The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitatio...
详细信息
The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitations of traditional analysis methods. In this study, we present a machine learning framework designed to reveal obscured phonon dynamics from powder spectra. Using a variational autoencoder, we obtain a disentangled latent representation of spectra and successfully extract force constants for reconstructing phonon dispersions. Notably, our model demonstrates effective applicability to experimental data even when trained exclusively on physics-based simulations. The fine-tuning with experimental spectra further mitigates issues arising from domain shift. Analysis of latent space underscores the model's versatility and generalizability, affirming its suitability for complex system applications. Furthermore, our framework's two-stage design is promising for developing a universal pre-trained feature extractor. This approach has the potential to revolutionize neutron measurements of phonon dynamics, offering researchers a potent tool to decipher intricate spectra and gain valuable insights into the intrinsic physics of materials.
To address the class imbalance issue in network intrusion detection, which degrades performance of intrusion detection models, this paper proposes a novel generative model called VAE-WACGAN to generate minority class ...
详细信息
To address the class imbalance issue in network intrusion detection, which degrades performance of intrusion detection models, this paper proposes a novel generative model called VAE-WACGAN to generate minority class samples and balance the dataset. This model extends the variational autoencoder Generative Adversarial Network (VAEGAN) by integrating key features from the Auxiliary Classifier Generative Adversarial Network (ACGAN) and the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP). These enhancements significantly improve both the quality of generated samples and the stability of the training process. By utilizing the VAE-WACGAN model to oversample anomalous data, more realistic synthetic anomalies that closely mirror the actual network traffic distribution can be generated. This approach effectively balances the network traffic dataset and enhances the overall performance of the intrusion detection model. Experimental validation was conducted using two widely utilized intrusion detection datasets, UNSW-NB15 and CIC-IDS2017. The results demonstrate that the VAE-WACGAN method effectively enhances the performance metrics of the intrusion detection model. Furthermore, the VAE-WACGAN-based intrusion detection approach surpasses several other advanced methods, underscoring its effectiveness in tackling network security challenges.
Identification of intra-pulse modulation (IPM) of radar signals is a crucial part of contemporary electronic support systems and electronic intelligence reconnaissance. Artificial intelligence (AI)-based methods can b...
详细信息
Identification of intra-pulse modulation (IPM) of radar signals is a crucial part of contemporary electronic support systems and electronic intelligence reconnaissance. Artificial intelligence (AI)-based methods can be very effective in recognising the IPM of radar signals. In this direction, an automatic method is proposed for recognising a few IPMs of radar signals based on continuous wavelet transform (CWT) and a hybrid model of self-attention (SA)-aided convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM). Firstly, time-frequency attributes of different radar signals are obtained using CWT, and thereafter CNN-SA-BiLSTM is utilised for feature extraction from the 2D scalograms formed by the time-frequency components. The CNN extracts features from the scalograms, SA enhances the discriminative power of the feature map, and BiLSTM detects radar signals based on these features. Additionally, the study addresses real-world data imbalance issues by incorporating a generative AI model, namely the variational autoencoder (VAE). The VAE-based approach effectively mitigates challenges arising from data imbalance situations. This method is tested at varying noise levels to give a proper representation of the actual electronic warfare environment. The simulation results demonstrate that the best overall recognition accuracy of the proposed method is 98.4%, even at low signal-to-noise ratios (SNR).
In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-ba...
详细信息
ISBN:
(纸本)9789082797091
In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could be improved by deep representation learning (DRL). Based on our previous work, we in this paper propose to use beta-VAE to further improve PVAE's ability of representation learning. More specifically, our beta-VAE can improve PVAE's capacity of disentangling different latent variables from the observed signal without the trade-off problem between disentanglement and signal reconstruction. This trade-off problem widely exists in previous beta-VAE algorithms. Unlike the previous beta-VAE algorithms, the proposed beta-VAE strategy can also be used to optimize the DNN's structure. This means that the proposed method can not only improve PVAE's SE performance but also reduce the number of PVAE training parameters. The experimental results show that the proposed method can acquire better speech and noise latent representation than PVAE. Meanwhile, it also obtains a higher scale-invariant signal-to-distortion ratio, speech quality, and speech intelligibility.
Considering sporadic traffic in IoT networks, grantfree random access is inevitable. In a grant-free random access system, channel estimation and activity detection are crucial to enable data transmission. In this pap...
详细信息
ISBN:
(数字)9781665499279
ISBN:
(纸本)9781665499279
Considering sporadic traffic in IoT networks, grantfree random access is inevitable. In a grant-free random access system, channel estimation and activity detection are crucial to enable data transmission. In this paper, we propose a deep learning-based activity detection scheme for mmWave grant-free IoT networks, and the detection accuracy is validated by the simulation result.
Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable re...
详细信息
ISBN:
(纸本)9781450392686
Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable research has been performed on creating novel evolutionary algorithms or specialized genetic operators. However, if the representation that defined the search space could be altered such that it only permitted valid solutions that satisfied the constraints, the task of finding the optimal would be made more feasible without any need for specialized optimization algorithms. We propose Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation. Preliminary experiments show promise: compared to an identical GA using a standard representation that cannot meet the constraints or find fit solutions, COIL with its learned latent representation can perfectly satisfy different types of constraints while finding high-fitness solutions.
Current research on deep learning for medical image segmentation exposes their limitations in learning either global semantic information or local contextual information. To tackle these issues, a novel network named ...
详细信息
ISBN:
(纸本)9781665429238
Current research on deep learning for medical image segmentation exposes their limitations in learning either global semantic information or local contextual information. To tackle these issues, a novel network named SegTransVAE is proposed in this paper. SegTransVAE is built upon encoderdecoder architecture, exploiting transformer with the variational autoencoder (VAE) branch to the network to reconstruct the input images jointly with segmentation. To the best of our knowledge, this is the first method combining the success of CNN, transformer, and VAE. Evaluation on various recently introduced datasets shows that SegTransVAE outperforms previous methods in Dice Score and 95%-Haudorff Distance while having comparable inference time to a simple CNN-based architecture network. The source code is available at: https://***/itruonghai/SegTransVAE.
To overcome high computational cost suffered by statistical inference algorithms used in traditional topic models, recently, variational autoencoder (VAE) frameworks have been proposed for topic modeling. However, the...
详细信息
ISBN:
(纸本)9783031059360;9783031059353
To overcome high computational cost suffered by statistical inference algorithms used in traditional topic models, recently, variational autoencoder (VAE) frameworks have been proposed for topic modeling. However, the vanilla VAE model is originally introduced for unsupervised learning, which cannot meet more precise and customized requirements. In addition, the approximate posterior distribution in VAE is often selected as a Gaussian with a diagonal covariance matrix. This unimodal choice may hinder the ability of representation of latent space. In view of these limitations, in this paper, we propose to use Gaussian mixture model and Householder Flows for topic modeling under semi-supervised settings. We assume a document is associated with a mixture of classes, and a class is modeled as a multivariate Gaussian over latent topics. Specifically, an input document is encoded by a network into a discrete distribution, which not only serves the classifier for prediction, but also acts as mixing weights of Gaussian components. Another network is adopted to learn the parameters of Gaussian components. Additionally, Gaussian mixture is transformed by a Householder Flow to produce a more general posterior distribution. The effectiveness of the proposed model has been validated by the experiments performed on several standard datasets.
Transformer-based NLP models have achieved state-of-the-art results in many NLP tasks including text classification and text generation. However, the layers of these models do not output any explicit repre-sentations ...
详细信息
Transformer-based NLP models have achieved state-of-the-art results in many NLP tasks including text classification and text generation. However, the layers of these models do not output any explicit repre-sentations for texts units larger than tokens (e.g. sentences), although such representations are required to perform text classification. Sentence encodings are usually obtained by applying a pooling technique during fine-tuning on a specific task. In this paper, a new sentence encoder is introduced. Relying on an autoencoder architecture, it was trained to learn sentence representations from the very beginning of its training. The model was trained on bilingual data with variational Bayesian inference. Sentence repre-sentations were evaluated in downstream and linguistic probing tasks. Although the newly introduced encoder generally performs worse than well-known Transformer-based encoders, the experiments show that it was able to learn to incorporate linguistic information in the sentence representations.
Effective intelligent fault diagnosis of rotating machinery using its vibrational signals has a considerable influence on certain analysis factors such as the reliability, performance, and productivity of a variety of...
详细信息
Effective intelligent fault diagnosis of rotating machinery using its vibrational signals has a considerable influence on certain analysis factors such as the reliability, performance, and productivity of a variety of modern manufacturing machines. Traditional intelligent approaches lack generalization schemes and add the burden of extracting features from data-driven cases. On the other hand, the Deep Learning (DL) studies have reported capabilities higher than the expectations of the researchers' objectives. In this context, this paper proposes a new deep architecture based on Stacked Variant autoencoders for multi-fault machinery identification with imbalanced samples. The proposed model starts with a variational autoencoder (VAE) for facilitating data augmentation of small and imbalanced data samples using Gaussian distribution. After the preparation of suitable samples based on quality and size, the preprocessed vibration signals obtained are injected into the deep framework. The proposed deep architecture contains two subsequent unsupervised Sparse autoencoders (SAE) with a penalty term that helps in acquiring more abstract and essential features as well as avoiding redundancy. The output of the second SAE is integrated on a supervised Logistic Regression (LR) with 10 classes. This is utilized for the proposed classifier training to achieve accurate fault identification. Experimental results show the efficiency of the proposed model which achieved an accuracy of 93.2%. In addition, for extensive comparative analysis issue, the Generative Adversarial Network (GAN) and triNetwork Generative Adversarial Network (tnGAN) were both implemented on the vibrational signal data, where the proposed method reported better results in terms of training and testing time and overall accuracy.
暂无评论