Artificial neuralnetworks (ANN) have become one of the most powerful machinelearning tools that cover a wide range of applications such as surveillance, video and image recognition, medical image analysis, control s...
详细信息
This paper presents algorithms, simulations, and results using machinelearning and quantum image fusion algorithms for radar and remote sensing applications. Previous efforts in the classification of synthetic apertu...
详细信息
ISBN:
(纸本)9798350304626
This paper presents algorithms, simulations, and results using machinelearning and quantum image fusion algorithms for radar and remote sensing applications. Previous efforts in the classification of synthetic aperture radar (SAR) images using quantum machinelearning provided encouraging results but, nevertheless modest accuracy. In this paper, we propose a novel quantum image fusion technique used for identifying and classifying objects obtained from C-band SAR and optical images. More specifically, we design a four-qubit quantum circuit to process the SAR image dataset. This method enhances the spectral details otherwise not seen when using the raw SAR dataset. In addition to the quantum circuit, we design deep neuralnetworks (NN) to improve classification results. The Visual Geometry Group 16 (VGG16), a convolutional neural network that is sixteen layers deep, is customized and used for classification. The merit of quantum fusion as well as the promising results in improving the overall system and the potential of lowering size, weight, power, and cost (SWaP-C) is described.
Given the recent rate of population expansion, it is anticipated that by 2050, global crop productivity will need to double. Getting this production result is significantly hampered by pests and diseases. It is essent...
详细信息
Single image reflection removal (SIRR) problem can be interpreted as a canonical blind source separation problem and is highly ill-posed. A parameter effective, fast learning and interpretable reflection removal algor...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Single image reflection removal (SIRR) problem can be interpreted as a canonical blind source separation problem and is highly ill-posed. A parameter effective, fast learning and interpretable reflection removal algorithm is essential for many vision analysis applications. In this paper, we propose a novel model-inspired and learning-based SIRR method called Deep Unfolded Reflection Removal Network (DURRNet). It combines the merits of both model-based and learning-based paradigms, leading to a more interpretable and effective deep architecture. To achieve this, we first propose a model-based optimization approach and then obtain DURRNet by unfolding an iterative step into a Unfolded Separation Block (USB) based on proximal gradient descent. Key features of DURRNet include the use of Invertible neuralnetworks to impose the transform-based exclusion prior on the basis of natural image prior, as well as a coarse-to-fine architecture to finegrain the reflection removal process. Extensive experiments on public datasets demonstrate that DURRNet achieves state-of-the-art results not only visually, quantitatively, but also effectively.
Convolutional neuralnetworks (CNNs), a deep learning application, are powerful tools particularly suited for imageprocessing and classification applications. Pooling is a major component of CNNs and significantly in...
详细信息
ISBN:
(纸本)9783031821493;9783031821509
Convolutional neuralnetworks (CNNs), a deep learning application, are powerful tools particularly suited for imageprocessing and classification applications. Pooling is a major component of CNNs and significantly influences learning. In this step, data is reduced in size through a specific algorithm or technique, resulting in the reduction of the computational load on the layers. The various pooling techniques in CNNs have specific uses, features, and effects, some desirable and others counterproductive to the training goal. Using one pooling technique can produce results that other techniques cannot. Some cases can benefit differently from different pooling techniques. This raises the question of whether combining these pooling techniques could achieve a collective positive impact, potentially leading to performance gains beyond those achievable by individual techniques used separately. A control parameter is added to optimize the selection of the pooling method or could be a weighted combination of more than one method. The results show that the presented method guarantees the same performance as a single pooling layer at least and could be improved when weighted pooling layers are involved in some datasets.
Alzheimer's Disease (AD) represents a crucial challenge in healthcare, necessitating effective diagnostic tools and therapeutic interventions. In an effort to promote early identification and intervention, this re...
详细信息
Deep learning techniques have significantly impacted fields such as imageprocessing, computer vision, and natural language processing. However, their influence on quantitative finance, particularly in option pricing,...
详细信息
ISBN:
(纸本)9798400710810
Deep learning techniques have significantly impacted fields such as imageprocessing, computer vision, and natural language processing. However, their influence on quantitative finance, particularly in option pricing, hedging, and portfolio management, has been limited. Traditional financial applications rely on rigorous mathematical models and established numerical methods like Monte Carlo and finite difference methods. However, these methods struggle with high-dimensional problems. Recent works propose using Deep neuralnetworks (DNNs) to solve high-dimensional Partial Differential Equations (PDEs) in finance, potentially overcoming the limitations of conventional techniques. Despite the recent progress, DNN methods face high computational costs, stability issues, and generally fail to meet the high accuracy requirements of the financial industry. This paper addresses these challenges. To address the high computational cost of training deep neuralnetworks for financial applications, we propose a multilevel architecture inspired by multilevel Monte Carlo methods. To enhance stability, we adopt a dynamical systems perspective and utilize the NAIS-Net architecture, which ensures global asymptotic stability. For improving accuracy, we leverage the forward and backward systems of stochastic differential equations (FBSDEs) for option pricing problems. We also provide a theoretical argument that suggests that the proposed approach is superior to Physics Informed neuralnetworks. Finally, the proposed methodology is implemented on several option pricing and xVA problems and is shown to achieve higher efficiency and accuracy, notably improving the pricing of options and xVAs by an order of magnitude over state-of-the-art methods.
Breast cancer is a relatively common cancer among gynecological cancers. Its diagnosis often relies on the pathology of cells in the lesion. The pathological diagnosis of breast cancer not only requires professionals ...
详细信息
ISBN:
(纸本)9798400716553
Breast cancer is a relatively common cancer among gynecological cancers. Its diagnosis often relies on the pathology of cells in the lesion. The pathological diagnosis of breast cancer not only requires professionals and time, but also sometimes involves subjective judgment. To address the challenges of dependence on pathologists expertise and the time-consuming nature of achieving accurate breast pathological image classification, this paper introduces an approach utilizing convolutional neuralnetworks (CNNs) for the rapid categorization of pathological images, aiming to enhance the efficiency of breast pathological image detection. And the approach enables the rapid and automatic classification of pathological images into benign and malignant groups. The methodology involves utilizing a convolutional neural network (CNN) model leveraging the Inceptionv3 architecture and transfer learning algorithm for extracting features from pathological images. Utilizing a neural network with fully connected layers and employing the SoftMax function for image classification. Additionally, the concept of image partitioning is introduced to handle high-resolution images. To achieve the ultimate classification outcome, the classification probabilities of each image block are aggregated using three algorithms: summation, product, and maximum. Experimental validation was conducted on the BreaKHis public dataset, resulting in accuracy rates surpassing 0.92 across all four magnification coefficients (40X, 100X, 200X, and 400X). It demonstrates that the proposed method effectively enhances the accuracy in classifying pathological images of breast cancer.
Accurately classifying age and gender using sound is beneficial for speaker and speech recognition as well as speech emotion classification. This is because separate acoustic models for men and women have been shown t...
详细信息
Satellite data transmission is a crucial bottleneck for Earth observation applications. To overcome this problem, we propose a novel solution that trains a neural network on board multiple satellites to compress raw d...
详细信息
ISBN:
(纸本)9798350365474
Satellite data transmission is a crucial bottleneck for Earth observation applications. To overcome this problem, we propose a novel solution that trains a neural network on board multiple satellites to compress raw data and only send down heavily compressed previews of the images while retaining the possibility of sending down selected losslessly compressed data. The neural network learns to encode and decode the data in an unsupervised fashion using distributed machinelearning. By simulating and optimizing the learning process under realistic constraints such as thermal, power and communication limitations, we demonstrate the feasibility and effectiveness of our approach. For this, we model a constellation of three satellites in a Sun-synchronous orbit. We use real raw, multispectral data from Sentinel-2 and demonstrate the feasibility on space-proven hardware for the training. Our compression method outperforms JPEG compression on different image metrics, achieving better compression ratios and image quality. We report key performance indicators of our method, such as image quality, compression ratio and benchmark training time on a Unibap ix10-100 processor. Our method has the potential to significantly increase the amount of satellite data collected that would typically be discarded (e.g., over oceans) and can potentially be extended to other applications even outside Earth observation. All code and data of the method are available online to enable rapid application of this approach.
暂无评论