8:00 Session 5 – Image Analysis I (Chair: Dr. Nitin Naik)

  • 8:00 Improved SLAM Method based on Dynamic Objects Detecting with the Fusion of Vision and Lidar
    Ren Zhang, Yitian Li, and Lu Lou
  • 8:20 Image Fusion for Remote Sizing of Hot High Quality Steel Sections
    Y. Lin, P. Wang, R. Muroiwa, S. Pike, and L. Mihaylova
  • 8:40 Fast Lane Detection based on Improved Enet for Driverless Cars
    Boyi Li, Yi Zhao, and Lu Lou
  • 9:00 An Improved SLAM Based on the Fusion of Lidar and Monocular Vision
    Yitian Li, Ren Zhang, Qihuan Li, and Lu Lou

9:20 – 10:00 BREAK

10:00 Session 6 – Neural Networks, Deep Learning & Applications I (Chair: Prof. Longzhi Yang)

  • 10:00 Discrete-time Recurrent Neural Network for Solving Multi-linear M-tensor Equation
    Huanmei Wu, Shuqiao Wang, Xiujuan Du, and Mei Liu
  • 10:20 An Approach to Implementing Convolutional Neural Network Based on Low Density FPGA
    Hanzhong Zhang, Qihuan Li, Xin Bai, Zhengxia Wang, and Lu Lou
  • 10:40 Syntactic Dependency Constraint based Graph Convolutional Network for Aspect Level Sentiment Classification
    Jinpeng You, Dazhen Lin, Donglin Cao, and Fei Chao
  • 11:00 Fast and Accurate 3D Reconstruction of Plants Using MVSNet and Multi-View Images
    Zhen Chen, Hui Lv, Lu Lou, and John H. Doonan
  • 11:20 Detecting and Tracking the Moving Vehicles Based on Deep Learning
    Jia Yan, Zhengxia Wang, Yitian Li, Zhen Chen, Xiaoyun Chen, and Lu Lou

11:40 – 12:00 BREAK

12:00 Keynote 2: Prof. Emma Hart (Chair: Dr. Thomas Jansen)

“Towards the Autonomous Evolution of Robotic Ecosystems”

Abstract: From its very beginnings, Evolutionary Computation has been used as a tool to design artefacts, starting with the very first optimisation of a joint plate at the Technical University of Berlin in 1965. Since then, advances in computing (CPU power, simulation engines), materials science, and engineering (3D printing, automated assembly) have considerably enhanced our ability to apply evolution to design tasks, producing optimised and even creative solutions. A natural extension to this is to apply evolution to design moving artefacts, e.g. robots, in which both body and brain must be evolved. In this talk I will describe a vision to create an evolution-powered disruptive robotic technology in which robots are created, reproduce and evolve in real-time and real space without human intervention. The long-term vision is of a technology that enables the evolution of entire autonomous robotic ecosystems that live and work for long periods in challenging and dynamic environments where there is insufficient knowledge to enable human design, e.g. exploring new planets or decommissioning a nuclear reactor. The vision brings new challenges both in engineering and in computational intelligence … the talk will give a high level overview of some of the ways these challenges can be tackled and touch briefly on the ethics of designing an “automated robot factory”.

13:00 – 14:00 LUNCH BREAK

14:00 Session 7 – Data Mining and Data-Driven Approaches II (Chair: Prof. Trevor Martin)

  • 14:00 Comparative Analysis of K-Means and Traversal Optimisation Algorithms
    David Ada Adama, Timilehin Yinka Olatunji, Salisu Wada Yahaya, and Ahmad Lotfi
  • 14:20 Emojional: Emoji Embeddings
    Elena Barry, Shoaib Jameel, and Haider Raza
  • 14:40 Q-Routing Using Multiple QoS Metrics in SDN
    Douglas Harewood-Gill, Trevor Martin, and Reza Nejabati
  • 15:00 Creating a Hierarchical Fuzzy System to Assess Physical Activity Levels from Fitbit Data
    F. A. Chaudhry, J. M. Garibaldi, and N. Qureshi
  • 15:20 Fuzzy Multi-Criteria Decision-Making: Example of an explainable classification framework
    Hesham Yusuf, Kai Yang, and George Panoutsos

15:40 16:00 BREAK

16:00 Session 8 – Neural Networks, Deep Learning & Applications II (Chair: Prof. Dan Neagu)

  • 16:00 Faster RCNN Hyperparameter Selection for Breast Lesion Detection in 2D Ultrasound Images
    Anu Bose, Tuan Nguyen, Hongbo Du, and Alaa AlZoubi
  • 16:20 Asymmetric Convolution View Adaptation Networks for Skeleton-based Human Action Recognition
    Tianyu Ma, Jiahui Yu, Hongwei Gao, and Zhaojie Ju
  • 16:40 Towards a Framework for Interpretation of CNN Results with ANFIS
    Muhammad Ismail, Changjing Shang, and Qiang Shen

17:00 Business meeting (Chair: Prof. Qiang Shen): All delegates are welcome to attend