Routing using reinforcement learning in vehicular ad hoc networks

In vehicular ad hoc networks (VANETs), the frequent change in vehicle mobility creates dynamic changes in communication link and topology of the network. Hence, the key challenge is to address and resolve longer transmission delays and reduced transmission stability. During the establishment of routing path, the focus of entire research is on traffic detection and road selection with high traffic density for increased packet transmission. This reduces the transmission delays and avoids carry-and-forward scenarios; however, these techniques fail in obtaining accurate traffic density in real-time scenario due to rapid change in traffic density. Thus, it is necessary to create a model that efficiently monitors the traffic density and assist VANETs in route selection in an automated way with increased accuracy. In this article, a novel machine learning architecture using deep reinforcement learning (DRL) model is proposed to monitor and estimate the data essential for the routing protocol. In this model, the roadside unit maintains the traffic information on roads using DRL. The DRL predicts the movement of the vehicle and makes a suitable routing path for transmitting the packets with improved transmission capacity. It further uses predicted transmission delays and the destination location to choose the forwarding directions between two road safety units (RSUs). The application of DRL over VANETs yields increased network performance, which provides on-demand routing information. The simulation results show that the DRL-based routing is effective in routing the data packets between the source and destination vehicles than other existing method.     

Bilingual text detection from natural scene images using faster R-CNN and extended histogram of oriented gradients

Pattern Analysis and Applications - In today's world, scene text detection is important for a wide range of scientific and industrial processes. Compared with text detection in documents, text...     

A novel Z-source boost derived hybrid converter for PV applications

Analog Integrated Circuits and Signal Processing - This paper proposes a novel Z-source boost derived hybrid converter (ZSBDHC) that produces high gain dual output from a single DC input, which is...     

Enhanced Energy Proficient Encoding Algorithm for Reducing Medium Time in Wireless Networks

Wireless Personal Communications - Providing increased network coding gain is one of the optimum-based medium time problems in wireless networks. This problem is identified using non-linear...     

Thermal degradation of water soluble polymers and their binary blends

The effect of five different metal oxides on the pyrolysis of poly(ethylene oxide) (PEO), polyacrylamide (PAM), and poly(vinyl alcohol) (PVA) was investigated using thermogravimetry. The presence of metal oxide did not influence the degradation of PEO while the order of metal oxide on the degradation rate of PAM and PVA was PbO > Co₃O₄ > CuO > ZnO > Al₂O₃. The miscibility and the decomposition of PEO–PAM and PVA–PAM blends were also investigated. The blends were found to be immiscible and the presence of one polymer did not influence the degradation of the other polymer in the polymer blend. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 101: 233–240, 2006     

Dielectric and conductivity studies on cobalt phthalocyanine tetramers

Electrically conductive organic and metalloorganic polymers are of great interest and they have applications in electronic, optical, photonic, photoelectric, electrochemical, and dielectric devices. Tetrameric cobalt phthalocyanine was prepared by conventional chemical method. The dielectric permittivity of the tetrameric cobalt phthalocyanine sample was evaluated from the observed capacitance values in the frequency range 100 KHz to 5 MHz and in the temperature range of 300 to 383°K. It is found that the system obeys the Maxwell Wagner relaxation of space charge phenomenon. Further, from the permittivity studies AC conductivity was evaluated. The values of AC conductivity and DC conductivity were compared. Activation energy was calculated. To understand the conduction mechanism Mott's variable range hopping model was applied to the system. The T^?1/4 behavior of the DC conductivity along with the values of Mott's Temperature (T₀), density of states at the Fermi energy N (E_F), and range of hopping R and hopping energy W indicate that the transport of charge carriers are by three‐dimensional variable range hopping. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 91: 2529–2535, 2004     

Tolerance design optimization of machine elements using genetic algorithm

An important problem that faces design engineers is how to assign tolerance limits. In practical applications, tolerances are most often assigned as an informal compromise between functionality, quality and manufacturing cost. Frequently, the compromise is obtained iteratively by trial and error. A more scientific approach is often desirable for better performance. In this paper, a genetic algorithm (GA) is used for the design of tolerances of machine elements to obtain the global optimal solution. The objective is to design the optimum tolerances of the individual components to achieve the required assembly tolerance, zero percentage rejection of the components and minimum cost of manufacturing. The proposed procedure using GA is described in this paper for two tolerance design optimization problems: gear train and overrunning clutch assemblies. Results are compared with conventional techniques and the performances are analyzed.     

Fuzzy control of multivariable process by modified error decoupling

In this paper, a control concept for the squared (equal number of inputs and outputs) multivariable process systems is given. The proposed control system consists of two parts, single loop fuzzy controllers in each loop and a centralized decoupling unit. The fuzzy control system uses feedback control to minimize the error in the loop and the decoupler uses an adaptive technique to mitigate loop interactions. The decoupler predicts the interacting loop changes and modifies the input (error) of the loop controller. The controller was tested on the simulation model of "single component vaporizer" process. The results indicate that the decoupling controller shows better performance for set point and load changes.     

Scheduling optimisation of flexible manufacturing systems using particle swarm optimisation algorithm

The increased use of flexible manufacturing systems (FMS) to efficiently provide customers with diversified products has created a significant set of operational challenges. Although extensive research has been conducted on design and operational problems of automated manufacturing systems, many problems remain unsolved. In particular, the scheduling task, the control problem during the operation, is of importance owing to the dynamic nature of the FMS such as flexible parts, tools and automated guided vehicle (AGV) routings. The FMS scheduling problem has been tackled by various traditional optimisation techniques. While these methods can give an optimal solution to small-scale problems, they are often inefficient when applied to larger-scale problems. In this work, different scheduling mechanisms are designed to generate optimum scheduling; these include non-traditional approaches such as genetic algorithm (GA), simulated annealing (SA) algorithm, memetic algorithm (MA) and particle swarm algorithm (PSA) by considering multiple objectives, i.e., minimising the idle time of the machine and minimising the total penalty cost for not meeting the deadline concurrently. The memetic algorithm presented here is essentially a genetic algorithm with an element of simulated annealing. The results of the different optimisation algorithms (memetic algorithm, genetic algorithm, simulated annealing, and particle swarm algorithm) are compared and conclusions are presented .