Safe Driving Distance and Speed for Collision Avoidance in Connected Vehicles.

Vehicle tailgating or simply tailgating is a hazardous driving habit. Tailgating occurs when a vehicle moves very close behind another one while not leaving adequate separation distance in case the vehicle in front stops unexpectedly; this separation distance is technically called "Assured Clear Distance Ahead" (ACDA) or Safe Driving Distance. Advancements in Intelligent Transportation Systems (ITS) and the Internet of Vehicles (IoV) have made it of tremendous significance to have an intelligent approach for connected vehicles to avoid tailgating; this paper proposes a new Internet of Vehicles (IoV) based technique that enables connected vehicles to determine ACDA or Safe Driving Distance and Safe Driving Speed to avoid a forward collision. The technique assumes two cases: In the first case, the vehicle has Autonomous Emergency Braking (AEB) system, while in the second case, the vehicle has no AEB. Safe Driving Distance and Safe Driving Speed are calculated under several variables. Experimental results show that Safe Driving Distance and Safe Driving Speed depend on several parameters such as weight of the vehicle, tires status, length of the vehicle, speed of the vehicle, type of road (snowy asphalt, wet asphalt, or dry asphalt or icy road) and the weather condition (clear or foggy). The study found that the technique is effective in calculating Safe Driving Distance, thereby resulting in forward collision avoidance by connected vehicles and maximizing road utilization by dynamically enforcing the minimum required safe separating gap as a function of the current values of the affecting parameters, including the speed of the surrounding vehicles, the road condition, and the weather condition.

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.

Genetic algorithms with permutation coding for multiple sequence alignment.

Multiple sequence alignment (MSA) is one of the topics of bio informatics that has seriously been researched. It is known as NP-complete problem. It is also considered as one of the most important and daunting tasks in computational biology. Concerning this a wide number of heuristic algorithms have been proposed to find optimal alignment. Among these heuristic algorithms are genetic algorithms (GA). The GA has mainly two major weaknesses: it is time consuming and can cause local minima. One of the significant aspects in the GA process in MSA is to maximize the similarities between sequences by adding and shuffling the gaps of Solution Coding (SC). Several ways for SC have been introduced. One of them is the Permutation Coding (PC). We propose a hybrid algorithm based on genetic algorithms (GAs) with a PC and 2-opt algorithm. The PC helps to code the MSA solution which maximizes the gain of resources, reliability and diversity of GA. The use of the PC opens the area by applying all functions over permutations for MSA. Thus, we suggest an algorithm to calculate the scoring function for multiple alignments based on PC, which is used as fitness function. The time complexity of the GA is reduced by using this algorithm. Our GA is implemented with different selections strategies and different crossovers. The probability of crossover and mutation is set as one strategy. Relevant patents have been probed in the topic.