Prof. Yunghsiang S. Han, IEEE Fellow, School of Electrical Engineering & Intelligentization,  Dongguan University of Technology. Born in Taiwan, China (click) Research Area: error-control coding, wireless networks, and security

Title: Codes over Rings for Distributed Storage Systems

Abstract: Array codes have been widely used in distributed storage systems such as RAID (Redundant Array of Independent Disks). Binary maximum distance separable (MDS) array codes are constructed by encoding k information columns into r parity columns, in which each element in a column is a bit, such that any k out of the k+r columns suffice to recover all information bits. Binary MDS array codes have low computational complexity since the encoding and decoding procedures only involve XOR operations. In addition to the computational complexity, it is critical to improve repair performance in big data storage applications. Specifically, if a single column fails, the goal is to minimize the repair bandwidth by downloading the least amount of bits from d healthy columns, where k<= d<= k+r-1. If one column of an MDS code is failed, it is known that we need to download at least 1/(d-k+1) fraction of the data stored in each of d healthy columns. In this talk, we present a generic binary cyclic ring for designing binary MDS array codes.  We show that EVENODD codes and RDP codes can be viewed as array codes over a special binary cyclic ring with encoding matrix being a Vandermonde matrix, and propose a fast decoding method for EVENODD codes and RDP codes based on an LU factorization of Vandermonde matrix. Moreover, we also present a new construction of Rabin-like codes over the special binary cyclic ring with encoding matrix being a Cauchy matrix and give a fast decoding method for the proposed codes. More importantly, we propose two explicit constructions of new array codes over the generic binary cyclic ring that have optimal repair bandwidth.

Prof. Anu Gokhale, Illinois State University, USA(click) Research Area: Computer science, artificial intelligence

Title: Detecting Happiness Using Hyperspectral Imaging Technology

Abstract: Hyperspectral imaging (HSI) technology can be used to detect human emotions based on the power of material discrimination from their faces. In this paper, HSI is used to remotely sense and distinguish blood chromophores in facial tissues and acquire an evaluation indicator (tissue oxygen saturation, StO 2 ) using an optical absorption model. This study explored facial analysis while people were showing spontaneous expressions of happiness during social interaction. Happiness, as a psychological emotion, has been shown to be strongly linked to other activities such as physiological reaction and facial expression. Moreover, facial expression as a communicative motor behavior likely arises from musculoskeletal anatomy, neuromuscular activity, and individual personality. This paper quantified the neuromotor movements of tissues surrounding some regions of interest (ROIs) on smiling happily. Next, we selected six regions—the forehead, eye, nose, cheek, mouth, and chin—according to a facial action coding system (FACS). Nineteen segments were subsequently partitioned from the above ROIs. The affective data (StO 2 ) of 23 young adults were acquired by HSI while the participants expressed emotions (calm or happy), and these were used to compare the significant differences in the variations of StO 2 between the different ROIs through repeated measures analysis of variance. Results demonstrate that happiness causes different distributions in the variations of StO 2 for the above ROIs; these are explained in depth in the article. This study establishes that facial tissue oxygen saturation is a valid and reliable physiological indicator of happiness and merits further research.

Prof. Rongrong Ji, IEEE Senior Member, “Minjiang”Chair Professor, Fujian Province, School of Informatis,  Xiamen University, China (click) Research Area: Computer Vision, Multimedia and Machine Learning

Title: Semi-Supervised Adversarial Monocular Depth Estimation

Abstract: In this research, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth, i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can improve most state-of-the-art models on the NYUD v2 dataset by effectively.

Prof. Faisal N. Abu-Khzam, IEEE Senior Member, Computer Science and Mathematics Department, Lebanese  American University, Lebanon (click) Research Area: Exact and Parameterized Algorithms, High Performance Computing, Combinatorial Optimization, Graph Theory and Computational Biology

Title: Efficient Parallel Algorithms for Parameterized Problems

Abstract: A parameterized problem is fixed-parameter parallelizable (FPP) if it can be solved in O(f(k)⋅(logN)α) time using O(g(k)⋅Nβ) processors, where N is the input size, k is the parameter and g are arbitrary computable functions, and α, β are constants independent of N and k. We re-examine the k-vertex cover problem from a parameterized parallel complexity standpoint and present a parallel algorithm that outperforms the previous known algorithm: using O(m) instead of O(n²) processors, the running time improves from O(kk) to O(k³logn+1.2738k), where n and m are the number of vertices and edges of the input graph, respectively. This is achieved by first showing that vertex cover kernelization that is based on crown decomposition is in FPP as well. Finally, we consider the use of the recently introduced modular-width parameter. In particular, we show that the weighted maximum clique problem is FPP when parameterized by this auxiliary parameter. 

Prof. Mamoun Alazab,Founder and Chair of IEEE Northern Territory Subsection, Charles Darwin University, Australia (click) Research Area: cybersecurity and digital forensics, Computer science,machine learning,artificial intelligence

Title:Malware Analysis using Artificial Intelligence and Deep Learning

Abstract: Malicious software is one of the most serious threats to information security today. Malware analysis is a fastgrowing field demanding a great deal of attention because of remarkable progress in social networks, cloud and web technologies, ecommerce, mobile environments, smart grids, Internet of Things (IoT), etc. Due to this evolving cyber threat landscape, legacy solutions built on specified rule sets, such as signaturedriven security capabilities, cannot scale to fully meet the demand of advanced malware and other cybercrime detection and prevention. Artificial Intelligence (AI) and Deep Learning (DL) techniques have been successfully applied to many computer applications. These solutions often provide significant improvements as compared to more traditional machine learning methods and have resulted in new industry standards in highly cognitive tasks, ranging from natural language processing to self-driving cars. However, a relatively limited number of studies have applied these powerful techniques for malware analysis. The purpose of this presentation is to describe a recent trend in malware attacks, such as obfuscations,  zeroday exploits, botnet attacks against internet banking applications, the emergence of the darknet, malware-as-a-service.  Signature recognition and anomaly detection are the most common security detection techniques in use today. These techniques provide a strong defense. However, they fall short of detecting complicated or sophisticated attacks. I will also illustrate how new analytics using AI and DL can be used to uncover hidden patterns in malware attacks draw on real-world data. 

Prof. Fenghua Huang, IEEE Member, College of Artificial Intelligence, Yango University, China (click) Research Area: Machine Learning, Big Data, Remote Sensing Application

Title: Automatic Extraction of Impervious Surfaces from High Resolution Remote Sensing Images Based on Deep Learning

Abstract: Due to the complexity of urban surface, the differences in impervious surface materials, the mutual interference between the spectra of ground objects and the huge impact of ground object shadows in high-resolution remote sensing (HRRS) images, it is improper to directly use shallow machine learning algorithms and conventional object-oriented segmentation methods to extract urban impervious surfaces from HRRS images. Therefore, a method for automatic extraction of impervious surfaces from HRRS images based on deep learning (AEISHIDL) is proposed to address this problem. Firstly, the original HRRS images are pre-processed and the Gram-Schmidt algorithm is employed for the fusion of panchromatic and multi-spectral bands in HRRS images. In addition, an enhanced bilateral filtering method considering edge characteristics (EBFCEC) is designed and adopted to remove noises and enhance edges of man-made objects in original HRRS images. Secondly, the EBFCEC filtered images are partitioned into multi-layer object sets by using improved marker watershed based on LAB color space (IMWLCS), and the related objects in different sets are re-segmented to have the same edges through edge integration, after which we extract spectral feature averages and shape feature values of all objects while the convolutional neural network (CNN) is used to calculate the CNN feature averages of all pixel neighborhoods in each object. Finally, the fuzzy c-means clustering (FCM) algorithm is employed jointly considering the spectrum, shape and CNN features of the segmented objects in HRRS images to judge whether the objects belong to impervious surfaces, thereby effectively increasing the accuracy of automatically extracting impervious surfaces. Two different experimental regions are selected from two different types of HRRS images (WorldView 2 and Pléiades-1A) respectively (4 experimental regions in all). The experimental results show that AEISHIDL has higher accuracy and automation level compared with other four representative methods in urban impervious surfaces extraction from HRRS images.

Senior lecturer Peter Shaw, IEEE Member, School of Computer and Mathematics of Massey University, Massey University, New Zealand (click) Research Area: computer science, artificial intelligence, big data, life science information analysis

Title: Combinatorial Text Classification: the effect of multi-parameterized correlation clustering

Abstract: The report will demonstrate the potential of chaining two distinct methodologies in service of topic modelling. The first, as of recent years, is more-or-less standard natural language processing (NLP) with word2vec; the second is graph-theoretical or combinatorial algorithm. Together, we show how they may be used to help classify documents into distinct, but perhaps not disjointed classes. The procedure is demonstrated on a collection of Twitter feeds, or tweets. Heuristics is the basis for this procedure; it is not presumed to perfectly work in every situation, or for every input, and, in fact, it is believed that the procedure will yield better results in a more homogeneous corpora written in some standardized fashion, as written in, e.g.,legal or medical documents.