Models, code, and papers for "Zhanyu Ma":

Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency

Aug 02, 2018
Zhanyu Ma

In this paper, we continue our previous work on the Dirichlet mixture model (DMM)-based VQ to derive the performance bound of the LSF VQ. The LSF parameters are transformed into the $\Delta$LSF domain and the underlying distribution of the $\Delta$LSF parameters are modelled by a DMM with finite number of mixture components. The quantization distortion, in terms of the mean squared error (MSE), is calculated with the high rate theory. The mapping relation between the perceptually motivated log spectral distortion (LSD) and the MSE is empirically approximated by a polynomial. With this mapping function, the minimum required bit rate for transparent coding of the LSF is estimated.

* Technical Report 

  Click for Model/Code and Paper
Classification of EEG Signal based on non-Gaussian Neutral Vector

Aug 02, 2018
Zhanyu Ma

In the design of brain-computer interface systems, classification of Electroencephalogram (EEG) signals is the essential part and a challenging task. Recently, as the marginalized discrete wavelet transform (mDWT) representations can reveal features related to the transient nature of the EEG signals, the mDWT coefficients have been frequently used in EEG signal classification. In our previous work, we have proposed a super-Dirichlet distribution-based classifier, which utilized the nonnegative and sum-to-one properties of the mDWT coefficients. The proposed classifier performed better than the state-of-the-art support vector machine-based classifier. In this paper, we further study the neutrality of the mDWT coefficients. Assuming the mDWT vector coefficients to be a neutral vector, we transform them non-linearly into a set of independent scalar coefficients. Feature selection strategy is proposed on the transformed feature domain. Experimental results show that the feature selection strategy helps improving the classification accuracy.

* Technical Report 

  Click for Model/Code and Paper
Language Identification with Deep Bottleneck Features

Sep 18, 2018
Zhanyu Ma, Hong Yu

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features used for LSTM learning are generated by a transfer learning method. Bottle-neck features of a deep neural network (DNN) which are trained for mandarin acoustic-phonetic classification are used for LSTM training. In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance. By splicing the normal, speech rate reduced and increased utterances, we can extend length of test utterances so as to improved improved the performance of the SLD system. The experimental results on AP17-OLR database shows that the proposed methods can improve the performance of SLD, especially on short utterance with 1s and 3s durations.

* Preliminary work report 

  Click for Model/Code and Paper
Deep Neural Network for Analysis of DNA Methylation Data

Aug 02, 2018
Hong Yu, Zhanyu Ma

Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different subtypes of the tumor. However, the conventional statistical methods are not suitable for analyzing the highly dimensional DNA methylation data with bounded support. In order to explicitly capture the properties of the data, we design a deep neural network, which composes of several stacked binary restricted Boltzmann machines, to learn the low dimensional deep features of the DNA methylation data. Experiments show these features perform best in breast cancer DNA methylation data cluster analysis, comparing with some state-of-the-art methods.

* Techinical Report 

  Click for Model/Code and Paper
Histogram Transform-based Speaker Identification

Aug 02, 2018
Zhanyu Ma, Hong Yu

A novel text-independent speaker identification (SI) method is proposed. This method uses the Mel-frequency Cepstral coefficients (MFCCs) and the dynamic information among adjacent frames as feature sets to capture speaker's characteristics. In order to utilize dynamic information, we design super-MFCCs features by cascading three neighboring MFCCs frames together. The probability density function (PDF) of these super-MFCCs features is estimated by the recently proposed histogram transform~(HT) method, which generates more training data by random transforms to realize the histogram PDF estimation and recedes the commonly occurred discontinuity problem in multivariate histograms computing. Compared to the conventional PDF estimation methods, such as Gaussian mixture models, the HT model shows promising improvement in the SI performance.

* Technical Report 

  Click for Model/Code and Paper
Infinite Mixture of Inverted Dirichlet Distributions

Jul 27, 2018
Zhanyu Ma, Yuping Lai

In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements. The recently proposed extended variational inference (EVI) framework is adopted to derive an analytically tractable solution. The convergency of the proposed algorithm is theoretically guaranteed by introducing single lower bound approximation to the original objective function in the VI framework. In principle, the proposed model can be viewed as an infinite inverted Dirichelt mixture model (InIDMM) that allows the automatic determination of the number of mixture components from data. Therefore, the problem of pre-determining the optimal number of mixing components has been overcome. Moreover, the problems of over-fitting and under-fitting are avoided by the Bayesian estimation approach. Comparing with several recently proposed DP-related methods, the good performance and effectiveness of the proposed method have been demonstrated with both synthesized data and real data evaluations.

* Technical Report of ongoing work 

  Click for Model/Code and Paper
Deep Zero-Shot Learning for Scene Sketch

May 11, 2019
Yao Xie, Peng Xu, Zhanyu Ma

We introduce a novel problem of scene sketch zero-shot learning (SSZSL), which is a challenging task, since (i) different from photo, the gap between common semantic domain (e.g., word vector) and sketch is too huge to exploit common semantic knowledge as the bridge for knowledge transfer, and (ii) compared with single-object sketch, more expressive feature representation for scene sketch is required to accommodate its high-level of abstraction and complexity. To overcome these challenges, we propose a deep embedding model for scene sketch zero-shot learning. In particular, we propose the augmented semantic vector to conduct domain alignment by fusing multi-modal semantic knowledge (e.g., cartoon image, natural image, text description), and adopt attention-based network for scene sketch feature learning. Moreover, we propose a novel distance metric to improve the similarity measure during testing. Extensive experiments and ablation studies demonstrate the benefit of our sketch-specific design.

* 5 pages, 3 figures, IEEE International Conference on Image Processing (ICIP) 

  Click for Model/Code and Paper
Channel Max Pooling Layer for Fine-Grained Vehicle Classification

Feb 14, 2019
Zhanyu Ma, Dongliang Chang, Xiaoxu Li

Deep convolutional networks have recently shown excellent performance on Fine-Grained Vehicle Classification. Based on these existing works, we consider that the back-probation algorithm does not focus on extracting less discriminative feature as much as possible, but focus on that the loss function equals zero. Intuitively, if we can learn less discriminative features, and these features still could fit the training data well, the generalization ability of neural network could be improved. Therefore, we propose a new layer which is placed between fully connected layers and convolutional layers, called as Chanel Max Pooling. The proposed layer groups the features map first and then compress each group into a new feature map by computing maximum of pixels with same positions in the group of feature maps. Meanwhile, the proposed layer has an advantage that it could help neural network reduce massive parameters. Experimental results on two fine-grained vehicle datasets, the Stanford Cars-196 dataset and the Comp Cars dataset, demonstrate that the proposed layer could improve classification accuracies of deep neural networks on fine-grained vehicle classification in the situation that a massive of parameters are reduced. Moreover, it has a competitive performance with the-state-of-art performance on the two datasets.

* Report of ongoing work 

  Click for Model/Code and Paper
On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models

Feb 13, 2019
Zhanyu Ma, Jalil Taghia, Jun Guo

Variational inference (VI) is a widely used framework in Bayesian estimation. For most of the non-Gaussian statistical models, it is infeasible to find an analytically tractable solution to estimate the posterior distributions of the parameters. Recently, an improved framework, namely the extended variational inference (EVI), has been introduced and applied to derive analytically tractable solution by employing lower-bound approximation to the variational objective function. Two conditions required for EVI implementation, namely the weak condition and the strong condition, are discussed and compared in this paper. In practical implementation, the convergence of the EVI depends on the selection of the lower-bound approximation, no matter with the weak condition or the strong condition. In general, two approximation strategies, the single lower-bound (SLB) approximation and the multiple lower-bounds (MLB) approximation, can be applied to carry out the lower-bound approximation. To clarify the differences between the SLB and the MLB, we will also discuss the convergence properties of the aforementioned two approximations. Extensive comparisons are made based on some existing EVI-based non-Gaussian statistical models. Theoretical analysis are conducted to demonstrate the differences between the weak and the strong conditions. Qualitative and quantitative experimental results are presented to show the advantages of the SLB approximation.

* Technical Report 

  Click for Model/Code and Paper
Impacts of Weather Conditions on District Heat System

Aug 02, 2018
Jiyang Xie, Zhanyu Ma, Jun Guo

Using artificial neural network for the prediction of heat demand has attracted more and more attention. Weather conditions, such as ambient temperature, wind speed and direct solar irradiance, have been identified as key input parameters. In order to further improve the model accuracy, it is of great importance to understand the influence of different parameters. Based on an Elman neural network (ENN), this paper investigates the impact of direct solar irradiance and wind speed on predicting the heat demand of a district heating network. Results show that including wind speed can generally result in a lower overall mean absolute percentage error (MAPE) (6.43%) than including direct solar irradiance (6.47%); while including direct solar irradiance can achieve a lower maximum absolute deviation (71.8%) than including wind speed (81.53%). In addition, even though including both wind speed and direct solar irradiance shows the best overall performance (MAPE=6.35%).

* Technical Report 

  Click for Model/Code and Paper
Mobile big data analysis with machine learning

Aug 02, 2018
Jiyang Xie, Zeyu Song, Yupeng Li, Zhanyu Ma

This paper investigates to identify the requirement and the development of machine learning-based mobile big data analysis through discussing the insights of challenges in the mobile big data (MBD). Furthermore, it reviews the state-of-the-art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently adopted methods of data analysis are reviewed. Three typical applications of MBD analysis, namely wireless channel modeling, human online and offline behavior analysis, and speech recognition in the internet of vehicles, are introduced respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.

* Version 0.1 

  Click for Model/Code and Paper
DNN Filter Bank Cepstral Coefficients for Spoofing Detection

Feb 13, 2017
Hong Yu, Zheng-Hua Tan, Zhanyu Ma, Jun Guo

With the development of speech synthesis techniques, automatic speaker verification systems face the serious challenge of spoofing attack. In order to improve the reliability of speaker verification systems, we develop a new filter bank based cepstral feature, deep neural network filter bank cepstral coefficients (DNN-FBCC), to distinguish between natural and spoofed speech. The deep neural network filter bank is automatically generated by training a filter bank neural network (FBNN) using natural and synthetic speech. By adding restrictions on the training rules, the learned weight matrix of FBNN is band-limited and sorted by frequency, similar to the normal filter bank. Unlike the manually designed filter bank, the learned filter bank has different filter shapes in different channels, which can capture the differences between natural and synthetic speech more effectively. The experimental results on the ASVspoof {2015} database show that the Gaussian mixture model maximum-likelihood (GMM-ML) classifier trained by the new feature performs better than the state-of-the-art linear frequency cepstral coefficients (LFCC) based classifier, especially on detecting unknown attacks.


  Click for Model/Code and Paper
Competing Ratio Loss for Discriminative Multi-class Image Classification

Aug 01, 2019
Ke Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma, Tony X. Han

The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance. Contrary to these studies, we focus on the loss function. Cross-entropy Loss (CEL) is widely used for training a multi-class classification deep convolutional neural network. While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. In order to solve the problem of CEL, we propose Competing Ratio Loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better discriminate the correct class from competing wrong classes, increasing the difference between the negative log likelihood of the correct class and the negative log likelihood of competing wrong classes, widening the difference between the probability of the correct class and the probabilities of wrong classes. To demonstrate the effectiveness of our loss function, we perform some sets of experiments on different types of image classification datasets, including CIFAR, SVHN, CUB200- 2011, Adience and ImageNet datasets. The experimental results show the effectiveness and robustness of our loss function on different deep convolutional neural network architectures and different image classification tasks, such as fine-grained image classification, hard face age estimation and large-scale image classification.

* The method proposed in this paper has major technical shortcomings, so we want to withdraw 

  Click for Model/Code and Paper
SEA: A Combined Model for Heat Demand Prediction

Jul 28, 2018
Jiyang Xie, Jiaxin Guo, Zhanyu Ma, Jing-Hao Xue, Qie Sun, Hailong Li, Jun Guo

Heat demand prediction is a prominent research topic in the area of intelligent energy networks. It has been well recognized that periodicity is one of the important characteristics of heat demand. Seasonal-trend decomposition based on LOESS (STL) algorithm can analyze the periodicity of a heat demand series, and decompose the series into seasonal and trend components. Then, predicting the seasonal and trend components respectively, and combining their predictions together as the heat demand prediction is a possible way to predict heat demand. In this paper, STL-ENN-ARIMA (SEA), a combined model, was proposed based on the combination of the Elman neural network (ENN) and the autoregressive integrated moving average (ARIMA) model, which are commonly applied to heat demand prediction. ENN and ARIMA are used to predict seasonal and trend components, respectively. Experimental results demonstrate that the proposed SEA model has a promising performance.


  Click for Model/Code and Paper
Decorrelation of Neutral Vector Variables: Theory and Applications

May 30, 2017
Zhanyu Ma, Jing-Hao Xue, Arne Leijon, Zheng-Hua Tan, Zhen Yang, Jun Guo

In this paper, we propose novel strategies for neutral vector variable decorrelation. Two fundamental invertible transformations, namely serial nonlinear transformation and parallel nonlinear transformation, are proposed to carry out the decorrelation. For a neutral vector variable, which is not multivariate Gaussian distributed, the conventional principal component analysis (PCA) cannot yield mutually independent scalar variables. With the two proposed transformations, a highly negatively correlated neutral vector can be transformed to a set of mutually independent scalar variables with the same degrees of freedom. We also evaluate the decorrelation performances for the vectors generated from a single Dirichlet distribution and a mixture of Dirichlet distributions. The mutual independence is verified with the distance correlation measurement. The advantages of the proposed decorrelation strategies are intensively studied and demonstrated with synthesized data and practical application evaluations.


  Click for Model/Code and Paper
BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint

Jul 08, 2018
Jiyang Xie, Zhanyu Ma, Guoqiang Zhang, Jing-Hao Xue, Jen-Tzung Chien, Zhiqing Lin, Jun Guo

A Bayesian approach termed BAyesian Least Squares Optimization with Nonnegative L1-norm constraint (BALSON) is proposed. The error distribution of data fitting is described by Gaussian likelihood. The parameter distribution is assumed to be a Dirichlet distribution. With the Bayes rule, searching for the optimal parameters is equivalent to finding the mode of the posterior distribution. In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution. We estimate the statistics of the approximating Dirichlet posterior distribution by sampling methods. Four sampling methods have been introduced. With the estimated posterior distributions, the original parameters can be effectively reconstructed in polynomial fitting problems, and the BALSON framework is found to perform better than conventional methods.


  Click for Model/Code and Paper
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

Apr 04, 2018
Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo

We propose a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset. Leveraging on this large dataset, we explore a few sketch-specific traits that were otherwise under-studied in prior literature. Instead of following the conventional sketch recognition task, we introduce the novel problem of sketch hashing retrieval which is not only more challenging, but also offers a better testbed for large-scale sketch analysis, since: (i) more fine-grained sketch feature learning is required to accommodate the large variations in style and abstraction, and (ii) a compact binary code needs to be learned at the same time to enable efficient retrieval. Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches. By working with a 3.8M sketch dataset, we show that state-of-the-art hashing models specifically engineered for static images fail to perform well on temporal sketch data. Our network on the other hand not only offers the best retrieval performance on various code sizes, but also yields the best generalization performance under a zero-shot setting and when re-purposed for sketch recognition. Such superior performances effectively demonstrate the benefit of our sketch-specific design.

* Accepted by CVPR2018 

  Click for Model/Code and Paper
Cross-modal Subspace Learning for Fine-grained Sketch-based Image Retrieval

May 28, 2017
Peng Xu, Qiyue Yin, Yongye Huang, Yi-Zhe Song, Zhanyu Ma, Liang Wang, Tao Xiang, W. Bastiaan Kleijn, Jun Guo

Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo. Compared with pixel-perfect depictions of photos, sketches are iconic renderings of the real world with highly abstract. Therefore, matching sketch and photo directly using low-level visual clues are unsufficient, since a common low-level subspace that traverses semantically across the two modalities is non-trivial to establish. Most existing SBIR studies do not directly tackle this cross-modal problem. This naturally motivates us to explore the effectiveness of cross-modal retrieval methods in SBIR, which have been applied in the image-text matching successfully. In this paper, we introduce and compare a series of state-of-the-art cross-modal subspace learning methods and benchmark them on two recently released fine-grained SBIR datasets. Through thorough examination of the experimental results, we have demonstrated that the subspace learning can effectively model the sketch-photo domain-gap. In addition we draw a few key insights to drive future research.

* Accepted by Neurocomputing 

  Click for Model/Code and Paper