Given the importance of continuous traffic flow forecasting in most Intelligent Transportation Systems (ITS) applications, where every new data become available few minutes or seconds, main objective this study is to perform a multi-step ahead that can meet trade-off between accuracy, low computational load, and limited memory capacity. To aim, based on adaptive Kalman filtering theory, two approaches are proposed. We suggest solving prediction problem as one by considering...

In this paper, we consider the problem of finding a linear iteration scheme that yields distributed average consensus in finite number steps D. By modeling interactions between nodes network by means time-invariant undirected graph, is solved deriving set D Laplacian based matrices. We show given nonzero distinct eigenvalues graph matrix. Moreover inverse these constitute step-sizes involved When communications are made through an additive white Gaussian noise channel, on ensemble averaging...

In this letter, we first present explicit relations between block-oriented nonlinear representations and Volterra models. For an identification purpose, show that the estimation of diagonal coefficients kernels associated with considered structures is sufficient to recover overall model. An alternating least squares-type algorithm provided carry out model identification.

SUMMARY Discrete‐time Volterra models are widely used in various application areas. Their usefulness is mainly because of their ability to approximate an arbitrary precision any fading memory nonlinear system and property linearity with respect parameters, the kernels coefficients. The main drawback these parametric complexity implying need estimate a huge number parameters. Considering order higher than two as symmetric tensors, we use parallel factor (PARAFAC) decomposition derive...

<h2>Abstract</h2> Urbanisation is a global trend that significantly impacts sustainable urban development and the quality of life. Assessing sprawl critical for planning aligns with key objectives United Nations goals. This study employed geospatial technology landscape metrics to comprehensively assess, map, quantify extent in Bulawayo from 1984 2022. The leveraged Support Vector Machine (SVM) supervised machine learning algorithm coupled achieve this objective. combined approach allowed...

Traditional non-atomic selfish routing games present some limitations in properly modeling road traffic. This paper introduces a novel type of game leveraging concepts from Daganzo’s cell transmission model (CTM). Each network link is characterized by supply and demand mechanism that enforces capacity constraints based on current density, providing more accurate representation real-world traffic phenomena. We characterize the Wardrop equilibria social optima this identify previously...

The issue of mobility from disadvantaged areas to places interest for work, health care, education, or entertainment poses specific challenges that cannot be approached under the same prism as well-resourced areas. In such areas, commuters are often captive available transportation modes. However, very few studies have focused on identifying key factors influence satisfaction these commuters. this paper, we introduce an agent based modeling and simulation approach, identify classify factors....

In this paper, we consider the problem of a rigid body attitude estimation under external acceleration using small inertial/magnetic sensors module containing triad gyroscope, accelerometer, and magnetometer. This paper is focused on two main challenges. The first one concerns during dynamic cases, in which occurs. order to compensate for such acceleration, design quaternion-based adaptive Kalman filter q-AKF. Precisely, smart detector designed decide whether static or case. Then, covariance...

The start from the Ocean House was something marvelous to see. drivers stormed and scolded, women shrieked cried, wheels locked at intervals of perhaps ten minutes. Occasionally, too, a carriage would capsize, be hauled over fence for repairs . [It was] like huge funeral procession, crawling along snail's pace. It feat get city all.

This paper studies the problem of distributed estimation a static parameter with sensors communicating through an additive white Gaussian noise (AWGN) channel. In noiseless case, we first introduce concept finite-time average consensus, in which nodes can compute exactly finite number steps for arbitrary graph, provided topology is time-invariant. fact, consensus achieved owing to joint diagonalizable matrices. By considering linear iterations scheme, derive closed form expressions such...

Public transport is a fundamental aspect of urban life and its quality service can significantly impact the daily passengers. Research on in public vital to creating efficient inclusive systems. This study which both timely imperative, provides systematic literature review bibliometric analysis with special focus gender machine learning. The employed search Web Science using relevant keywords. Based 270 published articles Science, we evaluate state knowledge through keyword analysis,...

This paper considers rigid body attitude estimation from a small inertial/magnetic sensor module containing triaxial gyroscopes, accelerometers, and magnetometers. Precisely, two challenges are addressed. The first one concerns during various dynamic conditions, in which external acceleration occurs. Although is of the main source loss performance methods, this problem has not been sufficiently addressed literature. An adaptive algorithm compensating residual accelerometer proposed. At each...

This letter is concerned with the parameter estimation of linear and nonlinear subsystems parallel-cascade Wiener systems (PCWS). We first present relationship between a PCWS its associated Volterra model. show that coefficients can be obtained using joint diagonalization third-order kernel slices. Then, are estimated least square algorithm. The proposed method illustrated by means simulation results.

Canonical Polyadic Decomposition (CPD), also known as PARAFAC, is a useful tool for tensor factorization. It has found application in several domains including signal processing and data mining. With the deluge of faced our societies, large-scale matrix factorizations become crucial issue. Few works have been devoted to factorizations. In this paper, we introduce fully distributed method compute CPD across network machines with limited computation resources. The proposed approach based on...

This paper concerns the study of observability in consensus networks modeled with strongly regular graphs or distance graphs. We first give a Kalman-like simple algebraic criterion for consists evaluating rank matrix built components Bose-Mesner algebra associated considered graph. Then, we define some bipartite that capture properties graph to be studied. In particular, show necessary and sufficient conditions are given by nullity so-called local (respectively, unfolded graph) graphs). When...