In most practical adaptive filtering problems, estimated filters are not arbitrary, but instead lie on a manifold that encapsulates characteristics of the problem at hand. Consequently, it is desirable to steer adapta...
详细信息
With the rise of cloud computing, many applications have been implemented into microservices to fully utilize cloud computing for scalability and maintainability purposes. However, there are some traditional monolith ...
详细信息
ISBN:
(数字)9781665475341
ISBN:
(纸本)9781665475341
With the rise of cloud computing, many applications have been implemented into microservices to fully utilize cloud computing for scalability and maintainability purposes. However, there are some traditional monolith applications that developers would like to partition into microservices. Unfortunately, it is difficult to find a solution when considering multiple factors (i.e., the strong dependency in each cluster and how often different microservices communicate with each other). Further, because we allow duplications of classes in multiple microservices to reduce the communications between them, the number of duplicated classes is also another important factor for maintainability. Therefore, we need to use machine learning algorithms to approximate a good solution due to the infeasibility of finding the optimal solution. We apply the variational autoencoder to extract features of classes and use the fuzzy c means to group the classes into microservices according to their extracted features. As a result, our approach outperforms the other baselines in some significant metrics. Also, when we allow duplication, we find that it is helpful in terms of reducing the overhead of communications between microservices.
Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoptio...
详细信息
ISBN:
(纸本)9783031299551;9783031299568
Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoption of web typography make type design better known and more accessible. This domain has received an even greater push with the increasing adoption of generative tools to create more diverse and experimental fonts. Nowadays, with the application of Machine Learning to various domains, typography has also been influenced by it. In this work, we produce a dataset by extracting letter skeletons from a collection of existing fonts. Then we trained a variational autoencoder and a Sketch Decoder to learn to create these skeletons that can be used to generate new ones by exploring the latent space. This process also allows us to control the style of the resulting skeletons and interpolate between different characters. Finally, we developed new glyphs by filling the generated skeletons based on the original letters' stroke width and showing some applications of the results.
This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, which correspond to the four quarters of ...
详细信息
ISBN:
(纸本)9781665442077
This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, which correspond to the four quarters of Russell's model, were used. Conditional variational autoencoder using a recurrent neural network for sequence processing was used as a generative model. The obtained results in the form of the generated music examples with a specific emotion are convincing in their structure and sound. The generated examples were evaluated through comparison with the training set.
As the trend of climate change continues, an increase in the severity of extreme weather events is expected, posing a significant threat to the electric power infrastructure. The efficiency of service restoration effo...
详细信息
ISBN:
(纸本)9798350336962
As the trend of climate change continues, an increase in the severity of extreme weather events is expected, posing a significant threat to the electric power infrastructure. The efficiency of service restoration efforts can be enhanced by having access to a highly granular outage forecasting tool with long lead times. In this study, we propose to develop and implement a multi-model framework as an operational tool that utilizes a dynamic, granular, multi-day outage forecasting model based on operational weather forecasts and detailed component outage information. To address the uneven distribution of different types of weather events and make better use of the timeseries data, a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework was developed to sample synthetic data and address data imbalance. With the balanced data, a prediction model was developed to estimate outages given a period of weather forecasts. The performance of the framework is demonstrated through several comparative studies.
Recently, adversarial examples become one of the most dangerous risks in deep learning, which affects applications of real world such as robotics, cyber-security and computer vision. In image classification, adversari...
详细信息
ISBN:
(纸本)9781510640412
Recently, adversarial examples become one of the most dangerous risks in deep learning, which affects applications of real world such as robotics, cyber-security and computer vision. In image classification, adversarial attacks showed the ability to fool classifiers with small imperceptible perturbations added to the input. In this paper, we present an efficient defense mechanism, we call DVAE-SR that combine variational autoencoder and super-resolution to eliminate adversarial perturbation from image input before feeding it to the CNN classifier. The DVAE-SR can successfully defend against both white-box and black-box attacks without retraining CNN classifier and it recovers better accuracy than Defense-GAN and Defense-VAE..
In the real world, data missing is inevitable in traffic data collection due to detector failures or signal interference. However, missing traffic data imputation is non-trivial since traffic data usually contains bot...
详细信息
ISBN:
(纸本)9783030863838;9783030863821
In the real world, data missing is inevitable in traffic data collection due to detector failures or signal interference. However, missing traffic data imputation is non-trivial since traffic data usually contains both temporal and spatial characteristics with inherent complex relations. In each time interval, the traffic measurements collected in all spatial regions can be regarded as an image with more or fewer channels. Therefore, the traffic raster data over time can be learned as videos. In this paper, we propose a novel unsupervised generative neural network for traffic raster data imputation called STVAE, which works well robustly even under different missing rates. The core idea of our model is to discover more complex spatio-temporal representations inside the traffic data under the architecture of variational autoencoder (VAE) with Sylvester normalizing flows (SNFs). After transforming the traffic raster data into multi-channel videos, a Detection-and-Calibration Block (DCB), which extends 3D gated convolution and multi-attention mechanism, is proposed to sense, extract and calibrate more flexible and accurate spatio-temporal dependencies of the original data. The experiments are employed on three real-world traffic flow datasets and demonstrate that our network STVAE achieves the lowest imputation errors and outperforms state-of-the-art traffic data imputation models.
In the production and daily life of various industries in today's society, it is often necessary to arrange a large number of sensors to collect data on a scheduled basis. However, due to factors such as collectio...
详细信息
ISBN:
(纸本)9798350375084;9798350375077
In the production and daily life of various industries in today's society, it is often necessary to arrange a large number of sensors to collect data on a scheduled basis. However, due to factors such as collection errors, sensor failures, network transmission anomalies, and human influence, the obtained multidimensional temporal data may exhibit anomalies. In order to better analyze multidimensional temporal data, understand patterns, trends, and correlations in observed phenomena, and help people better analyze problems and make decisions, a design scheme for anomaly detection models that have always been oriented towards multidimensional temporal data is proposed. This scheme utilizes Convolutional Neural Networks (CNN) to extract local features, Long Short Term Memory Networks (LSTM) to store and extract time-series data features, combined with attention mechanisms to enhance feature extraction capabilities, and uses variational autoencoder (VAE) for anomaly detection, significantly improving the accuracy and efficiency of detection. Through experimental verification, this method performs well in practical applications and has broad application prospects.
Infectious keratitis is a major cause of visual impairment and a common blinding eye disease. Deep learning based prior researches mainly regard infectious keratitis diagnosis as a classification task on the slit-lamp...
详细信息
ISBN:
(数字)9781665496209
ISBN:
(纸本)9781665496209
Infectious keratitis is a major cause of visual impairment and a common blinding eye disease. Deep learning based prior researches mainly regard infectious keratitis diagnosis as a classification task on the slit-lamp images of single-visit. However, in real clinical applications, it is critical to analyze the lesion evolution characteristics represented by time-varying features over multiple-visits. To bridge this gap, in this paper, we focus on the problem with sequential clinical images of patients, and propose a novel disentangled sequential auto-encoder (DSLC-VAE) algorithm to separate the time-varying pathological features from the time-invariant ones for infectious keratitis diagnosis. Specifically, a inference model is exploited to generate time series of the shape and appearance of corneal lesions to represent keratitis progression, which are combined with location-related features to identify keratitis pathogen. Moreover, we construct a local consistent regularizer with a self-supervised task to enhance the consistency of the time-varying features across different infectious keratitis. Extensive experiments on real world dataset demonstrate superiority of our DSLC-VAE on both representation disentanglement and diagnosis accuracy.
We present a generative model for the 3D facial expression mesh sequences, from onset to the termination of a desired expression. We tailor a Transformer VAE architecture: The encoder compresses a sequence of facial l...
详细信息
ISBN:
(纸本)9781728198354
We present a generative model for the 3D facial expression mesh sequences, from onset to the termination of a desired expression. We tailor a Transformer VAE architecture: The encoder compresses a sequence of facial landmarks into an expression-aware regularized latent space, while the decoder generates a new sequence from the sampled latent variable, conditioned on a desired expression. After a landmark-guided mesh deformation, a given 3D neutral face is driven to an animated mesh sequence with the expected expression. The generated sequences are consistent, of quality, and exhibit a good level of diversity, improving over state-of-the-art methods. We validate our model by conducting extensive experiments on two representative datasets. The supplementary video and code are available on a GitHub page (https://***/ZOUKaifeng/ FacialExpressionGeneration).
暂无评论