scholarly journals A COMPARISON OF ARTIFICIAL NEURAL NETWORK AND HOMOTOPY CONTINUATION IN 3D INTERIOR BUILDING MODELLING

2017 ◽  
Vol XLII-4/W7 ◽  
pp. 13-21 ◽  
Author(s):  
A. Jamali ◽  
F. Anton ◽  
A. Abdul Rahman ◽  
D. Mioc
Keyword(s):  
Neural Network ◽  
Interval Analysis ◽  
Laser Scanning ◽  
Homotopy Continuation ◽  
Range Finder ◽  
Combined Method ◽  
Basic Model ◽  
Construction Model ◽  
Interval Valued ◽  
Data Acquisition Process

Indoor surveying is currently based on laser scanning technology, which is time-consuming and costly. A construction model depends on complex calculations which need to manage a large number of measured points. This is suitable for the detailed geometrical models utilized for representation, yet excessively overstated when a simple model including walls, floors, roofs, entryways, and windows is required, such a basic model being a key for efficient network analysis such as shortest path finding. To reduce the time and cost of the indoor building data acquisition process, the Trimble LaserAce 1000 range finder is used. A comparison of neural network and a combined method of interval analysis and homotopy continuation in 3D interior building modelling for calibration of inaccurate surveying equipment is presented. We will present the interval valued homotopy model of the measurement of horizontal angles by the magnetometer component of the rangefinder. This model blends interval analysis and homotopy continuation. The results prove that homotopies give the best results both in terms of RMSE and the L<sub>∞</sub> metric.

scholarly journals 3D Indoor Building Environment Reconstruction using Least Square Adjustment, Polynomial Kernel, Interval Analysis and Homotopy Continuation

2016 ◽  
Vol XLII-2/W1 ◽  
pp. 103-113 ◽  
Author(s):  
Ali Jamali ◽  
François Anton ◽  
Alias Abdul Rahman ◽  
Darka Mioc
Keyword(s):  
Data Acquisition ◽  
Interval Analysis ◽  
Laser Scanning ◽  
Least Square ◽  
Polynomial Kernel ◽  
Homotopy Continuation ◽  
Indoor Environments ◽  
Range Finder ◽  
Angle Sensor ◽  
Scanning Method

Nowadays, municipalities intend to have 3D city models for facility management, disaster management and architectural planning. Indoor models can be reconstructed from construction plans but sometimes, they are not available or very often, they differ from ‘as-built’ plans. In this case, the buildings and their rooms must be surveyed. One of the most utilized methods of indoor surveying is laser scanning. The laser scanning method allows taking accurate and detailed measurements. However, Terrestrial Laser Scanner is costly and time consuming. In this paper, several techniques for indoor 3D building data acquisition have been investigated. For reducing the time and cost of indoor building data acquisition process, the Trimble LaserAce 1000 range finder is used. The proposed approache use relatively cheap equipment: a light Laser Rangefinder which appear to be feasible, but it needs to be tested to see if the observation accuracy is sufficient for the 3D building modelling. The accuracy of the rangefinder is evaluated and a simple spatial model is reconstructed from real data. This technique is rapid (it requires a shorter time as compared to others), but the results show inconsistencies in horizontal angles for short distances in indoor environments. The range finder horizontal angle sensor was calibrated using a least square adjustment algorithm, a polynomial kernel, interval analysis and homotopy continuation.

scholarly journals 3D INDOOR BUILDING ENVIRONMENT RECONSTRUCTION USING CALIBRATION OF RANGEFINDER DATA

2015 ◽  
Vol II-2/W2 ◽  
pp. 29-34 ◽  
Author(s):  
A. Jamali ◽  
F. Anton ◽  
A. A. Rahman ◽  
P. Boguslawski ◽  
C. M. Gold
Keyword(s):  
Data Acquisition ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Real Data ◽  
Facility Management ◽  
Least Square ◽  
Homotopy Continuation ◽  
Indoor Environments ◽  
Range Finder ◽  
Architectural Planning

Nowadays, municipalities intend to have 3D city models for facility management, disaster management and architectural planning. 3D data acquisition can be done by laser scanning for indoor environment which is a costly and time consuming process. Currently, for indoor surveying, Electronic Distance Measurement (EDM) and Terrestrial Laser Scanner (TLS) are mostly used. In this paper, several techniques for indoor 3D building data acquisition have been investigated. For reducing the time and cost of indoor building data acquisition process, the Trimble LaserAce 1000 range finder is used. The accuracy of the rangefinder is evaluated and a simple spatial model is reconstructed from real data. This technique is rapid (it requires a shorter time as compared to others), but the results show inconsistencies in horizontal angles for short distances in indoor environments. The range finder was calibrated using a least square adjustment algorithm. To control the uncertainty of the calibration and of the reconstruction of the building from the measurements, interval analysis and homotopy continuation are used.

scholarly journals A Convex Combination Approach for Artificial Neural Network of Interval Data

2021 ◽  
Vol 11 (9) ◽  
pp. 3997
Author(s):  
Woraphon Yamaka ◽  
Rungrapee Phadkantha ◽  
Paravee Maneejuk
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Convex Combination ◽  
Reference Points ◽  
Combination Method ◽  
Suitable Alternative ◽  
Input And Output ◽  
Artificial Neural ◽  
Conventional Models ◽  
Interval Valued

As the conventional models for time series forecasting often use single-valued data (e.g., closing daily price data or the end of the day data), a large amount of information during the day is neglected. Traditionally, the fixed reference points from intervals, such as midpoints, ranges, and lower and upper bounds, are generally considered to build the models. However, as different datasets provide different information in intervals and may exhibit nonlinear behavior, conventional models cannot be effectively implemented and may not be guaranteed to provide accurate results. To address these problems, we propose the artificial neural network with convex combination (ANN-CC) model for interval-valued data. The convex combination method provides a flexible way to explore the best reference points from both input and output variables. These reference points were then used to build the nonlinear ANN model. Both simulation and real application studies are conducted to evaluate the accuracy of the proposed forecasting ANN-CC model. Our model was also compared with traditional linear regression forecasting (information-theoretic method, parametrized approach center and range) and conventional ANN models for interval-valued data prediction (regularized ANN-LU and ANN-Center). The simulation results show that the proposed ANN-CC model is a suitable alternative to interval-valued data forecasting because it provides the lowest forecasting error in both linear and nonlinear relationships between the input and output data. Furthermore, empirical results on two datasets also confirmed that the proposed ANN-CC model outperformed the conventional models.

scholarly journals Interval-valued data prediction via regularized artificial neural network

2019 ◽  
Vol 331 ◽  
pp. 336-345 ◽  
Author(s):  
Zebin Yang ◽  
Dennis K.J. Lin ◽  
Aijun Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Data Prediction ◽  
Artificial Neural ◽  
Interval Valued

scholarly journals Segmentation and Multi-Scale Convolutional Neural Network-Based Classification of Airborne Laser Scanner Data

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3347 ◽  
Author(s):  
Zhishuang Yang ◽  
Bo Tan ◽  
Huikun Pei ◽  
Wanshou Jiang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Region Growing ◽  
Point Clouds ◽  
Classification Method ◽  
Multi Scale ◽  
Airborne Laser

The classification of point clouds is a basic task in airborne laser scanning (ALS) point cloud processing. It is quite a challenge when facing complex observed scenes and irregular point distributions. In order to reduce the computational burden of the point-based classification method and improve the classification accuracy, we present a segmentation and multi-scale convolutional neural network-based classification method. Firstly, a three-step region-growing segmentation method was proposed to reduce both under-segmentation and over-segmentation. Then, a feature image generation method was used to transform the 3D neighborhood features of a point into a 2D image. Finally, feature images were treated as the input of a multi-scale convolutional neural network for training and testing tasks. In order to obtain performance comparisons with existing approaches, we evaluated our framework using the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) 3D labeling benchmark tests. The experiment result, which achieved 84.9% overall accuracy and 69.2% of average F1 scores, has a satisfactory performance over all participating approaches analyzed.

A study on global optimization and deep neural network modeling method in performance-seeking control

2019 ◽  
Vol 234 (1) ◽  
pp. 46-59 ◽  
Author(s):  
Qiangang Zheng ◽  
Dawei Fu ◽  
Yong Wang ◽  
Haoying Chen ◽  
Haibo Zhang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Global Optimization ◽  
Interval Analysis ◽  
Sequential Quadratic Programming ◽  
Deep Neural Network ◽  
Network Modeling ◽  
Engine Performance ◽  
Neural Network Modeling ◽  
Swarm Optimization

In this article, a novel performance-seeking control method based on deep neural network and interval analysis is proposed to obtain a better engine performance. A deep neural network modeling method which has stronger representation capability than conventional neural network and can deal with big training data is adopted to establish an on-board model in the subsonic and supersonic cruising envelops. Meanwhile, a global optimization algorithm interval analysis is applied here to get a better engine performance. Finally, two simulation experiments are conducted to verify the effectiveness of the proposed methods. One is the on-board model modeling which compares the deep neural network with the conventional neural network, and the other is the performance-seeking control simulations comparing interval analysis with feasible sequential quadratic programming, particle swarm optimization, and genetic algorithm, respectively. These two experiments show that the deep neural network has much higher precision than the conventional neural network and the interval analysis gets much better engine performance than feasible sequential quadratic programming, particle swarm optimization, and genetic algorithm.

Sign in / Sign up

Export Citation Format

Share Document