Improvement of Envelope Design Through Multilayer Feed-Forward Neural Networks

2016 ◽  
Vol 41 (3) ◽  
pp. 32-37
Author(s):  
Qiquan Chen ◽  
Ji Weng ◽  
Stephen Corcoran ◽  
Chenhao Fan
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Large Scale ◽  
Design Strategy ◽  
Building Envelope ◽  
Optimum Shape ◽  
Future Research ◽  
Feed Forward ◽  
Shape Coefficient ◽  
Strategy Combination

The performance of the building envelope of a large-scale public building significantly influences the energy consumption of such a building. This study aims to determine the best strategy for the envelope by examining the engineering design of the building in Nanchang University. The building shape coefficient, sun-shading strategies, window–wall ratio, roof, and walls were studied through a method involving multilayer feed-forward neural network model simulations. Results show that the optimum shape coefficient value is 0.32. The combination of interior and exterior blinds and electrochromic glass is the ideal option to reduce the increase in the energy consumption of the architecture caused by solar radiation. Maintaining the window–wall ratio at 0.4 is ideal. A green roof exerts a minimal effect on building energy consumption decrease (only 0.4%). Applying the strategy of vertical greening to the external wall can reduce cooling energy consumption by as much as 5.4%. Adopting the best envelope strategy combination can further decrease energy consumption by 20.8%. This strategy is also applicable to the middle and lower reaches of Yangtze River in China, which flow through Nanchang and have a climate similar to that of the said area. Future research should be directed toward applying artificial neural networks to quantitatively evaluate the effects of a design strategy and produce the best design strategy combination.

scholarly journals Structure-preserving deep learning

2021 ◽  
pp. 1-49
Author(s):  
E. CELLEDONI ◽  
M. J. EHRHARDT ◽  
C. ETMANN ◽  
R. I. MCLACHLAN ◽  
B. OWREN ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Large Scale ◽  
Computational Effort ◽  
Model Complexity ◽  
Future Research ◽  
Learning Methods ◽  
Open Problems ◽  
Mathematical Problems ◽  
Made In

Over the past few years, deep learning has risen to the foreground as a topic of massive interest, mainly as a result of successes obtained in solving large-scale image processing tasks. There are multiple challenging mathematical problems involved in applying deep learning: most deep learning methods require the solution of hard optimisation problems, and a good understanding of the trade-off between computational effort, amount of data and model complexity is required to successfully design a deep learning approach for a given problem.. A large amount of progress made in deep learning has been based on heuristic explorations, but there is a growing effort to mathematically understand the structure in existing deep learning methods and to systematically design new deep learning methods to preserve certain types of structure in deep learning. In this article, we review a number of these directions: some deep neural networks can be understood as discretisations of dynamical systems, neural networks can be designed to have desirable properties such as invertibility or group equivariance and new algorithmic frameworks based on conformal Hamiltonian systems and Riemannian manifolds to solve the optimisation problems have been proposed. We conclude our review of each of these topics by discussing some open problems that we consider to be interesting directions for future research.

scholarly journals Artificial Intelligence Applications and Future Research Directions

2019 ◽  
Vol 8 (10S) ◽  
pp. 35-40
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Current Knowledge ◽  
Extensive Study ◽  
Performance Comparison ◽  
Future Research ◽  
Neural Network Models ◽  
Feed Forward ◽  
Artificial Neural

This is an extensive study of Artificial Intelligence applications. It offers artificial neural networks (ANN) taxonomy and supplies investigators with current knowledge and raising needs in ANN based research applications and concentration for investigators. In addition, this study offers an ANN application contributions, challenges, performance comparison and evaluation. This study is demonstrated various ANN applications in diverse disciplines comprise science, computing, medicine, environmental, engineering, climate, technology, mining, arts, nanotechnology, business and so on. Based on this review, it is identified that neural network models like Feedback propagation and Feed forward artificial neural networks performs effectually in human problems based application. Henceforth, feed forward and feed backward propagation ANN focuses on research sourced on data analysis parameters such as accuracy, fault tolerance, latency, volume, convergence, scalability and performance. However, this study suggests that indeed of utilizing single method, future investigation concentrates on merging ANN models into cloud and dentistry based network wide application.

scholarly journals Predicting the Quality of Short Narratives from Social Media

2017 ◽  
Author(s):  
Tong Wang ◽  
Ping Chen ◽  
Boyang Li
Keyword(s):  
Neural Networks ◽  
Social Media ◽  
Large Scale ◽  
Computational Models ◽  
Quality Evaluation ◽  
Future Research ◽  
Automatic Evaluation ◽  
Need To Evaluate ◽  
Difficult Challenge

An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality. Quality evaluation connects narrative understanding and generation as generation systems need to evaluate their own products. To circumvent difficulties in acquiring annotations, we employ upvotes in social media as an approximate measure for story quality. We collected 54,484 answers from a crowd-powered question-and-answer website, Quora, and then used active learning to build a classifier that labeled 28,320 answers as stories. To predict the number of upvotes without the use of social network features, we create neural networks that model textual regions and the interdependence among regions, which serve as strong benchmarks for future research. To our best knowledge, this is the first large-scale study for automatic evaluation of narrative quality.

scholarly journals Data Augmentation for Deep Neural Networks Model in EEG Classification Task: A Review

2021 ◽  
Vol 15 ◽  
Author(s):  
Chao He ◽  
Jialu Liu ◽  
Yuesheng Zhu ◽  
Wencai Du
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Performance Outcomes ◽  
Future Research ◽  
Eeg Classification ◽  
Practical Applications ◽  
Automatic Feature Extraction ◽  
And Performance

Classification of electroencephalogram (EEG) is a key approach to measure the rhythmic oscillations of neural activity, which is one of the core technologies of brain-computer interface systems (BCIs). However, extraction of the features from non-linear and non-stationary EEG signals is still a challenging task in current algorithms. With the development of artificial intelligence, various advanced algorithms have been proposed for signal classification in recent years. Among them, deep neural networks (DNNs) have become the most attractive type of method due to their end-to-end structure and powerful ability of automatic feature extraction. However, it is difficult to collect large-scale datasets in practical applications of BCIs, which may lead to overfitting or weak generalizability of the classifier. To address these issues, a promising technique has been proposed to improve the performance of the decoding model based on data augmentation (DA). In this article, we investigate recent studies and development of various DA strategies for EEG classification based on DNNs. The review consists of three parts: what kind of paradigms of EEG-based on BCIs are used, what types of DA methods are adopted to improve the DNN models, and what kind of accuracy can be obtained. Our survey summarizes the current practices and performance outcomes that aim to promote or guide the deployment of DA to EEG classification in future research and development.

scholarly journals Metamodeling of the Energy Consumption of Buildings with Daylight Harvesting – Application of Artificial Neural Networks Sensitive to Orientation

2021 ◽  
Vol 8 (2) ◽  
pp. 255-269
Author(s):  
Raphaela Walger da Fonseca ◽  
◽  
Fernando Oscar Ruttkay Pereira ◽  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Energy Consumption ◽  
Input Parameter ◽  
Building Envelope ◽  
Building Energy Efficiency ◽  
Input Parameters ◽  
Artificial Neural ◽  
End Use ◽  
Daylight Harvesting

Daylight harvesting is a well-known strategy to address building energy efficiency. However, few simplified tools can evaluate its dual impact on lighting and air conditioning energy consumption. Artificial neural networks (ANNs) have been used as metamodels to predict energy consumption with high precision, few input parameters and instant response. However, this approach still lacks the potential to estimate consumption when there is daylight harvesting, at the ambient level, where the effect of orientation can be noted. This study investigates this potential, in order to evaluate the applicability of ANNs as a tool to aid the architectonic design. The ANNs were approached as metamodels trained based on EnergyPlus thermo-energetic simulations. The network configuration focused on determining its simplest feasible form. The input parameters adopted as the main variables of the building envelope were as follows: orientation, window-to-wall ratio and visible transmission. The effects of the encoding of orientation as a network input parameter, the number of examples of each variable for network training and changing the parameters used for the training were evaluated. The networks predicted the individualized consumption according to the end use with errors below 5%, indicating their potential to be applied as a simplified tool to support the design process, considering the elementary variables of the building envelope. The discussion of results focused on guidelines and challenges to achieve this purpose when contemplating the broadening of the metamodel scope.

scholarly journals Efficient Training of Feed-Forward Neural Networks

1993 ◽  
Vol 22 (464) ◽  
Author(s):  
Martin F. Møller
Keyword(s):  
Neural Networks ◽  
Conjugate Gradient ◽  
Large Scale ◽  
Hessian Matrix ◽  
Back Propagation ◽  
Gradient Algorithm ◽  
Feed Forward ◽  
Conjugate Gradient Algorithms ◽  
Stochastic Version ◽  
Feed Forward Neural Networks

<p>Since the discovery of the back-propagation method, many modified and new algorithms have been proposed for training of feed-forward neural networks. The problem with slow convergence rate has, however, not been solved when the training is on large scale problems. There is still a need for more efficient algorithms. This Ph.D. thesis describes different approaches to improve convergence. The main results of the thesis is the development of the Scaled Conjugate Gradient Algorithm and the stochastic version of this algorithm. Other important results are the development of methods that can derive and use Hessian information in an efficient way. The main part of this thesis is the 5 papers presented in appendices A-E. Chapters 1-6 give an overview of learning in feed-forward neural networks, put these papers in perspective and present the most important results. The conclusion of this thesis is:</p><p> </p><p>* Conjugate gradient algorithms are very suitable for training of feed-forward networks.</p><p>* Use of second order information by calculations on the Hessian matrix can be used to improve convergence.</p>

scholarly journals A Large Scale, App-Based Behaviour Change Experiment Persuading Sustainable Mobility Patterns: Methods, Results and Lessons Learnt

2019 ◽  
Vol 11 (9) ◽  
pp. 2674 ◽  
Author(s):  
Francesca Cellina ◽  
Dominik Bucher ◽  
Francesca Mangili ◽  
José Veiga Simão ◽  
Roman Rudel ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Public Transportation ◽  
Urban Areas ◽  
Large Scale ◽  
Controlled Trial ◽  
Drop Out ◽  
Future Research ◽  
Sustainable Mobility ◽  
Randomized Controlled ◽  
Lessons Learnt

The present urban transportation system, mostly tailored for cars, has long shown its limitations. In many urban areas, public transportation and soft mobility would be able to effectively satisfy many travel needs. However, they tend to be neglected, due to a deep-rooted car dependency. How can we encourage people to make sustainable mobility choices, reducing car use and the related CO 2 emissions and energy consumption? Taking advantage of the wide availability of smartphone devices, we designed GoEco!, a smartphone application exploiting automatic mobility tracking, eco-feedback, social comparison and gamification elements to persuade individual modal change. We tested the effectiveness of GoEco! in two regions of Switzerland (Cantons Ticino and Zurich), in a large-scale, one year long randomized controlled trial. Notwithstanding a large drop-out rate experienced throughout the experiment, GoEco! was observed to produce a statistically significant impact (a decrease in CO 2 emissions and energy consumption per kilometer) for systematic routes in highly car-dependent urban areas, such as the Canton Ticino. In Zurich, instead, where high quality public transport is already available, no statistically significant effects were found. In this paper we present the GoEco! experiment and discuss its results and the lessons learnt, highlighting practical difficulties in performing randomized controlled trials in the field of mobility and providing recommendations for future research.

Sign in / Sign up

Export Citation Format

Share Document