Alzheimer's Disease (AD) detection is essential for timely treatment and better patient care. Magnetic Resonance Imaging (MRI) is a technique in which radio waves and magnetic fields are used to capture high-resolution, multi-dimensional representations of brain structures. This high-resolution imaging capability makes MRI a key tool for diagnosing neurological disorders such as Alzheimer's disease. However, the problem is to correctly classify the fresh MRI scans of patients. Researchers have proposed a deep learning-based method for Alzheimer's disease diagnosis using a Siamese Convolutional Neural Network (SCNN) with three ResNet-34 branches trained on structural MRI data. However, this method relies solely on ResNet34 for feature extraction which struggles to preserve spatial relationship due to pooling operations, causing loss of positional information. Other researchers have explored methods like attention mechanisms and 3D convolutional networks to capture spatial dependencies. However, these methods underperform by missing brain complexity or needing high resources without consistent accuracy. In this study, we propose a cognitively inspired approach for classifying MRI images as Non Demented, Very Mild Demented, Mild Demented and Moderate Demented using Siamese Capsule Network (SNNCap). SNNCap uses ResNet-18 for feature extraction and capsule layers to preserve spatial and part-whole relationships in the images. It compares a test image against a few known reference examples per class. This reference-based validation closely mimics cognitive reasoning, improving the system's generalizability. The model achieves strong results on unseen data and demonstrates its effectiveness through classification reports and confusion matrices.

Flipped learning (FL) utilizes blended learning approaches, where students first learn the lesson from preloaded lecture videos (i.e., online lectures). They complete their activities such as assignments, doubt clearing, practical work, real-life problemsolving inside classroom. Learning is directly connected to brain activities, and it becomes crucial to analyze the brain signals to identify the attention level of the learner. In order to analyze students' activity during the lesson, we capture the brain signals of the students and propose a framework for the feature extraction of brain wave (Electroencephalogram (EEG)) signals using variational autoencoder (VAE) in this article. The classification techniques are exploited to identify the weak students in the flipped learning scenario based on their cognitive state; subsequently, cognitive-aware lecture video recommendation system is developed to recommend the non-attentive lecture video/videos to the weak students. This study can be useful for instructors to identify learners who require special care to enhance their learning ability.

Flipped Classroom is an innovative learning pedagogy based on students’ academic engagement inside and outside the classroom. Students take lessons from pre-loaded lecture videos through desktop, tablets and mobiles before coming to the classroom. Inside the classroom, the sole focus is on doubt clearing and problem solving. However, it is very difficult to ensure that students really pay attention while watching lecture videos. This is a concern, given the levels of distraction the students are exposed to in this age of internet. Electroencephalogram (EEG) signals can be captured from brain of students and used to monitor their attention.In this study, we develop an efficient approach of feature engineering to analyze the attention level of students in Flipped Classroom from captured brain wave signals. We process the EEG signals using Fast Fourier Transform (FFT). Subsequently, we apply our proposed novel handcrafted features method to obtain the features. Standard classification methods are employed to test the effectiveness of our designed features. Experimental results demonstrate that our proposed handcrafted features perform better than standard FFT-derived-frequency bands.

In traditional teacher-directed learning pedagogy (direct instruction), an instructor devotes a significant amount of time in delivering the instruction or lesson. As a result, class hours have not been used effectively for critical problem solving, collaborative activities, etc. Flipped learning is an innovative learning pedagogy in which students are allowed to take lesson from pre-recorded lecture videos outside class hours and be active and accountable for their development. Organization of pre-recorded lecture videos play an important role for effective learning. So, attentiveness of the students also depends on the arrangements and organization of the contents of lecture video. Research in this direction of educational technology is unexplored.In this paper, we propose a method to verify whether the organization of lecture videos is effective for the learner to learn the concept. In this proposed method, we suggest the instructors modify the learning materials (lecture video) based on the attention and feedback of the student. Dataset collected at National Institute of Technology Rourkela for the purpose of research in flipped learning is used. Results show the effectiveness of our proposed method.

Various learning pedagogies have been developed, and they are adapted in a large number of institutes in various forms for improving learning ability of individual students. Flipped Learning (FL) model is one popular approach adopted in many higher learning institutions across the globe. In the flipped learning model, students take lesson from pre-loaded lecture videos before they solve critical problems in live classroom unlike other learning modes such as MOOCs (Massive Open Online Courses), Distance Learning, etc. However, student may not remain attentive throughout the video duration before solving critical problems in the live classroom. This may lead to serious learning incompetence over time in this learning pedagogy. In this paper, we analyze cognitive states of an individual student using brain waves signals while taking instructions in the absence of an instructor. The brain waves (Electroencephalogram (EEG)) signal is analyzed using unsupervised learning (clusters) techniques to group similar behaviors exhibited by student over video duration. Based on this analysis, we propose a recommendation technique which detects non-attentive video and suggests for retaking the lesson. This is termed as L ecture Video R ecommendation in F lipped L earning (LRFL) . We validate our approach with the data collected at our laboratory for the research purpose on flipped learning. Results demonstrate the effectiveness of our recommender technique.

Flipped Classroom is a mode of learning which is developed based on students' academic engagement inside and outside the classroom. In this learning pedagogy, students take lessons from pre-loaded lecture videos before coming to the classroom for doubt clearing, discussion, problem solving, etc. However, it is very difficult to ensure that students really pay attention while watching lecture videos. In this paper, we adopt a feature selection technique called 1D local binary pattern (1D-LBP) to analyze captured brain signals of the students. The proposed feature selection technique is termed as 1D Multi-Point Local Ternary Pattern (MP-LTP), which extracts unique statistical features from EEG signals. Subsequently, standard classification techniques are exploited to analyze the attention level of students. Experimental results show that the proposed method outperforms state-of-the-art classification techniques using LBP.