Arrival Rate Research Articles

A reliable neural network procedure for the novel sixth-order nonlinear singular pantograph differential model

An innovative singular nonlinear sixth-order (SNSO) pantograph differential model (PDM), known as the SNSO-PDM, is the subject of this novel study along with its numerical investigation. The concepts of pantograph and conventional Emden-Fowler have been presented in the design of the novel SNSO-PDM. The models based on Emden–Fowler have huge applications in mathematics and engineering and are always difficult to solve due to singularity. For each class of the innovative SNSO-PDM, the singularity, shape and pantograph factors are described. A reliable stochastic Levenberg-Marquardt backpropagation neural network (LMBPNN) procedure is designed for the SNSO-PDM. The correctness of the SNSOs-PDM is observed through the comparison performances of the achieved and reference outputs. The obtained results of the SNSO-PDM are considered by applying the process of training, certification, and testing to reduce the mean square error. To authenticate the efficacy of the innovative SNSO-PDM, the numerical performances of the solutions are depicted in the sense of regression, error histograms and correlation.

Industry Image Classification Based on Stochastic Configuration Networks and Multi-Scale Feature Analysis.

For industry image data, this paper proposes an image classification method based on stochastic configuration networks and multi-scale feature extraction. The multi-scale features are extracted from images of different scales using deep 2DSCN, and the hidden features of multiple layers are also connected together to obtain more informational features. The integrated features are fed into SCNs to learn a classifier which improves the recognition rate for different categories. In the experiments, a handwritten digit database and an industry hot-rolled steel strip database are used, and the comparison results demonstrate the proposed method can effectively improve the classification accuracy.

Sales strategy selection for liner companies under shipping e-commerce considering canvassing ability competition

The rapid growth of e-commerce applications has promoted the establishment of shipping e-commerce channels by many liner companies in addition to their existing traditional Non-vessel operating common carrier (NVOCC) channel. Unlike NVOCC channels, shipping e-commerce channels guarantee shippers the availability of contracted container slots. However, some problems arise, including the competition with NVOCC channels, shipping slot sales’ risk, and the increasing liner companies’ costs. Therefore, this paper addresses optimal sales strategy selection in the liner transportation industry, including a single traditional NVOCC channel (TN) strategy, and a dual channel with both e-commerce and NVOCC channels (EN) strategy. Two contract scheme models are constructed considering the channel competition on canvassing ability, overselling behavior, demand fluctuation, and the limited liner vessel capacity. Findings show that the impact of overselling behavior on the profit under the EN and TN is not always negative, which is related to the shipping capacity and probability of the high canvassing ability. Comparative analyses reveal that the EN is dominant if the unit overselling compensation cost varies small. Meanwhile, the TN is profitable if the unit overselling compensation cost increases and the canvassing cost of e-commerce channel exceeds a certain value. Otherwise, the selection of sales strategy relies on the arrival rate, the canvassing cost of the e-commerce channel and shipping capacity. The results offer new insights to both theoretical research on container slot sales and the practical selection of sales strategy since shipping e-commerce has changed the slot selling mode in the container shipping industry, which could also enhance the competitiveness of liner companies in the container shipping industry.

A Recurrent Stochastic Configuration Network for Dynamic System Modeling and Its Application

In order to model nonlinear dynamic systems quickly and accurately, a recurrent stochastic configuration network (RSCN) with universal approximation ability is proposed in this paper. The method consists of network parameter learning and network structure determination. The network parameter learning strategy consists of input weights and the biases of hidden nodes generated randomly through a supervision mechanism, while the output weights of hidden nodes are determined by solving the least-squares problem. The network structure is determined incrementally by the training error of a single-layer recurrent neural network. The effectiveness of RSCN is tested and evaluated by using three nonlinear dynamic functions and historical data from a municipal solid waste incineration (MSWI) process. The experimental results show that the proposed method can improve modeling accuracy and reduce training time, which is valuable for applications in the field of industrial process modeling.

Data Farming the Parameters of Simulation-Optimization Solvers

The performance of a simulation-optimization algorithm, a.k.a. a solver, depends on its parameter settings. Much of the research to date has focused on how a solver’s parameters affect its convergence and other asymptotic behavior. While these results are important for providing a theoretical understanding of a solver, they can be of limited utility to a user who must set up and run the solver on a particular problem. When running a solver in practice, good finite-time performance is paramount. In this paper, we explore the relationship between a solver’s parameter settings and its finite-time performance by adopting a data farming approach. The approach involves conducting and analyzing the outputs of a designed experiment wherein the factors are the solver’s parameters and the responses are assorted performance metrics measuring the solver’s speed and solution quality over time. We demonstrate this approach with a study of the ASTRO-DF solver when solving a stochastic activity network problem and an inventory control problem. Through these examples, we show that how some of the solver’s parameters are set greatly affects its ability to achieve rapid, reliable progress and gain insights into the solver’s inner workings. We discuss the implications of using this framework for tuning solver parameters, as well as for addressing related questions of interest to solver specialists and generalists.

A multicriteria decision model to improve emergency preparedness: Locating-allocating urban shelters against floods

The increasing prominence of natural disasters in recent years has made emergency disaster management one of the main challenges for building resilient societies. This way, the warming combination with human-induced urban interventions with climate change reshapes the strategic decision-making that public managers must deal with to promote safety and preparedness. Consequently, it implies complex situations under uncertainty that comprise conflicting dilemmas about which decision-makers (DMs) should establish trade-offs. Given this backdrop, this work proposes a risk-based multidimensional model for assessing urban shelter location against flood risk with Decision Analysis and Multi-Attribute Utility Theory. By using principles of the Queue Theory, the decision model undertakes four criteria that measure in a probabilistic manner the alternatives’ performance when considering urban flood disaster evacuation routes in affected areas. Altogether, it enables the DM to establish his/her preferences with views to rank potential locations for mounting temporary shelters and for planning emergency preparedness in risky areas. Being replicable to any urban context, our proposal has the potential to support and promote the development and implementation of crisis protocols consisting of measures to reduce flood impacts and adapt critical areas to climate change. From a numerical application of the proposed model, the DM is encouraged to explore graphical and tabular visualization tools, as well as sensitivity analysis, to establish in strategic terms how to design and implement emergency shelters to reduce flood risks in urban areas effectively.

Numerical Performance of the Fractional Direct Spreading Cholera Disease Model: An Artificial Neural Network Approach

The current investigation examines the numerical performance of the fractional-order endemic disease model based on the direct spreading of cholera by applying the neuro-computing Bayesian regularization (BR) neural network process. The purpose is to present the numerical solutions of the fractional-order model, which provides more precise solutions as compared to the integer-order one. Real values based on the parameters can be obtained and one can achieve better results by utilizing these values. The mathematical form of the fractional direct spreading cholera disease is categorized as susceptible, infected, treatment, and recovered, which represents a nonlinear model. The construction of the dataset is performed through the implicit Runge–Kutta method, which is used to lessen the mean square error by taking 74% of the data for training, while 8% is used for both validation and testing. Twenty-two neurons and the log-sigmoid fitness function in the hidden layer are used in the stochastic neural network process. The optimization of BR is performed in order to solve the direct spreading cholera disease problem. The accuracy of the stochastic process is authenticated through the valuation of the outputs, whereas the negligible calculated absolute error values demonstrate the approach’s correctness. Furthermore, the statistical operator performance establishes the reliability of the proposed scheme.

Application of Queue Theory in Cafe Services with Erlang Distribution

As urban lifestyles evolve, culinary businesses, particularly cafes, have experienced rapid growth. This surge in popularity has led to an increase in customers and, consequently, longer queues. These extended wait times can frustrate customers and pose challenges to cafe management. To address this issue, we conducted a comprehensive eval___uation and optimization of the service system at a Samarinda cafe using the Erlang distribution queuing system. Primary data was meticulously collected over six days, amounting to a total of 12 hours of observation. Kolmogorov-Smirnov distribution fitting tests were employed, revealing that customer service times adhered to an exponential distribution. The average customer arrival rate was determined to be 0.351 per minute, while the average service time was calculated at 5.546 minutes per customer. Our analysis confirmed that the system operates in a steady state with a utility value of 0.06, indicating sufficient service capacity to handle the current customer load. Therefore, the study concludes that the cafe's service system is currently optimal.

The Cost of Impatience in Dynamic Matching: Scaling Laws and Operating Regimes

We study matching queues with abandonment. The simplest of these is the two-sided queue with servers on one side and customers on the other, both arriving dynamically over time and abandoning if not matched by the time their patience elapses. We identify nonasymptotic and universal scaling laws for the matching loss due to abandonment, which we refer to as the “cost of impatience.” The scaling laws characterize the way in which this cost depends on the arrival rates and the (possibly different) mean patience of servers and customers. Our characterization reveals four operating regimes identified by an operational measure of patience that brings together mean patience and utilization. The four regimes subsume the regimes that arise in asymptotic (heavy-traffic) approximations. The scaling laws, specialized to each regime, reveal the fundamental structure of the cost of impatience and show that its order of magnitude is fully determined by (i) a “winner-take-all” competition between customer impatience and utilization, and (ii) the ability to accumulate inventory on the server side. Practically important is that when servers are impatient, the cost of impatience is, up to an order of magnitude, given by an insightful expression where only the minimum of the two patience rates appears. Considering the trade-off between abandonment and capacity costs, we characterize the scaling of the optimal safety capacity as a function of costs, arrival rates, and patience parameters. We prove that the ability to hold inventory of servers means that the optimal safety capacity grows logarithmically in abandonment cost and, in turn, slower than the square-root growth in the single-sided queue. This paper was accepted by Baris Ata, stochastic models and simulation. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.01513 .

Improving the forecasting of inbound tourism demand based on the mixed-frequency data sampling approach: evidence from Australia

ABSTRACT This study explores how the mixed-frequency data sampling (MIDAS) approach enhances the forecasting of Australia’s inbound tourism demand by employing an autoregressive distributed lag (ARDL)-MIDAS model. The main findings are as follows: First, after capturing the effects of control variables, both daily exchange rate returns and daily exchange rate volatility affect Australia’s inbound tourism demand. Second, the monthly growth rate of inbound tourist arrivals follows a mean-reverting process and incorporating its historical fluctuation information from the past 3 months significantly increases the explanatory power of the ARDL-MIDAS model. Third, the results of the out-of-sample predictive performance indicate that the two MIDAS-based models significantly outperform the benchmark model and the other two candidate models due to the incorporation of intra-month exchange rate information. These findings provide insights into the forecasting of inbound tourism demand and lay the foundation for further tourism business planning, resource allocation, and policymaking.

Payment schemes for resource reallocation in hierarchical medical system: Fee-for-capacity versus performance payment

This study explores resource reallocation, or capacity sinking, in a hierarchical medical system that includes a healthcare funder, a comprehensive hospital, a community hospital, and patients with varying perceptions of different hospital levels. To help the funder better coordinate the process and induce a comprehensive hospital to willingly sink its high-quality medical resources to a community hospital, we design and evaluate two payment schemes: Fee-For-Capacity (FFC) scheme and Performance Payment (PP) scheme. In the FFC scheme, the funder pays a unit capacity sinking price to the comprehensive hospital. In the PP scheme, the sinking price is paid only if the community hospital increases the rate of patient visits. By considering different parties’ decision-making behaviors, we develop a sequential game model within a queuing framework to determine equilibrium results in terms of the patient arrival rate at each hospital, the community hospital’s capacity planning, the comprehensive hospital’s capacity sinking rate, and the funder’s capacity sinking price. Our study indicates that the FFC scheme outperforms the PP scheme in terms of social welfare, patient utility, and waiting time when the budget is low or the funder’s concern about patient utility is relatively high or low. However, both schemes are suboptimal when the budget and the funder’s concern degree are medium. We find that a hybrid payment scheme can alleviate the drawbacks of FFC and PP and help achieve system optimum.

Oversaturated intersections: A real-world assessment of polynomial fluid queue models

This paper investigates the challenges of quantifying stochasticity and dynamics in traffic states, crucial to efficient transportation systems, particularly during oversaturated conditions at signalized intersections. We build upon Newell's polynomial fluid queuing-theoretic ordinary differential equation (ODE) model as an example of model order reduction, with a focus on time-dependent stochastic arrival rates and departure rates. These assumptions facilitate dynamic arrival rate approximation using polynomial functions, which, when integrated with queue lengths, yield total delay per episode. Validation of Newell's polynomial fluid-queue based dynamic patterns is sought by analyzing cumulative cycles during peak periods, segmented based on residual queue values. A comprehensive real-world experiment employs emerging high resolution video detector cameras to capture various queue lengths, revealing recurring congestion patterns. Real-time arrival and departure count during peak periods further allow for the creation of cumulative curves, enhancing our understanding of congestion dynamics at signalized intersections under partially oversaturated conditions. This foundational understanding is essential for applying deep reinforcement learning in such environments, where the goal is to observe environment states to maximize expected long-term reward.

Accelerated MPC: A real-time model predictive control acceleration method based on TSMixer and 2D block stochastic configuration network imitative controller

Modern industrial processes demand real-time model predictive control (MPC) method within the constraints of limited computing resources. This paper introduces an accelerated MPC method to address the issue. Specifically, we employ the time series mixing model (TSMixer) to construct a predictive model capable of accurately forecasting the behavior of the system under control. Furthermore, we extend the capabilities of TSMixer by integrating a feature classification model (TSMixer with FCM). This enhanced version takes into account both future information and static variables, resulting in superior accuracy compared to the transformer model while maintaining a significantly smaller parameter count. Finally, to further enhance MPC’s responsiveness, we develop a two-dimensional block stochastic configuration network (2D-BSCN) imitative controller. This innovative network clones the behavior of rolling optimization, effectively replacing online optimization to reduce computational time. The experimental results show that the accelerated MPC has an excellent performance in numerical simulation and actual industrial processes. Notably, the algorithm achieves a smaller FLOPs and tracking time than other state-of-the-art models, well within the requirement for industrial process control.

Disclosing Delivery Performance Information When Consumers Are Sensitive to Promised Delivery Time, Delivery Reliability, and Price

Problem definition: We investigate how the characteristics of consumers and a service firm influence the firm’s optimal pricing and promised delivery-time decisions as well as the optimal investment in the quality of delivery reliability information available to consumers. Methodology/results: We use utility, queuing, and choice modeling theories to model consumers’ behavior and to find solutions to the firm’s profit maximization problem. Managerial implications: The optimal strategy is to disclose either error-free delivery reliability information or no information at all. We also delineate conditions for each of the two strategies to dominate. Funding: This research was supported by the General Research Fund (GRF) of the Hong Kong Research Grants Council under Research Project LU13500822. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0223 .

Waiting Line System in Health Sector of Bangladesh:

Waiting is inevitable in any service organization. Hence queues are formed. A long queue makes customer dissatisfied whereas increasing server to decrease the length of a queue requires costs. Waiting Line Theory provides a platform to that notion. The health sector of Bangladesh has been facing a bad experience for any citizen of Bangladesh. One of the reasons behind this is the queuing system prevailing in this sector. This paper presents an investigation into the prevailing queuing system in the private practices of Dhaka city. On the basis of investigation suggestions are put forward to improve the situation.

Cancer mutationscape: revealing the link between modular restructuring and intervention efficacy among mutations

There is increasing evidence that biological systems are modular in both structure and function. Complex biological signaling networks such as gene regulatory networks (GRNs) are proving to be composed of subcategories that are interconnected and hierarchically ranked. These networks contain highly dynamic processes that ultimately dictate cellular function over time, as well as influence phenotypic fate transitions. In this work, we use a stochastic multicellular signaling network of pancreatic cancer (PC) to show that the variance in topological rankings of the most phenotypically influential modules implies a strong relationship between structure and function. We further show that induction of mutations alters the modular structure, which analogously influences the aggression and controllability of the disease in silico. We finally present evidence that the impact and location of mutations with respect to PC modular structure directly corresponds to the efficacy of single agent treatments in silico, because topologically deep mutations require deep targets for control.

Stochastic filtering of reaction networks partially observed in time snapshots

Stochastic reaction network models arise in intracellular chemical reactions, epidemiological models and other population process models, and are a class of continuous time Markov chains which have the nonnegative integer lattice as state space. We consider the problem of estimating the conditional probability distribution of a stochastic reaction network given exact partial state observations in time snapshots. We propose a particle filtering method called the targeting method. Our approach takes into account that the reaction counts in between two observation snapshots satisfy linear constraints and also uses inhomogeneous Poisson processes as proposals for the reaction counts to facilitate exact interpolation. We provide rigorous analysis as well as numerical examples to illustrate our method and compare it with other alternatives.

The k-th order mean-deviation model for route choice under uncertainty

This study introduces the k-th order mean-deviation model for optimizing route choice within large, stochastic, and time-variant networks. This model addresses the limitations of the traditional mean-standard deviation approach by better handling extreme outcomes in travel times. It features an objective function called the “travel time budget”, which combines the average path travel time with a safety margin. This margin is defined by a trade-off coefficient and a selected deviation measure (total or semi) of the travel time. The model is divided into three variations: 1) The mean-total deviation (MTD) model for symmetric travel time distributions, 2) The mean-upper-semi-deviation (MUSD) model for asymmetric distributions prioritizing upper semi-deviations, suitable for risk-averse travelers, and 3) The mean-lower-semi-deviation (MLSD) model for asymmetric distributions focusing on lower semi-deviations, preferred by risk-prone individuals. We explore these models’ alignment with the stochastic dominance (SD) rule and develop a solution methodology based on SD principles. Numerical experiments in two real-world transportation networks demonstrate the models’ effectiveness and show how the choice of deviation affects route selection decisions.

LN: A Flexible Algorithmic Framework for Layered Queueing Network Analysis

Layered queueing networks (LQNs) are an extension of ordinary queueing networks useful to model simultaneous resource possession and stochastic call graphs in distributed systems. Existing computational algorithms for LQNs have primarily focused on mean-value analysis. However, other solution paradigms, such as normalizing constant analysis and mean-field approximation, can improve the computation of LQN mean and transient performance metrics, state probabilities, and response time distributions. Motivated by this observation, we propose the first LQN meta-solver, called LN, that allows for the dynamic selection of the performance analysis paradigm to be iteratively applied to the submodels arising from layer decomposition. We report experiments where this added flexibility helps us to reduce the LQN solution errors. We also demonstrate that the meta-solver approach eases the integration of LQNs with other formalisms, such as caching models, enabling the analysis of more general classes of layered stochastic networks. Additionally, to support the accurate evaluation of the LQN submodels, we develop novel algorithms for homogeneous queueing networks consisting of an infinite server node and a set of identical queueing stations. In particular, we propose an exact method of moment algorithms, integration techniques for normalizing constants, and a fast non-iterative mean-value analysis technique.

T-distributed Stochastic Neighbor Network for unsupervised representation learning

Unsupervised representation learning (URL) is still lack of a reasonable operator (e.g. convolution kernel) for exploring meaningful structural information from generic data including vector, image and tabular data. In this paper, we propose a simple end-to-end T-distributed Stochastic Neighbor Network (TsNet) for URL with clustering downstream task. Concretely, our TsNet model has three major components: (1) an adaptive connectivity distribution learning module is presented to construct a pairwise graph for preserving the local structure of generic data; (2) a T-distributed stochastic neighbor embedding based loss function is designed to learn a transformation between embeddings and original data, which improves the discrimination of representations; (3) a nonlinear parametric mapping is learned via our TsNet on an unsupervised generalized manner, which can address the “out-of-sample” issue. By combining these components, our method is able to considerably outperform previous related unsupervised learning approaches on visualization and clustering of generic data. A simple deep neural network equipped on our model respectively achieves 74.90%, 76.56% ACC and NMI, which is 8% relative improvement over previous state-of-the-art on real single-cell RNA-sequencing (scRNA-seq) datasets clustering.