arXiv subjects

Fuchun Sun

Publications and source records attributed to Fuchun Sun.

151 records · Page 9Linked to original sources

arXiv2018

Spatial and Spectral Features Fusion for EEG Classification during Motor Imagery in BCI

Brain computer interface (BCI) is the only way for some special patients to communicate with the outside world and provide a direct control channel between brain and the external devices. As a non-invasive interface, the scalp electroencephalography (EEG) has a significant potential to be a major input signal for future BCI systems. Traditional methods only focus on a particular feature in the EEG signal, which limits the practical applications of EEG-based BCI. In this paper, we propose a algorithm for EEG classification with the ability to fuse multiple features. First, use the common spatial pattern (CSP) as the spatial feature and use wavelet coefficient as the spectral feature. Second, fuse these features with a fusion algorithm in orchestrate way to improve the accuracy of classification. Our algorithms are applied to the dataset IVa from BCI complete \uppercase\expandafter{\romannumeral3}. By analyzing the experimental results, it is possible to conclude that we can speculate that our algorithm perform better than traditional methods.

q-bio.QM↗

arXiv2018

Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography

Electroencephalography (EEG) has become the most significant input signal for brain computer interface (BCI) based systems. However, it is very difficult to obtain satisfactory classification accuracy due to traditional methods can not fully exploit multimodal information. Herein, we propose a novel approach to modeling cognitive events from EEG data by reducing it to a video classification problem, which is designed to preserve the multimodal information of EEG. In addition, optical flow is introduced to represent the variant information of EEG. We train a deep neural network (DNN) with convolutional neural network (CNN) and recurrent neural network (RNN) for the EEG classification task by using EEG video and optical flow. The experiments demonstrate that our approach has many advantages, such as more robustness and more accuracy in EEG classification tasks. According to our approach, we designed a mixed BCI-based rehabilitation support system to help stroke patients perform some basic operations.

cs.CV↗

arXiv2017

MAT: A Multimodal Attentive Translator for Image Captioning

In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from most existing work where the whole image is represented by convolutional neural network (CNN) feature, we propose to represent the input image as a sequence of detected objects which feeds as the source sequence of the RNN model. In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model. To represent the image in a sequential way, we extract the objects features in the image and arrange them in a order using convolutional neural networks. To further leverage the visual information from the encoded objects, a sequential attention layer is introduced to selectively attend to the objects that are related to generate corresponding words in the sentences. Extensive experiments are conducted to validate the proposed approach on popular benchmark dataset, i.e., MS COCO, and the proposed model surpasses the state-of-the-art methods in all metrics following the dataset splits of previous work. The proposed approach is also evaluated by the evaluation server of MS COCO captioning challenge, and achieves very competitive results, e.g., a CIDEr of 1.029 (c5) and 1.064 (c40).

cs.CV↗

arXiv2017

RON: Reverse Connection with Objectness Prior Networks for Object Detection

We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully convolutional architecture, RON mainly focuses on two fundamental problems: (a) multi-scale object localization and (b) negative sample mining. To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs. To deal with (b), we propose the objectness prior to significantly reduce the searching space of objects. We optimize the reverse connection, objectness prior and object detector jointly by a multi-task loss function, thus RON can directly predict final detection results from all locations of various feature maps. Extensive experiments on the challenging PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO benchmarks demonstrate the competitive performance of RON. Specifically, with VGG-16 and low resolution 384X384 input size, the network gets 81.3% mAP on PASCAL VOC 2007, 80.7% mAP on PASCAL VOC 2012 datasets. Its superiority increases when datasets become larger and more difficult, as demonstrated by the results on the MS COCO dataset. With 1.5G GPU memory at test phase, the speed of the network is 15 FPS, 3X faster than the Faster R-CNN counterpart.

cs.CV↗

arXiv2017

Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

Encoding time-series with Linear Dynamical Systems (LDSs) leads to rich models with applications ranging from dynamical texture recognition to video segmentation to name a few. In this paper, we propose to represent LDSs with infinite-dimensional subspaces and derive an analytic solution to obtain stable LDSs. We then devise efficient algorithms to perform sparse coding and dictionary learning on the space of infinite-dimensional subspaces. In particular, two solutions are developed to sparsely encode an LDS. In the first method, we map the subspaces into a Reproducing Kernel Hilbert Space (RKHS) and achieve our goal through kernel sparse coding. As for the second solution, we propose to embed the infinite-dimensional subspaces into the space of symmetric matrices and formulate the sparse coding accordingly in the induced space. For dictionary learning, we encode time-series by introducing a novel concept, namely the two-fold LDSs. We then make use of the two-fold LDSs to derive an analytical form for updating atoms of an LDS dictionary, i.e., each atom is an LDS itself. Compared to several baselines and state-of-the-art methods, the proposed methods yield higher accuracies in various classification tasks including video classification and tactile recognition.

cs.CV↗

arXiv2016

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus hurting the detection efficiency. Although the latest Region Proposal Network method gets promising detection accuracy with several hundred proposals, it still struggles in small-size object detection and precise localization (e.g., large IoU thresholds), mainly due to the coarseness of its feature maps. In this paper, we present a deep hierarchical network, namely HyperNet, for handling region proposal generation and object detection jointly. Our HyperNet is primarily based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space. The Hyper Features well incorporate deep but highly semantic, intermediate but really complementary, and shallow but naturally high-resolution features of the image, thus enabling us to construct HyperNet by sharing them both in generating proposals and detecting objects via an end-to-end joint training strategy. For the deep VGG16 model, our method achieves completely leading recall and state-of-the-art object detection accuracy on PASCAL VOC 2007 and 2012 using only 100 proposals per image. It runs with a speed of 5 fps (including all steps) on a GPU, thus having the potential for real-time processing.

cs.CV↗

arXiv2014

High-order S-Lemma with application to stability of a class of switched nonlinear systems

This paper extends some results on the S-Lemma proposed by Yakubovich and uses the improved results to investigate the asymptotic stability of a class of switched nonlinear systems. Firstly, the strict S-Lemma is extended from quadratic forms to homogeneous functions with respect to any dilation, where the improved S-Lemma is named the strict homogeneous S-Lemma (the SHS-Lemma for short). In detail, this paper indicates that the strict S-Lemma does not necessarily hold for homogeneous functions that are not quadratic forms, and proposes a necessary and sufficient condition under which the SHS-Lemma holds. It is well known that a switched linear system with two sub-systems admits a Lyapunov function with homogeneous derivative (LFHD for short), if and only if it has a convex combination of the vector fields of its two sub-systems that admits a LFHD. In this paper, it is shown that this conclusion does not necessarily hold for a general switched nonlinear system with two sub-systems, and gives a necessary and sufficient condition under which the conclusion holds for a general switched nonlinear system with two sub-systems. It is also shown that for a switched nonlinear system with three or more sub-systems, the "if" part holds, but the "only if" part may not. At last, the S-Lemma is extended from quadratic polynomials to polynomials of degree more than $2$ under some mild conditions, and the improved results are called the homogeneous S-Lemma (the HS-Lemma for short) and the non-homogeneous S-Lemma (the NHS-Lemma for short), respectively. Besides, some examples and counterexamples are given to illustrate the main results.

math.OC↗