19 February 2024 in VFAST Transactions on Software Engineering
Automatic identification and classification of human actions is one the important and challenging tasks in the field of computer vision that has appealed many researchers since last two decays. It has wide range of applications such as security and surveillance, sports analysis, video analysis, human computer interaction, health care, autonomous vehicles and robotic. In this paper we developed and trained a VGG19 based CNN-RNN deep learning model using transfer learning for classification or prediction of actions and its performance is evaluated on two public actions datasets; KTH and UCF11. The models achieved significant accuracies on these datasets that are equal to 90% and 95% respectively on KTH and UCF11 which beats some of the accuracies achieved by handcraftedfeature based and deep learning based methods on these datasets.
18 August 2024 in VFAST Transactions on Software Engineering
Software quality is one of the most important components of software development. Software quality attracts the user's attention and produces reliable and error-free software. Poor approach strategies lead to less effective outcomes and a higher likelihood of failure. The gap between software quality research and practice is one of the main problems with software quality. The difference between the way software quality research is communicated and the way industry concerns related to software quality is the actual gap.software industries are unaware about rapid technological change, complexities of Modern software systems, security concerns, skill shortage impact on software quality, to overcome theses problems and gaps. Taxonomy is proposed to enhance industry-academia collaboration by facilitating better communication between software quality research and practice. Some of the best quality standards are outlined and authorized in this paper that yields the greatest out-comes. A methodical and goal-oriented strategy is used to develop the proposed taxonomy, with the help of literature review, blogs, articles, and interviews with researchers and practitioners. Twenty distinct questions regarding team co-ordination, dispersion, culture, behaviors and attitudes, experience, and other topics are included in the questionnaire. The taxonomy is evaluated through online survey by implementing it in an industry-academia collaboration project. Researchers and practitioners could use the proposed taxonomy to classify and identify quality concerns or obstacles.