Publications

  1. "Automated Repair of Asymmetric Web Pages during Resolution of Mobile Friendly Problems" Md. Aquib Azmain, Kishan Kumar Ganguly. The 16th International Conference on Evaluation of Novel Approaches to Software Engineering, ENASE 2021. [PDF] [Certificate] [Presentation]

    This conference held online from April 26 to 27, 2021. I presented the paper as Conference Speaker. Check out the video of that presentation.
  2. "Impact of label noise and efficacy of noise filters in software defect prediction", Shihab Shahriar Khan, Md. Aquib Azmain, Nishat Tasnim Niloy, and Ahmedul Kabir. The 32nd International Conference on Software Engineering and Knowledge Engineering, SEKE 2020, USA, pages 347-352. [PDF]
  3. "On the Evolutionary Properties of Fix Inducing Changes", Syed Fatiul Huq (Sujoy), Md. Aquib Azmain, Nadia Nahar and Md. Tawhid, QuASoQ 2020 in conjunction with the 27th Asia-Pacific Software Engineering Conference (APSEC 2020). [PDF]
Research Experience
  • Improving symmetric structure during resolution of mobile friendly problems in web pages: Mobile friendly problem (MFP) causes the low quality of the website visibility and has a potential risk to decrease usability for a mobile user. The solution proposed an automatic repair technique that generates symmetric mobile friendly patches for a web page. [PDF]
  • On the evolutionary properties of fix inducing changes: Analyzing Fix-Inducing Changes (developer code that introduce bugs) provides the opportunity to estimate bugs beforehand. This study analyzes the evolution of FICs to visualize patterns associated with the introduction of bugs throughout and within project releases. [PDF]
  • Noise filters in software defect prediction: By using a diverse set of classifiers, imbalance-methods and noise filters, this study empirically investigates how the presence of label noise in post-release defect prediction datasetsaffect performance and evaluates the effectiveness of noisefilters in minimizing the adverse effects of noise. [PDF]
  • An Improved Creative Adversarial Network: A novel method for painting generation that explicitly seeks to maximize creativity of produced paintings is proposed. Our method reinterprets and formalizes the notion of creativity and borrows ideas from adversarial sample generation to propose a simple and efficient algorithm for creative art generation. [PDF]
  • Towards the detection and refactoring of message chains: Message Chain is a code smell which occurs when inefficient responsibility delegations create chains of consequent method calls, resulting incode that becomes difficult to interpret and maintain. This study proposes a method of detecting and suggesting the refactoring for Message Chains. [PDF]
  • A machine learning-based inference and analysis of crop production based on climate parameters in Bangladesh: Using standard approaches of machine learning – linear regression, support vector machine, random forest and more – this study provides appropriate prediction models for all the crops considered and infers the numeric effect of various climate factors on the unit production of the crops. [PDF]