Developing a multivariate time series forecasting framework based on stacked autoencoders and multi-phase feature.

Time series forecasting across different domains has received massive attention as it eases intelligent decision-making activities. Recurrent neural networks and various deep learning algorithms have been applied to modeling and forecasting multivariate time series data. Due to intricate non-linear patterns and significant variations in the randomness of characteristics across various categories of real-world time series data, achieving effectiveness and robustness simultaneously poses a considerable challenge for specific deep-learning models. We have proposed a novel prediction framework with a multi-phase feature selection technique, a long short-term memory-based autoencoder, and a temporal convolution-based autoencoder to fill this gap. The multi-phase feature selection is applied to retrieve the optimal feature selection and optimal lag window length for different features. Moreover, the customized stacked autoencoder strategy is employed in the model. The first autoencoder is used to resolve the random weight initialization problem. Additionally, the second autoencoder models the temporal relation between non-linear correlated features with convolution networks and recurrent neural networks. Finally, the model's ability to generalize, predict accurately, and perform effectively is validated through experimentation with three distinct real-world time series datasets. In this study, we conducted experiments on three real-world datasets: Energy Appliances, Beijing PM2.5 Concentration, and Solar Radiation. The Energy Appliances dataset consists of 29 attributes with a training size of 15,464 instances and a testing size of 4239 instances. For the Beijing PM2.5 Concentration dataset, there are 18 attributes, with 34,952 instances in the training set and 8760 instances in the testing set. The Solar Radiation dataset comprises 11 attributes, with 22,857 instances in the training set and 9797 instances in the testing set. The experimental setup involved evaluating the performance of forecasting models using two distinct error measures: root mean square error and mean absolute error. To ensure robust evaluation, the errors were calculated at the identical scale of the data. The results of the experiments demonstrate the superiority of the proposed model compared to existing models, as evidenced by significant advantages in various metrics such as mean squared error and mean absolute error. For PM2.5 air quality data, the proposed model's mean absolute error is 7.51 over 12.45, about ∼40% improvement. Similarly, the mean square error for the dataset is improved from 23.75 to 11.62, which is ∼51%of improvement. For the solar radiation dataset, the proposed model resulted in ∼34.7% improvement in means squared error and ∼75% in mean absolute error. The recommended framework demonstrates outstanding capabilities in generalization and outperforms datasets spanning multiple indigenous domains.

The Identification of Calcified Coronary Plaque Is Associated With Initiation and Continuation of Pharmacological and Lifestyle Preventive Therapies: A Systematic Review and Meta-Analysis.

OBJECTIVES: The aim of this study was to assess the odds of initiation or continuation of pharmacological and lifestyle preventive therapies in patients with nonzero versus zero coronary artery calcium (CAC) score detected on cardiac computed tomography. BACKGROUND: Detection of calcified coronary plaque could serve as a motivational tool for physicians and patients to intensify preventive therapies. METHODS: We searched PubMed, EMBASE (Excerpta Medica database), Web of Science, Cochrane CENTRAL (Cochrane central register of controlled trials), ClinicalTrials.gov, and the International Clinical Trials Registry Platform for studies evaluating the association of CAC scores with downstream pharmacological or lifestyle interventions for prevention of cardiovascular disease. Pooled odds ratios (ORs) of downstream interventions were obtained using the DerSimonian and Laird random effects model. RESULTS: After a review of 6,256 citations and 54 full-text papers, 6 studies (11,256 participants, mean follow-up time: 1.6 to 6.0 years) were included. Pooled estimates of the odds of aspirin initiation (OR: 2.6; 95% confidence interval [CI]: 1.8 to 3.8), lipid-lowering medication initiation (OR: 2.9; 95% CI: 1.9 to 4.4), blood pressure-lowering medication initiation (OR: 1.9; 95% CI: 1.6 to 2.3), lipid-lowering medication continuation (OR: 2.3; 95% CI: 1.6 to 3.3), increase in exercise (OR: 1.8; 95% CI: 1.4 to 2.4), and dietary change (OR: 1.9; 95% CI: 1.5 to 2.5) were higher in individuals with nonzero CAC versus zero CAC scores, but not for aspirin or blood pressure-lowering medication continuation. When assessed within individual studies, these findings remained significant after adjustment for baseline patient characteristics and cardiovascular risk factors. CONCLUSIONS: This systematic review and meta-analysis suggests that nonzero CAC score, identifying calcified coronary plaque, significantly increases the likelihood of initiation or continuation of pharmacological and lifestyle therapies for the prevention of cardiovascular disease.

Rapidly growing cardiac mass: a rare case of left atrial intramural hematoma complicating coronary artery stenting.

Formation of an intramural left atrial hematoma (ILAH) is a rare complication of coronary artery stenting. Rapid diagnosis with noninvasive multimodality imaging can potentially be lifesaving. We report a case of ILAH that resulted in left ventricular inflow obstruction and pericardial tamponade in a 55-year-old male who presented with hemodynamic instability and worsening dyspnea three weeks after seemingly uncomplicated left circumflex artery stenting. We demonstrate features on transthoracic echocardiography with contrast and cardiac computed tomography that were used for diagnosis and management.

Garlic and Heart Disease.

BACKGROUND: Thousands of studies have been published based on animal and human studies evaluating garlic's effects and safety. OBJECTIVE: We reviewed the available literature investigating the effects of garlic supplements on hypertension, hypercholesterolemia, C-reactive protein (CRP), pulse wave velocity (PWV), and coronary artery calcium (CAC), as well as available data on side effects. METHODS: We searched PubMed for all human studies using medical subject heading words through 30 May 2013 and assessed relevant review articles and original studies. Only double-blind, randomized, controlled trials and meta-analyses of double-blind, randomized, controlled trials were included. The review of articles and data extraction were performed by 2 independent authors, with any disagreements resolved by consensus. RESULTS: Garlic supplementation reduced blood pressure by 7-16 mm Hg (systolic) and 5-9 mm Hg (diastolic) (4 meta-analyses and 2 original studies). It reduced total cholesterol by 7.4-29.8 mg/dL (8 meta-analyses). The most consistent benefits were shown in studies that used aged garlic extract (AGE). A few small studies that used AGE also showed favorable effects on CAC, CRP, and PWV. Although garlic is generally safe, rare adverse reactions have been documented with limited causality established. CONCLUSION: We conclude that garlic supplementation has the potential for cardiovascular protection based on risk factor reduction (hypertension and total cholesterol) and surrogate markers (CRP, PWV, and CAC) of atherosclerosis. Larger studies are warranted to evaluate these effects further.

Design of a Bragg fiber with large mode area for mid-infrared applications.

The design of an all-solid, soft glass-based, large mode area Bragg fiber for effective single mode operation with mode effective area exceeding 1100 µm(2) across the wavelength range of 2-4 µm is reported. The design adopts a new strategy to induce large differential loss between the fundamental and higher order modes for effective single-mode operation within few tens of centimetres length of an otherwise multimode fiber. In addition to having the potential for the targeted application in high power laser delivery systems; complemented by a zero dispersion wavelength at 2.04 µm and rapidly developing mid-IR optical sources, the proposed fiber should also be attractive for generation of high power, single mode and less divergent supercontinuum light over this mid-IR window.