The outbreak of COVID – 19 and the consequent lockdown of commercial activities in 2020 put many developing nations like Nigeria amid sporadic ICT knowledge revolution, as new vistas in communication technology that had hitherto been neglected emerged. The closure of schools created challenges that almost eroded the three major purposes of tertiary institutions vis àvis education, advancement of knowledge, and outreach. Many students became idle with sharp rise in social vices and cybercrimes. Concerted effort were made to ameliorate this problem through online lessons but findings revealed that students’ inability to access e – learning platforms and learning materials, poor attendance of students,  social isolation and distraction from home inhibited the effectiveness thus the reopening of schools for physical learning. Recently there are advocacy for Blended learning (BL) as Post - Covid strategy to enhance quality and sustainable education as well as to maintain ‘new normal’. This paper, therefore, examines the concept of quality and sustainable education as well as the concept and challenges of blended learning. Challenges relating to the use of technology, social cohesion, mental health and wellbeing of students and lecturers were identified as possible hindrances to effective blended learning. The use of E-Counselling technologies was recommended to counsellors as strategies for deploying counselling services to assist the students and lecturers in achieving quality and sustainable blended learning.

This paper is on the development of an intelligent drowsy driver detection system using a deep neural network algorithm. The goal is to build an adaptive system that follows, monitors, and detects when a driver is displaying critical drowsy signs while driving. This was achieved using computer vision and deep neural network approach which was configured as convolutional neural network architecture. At the end of the training process, the features were classified and labelled as perfect driving condition, sensing drowsy behavior and critical drowsy behavior. The critical sleepy symptoms are a categorization of potentially harmful sleepy characteristics including sleep, micro sleep and face down while driving. The categorization of minor sleepy traits entails features such as yawning, eye blinking and other drowsy symptoms while the perfect driving conditions are attributes such as two eyes open with a focused gaze. The system was implemented with MATLAB and tested in real live scenarios and the result showed a drowsy detection accuracy of 98.7%.