Data augmentation using a variational autoencoder for estimating property prices

2021 ◽  
Vol 39 (3) ◽  
pp. 408-418 ◽  
Author(s):  
Changro Lee
Keyword(s):  
Deep Learning ◽  
South Korea ◽  
Data Augmentation ◽  
Model Performance ◽  
Content Type ◽  
Original Dataset ◽  
Learning Techniques ◽  
Variational Autoencoder ◽  
Price Estimation

PurposePrior studies on the application of deep-learning techniques have focused on enhancing computation algorithms. However, the amount of data is also a key element when attempting to achieve a goal using a quantitative approach, which is often underestimated in practice. The problem of sparse sales data is well known in the valuation of commercial properties. This study aims to expand the limited data available to exploit the capability inherent in deep learning techniques.Design/methodology/approachThe deep learning approach is used. Seoul, the capital of South Korea is selected as a case study area. Second, data augmentation is performed for properties with low trade volume in the market using a variational autoencoder (VAE), which is a generative deep learning technique. Third, the generated samples are added into the original dataset of commercial properties to alleviate data insufficiency. Finally, the accuracy of the price estimation is analyzed for the original and augmented datasets to assess the model performance.FindingsThe results using the sales datasets of commercial properties in Seoul, South Korea as a case study show that the augmented dataset by a VAE consistently shows higher accuracy of price estimation for all 30 trials, and the capabilities inherent in deep learning techniques can be fully exploited, promoting the rapid adoption of artificial intelligence skills in the real estate industry.Originality/valueAlthough deep learning-based algorithms are gaining popularity, they are likely to show limited performance when data are insufficient. This study suggests an alternative approach to overcome the lack of data problem in property valuation.

CID: Categorical Influencer Detection on microtext-based social media

2020 ◽  
Vol 44 (5) ◽  
pp. 1027-1055
Author(s):  
Thanh-Tho Quan ◽  
Duc-Trung Mai ◽  
Thanh-Duy Tran
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Learning Approaches ◽  
Content Type ◽  
Modeling Process ◽  
Variational Autoencoder ◽  
Media Channels

PurposeThis paper proposes an approach to identify categorical influencers (i.e. influencers is the person who is active in the targeted categories) in social media channels. Categorical influencers are important for media marketing but to automatically detect them remains a challenge.Design/methodology/approachWe deployed the emerging deep learning approaches. Precisely, we used word embedding to encode semantic information of words occurring in the common microtext of social media and used variational autoencoder (VAE) to approximate the topic modeling process, through which the active categories of influencers are automatically detected. We developed a system known as Categorical Influencer Detection (CID) to realize those ideas.FindingsThe approach of using VAE to simulate the Latent Dirichlet Allocation (LDA) process can effectively handle the task of topic modeling on the vast dataset of microtext on social media channels.Research limitations/implicationsThis work has two major contributions. The first one is the detection of topics on microtexts using deep learning approach. The second is the identification of categorical influencers in social media.Practical implicationsThis work can help brands to do digital marketing on social media effectively by approaching appropriate influencers. A real case study is given to illustrate it.Originality/valueIn this paper, we discuss an approach to automatically identify the active categories of influencers by performing topic detection from the microtext related to the influencers in social media channels. To do so, we use deep learning to approximate the topic modeling process of the conventional approaches (such as LDA).

scholarly journals Hypertrophic Cardiomyopathy Diagnosis Based on Cardiovascular Magnetic Resonance Using Deep Learning Techniques

2021 ◽  
Author(s):  
Danial Sharifrazi ◽  
Roohallah Alizadehsani ◽  
Navid Hoseini Izadi ◽  
Mohamad Roshanzamir ◽  
Afshin Shoeibi ◽  
...  
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Deep Learning ◽  
Hypertrophic Cardiomyopathy ◽  
Magnetic Resonance ◽  
Error Rate ◽  
Data Augmentation ◽  
Performance Metrics ◽  
Original Dataset ◽  
Learning Techniques ◽  
Method Accuracy

Abstract Hypertrophic cardiomyopathy (HCM) can lead to serious cardiac problems. HCM is often diagnosed by an expert using cardiovascular magnetic resonance (CMR) images obtained from patients. In this research, we aimed to develop a deep learning technique to automate HCM diagnosis. CMR images of 37421 healthy and 21846 HCM patients were obtained during two years. Images obtained from female patients form 53% of the collected dataset. The mean and standard deviation of the dataset patients’ age are 48.2 and 19.5 years, respectively. Three experts inspected images and determined whether a case has HCM or not. New data augmentation was used to generate new images by employing color filtering on the existing ones. To classify the augmented images, we used a deep convolutional neural network (CNN). To the best of our knowledge, this is the first time CNN is used for HCM diagnosis. We designed our CNN from scratch to reach acceptable diagnosis accuracy. Comparing the designed algorithm output with the experts’ opinions, the method could achieve accuracy of 95.23%, recall of 97.90%, and specificity of 93.06% on the original dataset. The same performance metrics for the designed algorithm on the augmented dataset were 98.53%, 98.70%, and 95.21%, respectively. We have also experimented with different optimizers (e.g. Adadelta and Adagrad) and other data augmentation methods (e.g. height shift and rotation) to further evaluate the proposed method. Using our data augmentation method, accuracy of 98.53% were achieved which is higher than the best accuracy (95.83%) obtained by the other data augmentation methods which have been evaluated. The upper bound on difference between true error rate and empirical error rate of the proposed method has also been provided in order to present better performance analysis. The advantages of employing the proposed method are elimination of contrast agent and its complications, decreased CMR examination time, lower costs for patients and cardiac imaging centers.

Data Augmentation Using GANs for 3D Applications

2020 ◽  
pp. 229-269
Author(s):  
Ioannis Maniadis ◽  
Vassilis Solachidis ◽  
Nicholas Vretos ◽  
Petros Daras
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Data Availability ◽  
Generative Adversarial Networks ◽  
Property A ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Learning Techniques ◽  
The Subject ◽  
3D Applications

Modern deep learning techniques have proven that they have the capacity to be successful in a wide area of domains and tasks, including applications related to 3D and 2D images. However, their quality depends on the quality and quantity of the data with which models are trained. As the capacity of deep learning models increases, data availability becomes the most significant. To counter this issue, various techniques are utilized, including data augmentation, which refers to the practice of expanding the original dataset with artificially created samples. One approach that has been found is the generative adversarial networks (GANs), which, unlike other domain-agnostic transformation-based methods, can produce diverse samples that belong to a given data distribution. Taking advantage of this property, a multitude of GAN architectures has been leveraged for data augmentation applications. The subject of this chapter is to review and organize implementations of this approach on 3D and 2D imagery, examine the methods that were used, and survey the areas in which they were applied.

scholarly journals Deep Learning for Laryngopharyngeal Reflux Diagnosis

2021 ◽  
Vol 11 (11) ◽  
pp. 4753
Author(s):  
Gen Ye ◽  
Chen Du ◽  
Tong Lin ◽  
Yan Yan ◽  
Jack Jiang
Keyword(s):  
Deep Learning ◽  
Speech Processing ◽  
Data Augmentation ◽  
Laryngopharyngeal Reflux ◽  
Ph Monitoring ◽  
Binary Classification ◽  
Classification Problem ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Auc Value

(1) Background: Deep learning has become ubiquitous due to its impressive performance in various domains, such as varied as computer vision, natural language and speech processing, and game-playing. In this work, we investigated the performance of recent deep learning approaches on the laryngopharyngeal reflux (LPR) diagnosis task. (2) Methods: Our dataset is composed of 114 subjects with 37 pH-positive cases and 77 control cases. In contrast to prior work based on either reflux finding score (RFS) or pH monitoring, we directly take laryngoscope images as inputs to neural networks, as laryngoscopy is the most common and simple diagnostic method. The diagnosis task is formulated as a binary classification problem. We first tested a powerful backbone network that incorporates residual modules, attention mechanism and data augmentation. Furthermore, recent methods in transfer learning and few-shot learning were investigated. (3) Results: On our dataset, the performance is the best test classification accuracy is 73.4%, while the best AUC value is 76.2%. (4) Conclusions: This study demonstrates that deep learning techniques can be applied to classify LPR images automatically. Although the number of pH-positive images used for training is limited, deep network can still be capable of learning discriminant features with the advantage of technique.

A method of locating the 3D centers of retroreflectors based on deep learning

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
BinBin Zhang ◽  
Fumin Zhang ◽  
Xinghua Qu
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Measurement Techniques ◽  
Recognition Rate ◽  
Detection Algorithm ◽  
Large Field ◽  
Small Scale ◽  
Data Set ◽  
Content Type ◽  
Ellipse Detection

Purpose Laser-based measurement techniques offer various advantages over conventional measurement techniques, such as no-destructive, no-contact, fast and long measuring distance. In cooperative laser ranging systems, it’s crucial to extract center coordinates of retroreflectors to accomplish automatic measurement. To solve this problem, this paper aims to propose a novel method. Design/methodology/approach We propose a method using Mask RCNN (Region Convolutional Neural Network), with ResNet101 (Residual Network 101) and FPN (Feature Pyramid Network) as the backbone, to localize retroreflectors, realizing automatic recognition in different backgrounds. Compared with two other deep learning algorithms, experiments show that the recognition rate of Mask RCNN is better especially for small-scale targets. Based on this, an ellipse detection algorithm is introduced to obtain the ellipses of retroreflectors from recognized target areas. The center coordinates of retroreflectors in the camera coordinate system are obtained by using a mathematics method. Findings To verify the accuracy of this method, an experiment was carried out: the distance between two retroreflectors with a known distance of 1,000.109 mm was measured, with 2.596 mm root-mean-squar error, meeting the requirements of the coarse location of retroreflectors. Research limitations/implications The research limitations/implications are as follows: (i) As the data set only has 200 pictures, although we have used some data augmentation methods such as rotating, mirroring and cropping, there is still room for improvement in the generalization ability of detection. (ii) The ellipse detection algorithm needs to work in relatively dark conditions, as the retroreflector is made of stainless steel, which easily reflects light. Originality/value The originality/value of the article lies in being able to obtain center coordinates of multiple retroreflectors automatically even in a cluttered background; being able to recognize retroreflectors with different sizes, especially for small targets; meeting the recognition requirement of multiple targets in a large field of view and obtaining 3 D centers of targets by monocular model-based vision.

Intelligent ubiquitous computing model for energy optimization of cloud IOTs in sensor networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Deepa S.N.
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Energy Level ◽  
Computational Model ◽  
Ubiquitous Computing ◽  
Sensor Network ◽  
Research Study ◽  
Content Type ◽  
Computing Model ◽  
Learning Techniques

Purpose Limitations encountered with the models developed in the previous studies had occurrences of global minima; due to which this study developed a new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization. Ubiquitous machine learning computational model process performs training in a better way than regular supervised learning or unsupervised learning computational models with deep learning techniques, resulting in better learning and optimization for the considered problem domain of cloud-based internet-of-things (IOTs). This study aims to improve the network quality and improve the data accuracy rate during the network transmission process using the developed ubiquitous deep learning computational model. Design/methodology/approach In this research study, a novel intelligent ubiquitous machine learning computational model is designed and modelled to maintain the optimal energy level of cloud IOTs in sensor network domains. A new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization is developed. A new unified deterministic sine-cosine algorithm has been developed in this study for parameter optimization of weight factors in the ubiquitous machine learning model. Findings The newly developed ubiquitous model is used for finding network energy and performing its optimization in the considered sensor network model. At the time of progressive simulation, residual energy, network overhead, end-to-end delay, network lifetime and a number of live nodes are evaluated. It is elucidated from the results attained, that the ubiquitous deep learning model resulted in better metrics based on its appropriate cluster selection and minimized route selection mechanism. Research limitations/implications In this research study, a novel ubiquitous computing model derived from a new optimization algorithm called a unified deterministic sine-cosine algorithm and deep learning technique was derived and applied for maintaining the optimal energy level of cloud IOTs in sensor networks. The deterministic levy flight concept is applied for developing the new optimization technique and this tends to determine the parametric weight values for the deep learning model. The ubiquitous deep learning model is designed with auto-encoders and decoders and their corresponding layers weights are determined for optimal values with the optimization algorithm. The modelled ubiquitous deep learning approach was applied in this study to determine the network energy consumption rate and thereby optimize the energy level by increasing the lifetime of the sensor network model considered. For all the considered network metrics, the ubiquitous computing model has proved to be effective and versatile than previous approaches from early research studies. Practical implications The developed ubiquitous computing model with deep learning techniques can be applied for any type of cloud-assisted IOTs in respect of wireless sensor networks, ad hoc networks, radio access technology networks, heterogeneous networks, etc. Practically, the developed model facilitates computing the optimal energy level of the cloud IOTs for any considered network models and this helps in maintaining a better network lifetime and reducing the end-to-end delay of the networks. Social implications The social implication of the proposed research study is that it helps in reducing energy consumption and increases the network lifetime of the cloud IOT based sensor network models. This approach helps the people in large to have a better transmission rate with minimized energy consumption and also reduces the delay in transmission. Originality/value In this research study, the network optimization of cloud-assisted IOTs of sensor network models is modelled and analysed using machine learning models as a kind of ubiquitous computing system. Ubiquitous computing models with machine learning techniques develop intelligent systems and enhances the users to make better and faster decisions. In the communication domain, the use of predictive and optimization models created with machine learning accelerates new ways to determine solutions to problems. Considering the importance of learning techniques, the ubiquitous computing model is designed based on a deep learning strategy and the learning mechanism adapts itself to attain a better network optimization model.

Artificial intelligence exploitation in facility management using deep learning

2020 ◽  
Vol 20 (4) ◽  
pp. 609-624
Author(s):  
Mohamed Marzouk ◽  
Mohamed Zaher
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Life Cycle Cost ◽  
Facility Management ◽  
Support Vector ◽  
Maintenance Costs ◽  
Content Type ◽  
Protection Systems ◽  
Future Work

Purpose This paper aims to apply a methodology that is capable to classify and localize mechanical, electrical and plumbing (MEP) elements to assist facility managers. Furthermore, it assists in decreasing the technical complexity and sophistication of different systems to the facility management (FM) team. Design/methodology/approach This research exploits artificial intelligence (AI) in FM operations through proposing a new system that uses a deep learning pre-trained model for transfer learning. The model can identify new MEP elements through image classification with a deep convolutional neural network using a support vector machine (SVM) technique under supervised learning. Also, an expert system is developed and integrated with an Android application to the proposed system to identify the required maintenance for the identified elements. FM team can reach the identified assets with bluetooth tracker devices to perform the required maintenance. Findings The proposed system aids facility managers in their tasks and decreases the maintenance costs of facilities by maintaining, upgrading, operating assets cost-effectively using the proposed system. Research limitations/implications The paper considers three fire protection systems for proactive maintenance, where other structural or architectural systems can also significantly affect the level of service and cost expensive repairs and maintenance. Also, the proposed system relies on different platforms that required to be consolidated for facility technicians and managers end-users. Therefore, the authors will consider these limitations and expand the study as a case study in future work. Originality/value This paper assists in a proactive manner to decrease the lack of knowledge of the required maintenance to MEP elements that leads to a lower life cycle cost. These MEP elements have a big share in the operation and maintenance costs of building facilities.

Deep learning-based approach for segmentation of glioma sub-regions in MRI

2020 ◽  
Vol 13 (4) ◽  
pp. 389-406
Author(s):  
Jiten Chaudhary ◽  
Rajneesh Rani ◽  
Aman Kamboj
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Data Augmentation ◽  
Treatment Plan ◽  
Superior Performance ◽  
Content Type ◽  
Proposed Model ◽  
Life Threatening ◽  
Tumor Region ◽  
Magnetic Resonance Imaging Mri

PurposeBrain tumor is one of the most dangerous and life-threatening disease. In order to decide the type of tumor, devising a treatment plan and estimating the overall survival time of the patient, accurate segmentation of tumor region from images is extremely important. The process of manual segmentation is very time-consuming and prone to errors; therefore, this paper aims to provide a deep learning based method, that automatically segment the tumor region from MR images.Design/methodology/approachIn this paper, the authors propose a deep neural network for automatic brain tumor (Glioma) segmentation. Intensity normalization and data augmentation have been incorporated as pre-processing steps for the images. The proposed model is trained on multichannel magnetic resonance imaging (MRI) images. The model outputs high-resolution segmentations of brain tumor regions in the input images.FindingsThe proposed model is evaluated on benchmark BRATS 2013 dataset. To evaluate the performance, the authors have used Dice score, sensitivity and positive predictive value (PPV). The superior performance of the proposed model is validated by training very popular UNet model in the similar conditions. The results indicate that proposed model has obtained promising results and is effective for segmentation of Glioma regions in MRI at a clinical level.Practical implicationsThe model can be used by doctors to identify the exact location of the tumorous region.Originality/valueThe proposed model is an improvement to the UNet model. The model has fewer layers and a smaller number of parameters in comparison to the UNet model. This helps the network to train over databases with fewer images and gives superior results. Moreover, the information of bottleneck feature learned by the network has been fused with skip connection path to enrich the feature map.

scholarly journals Image editing-based data augmentation for illumination-insensitive background subtraction

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Dimitrios Sakkos ◽  
Edmond S. L. Ho ◽  
Hubert P. H. Shum ◽  
Garry Elvin
Keyword(s):  
Deep Learning ◽  
Pilot Study ◽  
Background Subtraction ◽  
Data Augmentation ◽  
Point Of View ◽  
Content Type ◽  
Illumination Changes ◽  
Image Appearance ◽  
Using Data ◽  
Limited Training Samples

PurposeA core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In our pilot study published in, Sakkos:SKIMA 2019, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly but also features semantic transformations of illumination which enhance the generalisation of the model.Design/methodology/approachIn our pilot study published in SKIMA 2019, the proposed framework successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. In this paper, we further enhance the data augmentation framework by proposing new variations in image appearance both locally and globally.FindingsExperimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place.Originality/valueSuch data augmentation allows us to effectively train an illumination-invariant deep learning model for BGS. We further propose a post-processing method that removes noise from the output binary map of segmentation, resulting in a cleaner, more accurate segmentation map that can generalise to multiple scenes of different conditions. We show that it is possible to train deep learning models even with very limited training samples. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation

scholarly journals Automatic Post-Disaster Damage Mapping Using Deep-Learning Techniques for Change Detection: Case Study of the Tohoku Tsunami

2019 ◽  
Vol 11 (9) ◽  
pp. 1123 ◽  
Author(s):  
Jérémie Sublime ◽  
Ekaterina Kalinicheva
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Machine Learning Methods ◽  
Learning Techniques ◽  
Before And After ◽  
Damage Mapping ◽  
Tohoku Tsunami ◽  
Post Disaster ◽  
Speed Of Analysis

Post-disaster damage mapping is an essential task following tragic events such as hurricanes, earthquakes, and tsunamis. It is also a time-consuming and risky task that still often requires the sending of experts on the ground to meticulously map and assess the damages. Presently, the increasing number of remote-sensing satellites taking pictures of Earth on a regular basis with programs such as Sentinel, ASTER, or Landsat makes it easy to acquire almost in real time images from areas struck by a disaster before and after it hits. While the manual study of such images is also a tedious task, progress in artificial intelligence and in particular deep-learning techniques makes it possible to analyze such images to quickly detect areas that have been flooded or destroyed. From there, it is possible to evaluate both the extent and the severity of the damages. In this paper, we present a state-of-the-art deep-learning approach for change detection applied to satellite images taken before and after the Tohoku tsunami of 2011. We compare our approach with other machine-learning methods and show that our approach is superior to existing techniques due to its unsupervised nature, good performance, and relative speed of analysis.

Sign in / Sign up

Export Citation Format

Share Document