An occupant-centric adaptive façade based on real-time and contactless glare and thermal discomfort estimation using deep learning algorithm

Wang, Yuxiao; Han, Yunsong; Wu, Yuran; KORKINA, E.V.; Zhou, Zhibo; Gagarin, Vladimir G.

doi:10.1016/j.buildenv.2022.108907

Cited by 20 publications

(10 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After implementing the design principle of big data store access map, we can implement java-based code [12,13] in the system. In the process of designing and building a Hadoop-based intrusion detection big data analysis, three functional interfaces are required: a map function, a reduce function, and some code to run the job.…”

Section: Big Data Storage For Intrusion Detection Based On Hadoopmentioning

confidence: 99%

Intrusion Detection Method Based on Deep Learning

Tian

Zhang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In today’s information age, the scale of the Internet is growing, the information capacity is also expanding explosively, and network security is becoming more and more important. Intrusion detection is regarded as a traditional security protection technology and is a key means to ensure the security of the network environment. Among them, the deep belief network performs well, and it can automatically learn abstract features for classification. In order to further improve the detection rate and reduce the false positive rate, it is necessary to improve the detection rate of small sample data. This paper builds an intelligent deep learning model and analysis model for intrusion detection data based on TensorFlow. By learning to identify network intrusion characteristic data, the characteristic data and model are stored in the big data storage system built by Hadoop. This algorithm has achieved good experiment result. Build a model knowledge base and an intrusion feature behavior library, use the decision tree model to automatically match the security control strategy, realize a highly intelligent security control model with self-learning ability, and solve the rapid identification of unknown intrusion behaviors. Experiments show that the algorithm can effectively improve the detection rate.

show abstract

Section: Big Data Storage For Intrusion Detection Based On Hadoopmentioning

confidence: 99%

Intrusion Detection Method Based on Deep Learning

Tian

Zhang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Deep learning models such as Convolutional Neural Networks (CNN) [46], Generative Adversarial Networks (GAN) [47], and Recurrent Neural Networks (RNN) [48] have been proven to significantly improve the accuracy of classification in various financial problems [49]. Previous applications of CNN include their use in image processing, sequence, and time-series [50,51], while in financial problems, they are mainly used in the stock market analysis [52]. Tsantekidis et al used CNN to predict mid-price movements of the limit order book; their empirical evidence reveals that CNN can obtain more accurate results than the multilayer perceptron model [53].…”

Section: Research On Default Risk Prediction Methodsmentioning

confidence: 99%

Default Risk Prediction of Enterprises Based on Convolutional Neural Network in the Age of Big Data: Analysis from the Viewpoint of Different Balance Ratios

Jiang

Pan

2022

Complexity

View full text Add to dashboard Cite

In the age of big data, machine learning models are globally used to execute default risk prediction. Imbalanced datasets and redundant features are two main problems that can reduce the performance of machine learning models. To address these issues, this study conducts an analysis from the viewpoint of different balance ratios as well as the selection order of feature selection. Accordingly, we first use data rebalancing and feature selection to obtain 32 derived datasets with varying ratios of balance and feature combinations for each dataset. Second, we propose a comprehensive metric model based on multimachine learning algorithms (CMM-MLA) to select the best-derived dataset with the optimal balance ratio and feature combination. Finally, the convolutional neural network (CNN) is trained on the selected derived dataset to evaluate the performance of our approach in terms of type-II error, accuracy, G-mean, and AUC. There are two contributions in this study. First, the optimal balance ratio is found through the classification accuracy, which changes the deficiency of the existing research that samples are imbalanced or the balance ratio is 1 : 1 and ensures the accuracy of the classification model. Second, a comprehensive metric model based on the machine learning algorithm is proposed, which can simultaneously find the best balance ratio and the optimal feature selection. The experimental results show that our method can noticeably improve the performance of CNN, and CNN outperforms the other four commonly used machine learning models in the task of default risk prediction on four benchmark datasets.

show abstract

“…The proposed strategy using the surrogate model technique resulted in considerable reductions in DGP (Daylight Glare Probability) and assured the target illuminance at up to 96% of occupied task planes, as well as noticeable reductions in lighting loads. To estimate glare and thermal discomfort based on occupants' postures, Wang et al [46] developed a deep learning model using convolutional neural networks (CNN) which regulates the adaptive facades modules and HVAC system. Trained by 1260 videos, the proposed model was able to recognize 13 occupant postures, allowing the occupant-centric contactless comfort evaluation.…”

Section: Occupant-centric Control Of Adaptive Facadesmentioning

confidence: 99%

“…In the mentioned studies, the OCC strategies were investigated in offices without façade shading ( [15,16,39,41]), with the typical roller or blind shading devices ( [13,40,42,45]), or with modular adaptive façade ( [43,46]). Moreover, the related control strategies were mostly established based on the preferences or thermal/visual comfort of one representative occupant with different visual preference scenarios ( [13,39,40,46]), or based on a number of occupants ([15,16,41,43,45]). Accordingly, studies on the topic of implementing OCC strategies in shared office spaces with adaptive façades and including more than one user are relatively rare.…”

Section: Occupant-centric Control Of Adaptive Facadesmentioning

confidence: 99%