CR) of at least 0.90, the data were deemed to meet the unidimental and cumulative features after being analyzed using the Guttman scale. The results revealed that the mean CS score was 0.91, indicating that the coefficients of scalability were deemed good, and the mean CR score from the three indicators was 0.90, indicating that the CR results were valid. Considering the mean recapitulation rate among the students was 16,33%, the students’ perception was positive. The results, which showed that students’ perceptions of the interactive smural’s use as a technology in the classroom were positively correlated with their use of learning resources. It was possible for the students to acquire new teaching tools, such as interactive murals. Murals werehave been suggested as a potentially engaging substitute for traditional classroom media, particularly when teaching vocabulary. In summary, by documenting the diverse perspectives, this research not only sheds light on the perceived advantages of interactive murals but also emphasizes how these visual aids can be utilizedused to create captivating and productive vocabulary learning opportunities. The findings have implications for teachers, curriculum developers, and legislators who want to improve vocabulary instruction in the classrooms by incorporating interactive and visually appealing elements of murals.

BEING MIGRANT AND BEING VULNERABLE: AN OVERVIEW OF THE COVID-19 SITUATION IN KUALA LUMPUR

COVID-19 can cause single or sporadic cases, leading to a limited or widespread outbreak or pandemic, requiring public health intervention. This disease is a global pandemic that requires extreme strategies from both local and global public health agencies. It has also caused havoc among public health practitioners and increases the risk among the vulnerable population. This research aims to provide an overview of the trend and demographic of COVID-19 cases in Kuala Lumpur, Malaysia. A total of 12,731 confirmed COVID-19 cases from January to December of 2020 are included, subjected to inclusion and exclusion criteria. Data only focuses on the cumulative features for COVID-19 cases based on the demographic. The analysis that had been carried out in this study are descriptive analysis for the demographic and Chi-Square test to determine the association between age and nationality. Result from the descriptive analysis shows that males (88.0%) recorded the highest number of COVID-19 cases with majority among those aged 31-50 years old (54.2%). In terms of case outcome, the majority of those infected were discharged from the hospital (99.8%). Immigrants represent the largest percentage of COVID-19 cases at 79.9% in total, with most coming from low-income countries. Chi-square between age and nationality indicates a significant association with p-value 0.000, highlighting a higher risk of transmission among the immigrants. This paper highlights the potential risk of COVID-19 among the immigrants in Kuala Lumpur at the start of the pandemic. As part of the vulnerable population, targeted efforts need to be made for immigrants to allow them equal access to healthcare and to reduce the burden of disease among public health practitioners.

Multi-task neural network for solving the problem of recognizing the type of QAM and PSK modulation under parametric a priori uncertainty

Objectives. Automatic modulation recognition of unknown signals is an important task for various fields oftechnology such as radio control, radio monitoring, and identification of interference and sources of radio emission. The paper aims to develop a method for recognizing the types of signal modulation under conditions of parametric a priori uncertainty, including the uncertainty of carrier frequency- and initial signal phase values. An additional task consists in estimating the offset values of the carrier frequency or signal phase at the initial stage of the recognition process.Methods. A multi-task learning with artificial neural network and the theory of cumulants of random variables are used.Results. For signals with a carrier frequency and initial phase shift, cumulant approaches for QAM-8, APSK-16, QAM-64, and PSK-8 modulations are calculated. A multi-task learning with artificial neural network using cumulant features and a data standardization algorithm is presented. The results of the experiment show that using multi-task learning with an artificial neural network provides high accuracy of recognizing QAM-8 and APSK-16, QAM-64 and PSK-8 modulations with small mismatches of the carrier frequency or initial phase. The accuracy of determining the offset values from the carrier frequency or the initial phase for QAM-8, APSK-16, QAM-64, and PSK-8 modulation is high.Conclusions. The multi-task learning with neural network using high-order signal cumulants makes it possible not only to recognize modulation types with high accuracy under conditions of a priori uncertainty of signal parameters, but also to determine the offset values of carrier frequency or initial signal phase from expected values.

Channel Prediction-Based Security Authentication for Artificial Intelligence of Things.

The emerging physical-layer unclonable attribute-aided authentication (PLUA) schemes are capable of outperforming traditional isolated approaches, with the advantage of having reliable fingerprints. However, conventional PLUA methods face new challenges in artificial intelligence of things (AIoT) applications owing to their limited flexibility. These challenges arise from the distributed nature of AIoT devices and the involved information, as well as the requirement for short end-to-end latency. To address these challenges, we propose a security authentication scheme that utilizes intelligent prediction mechanisms to detect spoofing attack. Our approach is based on a dynamic authentication method using long short term memory (LSTM), where the edge computing node observes and predicts the time-varying channel information of access devices to detect clone nodes. Additionally, we introduce a Savitzky-Golay filter-assisted high order cumulant feature extraction model (SGF-HOCM) for preprocessing channel information. By utilizing future channel attributes instead of relying solely on previous channel information, our proposed approach enables authentication decisions. We have conducted extensive experiments in actual industrial environments to validate our prediction-based security strategy, which has achieved an accuracy of 97%.

Battery SOH estimation based on decision tree and improved support vector machine regression algorithm

Battery state of health (SOH) estimation is crucial for the estimation of the remaining driving range of electric vehicles and is one of the core functions of the battery management system (BMS). The lithium battery feature sample data used in this paper is extracted from the National Aeronautics and Space Administration (NASA) of the United States. Based on the obtained feature samples, a decision tree algorithm is used to analyze them and obtain the importance of each feature. Five groups of different feature inputs are constructed based on the cumulative feature importance, and the original support vector machine regression (SVR) algorithm is applied to perform SOH estimation simulation experiments on each group. The experimental results show that four battery features (voltage at SOC = 100%, voltage, discharge time, and SOC) can be used as input to achieve high estimation accuracy. To improve the training efficiency of the original SVR algorithm, an improved SVR algorithm is proposed, which optimizes the differentiability and solution method of the original SVR objective function. Since the loss function of the original SVR is non-differentiable, a smoothing function is introduced to approximate the loss function of the original SVR, and the original quadratic programming problem is transformed into a convex unconstrained minimization problem. The conjugate gradient algorithm is used to solve the smooth approximation objective function in a sequential minimal optimization manner. The improved SVR algorithm is applied to the simulation experiment with four battery feature inputs. The results show that the improved SVR algorithm significantly reduces the training time compared to the original SVR, with a slight trade-off in simulation accuracy.

Deep-Learning-Based Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulants.

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used convolutional neural networks (CNNs) or residual networks (RESNETs) with the in-phase/quadrature (I/Q) data used for training and classification.

Improving Wildfire Danger Assessment Using Time Series Features of Weather and Fuel in the Great Xing’an Mountain Region, China

Wildfires directly threaten the safety of life and property. Predicting wildfires with a model driven by wildfire danger factors can significantly reduce losses. Weather conditions continuously influence the drying rate of fuel as well as the occurrence probability and danger degree of wildfires. Previous studies have paid little attention to the continuous effects of weather and fuel on wildfires. This study improved the accuracy and effect of wildfire danger assessment using the time series features of weather and fuel. First, the time series features of weather and fuel factors within the 16 days before the fire were analyzed. Then, four feature groups were selected—feature group without time series values, feature group with time series values, feature group with Tsfresh transformation of time series values, and feature group with gradient and cumulative transformation of time series values—and three models were trained, respectively: random forest, balanced random forest, and extreme gradient boosting. The results showed that the f1-score of all feature groups with time series values (0.93) increased by 0.15, on average, compared with those without time series values (0.78) for the three models. The feature group with gradient and cumulative features had a more stable prediction accuracy and a more accurate wildfire danger map. The results suggest that using the appropriate time series features of weather and fuel can help improve the precision and effect of the wildfire danger assessment model.

MBERT-GRU multilingual deep learning framework for hate speech detection in social media

One major issue plaguing online social media is hate speech, a complex phenomenon whose identification and target categorization have been studied by the natural language processing community. In recent years, notable studies have been made towards hate speech detection using various mechanisms varying from traditional machine learning to complex deep neural network models. However, these studies mainly focus on high-resource English language. The multilingual societies such as the Indian subcontinent: English, Hindi and Hindi-English code-mixed languages are widespread and convenient for the users. The research works studying hate speech detection in these languages are still very limited. To fill this gap, we propose an mBERT-GRU framework comprising of multilingual BERT embedding and bidirectional GRU layers to learn the cumulative features for hate speech detection and its target categorization. We evaluated our work on three datasets HASOC-2019, HS and HEOT to prove the competitive performance. Our results show that the proposed framework outperformed monolingual and state-of-the-art methods on English, Hindi and Hindi-English code-mixed datasets with Macro-F1 measure values of 0.87, 0.83 and 0.77, respectively.

Image recognition of sports dance teaching and auxiliary function data verification based on neural network algorithm

Nowadays, physical dance is widely spread in the society as an emerging sport. Dance movement is favored by people because of its unique social function and fitness effect. For dance teaching, dance movement analysis can help optimize and improve the existing dance movements and the understanding and inheritance of traditional dance movements. With the rise of online teaching, intelligent identification and analysis of dance movements can promote the better development of sports dance teaching. However, the relevant research in this area is still very scarce. As the basis of this kind of research, there is an urgent need for dance motion recognition technology. Based on this background, this paper by introducing neural network algorithm for dance teaching sports image special recognition design, the algorithm can combine feature extraction technology to process video, extract the dance movements in the target data set, then for the extraction of cumulative feature extraction operation, in order to accumulate all the collected target features, so as to further complete the gradient histogram acquisition. Through the design experimental test, the cumulative feature image extraction results obtained through the algorithm are obviously better than the traditional image recognition results, so the design rationality and effectiveness of the algorithm are proved, and the sports dance teaching can be specially assisted. This paper designs an effective auxiliary image recognition algorithm by introducing the neural network algorithm into the field of sports dance teaching.

Research and implementation of modulation recognition based on cascaded feature fusion

AbstractAiming at the problems of weak robustness of single feature and limited recognition range in modulation recognition, this paper proposes a modulation recognition algorithm based on cascaded feature fusion and multi‐classifier combination, in which time‐frequency map and instantaneous amplitude spectral density features are extracted from low intermediate frequency (IF) signal, constellation map and high‐order cumulant features are extracted from zero IF signal, and a three‐level recognition algorithm is designed through the decision fusion of decision tree, convolutional neural network, and support vector machine. In order to verify the performance of the algorithm, a modulation recognition system is designed and built based on USRP2974. The low IF and zero IF modulation signals are received through two channels, and the RF signals are received and processed in real time with the help of the built‐in CPU of the receiver. The recognition of 13 kinds of analog modulation and digital modulation signals is realized. Under the condition of wireless reception, the recognition rate of this system is more than 93% at 5 to 10 dB.

Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis.

Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model's explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.

Bearings Degradation Assessment Based on Signal Significance Index and Deep Cumulative Features

Bearings Degradation Assessment Based on Signal Significance Index and Deep Cumulative Features