Anomaly Detection Neural Network with Dual Auto-Encoders GAN and Its Industrial Inspection Applications

Recently, researchers have been studying methods to introduce deep learning into automated optical inspection (AOI) systems to reduce labor costs. However, the integration of deep learning in the industry may encounter major challenges such as sample imbalance (defective products that only account for a small proportion). Therefore, in this study, an anomaly detection neural network, dual auto-encoder generative adversarial network (DAGAN), was developed to solve the problem of sample imbalance. With skip-connection and dual auto-encoder architecture, the proposed method exhibited excellent image reconstruction ability and training stability. Three datasets, namely public industrial detection training set, MVTec AD, with mobile phone screen glass and wood defect detection datasets, were used to verify the inspection ability of DAGAN. In addition, training with a limited amount of data was proposed to verify its detection ability. The results demonstrated that the areas under the curve (AUCs) of DAGAN were better than previous generative adversarial network-based anomaly detection models in 13 out of 17 categories in these datasets, especially in categories with high variability or noise. The maximum AUC improvement was 0.250 (toothbrush). Moreover, the proposed method exhibited better detection ability than the U-Net auto-encoder, which indicates the function of discriminator in this application. Furthermore, the proposed method had a high level of AUCs when using only a small amount of training data. DAGAN can significantly reduce the time and cost of collecting and labeling data when it is applied to industrial detection.

Download Full-text

AN AI-BASED APPROACH TO ENHANCED FRACTURE RESOLUTION IN IMAGE LOGS

10.30632/spwla-2021-0081 ◽

2021 ◽

Author(s):

James Howard ◽

◽

Joe Tracey ◽

Mike Shen ◽

Shawn Zhang ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Nearest Neighbor ◽

Rock Fracture ◽

Short Interval ◽

Acoustic Properties ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Deep Learning Neural Network ◽

Borehole Image

Borehole image logs are used to identify the presence and orientation of fractures, both natural and induced, found in reservoir intervals. The contrast in electrical or acoustic properties of the rock matrix and fluid-filled fractures is sufficiently large enough that sub-resolution features can be detected by these image logging tools. The resolution of these image logs is based on the design and operation of the tools, and generally is in the millimeter per pixel range. Hence the quantitative measurement of actual width remains problematic. An artificial intelligence (AI) -based workflow combines the statistical information obtained from a Machine-Learning (ML) segmentation process with a multiple-layer neural network that defines a Deep Learning process that enhances fractures in a borehole image. These new images allow for a more robust analysis of fracture widths, especially those that are sub-resolution. The images from a BHTV log were first segmented into rock and fluid-filled fractures using a ML-segmentation tool that applied multiple image processing filters that captured information to describe patterns in fracture-rock distribution based on nearest-neighbor behavior. The robust ML analysis was trained by users to identify these two components over a short interval in the well, and then the regression model-based coefficients applied to the remaining log. Based on the training, each pixel was assigned a probability value between 1.0 (being a fracture) and 0.0 (pure rock), with most of the pixels assigned one of these two values. Intermediate probabilities represented pixels on the edge of rock-fracture interface or the presence of one or more sub-resolution fractures within the rock. The probability matrix produced a map or image of the distribution of probabilities that determined whether a given pixel in the image was a fracture or partially filled with a fracture. The Deep Learning neural network was based on a Conditional Generative Adversarial Network (cGAN) approach where the probability map was first encoded and combined with a noise vector that acted as a seed for diverse feature generation. This combination was used to generate new images that represented the BHTV response. The second layer of the neural network, the adversarial or discriminator portion, determined whether the generated images were representative of the actual BHTV by comparing the generated images with actual images from the log and producing an output probability of whether it was real or fake. This probability was then used to train the generator and discriminator models that were then applied to the entire log. Several scenarios were run with different probability maps. The enhanced BHTV images brought out fractures observed in the core photos that were less obvious in the original BTHV log through enhanced continuity and improved resolution on fracture widths.

Download Full-text

INFRASTRUCTURE DEGRADATION AND POST-DISASTER DAMAGE DETECTION USING ANOMALY DETECTING GENERATIVE ADVERSARIAL NETWORKS

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-573-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 573-582 ◽

Cited By ~ 1

Author(s):

S. M. Tilon ◽

F. Nex ◽

D. Duarte ◽

N. Kerle ◽

G. Vosselman

Keyword(s):

Deep Learning ◽

Damage Detection ◽

Training Data ◽

Generative Adversarial Networks ◽

Generative Adversarial Network ◽

Essential Information ◽

Urban Scenes ◽

Adversarial Network ◽

Collapsed Buildings ◽

Post Disaster

Abstract. Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.

Download Full-text

Generative Adversarial Network Performance in Low-Dimensional Settings

Journal of Research of the National Institute of Standards and Technology ◽

10.6028/jres.126.008 ◽

2021 ◽

Vol 126 ◽

Author(s):

Felix Jimenez ◽

Amanda Koepke ◽

Mary Gregg ◽

Michael Frey

Keyword(s):

Neural Network ◽

Network Performance ◽

Training Data ◽

High Dimensional ◽

Generative Adversarial Network ◽

Low Dimensions ◽

Target Distribution ◽

Adversarial Network ◽

Low Dimensional ◽

And Training

A generative adversarial network (GAN) is an artificial neural network with a distinctive training architecture, designed to createexamples that faithfully reproduce a target distribution. GANs have recently had particular success in applications involvinghigh-dimensional distributions in areas such as image processing. Little work has been reported for low dimensions, where properties of GANs may be better identified and understood. We studied GAN performance in simulated low-dimensional settings, allowing us totransparently assess effects of target distribution complexity and training data sample size on GAN performance in a simpleexperiment. This experiment revealed two important forms of GAN error, tail underfilling and bridge bias, where the latter is analogousto the tunneling observed in high-dimensional GANs.

Download Full-text

Pesticide detection combining the Wasserstein generative adversarial network and the residual neural network based on terahertz spectroscopy

RSC Advances ◽

10.1039/d1ra06905e ◽

2022 ◽

Vol 12 (3) ◽

pp. 1769-1776

Author(s):

Ruizhao Yang ◽

Yun Li ◽

Binyi Qin ◽

Di Zhao ◽

Yongjin Gan ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Terahertz Spectroscopy ◽

Learning Networks ◽

Pesticide Detection ◽

Generative Adversarial Network ◽

Adversarial Network

We proposed a WGAN-ResNet method, which combines two deep learning networks, the Wasserstein generative adversarial network (WGAN) and residual neural network (ResNet), to detect carbendazim based on terahertz spectroscopy.

Download Full-text

A De Novo Molecular Generation Method Using Latent Vector Based Generative Adversarial Network

10.26434/chemrxiv.8299544.v3 ◽

2019 ◽

Cited By ~ 1

Author(s):

Oleksii Prykhodko ◽

Simon Viet Johansson ◽

Panagiotis-Christos Kotsias ◽

Josep Arús-Pous ◽

Esben Jannik Bjerrum ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

De Novo ◽

Molecular Design ◽

Chemical Space ◽

Training Set ◽

Generative Adversarial Network ◽

Adversarial Network ◽

De Novo Molecular Design ◽

Novel Structures

Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases: sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

Download Full-text

Sentiment Analysis Method based on Piecewise Convolutional Neural Network and Generative Adversarial Network

International Journal of Computers Communications & Control ◽

10.15837/ijccc.2019.1.3374 ◽

2019 ◽

Vol 14 (1) ◽

pp. 7-20 ◽

Cited By ~ 2

Author(s):

Changshun Du ◽

Lei Huang

Keyword(s):

Neural Network ◽

Sentiment Analysis ◽

Language Processing ◽

Convolution Neural Network ◽

Training Data ◽

Sentence Structure ◽

Analysis Model ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Text Sentiment Analysis

Text sentiment analysis is one of the most important tasks in the field of public opinion monitoring, service evaluation and satisfaction analysis under network environments. Compared with the traditional Natural Language Processing analysis tools, convolution neural networks can automatically learn useful features from sentences and improve the performance of the affective analysis model. However, the original convolution neural network model ignores sentence structure information which is very important for text sentiment analysis. In this paper, we add piece-wise pooling to the convolution neural network, which allows the model to obtain the sentence structure. And the main features of different sentences are extracted to analyze the emotional tendencies of the text. At the same time, the user’s feedback involves many different fields, and there is less labeled data. In order to alleviate the sparsity of the data, this paper also uses the generative adversarial network to make common feature extractions, so that the model can obtain the common features associated with emotions in different fields, and improves the model’s Generalization ability with less training data. Experiments on different datasets demonstrate the effectiveness of this method.

Download Full-text

Network Attacks Detection Methods Based on Deep Learning Techniques: A Survey

Security and Communication Networks ◽

10.1155/2020/8872923 ◽

2020 ◽

Vol 2020 ◽

pp. 1-17

Author(s):

Yirui Wu ◽

Dabao Wei ◽

Jun Feng

Keyword(s):

Neural Network ◽

Deep Learning ◽

Attack Detection ◽

Detection Methods ◽

Generative Adversarial Network ◽

Network Attacks ◽

Adversarial Network ◽

Fifth Generation ◽

Learning Techniques ◽

Benchmark Datasets

With the development of the fifth-generation networks and artificial intelligence technologies, new threats and challenges have emerged to wireless communication system, especially in cybersecurity. In this paper, we offer a review on attack detection methods involving strength of deep learning techniques. Specifically, we firstly summarize fundamental problems of network security and attack detection and introduce several successful related applications using deep learning structure. On the basis of categorization on deep learning methods, we pay special attention to attack detection methods built on different kinds of architectures, such as autoencoders, generative adversarial network, recurrent neural network, and convolutional neural network. Afterwards, we present some benchmark datasets with descriptions and compare the performance of representing approaches to show the current working state of attack detection methods with deep learning structures. Finally, we summarize this paper and discuss some ways to improve the performance of attack detection under thoughts of utilizing deep learning structures.

Download Full-text

DEEP LEARNING FRAMEWORK FOR WOVEN COMPOSITE ANALYSIS

10.12783/asc36/35816 ◽

2021 ◽

Author(s):

HAOTIAN FENG ◽

SABARINATHAN SUBRAMANIYAN ◽

PAVANA PRABHAKAR

Keyword(s):

Neural Network ◽

Mechanical Properties ◽

Woven Composite ◽

Generative Adversarial Network ◽

Element Analysis ◽

Adversarial Network ◽

Stiffness Properties ◽

High Level ◽

Weave Pattern ◽

Pattern Prediction

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG

Download Full-text

A de novo molecular generation method using latent vector based generative adversarial network

Journal of Cheminformatics ◽

10.1186/s13321-019-0397-9 ◽

2019 ◽

Vol 11 (1) ◽

Cited By ~ 24

Author(s):

Oleksii Prykhodko ◽

Simon Viet Johansson ◽

Panagiotis-Christos Kotsias ◽

Josep Arús-Pous ◽

Esben Jannik Bjerrum ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

De Novo ◽

Molecular Design ◽

Chemical Space ◽

Training Set ◽

Generative Adversarial Network ◽

Adversarial Network ◽

De Novo Molecular Design ◽

Novel Structures

AbstractDeep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

Download Full-text

INCO-GAN: Variable-Length Music Generation Method Based on Inception Model-Based Conditional GAN

Mathematics ◽

10.3390/math9040387 ◽

2021 ◽

Vol 9 (4) ◽

pp. 387

Author(s):

Shuyu Li ◽

Yunsick Sung

Keyword(s):

Neural Network ◽

Deep Learning ◽

Generative Models ◽

Variable Length ◽

Sequential Data ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Music Generation ◽

Automatic Music Generation ◽

Frequency Vectors

Deep learning has made significant progress in the field of automatic music generation. At present, the research on music generation via deep learning can be divided into two categories: predictive models and generative models. However, both categories have the same problems that need to be resolved. First, the length of the music must be determined artificially prior to generation. Second, although the convolutional neural network (CNN) is unexpectedly superior to the recurrent neural network (RNN), CNN still has several disadvantages. This paper proposes a conditional generative adversarial network approach using an inception model (INCO-GAN), which enables the generation of complete variable-length music automatically. By adding a time distribution layer that considers sequential data, CNN considers the time relationship in a manner similar to RNN. In addition, the inception model obtains richer features, which improves the quality of the generated music. In experiments conducted, the music generated by the proposed method and that by human composers were compared. High cosine similarity of up to 0.987 was achieved between the frequency vectors, indicating that the music generated by the proposed method is very similar to that created by a human composer.

Download Full-text