Deep Learning Approaches for Big Data Analysis

Naomie Salim
2019 Proceeding of the Electrical Engineering Computer Science and Informatics  
Good representations of data eliminate irrelevant variability of the input data, while preserving the information that is useful for the ultimate task. Among the various ways for learning representation is using deep learning methods. Deep feature hierarchies are formed by stacking unsupervised modules on top of each other, forming multiple nonlinear transformations to produce better representations. In this talk, we will first show how deep learning is used for bioactivity prediction of
more » ... l compounds. Molecules are represented as several convolutional neural networks to predict their bioactivity. In addition, a new concept of merging multiple convolutional neural networks and an automatic learning features representation for the chemical compounds was proposed using the values within neurons of the last layer of the CNN architecture. We will also show how the concepts of deep learning is adapted into a deep belief network (DBN) to enhance the molecular similarity searching. The DBN achieves feature abstraction by reconstruction weight for each feature and minimizing the reconstruction error over the whole feature set. The DBN is later enhanced using data fusion to obtain a lower detection error probability and a higher reliability by using data from multiple distributed descriptors. Secondly, we will show how we used deep learning for stock market prediction. Here, we developed a Deep Long Short Term Memory Network model that is able to forecast the crude palm oil price movement with combined factors such as other commodities prices, weather and news sentiments and price movement of crude palm oil. We also show how we combined stock markets price and financial news and deployed the Long Short Term Memory (LSTM), Recurrent Neural Network (RNN), and Word 2 Vector (Word2Vec) to project the stock prices for the following seven days. Finally, we will show how we exploited deep learning method for the opinion mining and later used it to extract the product's aspects from the user textual review for recommendation systems. Specifically, we employ a multichannel convolutional neural network (MCNN) for two different input layers, namely, word embedding layer and Part-of-speech (POS) tag embedding layer. We show effectiveness of the proposed model in terms of both aspect extraction and rating prediction performance. Biography Professor Naomie Salim's main research goal is to design of new algorithms to improve the effectiveness of searching and mining new knowledge from various kinds of datasets, including unstructured, semi-structured and structured databases. The current focus of her research is on chemical databases and text databases to support the process of computer-aided drug design, text summarisation, plagiarism detection, automatic information extraction, sentiment analysis and recommendation systems. Professor Naomie Salim has been involved in 51 research projects out of which she heads 20 of the projects. The projects are in collaboration with colleagues within UTM or with external organisations and communities, to a total value of RM 6.18 million.
doi:10.11591/eecsi.v6.2008 fatcat:gqvjrcios5bl3aendwrlxr5uxu