The metastatic propensity of malignant primary tumors is a recurring theme when it comes to the cause of mortality in cancer. Establishing the primary site of a metastatic cancer is a significant but challenging task....
详细信息
The metastatic propensity of malignant primary tumors is a recurring theme when it comes to the cause of mortality in cancer. Establishing the primary site of a metastatic cancer is a significant but challenging task. There are ∼3% of metastatic cancer cases diagnosed as cancer of unknown primary (CUP), and the conventional diagnostic process fails to detect the primary site for 80% of CUP patients. Benefiting from the explosion of the information available from large-scale tumor DNA sequencing projects, it became favorable to predict the cancer primary sites from genomic perspective. The existing methods on the task intensively studied the mutational and oncogenic features with assists of machine learning (ML) and deep learning (DL) techniques, yet lack of development of a model architecture tailored for the mutational features. To address the gap, in this research, we aimed to develop a DL methodology specialized for the mutational data. A mutational fusion variational autoencoder (MutFusVAE) deep architecture is proposed to actualize the idea 1 . We downloaded mutational profiles meeting our criteria of 2,603 tumor samples, which get split into 2,082 training samples and 521 (20%) held-out testing samples, from the International Cancer Genome Consortium (ICGC) database. The proposed methods achieved 94% overall classification accuracy for differentiating among seven primary sites on the held-out testing set. The results show the discriminative power brought by a specialized design of deep models for the mutational data and gain insights to facilitate DL-based genomic diagnostics for cancer from a modeling view.
Long non-coding RNAs (lncRNAs) are recent listing in RNA Bioinformatics, which is getting more popular due to their important functional roles. According to the available research, lncRNAs play an essential role in mu...
详细信息
Long non-coding RNAs (lncRNAs) are recent listing in RNA Bioinformatics, which is getting more popular due to their important functional roles. According to the available research, lncRNAs play an essential role in multiple complex diseases. Determining the function of lncRNAs in diseases will help to comprehend many missing links in the disease mechanism. Predicting lncRNAdisease association (LDA) is a crucial stage in this process which is getting at most research interest nowadays. The developments in machine learning and deep learning technologies influenced recent research on LDA models. Most of the methods analyse the interactions of lncRNA with other molecules such as microRNA (miRNA), messenger RNA(mRNA), and proteins. Deep learning models, specifically from autoencoder classes, used extensively in unsupervised learning of features from these associations. This research paper proposes a denoising autoencoder (DAE) based LDA prediction approach. The proposed model uses DAE to learn lncRNA-disease representations from multiple biological networks such as lncRNA-miRNA, miRNA-disease, and disease-lncRNA interactions. The experiments show that the model outperforms other state-of-the-art LDA models concerning the area under the ROC curve (AUC-ROC, 0.94) and the area under precision-recall (AUPR, 0.9592).
autoencoders have been used widely for diagnosing devices, for example, faults in rotating machinery. However, autoencoder-based approaches lack explainability for their results and can be hard to tune. In this articl...
详细信息
autoencoders have been used widely for diagnosing devices, for example, faults in rotating machinery. However, autoencoder-based approaches lack explainability for their results and can be hard to tune. In this article, we propose an explainable method for applying autoencoders for diagnosis, where we use a metric that maximizes the diagnostics accuracy. Since an autoencoder projects the input into a reduced subspace (the code), we define a theoretically well-understood approach, the subspace principal angle, to define a metric over the possible fault labels. We show how this approach can be used for both single-device diagnostics (e.g., faults in rotating machinery) and complex (multi-device) dynamical systems. We empirically validate the theoretical claims using multiple autoencoder architectures.
The framework of locally weighted learning (LWL) has established itself as a popular tool for developing nonlinear soft sensors in process industries. For LWL-based soft sensors, the key factor for achieving high perf...
详细信息
The framework of locally weighted learning (LWL) has established itself as a popular tool for developing nonlinear soft sensors in process industries. For LWL-based soft sensors, the key factor for achieving high performance is to construct accurate localized models. To this end, in this paper a nonlinear local model training algorithm called nonlinear Bayesian weighted regression (NBWR) is proposed. In the NBWR, the nonlinear features of process data are first extracted by the autoencoder;then, given a query sample a local dataset is selected on the feature space and a fully Bayesian regression model with differentiated sample weights is developed. The benefits of this approach, which include better consistency of correlation, stronger abilities to deal with process nonlinearities and uncertainties, overfitting and numerical issues, lead to superior performance. The NBWR is used for developing a soft sensor under the LWL framework, and a real-world industrial process is used to evaluate the performance of the NBWR-based soft sensor. The experimental results demonstrate that the proposed method outperforms several benchmarking soft sensing approaches. (C) 2020 ISA. Published by Elsevier Ltd. All rights reserved.
Image restoration, which is the process of denoising noisy images in order to recover their latent clean images, has been frequently addressed. The importance of this field resides in the impact of noisy images on the...
详细信息
ISBN:
(纸本)9780738133669
Image restoration, which is the process of denoising noisy images in order to recover their latent clean images, has been frequently addressed. The importance of this field resides in the impact of noisy images on the performance of computer vision systems. In this work, a deep autoencoder neural network architecture is proposed to denoise images affected by Gaussian noise. The performance of the system is enhanced by using a test time augmentation scheme. Experiments have been carried out by considering different levels of Gaussian noise. Results demonstrate the suitability of the proposed methodology in order to enhance the quality of the image restoration process in images affected by Gaussian noise.
Background: Magnetic resonance imaging (MRI) image retrieval holds significant value in clinical contexts and medical education due to the shortcomings of traditional methods: slow speed, low accuracy, and limited lea...
详细信息
Background: Magnetic resonance imaging (MRI) image retrieval holds significant value in clinical contexts and medical education due to the shortcomings of traditional methods: slow speed, low accuracy, and limited learning capabilities. Improving this retrieval process is crucial for enhancing medical diagnostics and educational outcomes. Efforts to overcome these challenges are paramount for advancing healthcare practices and educational methodologies. Method: This study explores the use of autoencoders in deep learning to effectively retrieve MRI images from databases for medical education, emphasizing the model's capacity to be trained with a small amount of labeled data. This work intends to improve the MRI image retrieval process by utilizing autoencoders, demonstrating the promise of deep learning technologies in medical image analysis without the need for large labeled datasets for training. Results: Research has demonstrated the exceptional advantages of this method for MRI image retrieval tasks, with an average accuracy of 99.09%. This indicates that the technique performs exceptionally well in this particular domain and is very effective and reliable in extracting MRI images. Conclusions: This innovative approach can improve the archival management and diagnostic functions of medical images, providing an efficient and reliable solution for MRI image retrieval. It not only helps doctors with clinical diagnosis and medical teaching and research more quickly but also suggests a convenient solution for file management related to medical images.
Hybrid beamforming (HB) is a promising technology for the millimeter-wave (mmWave) massive multiple-input-multiple-output (MIMO) system, which supplies high data capacity with low complexity for next-generation commun...
详细信息
Hybrid beamforming (HB) is a promising technology for the millimeter-wave (mmWave) massive multiple-input-multiple-output (MIMO) system, which supplies high data capacity with low complexity for next-generation communication systems. However, the joint design of digital and analog beamformer is a non-convex optimization problem due to the hardware constraints of analog shifter arrays. To address this issue, we proposed an intelligent HB design method based on the autoencoder (AE) neural network in this paper. By mapping the HB system to an AE neural network, the solving of the original non-convex optimization problem is converted to the neural network training process. The beamformer and combiner can be automatically formulated by the training process of the neural network. We also discuss the chosen of hyper-parameter and provide a guideline for the AE neural network HB design. With the strong representation ability of the deep neural network, the proposed intelligent HB exhibits superior performance in terms of bit error rate (BER).
In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disenta...
详细信息
ISBN:
(纸本)9781728176055
In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches. We further demonstrate an increased robustness of the content representation against a train-test mismatch compared to spectral features, when used for phone recognition.
Malware is becoming an effective support tool not only for professional hackers but also for amateur ones. Due to the support of free malware generators, anyone can easily create various types of malicious code. The i...
详细信息
Malware is becoming an effective support tool not only for professional hackers but also for amateur ones. Due to the support of free malware generators, anyone can easily create various types of malicious code. The increasing amount of novel malware is a daily global problem. Current machine learning-based methods, especially image-based malware classification approaches, are attracting significant attention because of their accuracy and computational cost. Convolutional Neural Networks are widely applied in malware classification;however, CNN needs a deep architecture and GPUs for parallel processing to achieve high performance. By contrast, a simple model merely contained a Multilayer Perceptron called MLP-mixer with fewer hyperparameters that can run in various environments without GPUs and is not too far behind CNN in terms of performance. In this study, we try applying an autoencoder (AE) to improve the performance of the MLP-mixer. AE is widely used in several applications as dimensionality reduction to filter out the noise and identify crucial elements of the input data. Taking this advantage from AE, we propose a lightweight ensemble architecture by combining a customizer MLP-mixer and autoencoder to refine features extracted from the MLP-mixer with the encoder-decoder architecture of the autoencoder. We achieve overperformance through various experiments compared to other cutting-edge techniques using Malimg and Malheur datasets which contain 9939 (25 malware families) and 3133 variant samples (24 malware families).
In this paper, we propose an autoencoder-based missing data completion method for multi-channel acoustic scene classification (ASC). It has been reported that many deep-learning-based ASC methods using multi-channel s...
详细信息
In this paper, we propose an autoencoder-based missing data completion method for multi-channel acoustic scene classification (ASC). It has been reported that many deep-learning-based ASC methods using multi-channel signals have robust performance. The advantage of using multi-channel data is the capture of spatial and frequency information. However, when there is missing data in multi-channel signals, the classification performance declines significantly. We focus on completing the missing data by using an autoencoder as the preprocessor of ASC models. Since positional relationships between multi-channel microphones are modeled in the latent space of the proposed autoencoder, missing information is reconstructed via the latent space from the multi-channel input, including missing data. In an experiment, the missing data is completed by using the proposed autoencoder, and the accuracy of ASC systems is improved by using the completed multi-channel signals.
暂无评论