An Evaluation of a NN-Based Model for the Prediction of Foundation Heat Transfer From Basements

2001 ◽  
Author(s):  
Mustafa Salehi ◽  
Moncef Krarti
Keyword(s):  
Heat Transfer ◽  
Network Architecture ◽  
Model Development ◽  
Training Data ◽  
Testing Procedures ◽  
Coupled Problem ◽  
Building Foundation ◽  
Soil Thermal Properties ◽  
Input Variables ◽  
Indoor And Outdoor

Abstract In this paper, a feed-forward artificial neural network module is presented to predict seasonal variations of foundation heat transfer from conditioned basements. The training data for the NN-based module were obtained from a detailed solution of the ground-coupled problem. Input variables for the NN module include foundation geometric dimensions, insulation configuration, indoor and outdoor temperatures, and soil thermal properties. The paper discusses the network architecture and the training and testing procedures. The predictions of the NN-based module are compared to a correlation-based method for a set of basement configurations. The main conclusion of the paper is that NNs can predict seasonal variation of building foundation heat transfer with high accuracy and little effort for model development.

Impact of Layered Soil on Foundation Heat Transfer for Slab-On Grade Floors

2009 ◽  
Author(s):  
Nizar Khaled ◽  
Moncef Krarti
Keyword(s):  
Heat Transfer ◽  
Temperature Estimation ◽  
Soil Medium ◽  
Coupled Heat Transfer ◽  
Building Foundation ◽  
Soil Thermal Properties ◽  
Homogeneous Soil ◽  
Periodic Heat ◽  
The Impact ◽  
Zone Temperature

This paper presents an analytical solution for the steady-periodic heat transfer for a typical slab-on-grade floor building foundation beneath non-homogeneous soil medium. The impact of the above-grade walls on ground-coupled heat transfer is accounted for in the presented solution. The Inter-zone Temperature Estimation Profile (ITPE) technique is utilized to obtain the 3-D solutions to determine soil temperature distributions and to estimate foundation heat loss/gain from slab-on-grade floors. The impact of the non-homogeneous soil properties on the transient foundation heat transfer is investigated for various slab configurations and soil thermal properties.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

RANS Model development on temperature variance in conjugate heat transfer

2020 ◽  
pp. 1-28
Author(s):  
Gaoqiang Yang ◽  
Hector Iacovides ◽  
Timothy Craft ◽  
David Apsley
Keyword(s):  
Heat Transfer ◽  
Conjugate Heat Transfer ◽  
Model Development ◽  
Temperature Variance ◽  
Rans Model

Heat Transfer Analysis and Energy-Saving Methods of the Exterior Windows in the Northern Area

2014 ◽  
Vol 881-883 ◽  
pp. 1233-1236
Author(s):  
Zhong Hua Wang
Keyword(s):  
Heat Transfer ◽  
Thermal Resistance ◽  
Energy Saving ◽  
Outdoor Environment ◽  
Heat Transfer Analysis ◽  
Radiation Heat ◽  
Mathematical Formula ◽  
Factors Affecting ◽  
Northern Area ◽  
Indoor And Outdoor

In this paper, ways of heat transfer through windows and doors between the indoor and outdoor environment in the northern area are summarized. And every heat transfer way is described by mathematical formula. On this basis, methods to improve the energy saving performance of exterior windows are put forward according to factors affecting heat transfer through windows. The first method is increasing solar radiation heat, and then reducing heat loss by infiltration, and increasing the thermal resistance as much as possible. Ideal form of energy-saving window is proposed based on compared windows with different material and thermal resistance.

Analysis and Modelling of Temperature at Lake’s Water – Atmosphere Interface

2021 ◽  
Author(s):  
Vassilis Z. Antonopoulos ◽  
Soultana K. Gianniou
Keyword(s):  
Heat Transfer ◽  
Energy Balance ◽  
Surface Temperature ◽  
Water Surface ◽  
Heat Transfer Model ◽  
Transfer Model ◽  
Net Radiation ◽  
Water Surface Temperature ◽  
Simulation Results ◽  
Input Variables

Abstract The knowledge of micrometeorological conditions on water surface of impoundments is crucial for the better modeling of the temperature and water quality parameters distribution in the water body and against the climatic changes. Water temperature distribution is an important factor that affects most physical, chemical and biological processes and reactions occurring in lakes. In this work, different processes of water surface temperature of lake’s estimation based on the energy balance method are considered. The daily meteorological data and the simulation results of energy balance components from an integrated heat transfer model for two complete years as well as the lake’s characteristics for Vegoritis lake in northern Greece were used is this analysis.The simulation results of energy balance components from a heat transfer model are considered as the reference and more accurate procedure to estimate water surface temperature. These results are used to compare the other processes. The examined processes include a) models of heat storage changes in relationship to net radiation (Qt(Rn) values, b) net radiation estimation with different approaches, as the process of Slob’s equation with adjusted coefficients to lake data, and c) ANNs models with different architecture and input variables. The results show that the model of heat balance describes the water surface temperature with high accuracy (r2=0.916, RMSE=2.422oC). The ANN(5,6,1) model in which Tsw(i-1) is incorporated in the input variables was considered the better of all other ANN structures (r2=0.995, RMSE=0.490oC). The use of different approaches for simulating net radiation (Rn) and Qt(Rn) in the equation of water surface temperature gives results with lower accuracy.

scholarly journals DeepIsoFun: a deep domain adaptation approach to predict isoform functions

2018 ◽  
Vol 35 (15) ◽  
pp. 2535-2544 ◽  
Author(s):  
Dipan Shaw ◽  
Hao Chen ◽  
Tao Jiang
Keyword(s):  
Network Architecture ◽  
Domain Adaptation ◽  
Multiple Instance Learning ◽  
Training Data ◽  
Supplementary Information ◽  
Operating Characteristics ◽  
Neural Network Architecture ◽  
Receiver Operating Characteristics Curve ◽  
Gene Functions ◽  
Better Than

AbstractMotivationIsoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms.ResultsWe evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions.Availability and implementationhttps://github.com/dls03/DeepIsoFun/Supplementary informationSupplementary data are available at Bioinformatics online.

Patent Innovation Factors Evolution Based on P-SVM and GCCA

2010 ◽  
Vol 39 ◽  
pp. 247-252
Author(s):  
Sheng Xu ◽  
Zhi Juan Wang ◽  
Hui Fang Zhao
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machines ◽  
Correlation Coefficient ◽  
Network Architecture ◽  
Innovation Management ◽  
Model Development ◽  
Real Data ◽  
Support Vector ◽  
Vector Machines ◽  
Gray Correlation

A two-stage neural network architecture constructed by combining potential support vector machines (P-SVM) with genetic algorithm (GA) and gray correlation coefficient analysis (GCCA) is proposed for patent innovation factors evolution. The enterprises patent innovation is complex to conduct due to its nonlinearity of influenced factors. It is necessary to make a trade off among these factors when some of them conflict firstly. A novel way about nonlinear regression model with the potential support vector machines (P-SVM) is presented in this paper. In the model development, the genetic algorithm is employed to optimize P-SVM parameters selection. After the selected key factors by the PSVM with GA model, the main factors that affect patent innovation generation have been quantitatively studied using the method of gray correlation coefficient analysis. Using a set of real data in China, the results show that the methods developed in this paper can provide valuable information for patent innovation management and related municipal planning projects.

scholarly journals Deep learning of stochastic contagion dynamics on complex networks

2020 ◽  
Author(s):  
Charles Murphy ◽  
Edward Laurence ◽  
Antoine Allard
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Neural Network Architecture ◽  
Complementary Approach ◽  
Quantitative Accuracy ◽  
Simplifying Assumptions ◽  
Effective Models

Abstract Forecasting the evolution of contagion dynamics is still an open problem to which mechanistic models only offer a partial answer. To remain mathematically and/or computationally tractable, these models must rely on simplifying assumptions, thereby limiting the quantitative accuracy of their predictions and the complexity of the dynamics they can model. Here, we propose a complementary approach based on deep learning where the effective local mechanisms governing a dynamic are learned automatically from time series data. Our graph neural network architecture makes very few assumptions about the dynamics, and we demonstrate its accuracy using stochastic contagion dynamics of increasing complexity on static and temporal networks. By allowing simulations on arbitrary network structures, our approach makes it possible to explore the properties of the learned dynamics beyond the training data. Our results demonstrate how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.

Sign in / Sign up

Export Citation Format

Share Document