The novel coronavirus 2019 (COVID-19) has rapidly spread, evolving into a global epidemic. Existing pharmaceutical techniques and diagnostic tests, such as reverse transcription–polymerase chain reaction (RT-PCR) and...
详细信息
In hazy weather, the image in the scene suffers from noise which makes them less visible and to detect an object in hazy weather becomes a challenging task in computer vision. To have noise free image, many researcher...
详细信息
In hazy weather, the image in the scene suffers from noise which makes them less visible and to detect an object in hazy weather becomes a challenging task in computer vision. To have noise free image, many researchers have devised denoising techniques for enhancing visibility of images. Denoising is to remove the random variation from images and preserve the image features. As hazy images cause lots of visibility issues, this paper proposes removing haze and enhancing visibility of bad weather images with improved efficacy using an unsupervised neural network autoencoder that compress the data using machine learning and learns through Convolutional Neural Network (CNN). It has been observed that to have increased accuracy, the image classification and analysis is most effective using CNN. An end-to-end decoder training model is used to achieve the quality images. Further, various optimizers are compared to have better accuracy. The quality of images identified by estimation of performance such as RMSE and PSNR values are evaluated over single image and images from existing datasets and our own dataset. In the proposed method, RMSE value comes out to be 0.0373 for image from BSD500 dataset for specific image compared with other state of art approaches. The proposed model is intended in addition to other active, or progressive methods and the suggested method exceeds. The performance quality of images is explored applying measurable metrics. The images are taken from the datasets O-Haze, I-Haze, BSDS500, RESIDE, FRIDA and some from google.
With each new generation of mobile communication, the mobile traffic data are increasing exponentially. However, there are limitations to the capacity of base stations. As a result, it become necessary to manage mobil...
详细信息
With substantial recent developments in aviation technologies, unmanned aerial vehicles (UAVs) are becoming increasingly integrated in commercial and military operations internationally. Research on the applications o...
详细信息
With substantial recent developments in aviation technologies, unmanned aerial vehicles (UAVs) are becoming increasingly integrated in commercial and military operations internationally. Research on the applications of aircraft data is essential in improving safety, reducing operational costs, and developing the next frontier of aerial technology. Having an outlier detection system that can accurately identify anomalous behavior in aircraft is crucial for these reasons. This article proposes a system incorporating a long short-term memory (LSTM) deep learning autoencoder-based method with a novel dynamic thresholding algorithm and weighted loss function for anomaly detection of a UAV dataset, in order to contribute to the ongoing efforts that leverage innovations in machine learning and data analysis within the aviation industry. The dynamic thresholding and weighted loss functions showed promising improvements to the standard static thresholding method, both in accuracy-related performance metrics and in speed of true fault detection.
Reconstruction of gene regulatory networks from gene expression profile have been an important challenge task in system biology for decades. Recently, with the advancement of single cell RNA-seq technology, the studie...
详细信息
Metamodel-assisted optimization is a frequently applied approach for structural design optimization problems. Here, a data-driven metamodel approximates the computationally expensive simulation results of first princi...
详细信息
Metamodel-assisted optimization is a frequently applied approach for structural design optimization problems. Here, a data-driven metamodel approximates the computationally expensive simulation results of first principle models, e.g., finite element analyses. A significant drawback of typical metamodels is the limited amount of information that can be predicted due to their generally low-dimensional model output. Consequently, the metamodel usually does not predict the distribution of the desired quantity. This work presents a metamodel approach capable of predicting the spatial and temporal distribution of quantities for structural processes. This increases the modeling capability and makes more information available for the optimization. The autoencoder compresses the spatial distribution into a couple of features. The proposed methodology is applied to a three-stage forming process.
The timely and quantitative evaluation of the degradation is crucial for traction inverter systems in railway applications. The implementation in the industry is impeded by two major challenges including the varying o...
详细信息
In the context of discrete-event systems (DES), the terms detection and diagnosis refer to two distinct stages of handling faults and anomalies. Both steps are critical for ensuring the reliable and safe operation of ...
详细信息
In the context of discrete-event systems (DES), the terms detection and diagnosis refer to two distinct stages of handling faults and anomalies. Both steps are critical for ensuring the reliable and safe operation of complex systems. In this paper, we propose the use of autoencoders for fault detection in an automated production system with sensors and actuators delivering discrete binary signals that can be modeled as DES. We train an autoencoder exclusively on data representing normal behavior. The model learns to encode typical patterns and reconstruct input data with low loss. A predetermined threshold, determined by the characteristics of the training data, is set for the reconstruction error. During normal behavior, the autoencoder is expected to achieve low reconstruction error below this threshold. When a fault occurs, the autoencoder strives to accurately reconstruct faulty data, leading to a higher error. The detection of a reconstruction error exceeding the threshold signals a potential fault in the system. The results of applying our method to the Factory IO software sorting system demonstrate the significant contribution and the interest of this method for detecting faults.
By using machine learning algorithms, banks and other lending institutions can construct intelligent risk control models for loan businesses, which helps to overcome the disadvantages of traditional evaluation methods...
详细信息
By using machine learning algorithms, banks and other lending institutions can construct intelligent risk control models for loan businesses, which helps to overcome the disadvantages of traditional evaluation methods, such as low efficiency and excessive reliance on the subjective judgment of auditors. However, in the practical evaluation process, it is inevitable to encounter data with missing credit characteristics. Therefore, filling in the missing characteristics is crucial for the training process of those machine learning algorithms, especially when applied to rural banks with little credit data. In this work, we proposed an autoencoder-based algorithm that can use the correlation between data to restore the missing data items in the features. Also, we selected several open-source datasets (German Credit Data, Give Me Some Credit on the Kaggle platform, etc.) as the training and test dataset to verify the algorithm. The comparison results show that our model outperforms the others, although the performance of the autoencoder-based feature restorer decreases significantly when the feature missing ratio exceeds 70%.
Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. This study proposes an unsupervised method tha...
详细信息
Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. This study proposes an unsupervised method that effectively addresses this challenge by achieving both accurate defect detection and a high-quality normal background reconstruction without noise. We propose an adaptive weighted structural similarity (AW-SSIM) loss for focused feature learning. AW-SSIM improves structural similarity (SSIM) loss by assigning different weights to its sub-functions of luminance, contrast, and structure based on their relative importance for a specific training sample. Moreover, it dynamically adjusts the Gaussian window's standard deviation (sigma) during loss calculation to balance noise reduction and detail preservation. An artificial defect generation algorithm (ADGA) is proposed to generate an artificial defect closely resembling real ones. We use a two-stage training strategy. In the first stage, the model trains only on normal samples using AW-SSIM loss, allowing it to learn robust representations of normal features. In the second stage of training, the weights obtained from the first stage are used to train the model on both normal and artificially defective training samples. Additionally, the second stage employs a combined learned Perceptual Image Patch Similarity (LPIPS) and AW-SSIM loss. The combined loss helps the model in achieving high-quality normal background reconstruction while maintaining accurate defect detection. Extensive experimental results demonstrate that our proposed method achieves a state-of-the-art defect detection accuracy. The proposed method achieved an average area under the receiver operating characteristic curve (AuROC) of 97.69% on six samples from the MVTec anomaly detection dataset.
暂无评论