Computational Intelligence For Data Analysis

At present, vehicular traffic flow prediction is treated as a crucial issue in the intelligent transportation system. It mainly focuses on the estimation of vehicular traffic flow on roadways or stations in the subsequent time interval ahead of the future. Generally, traffic flow prediction comprises two major stages, namely feature learning and predictive modeling. In this view, this paper introduces an Intelligent Vehicular Traffic Flow Prediction (IVTFP) model to effectively predict the flow of traffic on the road. The proposed IVTFP model involves two main stages, namely feature selection (FS) and classification. At the first level, the whale optimization algorithm (WOA) is applied as a feature selector called WOA-FS to select the useful subset of features. Next, in the second level, the multiple linear regression (MLR) technique is utilized as a prediction model to forecast the traffic flow. The performance of the IVTFP model takes place on the benchmark Brazil dataset. The simulation outcome indicated the effective outcome of the IVTFP model, and it ensured that the application of the WOA-FS model helps attain improved classification outcomes.

Smart vehicle frames have many special uses and frameworks designed to improve road safety and productivity. We are experiencing rapid advances in advanced Inter Vehicular Communication (IVC) designed by Intelligent Transportation Systems (ITS) to allow the collection, evaluation, and dissemination of applicable data. These frameworks allow you to screen, monitor, and control different parts of the road. The main research to regulate the behavior of the driver is focused on two issues: the formation of identifiable patterns in the test and the grouping of the characteristics of the driver's behavior. In this research proposal, we will have a layout of a Rule-Based Fuzzy Polynomial Neural Networks system based on their behavior in different profiles. Given our reproductive system, we have had the opportunity to speak accurately with the control model, but the main probability models show that the observer rating works relatively well with the sophisticated models.

Utilizing intelligent navigation systems necessitates the development of effective methods for assessing road conditions. This comprises real-time root data collection from the road network and forecasting the evolution of route characteristics, which are frequently dependent on incomplete or erroneous data from vehicle detectors. This article presents an overview of the imputation capabilities of artificial immune systems that are suited for future Internet services allowed by OpenFlow. OpenFlow technology enables network operations, protocol segmentation, and an integrated management layer in routers and switches. OpenFlow enables major changes in the behavior of the networks and protocols with which it is related. Numerous services are not offered actively. As a result, this article is titled Artificial Immune System (AIS) Algorithm-Based Traffic Prediction, which describes how this algorithm is utilized to anticipate long-term underlying causes. Data on urban data flow are used to make predictive estimations of data sensitivity. The simulation results demonstrate that the proposed sequence achieves the same accuracy as random predictions while requiring fewer blocks than standard solutions.

Traffic congestion is a crucial issue that raises the uncertainty level of the traveling duration resulting in high stress and unsafe traffic scenarios. Effective traffic estimation and forecasting via Intelligent Transportation Systems (ITS) applications are beneficial in a variety of applications. The process of accurately and rapidly predicting the traffic condition helps the travelers to determine the traveling path and make decisions wisely. This paper develops a new deep learning (DL) based traffic density estimation and prediction model for ITS. The proposed model involves a set of two DL models, namely convolutional neural network (CNN) and long short term memory (LSTM) for traffic density estimation and prediction. These models are applied, and the results are analyzed under diverse situations. The experimental outcome indicated that the LSTM model is superior to CNN on both estimation and prediction processes.

Fog computing helps us to extend the facility from the cloud center to edge networks. As this technology has advantages, we want to implement this in the transportation system as it plays an important role in everyone’s life. In the urban area, the traffic has rapidly increased, which costs a lot of time, consumes more fuel, and leads to accidents. A combination of fog computing and vehicle network will help in real-time in various transportation sectors and help to access the data from anywhere. The system should be such that it can analyze and store the data much faster than the systems available till now, so in this paper, we will be focusing on reducing the latency with advanced algorithms in data transferring between the fog and edge layers. Reducing latency is a major challenge in many communication systems. We will be discussing its application and the internal processing in the fog layers with advanced algorithms. This will improve the system capabilities and performance to a further extent which will be useful in ITS. Finally, the chapter focuses on challenges and issues with ITS (intelligent transportation system) and the future scope.

In the present scenario, due to urban development and population growth, the usage of transportation has increased significantly. This has caused serious issues of traffic congestions, accidents, lack of lane discipline, etc. Due to this reason, the Government of India has come up with a new initiative of building 100 smart cities. The main aim of smart cities mission is to build well-sophisticated roads and infrastructure to accommodate all the commutation needs. This project also helps to construct smart pavements for the future use of introducing autonomous vehicles to make traveling safer and comfortable for the people. The transportation network in smart cities uses various technologies like sensors and data acquisition devices integrated with networks to monitor the movement of vehicles on the road. The data obtained from sensors is processed by DAQ devices to provide surrounding information to network and vehicles to travel without any problem of delay. The processed data is huge to store in local hardware and difficult to share between the nodes. The captured data from the monitoring devices is saved for future uses. Big Data analytics is used to assess and filter out crucial elements of the processed data and it is stored for future use. The predictions of traffic are made by using various analytical methods. This chapter focuses on the technologies being used for the integration of sensors with DAQ devices via wireless communication technologies in the transportation network. The integrated network of sensors and DAQ devices is implemented in traffic management, lane discipline, parking management, environment assistance systems, reduces pollution and accidents.

The surge in the use of fossil fuels has led to the alarming depletion of these resources. To save the non-renewable resources with a greener environment, battery electric vehicles (BEV) have been invented. However, the primary charging source of BEV is through the conventional grid. This does not fulfill the overall objective of having a BEV, as presently, electricity supplied to the grid is generated by nonrenewable sources. In this work, a standalone Solar PV array system has been developed to effectively charge the BEV battery and supply the excess electricity generated to an IEEE 5 Bus system. The power flow control logic has been developed to realize switching between various modes. The PID controller is used to eliminate the transients occurring in inverter output. The MATLAB simulations show that excellent transient overvoltage protection has been achieved with the effective utilization of surplus electricity by the proposed control scheme.

Hyperloop is a new, better, and more efficient mode of transportation that is being proposed in this paper as an alternative to India’s railway and airport network with the benefit of better and more efficient performance at lower overall costs. This revolutionary hyperloop system consists of a capsule traveling through a tube (which is built underground) under a light vacuum (not exactly zero atmospheric pressure but close to zero) suspended on air bearings along the tube. The movement of the capsule is taken care of by a set of linear electromagnetic accelerators attached to the tube. The tube is held on concrete columns so that the tube is straight, and the capsule can follow a straight trajectory. The capsule can travel at transonic speeds (up to 1126 kmph), resulting in a 30-40-minute travel time between Chennai and Hyderabad (around 627 km) compared to an overnight train journey or a much more expensive 1-hour 15- minute flight.