scholarly journals A Novel Multilevel-SVD Method to Improve Multistep Ahead Forecasting in Traffic Accidents Domain

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Lida Barba ◽  
Nibaldo Rodríguez
Keyword(s):  
Time Series ◽  
High Frequency ◽  
Traffic Accidents ◽  
Nonlinear Models ◽  
Multiple Input Multiple Output ◽  
Hankel Matrix ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Novel Method ◽  
Value Decomposition

Here is proposed a novel method for decomposing a nonstationary time series in components of low and high frequency. The method is based on Multilevel Singular Value Decomposition (MSVD) of a Hankel matrix. The decomposition is used to improve the forecasting accuracy of Multiple Input Multiple Output (MIMO) linear and nonlinear models. Three time series coming from traffic accidents domain are used. They represent the number of persons with injuries in traffic accidents of Santiago, Chile. The data were continuously collected by the Chilean Police and were weekly sampled from 2000:1 to 2014:12. The performance of MSVD is compared with the decomposition in components of low and high frequency of a commonly accepted method based on Stationary Wavelet Transform (SWT). SWT in conjunction with the Autoregressive model (SWT + MIMO-AR) and SWT in conjunction with an Autoregressive Neural Network (SWT + MIMO-ANN) were evaluated. The empirical results have shown that the best accuracy was achieved by the forecasting model based on the proposed decomposition method MSVD, in comparison with the forecasting models based on SWT.

scholarly journals Broadband over Power Lines Systems Convergence: Multiple-Input Multiple-Output Communications Analysis of Overhead and Underground Low-Voltage and Medium-Voltage BPL Networks

2013 ◽  
Vol 2013 ◽  
pp. 1-30 ◽  
Author(s):  
Athanasios G. Lazaropoulos
Keyword(s):  
Modal Analysis ◽  
Review Paper ◽  
Low Voltage ◽  
Multiple Input Multiple Output ◽  
Power Lines ◽  
Mimo Channels ◽  
Medium Voltage ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Value Decomposition

This review paper reveals the broadband potential of overhead and underground low-voltage (LV) and medium-voltage (MV) broadband over power lines (BPL) networks associated with multiple-input multiple-output (MIMO) technology. The contribution of this review paper is fourfold. First, the unified value decomposition (UVD) modal analysis is introduced. UVD modal analysis is a new technique that unifies eigenvalue decomposition (EVD) and singular value decomposition (SVD) modal analyses achieving the common handling of traditional SISO/BPL and upcoming MIMO/BPL systems. The validity of UVD modal analysis is examined by comparing its simulation results with those of other exact analytical models. Second, based on the proposed UVD modal analysis, the MIMO channels of overhead and underground LV and MV BPL networks (distribution BPL networks) are investigated with regard to their inherent characteristics. Towards that direction, an extended collection of well-validated metrics from the communications literature, such as channel attenuation, average channel gain (ACG), root-mean-square delay spread (RMS-DS), coherence bandwidth (CB), cumulative capacity, capacity complementary cumulative distribution function (CCDF), and capacity gain (GC), is first applied in overhead and underground MIMO/LV and MIMO/MV BPL channels and systems. It is found that the results of the aforementioned metrics portfolio depend drastically on the frequency, the power grid type (either overhead or underground, either LV or MV), the MIMO scheme configuration properties, the MTL configuration, the physical properties of the cables used, the end-to-end distance, and the number, the electrical length, and the terminations of the branches encountered along the end-to-end BPL signal propagation. Third, three interesting findings concerning the statistical properties of MIMO channels of distribution BPL networks are demonstrated, namely, (i) the ACG, RMS-DS, and cumulative capacity lognormal distributions; (ii) the correlation between RMS-DS and ACG; and (iii) the correlation between RMS-DS and CB. By fitting the numerical results, unified regression distributions appropriate for MIMO/BPL channels and systems are proposed. These three fundamental properties can play significant role in the evaluation of recently proposed statistical channel models for various BPL systems. Fourth, the potential of transformation of overhead and underground LV/BPL and MV/BPL distribution grids to an alternative solution to fiber-to-the-building (FTTB) technology is first revealed. By examining the capacity characteristics of various MIMO scheme configurations and by comparing these capacity results against SISO ones, a new promising urban backbone network seems to be born in a smart grid (SG) environment.

Design of Massive Multiuser MIMO System to Mitigate Inter Antenna Interference and Multiuser Interference in 5G Wireless Networks

2020 ◽  
pp. 693-701 ◽  
Author(s):  
Naga Raju Challa ◽  
◽  
Kalapraveen Bagadi
Keyword(s):  
Communication Networks ◽  
Mimo System ◽  
Multiple Input Multiple Output ◽  
Matrix Computations ◽  
User Terminal ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Major Factors ◽  
Value Decomposition ◽  
User Interference

Massive Multi-user Multiple Input Multiple Output (MU‒MIMO) system is aimed to improve throughput and spectral efficiency in 5G communication networks. Inter-antenna Interference (IAI) and Multi-user Interference (MUI) are two major factors that influence the performance of MU–MIMO system. IAI arises due to closely spaced multiple antennas at each User Terminal (UT), whereas MUI is generated when one UT comes in the vicinity of another UT of the same cellular network. IAI can be mitigated by the use of a pre-coding scheme such as Singular Value Decomposition (SVD) and MUI can be cancelled through efficient Multi-user Detection (MUD) schemes. The highly complex and optimal Maximum Likelihood (ML) detector involves a large number of computations, especially when in massive structures. Therefore, the local search-based algorithm such as Likelihood Ascent Search (LAS) has been found to be a better alternative for mitigation of MUI, as it results in near optimal performance using lesser number of matrix computations. Most of the literature have been aimed at mitigating either IAI or MUI, whereas the proposed work presents SVD pre-coding and LAS MUD to mitigate both IAI and MUI. Simulation results indicate that the proposed scheme can attain near-optimal bit error rate (BER) performance with fewer computations.

scholarly journals Phase Noise Effect on MIMO-OFDM Systems with Common and Independent Oscillators

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Xiaoming Chen ◽  
Hua Wang ◽  
Wei Fan ◽  
Yaning Zou ◽  
Andreas Wolfgang ◽  
...  
Keyword(s):  
Orthogonal Frequency Division Multiplexing ◽  
Multiple Input Multiple Output ◽  
Spatial Multiplexing ◽  
Ofdm Systems ◽  
Error Vector Magnitude ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Mimo Ofdm ◽  
Value Decomposition ◽  
Vector Magnitude

The effects of oscillator phase noises (PNs) on multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems are studied. It is shown that PNs of common oscillators at the transmitter and at the receiver have the same influence on the performance of (single-stream) beamforming MIMO-OFDM systems, yet different influences on spatial multiplexing MIMO-OFDM systems with singular value decomposition (SVD) based precoding/decoding. When each antenna is equipped with an independent oscillator, the PNs at the transmitter and at the receiver have different influences on beamforming MIMO-OFDM systems as well as spatial multiplexing MIMO-OFDM systems. Specifically, the PN effect on the transmitter (receiver) can be alleviated by having more transmit (receive) antennas for the case of independent oscillators. It is found that the independent oscillator case outperforms the common oscillator case in terms of error vector magnitude (EVM).

scholarly journals Smoothing Strategies Combined with ARIMA and Neural Networks to Improve the Forecasting of Traffic Accidents

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Lida Barba ◽  
Nibaldo Rodríguez ◽  
Cecilia Montt
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Traffic Accidents ◽  
Learning Algorithm ◽  
Moving Average ◽  
Arima Model ◽  
Hankel Matrix ◽  
One Step ◽  
Value Decomposition ◽  
Two Stages

Two smoothing strategies combined with autoregressive integrated moving average (ARIMA) and autoregressive neural networks (ANNs) models to improve the forecasting of time series are presented. The strategy of forecasting is implemented using two stages. In the first stage the time series is smoothed using either, 3-point moving average smoothing, or singular value Decomposition of the Hankel matrix (HSVD). In the second stage, an ARIMA model and two ANNs for one-step-ahead time series forecasting are used. The coefficients of the first ANN are estimated through the particle swarm optimization (PSO) learning algorithm, while the coefficients of the second ANN are estimated with the resilient backpropagation (RPROP) learning algorithm. The proposed models are evaluated using a weekly time series of traffic accidents of Valparaíso, Chilean region, from 2003 to 2012. The best result is given by the combination HSVD-ARIMA, with a MAPE of 0 : 26%, followed by MA-ARIMA with a MAPE of 1 : 12%; the worst result is given by the MA-ANN based on PSO with a MAPE of 15 : 51%.

Sign in / Sign up

Export Citation Format

Share Document