A Deep Learning-Based Segregation of Housing Image Data for Real Estate Application

Kumari, Annu; Maan, Vinod; Sangwan, Dhiraj

doi:10.1007/978-981-33-4582-9_14

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important factor for real estate is convenience, and the classification of supporting facilities available nearby should include as comprehensive details of the daily commuting needs of residents as possible [25]. Kumari and Maan [26] analyzed image and scene (living room, kitchen, bathroom, bedroom, front yard, and backyard) classifications.…”

Section: Introductionmentioning

confidence: 99%

Sustainable Construction Investment, Real Estate Development, and COVID-19: A Review of Literature in the Field

et al. 2021

View full text Add to dashboard Cite

Aspects of sustainable construction investment and real estate development (CIRED) and their interrelations during the period pre-, intra-, and post-COVID-19, are presented in the research. Applications of the topic model, environmental psychology theory, building life cycle method, and certain elements of bibliometrics, webometrics, article level metrics, altmetrics, and scientometrics make it possible to perform a quantitative analysis on CIRED. The CIRED topic model was developed in seven steps. This paper aims to present a literature review on CIRED throughout the pandemic and to look at the responses from the real estate and construction sector. This sector is a field that appears to be rapidly expanding, judging from the volume of current research papers. This review focuses on last year’s leading peer-reviewed journals. A combination of various keywords was applied for the review and the criteria for paper selections included construction investment, real estate development, civil engineering, COVID-19, and sustainability, as well as residential, industrial, commercial, land, and special purpose real estate, along with their risks, strategies, and trends. The articles reviewed for this paper, which analyzes three hypotheses, look at pre-, intra-, and post-pandemic CIRED. The three hypotheses were validated by analyzing scientific publications from around the world. Two innovative elements make this study stand out among the most advanced research on pre-, intra-, and post-pandemic CIRED. The first of the two innovations is the integrated analysis of the COVID-19 pandemic, COVID-19-related national policies, and business investment strategies relevant to CIRED and the interests of investors as well as on the impact a CIRED policy and investors make on the spread of COVID-19. In addition, this research demonstrates a marked increase in the effectiveness of a CIRED analysis, when the life cycle of a CIRED, the involved stakeholders with their own individual interests, the COVID-19 situation, and the external micro-, meso-, and macro-environments are covered comprehensively as a single entity.

show abstract

Section: Introductionmentioning

confidence: 99%

Sustainable Construction Investment, Real Estate Development, and COVID-19: A Review of Literature in the Field

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Wu, Christensen and Rehg (2009) used the Bayesian filtering approach. On the other hand, Kumari and Maan (2020) proposed a convolutional neural network (CNN) based deep learning model for spatial classification. Swadzba and Wachsmuth (2014) proposed a method introducing the gist feature vector of images with the RANSAC algorithm (RANdom SAmple Consensus).…”

Section: Literaturementioning

confidence: 99%

Automatic and Accurate Classification of Hotel Bathrooms from Images with Deep Learning

Temiz

2022

IJERAD

View full text Add to dashboard Cite

Hotel bathrooms are one of the most important places in terms of customer satisfaction, and where the most complaints are reported. To share their experiences, guests rate hotels, comment, and share images of their positive or negative ratings. An important part of the room images shared by guests is related to bathrooms. Guests tend to prove their satisfaction or dissatisfaction with the bathrooms with images in their comments. These Positive or negative comments and visuals potentially affect the prospective guests. In this study, two different versions of a deep learning algorithm were designed to classify hotel bathrooms as satisfactory (good) or unsatisfactory (bad, when any defects such as dirtiness, deficiencies, malfunctions were present) by analyzing images. The best-performer between the two models was determined as a result of a series of extensive experimental studies. The models were trained for each of 144 combinations of 5 hyper-parameter sets with a data set containing more than 11 thousand bathroom images, specially created for this study. The “HotelBath” data set was shared also with the community with this study. Four different image sizes were taken into consideration: 128, 256, 512 and 1024 pixels in both directions. The classification performances of the models were measured with several metrics. Both algorithms showed very attractive performances even with many combinations of hyper-parameters. They can classify bathroom images with very high accuracy. Suh that the top algorithm achieved an accuracy of 92.4% and an AUC (area under the curve) score of 0.967. In addition, other metrics also proved the success of the algorithm. The proposed method can allow the rapid, accurate and automatic detection of such undesired circumstances in hotel bathrooms from images. Such a detection system can allow hotel management to take necessary actions quickly to remedy such unsatisfactory cases.

show abstract

Preserving human privacy in real estate listing applications by deep learning methods

VARUL

ADIYAMAN

Bakırman

et al. 2023

Mersin Photogrammetry Journal

View full text Add to dashboard Cite

The images are important components of real estate applications on the internet to inform users. There are multiple rental and sale properties and many images of these properties on the internet and it is challenging to control the images of these real estate in terms of time, workload and cost. Considering the requirements of the problem, Deep Learning (DL), one of the Artificial Intelligence (AI) methods, offers ideal solutions. This study aims to distinguish images that contain humans using deep learning techniques. This will also aid not to violate the privacy of people according to the Law on the Protection of Personal Data in the image content used in real estate applications. For this purpose, firstly, a dataset of real estate images with and without humans called Real Estate Privacy (REP) dataset was created. The REP dataset was split into 70%, 20%, and 10% for training, validation, and testing, respectively. Secondly, the REP dataset was trained with Inceptionv3, ResNet-50, and DenseNet-169 architectures using transfer learning. Lastly, the performances of the architectures were evaluated by accuracy, precision, recall, and F1-score accuracy metrics. Experimental results indicate that the 52 epoch ResNet-50 architecture is the best for our datasets with 98.45% overall accuracy and 98.00% precision, 98.90% recall, and 98.44% F1-score. The Inceptionv3 model provided the best results on the 55th epoch with 98.27% accuracy, 97.81% precision, 98.71% recall, and 98.26% F1-score. Finally, the DenseNet-169 model produced the best results on the 47th epoch, with 97.81% accuracy, 97.09% precision, 98.52% recall, and 97.80% F1-score. Accuracy assessment shows that the highest accuracy among the three architectures was obtained with the ResNet-50 architecture This study shows that deep learning methods offer a perspective to image content control and can be used efficiently in real estate applications.

show abstract

A Deep Learning-Based Segregation of Housing Image Data for Real Estate Application

Cited by 3 publications

References 16 publications

Sustainable Construction Investment, Real Estate Development, and COVID-19: A Review of Literature in the Field

Sustainable Construction Investment, Real Estate Development, and COVID-19: A Review of Literature in the Field

Automatic and Accurate Classification of Hotel Bathrooms from Images with Deep Learning

Preserving human privacy in real estate listing applications by deep learning methods

Contact Info

Product

Resources

About