School of Computer Science and Informatics

Permanent URI for this collection

https://hdl.handle.net/2086/63

Browse

Browsing School of Computer Science and Informatics by Type "Presentation"

Now showing 1 - 5 of 5
  • Thumbnail Image
    ItemOpen Access
    Evolutionary computation for dynamic optimization problems
    (ACM Press, 2013-07) Yang, Shengxiang
  • Thumbnail Image
    ItemOpen Access
    Evolutionary Computation for Dynamic Optimization Problems
    (ACM Press, 2015-07) Yang, Shengxiang
    Many real-world optimization problems are subject to dynamic environments, where changes may occur over time regarding optimization objectives, decision variables, and/or constraint conditions. Such dynamic optimization problems (DOPs) are challenging problems for researchers and practitioners in decision-making due to their nature of difficulty. Yet, they are important problems that decision-makers in many domains need to face and solve. Evolutionary computation (EC) is a class of stochastic optimization methods that mimic principles from natural evolution to solve optimization and search problems. EC methods are good tools to address DOPs due to their inspiration from natural and biological evolution, which has always been subject to changing environments. EC for DOPs has attracted a lot of research effort during the last twenty years with some promising results. However, this research area is still quite young and far away from well-understood. This tutorial aims to summarise the research area of EC for DOPs and attract potential young researchers into the important research area. It will provide an introduction to the research area of EC for DOPs and carry out an in-depth description of the state-of-the-art of research in the field regarding the following five aspects: benchmark problems and generators, performance measures, algorithmic approaches, theoretical studies, and applications. Some future research issues and directions regarding EC for DOPs will also be presented. The purpose is to (i) provide clear definition and classification of DOPs; (ii) review current approaches and provide detailed explanations on how they work; (iii) review the strengths and weaknesses of each approach; (iv) discuss the current assumptions and coverage of existing research on EC for DOPs; and (v) identify current gaps, challenges, and opportunities in EC for DOPs.
  • Thumbnail Image
    ItemOpen Access
    Examining the behaviours of recent malware exploiting the COVID19 pandemic
    (2020-11-24) Yerima, Suleiman
    The current COVID-19 climate has led to an increase in social engineering-based malware infections worldwide, as malicious actors exploit people’s anxieties and changes in working patterns brought about by the pandemic. Cybercriminals have been using COVID19-themed emails and fraudulent websites to entice Internet users into downloading malware so as to gain a foothold on their systems or networks. These types of malware attacks are set to continue as the pandemic is far from over, with many parts of the world experiencing resurgence of the COVID-19 virus after the easing of lockdown measures. Hence, this talk will focus on recent malware that have been designed to exploit the pandemic to inflict damage to individuals and organizations. The infection methods used by such malware will be discussed, and their various techniques, behaviour and impact will be analyzed. This will not only raise our collective awareness about the COVID-19 related malware but will also provide some technical insight that will enhance preventive and defensive efforts to curb the spread of such malware.
  • Thumbnail Image
    ItemOpen Access
    Mobile malware detection with machine learning: state of play and emerging challenges
    (2019-11-12) Yerima, Suleiman
    Malware (or malicious software) on the mobile platform has been growing at an astonishing rate since smartphones started becoming popular over a decade ago. Android, the dominant mobile operating system worldwide, has been relentlessly targeted by malicious actors who have capitalized on its openness and global reach to monetize their malware. According to the 2019 Q1 McAfee Mobile Threat Report, more than 6 million new pieces of mobile malware were discovered in the wild in 2018 alone. Unfortunately, new malware is highly evasive to detection by traditional signature-based antivirus scanning. The shortcomings of the traditional anti-malware solutions have led to the emergence of research in machine learning (ML) based malware detection approaches in the last few years. Whilst the research results in this area has been encouraging, some challenges still remain. This talk will present the evolution of mobile malware and the state-of-the art research in machine learning based detection of Android malware. It will also discuss some emerging challenges and opportunities in the field of ML-based malware detection. The speaker will also present results of some of the recent research in ML-based malware detection that is being conducted at De Montfort University’s Cyber Technology Institute.
  • Thumbnail Image
    ItemOpen Access
    Nurturing the digital transformation aspirations of micro-businesses in Nigeria: A strategy formulation approach using photo-elicitation
    (DSA Conference, 2023-06-28) Owoseni, Adebowale; Tolani, Adedamola
    Micro businesses in developing countries are increasingly adopting digital technologies to improve their operations and competitiveness. However, the process of digital transformation is unstructured, lacking a clear strategy. In countries like Nigeria, micro businesses play a critical role in the economy, therefore it is important to consider a structured approach to support micro business digital transformation (mbDT) aspirations, to ensure that they can fully benefit from the advantages that technology can bring. This study proposed a strategy formulation approach for mbDT using the photo-elicitation technique and in-depth interviews. In this study, 18 micro business owners in Nigeria were interviewed using photographs to gather insights on their perspective of digital transformation. This approach helped researchers to gain a deeper understanding of the challenges faced by these businesses and to develop strategies that are tailored to their specific needs. The analysis of the pictures and interview data revealed the figurative meaning of digital transformation and what it represents. Key contributions of the study are twofold: first, it communicates digital transformation in metaphors, in a way that aligns with the social structure of micro-businesses, taking into account language, experience, and level of literacy. Second, it proposed an inclusive and tailored approach to strategy formulation, addressing the barriers faced by micro businesses. These contributions will help to foster a culture of innovation and experimentation among micro businesses in Nigeria, encouraging them to explore new digital technologies and business models, identify new opportunities and remain competitive in the ever-changing digital landscape.