Search

Recently, renewable energy sources integrated with microgrid (MG) networks have provided safe, secure, and reliable power supply to both utility and industrial purposes. Power quality disturbances (PQDs) seriously affect the performance of MG networks and reduce the lifecycle of numerous sensitive devices in MG networks. Hence, this paper presents a new approach to detect and classify the PQDs using discrete wavelet transform, multiresolution analysis, and optimized‐kernel support vector machine. The obtained unique features from DWT‐MRA are fed to train the well‐known intelligent classifiers. In the optimized‐kernel SVM model, computing power is enhanced for classifying multiple PQ events based on the local density and leave‐one‐out (LOO) algorithm. To get higher separation in feature space, the kernel width of each sample is estimated based on the local density. By using the LOO method, an improved grid search strategy is implemented to get the penalty parameter to achieve satisfactory results. Moreover, a typical MG network is simulated in MATLAB software considering the validation of the proposed technique to address the power quality issues in MG networks, and the results of the proposed method are compared with other conventional ML classifiers. The simulation results confirm that the proposed method is more effective and accurate than other intelligent classifiers. [ABSTRACT FROM AUTHOR]

The vibration signal from the planetary gearbox exhibits nonlinear and impulsive characteristics amidst strong noise, impeding the effective extraction of fault information and compromising the accuracy of fault diagnosis. To address this challenge, a fault diagnosis method rooted in feature mode decomposition (FMD) is proposed. Initially, the critical parameters (modal number n and filter length L) of FMD are optimized using an improved genetic algorithm (IGA), and the refined FMD is employed to decompose the vibration signals from the planetary gearbox. Subsequently, a convolutional neural network integrated with the support vector machine model (CNN‐SVM) is established, leveraging the convolutional neural network for feature extraction. Ultimately, SVM iteratively optimized by the particle swarm optimization (PSO) algorithm, serves as the classification technique. Simulation and experiment results demonstrate the effectiveness of this method in extracting and identifying fault information within planetary gearboxes. [ABSTRACT FROM AUTHOR]

Objective. One of the most frequent consequences of diabetes mellitus has been identified as diabetic peripheral neuropathy (DPN), and numerous inflammatory disorders, including diabetes, have been documented to be reflected by the neutrophil‐to‐lymphocyte ratio (NLR). This study aimed to explore the correlation between peripheral blood NLR and DPN, and to evaluate whether NLR could be utilized as a novel marker for early diagnosis of DPN among those with type 2 Diabetes Mellitus (T2DM). Methods. We reviewed the medical records of 1154 diabetic patients treated at Tongji Hospital Affiliated to Tongji University from January 2022 to March 2023. These patients did not have evidence of acute infections, chronic inflammatory status within the past three months. The information included the clinical, laboratory, and demographic characteristics of the patient. Finally, a total of 442 T2DM individuals with reliable, complete, and accessible medical records were recruited, including 216 T2DM patients without complications (DM group) and 226 T2DM patients with complications of DPN (DPN group). One‐way ANOVA and multivariate logistic regression were applied to analyze data from the two groups, including peripheral blood NLR values and other biomedical indices. The cohort was divided in a 7 : 3 ratio into training and internal validation datasets following feature selection and data balancing. Based on machine learning, training was conducted using extreme gradient boosting (XGBoost) and support vector machine (SVM) methods. K‐fold cross‐validation was applied for model assessment, and accuracy, precision, recall, F1‐score, and the area under the receiver operating characteristic curve (AUC) were used to validate the models' discrimination and clinical applicability. Using Shapley Additive Explanations (SHAP), the top‐performing model was interpreted. Results. The values of 24‐hour urine volume (24H UV), lower limb arterial plaque thickness (LLAB thickness), carotid plaque thickness (CP thickness), D‐dimer and onset time were significantly higher in the DPN group compared to the DM group, whereas the values of urine creatinine (UCr), total cholesterol (TC), low‐density lipoprotein (LDL), alpha‐fetoprotein (AFP), fasting c‐peptide (FCP), and nerve conduction velocity and wave magnitude of motor and sensory nerve shown in electromyogram (EMG) were considerably lower than those in the DM group (P < 0.05, respectively). NLR values were significantly higher in the DPN group compared to the DM group (2.60 ± 4.82 versus 1.85 ± 0.98, P < 0.05). Multivariate logistic regression analysis revealed that NLR (P = 0.008, C = 0.003) was a risk factor for DPN. The multivariate logistic regression model scores were 0.6241 for accuracy, 0.6111 for precision, 0.6667 for recall, 0.6377 for F1, and 0.6379 for AUC. Machine learning methods, XGBoost and SVM, built prediction models, showing that NLR can predict the onset of DPN. XGBoost achieved an accuracy of 0.6541, a precision of 0.6316, a recall of 0.7273, a F1 value of 0.6761, and an AUC value of 0.690. SVM scored an accuracy of 0.5789, a precision of 0.5610, a recall of 0.6970, an F1 value of 0.6216, and an AUC value of 0.6170. Conclusions. Our findings demonstrated that NLR is highly correlated with DPN and is an independent risk factor for DPN. NLR might be a novel indicator for the early diagnosis of DPN. XGBoost and SVM models have great predictive performance and could be reliable tools for the early prediction of DPN in T2DM patients. This trial is registered with ChiCTR2400087019. [ABSTRACT FROM AUTHOR]

Background. Functional near‐infrared spectroscopy (fNIRS) is being extensively explored as a potential primary screening tool for major depressive disorder (MDD) because of its portability, cost‐effectiveness, and low susceptibility to motion artifacts. However, the fNIRS‐based computer‐aided diagnosis (CAD) of MDD using deep learning methods has rarely been studied. In this study, we propose a novel deep learning framework based on a convolutional neural network (CNN) for the fNIRS‐based CAD of MDD with high accuracy. Materials and Methods. The fNIRS data of participants—48 patients with MDD and 68 healthy controls (HCs)—were obtained while they performed a Stroop task. The hemodynamic responses calculated from the preprocessed fNIRS data were used as inputs to the proposed CNN model with an ensemble CNN architecture, comprising three 1D depth‐wise convolutional layers specifically designed to reflect interhemispheric asymmetry in hemodynamic responses between patients with MDD and HCs, which is known to be a distinct characteristic in previous MDD studies. The performance of the proposed model was evaluated using a leave‐one‐subject‐out cross‐validation strategy and compared with those of conventional machine learning and CNN models. Results. The proposed model exhibited a high accuracy, sensitivity, and specificity of 84.48%, 83.33%, and 85.29%, respectively. The accuracies of conventional machine learning algorithms—shrinkage linear discriminator analysis, regularized support vector machine, EEGNet, and ShallowConvNet—were 73.28%, 74.14%, 62.93%, and 62.07%, respectively. Conclusions. In conclusion, the proposed deep learning model can differentiate between the patients with MDD and HCs more accurately than the conventional models, demonstrating its applicability in fNIRS‐based CAD systems. [ABSTRACT FROM AUTHOR]

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F 1 score, accuracy, precision, and recall. Model performance was high, with F 1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F 1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments. [ABSTRACT FROM AUTHOR]

Stroke is a high morbidity and mortality disease that poses a serious threat to people's health. Early recognition of the various warning signs of stroke is necessary so that timely clinical intervention can help reduce the severity of stroke. Deep neural networks have powerful feature representation capabilities and can automatically learn discriminant features from large amounts of data. This paper uses a range of physiological characteristic parameters and collaborates with deep neural networks, such as the Wasserstein generative adversarial networks with gradient penalty and regression network, to construct a stroke prediction model. Firstly, to address the problem of imbalance between positive and negative samples in the stroke public data set, we performed positive sample data augmentation and utilized WGAN‐GP to generate stroke data with high fidelity and used it for the training of the prediction network model. Then, the relationship between observable physiological characteristic parameters and the predicted risk of suffering a stroke was modeled as a nonlinear mapping transformation, and a stroke prediction model based on a deep regression network was designed. Finally, the proposed method is compared with commonly used machine learning‐based classification algorithms such as decision tree, random forest, support vector machine, and artificial neural networks. The prediction results of the proposed method are optimal in the comprehensive measurement index F. Further ablation experiments also show that the designed prediction model has certain robustness and can effectively predict stroke diseases. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative approach, Deep Multiscale Soft-Threshold Support Vector Data Description (DMS-SVDD), designed for the detection of anomalies and prediction of faults in heavy-duty gas turbine generator sets (GENSETs). The model combines a support vector data description (SVDD) with a deep autoencoder backbone network framework, integrating a multiscale convolutional neural network (M) and soft-threshold activation network (S) into the Deep-SVDD framework. In comparison with conventional methods, such as One-Class Support Vector Machine (OCSVM) and autoencoder (AE), DMS-SVDD demonstrates improvements in accuracy (by 22.94%), recall (by 32%), F1 score (by 12.02%), and smoothness (by 39.15%). The model excels particularly in feature extraction, denoising, and early fault detection, offering a proactive strategy for maintenance. Furthermore, the DMS-SVDD demonstrated enhanced training efficiency with a reduction in the convergence rounds by 66% and overall training times by 34.13%. The study concludes that DMS-SVDD presents a robust and efficient solution for gas turbine anomaly detection, with practical advantages for decision support in turbine maintenance. Future research could explore additional refinements and applications of the DMS-SVDD model across diverse industrial contexts. [ABSTRACT FROM AUTHOR]

The widespread integration of renewable energy sources (RESs) into power systems using power electronics-based interface devices has led to a substantial rise in power quality (PQ) issues. There is an immediate requirement for effective monitoring, detection, and classification of power quality disturbances (PQDs) that is needed to take remedial measures and design planning of the system architecture. This study presents a hybrid approach with an objective for the feature extraction and classification of PQDs. The proposed hybrid approach is comprised of an optimized tunable-Q wavelet transform (OTQWT) for the feature extraction and incremental support vector machine (ISVM). A four-stage approach is suggested for the PQ detection and classification in this study. In the first stage, the various data are retrieved both in the form of synthetic data by mathematical formulations and real-time data with prototype design setup. In the second stage, regardless of the specified wavelet function, the PQD signals are decomposed into low-pass and high-pass sub-bands using the tunable-Q wavelet transform (TQWT). However, the utilization of default decomposition parameters to address nonstationary PQ signals may lead to information loss and reduced performance of the system. To avoid this limitation, an OTQWT as an enhanced technique to TQWT based on an Adaptive Particle Swarm Optimization (APSO) is suggested. A modified objective function based on the mean square error (MSE) is used to improve the decomposition process. In the third stage, an efficient classifier is suggested based on the ISVM. Lastly, to test and evaluate the performance of the proposed approach, twelve types of PQDs including noise and multiple occurrences are considered. The comparative analysis with other popular methods reflects the better performance of the proposed approach and justifies its use for PQ detection and classification purposes in real-time​ conditions. [ABSTRACT FROM AUTHOR]

The respiratory disease of coronavirus disease 2019 (COVID-19) has wreaked havoc on the economy of every nation by infecting and killing millions of people. This deadly disease has taken a toll on the life of the entire human race, and an exact cure for it is still not developed. Thus, the control and cure of this disease mainly depend on restricting its transmission rate through early detection. The detection of coronavirus infection facilitates the isolation and exclusive care of infected patients. This research paper proposes a novel data mining system that combines the ensemble feature selection method and machine learning classifier for the effective identification of COVID-19 infection. Different feature selection approaches including chi-square test, recursive feature elimination (RFE), genetic algorithm (GA), particle swarm optimization (PSO), and random forest are evaluated for their effectiveness in enhancing the classification accuracy of the machine learning classifiers. The classifiers that are considered in this research work are decision tree, naïve Bayes, K -nearest neighbor (KNN), multilayer perceptron (MLP), and support vector machine (SVM). Two COVID-19 datasets were used for testing from which the best features supporting the dataset were extracted by the proposed system. The performance of the machine learning classifiers based on the ensemble feature selection methods is analyzed. [ABSTRACT FROM AUTHOR]

Recent experience with the strongest earthquakes greater than magnitude 5.4 in Korea leads to public interest in the safety and resilience of critical infrastructures. There are many nuclear power plants near the epicenters of the earthquakes. Nuclear power plants are essential infrastructures that provide stable and enough energy for human life, and simultaneously, control systems for the safety and security of nuclear power plants are critical due to the risk of nuclear accidents on public health and the environment. The nuclear area uses probabilistic risk assessment to estimate the risk of structures, systems, and components in nuclear power plants, and the evaluation of the fragility curve is a key process for probabilistic risk assessment. The challenges of a seismic fragility analysis lie in estimating the influence of various uncertainties in material, geometry, and earthquake and improving the existing fragility analysis methods, which require time-consuming nonlinear time history analysis. Thus, this paper conducts a multivariate seismic fragility analysis using surrogate models for reinforced concrete squat shear walls and proposes a simplified closed form equation for a chosen surrogate seismic demand model. The surrogate models are trained and validated by several approaches: response surface method, support vector machine, Gaussian process regression, and neural network. In addition, a correlation analysis is used to evaluate the relative importance of the variables to the seismic demand to simplify the surrogate model further. Finally, simplified surrogate models based on the importance of the variables are proposed as closed form of polynomials, and the performance of these models on the fragility analysis is evaluated. [ABSTRACT FROM AUTHOR]

Gas reservoir development and the estimation of rock properties heavily rely on lithology classification, which can be difficult, time-consuming, and prone to errors. In this study, a novel deep learning-based approach has been developed for the rapid, accurate, and efficient prediction of lithology in a gas field from conventional well-log data. The well-logs, referred to as numerical well-logs (NWLs), are transformed into two-dimensional images through two proposed approaches: shallow images (SIs) and deep images (DIs). In these images, the pixels effectively represent the relationships between different logs. For this purpose, we developed residual convolutional neural networks (ResCNN) named SIs-ResCNN 2D and DIs-ResCNN 2D. The feed data for DIs-ResCNN 2D are images created and referred to as DIs, which are initially formed from a vector in which the order of logs is somehow repeated, ensuring that each pairwise combination occurs only once. This resulted in the incorporation of the connection between the logs within the pixels of the generated images, alongside the integration of unique binary combinations of the logs. We compared the proposed models, including DIs-ResCNN 2D, DIs-ResCNN 2D, and NWLs-ResCNN 1D with baseline methods such as random forest (RF), K-nearest neighbor (KNN), and support vector machine (SVM). Based on the evaluation metrics, DIs-ResCNN 2D outperformed the other proposed and baseline methods on the test dataset. A balanced DIs-ResCNN 2D model achieved 93% accuracy and F1-score of 80% on a test well, highlighting the importance of data balancing during CNN model training. [ABSTRACT FROM AUTHOR]

Bridges situated on small-radius reverse curves play a pivotal role within some railway networks, exerting influence over project-wide design progress. Typically, assessing the safety of bridge design parameters necessitates laborious vehicle-bridge dynamic coupling vibration numerical analysis or model experiments. To streamline the design process and enhance efficiency during the preliminary design phase, we propose an efficient method to assess the dynamic performance of bridges on small-radius reverse curves. This approach enables direct prediction of bridge dynamic performance based on design parameters, eliminating the need for numerical simulations and model experiments. We first develop a vehicle-bridge coupling vibration program grounded in train-curve bridge coupling vibration theory, validated using on-site measured data. Subsequently, through numerical simulation experiments, we evaluate 80 simply supported beam bridges on small-radius reverse curves under various operating conditions, generating ample dynamic response data for bridge pier tops and girders. These data are then compared with regulatory thresholds to assign dynamic performance labels. After identifying essential design parameters as data features using Fisher scores, we proceed to input these features into a support vector machine (SVM). Through supervised training with dynamic performance labels, this process empowers the SVM model to predict the dynamic performance of the bridge. Our results demonstrate that this method circumvents the need for detailed vehicle-bridge interaction analysis, yielding an impressive 86.9% accuracy in predicting dynamic performance and significantly boosting computational efficiency. Besides, the top five design parameters that significantly influence the prediction of bridge dynamic performance are obtained. This novel approach has the potential to expedite design assessments and enhance safety in railway bridge construction. [ABSTRACT FROM AUTHOR]

The primary aim of this study is to explore the utility of machine learning algorithms for predicting personal PM2.5 exposures of elderly participants and to evaluate the effect of individual variables on model performance. Personal PM2.5 was measured on five consecutive days across seasons in 66 retired adults in Beijing (BJ) and Nanjing (NJ), China. The potential predictors were extracted from routine monitoring data (ambient PM2.5 concentrations and meteorological factors), basic questionnaires (personal and household characteristics), and time-activity diary (TAD). Prediction models were developed based on either traditional multiple linear regression (MLR) or five advanced machine learning methods. Our results revealed that personal PM2.5 exposures were well predicted by both MLR and machine learning models with predictors extracted from routine monitoring data, which was indicated by the high nested cross-validation (CV) R 2 ranging from 0.76 to 0.88. The addition of predictors from either the questionnaire or TAD did not improve predictive accuracy for all algorithms. The ambient PM2.5 concentrations were the most important predictor. Overall, the random forest, support vector machine, and extreme gradient boosting algorithms outperformed the reference MLR method. Compared with the traditional MLR approach, the CV R 2 of the RF model increased up to 7% (from 0.82 ± 0.13 to 0.88 ± 0.10), while the RMSE reduced up to 18% (from 19.8 ± 5.4 to 16.3 ± 4.5) in BJ. [ABSTRACT FROM AUTHOR]

As a kind of thermal control device, fluid loop systems must operate with the demands of high safety, high reliability, and long life. In order to accurately assess the health status of fluid loop systems, a hierarchical multi-information fusion (HMIF) method is proposed in this paper. Considering that fluid loop systems generally have distinct structural hierarchies, the health evaluation process in this method is divided into three levels, which are the indicator level, the component level, and the system level. In the evaluation process, the health indices are, respectively, constructed to quantify the health status at the three levels. At the indicator level, One-Class support vector machine algorithm is used to obtain the distribution space of each state monitoring indicator under a normal state. The indicator-level health indices are evaluated by calculating the ratio of the data located in the distribution space to the overall data. At the component level, a fuzzy theory is used to calculate the health indices of the component level. Health indices at the indicator level are first converted to membership degree by membership degree function. Then, the evaluation fusion strategy is used to deduce the membership degree of the component level. The health indices at the component level are obtained from the mapping relationship between the membership degree and the health index. At the system level, an adaptive weight adjustment strategy is proposed to fuze all component-level health indices. Taking a practical fluid loop system as an example, health indices at the three levels evaluated by the HMIF method are compared with the actual status. The results indicate that the proposed method can correctly judge the health state of the system and provide a reference for the maintenance and fault diagnosis of fluid loop systems. [ABSTRACT FROM AUTHOR]

This paper proposes a diagnosis method based on time series and support vector machine (SVM) to improve the timeliness, accuracy, and feasibility of fault diagnosis for photovoltaic (PV) arrays. It obtains the nominal output power of the PV array based on real-time collected data such as voltage, current, radiation, and temperature and normalizes the power values at different time points throughout the day to form a time series. Using the time series values as input data for a "one-to-one" multiclass classifier, we can identify and classify typical operational faults such as random shading, fixed shading, and aging degradation of PV arrays. The developed algorithmic model is trained and tested for different fault conditions using the data sets generated by the PV array simulation device. The experimental results show that our model has fairly good reliability and accuracy, and to some extent, it solves the problem of classifying shading and aging faults, two of which exhibit rather similar degradation characteristics. [ABSTRACT FROM AUTHOR]

The air-conditioning systems have become an indispensable part of our daily life for keeping the quality of life. However, to improve the thermal comfort and reduce energy consumption is crucial to use the air conditioners effectively with rapid development of artificial intelligence technology. This study explored the correlation between the response of human physiological parameters and thermal sensation voting (TSV) to evaluate the comfort level among various cold and hot stimulations. The variations of the three physiological parameters, which were body surface temperature, skin blood flow (SBF), and sweat area on the skin surface, and TSV values were all positively correlated with the stimulation amount under the stimulation of cold wind, hot wind, and heat radiation, but the relationship was not completely linear. Among the three physiological parameters, the forehead skin temperature has the closest relationship with TSV, followed by the SBF and sweat. Among three stimulations, the cold wind stimulation causes the closest relationship between TSV and forehead temperature, followed by the radiation and hot wind stimulations. Through three different machine learning models, namely, random forest (RF) model, support vector machine (SVM) model, and neural network (NN) model, the stimulation of cold wind, hot wind, and heat radiation was applied to investigate the variation of the three physiological parameters as the input of the models. Moreover, the models were evaluated and verified by TSV. The results revealed that among the three different machine learning methods, RF had the best accuracy. The established thermal comfort models can predict the real-time user's thermal comfort feeling, so that air-conditioning equipment's performance can be optimized to create a healthy and energy-saving comfortable environment. [ABSTRACT FROM AUTHOR]

The objective of this study was to determine whether multi-microRNA analysis using a combination of four microRNA biomarkers (miR-1246, 202, 21, and 219B) could improve the diagnostic performance of mammography in determining breast cancer risk by age group (under 50 vs. over 50) and distinguish breast cancer from benign breast diseases and other cancers (thyroid, colon, stomach, lung, liver, and cervix cancers). To verify breast cancer classification performance of the four miRNA biomarkers and whether the model providing breast cancer risk score could distinguish between benign breast disease and other cancers, the model was verified using nonlinear support vector machine (SVM) and generalized linear model (GLM) and age and four miRNA qRT-PCR analysis values (dCt) were input to these models. Breast cancer risk scores for each Breast Imaging-Reporting and Data System (BI-RADS) category in multi-microRNA analysis were analyzed to examine the correlation between breast cancer risk scores and mammography categories. We generated two models using two classification algorithms, SVM and GLM, with a combination of four miRNA biomarkers showing high performance and sensitivities of 84.5% and 82.1%, a specificity of 85%, and areas under the curve (AUCs) of 0.967 and 0.965, respectively, which showed consistent performance across all stages of breast cancer and patient ages. The results of this study showed that this multi-microRNA analysis using the four miRNA biomarkers was effective in classifying breast cancer in patients under the age of 50, which is challenging to accurately diagnose. In addition, breast cancer and benign breast diseases can be classified, showing the possibility of helping with diagnosis by mammography. Verification of the performance of the four miRNA biomarkers confirmed that multi-microRNA analysis could be used as a new breast cancer screening aid to improve the accuracy of mammography. However, many factors must be considered for clinical use. Further validation with an appropriate screening population in large clinical trials is required. This trial is registered with (KNUCH 2022-04-036). [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The cyber-physical power system (CPPS) is a modern infrastructure utilising information and communication technology that has become more vulnerable to cyberattacks in recent years. The attack magnitude injected by the adversary is stealthier and it cannot be detected using conventional bad data detection techniques. Protecting sensitive data from data integrity attacks (DIA) is essential for ensuring system security and reliability. A tragic event will occur if the attack goes unreported. Therefore, DIA detection is highly vital for the operator in the control centre to make important decisions. This paper addresses the attack impact on WAC applications and attack detection using the model-based method and data-driven-based methods. On the basis of the validation of performance indicators, various detection approaches are simulated and compared to determine the best detection strategy. Simulation results show that in the model-based anomaly detection method, the recursive polynomial model estimator (RPME) has better detection performance than the recursive least square estimator (RLSE). The convolutional neural network- (CNN-) based data-driven anomaly detection technique outperforms other machine learning (ML) techniques such as support vector machine (SVM), K-nearest neighbour (KNN), and random forest (RF). On the WSCC 3 machine 9-bus system, the efficacy of the suggested methods is evaluated. [ABSTRACT FROM AUTHOR]

Bearings are critical components in modern manufacturing, yet they are prone to failures in induction machines. Detecting these faults early can reduce repair costs. To achieve efficient and accurate fault detection, we explore vibration-based analysis. Traditional methods rely on manual feature extraction, which is time-consuming. In contrast, our work leverages deep learning, particularly convolutional neural networks, to automatically extract fault features from raw data. We investigate various image sizes (16 × 16, 32 × 32, 64 × 64, 128 × 128, 256 × 256) and their performance in bearing fault diagnosis. Our convolutional neural networks-based approach is compared to traditional methods such as support vector machine, nearest neighbors, and artificial neural networks. Results demonstrate the superior performance of our data-driven fault diagnosis using convolutional neural networks. [ABSTRACT FROM AUTHOR]

Credit-risk prediction is one of the challenging tasks in the banking industry. In this study, a hybrid convolutional neural network—support vector machine/random forest/decision tree (CNN—SVM/RF/DT) model has been proposed for efficient credit-risk prediction. We proposed four classifiers to develop the model. A fully connected layer with soft-max trained using an end-to-end process makes up the first classifier and by deleting the final fully connected with soft-max layer, the other three classifiers—a SVM, RF, and DT classifier stacked after the flattening layer. Different parameter values were considered and fine-tuned throughout testing to select appropriate parameters. In accordance with the experimental findings, a fully connected CNN and a hybrid CNN with SVM, DT, and RF, respectively, achieved a prediction performance of 86.70%, 98.60%, 96.90%, and 95.50%. According to the results, our suggested hybrid method exceeds the fully connected CNN in its ability to predict credit risk. [ABSTRACT FROM AUTHOR]

The process of identifying a person using their facial traits is referred to as face recognition, and it is a form of biometric identification. The use of facial recognition might range from that of an entertainment tool to one of a security tool. Even while other forms of biometric identification, such as fingerprints and iris scans, are reliable, they require the active participation of an individual. As a result, criminals cannot rely on them as the most reliable means of verification. When a criminal database, which stores the individual details of a criminal, and facial recognition technology are brought together, it can identify a criminal who is depicted in an image or seen in a video feed. Not only does a criminal recognition system needs to have a high level of accuracy, but it also needs to be able to adapt to significant changes in lighting, occlusion, aging, expressions, and other factors. In this study, they were analyzed and compared with the many methods of face detection and face recognition, such as HAAR cascades, local binary patterns histogram, support vector machines, convolutional neural networks, and ResNet-34. These methods include a variety of different approaches to recognizing faces. An analysis of these strategies is also conducted and then put into practice to those that seem to be the most effective for the designed criminal recognition system. In addition to that, a variety of uses of this criminal recognition in the real world are also discussed. [ABSTRACT FROM AUTHOR]

Around the world, road traffic accidents are the leading cause of serious injuries and deaths. Ethiopia is one of the countries that suffer the most from traffic accidents. Every government in every country wants to keep its citizens safe from accidents. To keep people safe from accidents, it is necessary to conduct a detailed analysis of the factors that contribute to high-severity accidents and deaths. As a result, we developed a data mining algorithm-based road traffic accident severity analysis for the Addis Ababa subcity in this study. The longest frequent factors in the dataset were generated using the Apriori algorithm. The Apriori algorithm generates the most frequent factors as sex: male, driver–vehicle relationship: employee, weather condition: normal, pedestrian movement: not a pedestrian, road surface type: asphalt, and accident severity: high severity, with 42.21% and 84.35% support and confidence, respectively. In addition, we created an accident severity level predictive model using a support vector machine. The predictive model has an accuracy of 85%. The proposed predictive model outperforms other well-known predictive models, such as K-nearest neighbors, decision trees, and random forests. As a result, when making decisions or policies in Ethiopia, the government or private organizations should consider the association of factors that lead to serious severe accidents. [ABSTRACT FROM AUTHOR]

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is one of the significant common neurological disorders of the current age that causes uncontrollable movements like shaking, stiffness, and difficulty. The early clinical diagnosis of this disease is essential for preventing the progression of PD. Hence, an innovative method is proposed here based on combining the crow search algorithm and decision tree (CSADT) for the early PD diagnosis. This approach is used on four crucial Parkinson's datasets, including meander, spiral, voice, and speech-Sakar. Using the presented method, PD is effectively diagnosed by evaluating each dataset's critical features and extracting the primary practical outcomes. The used algorithm was compared with other machine learning algorithms of k-nearest neighbor (KNN), support vector machine (SVM), naive Baye (NB), multilayer perceptron (MLP), decision tree (DT), random tree, logistic regression, support vector machine of radial base functions (SVM of RBFs), and combined classifier in terms of accuracy, recall, and combination measure F1. The analytical results emphasize the used algorithm's superiority over the other selected ones. The proposed model yields nearly 100% accuracy through various trials on the datasets. Notably, a high detection speed achieved the lowest detection time of 2.6 seconds. The main novelty of this paper is attributed to the accuracy of the presented PD diagnosis method, which is much higher than its counterparts. [ABSTRACT FROM AUTHOR]

Credit card fraud is a common occurrence in today's society because the majority of us use credit cards as a form of payment more frequently. This is the outcome of developments in technology and an increase in online transactions, which have given rise to frauds that have caused significant financial losses. In order to detect fraud in credit card transactions, efficient and effective approaches are needed. In this study, we developed a hybrid CNN-SVM model for detecting fraud in credit card transactions. The effectiveness of our suggested hybrid CNN-SVM model for detecting fraud in credit card transactions was tested using real-world public credit card transaction data. The architecture of our hybrid CNN-SVM model was developed by replacing the final output layer of the CNN model with an SVM classifier. The first classifier is a fully connected layer with softmax that is trained using an end-to-end approach, whereas the second classifier is a support vector machine that is piled on top by deleting the final fully connected and softmax layer. According to experimental results, our hybrid CNN-SVM model produced classification performances with accuracy, precision, recall, F1-score, and AUC of 91.08%, 90.50%, 90.34%, 90.41, and 91.05%, respectively. [ABSTRACT FROM AUTHOR]

This work pursues two primary aims: identifying the precursory point by the CSD analysis of AE series and using acoustic emission parameters to predict the compressive strength of concrete utilizing the artificial neural network (ANN), extreme learning machine (ELM), and support vector machine (SVM). The concrete specimens with a water-cement ratio of 0.45 and 0.55 were tested for compressive strength, and the failure process of concrete was monitored by acoustic emission. The results demonstrate that the advantage of variance was being intuitive, robust, and less affected by the window. The fluctuation and abrupt increase of the variance can be regarded as the critical point and the formation of the main failure surface, which provided warning information for preventing catastrophic failures. The precursory point determined by the variance was 80%–90% of the ultimate strength, consistent with the improved b value (Ib). Then, an approach to predict the compressive strength of concrete was proposed to predict the compressive strength of concrete utilizing the ANN, ELM, and SVM. The results of the ELM were more outstanding than those of the ANN and SVM. The results suggest that it was possible to predict the compressive strength of concrete with a small number of samples using the AE parameters. [ABSTRACT FROM AUTHOR]

Humans are familiar with "diabetes," a chronic metabolic disease that causes resistance to insulin in the human body, and about 425 million cases worldwide. Diabetes is a hazard to human health since it can gradually cause significant damage to the heart, blood vessels, eyes, kidneys, and nerves. As a result, it is critical to recognize diabetes early on to minimize its negative consequences. Over the years, artificial intelligence (AI) technology and data mining methods are playing a crucial role in detecting diabetic patients. Considering this opportunity, we present a fine-tuned random forest algorithm with the best parameters (RFWBP) that is used with the RF algorithm and feature engineering to detect diabetes patients at an early stage. We have employed several data processing techniques (e.g., normalization, conversion into numerical data) to raw data during the prepossessing phase. After that, we further applied some data mining techniques, adding related characteristics to the primary dataset. Finally, we train the proposed RFWBP and conventional methods like the AdaBoost algorithm, support vector machine, logistic regression, naive Bayes, multilayer perceptron, and a regular random forest with the dataset. Furthermore, we also utilized 5-fold cross-validation to enhance the performance of the RFWBP classifier. The proposed RFWBP achieved an accuracy of 95.83% and 90.68% with and without 5-fold cross-validation, respectively. Moreover, the proposed RFWBP is compared with conventional machine learning methods to evaluate the performance. The experimental results confirm that the proposed RFWBP outperformed conventional machine learning methods. [ABSTRACT FROM AUTHOR]

Almost 17.9 million people are losing their lives due to cardiovascular disease, which is 32% of total death throughout the world. It is a global concern nowadays. However, it is a matter of joy that the mortality rate due to heart disease can be reduced by early treatment, for which early-stage detection is a crucial issue. This study is aimed at building a potential machine learning model to predict heart disease in early stage employing several feature selection techniques to identify significant features. Three different approaches were applied for feature selection such as chi-square, ANOVA, and mutual information, and the selected feature subsets were denoted as SF1, SF2, and SF3, respectively. Then, six different machine learning models such as logistic regression (C1), support vector machine (C2), K-nearest neighbor (C3), random forest (C4), Naive Bayes (C5), and decision tree (C6) were applied to find the most optimistic model along with the best-fit feature subset. Finally, we found that random forest provided the most optimistic performance for SF3 feature subsets with 94.51% accuracy, 94.87% sensitivity, 94.23% specificity, 94.95 area under ROC curve (AURC), and 0.31 log loss. The performance of the applied model along with selected features indicates that the proposed model is highly potential for clinical use to predict heart disease in the early stages with low cost and less time. [ABSTRACT FROM AUTHOR]

Facial emotion expressions are among the most potent, natural, and powerful means of human communication. Due to the COVID-19 pandemic, educational institutions worldwide are forced to switch rapidly to remote and online learning. Students are currently in an emergency state and must adapt to various and readily accessible learning methods, such as mobile learning applications or an e-learning system. A systematic literature review (SLR) is conducted to extract and synthesize information such as the emotion classifier used in the facial expression recognition (FER) system, the dataset used, the preprocessing technique applied, the feature extraction approach used, and the strength and limitation of the previous studies. Based on the search criteria, 701 publications were initially retrieved from five different digital databases, of which 48 studies have been chosen as primary studies for further analysis. Based on the findings of this study, the deep learning approach is the most frequently adopted approach in classifying student emotions during online learning. FER-2013 is the most commonly used FER dataset in FER studies, while DAiSEE is the most used academic emotion dataset. Moreover, support vector machine (SVM) is the conventional learning emotion classifier that is widely used in the FER systems, while convolutional neural network (CNN) is the most frequently used deep learning classifier. Next, it was found that the number of real-time FER systems is less than that of non-real-time FER systems. Finally, the top-1 accuracy of 94.6% was achieved by the long-term recurrent convolutional network on the academic emotion dataset, and the limitation is that it has low illumination and a lack of frontal pose. [ABSTRACT FROM AUTHOR]

Based on the brain signals, decoding and analyzing the gait features to make a reliable prediction of action intention are the core issues in the brain computer interface (BCI)-based hybrid rehabilitation and intelligent walking aid robot system. In order to realize the classification and recognition of the most basic gait processes such as standing, sitting, and quiet, this paper proposes a feature representation method based on the signal complexity and entropy of each brain region. Through the statistical analysis of these parameters between different conditions, these characteristics which sensitive to different actions are determined as a feature vector, and the classification and recognition of these actions are completed by combing support vector machine, linear discriminant analysis, and logistic regression. Experimental results show the proposed method can better realize the recognition of the aforementioned action intention. The recognition accuracy of standing, sitting, and quiet of 13 subjects is higher than 80.9%, and the highest one can reach 86.8%. Directed dynamic brain network analysis of the 8 brain regions shows that the occurrence of lower limb movement will weaken the dependence between brain regions, resulting in the weakening of network topological connection. The result has significant value for understanding human's brain cognitive characteristics in the process of lower limb movement and carrying out the study of BCI based strategy and system for lower limb rehabilitation. [ABSTRACT FROM AUTHOR]

In the process of multiscale network traffic prediction using a single model, the results are often single, resulting in a decline in the accuracy of multiscale network traffic prediction. In order to solve this problem effectively, a mathematical modeling method of multiscale network traffic combination prediction based on fuzzy SVM is proposed. Firstly, according to the multiscale network approximation signal, the multiscale network traffic feature function is constructed to complete the multiscale network traffic feature extraction. Secondly, according to the feature extraction results, the fuzzy membership function is introduced into the SVM, and the fuzzy SVM is used to classify the multiscale network traffic. Finally, based on the traffic classification results, the combination prediction of multiscale network traffic is completed by combining the grey Verhulst prediction model with the GNN model. The experimental results show that the prediction accuracy of this method for multiscale network traffic is higher, and the prediction accuracy can always maintain above 95%, and the MSE and MAE values are relatively low. [ABSTRACT FROM AUTHOR]

This article investigates an issue of road safety and a method for detecting drowsiness in images. More fatal accidents may be averted if fatigued drivers are using this technology accurately and the proposed models provide quick response by recognising the driver's state of falling asleep. There are the following drowsiness models for depicting the possible eye state classifications as VGG16, VGG19, RESNET50, RESNET101 and MobileNetV2. The absence of a readily available and trustworthy eye dataset is perceived acutely in the realm of eye closure detection. On extracting the deep features of faces with VGG16, 98.68% accuracy has been achieved, VGG19 provides an accuracy of 98.74%, ResNet50 works with 65.69% accuracy, ResNet101 has achieved 95.77%, and MobileNetV2 is achieving 96.00% accuracy with the proposed dataset. The put forth model using the support vector machine (SVM) has been used to evaluate several models, and the present results in terms of loss function and accuracy have been obtained. In the proposed dataset, 99.85% accuracy in detecting facial expressions has been achieved. These experimental results show that the eye closure estimation has a higher accuracy and cheap processing cost, as well as the ability of the proposed framework for drowsiness. [ABSTRACT FROM AUTHOR]

Effective accident detection and traffic flow forecasting are of great importance for quick respond, impact elimination and intelligent control of the traffic flow consisting of autonomous vehicles. This paper proposes a traffic accident detection method for connected and automated transport systems by conducting a grid-based parameter extracting and SVC-based traffic state classification. Allowing for the dynamic spread of traffic flow over time, from upstream to downstream and from accident lanes to other lanes, a spatiotemporal Markov model is established to predict the evolution of traffic flow after accident by introducing the grid as state detection unit and fitting the spatiotemporal evolution with the parameter space mean speed to match the need of both detection accuracy and monitoring scope. Compared with actual accident data, the validation results indicate that the proposed methods present a good performance in accident detection with the accident detection rate as 87.72% and a higher precision rate than both SVM (support vector machine) and ANN (artificial neural network) models in traffic flow prediction. With the active traffic accident identification and dynamic traffic flow prediction, it is beneficial to shorten detection time, reduce possible impacts of traffic accidents and carbon emissions from congestion. The methods can be implied to traffic state recognition and traffic flow prediction, which is one of the significant sections of connected and automated transport systems, and serve as references for accident handling and urban traffic management. [ABSTRACT FROM AUTHOR]

Background. Nasopharyngeal carcinoma (NPC) is one of the most prevalent cancers with a poor prognosis. Immunotherapy, especially immune checkpoint blockade (ICB), is becoming a potential therapeutic choice for NPC patients. Thus, the identification of patients who could benefit from immunotherapy is clinically significant. Methods. The NPC expression profiles from GSE102349 were used to calculate the cell scores of the tumor microenvironment (TME). The consensus clustering method was utilized to identify the potential molecular subtypes among NPC samples. The hub genes were selected from subtype-specific genes by bioinformatics analysis. Machine learning models, including random forest (RF) and support vector machine (SVM) algorithms, were constructed to predict the immune subtype. Results. In the present study, we identified two TME subtypes among NPC patients. Patients with the S1 subtype have higher levels of immune cells, immune checkpoint genes, and prognosis. Using expression data profiles of NPC patients, we constructed machine learning models for predicting TME subtypes of NPC patients. This model consists of 8 genes (LCK, CD247, FYN, ZAP70, SH2D1A, CD3D, CD3E, and CD3G). Among them, LCK, FYN, SH2D1A, and CD3D were associated with better prognoses. Among the two constructed models, SVM exhibited a higher area under curve (AUC) of 0.977, when compared with RF (AUC = 0.966). The web server based on the constructed machine learning models will contribute to the identification of NPC patients likely to benefit from ICB therapies. Conclusions. This study identified NPC subtypes and provided an accurate model to select individuals who are most likely to respond to ICB. [ABSTRACT FROM AUTHOR]

Accurate and reliable traffic state identification is the prerequisite for developing intelligent traffic programs. With the improvement of intelligent traffic control measures, the traffic state of some highways has gradually stabilized. The current research on traffic state identification needs to fully meet the highly informative intelligent traffic system and traffic state subcategory analysis. To fill the gap above, we propose an improved support tensor machine (STM) method based on self-training and multiclassification for traffic state subcategory identification (ISTM) with ETC gantry data. This paper takes the excellent application of the support vector machine (SVM) in traffic state identification as the starting point of method design and extends to the STM. The ETC gantry data are represented as a third-order tensor model. This paper utilizes the similarity among tensor samples to construct the kernel function and recognize the traffic states. We simplify STM calculation with a one-against-one model and a self-training idea. An optimal fit of the characteristics is supplied by maximizing inter-subcategory tensor block distances and minimizing intra-subcategory tensor block distances throughout a joint utilization of the STM and multiscale training theories. The experiment in this paper uses ETC gantry data from the Jingtai highway in Shandong Province, and the findings reveal that the ISTM has optimum values of 0.2578 and 0.3254 for the SumD and 0.1718 and 0.1901 for the DBI as compared to K-mean clustering and the SVM. The ISTM trains the traffic state subcategory classifiers with high accuracy and strong generalization ability. [ABSTRACT FROM AUTHOR]

In order to estimate the power system accurately and identify anomaly detection in real time, an identification method of anomaly detection in power system state estimation based on Fuzzy C-means algorithm is proposed. Considering the problems of scale and redundancy of power system measurement data, effective measurement data of the power system is extracted by the principal component analysis method. On this basis, the power system state estimation model established by particle swarm optimization support vector machines is used to judge the operational state of the power system. An anomaly detection identification method based on fuzzy C-means algorithm is proposed to cluster the measured data and identify the anomaly detection of power system. The experimental results show that this method can accurately estimate the state of the power system and has the highest identification accuracy for anomaly detection compared with similar methods. When the equivalent measurement data is affected by noise, the identification delay of this method for anomaly detection in a power system is 1 s, and the real-time performance is high. [ABSTRACT FROM AUTHOR]

ROP is an important index to evaluate the efficiency of oil and gas drilling. In order to accurately predict the ROP of an oilfield in Xinjiang working area, a ROP prediction model based on the historical drilling data of this working area was established based on stacking ensemble learning. This model integrates the K -nearest neighbor algorithm and support vector machine algorithm by stacking ensemble strategy and uses genetic algorithm to optimize model parameters, forming a new method of ROP prediction suitable for this oilfield. The prediction results show that the accuracy of ROP prediction by this method is up to 92.5%, and the performance is stable, which can provide reference for the optimization of drilling parameters in this oilfield and has specific guiding significance for improving the efficiency of drilling operations. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate the feasibility of applying a clinical multimodal radiomics nomogram based on ultrasonography (US) and multiparametric magnetic resonance imaging (MRI) for the prediction of cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) preoperatively. We performed retrospective evaluations of 133 patients with pathologically confirmed PTC, who were assigned to the training cohort and validation cohort (7 : 3), and extracted radiomics features from the preoperative US, T2-weighted (T2WI),diffusion-weighted (DWI), and contrast-enhanced T1-weighted (CE-T1WI) images. Optimal subsets were selected using minimum redundancy, maximum relevance, and recursive feature elimination in the support vector machine (SVM). For LNM prediction, the radiomics model was constructed by SVM, and Multi-Omics Graph cOnvolutional NETworks (MOGONET) was used for the effective classification of multiradiomics data. Multivariable logistic regression incorporating multiradiomics signatures and clinical risk factors was used to generate a nomogram, whose performance and clinical utility were assessed. Results showed that the nine most predictive features were separately selected from US, T2WI, DWI, and CE-T1WI images, and 18 features were selected in the combined model. The combined radiomics model showed better performance than models based on US, T2WI, DWI, and CE-T1WI. In a comparison of the combined radiomics and MOGONET model, receiver operating curve analysis showed that the area under the curve (AUC) value (95% CI) was 0.84 (0.76–0.93) and 0.84 (0.71–0.96) for the MOGONET model in the training and validation cohorts, respectively. The corresponding values (95% CI) for the combined radiomics model were 0.82 (0.74–0.90) and 0.77 (0.61–0.94), respectively. The MOGONET model had better performance and better prediction specificity compared with the combined radiomics model. The nomogram including the MOGONET signature showed a better predictive value (AUC: 0.81 vs. 0.88) in the training and validation (AUC: 0.74vs. 0.87) cohorts, as compared with the clinical model. Calibration curves showed good agreement in both cohorts. The applicability of the clinical multimodal radiomics (CMR) nomogram in clinical settings was validated by decision curve analysis. In patients with PTC, the CMR nomogram could improve the prediction of cervical LNM preoperatively and may be helpful in clinical decision-making. [ABSTRACT FROM AUTHOR]

Accurate load forecasting (LF) plays an important role in the operation and decision-making process of the power grid. Although the stochastic and nonlinear behavior of loads is highly dependent on consumer energy requirements, that demands a high level of accuracy in LF. In spite of several research studies being performed in this field, accurate load forecasting remains an important consideration. In this article, the design of a hybrid short-term load forecasting model (STLF) is proposed. This work combines the features of an artificial neural network (ANN), ensemble forecasting, and a deep learning network. RBFNNs and CNNs are trained in two phases using the functional link artificial neural network (FLANN) optimization method with a deep learning structure. The predictions made from RBFNNs have been computed and produced as the forecast of each activated cluster. This framework is known as fuzzy-RBFNN. This proposed framework is outlined to anticipate one-week ahead load demand on an hourly basis, and its accuracy is determined using two case studies, i.e., Hellenic and Cretan power systems. Its results are validated while comparing with four benchmark models like multiple linear regression (MLR), support vector machine (SVM), ML-SVM, and fuzzy-RBFNN in terms of accuracy. To demonstrate the performance of RBF-CNN, SVMs replace the RBF-CNN regressor, and this model is identified as an ML-SVM having 3 layers. [ABSTRACT FROM AUTHOR]

Atrial flutter (AFL) is a common arrhythmia with two significant mechanisms, namely, focal (FAFL) and macroreentry (MAFL). Discrimination of the AFL mechanism through noninvasive techniques can improve radiofrequency ablation efficacy. This study aims to differentiate the AFL mechanism using a 12-lead surface electrocardiogram. P-P interval series variability is hypothesized to be different in FAFL and MAFL and may be useful for discrimination. 12-lead ECG signals were collected from 46 patients with known AFL mechanisms. Features for a proposed classifier are extracted through descriptive statistics of the interval series. On the other hand, the class ratio of MAFL and FAFL was 41 : 5, respectively, which was highly imbalanced. To resolve this, different data augmentation techniques (SMOTE, modified-SMOTE, and smoothed-bootstrap) have been applied on the interval series to generate synthetic interval series and minimize imbalance. Modification is introduced in the classic SMOTE technique (modified-SMOTE) to properly produce data samples from the original distribution. The characteristics of modified-SMOTE are found closer to the original dataset than the other two techniques based on the four validation criteria. The performance of the proposed model has been evaluated by three linear classifiers, namely, linear discriminant analysis (LDA), logistic regression (LOG), and support vector machine (SVM). Filter and wrapper methods have been used for selecting relevant features. The best average performance was achieved at 400% augmentation of the FAFL interval series (90.24% sensitivity, 49.50% specificity, and 76.88% accuracy) in the LOG classifier. The variation of consecutive P-wave intervals has been shown as an effective concept that differentiates FAFL from MAFL through the 12-lead surface ECG. [ABSTRACT FROM AUTHOR]

Social media platforms play a key role in fostering the outreach of extremism by influencing the views, opinions, and perceptions of people. These platforms are increasingly exploited by extremist elements for spreading propaganda, radicalizing, and recruiting youth. Hence, research on extremism detection on social media platforms is essential to curb its influence and ill effects. A study of existing literature on extremism detection reveals that it is restricted to a specific ideology, binary classification with limited insights on extremism text, and manual data validation methods to check data quality. In existing research studies, researchers have used datasets limited to a single ideology. As a result, they face serious issues such as class imbalance, limited insights with class labels, and a lack of automated data validation methods. A major contribution of this work is a balanced extremism text dataset, versatile with multiple ideologies verified by robust data validation methods for classifying extremism text into popular extremism types such as propaganda, radicalization, and recruitment. The presented extremism text dataset is a generalization of multiple ideologies such as the standard ISIS dataset, GAB White Supremacist dataset, and recent Twitter tweets on ISIS and white supremacist ideology. The dataset is analyzed to extract features for the three focused classes in extremism with TF-IDF unigram, bigrams, and trigrams features. Additionally, pretrained word2vec features are used for semantic analysis. The extracted features in the proposed dataset are evaluated using machine learning classification algorithms such as multinomial Naïve Bayes, support vector machine, random forest, and XGBoost algorithms. The best results were achieved by support vector machine using the TF-IDF unigram model confirming 0.67 F1 score. The proposed multi-ideology and multiclass dataset shows comparable performance to the existing datasets limited to single ideology and binary labels. [ABSTRACT FROM AUTHOR]

As one of the foods commonly eaten all over the world, eggs have attracted more and more attention for their quality and price. A method based on elemental profiles and chemometrics to discriminate between free-range and caged eggs was established. Free-range (n1 = 127) and caged (n2 = 122) eggs were collected from different producing areas in China. The content of 16 elements (Zn, Pb, Cd, Co, Ni, Fe, Mn, Cr, Mg, Cu, Se, Ca, Al, Sr, Na, and K) in the eggshell was determined using a inductively coupled plasma atomic emission spectrometer (ICP-AES). Outlier diagnosis is performed by robust Stahel–Donoho estimation (SDE) and the Kennard and Stone (K-S) algorithm for training and test set partitioning. Partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) were used for classification of the two types of eggs. As a result, Cd, Mn, Mg, Se, and K make an important contribution to the classification of free-range and caged eggs. By combining column-wise and row-wise rescaling of the elemental data, the sensitivity, specificity, and accuracy were 91.9%, 91.1%, and 92.7% for PLS-DA, while the results of LS-SVM were 95.3%, 95.6%, and 95.1%, respectively. The result indicates that chemometrics analysis of the elemental profiles of eggshells could provide a useful and effective method to discriminate between free-range and caged eggs. [ABSTRACT FROM AUTHOR]

The half-bridge converter series Y-connection microgrid (HCSY-MG) is a new type of series microgrid. In order to reduce the harmonic content in HCSY-MG grid-connected current and at the same time simplify the parameter design process of the LCL filter, this study proposed an LCL filter parameter design method based on an improved particle swarm optimization-least squares support vector machine (PSO-LSSVM) by analyzing the harmonic characteristics of the HCSY-MG grid-connected current. In addition, to enhance the convergence speed of PSO-LSSVM, the inertia factor during its parameters' update is made to adjust adaptively according to the direction of two consecutive parameter changes to constitute an improved PSO-LSSVM. Through simulation and comparative analysis, it is demonstrated that the improved PSO-LSSVM can enhance the convergence speed; the proposed filter parameter design method can effectively reduce the harmonic content in the HCSY-MG grid-connected current and is simpler and more comprehensive than the existing design method. [ABSTRACT FROM AUTHOR]

Chemotherapy is not recommended for patients with deficient mismatch repair (dMMR) in colorectal cancer (CRC); therefore, assessing the status of MMR is crucial for the selection of subsequent treatment. This study is aimed at building predictive models to accurately and rapidly identify dMMR. A retrospective analysis was performed at Wuhan Union Hospital between May 2017 and December 2019 based on the clinicopathological data of patients with CRC. The variables were subjected to collinearity, least absolute shrinkage and selection operator (LASSO) regression, and random forest (RF) feature screening analyses. Four sets of machine learning models (extreme gradient boosting (XGBoost), support vector machine (SVM), naive Bayes (NB), and RF) and a conventional logistic regression (LR) model were built for model training and testing. Receiver operating characteristic (ROC) curves were plotted to evaluate the predictive performance of the developed models. In total, 2279 patients were included in the study and were randomly divided into either the training or test group. Twelve clinicopathological features were incorporated into the development of the predictive models. The area under curve (AUC) values of the five predictive models were 0.8055 for XGBoost, 0.8174 for SVM, 0.7424 for NB, 8584 for RF, and 0.7835 for LR (Delong test, P value < 0.05). The results showed that the RF model exhibited the best recognition ability and outperformed the conventional LR method in identifying dMMR and proficient MMR (pMMR). Our predictive models based on routine clinicopathological data can significantly improve the diagnostic performance of dMMR and pMMR. The four machine learning models outperformed the conventional LR model. [ABSTRACT FROM AUTHOR]

Pipelines are crucial for transporting liquid and gaseous resources at various industrial sites. As unexpected pipeline failures and improper spill responses often cause detrimental effects on the environment and public safety, real-time leakage monitoring and detection are important. This study proposes a nonintrusive sensor system to measure the pressure and integrity of a pipeline in real time by easily installing nonintrusive sensors on the exterior of the pipelines. Initially, a prototype of the nonintrusive pressure-monitoring sensor was designed and fabricated. This sensor correlated the changes in pressure inside a pipe with those in the contact force exerted between the pipe and the surrounding high-stiffness band; a force-sensing resistor was used to measure the contact force. Furthermore, parametric studies were performed on a six-inch pipe, which indicated that the developed sensor can accurately monitor the inner pressure of the pipe. We also developed a methodology to determine the optimal sensor placement in a pipeline network for detecting damages using the Euclidean distance method. This was combined with the methodology of determining the decision boundary for classifying the damage location using a support vector machine to rapidly detect the damage using a minimum number of sensors. Finally, a nonintrusive sensor system was installed on the fire main pipeline system, and the damage detection performance was experimentally validated. The developed nonintrusive sensor system can be easily installed on operating pipes to monitor the inner pressure of a pipe in real-time and accurately detect damages in a pipeline network. [ABSTRACT FROM AUTHOR]

Antinuclear antibodies (ANAs) testing is the main serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted principally by the indirect immunofluorescence (IIF) on human epithelial cell-substrate (HEp-2) protocol. However, due to its high variability and human subjectivity, there is an insistent need to develop an efficient method for automatic image segmentation and classification. This article develops an automatic segmentation and classification framework based on artificial intelligence (AI) on the ANA images. The Otsu thresholding method and watershed segmentation algorithm are adopted to segment IIF images of cells. Moreover, multiple texture features such as scale-invariant feature transform (SIFT), local binary pattern (LBP), cooccurrence among adjacent LBPs (CoALBP), and rotation invariant cooccurrence among adjacent LBPs (RIC-LBP) are utilized. Firstly, this article adopts traditional machine learning methods such as support vector machine (SVM), k-nearest neighbor algorithm (KNN), and random forest (RF) and then uses ensemble classifier (ECLF) combined with soft voting rules to merge these machine learning methods for classification. The deep learning method InceptionResNetV2 is also utilized to train on the classification of cell images. Eventually, the best accuracy of 0.9269 on the Changsha dataset and 0.9635 on the ICPR 2016 dataset for the traditional methods is obtained by a combination of SIFT and RIC-LBP with the ECLF classifier, and the best accuracy obtained by the InceptionResNetV2 is 0.9465 and 0.9836 separately, which outperforms other schemes. [ABSTRACT FROM AUTHOR]

Background. Cancer-associated fibroblasts (CAFs) have reported widely involved in cancer progression. However, its underlying mechanism in gastric cancer is still not clarified. Methods. The data used in this study were all downloaded from the Cancer Genome Atlas database. R software and the R packages were used for all the analyses. Results. In our study, we first quantified the CAFs infiltration using the ssGSEA algorithm. The clinical correlation result showed that CAFs were associated with a worse prognosis and clinical features. Pathway enrichment also indicated several oncogenic pathways in GC patients with high CAFs infiltration, including epithelial-mesenchymal transition (EMT), myogenesis, allograft rejection, the inflammatory response, and IL2/STAT5 signaling. Furthermore, FNDC1 and RSPO3 were identified as the characteristic genes of CAFs through two machine learning algorithms, LASSO logistic regression and SVM-RFE. The following analysis showed that FNDC1 and RSPO3 were associated with more progressive clinical features and had a good prediction efficiency of the CAFs infiltration status in GC patients. Pathway enrichment and genomic instability were performed to explore the underlying mechanisms of FNDC1 and RSPO3. Immune infiltration analysis showed that CAFs were positively correlated with M2 macrophages. Moreover, we found that the GC patients with low CAFs infiltration were more sensitive to immunotherapy. Also, the CAFs, FNDC1, and RSPO3 could generate a certain effect on the sensitivity of doxorubicin, mitomycin, and paclitaxel. Conclusions. In summary, our study comprehensively investigated the role of CAFs in GC, which might be associated with immunotherapy sensitivity. Meanwhile, FNDC1 and RSPO3 were identified as the underlying targets of GC. [ABSTRACT FROM AUTHOR]

Motivation. Immunoglobulin proteins (IGP) (also called antibodies) are glycoproteins that act as B-cell receptors against external or internal antigens like viruses and bacteria. IGPs play a significant role in diverse cellular processes ranging from adhesion to cell recognition. IGP identifications via the in-silico approach are faster and more cost-effective than wet-lab technological methods. Methods. In this study, we developed an intelligent theoretical deep learning framework, "IGPred-HDnet" for the discrimination of IGPs and non-IGPs. Three types of promising descriptors are feature extraction based on graphical and statistical features (FEGS), amphiphilic pseudo-amino acid composition (Amp-PseAAC), and dipeptide composition (DPC) to extract the graphical, physicochemical, and sequential features. Next, the extracted attributes are evaluated through machine learning, i.e., decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), and hierarchical deep network (HDnet) classifiers. The proposed predictor IGPred-HDnet was trained and tested using a 10-fold cross-validation and independent test. Results and Conclusion. The success rates in terms of accuracy (ACC) and Matthew's correlation coefficient (MCC) of IGPred-HDnet on training and independent dataset (Dtrain Dtest) are ACC = 98.00%, 99.10%, and MCC = 0.958, and 0.980 points, respectively. The empirical outcomes demonstrate that the IGPred-HDnet model efficacy on both datasets using the novel FEGS feature and HDnet algorithm achieved superior predictions to other existing computational models. We hope this research will provide great insights into the large-scale identification of IGPs and pharmaceutical companies in new drug design. [ABSTRACT FROM AUTHOR]

Classification of imbalanced data is a challenging task that has captured considerable interest in numerous scientific fields by virtue of the great practical value of minority accuracy. Some methods for improving generalization performance have been developed to address this classification situation. Here, we propose a cost-sensitive ensemble learning method using a support vector machine as a base learner of AdaBoost for classifying imbalanced data. Considering that the existing methods are not well studied in terms of how to precisely control the classification accuracy of the minority class, we developed a novel way to rebalance the weights of AdaBoost, and the weights influence the base learner training. This weighting strategy increases the sample weight of the misclassified minority while decreasing the sample weight of the misclassified majority until their distributions are even in each round. Furthermore, we included P-mean as one of the assessment markers and discussed why it is necessary. Experiments were conducted to compare the proposed and comparison 10 models on 18 datasets in terms of six different metrics. Through comprehensive experimental findings, the statistical study is performed to verify the efficacy and usability of the proposed model. [ABSTRACT FROM AUTHOR]