Southeast University

About: Southeast University is a education organization based out in Nanjing, China. It is known for research contribution in the topics: MIMO & Control theory. The organization has 66363 authors who have published 79434 publications receiving 1170576 citations. The organization is also known as: SEU.

Deep Direct Reinforcement Learning for Financial Signal Representation and Trading

Abstract: Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks.

Abstract: In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

Facial Age Estimation by Learning from Label Distributions

Abstract: One of the main difficulties in facial age estimation is that the learning algorithms cannot expect sufficient and complete training data. Fortunately, the faces at close ages look quite similar since aging is a slow and smooth process. Inspired by this observation, instead of considering each face image as an instance with one label (age), this paper regards each face image as an instance associated with a label distribution. The label distribution covers a certain number of class labels, representing the degree that each label describes the instance. Through this way, one face image can contribute to not only the learning of its chronological age, but also the learning of its adjacent ages. Two algorithms, named IIS-LLD and CPNN, are proposed to learn from such label distributions. Experimental results on two aging face databases show remarkable advantages of the proposed label distribution learning algorithms over the compared single-label learning algorithms, either specially designed for age estimation or for general purpose.

CircRNA: a novel type of biomarker for cancer

Abstract: Circular RNAs (circRNAs) are a class of long, non-coding RNAs molecules that shape a covalently closed continuous loop which have no 5'-3' polarity and contain no polyA tail. CircRNAs also possess relatively jarless framework and are highly tissue-specific expressed in the eukaryotic transcriptome. Emerging evidences have discovered that thousands of endogenous circRNAs are present in mammalian cells and they mediate gene expression at the transcriptional or post-transcriptional level by binding to microRNAs or other molecules and then inhibit their function. Similarly, increasing evidence indicates that circRNAs may play a role in the development of several types of diseases, including atherosclerotic vascular disease risk, neurological disorders, prion diseases, osteoarthritis and diabetes. Furthermore, circRNAs exhibit aberrant expression in multiform types of cancer, including colorectal cancer, hepatocellular carcinoma and pancreatic ductal adenocarcinoma. And based on the function of circRNAs in cancer, we believe that circRNAs may serve as diagnostic or tumor promising biomarkers. Moreover, it will provide a new therapeutic target for the treatment of cancer.