Implementation of an Intelligent Exam Supervision System Using Deep Learning Algorithms.

Examination cheating activities like whispering, head movements, hand movements, or hand contact are extensively involved, and the rectitude and worthiness of fair and unbiased examination are prohibited by such cheating activities. The aim of this research is to develop a model to supervise or control unethical activities in real-time examinations. Exam supervision is fallible due to limited human abilities and capacity to handle students in examination centers, and these errors can be reduced with the help of the Automatic Invigilation System. This work presents an automated system for exams invigilation using deep learning approaches i.e., Faster Regional Convolution Neural Network (RCNN). Faster RCNN is an object detection algorithm that is implemented to detect the suspicious activities of students during examinations based on their head movements, and for student identification, MTCNN (Multi-task Cascaded Convolutional Neural Networks) is used for face detection and recognition. The training accuracy of the proposed model is 99.5% and the testing accuracy is 98.5%. The model is fully efficient in detecting and monitoring more than 100 students in one frame during examinations. Different real-time scenarios are considered to evaluate the performance of the Automatic Invigilation System. The proposed invigilation model can be implemented in colleges, universities, and schools to detect and monitor student suspicious activities. Hopefully, through the implementation of the proposed invigilation system, we can prevent and solve the problem of cheating because it is unethical.

Neuro-fuzzy system based proportional derivative gain optimized attitude control of CubeSat under LEO perturbations.

Prompt attitude stabilization is more challenging in Nano CubeSat due to its minimal capacity, weight, energy, and volume-constrained architecture. Fixed gain non-adaptive classical proportional integral derivative control methodology is ineffective to provide optimal attitude stability in low earth orbit under significant environmental disturbances. Therefore, an artificial neural network with fuzzy inference design is developed in a simulation environment to control the angular velocity and quaternions of a CubeSat by autonomous gain tuning of the proportional-derivative controller according to space perturbations. It elucidates the dynamics and kinematics of the CubeSat attitude model with reaction wheels and low earth orbit disruptions, i.e., gravity gradient torque, atmospheric torque, solar radiation torque, and residual magnetic torque. The effectiveness of the proposed ANFIS-PD control scheme shows that the CubeSat retained the three-axis attitude controllability based on initial quaternions, the moment of inertia, Euler angle error, attitude angular rate, angular velocity rate as compared to PID, ANN, and RNN methodologies. Outcomes from the simulation indicated that the proposed controller scheme achieved minimum root mean square errors that lead towards rapid stability in roll, pitch, and yaw axis respectively within 20 s of simulation time.

Improving the Survival Time of Multiagents in Social Dilemmas through Neurotransmitter-Based Deep Q-Learning Model of Emotions.

In multiagent systems, social dilemmas often arise whenever there is a competition over the limited resources. The major challenge is to establish cooperation among intelligent virtual agents for solving the situations of social dilemmas. In humans, personality and emotions are the primary factors that lead them toward a cooperative environment. To make agents cooperate, they have to become more like humans, that is, believable. Therefore, we hypothesize that emotions according to the personality give birth to believability, and if believability is introduced into agents through emotions, it improves their survival rate in social dilemma situations. The existing researches have introduced different computational models to introduce emotions in virtual agents, but they lack emotions through neurotransmitters. We have proposed a neurotransmitters-based deep Q-learning computational model in multiagents that is a suitable choice for emotion modeling and, hence, believability. The proposed model regulates the agents' emotions by controlling the virtual neurotransmitters (dopamine and oxytocin) according to the agent's personality. The personality of the agent is introduced using OCEAN model. To evaluate the proposed system, we simulated a survival scenario with limited food resources in different experiments. These experiments vary the number of selfish agents (higher neuroticism personality trait) and the selfless agents (higher agreeableness personality trait). Experimental results show that by adding the selfless agents in the scenario, the agents develop cooperation, and their collective survival time increases. Thus, to resolve the social dilemma problems in virtual agents, we can make agents believable through the proposed neurotransmitter-based emotional model. This proposed work may help in developing nonplayer characters (NPCs) in games.

An Intelligent Cost-Efficient System to Prevent the Improper Posture Hazards in Offices Using Machine Learning Algorithms.

In this research, an intelligent and cost-efficient system has been proposed to detect the improper sitting posture of a person working at a desk, mostly in offices, using machine learning classification techniques. The current era demands to avoid the harms of an improper posture as it, when prolonged, is very painful and can be fatal sometimes. This study also includes a comparison of two arrangements. Arrangement 01 includes six force-sensitive resistor (FSR) sensors alone, and it is less expensive. Arrangement 02 consists of two FSR sensors and one ultrasonic sensor embedded in the back seat of a chair. The K-nearest neighbor (KNN), Naive Bayes, logistic regression, and random forest algorithms are used to augment the gain and enhanced accuracy for posture detection. The improper postures recognized in this study are backward-leaning, forward-leaning, left-leaning, and right-leaning. The presented results validate the proposed system as the accuracy of 99.8% is achieved using a smaller number of sensors that make the proposed prototype cost-efficient with improved accuracy and lower execution time. The proposed model is of a dire need for employees working in offices or even at the residential level to make it convenient to work for hours without having severe effects of improper posture and prolonged sitting.