Linear Components Research Articles

Early menarche and other endocrine disrupting effects of per- and polyfluoroalkyl substances (PFAS) in adolescents from Northern Norway. The Fit Futures study

BackgroundPer- and polyfluoroalkyl substances (PFAS) comprise a large group of chemicals that are ubiquitous in the environment and include recognized persistent organic pollutants. The aim of this cross-sectional study was to investigate possible endocrine disrupting effects of different PFAS in adolescents. MethodsSerum concentrations of PFAS, thyroid, parathyroid and steroid hormones were measured in 921 adolescents aged 15–19 years in the Fit Futures study, Northern Norway. The questionnaire included data on self-reported age at menarche and puberty development score (PDS). Multiple linear and logistic regression analyses and principle component analyses (PCA) were used to assess associations of PFAS with hormones concentrations and puberty indices. ResultsIn girls, total PFAS (∑PFAS), perfluorooctanoate (PFOA), perfluorooctane sulfonate (PFOS), perfluorononanoate (PFNA), perfluorodecanoate (PFDA) were positively associated with dehydroepiandrosterone sulfate (DHEAS) and negatively associated with 11-deoxycorticosterone (11-DOC)/DHEAS ratio. In boys, the associations with 11-DOC/DHEAS ratio were positive for ∑PFAS, perfluoroheptanoate (PFHpA), perfluoroheptane sulfonate (PFHpS), PFOA, and PFOS. Perfluoroundecanoate (PFUnDA) was negatively associated with free thyroxine (fT4) and free triiodothyronine (fT3) in boys. PFNA and PFDA were also negatively associated with fT3 in boys. Serum parathyroid hormone concentration (PTH) was negatively associated with ∑PFAS and perfluorohexane sulfonate (PFHxS) in girls, and with PFOS in boys. PFDA and PFUnDA were positively associated with early menarche, while ∑PFAS and PFOA were positively associated with PDS in boys.No associations of PFAS with serum testosterone, follicle-stimulating hormone, or luteinizing hormone were found in either sex. In girls, PFOA was positively associated with free testosterone index (FTI). In boys, PFOA was positively associated with androstendione and 17-OH-progesterone, while PFHpA was positively associated with estradiol. ConclusionsSerum concentrations of several PFAS were associated with parathyroid and steroid hormones in both sexes, and with thyroid hormones in boys, as well as with early menarche in girls and higher PDS in boys.

Learning Kernel Stein Discrepancy for Training Energy-Based Models

The primary challenge in unsupervised learning is training unnormalized density models and then generating similar samples. Few traditional unnormalized models know what the quality of the trained model is, as most models are evaluated by downstream tasks and often involve complex sampling processes. Kernel Stein Discrepancy (KSD), a goodness-of-fit test method, can measure the discrepancy between the generated samples and the theoretical distribution; therefore, it can be employed to measure the quality of trained models. We first demonstrate that, under certain constraints, KSD is equal to Maximum Mean Discrepancy (MMD), a two-sample test method. PT KSD GAN (Kernel Stein Discrepancy Generative Adversarial Network with a Pulling-Away Term) is produced to compel generated samples to approximate the theoretical distribution. The generator, functioning as an implicit generative model, employs KSD as loss to avoid tedious sampling processes. In contrast, the discriminator is trained to identify the data manifold, also known as an explicit energy-based model. To demonstrate the effectiveness of our approach, we undertook experiments on two-dimensional toy datasets. Our results highlight that our generator adeptly captures the accurate density distribution, while the discriminator proficiently recognizes the unnormalized approximate distribution shape. When applied to linear Independent Component Analysis datasets, the log likelihoods of PT KSD GAN improve by about 5‰ over existing methods when the data dimension is less than 30. Furthermore, our tests on image datasets reveal that the PT KSD GAN excels in navigating high-dimensional challenges, yielding authentically genuine samples.

Lie groups in the symmetric group: Reducing Ulam's problem to the simple case

Ulam asked whether all Lie groups can be represented faithfully on a countable set. We establish a reduction of Ulam's problem to the case of simple Lie groups.In particular, we solve the problem for all solvable Lie groups and more generally Lie groups with a linear Levi component. It follows that every amenable locally compact second countable group acts faithfully on a countable set.

An advanced multi-objective collaborative scheduling strategy for large scale EV charging and discharging connected to the predictable wind power grid

With the large-scale EV connected into the wind power grid, the intermittent, fluctuating and stability bring rigorous challenges for power quality and dispatch, thus wind curtailment becomes more serious. This paper proposes an advanced multi-objective collaborative scheduling strategy to improve the accuracy of the predictable wind grid and ensure the stable operation of the grid by optimizing wind power and EV synergistically. Firstly, a hybrid power prediction method is proposed based on density-based spatial clustering applied to noise (DBSCAN) and partial least squares regression (PLSR) combined with long and short-term memory neural network (LSTM). It establishes a linear component prediction mode to predict the nonlinear wind power efficiently. Secondly, a multi-objective optimization scheduling model is established according to the predicted wind power, considering the vehicle-to-grid (V2G) characteristics of EV, grid load fluctuations, wind curtailment capacity, EV charging costs, and grid losses. The global control aims to achieve overall energy balance and optimize the charging and discharging of EV in a time dimension under constrained conditions. Additionally, based on the total number of EV charging and discharging determined by the global level control, a spatial scheduling optimization is conducted for EV and wind power by the distribution network control, with the goal of minimizing network losses in the distribution network system. Finally, through simulation and comparison of four scenarios, the results demonstrate that the proposed method achieves synergistic optimization of wind power and EV. This paper provides an efficient solution for the optimized scheduling of large-scale EV connected to the predictable wind power grid.

A general configuration for nonlinear circuit employing current-controlled nonlinearity: Application in Chua’s circuit

In this paper, a general configuration for nonlinear circuit employing current-controlled nonlinearity is proposed, which has a simple topology and only contains three linear energy storage components, one nonlinear element, and one multi-port network that can be made by linear resistor. Under this configuration, we design two new five-element chaotic circuits including the first third-order one employing a current-controlled anti-parallel connection diode pair and the second fourth-order one employing a current-controlled memristor emulator. The analyses show that the third-order chaotic circuit is dual to the canonical Chua’s circuit, and the extended fourth-order one can be regarded as a dual canonical memristive Chua’s circuit. The basic analyses including the model description, equilibrium point and stability are presented. Several rich dynamical properties of the two chaotic circuits are investigated using numerical simulations and certified by both Pspice circuit simulations and analog circuit measurements.

54 Individuals Employing Extreme Coping Behaviors Correlated with Increased Severity of Symptoms Following mTBI

Objective:Approximately 10-15% of patients with mild traumatic brain injury (mTBI) report persistent, chronic symptoms more than one month later. Coping behaviors after mTBI can range from fear avoidance (FA), or a reluctance to return to activity because of the fear of symptom exaggeration, to endurance (END), or an overly aggressive return to activity. We evaluated how coping strategy relates to self-reported symptoms in patients with prolonged recovery from mTBI.Participants and Methods:Participants were 72 individuals (age 37.8 + 18.4, 65% female) who sustained a mTBI at least one month prior to assessment (median (IQR) = 5.5 (2.0-11.3) months). Participants completed the Brain Injury Recovery Disposition Scale (BIRDS) to assess FA and END behaviors, and Sport Concussion Assessment Tool (SCAT5) Symptom Inventory. A BIRDS spectrum score was calculated as the difference between FA and END scores to determine individual coping behavior on a spectrum from extreme FA (more negative) to extreme END (more positive). SCAT5 symptoms were separated into four domain scores: somatic, cognitive, sleep, and emotion. Regressions were performed for each outcome examining their potential linear and quadratic associations to coping behavior (i.e., BIRDS spectrum score). Follow-up regressions were performed covarying for age and sex to explore the potential influence of these variables on each outcome.Results:The linear and quadratic components of the BIRDS spectrum score were not significantly related to total number of persisting concussive symptoms. For overall total symptom severity, the quadratic component of the relationship was significant (B = .24, p = 0.04). Visualization of the overall trend line suggested that symptom severity was highest on the extreme FA side of the BIRDS spectrum (highly negative BIRDS spectrum score), decreased as coping behavior become more balanced (BIRDS spectrum score surrounding “0"), plateaued, then increased abruptly on the extreme END side (highly positive BIRDS spectrum score). For cognitive symptoms, the linear component of the BIRDS spectrum score was significant (B = -.28, p = 0.02) and the quadratic component was marginally significant (B = .22, p = 0.06). The quadratic (but not linear) component was significantly related to both the severity of sleep (B = .31, p = 0.01) and emotion symptoms (B = .25, p = 0.03). Finally, neither the linear nor quadratic components were significantly related to the somatic symptom severity. After covarying for age and sex, the quadratic component remained significant for total symptom severity (p = 0.05) as well as the linear component for cognitive severity (p = 0.02).Conclusions:Both extreme “fear avoidance” and “endurance” coping styles may be related to more severe chronic mTBI symptoms, especially in domains of sleep and emotion symptoms. Patients with balance of both fear avoidance and endurance behaviors may be more likely to experience less severe symptoms even among mTBI patients with persistent complaints. Identifying coping behavior styles early after mTBI could improve prognostication and help with developing personalized treatment plans to improve patient recovery. Future research with larger sample sizes should further examine the influence of age and sex on the relationship between coping behavior and symptom severity.

Circular building design: a case study in Pakistan

A major transformation from the current, linear practice to a closed-loop system, linked with a circular economy, is required to transform the negative effects of buildings on the environment. Pakistan has one of the fastest growing populations, and conventional building construction is increasing in urban areas due to urban sprawl. This research aims to demonstrate the possible shift to a circular construction industry in Pakistan by comparing the linear design components with the circular design components of exterior walls of a case study taking advantage of life cycle assessment. The results of life cycle assessment applied to the external walls of a house in Karachi show that finding the solution with the lowest impacts is not obvious and that use of apparently “green” solutions may turn out to have higher impacts. Study suggests that building components can be gradually replaced with more circular ones to create a circular built environment.

Hybrid Autoregressive Integrated Moving Average-Support Vector Regression for Stock Price Forecasting

Stock investment provides high-profit opportunities but also has a high risk of loss. Investors use various decision-making methods to minimize this risk, such as stock price forecasting. This research aims to predict daily closing stock prices using a hybrid Autoregressive Integrated Moving Average (ARIMA)-Support Vector Regression (SVR) model and compare it with the single model of ARIMA and SVR, as well as compiling the R-shiny web for the hybrid ARIMA-SVR model which makes it easier for investors to use the model to support investment decision making. The hybrid ARIMA-SVR model is composed of two components: the linear component from the results of stock price forecasting using the Autoregressive Integrated Moving Average (ARIMA) model and the nonlinear components from the residual forecasting results of the ARIMA model using the Support Vector Regression (SVR) model. The data used was closing stock price data from April 1, 2019, to April 1, 2021, from PT Unilever Indonesia Tbk (UNVR.JK), PT Perusahaan Gas Negara Tbk (PGAS.JK), and PT Telekomunikasi Indonesia Tbk (TLKM.JK), from the Yahoo Finance website. The research results conclude that the hybrid ARIMA-SVR model has excellent capabilities in forecasting stock prices with the MAPE values ​​for UNVR, PGAS, and TLKM stocks, respectively of 0.797%, 2.213%, and 0.993%, which are lower than the MAPE values of ARIMA-GARCH and SVR models. The hybrid model can be an alternative model with excellent capabilities in forecasting stock prices.

Extended observer form with vector fields

This paper addresses the problem of transforming a single-input single-output discrete-time system into the extended observer form which comprises a linear observable component and a nonlinear injection term depending on the input, output and their forward shifts up to a finite order. The necessary and sufficient conditions for the existence of the extended observer form are provided in terms of vector fields. The algorithm is presented to find a parametrised state transformation necessary to transform the system into the extended observer form. The obtained results are applicable also in case of non-reversible systems.

Oceanographic wave buoy motion as a 3D-vector field: Spectra, linear components and bound harmonics

This study analyses time history data measured by a widely used type of oceanographic buoy. The motion of the buoy is recorded as a three-component displacement vector with one vertical and two horizontal components. Focusing on the average shapes of the large events in the time series, we investigate the linear and nonlinear structure of the displacements and their inherent relationships. All three displacements show clear evidence of both linear and second-order contributions. Two types of nonlinear contributions are identified: the difference term representing slow oscillation on the mooring system, and the sum term oscillating at roughly twice the frequency of the linear waves. These terms are small vertically but larger horizontally. We examine the coupled structure of the vertical and horizontal motions with a conditioning analysis. The averaged time histories associated with large waves are found to obey a simple reciprocal relationship, and the average shape of the motion in space associated with large waves in the sea-state resembles that in a localised steep wave-group. The power spectrum of the vertical motion can be transformed into those in the horizontal plane. This work demonstrates that, as well as providing accurate spectral information of the sea state, oceanographic wave buoys can provide internally consistent time series for the vector displacement field with little observable distortion from the mooring system.

Manipulation of polarization conversion and dual foci in a twisted caustic vector optical field in free space

Manipulation of polarization states in a complex structured optical field during propagation has become an important topic due to its fundamental interest and potential applications. This work demonstrates the effect of the caustic and twisting phases on the polarization states of a vector beam experimentally and theoretically. The novel properties of polarization evolution, especially the conversions of different states of polarization (SoPs) in a twisted caustic vector beam, occur during propagation in free space because of the modulation of twisting and caustic phases. The orthogonal polarization components tend to appear on the beam centers of two foci, and the two focal distances are closely related to the caustic and twisting phases. The twisting and caustic phases can manipulate the conversions between linear and circular polarization components that occur during propagation. These results provide a new approach to more complex manipulations of a structured optical field, especially in tailoring the evolution of polarization states and two foci. They may find potential applications in the corresponding field.

Structural Time Series Model using Hamiltonian Monte Carlo for Rice Price

Although forecasts of future events are simply uncertain, predicting is one of the most important aspects of future planning. Accurate rice price predictions tend to be helpful for wholesalers, producers, and farmers to develop plans and strategies to reduce the risks that can be faced. Structural time series models are the most plausible alternative for long-term forecasting. This paper proposes an alternate method for modeling average rice prices using structural time series along with Bayesian parameter inference via Hamiltonian Monte Carlo (HMC). The model has been built using the monthly average wholesale rice price from January 2010 to December 2019. For working out both structural time series and HMC, the TensorFlow Probability Library was used. Linear trend, seasonal, and autoregressive components were combined as an additive model to the structural time model. The proposed Hamiltonian parameter produces an optimal acceptance rate. Their trace plot was used to diagnose the convergence of their chain. One of the predictive accuracy of models was assessed using the mean absolute percent error (MAPE). Through both single and multiple chain iterations, the prediction accuracy of a year-ahead is highly accurate, with MAPE less than 2%. Long-term iteration draws during Hamiltonian Monte Carlo should be considered when attempting to achieve more convergence.

The nonlinearity of scattering waves due to interaction between focusing waves and floating production storage and offloading

The study of the full-scale wave–structure interaction is essential to our understanding of the nonlinear characteristics of offshore structures in real-sea states. This paper deals with full-scale numerical studies of the interactions between focusing waves and a fixed floating production storage and offloading (FPSO) in an efficient potential-viscous coupled method. The potential-viscous method combines in-house computational fluid dynamics code developed at Shanghai Jiao Tong University (SJTU) for naval architecture and ocean engineering (naoe) based on an open field operation and manipulation (FOAM), i.e., naoe-FOAM-SJTU solver, with high-order spectral method. The approach is verified on a model-scaled case and shows reasonably good agreement with experimental data. A phase-separation method and a dynamic mode decomposition method are utilized to extract linear and higher-order harmonic components from the scattering waves. The scattering waves around the FPSO are found to affect the higher-order harmonic components. Two kinds of scale ratios are considered to magnify the focusing wave and FPSO by 10 and 100 times to discuss the scale effect, both non-breaking and green water conditions are included to investigate the flow phenomenon. The harmonic components of scattering waves are not proportional to the scale ratio, and the scale effects influence more on higher-order harmonic components. The third- and fourth-order harmonic components of scattering waves around the FPSO in large-scale cases are obvious.

Event‐based reduced‐order H∞$H_{\infty }$ estimation for switched complex networks based on T‐S fuzzy model

AbstractThis paper investigates the design of a reduced‐order filter for a specific class of switched complex network systems with time‐varying delays. To handle the nonlinear components of the complex network, a T‐S fuzzy model is employed to convert them into a set of linear components. To tackle the issue of heavy network load, a memory‐based adaptive trigger mechanism is proposed. In this study, a reduced‐order state estimator is designed using the T‐S fuzzy model. To demonstrate the exponential stability of the error system, a suitable Lyapunov function is constructed based on the Lyapunov stability principle. The parameter matrix of the reduced‐order estimator is determined using the linear matrix inequality and convex linearization method. Additionally, a sufficient condition for the exponential stability of the error system at the suppression level is provided. Finally, the feasibility of the proposed scheme is validated through a simulation experiment.

Influence of High-Order Twisting Phases on Polarization States and Optical Angular Momentum of a Vector Light Field

This study investigates the influence of high-order twisting phases on polarization states and optical angular momentum of a vector light field with locally linear polarization and a hybrid state of polarization (SoP). The twisted vector optical field (TVOF) is experimentally generated based on the orthogonal polarization bases with high-order twisting phases. The initial SoP of a TVOF modulated by the high-order twisting phase possesses various symmetric distributions. The propagation properties of a high-order TVOF with locally linear polarization and hybrid SoP are explored, including the intensity compression, expansion, and conversion between the linear and circular polarization components. In particular, orbital angular momentum (OAM) appears in a high-order TVOF during propagation where no OAM exists in the initial field. The variation of OAM distribution in cross-section becomes more frequent with the increase of the twisting phase order. In addition, a non-symmetric OAM distribution appears in a non-isotropic TVOF, leading to the rotation of the beam around the propagation axis during propagation. The optical energy flow distribution of a high-order TVOF provides a more profound understanding of the propagation dynamics of high-order TVOF. These results provide a new approach for optical field manipulation in a high-order TVOF.

B-123 Utilization of Five Data Mining Algorithms Combined with Simplified Preprocessing to Establish Reference Intervals of Thyroid Related Hormones for Nonelderly Adults

Abstract Background Despite the extensive research on data mining algorithms, there is still a lack of a standard protocol to evaluate the performance of the existing algorithms. Therefore, the study aims to provide a novel procedure that combines data mining algorithms and simplified preprocessing to establish reference intervals (RIs), with the performance of five algorithms assessed objectively as well. Methods The Test data set and the Reference data set are the two data sets derived from the population undergoing a physical examination. After the thyroid-related hormone including thyroid stimulating hormone (TSH), free triiodo-thyronine (FT3), total triiodo-thyronine (TT3), free thyroxine(FT4), and total thyroxine (TT4) were measured by an ADVIA Centaur XP chemiluminescence immunoassay analyzer, five data algorithms were used to calculated RIs. Hoffmann, Bhattacharya, Expectation Maximum (EM), kosmic, and refineR algorithms combined with two-step data preprocessing respectively were implemented in the Test data set to establish RIs for thyroid-related hormones. The first step is to conduct a random sampling strategy to balance the ratio of sex and age, and the second step is to identify the outliers of variables in each subgroup by the Tukey method. Algorithm-calculated RIs were compared with the standard RIs calculated by transformed parametric method from the Reference data set in which reference individuals were selected following strict inclusion and exclusion criteria. RIs partition were comprehensively determined by the multiple linear regression and variance component analysis. Objective assessment of the methods is implemented by the bias ratio (BR) matrix, of which the BR threshold was set to 0.375. Results The levels of the all five thyroid-related hormones are significantly different in sex, with the male having lower TSH and higher FT3, FT4, TT3, and TT4 compared to the female. Further analysis indicates the establishment of sex-specific RIs for FT3 and FT4. Standard RIs derived from the Reference data set by transformed parametric method are 0.801–4.221 μIU/L for TSH, 2.58–3.82 pg/mL for FT3, 0.98–1.53 ng/dL for FT4, 0.80–1.38 ng/mL for TT3, 5.46–10.05 g/dL for TT4, respectively. There is a high consistency between TSH RIs established by the EM algorithm and the standard TSH RIs (BR = 0.063), although EM algorithms seems to perform poor on other hormones with the BR higher than 0.375. RIs calculated by Hoffmann, Bhattacharya, and refineR methods for free and total triiodo-thyronine, free and total thyroxine respectively are close and matched the standard RIs. Conclusion An effective approach for objectively evaluating the performance of the algorithm based on the BR matrix is established. EM algorithm combined with simplified preprocessing can handle data with significant skewness, but its performance is limited in other scenarios. The other four algorithms perform well for data with Gaussian or near-Gaussian distribution. Using the appropriate algorithm based on the data distribution characteristics is recommended.

Controlling the polarization dependence of the complex transmission spectrum using the Brewster effect in metafilms.

We propose a method for controlling the polarization dependence of the complex transmission spectrum using the Brewster effect in a two-dimensional array of meta-atoms with finite thickness, which we refer to as a metafilm. We show that the complex transmission spectra of the orthogonal linear polarization components can be controlled independently without reflection by stacking multiple metafilms that exhibit only an electric dipole resonance. As a proof-of-concept numerical demonstration, we design several broadband waveplates with high transmission efficiency based on simple design principles. The proposed method would enable us to easily design anisotropic metamaterials with various complex transmission spectra.

Specialist hybrid models with asymmetric training for malaria prevalence prediction.

Malaria is a common and serious disease that primarily affects developing countries and its spread is influenced by a variety of environmental and human behavioral factors; therefore, accurate prevalence prediction has been identified as a critical component of the Global Technical Strategy for Malaria from 2016 to 2030. While traditional differential equation models can perform basic forecasting, supervised machine learning algorithms provide more accurate predictions, as demonstrated by a recent study using an elastic net model (REMPS). Nevertheless, current short-term prediction systems do not achieve the required accuracy levels for routine clinical practice. To improve in this direction, stacked hybrid models have been proposed, in which the outputs of several machine learning models are aggregated by using a meta-learner predictive model. In this paper, we propose an alternative specialist hybrid approach that combines a linear predictive model that specializes in the linear component of the malaria prevalence signal and a recurrent neural network predictive model that specializes in the non-linear residuals of the linear prediction, trained with a novel asymmetric loss. Our findings show that the specialist hybrid approach outperforms the current state-of-the-art stacked models on an open-source dataset containing 22 years of malaria prevalence data from the city of Ibadan in southwest Nigeria. The specialist hybrid approach is a promising alternative to current prediction methods, as well as a tool to improve decision-making and resource allocation for malaria control in high-risk countries.

Stability Analysis for Seed Yield Trait in Indian Mustard (Brassica juncea L. Czern & Coss.)

Present study was undertaken to estimate the magnitude of genotype × environment interaction (GEI) and to identify stability of improved and high-yielding varieties of Indian mustard (Brassica juncea L. Czerns & coss.). The 57 Indian mustard genotypes were evaluated in RBD along with three replications during Rabi crop seasons in three environments. Analysis of variance on 14 traits was carried out individually as well as pooled over environments. Yield stability was analysed employing Eberhart and Russell’s model [1] which revealed highly significant differences among genotypes and environments. Mean squares due to environment + genotype x environment interactions (E + G x E) indicated that genotypes interacted considerably with environmental conditions. Further, partitioning of E+G x E effects indicated that E (linear), G x E (linear) components were highly significant for grain yield. Genotypes RH-749, DRMR 1165-40 X RH-406, DRMR IJ-31 X RH-749 had high mean than general mean coupled with regression coefficient close to unity bi = 1 and S2di = 0 and are identified as most stable and desirable Indian mustard genotypes.

An optimized hybrid methodology for short‐term traffic forecasting in telecommunication networks

AbstractWith the rapid development of telecommunication networks, the predictability of network traffic is of significant interest in network analysis and optimization, bandwidth allocation, and load balancing adjustment. Consequently, in recent years, significant research attention has been paid to forecasting telecommunication network traffic. Telecommunication traffic forecasting problems can be considered a time‐series problem, wherein periodic historical data is fed as the input to a model. Time‐series forecasting approaches are broadly categorized as statistical machine learning (ML) methods and their combinations. Statistical approaches forecast linear characteristics of time‐series data, unable to capture nonlinear and complex patterns. ML‐based approaches can model nonlinear characteristics of data. In recent years, hybrid approaches combining statistical and ML‐based approaches have been widely used to model linear and nonlinear data characteristics. However, the performance of these approaches highly depends on feature selection techniques and hyper‐parameter tuning of ML methods. A novel hybrid method is proposed for short‐term traffic forecasting based on feature selection and hyperparameter optimization to address this problem. It combines statistical and ML methods to model linear and nonlinear components of data. First, a novel feature selection technique, modified mutual information based on a linear combination of targets, is proposed to find the candidate input variables. Next, a combination of vector auto regressive moving average (VARMA), long short‐term memory (LSTM), and multilayer perceptron (MLP), called VARMA‐LSTM‐MLP forecaster, is suggested to forecast short‐term traffic. A hybrid metaheuristic algorithm, composed of firefly and BAT, is employed to find the optimal set of hyper‐parameter values. The proposed method is assessed by a real‐world dataset containing Tehran city's daily telecommunication data in IRAN. The evaluation results demonstrate that the proposed method outperforms the existing methods in terms of mean squared error and mean absolute error.