A developing methodology that may be used in intelligent transportation frameworks is Vehicular Ad hoc Networks (VANETs). For VANET systems to be dependable, routing protocols are necessary. The innovative paradigm Reliability Based Multi-Objective Optimized Routing Protocol for VANETs (RBMOORPV) is proposed in this research. The structure consists of three levels: the modelling of the VANET network at level 1, the routing condition at level 2, which is dependent on dependability and a meta heuristic algorithm at level 2, and the routing algorithm at level 3. The following step describes the real network through an optimization block. The overall structure also has an optimization block, which regulates the reliability, meta heuristic algorithm, and routing blocks' individual characteristics. The Pelican Optimization Algorithm (POA) provides the basis for the optimization, which is given from a multi-objective standpoint. This covers the stages of exploration and exploitation. Two levels were used to accomplish the evaluation. The first was the RBMOORPV evaluation on the basis of the network simulator, and the second was the POA evaluation utilizing benchmarking mathematical functions. The acquired measures, such as delta metric, set coverage, Packet Delivery Ratio (PDR), hyper-volume, and End to End (E2E) delay, show that POA and RBMOORPV with POA are superior to their base techniques.

Children with autism spectrum disorder (ASD) exhibit deficiencies in the socio-communicative domain and commonly struggle with emotion perception and expression. Robots are becoming increasingly prevalent in our lives, notably in the medical field. Some therapists at therapeutic centers are beginning to experiment with techniques such as computer games, Online exchanges that are available and robot-assisted therapy. Robot-assisted therapy has been widely proven to provide a reliable and effective intervention for enhancing communication and social skills in children having ASD. The humanoid robot may grab the attention of young children and later draw the interest of researchers. This study is accomplished through the use of a revolutionary technique based on deep learning algorithms that comprises essential data and understanding about patients, diagnostic procedures, and medicines. A robot therapist can transmit the results responsibly using this paradigm. Here parameter tunned CNN based model are used and the model is achieved with an accuracy rate of 96% in ASD detection.