-Face spoofing attack is one of the recent security traits that face recognition systems are proven to be vulnerable to. The spoofing occurs when an attacker bypass the authentication scheme by presenting a copy of the face image for a valid user. Therefore, it's very easy to perform face recognition spoofing attack with compare to other biometrics. This paper, addresses the problem of detecting imposter face image from live image. In practically, we address this problem from texture analysis point of view because the printed face usually has less quality defect that can be observed by extracting texture features. We adopt Local graph structure LGS to extract the features. Moreover, LGS is based on applying a dominant graph into the input image and it's proved to be a powerful texture operator. Finally, extensive experimental analysis on NUAA showed an encouraging performance.

Background: The Covid-19 pandemic has imposed adaption to virtual learning for students and educators across all levels of education in the world. The effectiveness of virtual learning varies amongst age groups. It has been suggested that the adoption of virtual learning will continue to be implemented even after pandemic, particularly in higher education. Therefore, it is crucial to validate the effectiveness of a virtual learning approach among university students to ensure a smooth transition from a conventional education model to a hybrid education model. Thus, this study aims to evaluate the impact of virtual learning on students’ performance in a virtual classroom. Methods: We analysed survey data collected from undergraduate students at Multimedia University, Malaysia. Convenience sampling and self-administered online surveys were used to understand the impact of virtual learning. Multiple regression analysis was performed using SPSS software Results: A total of 210 first and second year degree and diploma students responded to the online surveys. Factors affecting virtual learning were segregated into three categories: virtual teaching techniques, technology issues, and environment distraction. Respondents stated that the critical factor that affect the effectiveness of virtual learning and impacts on students’ performance was the virtual teaching techniques employed by educators. Conclusions: This study concluded that virtual teaching techniques have significant impact on students’ performance whereas technology issues and environment distraction do not significantly influence students’ performance during virtual learning. Although this study is limited to students from Multimedia University, it lays the groundwork for future research to involve students from other universities or other countries. A future study can address more factors that affect virtual learning and students’ performance, such as students’ attitude and motivation.

No abstract

No abstract

Background Owing to low cost and ubiquity, human activity recognition using smartphones is emerging as a trendy mobile application in diverse appliances such as assisted living, healthcare monitoring, etc. Analysing this one-dimensional time-series signal is rather challenging due to its spatial and temporal variances. Numerous deep neural networks (DNNs) are conducted to unveil deep features of complex real-world data. However, the drawback of DNNs is the un-interpretation of the network's internal logic to achieve the output. Furthermore, a huge training sample size (i.e. millions of samples) is required to ensure great performance. Methods In this work, a simpler yet effective stacked deep network, known as Stacked Discriminant Feature Learning (SDFL), is proposed to analyse inertial motion data for activity recognition. Contrary to DNNs, this deep model extracts rich features without the prerequisite of a gigantic training sample set and tenuous hyper-parameter tuning. SDFL is a stacking deep network with multiple learning modules, appearing in a serialized layout for multi-level feature learning from shallow to deeper features. In each learning module, Rayleigh coefficient optimized learning is accomplished to extort discriminant features. A subject-independent protocol is implemented where the system model (trained by data from a group of users) is used to recognize data from another group of users. Results Empirical results demonstrate that SDFL surpasses state-of-the-art methods, including DNNs like Convolutional Neural Network, Deep Belief Network, etc., with ~97% accuracy from the UCI HAR database with thousands of training samples. Additionally, the model training time of SDFL is merely a few minutes, compared with DNNs, which require hours for model training. Conclusions The supremacy of SDFL is corroborated in analysing motion data for human activity recognition requiring no GPU but only a CPU with a fast- learning rate.