As one of the essential tools for spatio‒temporal traffic data mining,vehicle trajectory clustering is widely used to mine the behavior patterns of ***,uploading original vehicle trajectory data to the server and clus...
详细信息
As one of the essential tools for spatio‒temporal traffic data mining,vehicle trajectory clustering is widely used to mine the behavior patterns of ***,uploading original vehicle trajectory data to the server and clustering carry the risk of privacy ***,one of the current challenges is determining how to perform vehicle trajectory clustering while protecting user *** propose a privacy-preserving vehicle trajectory clustering framework and construct a vehicle trajectory clustering model(IKV)based on the variational autoencoder(VAE)and an improved K-means *** the framework,the client calculates the hidden variables of the vehicle trajectory and uploads the variables to the server;the server uses the hidden variables for clustering analysis and delivers the analysis results to the *** IKV’workflow is as follows:first,we train the VAE with historical vehicle trajectory data(when VAE’s decoder can approximate the original data,the encoder is deployed to the edge computing device);second,the edge device transmits the hidden variables to the server;finally,clustering is performed using improved K-means,which prevents the leakage of the vehicle *** is compared to numerous clustering methods on three *** the nine performance comparison experiments,IKV achieves optimal or sub-optimal performance in six of the ***,in the nine sensitivity analysis experiments,IKV not only demonstrates significant stability in seven experiments but also shows good robustness to hyperparameter *** results validate that the framework proposed in this paper is not only suitable for privacy-conscious production environments,such as carpooling tasks,but also adapts to clustering tasks of different magnitudes due to the low sensitivity to the number of cluster centers.
We propose a few shot learning approach for the problem of hematopoietic cell classification in digital pathology. In hematopoiesis cell classification, the classes correspond to the different stages of the cellular m...
详细信息
We propose a few shot learning approach for the problem of hematopoietic cell classification in digital pathology. In hematopoiesis cell classification, the classes correspond to the different stages of the cellular maturation process. Two consecutive stage categories are considered to have a neighborhood relationship, which implies a visual similarity between the two categories. We propose RelationVAE which incorporates these relationships between hematopoietic cell classes to robustly generate more data for the classes with limited training data. Specifically, we first model these relationships using a graphical model, and propose RelationVAE, a deep generative model which implements the graphical model. RelationVAE is trained to optimize the lower bound of the pairwise data likelihood of the graphical model. In this way, it can identify class level features of a specific class from a small number of input images together with the knowledge transferred from visually similar classes, leading to more robust sample synthesis. The experiments on our collected hematopoietic dataset show the improved results of our proposed RelationVAE over a baseline VAE model and other few shot learning methods. Our code and data are available at https://***/cvlab-stonybrook/hematopoiesis-relationvae.
Text-based speech editing systems are developed to enable users to modify speech based on the transcript. Existing state-of-the-art editing systems based on neural networks do partial inferences with no exception, tha...
详细信息
Text-based speech editing systems are developed to enable users to modify speech based on the transcript. Existing state-of-the-art editing systems based on neural networks do partial inferences with no exception, that is, only generate new words that need to be replaced or inserted. This manner usually leads to the prosody of the edited part being inconsistent with the surrounding speech and a failure to handle the alteration of intonation. To address these problems, we propose a cross-utterance conditioned coherent speech editing system, that first does the entire reasoning at the inference time. Our proposed system can generate speech by utilizing speaker information, context, acoustic features, and the mel-spectrogram from the original audio. Experiments conducted on subjective and objective metrics demonstrate that our approach outperforms the baseline on various editing operations regarding naturalness and prosody consistency.
The success of deep learning has inspired a lot of recent interests in exploiting neural network structures for statistical inference and learning. In this paper, we review some popular deep neural network structures ...
详细信息
The success of deep learning has inspired a lot of recent interests in exploiting neural network structures for statistical inference and learning. In this paper, we review some popular deep neural network structures and techniques under the framework of nonparametric regression with measurement errors. In particular, we demonstrate how to use a fully connected feed-forward neural network to approximate the regression function f (x), explain how to use a normalizing flow to approximate the prior distribution of X, and detail how to construct an inference network to generate approximate posterior samples of X. After reviewing recent advances in variational inference for deep neural networks, such as the importance weighted autoencoder, doubly reparametrized gradient estimator, and nonlinear independent components estimation, we describe an inference procedure built upon these advances. An extensive numerical study is presented to compare the neural network approach with classical nonparametric methods, which suggests that the neural network approach is more flexible in accommodating different classes of regression functions and performs superior or comparable to the best available method in many settings.
Background: A backdoor attack controls the output of a machine learning model in 2 stages. First, the attacker poisons the training data set, introducing a back door into the victim's trained model. Second, during...
详细信息
Background: A backdoor attack controls the output of a machine learning model in 2 stages. First, the attacker poisons the training data set, introducing a back door into the victim's trained model. Second, during test time, the attacker adds an imperceptible pattern called a trigger to the input values, which forces the victim's model to output the attacker's intended values instead of true predictions or decisions. While backdoor attacks pose a serious threat to the reliability of machine learning-based medical diagnostics, existing backdoor attacks that directly change the input values are detectable relatively easily. Objective: The goal of this study was to propose and study a robust backdoor attack on mortality-prediction machine learning models that use electronic health records. We showed that our backdoor attack grants attackers full control over classification outcomes for safety-critical tasks such as mortality prediction, highlighting the importance of undertaking safe artificial intelligence research in the medical field. Methods: We present a trigger generation method based on missing patterns in electronic health record data. Compared to existing approaches, which introduce noise into the medical record, the proposed backdoor attack makes it simple to construct backdoor triggers without prior knowledge. To effectively avoid detection by manual inspectors, we employ variational autoencoders to learn the missing patterns in normal electronic health record data and produce trigger data that appears similar to this data. Results: We experimented with the proposed backdoor attack on 4 machine learning models (linear regression, multilayer perceptron, long short-term memory, and gated recurrent units) that predict in-hospital mortality using a public electronic health record data set. The results showed that the proposed technique achieved a significant drop in the victim's discrimination performance (reducing the area under the precision-recall curve by at
This paper proposes a novel approach based on deep learning to improve oil reservoirs' history matching problem. Deep autoencoders are widely used to solve the oil industry problems. However, as the input data inc...
详细信息
This paper proposes a novel approach based on deep learning to improve oil reservoirs' history matching problem. Deep autoencoders are widely used to solve the oil industry problems. However, as the input data increases, the autoencoder parameters increase exponentially. Our model is based on a convolutional variational autoencoder using AlexNet and bi-directional gated recurrent units. It parameterizes large-scale oilfield reservoirs. The proposed model is integrated into an ensemble smoother with multiple data assimilation to perform history matching. The proposed approach is validated on two reservoir models: PUNQ-S3 and Volve field. The root mean squared error, R2, and mean absolute error are calculated to verify the effectiveness of the proposed approach. The results show that the proposed model can effectively study the complex geological features of oil fields and be used in expert systems for reservoir modeling.
User Interface testing is one of the most used routines for Android feature quality verification. Regarding this, several industrial and academic solutions are available for Graphical User Interface component identifi...
详细信息
ISBN:
(纸本)9798350359374
User Interface testing is one of the most used routines for Android feature quality verification. Regarding this, several industrial and academic solutions are available for Graphical User Interface component identification. However, the state-of-art works are still limited respecting the variety of widgets that can recognize. Also, most solutions use application metadata that can vary across different releases and device models, affecting the portability of automations. Research that approach widget classification using Machine Learning based solutions commonly use a large Android screen capture dataset called RICO. However, several annotations problems have been recurrently pointed on this dataset. In this work, we propose a selection of data cleaning and balancing techniques for removing noisy samples and leveling the number of samples per class on RICO dataset. We used a custom dataset with an extended number of classes (106) when comparing with the state-of-art works that approach widget classification with 15 classes on average. Finally, we showed that using these techniques to improve the quality of data can improve the accuracy when training Machine Learning models like Convolutional Neural Networks and eXtreme Gradient Boosting.
Despite a great success in learning representation for image data, it is challenging to learn the stochastic latent features from natural language based on variational inference. The difficulty in stochastic sequentia...
详细信息
ISBN:
(纸本)9781479981311
Despite a great success in learning representation for image data, it is challenging to learn the stochastic latent features from natural language based on variational inference. The difficulty in stochastic sequential learning is due to the posterior collapse caused by an autoregressive decoder which is prone to be too strong to learn sufficient latent information during optimization. To compensate this weakness in learning procedure, a sophisticated latent structure is required to assure good convergence so that random features are sufficiently captured for sequential decoding. This study presents a new variational recurrent autoencoder (VRAE) for sequence reconstruction. There are two complementary encoders consisting of a long short-term memory (LSTM) and a pyramid bidirectional LSTM which are merged to discover the global and local dependencies in a hierarchical latent variable model, respectively. Experiments on Penn Treebank and Yelp 2013 demonstrate that the proposed hierarchical VRAE is able to learn the complementary representation as well as tackle the posterior collapse in stochastic sequential learning. The performance of recurrent autoencoder is substantially improved in terms of perplexity.
In creative design, where aesthetics play a crucial role in determining the quality of outcomes, there are often multiple worthwhile possibilities, rather than a single "best" design. This challenge is compo...
详细信息
ISBN:
(纸本)9798400701207
In creative design, where aesthetics play a crucial role in determining the quality of outcomes, there are often multiple worthwhile possibilities, rather than a single "best" design. This challenge is compounded in the use of computational generative systems, where the sheer number of potential outcomes can be overwhelming. This paper introduces a method that combines evolutionary optimisation with AI-based image classification to perform quality-diversity search, allowing for the creative exploration of complex design spaces. The process begins by randomly sampling the genotype space, followed by mapping the generated phenotypes to a reduced representation of the solution space, as well as evaluating them based on their visual characteristics. This results in an elite group of diverse outcomes that span the solution space. The elite is then progressively updated via sampling and simple mutation. We tested our method on a generative system that produces abstract drawings. The results demonstrate that the system can effectively evolve populations of phenotypes with high aesthetic value and greater visual diversity compared to traditional optimisation-focused evolutionary approaches.
In multiple input multiple output (MIMO) wireless communication systems, neural networks are utilized for resource management, channel decoding, and the finding and assessment of channels. This paper addresses the pro...
详细信息
In multiple input multiple output (MIMO) wireless communication systems, neural networks are utilized for resource management, channel decoding, and the finding and assessment of channels. This paper addresses the problem of finding a precoding matrix with a high spectral efficiency (SE) using a variational autoencoder. An optimization procedure for finding optimal precoding matrices is known. The goal of this study is to construct a less time-consuming algorithm than the optimization procedure with minimum loss of quality. As a solution to achieve this goal, two types of variational autoencoders are used to construct precoding matrices: a classical variational autoencoder (VAE) and conditional variational autoencoder (CVAE). Both methods can be used to explore a wide range of optimal precoding matrices. The VAE and CVAE methods make it possible to restore the distribution of the predicted value by sampling random variables from the normal distribution at an intermediate stage of calculations. The construction of precoding matrices and their distribution for the SE objective function using the VAE and CVAE methods is described in a publication for the first time.
暂无评论