News and Events

CFP of Array Journal https://www.journals.elsevier.com/array

• Our ambition is to achieve an impact factor in the range of 1.5 – 2.5.
• The journal aspires to be in the Second quartile² in General Computer Science by the year 2025!

CFP of Special Issue “Decision Making in Heterogeneous Network Data Scenarios and Applications” in World Wide Web Journal, IF=2.892 (2019), SJR=Q1, Due: 15 October, 2021. Click Link.

CFP of Special Issue “Detection Models and Computation for Understanding the Frangibility of Complex Networks” in Complexity Journal, IF=2.462, SJR=Q1, Due: 04 December 2020. Click Link.

CFP – “The IEEE ISPA-2020 (18th IEEE International Symposium on Parallel and Distributed Processing with Applications) “, Ranked at CORE-B.  

CFP of Special Issue “Real-time Dynamic Network Learning for Location Inference Modelling and Computing” in Neurocomputing Journal, IF=4.072, SJR=Q1, Due: 15 October 2020. Click Link.

CFP of Special Issue “Dynamical Modeling, Analysis, and Control of Information Diffusion over Social Networks” Due: 24 August 2020. Click Link.

CFP of The 16th International Conference on Advanced Data Mining and Applications On 12-15 November 2020 in Foshan, China. More Information.

CFP of The 2020 IEEE/WIC/ACM International Joint Conference On Web Intelligence And Intelligent Agent Technology (WI-IAT ’20), , 14-17 December 2020, Melbourne, Australia. Website

Online Seminar title: Are SVMs still of interest when meeting deep neural networks
Date and time: 16 June, 2021, Wednesday 1pm in Melbourne time (11am in Perth Time). 

Presenter’s Name: Dr. Zeyi Wen at The University of Western Australia
Abstract: Deep neural networks (DNNs) have been a standard recipe for creating state-of-the-art solutions. As a result, models like Support Vector Machines (SVMs) have been overlooked. While the results from DNNs are encouraging, DNNs also come with their large number of parameters in the model and overheads in long training/inference time. SVMs have excellent properties such as convexity, good generality and efficiency. In this talk, I will highlight some of our recent techniques to enhance SVMs with an automatic pipeline which exploits the context of the learning problem. Experimental results show that SVMs with the pipeline is more efficient, while producing better results than the common usage of SVMs. Additionally, we conduct a case study of our solution on a popular sentiment analysis problem—the aspect term sentiment analysis (ATSA) task. The study shows that our SVM based solution can achieve competitive predictive accuracy to DNN (and even majority of the BERT) based approaches. Furthermore, our solution is about 40 times faster in inference and has 100 times fewer parameters than the models using BERT.

Bio: Dr. Zeyi Wen is a Lecturer in Computer Science at The University of Western Australia (UWA). Before working at UWA, he was a research fellow at National University of Singapore from 2017 to 2019 and The University of Melbourne from 2015 to 2016 after his PhD completion at The University of Melbourne in 2015. Dr. Wen is a winner of 2019 IEEE Transactions on Parallel and Distributed Systems (TPDS) Best Paper Award. His research work has also led to open-source machine learning systems including ThunderGBM and ThunderSVM. His areas of research include machine learning systems, high-performance computing and data mining.

Online Seminar title: Happy Emotion Recognition from Unconstrained Videos Using 3D Hybrid Deep Features
Date and time: 30^th April 2021, Friday 1pm-2pm
Place: Join Zoom Meeting https://deakin.zoom.us/j/84010156600?pwd=RVFiZGYvMnFUeThkdmNNMWhWWXFSdz09 

Meeting ID: 840 1015 6600
Password: 44526519

Presenter’s Name: Najmeh Samadiani
Abstract: Facial expressions have been proven to be the most effective way for the brain to recognize human emotions in a variety of contexts. With the exponentially increasing research for emotion detection in recent years, facial expression recognition has become an attractive, hot research topic to identify various basic emotions. Happy emotion is one of such basic emotions with many applications, which is more likely recognized by facial expressions than other emotion measurement instruments (e.g., audio/speech, textual and physiological sensing). Nowadays, most methods have been developed for identifying multiple types of emotions, which aim to achieve the best overall precision for all emotions; it is hard for them to optimize the recognition accuracy for single emotion (e.g., happiness). Only a few methods are designed to recognize single happy emotion captured in the unconstrained videos; however, their limitations lie in that the processing of severe head pose variations has not been considered, and the accuracy is still not satisfied. In this paper, we propose a Happy Emotion Recognition model using the 3D hybrid deep and distance features (HappyER-DDF) method to improve the accuracy by utilizing and extracting two different types of deep visual features. First, we employ a hybrid 3D Inception-ResNet neural network and long-short term memory (LSTM) to extract dynamic spatial-temporal features among sequential frames. Second, we detect facial landmarks’ features and calculate the distance between each facial landmark and a reference point on the face (e.g., nose peak) to capture their changes when a person starts to smile (or laugh). We implement the experiments using both feature-level and decision-level fusion techniques on three unconstrained video datasets. The results demonstrate that our HappyER-DDF method is arguably more accurate than several currently available facial expression models.

Bio: Najmeh Samadiani received the bachelor’s degree in computer engineering in 2012 and the master’s degree in artificial intelligence in 2014. She was a Lecturer with the Kosar University of Bojnord, Iran, from 2015 to 2018. She is currently third year PhD student at School of IT, Deakin University. Her research interests include image/video processing, human emotion modeling, expert systems, and pattern recognition.

PhD Supervisor: A/Professor Guangyan Huang.

 

Online Seminar title: Learning Heterogeneous Information Networks for Link Prediction
Date and time: 26^th, June, Friday 2pm-3pm
Place: Join Zoom Meeting https://deakin.zoom.us/j/94248110393?pwd=eitSOE1NQjkvQ1NmTG1UZTRoOXNoUT09  

Meeting ID: 942 4811 0393
Password: request by email – jianxin.li at deakin.edu.au

Presenter’s Name: Dr Hungxu Chen
Abstract: The ubiquitous network-structured data is a very important form of Big Data and widely used for modelling complex linked data with a broad spectrum of applications such as bioinformatics, web search, social network analytics, etc. Recently, Network Embedding (NE) techniques are attracting a large amount of research attention, which aim to learn low-dimensional vector representations for vertices such that the structure of the graph can be well preserved. In this talk, Dr. Hongxu Chen will introduce his recent research works on Network Embedding for Heterogenous Information Networks (HIN) in the context of various link prediction tasks. In particular, a series of challenging problems (e.g., heterogeneity, imbalanced distribution, modelling scalability, etc.) in HIN modelling will be discussed.

Short Bio: Dr. Hongxu Chen is now working as a Postdoctoral Research Fellow in Network Science Lab at University of Technology Sydney (UTS). Hongxu completed his Ph.D. in 2019 from The University of Queensland (UQ), Australia. Hongxu’s research interests include data mining, network science, network/graph embedding, recommender systems as well as social networks modelling and analytics. Hongxu has published 16 papers in these research fields, and most of them are in leading journals and conferences, such as KDD, TKDE, ICDE, ICDM, etc.