Researchers are interested in Facial Emotion Recognition (FER) because it could be useful in many ways and has promising applications. The main task of FER is to identify and recognize the original facial expressions of users from digital inputs. Feature extraction and emotion recognition make up the majority of the traditional FER. Deep Neural Networks, specifically Convolutional Neural Network (CNN), are popular and highly used in FER due to their inherent image feature extraction process. This work presents a novel method dubbed as EfficientNet-XGBoost that is based on Transfer Learning (TL) technique. EfficientNet-XGBoost is basically a cascading of the EfficientNet and the XGBoost techniques along with certain enhancements by experimentation that reflects the novelty of the work. To ensure faster learning of the network and to overcome the vanishing gradient problem, our model incorporates fully connected layers of global average pooling, dropout and dense. EfficientNet is fine-tuned by replacing the upper dense layer(s) and cascading the XGBoost classifier making it suitable for FER. Feature map visualization is carried out that reveals the reduction in the size of feature vectors. The proposed method is well-validated on benchmark datasets such as CK+, KDEF, JAFFE, and FER2013. To overcome the issue of data imbalance, in some of the datasets namely CK+ and FER2013, we augmented data artificially through geometric transformation techniques. The proposed method is implemented individually on these datasets and corresponding results are recorded for performance analysis. The performance is computed with the help of several metrics like precision, recall and F1 measure. Comparative analysis with competent schemes are carried out on the same sample data sets separately. Irrespective of the nature of the datasets, the proposed scheme outperforms the rest with overall rates of accuracy being 100%, 98% and 98% for the first three datasets respectively. However, for the FER2013 datasets, efficiency is less promisingly observed in support of the proposed work.

In this article, we have built a prototype of a decentralized IoT based biometric face detection framework for cities that are under lockdown during COVID-19 outbreaks. To impose restrictions on public movements, we have utilized face detection using three-layered edge computing architecture. We have built a deep learning framework of multi-task cascading to recognize the face. For the face detection proposal we have compared with the state of the art methods on various benchmarking dataset such as FDDB and WIDER FACE. Furthermore, we have also conducted various experiments on latency and face detection load on three-layer and cloud computing architectures. It shows that our proposal has an edge over cloud computing architecture.

Clinical methods for dementia detection are expensive and prone to human errors. Despite various computer-aided methods using electroencephalography (EEG) signals and artificial intelligence, a consistent separation of Alzheimer’s disease (AD) and normal-control (NC) subjects remains elusive. This paper proposes a low-complexity EEG-based AD detection CNN called LEADNet to generate disease-specific features. LEADNet employs spatiotemporal EEG signals as input, two convolution layers for feature generation, a max-pooling layer for asymmetric spatiotemporal redundancy reduction, two fully-connected layers for nonlinear feature transformation and selection, and a softmax layer for disease probability prediction. Different quantitative measures are calculated using an open-source AD dataset to compare LEADNet and four pre-trained CNN models. The results show that the lightweight architecture of LEADNet has at least a 150-fold reduction in network parameters and the highest testing accuracy of 98.75% compared to pre-trained models. The investigation of individual layers of LEADNet showed successive improvements in feature transformation and selection for separating AD and NC subjects. A comparison with the state-of-the-art AD detection models showed that the highest accuracy, sensitivity, and specificity were achieved by the LEADNet model.

A program’s bug, fault, or mistake that results in unintended results is known as a software defect or fault. Software flaws are programming errors due to mistakes in the requirements, architecture, or source code. Finding and fixing bugs as soon as they arise is a crucial goal of software development that can be achieved in various ways. So, selecting a handful of optimal subsets of features from any dataset is a prime approach. Indirectly, the classification performance can be improved through the selection of features. A novel approach to feature selection (FS) has been developed, which incorporates the Golden Jackal Optimization (GJO) algorithm, a meta-heuristic optimization technique that draws on the hunting tactics of golden jackals. Combining this algorithm with four classifiers, namely K-Nearest Neighbor, Decision Tree, Quadrative Discriminant Analysis, and Naive Bayes, will aid in selecting a subset of relevant features from software fault prediction datasets. To evaluate the accuracy of this algorithm, we will compare its performance with other feature selection methods such as FSDE (Differential Evolution), FSPSO (Particle Swarm Optimization), FSGA (Genetic Algorithm), and FSACO (Ant Colony Optimization). The result that we got from FSGJO is great for almost all the cases. For many of the results, FSGJO has given higher classification accuracy. By utilizing the Friedman and Holm tests, to determine statistical significance, the suggested strategy has been verified and found to be superior to prior methods in selecting an optimal set of attributes.

The life expectancy of the elderly has substantially increased compared to earlier times. The primary factors are greater awareness of nutrition, the environment, and personal hygiene. Advances in science and technology have also extended the lifespans of the aging population. Traditional care methods are inadequate to address this situation. To maintain the socioeconomic structure, there is a need for the integration of advanced frameworks. In this context, we propose a smart framework called human activity Internet of Things-enabled environment (HAIE) to provide a non-human assistive environment that helps the elderly live independently. Research into aging in place and assistive environments has focused on modernized environments, largely neglecting the impact of technology on the lives of elderly individuals who stay at home. This work addresses the gap by integrating advanced technologies, such as cloud computing and the Internet of Things (IoT). The inclusion of IoT facilitates a smart and automated environment for the elderly. Cloud integration enables the storage of large volumes of data for further analysis and the identification of patterns for future advancements. It also introduces the concept of accessing data from anywhere, on any device, at any time. To validate this work, two primary parameters were considered: accuracy and latency. Through simulation, the proposed HAIE model has demonstrated an accuracy of 93% out of 100 attempts and a latency of 84.35 ms for the deployed case studies under the HAIE framework.

This paper deals with the necessary steps to be followed in upgrading the traditional e-Learning system to the new Adaptive e-Learning system. The framework, which is an important part of the implementation, is also covered in the paper. Before implementing the adaptive learning system, the existing system needs to be reviewed. A survey was conducted to find practical feedback from both the users: students and instructors to recognize their belief about the current e-Learning system. Results are discussed to frame the strategy to implement an adaptive learning system in which the issues of the current system can be addressed. To confirm the feedback, a report from the university LMS has also been taken into account and talked about. There are many open sources available in the market for the implementation of the adaptive e-learning. Along with the conceptual model, various popular LMS has also been discussed. A detailed comparison has also been exercised to identify their features. This paper can help the readers to derive all the components of a conceptual model for an adaptive e-Learning system and choose a suitable LMS for the actual implementation of the model.