Search

Multivariate time series have more complex and high‐dimensional characteristics, which makes it difficult to analyze and predict the data accurately. In this paper, a new multivariate time series prediction method is proposed. This method is a generative adversarial networks (GAN) method based on Fourier transform and bi‐directional gated recurrent unit (Bi‐GRU). First, the Fourier transform is utilized to extend the data features, which helps the GAN to better learn the distributional features of the original data. Second, in order to guide the model to fully learn the distribution of the original time series data, Bi‐GRU is introduced as the generator of GAN. To solve the problems of mode collapse and gradient vanishing that exist in GAN, Wasserstein distance is used as the loss function of GAN. Finally, the proposed method is used for the prediction of air quality, stock price and RMB exchange rate. The experimental results show that the model can effectively predict the trend of the time series compared with the other nine baseline models. It significantly improves the accuracy and flexibility of multivariate time series forecasting and provides new ideas and methods for accurate time series forecasting in industrial, financial and environmental fields. [ABSTRACT FROM AUTHOR]

In this paper, we derive and analyze a new one-parameter family of modified Cauchy method free from second derivative for obtaining simple roots of nonlinear equations by using Padé approximant. The convergence analysis of the family is also considered, and the methods have convergence order three. Based on the family of third-order method, in order to increase the order of the convergence, a new optimal fourth-order family of modified Cauchy methods is obtained by using weight function. We also perform some numerical tests and the comparison with existing optimal fourth-order methods to show the high computational efficiency of the proposed scheme, which confirm our theoretical results. The basins of attraction of this optimal fourth-order family and existing fourth-order methods are presented and compared to illustrate some elements of the proposed family have equal or better stable behavior in many aspects. Furthermore, from the fractal graphics, with the increase of the value m of the series in iterative methods, the chaotic behaviors of the methods become more and more complex, which also reflected in some existing fourth-order methods.

The research of biomedical data is crucial for disease diagnosis, health management, and medicine development. However, biomedical data are usually characterized by high dimensionality and class imbalance, which increase computational cost and affect the classification performance of minority class, making accurate classification difficult. In this paper, we propose a biomedical data classification method based on feature selection and data resampling. First, use the minimal-redundancy maximal-relevance (mRMR) method to select biomedical data features, reduce the feature dimension, reduce the computational cost, and improve the generalization ability; then, a new SMOTE oversampling method (Spectral-SMOTE) is proposed, which solves the noise sensitivity problem of SMOTE by an improved spectral clustering method; finally, the marine predators algorithm is improved using piecewise linear chaotic maps and random opposition-based learning strategy to improve the algorithm's optimization seeking ability and convergence speed, and the key parameters of the spectral-SMOTE are optimized using the improved marine predators algorithm, which effectively improves the performance of the over-sampling approach. In this paper, five real biomedical datasets are selected to test and evaluate the proposed method using four classifiers, and three evaluation metrics are used to compare with seven data resampling methods. The experimental results show that the method effectively improves the classification performance of biomedical data. Statistical test results also show that the proposed PRMPA-Spectral-SMOTE method outperforms other data resampling methods. [ABSTRACT FROM AUTHOR]

The emergence of credit has generated a wealth of data on consumer lending behavior. In recent years, financial institutions have also started to use such data to make informed lending decisions based on fine-grained customer data, but conventional risk assessment models are inadequate in meeting the risk control requirements of the financial industry. Therefore, this paper proposes a credit scoring ensemble model incorporating fuzzy clustering particle swarm optimization (PSO) algorithm to obtain better credit risk prediction capability. First, a weighted outlier detection method based on the Induced Ordered Weighted Average Operator is proposed to preprocess the data to reduce noisy data's misleading effect on model training. Then, an undersampling method combined with fuzzy clustering PSO is proposed to overcome the negative effect of category imbalance on model training by resampling the data. In addition, a hyperparameter optimization framework is introduced to adaptively adjust important parameters in the ensemble model considering the impact of parameter settings on the training performance of the model. Based on the evaluation metrics of F-score, AUC, and Kappa coefficient, an empirical analysis was conducted on five credit risk datasets. The results show that the proposed method outperforms the comparative model with an improvement of 10% to 50% in terms of F-score and AUC. The highest achieved F-score is 0.9488, and the maximum AUC is 0.9807, demonstrating the effectiveness of the proposed method. The kappa coefficient results indicate a high level of consistency in the predicted classification results of the model. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is widely popular for its advantages such as fast training speed and good generalization performance. However, the randomness of hidden layer parameters in ELM leads to unstable prediction performance of the model. We propose a novel two-hidden-layer extreme learning machine (TELM) for complex data classification. Firstly, the idea of weighting is introduced into TELM, and a weighted two-hidden-layer extreme learning machine (WTELM) model is proposed to improve the classification accuracy of the model. Secondly, the convergence factor and position update formula in gray wolf optimization algorithm (GWO) are adjusted to enhance the optimization algorithm's ability to search for optimal parameters. Finally, an improved gray wolf optimization (IGWO) is utilized to search for the optimal parameters of the WTELM model. The impact of different intelligent optimization algorithms on the model's classification results is compared. The experimental results demonstrate that the classification accuracy of the WTELM model has been improved by about 11–18% compared to traditional ELM models. Moreover, compared to the WTELM model, the classification accuracy of the IGWO-WTELM model has improved by about 1–19%. This indicates that the method proposed in this paper is significantly superior to traditional ELM methods and their variants, improving the stability, training speed and classification accuracy of the model. [ABSTRACT FROM AUTHOR]

Recent epidemiological studies suggested that proton pump inhibitor (PPI) use was associated with an increased risk of biliary tract cancer (BTC), however, confounders were not adequately controlled. Our study aimed to evaluate PPI use and subsequent risk of BTC and its subtypes in three well‐established cohorts. We conducted a pooled analysis of the subjects free of cancers in UK Biobank (n = 463 643), Nurses' Health Study (NHS, n = 80 235) and NHS II (n = 95 869). Propensity score weighted Cox models were used to estimate marginal HRs of PPIs use on BTC risk, accounting for potential confounders. We documented 284 BTC cases in UK Biobank (median follow‐up: 7.6 years), and 91 cases in NHS and NHS II cohorts (median follow‐up: 15.8 years). In UK biobank, PPI users had a 96% higher risk of BTC compared to nonusers in crude model (HR 1.96, 95% CI 1.44‐2.66), but the effect was attenuated to null after adjusting for potential confounders (HR 0.95, 95% CI 0.60‐1.49). PPI use was not associated with risk of BTC in the pooled analysis of three cohorts (HR 0.93, 95% CI 0.60‐1.43). We also observed no associations between PPI use with risk of intrahepatic (HR 1.00, 95% CI 0.49‐2.04), extrahepatic bile duct (HR 1.09, 95% CI 0.52‐2.27) and gallbladder cancers (HR 0.66, 95% CI 0.26‐1.66) in UK Biobank. In summary, regular use of PPIs was not associated with the risk of BTC and its subtypes. [ABSTRACT FROM AUTHOR]

Objective: Medication adherence is considered an important risk factor for sudden unexpected death in epilepsy (SUDEP), although measurement accuracy is difficult. Using prescription dispensations, this study aims to estimate antiseizure medication (ASM) adherence and identify adherence patterns that influence epilepsy mortality. Methods: This is a retrospective cohort study of tertiary epilepsy outpatients seen at St Vincent's Hospital Melbourne, Victoria, Australia, from January 1, 2012 until December 31, 2017. Privacy‐preserving data linkage with the Australian national prescription, death, and coroner's databases was performed. We fitted a four‐cluster longitudinal group‐based trajectory model for ASM adherence from recurring 90‐day windows of prescription dispensations during a 3‐year "landmark period" from January 1, 2012 to December 31, 2014, using the AdhereR package. We estimated the risk of SUDEP and all‐cause death for each adherence pattern during an "observation period" from January 1, 2015 to December 31, 2017. The Cox proportional hazards and logistic regression models were adjusted for age, sex, socioeconomic status, epilepsy duration, comorbidity, drug resistance, and inadequate seizure control. Results: One thousand one hundred eighty‐seven participants were observed for a median of 3.2 years (interquartile range = 2.4–4.0 years). We observed 66 deaths with 10 SUDEP cases during the observation period. We identified four patterns of ASM adherence: good, 51%; declining, 24%; poor, 16%; and very poor, 9%. Declining adherence was associated with an increased risk for SUDEP, with hazard ratio (HR) = 8.43 (95% confidence interval [CI] = 1.10–64.45) at 1 year and HR = 9.17 (95% CI = 1.16–72.21) at 3 years. Compared to no ASM therapeutic change, the addition of a second to fourth ASM offered increased protection against SUDEP in patients with continuing drug‐resistant epilepsy. Significance: ASM nonadherence was observed in half of outpatients with epilepsy. A declining pattern of adherence, observed in a quarter of patients, was associated with more than eight times increased risk of SUDEP. Any ongoing medication interventions must include strategies to maintain and improve ASM adherence if we are to reduce the risk of SUDEP. [ABSTRACT FROM AUTHOR]

Background Polypharmacy among older people represents a global challenge due to its association with adverse drug events. The reported prevalence of polypharmacy varies widely across countries, and is particularly high in Asian countries. However, there is no multinational study using standardised measurements exploring variations in prescribing trends. Objective To compare polypharmacy trends in older people in Asia, Australia and the United Kingdom. Design Multinational, retrospective, time-trend, observational study using a common study protocol. Setting Outpatient and community settings. Subjects All individuals aged ≥ 65 years between 2013 and 2016. Methods We defined polypharmacy as the concomitant use of ≥5 medications for ≥45 days per year. We estimated the annual prevalence of polypharmacy and calculated average annual percentage change (AAPC) to assess the time trends. Results A total of 1.62 million individuals were included in this study. The highest prevalence of polypharmacy was observed in Hong Kong (46.4%), followed by Taiwan (38.8%), South Korea (32.0%), the United Kingdom (23.5%) and Australia (20.1%) in 2016. For the time trend, the Asian region showed a steady increase, particularly in Hong Kong and South Korea (AAPC: Hong Kong, 2.7%; South Korea, 1.8%; Taiwan, 1.0%). However, Australia and the United Kingdom showed a decreasing trend (Australia, −4.9%; the United Kingdom, −1.1%). Conclusions Polypharmacy prevalence in older people was higher in Hong Kong, Taiwan and South Korea, with an increasing trend over time, compared with Australia and the United Kingdom. Our findings underline the necessity to monitor polypharmacy among older people in Asia by conducting government-level interventions and introducing medicine-optimisation strategies. [ABSTRACT FROM AUTHOR]

Passenger flow is an important benchmark for measuring tourism benefits, and accurate tourism passenger flow prediction is of great significance to the government and related tourism enterprises and can promote the sustainable development of China's tourism industry. For daily passenger flow time series data, a passenger flow forecasting method based on convolutional neural network (CNN) and improved quantile regression long short-term memory network (QRLSTM), denoted as CNN-IQRLSTM, is proposed with reconstructed correlation features and in the form of sliding windows as inputs. First, four discrete variables such as whether the day is a weekend and holiday are created by time; then, a sliding window of width 42 is used to pass the passenger flow data into the network sequentially; finally, the loss function of the sparse Laplacian improved QRLSTM is introduced for passenger flow prediction, and the point prediction and interval prediction results under different quartiles are obtained. The application of quantile regression captures the overall picture of the data, enhances the robustness, fit, predictive power and nonlinear processing capability of neural networks, and fills the gap between quantile regression and neural network methods in the field of passenger flow prediction. CNN can effectively handle complex input data, and the improved nonlinear QR model can provide passenger flow quantile prediction information. The method is applied to the tourism traffic prediction of four 5A scenic spots in Jilin Province, and the effectiveness of the method is verified. The results show that the method proposed in this paper fits best in point prediction and has higher prediction accuracy. The MAPE of the Changbai Mountain dataset was 0.07, the MAPE of the puppet palace museum dataset was 0.05, the fit of the Sculpture Park dataset reached 93%, and the fit of the net moon lake dataset was as high as 99%. Meanwhile, the interval prediction results show that the method has a larger interval coverage as well as a smaller interval average width, which improves the prediction efficiency. In 95% of the interval predictions, the interval coverage of Changbai Mountain data is 99% and the interval average width is 0.49. It is a good reference value for the management of different scenic spots. [ABSTRACT FROM AUTHOR]

Rolling bearing fault diagnosis is a meaningful and challenging task. Most methods first extract statistical features and then carry out fault diagnosis. At present, the technology of intelligent identification of bearing mostly relies on deep neural network, which has high requirements for computer equipment and great effort in hyperparameter tuning. To address these issues, a rolling bearing fault diagnosis method based on the improved deep forest algorithm is proposed. Firstly, the fault feature information of rolling bearing is extracted through multigrained scanning, and then the fault diagnosis is carried out by cascade forest. Considering the fitting quality and diversity of the classifier, the classifier and the cascade strategy are updated. In order to verify the effectiveness of the proposed method, a comparison is made with the traditional machine learning method. The results suggest that the proposed method can identify different types of faults more accurately and robustly. At the same time, it has very few hyperparameters and very low requirements on computer hardware. [ABSTRACT FROM AUTHOR]

Aims: Inconclusive findings of lipid‐lowering medications (LLMs) on cancer survival benefit require more evidence. We tested the hypothesis that adherence to this drug is associated with reduced cancer‐specific mortality in a homogeneous population who had used this drug before cancer diagnosis. Methods: The Australian Cancer Database was linked to the Pharmaceutical Benefits Scheme database, and to the National Death Index (up to 2015). Medication adherence was calculated by proportion of days covered. Cox regression models with time‐varying covariates were used to derive multivariable‐adjusted cause‐specific hazard ratio (HR) and 95% confidence interval (CI) for the associations between adherence to LLMs, statins, lipophilic, and hydrophilic statins and cancer‐specific mortality. Results: From 2003 to 2013, 3 separate cohorts of 20 046, 11 719 and 6430 female patients with newly diagnosed breast, colorectal cancer, and melanoma respectively were identified. The 1‐year adherence was similar at 1‐year prediagnosis in the 3 cohorts, on average 82%. Each 10% increase in 1‐year adherence to LLMs was inversely associated with cancer‐specific mortality among women with breast cancer (fully adjusted HR = 0.92, 95% CI 0.91–0.93), colorectal cancer (fully adjusted HR = 0.92, 95% CI 0.91–0.93), or melanoma (fully adjusted HR = 0.97, 95% CI 0.94–1.00). The reductions in cancer‐specific mortality were more pronounced for women who adhered to lipophilic than hydrophilic statins in all 3 cancers albeit not statistically significant for melanoma. Conclusion: Among LLM users, adherence to this drug is associated with a decrease in cancer‐specific mortality. If confirmed, LLMs could be considered as an adjuvant cancer therapy to improve prognosis in cancer survivors. [ABSTRACT FROM AUTHOR]

Objectives: To (a) compare palliative care needs of lung cancer patients on their final admission to community‐based and inpatient palliative care services; and (b) explore whether and how these care needs affect their utilisation of different palliative care services in the last days of life. Methods: Descriptive study involving 17,816 lung cancer patients who received the last episode of palliative care from specialist services and died between 1 January 2013 and 31 December 2018. Results: Both groups of patients admitted to community‐based and inpatient palliative care services generally experienced relatively low levels of symptom distress, but high levels of functional impairment and dependency. "Unstable" versus "stable" palliative care phase (Odds ratio = 11.66; 95% Confidence Interval: 9.55–14.24), poorer functional outcomes and severe levels of distress from many symptoms predicted greater likelihood of use of inpatient versus community‐based palliative care. Conclusions: Most inpatient palliative care admissions are not associated with high levels of symptom severity. To extend the period of home care and rate of home death for people with lung cancer, additional investment is required to improve their access to sufficiently skilled palliative care staff, multi‐disciplinary teams and 24‐hour home support in community settings. [ABSTRACT FROM AUTHOR]

Aims: We investigated long-term adherence to renin–angiotensin system inhibitors (RASIs) and β-blockers, and associated predictors, in senior patients after hospitalization for heart failure (HF). Methods: A population-based data set identified 4488 patients who survived 60 days following their index hospitalization for HF in Western Australia from 2003 to 2008 with a 3-year follow-up. Their person-linked Pharmaceutical Benefits Scheme records identified medications dispensed during follow-up. Drug discontinuation was defined as the first break ≥90 days following the previous supply. Medication adherence was calculated using the proportion of days covered (PDC), with PDC ≥ 80% defined as being adherent. Multivariable logistic regression models were used to identify predictors of PDC < 80%. Results: In the cohort (57% male, mean age: 76.6 years), 77.4% were dispensed a RASI and 52.7% a β-blocker within 60 days postdischarge. Over the 3-year follow-up, 28% and 42% of patients discontinued RASI and β-blockers, respectively. Only 64.6% and 47.5% of RASI and β-blocker users, respectively, were adherent to their treatment over 3 years, with adherence decreasing over time (trend P <.0001 for RASI and trend P =.02 for β-blockers). Older age, increasing Charlson comorbidity score, chronic kidney disease, and chronic obstructive pulmonary disease were independent predictors of PDC < 80% for both drug groups. Conclusion: Among seniors hospitalized for HF, discontinuation gaps were common for RASI and β-blockers postdischarge, and long-term adherence to these medications was suboptimal. Where appropriate, strategies to improve long-term medication adherence are indicated in HF patients, particularly in elderly patients with comorbidities. [ABSTRACT FROM AUTHOR]

Rolling bearing is a critical part of machinery, whose failure will lead to considerable losses and disastrous consequences. Aiming at the research of rotating mechanical bearing data, a fault identification method based on Variational Mode Decomposition (VMD) and Iterative Random Forest (iRF) classifier is proposed. Furthermore, EMD and EEMD are used to decompose the data. At the same time, three mainstream classifiers were selected as the benchmark model. The results show that the proposed model has the highest recognition accuracy. [ABSTRACT FROM AUTHOR]