Efficient kNN Classification With Different Numbers of Nearest Neighbors

Analyzing the impact of sustainable economic development from the policy text network: Based on the practice of China's bay area policy

In order to break through the surface analysis of the content structure of policy texts, an in-depth discussion of the linkage between regional policy makers and objectives is helpful to analyze the formation mechanism of policy effects. Through social network analysis and multi-index analysis, this study takes the QianwanNew Area of Ningbo and the Guangdong-Hong Kong-Macao Greater Bay Area as representatives to explore the policy framework for the sustainable development of manufacturing industry in the two bay areas respectively. Through the construction of government department cooperation network, policy keyword co-occurrence network, department keyword correlation network, and the analysis of network density, network centrality, structural holes, and cohesive subgroups, it is found that the impact results show great differences, which is related to the network structure of manufacturing policy text.

The Three-Lead EEG Sensor: Introducing an EEG-Assisted Depression Diagnosis System Based on Ant Lion Optimization

For depression diagnosis, traditional methods such as interviews and clinical scales have been widely leveraged in the past few decades, but they are subjective, time-consuming, and labor-consuming. With the development of affective computing and Artificial Intelligence (AI) technologies, Electroencephalogram (EEG)-based depression detection methods have emerged. However, previous research has virtually neglected practical application scenarios, as most studies have focused on analyzing and modeling EEG data. Furthermore, EEG data is typically obtained from specialized devices that are large, complex to operate, and poorly ubiquitous. To address these challenges, a wearable three-lead EEG sensor with flexible electrodes was developed to obtain prefrontal-lobe EEG data. Experimental measurements show that the EEG sensor achieves promising performance (background noise of no more than 0.91 μVpp, Signal-to-Noise Ratio (SNR) of 26--48 dB, and electrode-skin contact impedance of less than 1 K Ω). In addition, EEG data from 70 depressed patients and 108 healthy controls were collected using the EEG sensor, and the linear and nonlinear features were extracted. The features were then weighted and selected using the Ant Lion Optimization (ALO) algorithm to improve classification performance. The experimental results show that the k-NN classifier achieves a classification accuracy of 90.70%, specificity of 96.53%, and sensitivity of 81.79%, indicating the promising potential of the three-lead EEG sensor combined with the ALO algorithm and the k-NN classifier for EEG-assisted depression diagnosis.

Accurate prediction and key protein sequence feature identification of cyclins

Cyclin proteins are a group of proteins that activate the cell cycle by forming complexes with cyclin-dependent kinases. Identifying cyclins correctly can provide key clues to understanding the function of cyclins. However, due to the low similarity between cyclin protein sequences, the advancement of a machine learning-based approach to identify cycles is urgently needed. In this study, cyclin protein sequence features were extracted using the profile-based auto-cross covariance method. Then the features were ranked and selected with maximum relevance-maximum distance (MRMD) 1.0 and MRMD2.0. Finally, the prediction model was assessed through 10-fold cross-validation. The computational experiments showed that the best protein sequence features generated by MRMD1.0 could correctly predict 98.2% of cyclins using the random forest (RF) classifier, whereas seven-dimensional key protein sequence features identified with MRMD2.0 could correctly predict 96.1% of cyclins, which was superior to previous studies on the same dataset both in terms of dimensionality and performance comparisons. Therefore, our work provided a valuable tool for identifying cyclins. The model data can be downloaded from https://github.com/YUshunL/cyclin.

Low-Rankness Guided Group Sparse Representation for Image Restoration

As a spotlighted nonlocal image representation model, group sparse representation (GSR) has demonstrated a great potential in diverse image restoration tasks. Most of the existing GSR-based image restoration approaches exploit the nonlocal self-similarity (NSS) prior by clustering similar patches into groups and imposing sparsity to each group coefficient, which can effectively preserve image texture information. However, these methods have imposed only plain sparsity over each individual patch of the group, while neglecting other beneficial image properties, e.g., low-rankness (LR), leads to degraded image restoration results. In this article, we propose a novel low-rankness guided group sparse representation (LGSR) model for highly effective image restoration applications. The proposed LGSR jointly utilizes the sparsity and LR priors of each group of similar patches under a unified framework. The two priors serve as the complementary priors in LGSR for effectively preserving the texture and structure information of natural images. Moreover, we apply an alternating minimization algorithm with an adaptively adjusted parameter scheme to solve the proposed LGSR-based image restoration problem. Extensive experiments are conducted to demonstrate that the proposed LGSR achieves superior results compared with many popular or state-of-the-art algorithms in various image restoration tasks, including denoising, inpainting, and compressive sensing (CS).

A Pilot Study: Detrusor Overactivity Diagnosis Method Based on Deep Learning

OBJECTIVE

To develop two intelligent diagnosis models of detrusor overactivity (DO) based on deep learning to assist doctors no longer heavily rely on visual observation of urodynamic study (UDS) curves.

METHODS

UDS curves of 92 patients were collected during 2019. We constructed two DO event recognition models based on convolutional neural network (CNN) with 44 samples, and tested the model performance with the remaining 48 samples by comparing other four classical machine learning models. During the testing phase, we developed a threshold screening strategy to quickly filter out suspected DO event segments in each patient's UDS curve. If two or more DO event fragments are determined to be DO by the diagnostic model, the patient is diagnosed as having DO.

RESULTS

We extracted 146 DO event samples and 1863 non-DO event samples from the UDS curves of 44 patients to train CNN models. Through 10-fold cross-validation, the training accuracy and validation accuracy of our models achieved the highest accuracy. In the model testing phase, we used a threshold screening strategy to quickly screen out the suspected DO event samples in the UDS curve of another 48 patients, and then input them into the trained models. Finally, the diagnostic accuracy of patients without DO and patients with DO was 78.12% and 100%, respectively.

CONCLUSION

Under the available data, the accuracy of the DO diagnostic model based on CNN is satisfactory. With the increase of the amount of data, the deep learning model is likely to have better performance.

CLINICAL TRIAL REGISTRATION

This experiment was certified by the Chinese Clinical Trial Registry (ChiCTR2200063467).

SARS-CoV-2 Prediction Strategy Based on Classification Algorithms from a Full Blood Examination

A fast and efficient diagnosis of serious infectious diseases, such as the recent SARS-CoV-2, is necessary in order to curb both the spread of existing variants and the emergence of new ones. In this regard and recognizing the shortcomings of the reverse transcription-polymerase chain reaction (RT-PCR) and rapid diagnostic test (RDT), strategic planning in the public health system is required. In particular, helping researchers develop a more accurate diagnosis means to distinguish patients with symptoms with COVID-19 from other common infections is what is needed. The aim of this study was to train and optimize the support vector machine (SVM) and K-nearest neighbors (KNN) classifiers to rapidly identify SARS-CoV-2 (positive/negative) patients through a simple complete blood test without any prior knowledge of the patient's health state or symptoms. After applying both models to a sample of patients at Israelita Albert Einstein at São Paulo, Brazil (solely for two examined groups of patients' data: "regular ward" and "not admitted to the hospital"), it was found that both provided early and accurate detection, based only on a selected blood profile via the statistical test of dependence (ANOVA test). The best performance was achieved by the improved SVM technique on nonhospitalized patients, with precision, recall, accuracy, and AUC values reaching 94%, 96%, 95%, and 99%, respectively, which supports the potential of this innovative strategy to significantly improve initial screening.

A machine learning-based model for predicting distant metastasis in patients with rectal cancer

Background

Distant metastasis from rectal cancer usually results in poorer survival and quality of life, so early identification of patients at high risk of distant metastasis from rectal cancer is essential.

Method

The study used eight machine-learning algorithms to construct a machine-learning model for the risk of distant metastasis from rectal cancer. We developed the models using 23867 patients with rectal cancer from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2017. Meanwhile, 1178 rectal cancer patients from Chinese hospitals were selected to validate the model performance and extrapolation. We tuned the hyperparameters by random search and tenfold cross-validation to construct the machine-learning models. We evaluated the models using the area under the receiver operating characteristic curves (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis, calibration curves, and the precision and accuracy of the internal test set and external validation cohorts. In addition, Shapley's Additive explanations (SHAP) were used to interpret the machine-learning models. Finally, the best model was applied to develop a web calculator for predicting the risk of distant metastasis in rectal cancer.

Result

The study included 23,867 rectal cancer patients and 2,840 patients with distant metastasis. Multiple logistic regression analysis showed that age, differentiation grade, T-stage, N-stage, preoperative carcinoembryonic antigen (CEA), tumor deposits, perineural invasion, tumor size, radiation, and chemotherapy were-independent risk factors for distant metastasis in rectal cancer. The mean AUC value of the extreme gradient boosting (XGB) model in ten-fold cross-validation in the training set was 0.859. The XGB model performed best in the internal test set and external validation set. The XGB model in the internal test set had an AUC was 0.855, AUPRC was 0.510, accuracy was 0.900, and precision was 0.880. The metric AUC for the external validation set of the XGB model was 0.814, AUPRC was 0.609, accuracy was 0.800, and precision was 0.810. Finally, we constructed a web calculator using the XGB model for distant metastasis of rectal cancer.

Conclusion

The study developed and validated an XGB model based on clinicopathological information for predicting the risk of distant metastasis in patients with rectal cancer, which may help physicians make clinical decisions. rectal cancer, distant metastasis, web calculator, machine learning algorithm, external validation.

Identification of the susceptible genes and mechanism underlying the comorbid presence of coronary artery disease and rheumatoid arthritis: a network modularization analysis

OBJECTIVE

The comorbidities of coronary artery disease (CAD) and rheumatoid arthritis (RA) are mutual risk factors, which lead to higher mortality, but the biological mechanisms connecting the two remain unclear. Here, we aimed to identify the risk genes for the comorbid presence of these two complex diseases using a network modularization approach, to offer insights into clinical therapy and drug development for these diseases.

METHOD

The expression profile data of patients CAD with and without RA were obtained from the GEO database (GSE110008). Based on the differentially expressed genes (DEGs), weighted gene co-expression network analysis (WGCNA) was used to construct a gene network, detect co-expression modules, and explore their relation to clinical traits. The Zsummary index, gene significance (GS), and module membership (MM) were utilized to screen the important differentiated modules and hub genes. The GO and KEGG pathway enrichment analysis were applied to analyze potential mechanisms.

RESULT

Based on the 278 DEGs obtained, 41 modules were identified, of which 17 and 24 modules were positively and negatively correlated with the comorbid occurrence of CAD and RA (CAD&RA), respectively. Thirteen modules with Zsummary < 2 were found to be the underlying modules, which may be related to CAD&RA. With GS ≥ 0.5 and MM ≥ 0.8, 49 hub genes were identified, such as ADO, ABCA11P, POT1, ZNF141, GPATCH8, ATF6 and MIA3, etc. The area under the curve values of the representative seven hub genes under the three models (LR, KNN, SVM) were greater than 0.88. Enrichment analysis revealed that the biological functions of the targeted modules were mainly involved in cAMP-dependent protein kinase activity, demethylase activity, regulation of calcium ion import, positive regulation of tyrosine, phosphorylation of STAT protein, and tissue migration, etc. CONCLUSION: Thirteen characteristic modules and 49 susceptibility hub genes were identified, and their corresponding molecular functions may reflect the underlying mechanism of CAD&RA, hence providing insights into the development of clinical therapies against these diseases.

Method for Classifying Schizophrenia Patients Based on Machine Learning

Schizophrenia is a chronic and severe mental disorder that affects individuals in various ways, particularly in their ability to perceive, process, and respond to stimuli. This condition has a significant impact on a considerable number of individuals. Consequently, the study, analysis, and characterization of this pathology are of paramount importance. Electroencephalography (EEG) is frequently utilized in the diagnostic assessment of various brain disorders due to its non-intrusiveness, excellent resolution and ease of placement. However, the manual analysis of electroencephalogram (EEG) recordings can be a complex and time-consuming task for healthcare professionals. Therefore, the automated analysis of EEG recordings can help alleviate the burden on doctors and provide valuable insights to support clinical diagnosis. Many studies are working along these lines. In this research paper, the authors propose a machine learning (ML) method based on the eXtreme Gradient Boosting (XGB) algorithm for analyzing EEG signals. The study compares the performance of the proposed XGB-based approach with four other supervised ML systems. According to the results, the proposed XGB-based method demonstrates superior performance, with an AUC value of 0.94 and an accuracy value of 0.94, surpassing the other compared methods. The implemented system exhibits high accuracy and robustness in accurately classifying schizophrenia patients based on EEG recordings. This method holds the potential to be implemented as a valuable complementary tool for clinical use in hospitals, supporting clinicians in their clinical diagnosis of schizophrenia.

Application of different mathematical models based on artificial intelligence technique to predict the concentration distribution of solute through a polymeric membrane

Membrane-based purification of therapeutic agents has recently attracted global attention as a promising replacement for conventional techniques like distillation and pervaporation. Despite the conduction of different investigations, development of more research about the operational feasibility of using polymeric membranes to separate the detrimental impurities of molecular entities is of great importance. The focus of this paper is to develop a numerical strategy based on multiple machine learning methods to predict the concentration distribution of solute through a membrane-based separation process. Two inputs are being analyzed in this study, specifically r and z. Furthermore, the single target output is C, and the number of data points exceeds 8000. To analyze and model the data for this study, we used the Adaboost (Adaptive Boosting) model over three different base learners (K-Nearest Neighbors (KNN), Linear Regression (LR), and Gaussian Process Regression (GPR)). In the process of hyper-parameter optimization for models, the BA optimization algorithm applied on the adaptive boosted models. Finally, Boosted KNN, Boosted LR, and Boosted GPR have scores of 0.9853, 0.8751, and 0.9793 in terms of R² metric. Based on the recent fact and other analyses, boosted KNN model is introduced as the most appropriate model of this research. The error rates for this model are 2.073 × 10¹ and 1.06 × 10^-2 in terms of MAE and MAPE metrics.

Automatic COVID-19 prediction using explainable machine learning techniques

The coronavirus is considered this century's most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person's body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms.

Clinical Decision Support System for Diabetic Patients by Predicting Type 2 Diabetes Using Machine Learning Algorithms

Diabetes is one of the most serious chronic diseases that result in high blood sugar levels. Early prediction can significantly diminish the potential jeopardy and severity of diabetes. In this study, different machine learning (ML) algorithms were applied to predict whether an unknown sample had diabetes or not. However, the main significance of this research was to provide a clinical decision support system (CDSS) by predicting type 2 diabetes using different ML algorithms. For the research purpose, the publicly available Pima Indian Diabetes (PID) dataset was used. Data preprocessing, K-fold cross-validation, hyperparameter tuning, and various ML classifiers such as K-nearest neighbor (KNN), decision tree (DT), random forest (RF), Naïve Bayes (NB), support vector machine (SVM), and histogram-based gradient boosting (HBGB) were used. Several scaling methods were also used to improve the accuracy of the result. For further research, a rule-based approach was used to escalate the effectiveness of the system. After that, the accuracy of DT and HBGB was above 90%. Based on this result, the CDSS was implemented where users can give the required input parameters through a web-based user interface to get decision support with some analytical results for the individual patient. The CDSS, which was implemented, will be beneficial for physicians and patients to make decisions about diabetes diagnosis and offer real-time analysis-based suggestions to improve medical quality. For future work, if daily data of a diabetic patient can be put together, then a better clinical support system can be implemented for daily decision support for patients worldwide.

Computer-aided diagnosis systems: a comparative study of classical machine learning versus deep learning-based approaches

The diagnostic phase of the treatment process is essential for patient guidance and follow-up. The accuracy and effectiveness of this phase can determine the life or death of a patient. For the same symptoms, different doctors may come up with different diagnoses whose treatments may, instead of curing a patient, be fatal. Machine learning (ML) brings new solutions to healthcare professionals to save time and optimize the appropriate diagnosis. ML is a data analysis method that automates the creation of analytical models and promotes predictive data. There are several ML models and algorithms that rely on features extracted from, for example, a patient's medical images to indicate whether a tumor is benign or malignant. The models differ in the way they operate and the method used to extract the discriminative features of the tumor. In this article, we review different ML models for tumor classification and COVID-19 infection to evaluate the different works. The computer-aided diagnosis (CAD) systems, which we referred to as classical, are based on accurate feature identification, usually performed manually or with other ML techniques that are not involved in classification. The deep learning-based CAD systems automatically perform the identification and extraction of discriminative features. The results show that the two types of DAC have quite close performances but the use of one or the other type depends on the datasets. Indeed, manual feature extraction is necessary when the size of the dataset is small; otherwise, deep learning is used.

Prognostic Models Using Machine Learning Algorithms and Treatment Outcomes of Occult Breast Cancer Patients

BACKGROUND

Occult breast cancer (OBC) is an uncommon malignant tumor and the prognosis and treatment of OBC remain controversial. Currently, there exists no accurate prognostic clinical model for OBC, and the treatment outcomes of chemotherapy and surgery in its different molecular subtypes are still unknown.

METHODS

The SEER database provided the data used for this study's analysis (2010-2019). To identify the prognostic variables for patients with ODC, we conducted Cox regression analysis and constructed prognostic models using six machine learning algorithms to predict overall survival (OS) of OBC patients. A series of validation methods, including calibration curve and area under the curve (AUC value) of receiver operating characteristic curve (ROC) were employed to validate the accuracy and reliability of the logistic regression (LR) models. The effectiveness of clinical application of the predictive models was validated using decision curve analysis (DCA). We also investigated the role of chemotherapy and surgery in OBC patients with different molecular subtypes, with the help of K-M survival analysis as well as propensity score matching, and these results were further validated by subgroup Cox analysis.

RESULTS

The LR models performed best, with high precision and applicability, and they were proved to predict the OS of OBC patients in the most accurate manner (test set: 1-year AUC = 0.851, 3-year AUC = 0.790 and 5-year survival AUC = 0.824). Interestingly, we found that the N1 and N2 stage OBC patients had more favorable prognosis than N0 stage patients, but the N3 stage was similar to the N0 stage (OS: N0 vs. N1, HR = 0.6602, 95%CI 0.4568-0.9542, p < 0.05; N0 vs. N2, HR = 0.4716, 95%CI 0.2351-0.9464, p < 0.05; N0 vs. N3, HR = 0.96, 95%CI 0.6176-1.5844, p = 0.96). Patients aged >80 and distant metastases were also independent prognostic factors for OBC. In terms of treatment, our multivariate Cox regression analysis discovered that surgery and radiotherapy were both independent protective variables for OBC patients, but chemotherapy was not. We also found that chemotherapy significantly improved both OS and breast cancer-specific survival (BCSS) only in the HR-/HER2+ molecular subtype (OS: HR = 0.15, 95%CI 0.037-0.57, p < 0.01; BCSS: HR = 0.027, 95%CI 0.027-0.81, p < 0.05). However, surgery could help only the HR-/HER2+ and HR+/HER2- subtypes improve prognosis.

CONCLUSIONS

We analyzed the clinical features and prognostic factors of OBC patients; meanwhile, machine learning prognostic models with high precision and applicability were constructed to predict their overall survival. The treatment results in different molecular subtypes suggested that primary surgery might improve the survival of HR+/HER2- and HR-/HER2+ subtypes, however, only the HR-/HER2+ subtype could benefit from chemotherapy. The necessity of surgery and chemotherapy needs to be carefully considered for OBC patients with other subtypes.

Identification of geographical origins of Radix Paeoniae Alba using hyperspectral imaging with deep learning-based fusion approaches

The Radix Paeoniae Alba (Baishao) is a traditional Chinese medicine (TCM) with numerous clinical and nutritional benefits. Rapid and accurate identification of the geographical origins of Baishao is crucial for planters, traders and consumers. Hyperspectral imaging (HSI) was used in this study to acquire spectral images of Baishao samples from its two sides. Convolutional neural network (CNN) and attention mechanism was used to distinguish the origins of Baishao using spectra extracted from one side. The data-level and feature-level deep fusion models were proposed using information from both sides of the samples. CNN models outperformed the conventional machine learning methods in classifying Baishao origins. The generalized Gradient-weighted Class Activation Mapping (Grad-CAM++) was utilized to visualize and identify important wavelengths that significantly contribute to model performance. The overall results illustrated that HSI combined with deep learning strategies was effective in identifying the geographical origins of Baishao, having good prospects of real-world applications.

Detection and classification of cracks and potholes in road images using texture descriptors

Traffic safety is directly affected by poor road conditions. Automating the detection of road defects allows improvements in the maintenance process. The identification of defects such as cracks and potholes can be done using computer vision techniques and supervised learning. In this paper, we propose the detection of cracks and potholes in images of paved roads using machine learning techniques. The images are subdivided into blocks, where Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Gabor Filter’s texture descriptors are used to extract features of the images. For the classification task, the Support Vector Machines (SVM), k-Nearest Neighbors (kNN), and Multi-Layer Perceptron (MLP) models are compared. We performed two experiments on a dataset built with images of Brazilian highways. In the first experiment, we obtained a F-measure of 75.16% when classifying blocks of images that have cracks and potholes, and 79.56% when comparing roads with defects and without defects. In the second experiment, a F-measure of 87.06% was obtained for the equivalent task. Thus, it is possible to state that the use of the techniques presented is feasible for locating faults in highways.

Machine learning to predict major bleeding during anticoagulation for venous thromboembolism: possibilities and limitations

Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of MB during the first 3 months of anticoagulation. A total of 55 baseline variables were used as predictors. New data prospectively collected from the RIETE were used for further validation. The RIETE and VTE-BLEED scores were used for comparisons. External validation was performed with the COMMAND-VTE database. Learning was carried out with data from 49 587 patients, of whom 873 (1.8%) had MB. The best performing ML method was XGBoost. In the prospective validation cohort the sensitivity, specificity, positive predictive value and F1 score were: 33.2%, 93%, 10%, and 15.4% respectively. F1 value for the RIETE and VTE-BLEED scores were 8.6% and 6.4% respectively. In the external validation cohort the metrics were 10.3%, 87.6%, 3.5% and 5.2% respectively. In that cohort, the F1 value for the RIETE score was 17.3% and for the VTE-BLEED score 9.75%. The performance of the XGBoost algorithm was better than that from the RIETE and VTE-BLEED scores only in the prospective validation cohort, but not in the external validation cohort.

Non-parametric Nearest Neighbor Classification Based on Global Variance Difference

As technology improves, how to extract information from vast datasets is becoming more urgent. As is well known, k-nearest neighbor classifiers are simple to implement and conceptually simple to implement. It is not without its shortcomings, however, as follows: (1) there is still a sensitivity to the choice of k-values even when representative attributes are not considered in each class; (2) in some cases, the proximity between test samples and nearest neighbor samples cannot be reflected accurately due to proximity measurements, etc. Here, we propose a non-parametric nearest neighbor classification method based on global variance differences. First, the difference in variance is calculated before and after adding the sample to be the subject, then the difference is divided by the variance before adding the sample to be tested, and the resulting quotient serves as the objective function. In the final step, the samples to be tested are classified into the class with the smallest objective function. Here, we discuss the theoretical aspects of this function. Using the Lagrange method, it can be shown that the objective function can be optimal when the sample centers of each class are averaged. Twelve real datasets from the University of California, Irvine are used to compare the proposed algorithm with competitors such as the Local mean k-nearest neighbor algorithm and the pseudo-nearest neighbor algorithm. According to a comprehensive experimental study, the average accuracy on 12 datasets is as high as 86.27$$\%$$ % , which is far higher than other algorithms. The experimental findings verify that the proposed algorithm produces results that are more dependable than other existing algorithms.

Development and validation of medical record-based logistic regression and machine learning models to diagnose diabetic retinopathy

PURPOSES

Many factors were reported to be associated with diabetic retinopathy (DR); however, their contributions remained unclear. We aimed to evaluate the prognostic and diagnostic accuracy of logistic regression and three machine learning models based on various medical records.

METHODS

This was a cross-sectional study. We investigated the prevalence and associations of DR among 757 participants aged 40 years or older in the 2005-2006 National Health and Nutrition Examination Survey (NHANES). We trained the models to predict if the participants had DR with 15 predictor variables. Area under the receiver operating characteristic (AUROC) and mean squared error (MSE) of each algorithm were compared in the external validation dataset using a replicate cohort from NHANES 2007-2008.

RESULTS

Among the 757 participants, 53 (7.00%) subjects had DR, the mean (standard deviation, SD) age was 57.7 (13.04), and 78.0% were male (n = 42). Logistic regression revealed that female gender (OR = 4.130, 95% CI: 1.820-9.380; P < 0.05), HbA1c (OR = 1.665, 95% CI: 1.197-2.317; P < 0.05), serum creatine level (OR = 2.952, 95% CI: 1.274-6.851; P < 0.05), and eGFR level (OR = 1.009, 95% CI: 1.000-1.014, P < 0.05) increased the risk of DR. The average performance obtained from internal validation was similar in all models (AUROC ≥ 0.945), and k-nearest neighbors (KNN) had the highest value with an AUROC of 0.984. In external validation, they remained robust or with modest reductions in discrimination with AUROC still ≥ 0.902, and KNN also performed the best with an AUROC of 0.982. Both logistic regression and machine learning models had good performance in the clinical diagnosis of DR.

CONCLUSIONS

This study highlights the utility of comparing traditional logistic regression to machine learning models. We found that logistic regression performed as well as optimized machine learning methods when classifying DR patients.

A modified weighted mean of vectors optimizer for Chronic Kidney disease classification

Chronic kidney Disease (CKD), also known as chronic renal disease, is an illness that affects the majority of adults and is defined by a progressive decrease in kidney function over time, particularly in those with diabetes and high blood pressure. Metaheuristic (MH) algorithms based machine learning classifiers have become reliable for medical treatment. The weIghted meaN oF vectOrs (INFO) is a recently developed MH but suffers from a fall into local optimal and slow convergence speed. Therefore, to improve INFO, a modified INFO (mINFO) with two enhancement strategies has been developed. The developed variant utilizes the Opposition-Based Learning (OBL) to improve the local search ability to avoid trapping into the local optimum, and the Dynamic Candidate Solution (DCS) is used to overcome the premature convergence problem in INFO and achieve the appropriate balance between exploration and exploitation ability. The performance of the proposed mINFO based on the k-Nearest Neighbor (kNN) classifier is evaluated on the complex CEC'22 test suite and applied to predict Chronic Kidney Disease (CKD) on datasets extracted from UCI. The statistical results revealed the superiority of mINFO compared with several well-known MH algorithms, including the Harris Hawks Optimization (HHO), the Hunger Games Search (HGS) algorithm, the Moth-Flame Optimization (MFO) algorithm, the Whale Optimization Algorithm (WOA), the Sine Cosine Algorithm (SCA), the Gradient-Based Optimizer (GBO), and the original INFO algorithm. According to our knowledge, this paper is the first of its sort to try employing the proposed mINFO for solving the CEC'22 test suite. Furthermore, the experimental results of mINFO-kNN for classifying two CKD datasets demonstrated its superiority with an overall classification accuracy of 93.17% on two CKD datasets over other competitors.

Nearest Neighbor-Based Strategy to Optimize Multi-View Triplet Network for Classification of Small-Sample Medical Imaging Data

Multi-view classification with limited sample size and data augmentation is a very common machine learning (ML) problem in medicine. With limited data, a triplet network approach for two-stage representation learning has been proposed. However, effective training and verifying the features from the representation network for their suitability in subsequent classifiers are still unsolved problems. Although typical distance-based metrics for the training capture the overall class separability of the features, the performance according to these metrics does not always lead to an optimal classification. Consequently, an exhaustive tuning with all feature-classifier combinations is required to search for the best end result. To overcome this challenge, we developed a novel nearest-neighbor (NN) validation strategy based on the triplet metric. This strategy is supported by a theoretical foundation to provide the best selection of the features with a lower bound of the highest end performance. The proposed strategy is a transparent approach to identify whether to improve the features or the classifier. This avoids the need for repeated tuning. Our evaluations on real-world medical imaging tasks (i.e., radiation therapy delivery error prediction and sarcoma survival prediction) show that our strategy is superior to other common deep representation learning baselines [i.e., autoencoder (AE) and softmax]. The strategy addresses the issue of feature's interpretability which enables more holistic feature creation such that the medical experts can focus on specifying relevant data as opposed to tedious feature engineering.

Human Postures Recognition by Accelerometer Sensor and ML Architecture Integrated in Embedded Platforms: Benchmarking and Performance Evaluation

Embedded hardware systems, such as wearable devices, are widely used for health status monitoring of ageing people to improve their well-being. In this context, it becomes increasingly important to develop portable, easy-to-use, compact, and energy-efficient hardware-software platforms, to enhance the level of usability and promote their deployment. With this purpose an automatic tri-axial accelerometer-based system for postural recognition has been developed, useful in detecting potential inappropriate behavioral habits for the elderly. Systems in the literature and on the market for this type of analysis mostly use personal computers with high computing resources, which are not easily portable and have high power consumption. To overcome these limitations, a real-time posture recognition Machine Learning algorithm was developed and optimized that could perform highly on platforms with low computational capacity and power consumption. The software was integrated and tested on two low-cost embedded platform (Raspberry Pi 4 and Odroid N2+). The experimentation stage was performed on various Machine Learning pre-trained classifiers using data of seven elderly users. The preliminary results showed an activity classification accuracy of about 98% for the four analyzed postures (Standing, Sitting, Bending, and Lying down), with similar accuracy and a computational load as the state-of-the-art classifiers running on personal computers.

Survey on Exact kNN Queries over High-Dimensional Data Space

k nearest neighbours (kNN) queries are fundamental in many applications, ranging from data mining, recommendation system and Internet of Things, to Industry 4.0 framework applications. In mining, specifically, it can be used for the classification of human activities, iterative closest point registration and pattern recognition and has also been helpful for intrusion detection systems and fault detection. Due to the importance of kNN queries, many algorithms have been proposed in the literature, for both static and dynamic data. In this paper, we focus on exact kNN queries and present a comprehensive survey of exact kNN queries. In particular, we study two fundamental types of exact kNN queries: the kNN Search queries and the kNN Join queries. Our survey focuses on exact approaches over high-dimensional data space, which covers 20 kNN Search methods and 9 kNN Join methods. To the best of our knowledge, this is the first work of a comprehensive survey of exact kNN queries over high-dimensional datasets. We specifically categorise the algorithms based on indexing strategies, data and space partitioning strategies, clustering techniques and the computing paradigm. We provide useful insights for the evolution of approaches based on the various categorisation factors, as well as the possibility of further expansion. Lastly, we discuss some open challenges and future research directions.

Sensitivity analysis of large body of control parameters in machine learning control of a square-back Ahmed body

Active drag reduction (DR) of a square-back Ahmed body is experimentally studied based on machine learning or artificial intelligence (AI) control. The control system consists of four independently operated arrays of pulsed microjets, 25 pressure taps and an explorative downhill simplex method controller. Two strategies, i.e. asymmetric and symmetric actuations, are investigated, with 12 and 9 control parameters, respectively. Both achieve a DR by 13%, though with distinct flow physics and control mechanisms behind. A model linking the control parameters with the cost is developed based on Taylor expansion around the K-nearest neighbours of the smallest cost obtained from the AI control, resulting in a substantially reduced deviation between measured and predicted costs, especially when involving a large number of control parameters, compared with that based on Taylor expansion around the optimum cost. Sensitivity analysis, conducted based on the model, indicates that the control efficiency, i.e. the ratio of the power saving from DR to the total power consumption, may reach 55 and 78 for the symmetric and asymmetric strategies, respectively, given a 1–2% sacrifice on DR. This efficiency greatly exceeds that (26.5) obtained by Fan et al. (Fan et al. 2020 Phys. Fluids 32 , 125117. ( doi:10.1063/5.0033156 )), whose independent control parameters are only three.

Supply chain risk management with machine learning technology: A literature review and future research directions

Coronavirus disease 2019 (COVID-19) has placed tremendous pressure on supply chain risk management (SCRM) worldwide. Recent technological advances, especially machine learning (ML) technology, have shown the possibility to prevent supply chain risk (SCR) by decreasing the need for human labor, increasing response speed, and predicting risk. However, the literature lacks a comprehensive analysis of the relationship between ML and SCRM. This work conducts a comprehensive review of the relatively limited literature in this field. An analysis of 67 shortlisted articles from 9 databases shows that this area is still in the rapid development stage and that researchers have shown extraordinary interest in it. The main purpose of this study is to review the current research status so that researchers have a clear understanding of the research gaps in this area. Moreover, this study provides an opportunity for researchers and practitioners to pay attention to ML algorithms for SCRM during the COVID-19 pandemic.

Interactive Visual Cluster Analysis by Contrastive Dimensionality Reduction

We propose a contrastive dimensionality reduction approach (CDR) for interactive visual cluster analysis. Although dimensionality reduction of high-dimensional data is widely used in visual cluster analysis in conjunction with scatterplots, there are several limitations on effective visual cluster analysis. First, it is non-trivial for an embedding to present clear visual cluster separation when keeping neighborhood structures. Second, as cluster analysis is a subjective task, user steering is required. However, it is also non-trivial to enable interactions in dimensionality reduction. To tackle these problems, we introduce contrastive learning into dimensionality reduction for high-quality embedding. We then redefine the gradient of the loss function to the negative pairs to enhance the visual cluster separation of embedding results. Based on the contrastive learning scheme, we employ link-based interactions to steer embeddings. After that, we implement a prototype visual interface that integrates the proposed algorithms and a set of visualizations. Quantitative experiments demonstrate that CDR outperforms existing techniques in terms of preserving correct neighborhood structures and improving visual cluster separation. The ablation experiment demonstrates the effectiveness of gradient redefinition. The user study verifies that CDR outperforms t-SNE and UMAP in the task of cluster identification. We also showcase two use cases on real-world datasets to present the effectiveness of link-based interactions.

Ribosomal Stress Couples with the Hypoxia Response in Dec1-Dependent Orthodontic Tooth Movement

This study characterized the effects of a deficiency of the hypoxia-responsive gene, differentiated embryonic chondrocyte gene 1 (Dec1), in attenuating the biological function of orthodontic tooth movement (OTM) and examined the roles of ribosomal proteins in the hypoxic environment during OTM. HIF-1α transgenic mice and control mice were used for hypoxic regulation of periodontal ligament (PDL) fibroblasts. Dec1 knockout (Dec1KO) and wild-type (WT) littermate C57BL/6 mice were used as in vivo models of OTM. The unstimulated contralateral side served as a control. In vitro, human PDL fibroblasts were exposed to compression forces for 2, 4, 6, 24, and 48 h. HIF-1α transgenic mice had high expression levels of Dec1, HSP105, and ribosomal proteins compared to control mice. The WT OTM mice displayed increased Dec1 expression in the PDL fibroblasts. Micro-CT analysis showed slower OTM in Dec1KO mice compared to WT mice. Increased immunostaining of ribosomal proteins was observed in WT OTM mice compared to Dec1KO OTM mice. Under hypoxia, Dec1 knockdown caused a significant suppression of ribosomal protein expression in PDL fibroblasts. These results reveal that the hypoxic environment in OTM could have implications for the functions of Dec1 and ribosomal proteins to rejuvenate periodontal tissue homeostasis.

An Efficient Approach to Predict Eye Diseases from Symptoms Using Machine Learning and Ranker-Based Feature Selection Methods

The eye is generally considered to be the most important sensory organ of humans. Diseases and other degenerative conditions of the eye are therefore of great concern as they affect the function of this vital organ. With proper early diagnosis by experts and with optimal use of medicines and surgical techniques, these diseases or conditions can in many cases be either cured or greatly mitigated. Experts that perform the diagnosis are in high demand and their services are expensive, hence the appropriate identification of the cause of vision problems is either postponed or not done at all such that corrective measures are either not done or done too late. An efficient model to predict eye diseases using machine learning (ML) and ranker-based feature selection (r-FS) methods is therefore proposed which will aid in obtaining a correct diagnosis. The aim of this model is to automatically predict one or more of five common eye diseases namely, Cataracts (CT), Acute Angle-Closure Glaucoma (AACG), Primary Congenital Glaucoma (PCG), Exophthalmos or Bulging Eyes (BE) and Ocular Hypertension (OH). We have used efficient data collection methods, data annotations by professional ophthalmologists, applied five different feature selection methods, two types of data splitting techniques (train-test and stratified k-fold cross validation), and applied nine ML methods for the overall prediction approach. While applying ML methods, we have chosen suitable classic ML methods, such as Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), AdaBoost (AB), Logistic Regression (LR), k-Nearest Neighbour (k-NN), Bagging (Bg), Boosting (BS) and Support Vector Machine (SVM). We have performed a symptomatic analysis of the prominent symptoms of each of the five eye diseases. The results of the analysis and comparison between methods are shown separately. While comparing the methods, we have adopted traditional performance indices, such as accuracy, precision, sensitivity, F1-Score, etc. Finally, SVM outperformed other models obtaining the highest accuracy of 99.11% for 10-fold cross-validation and LR obtained 98.58% for the split ratio of 80:20.

Air Quality Index prediction using an effective hybrid deep learning model

Environmentalism has become an intrinsic part of everyday life. One of the greatest challenge to the environment's long-term existence is the air pollution. Delhi, the capital of India, has experienced decreasing of air quality for several years. The poor air quality has a significant impact on the lives of individuals. Air Quality Index (AQI) prediction can help to its beneficiaries in taking safeguards about their health before moving to any polluted area. In this study, a variety of data forecasting approaches is evaluated to predict the AQI value for Particulate Matter (PM_2.5) μm at a particular area of Delhi and several error-prone strategies such as R-Squared (R²), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) methods are catalogued. In the proposed approach two deep learning models like Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are combined to predict the AQI of the environment. Several stand alone machine learning (ML) and deep learning (DL) models such as LSTM, Linear-Regression (LR), GRU, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are also trained on the same dataset to compare their performances with the proposed hybrid (LSTM-GRU) model and it is found that the proposed hybrid model shows supremacy in the performance with the MAE value 36.11 and R² value 0.84.

Predicting temporal and spatial variability in flood vulnerability and risk of rural communities at the watershed scale

Due to land-use and hydrology changes, people are constantly exposed to floods. The adverse impact of floods is greater on vulnerable populations that disproportionately inhabit flood-prone areas. This paper reports a comprehensive study on flood vulnerability of flood prone areas in residential areas of the Tajan watershed, Iran in two periods before 2006 and after 2006. Flood prone area were determined by the random forest (RF) and K-nearest neighbor (KNN) machine learning methods. To reduce time and cost, the vulnerability was assessed only in areas with very high flood hazard using 4 main criteria (social, policy, economic, infrastructure), 40 items, and 210 questionnaires across 40 villages. Independent t-test, Kruskal-Wallis, and paired t-test were used for statistical analysis of questionnaire data. The results of machine learning models (MLMs) showed that the RF model with AUC = 0.92% is more accurate in determining flood prone areas. The results of paired t-test showed that the three criteria of social (mean P1 = 2.97 and P2 = 3.35), infrastructure (mean P1 = 2.88 and P2 = 3.25), and policy (mean P1 = 3.02 and P2 = 3.50) had significant changes in both periods. The Kruskal-Wallis test also revealed the mean of all four criteria in both periods and all sub-watersheds, except three sub-watersheds 10 (Khalkhil village), 19 (Tellarem and Kerasp villages), and 23 (Dinehsar and Jafarabad), had a significant difference. The results of the t-test also showed a decrease in vulnerability in the second period (before 2006) compared to the first period (after 2006), so the number of sub-watersheds in the very high vulnerability class was more in the first period than in the second period. A vulnerability map was developed using three factors of risk zone area, area of each sub-watershed, and population of each sub-watershed.

Artificial intelligence-driven prediction of multiple drug interactions

When a drug is administered to exert its efficacy, it will encounter multiple barriers and go through multiple interactions. Predicting the drug-related multiple interactions is critical for drug development and safety monitoring because it provides foundations for practical, safe compatibility and rational use of multiple drugs. With the progress of artificial intelligence (AI) technology, a variety of novel prediction methods for single interaction have emerged and shown great advantages compared to the traditional, expensive and time-consuming laboratory research. To promote the comprehensive and simultaneous predictions of multiple interactions, we systematically reviewed the application of AI in drug-drug, drug-food (excipients) and drug-microbiome interactions. We began by outlining the model methods, evaluation indicators, algorithms and databases commonly used to build models for three types of drug interactions. The models based on the metabolic enzyme P450, drug similarity and drug targets have empathized among the machine learning models of drug-drug interactions. In particular, we discussed the limitations of current approaches and identified potential areas for future research. It is anticipated the in-depth review will be helpful for the development of the next-generation of systematic prediction models for simultaneous multiple interactions.

SDN-Defend: A Lightweight Online Attack Detection and Mitigation System for DDoS Attacks in SDN

With the development of Software Defined Networking (SDN), its security is becoming increasingly important. Since SDN has the characteristics of centralized management and programmable, attackers can easily take advantage of the security vulnerabilities of SDN to carry out distributed denial of service (DDoS) attacks, which will cause the memory of controllers and switches to be occupied, network bandwidth and server resources to be exhausted, affecting the use of normal users. To solve this problem, this paper designs and implements an online attack detection and mitigation SDN defense system. The SDN defense system consists of two modules: anomaly detection module and mitigation module. The anomaly detection model uses a lightweight hybrid deep learning method-Convolutional Neural Network and Extreme Learning Machine (CNN-ELM) for anomaly detection of traffic. The mitigation model uses IP traceback to locate the attacker and effectively filters out abnormal traffic by sending flow rule commands from the controller. Finally, we evaluate the SDN defense system. The experimental results show that the SDN defense system can accurately identify and effectively mitigate DDoS attack flows in real-time.

Noise Robust Face Hallucination Based on Smooth Correntropy Representation

Face hallucination technologies have been widely developed during the past decades, among which the sparse manifold learning (SML)-based approaches have become the popular ones and achieved promising performance. However, these SML methods always failed in handling noisy images due to the least-square regression (LSR) they used for error approximation. To this end, we propose, in this article, a smooth correntropy representation (SCR) model for noisy face hallucination. In SCR, the correntropy regularization and smooth constraint are combined into one unified framework to improve the resolution of noisy face images. Specifically, we introduce the correntropy induced metric (CIM) rather than the LSR to regularize the encoding errors, which admits the proposed method robust to noise with uncertain distributions. Besides, the fused LASSO penalty is added into the feature space to ensure similar training samples holding similar representation coefficients. This encourages the SCR not only robust to noise but also can well exploit the inherent typological structure of patch manifold, resulting in more accurate representations in noise environment. Comparison experiments against several state-of-the-art methods demonstrate the superiority of SCR in super-resolving noisy low-resolution (LR) face images.

Mortality predictors in patients with COVID-19 pneumonia: a machine learning approach using eXtreme Gradient Boosting model

Recently, global health has seen an increase in demand for assistance as a result of the COVID-19 pandemic. This has prompted many researchers to conduct different studies looking for variables that are associated with increased clinical risk, and find effective and safe treatments. Many of these studies have been limited by presenting small samples and a large data set. Using machine learning (ML) techniques we can detect parameters that help us to improve clinical diagnosis, since they are a system for the detection, prediction and treatment of complex data. ML techniques can be valuable for the study of COVID-19, especially because they can uncover complex patterns in large data sets. This retrospective study of 150 hospitalized adult COVID-19 patients, of which we established two groups, those who died were called Case group (n = 53) while the survivors were Control group (n = 98). For analysis, a supervised learning algorithm eXtreme Gradient Boosting (XGBoost) has been used due to its good response compared to other methods because it is highly efficient, flexible and portable. In this study, the response to different treatments has been evaluated and has made it possible to accurately predict which patients have higher mortality using artificial intelligence, obtaining better results compared to other ML methods.

A Neighborhood Model with Both Distance and Quantity Constraints for Multilabel Data

In this paper, a novel distance-based multilabel classification algorithm is proposed. The proposed algorithm combines k-nearest neighbors (kNN) with neighborhood classifier (NC) to impose double constraints on the quantity and distance of the neighbors. In short, the radius constraint is introduced in the kNN model to improve the classification accuracy, and the quantity constraint k is added in the NC model to speed up computing. From the neighbors with the double constraints, the probabilities for each label are estimated by the Bayesian rule, and the classification judgment is made according to the probabilities. Experimental results show that the proposed algorithm has slight advantages over similar algorithms in calculation speed and classification accuracy.

A generic optimization and learning framework for Parkinson disease via speech and handwritten records

Parkinson's disease (PD) is a neurodegenerative disorder with slow progression whose symptoms can be identified at late stages. Early diagnosis and treatment of PD can help to relieve the symptoms and delay progression. However, this is very challenging due to the similarities between the symptoms of PD and other diseases. The current study proposes a generic framework for the diagnosis of PD using handwritten images and (or) speech signals. For the handwriting images, 8 pre-trained convolutional neural networks (CNN) via transfer learning tuned by Aquila Optimizer were trained on the NewHandPD dataset to diagnose PD. For the speech signals, features from the MDVR-KCL dataset are extracted numerically using 16 feature extraction algorithms and fed to 4 different machine learning algorithms tuned by Grid Search algorithm, and graphically using 5 different techniques and fed to the 8 pretrained CNN structures. The authors propose a new technique in extracting the features from the voice dataset based on the segmentation of variable speech-signal-segment-durations, i.e., the use of different durations in the segmentation phase. Using the proposed technique, 5 datasets with 281 numerical features are generated. Results from different experiments are collected and recorded. For the NewHandPD dataset, the best-reported metric is 99.75% using the VGG19 structure. For the MDVR-KCL dataset, the best-reported metrics are 99.94% using the KNN and SVM ML algorithms and the combined numerical features; and 100% using the combined the mel-specgram graphical features and VGG19 structure. These results are better than other state-of-the-art researches.

Support vector machine optimization via an improved elephant herding algorithm for motor energy efficiency rating

Accurate evaluation of motor energy efficiency under off-condition operation can provide an important basis for an energy-saving upgrade of the motor and the elimination of backward motors. By considering the power quality, motor characteristics and load characteristics, a motor energy efficiency evaluation system with seven indexes and 10 grades was constructed. An improved elephant herding optimization method combined with a support vector machine rating model is proposed, it achieved an accuracy higher than 98%. Considering the slow convergence speed and low convergence precision of the standard elephant herding optimization (EHO) method, it is easy to fall into the local optimum problem. To improve population initialization, chaotic mapping and adversarial learning were used to achieve EHO with population diversity and global search capability. Group learning and elite retention have been added to improve the local development ability of the algorithm. The improved EHO has been compared with other intelligent optimization algorithms by using 12 benchmark functions, and the results show that the improved algorithm has better optimization performance.

Joint Specifics and Consistency Hash Learning for Large-Scale Cross-Modal Retrieval

With the dramatic increase in the amount of multimedia data, cross-modal similarity retrieval has become one of the most popular yet challenging problems. Hashing offers a promising solution for large-scale cross-modal data searching by embedding the high-dimensional data into the low-dimensional similarity preserving Hamming space. However, most existing cross-modal hashing usually seeks a semantic representation shared by multiple modalities, which cannot fully preserve and fuse the discriminative modal-specific features and heterogeneous similarity for cross-modal similarity searching. In this paper, we propose a joint specifics and consistency hash learning method for cross-modal retrieval. Specifically, we introduce an asymmetric learning framework to fully exploit the label information for discriminative hash code learning, where 1) each individual modality can be better converted into a meaningful subspace with specific information, 2) multiple subspaces are semantically connected to capture consistent information, and 3) the integration complexity of different subspaces is overcome so that the learned collaborative binary codes can merge the specifics with consistency. Then, we introduce an alternatively iterative optimization to tackle the specifics and consistency hashing learning problem, making it scalable for large-scale cross-modal retrieval. Extensive experiments on five widely used benchmark databases clearly demonstrate the effectiveness and efficiency of our proposed method on both one-cross-one and one-cross-two retrieval tasks.

Abnormal Detection for Running State of Linear Motor Feeding System Based on Deep Neural Networks

Because the linear motor feeding system always runs in complex working conditions for a long time, its performance and state transition have great randomness. Therefore, abnormal detection is particularly significant for predictive maintenance to promptly discover the running state degradation trend. Aiming at the problem that the abnormal samples of linear motor feed system are few and the samples have time-series features, a method of abnormal operation state detection of a linear motor feed system based on normal sample training was proposed, named GANomaly-LSTM. The method constructs an encoding-decoding-reconstructed encoding network model. Firstly, the time-series features of vibration, current and composite data samples are extracted by the long short-term memory (LSTM) network; Secondly, the three-layer fully connected layer is employed to extract potential feature vectors; Finally, anomaly detection of the system is completed by comparing the potential feature vectors of the two encodings. An experimental platform of the X-Y two-axis linkage linear motor feeding system is built to verify the rationality of the proposed method. Compared with other classical methods such as GANomaly and GAN-AE, the average AUROC index of this method is improved by 17.5% and 9.3%, the average accuracy is enhanced by 11.6% and 15.5%, and the detection time is shortened by 223 ms and 284 ms, respectively. GANomaly-LSTM has successfully proved its superiority for abnormal detection for running state of linear motor feeding systems.