An expert system based on wavelet transform and radon neural network for pavement distress classification

Nowadays, pavement distresses classification becomes more important, as the computational power increases. Recently, multi-resolution analysis such as wavelet decompositions provides very good multi-resolution analytical tools for different scales of pavement analysis and distresses classification. In this paper an expert system is proposed for pavement distress classification. A radon neural network, based on wavelet transform expert system is used for increasing the effectiveness of the scale invariant feature extraction algorithm. Wavelet modulus is calculated and Radon transform is then applied to the wavelet modulus. The features and parameters of the peaks are finally used for training and testing the neural network. Experimental results demonstrate that the proposed expert system is an effective method for pavement distress classification. The test performances of this study show the advantages of proposed expert system: it is rapid, easy to operate, and have simple structure.     

Presenting a traffic management and control system in driver assistance form based on vehicular networks

Vehicular Networks is considered a major step in the field of Intelligent Transportation System (ITS). In this technology, some equipment will be installed on vehicles and special places at roadsides which will enable the wireless communication between vehicles with each other and will provide the communication between the vehicles and roadside equipment. One of the ITS application is Traffic monitoring system. Such system enables accessing traffic videos by traffic monitoring centers to make traffic decision. However, providing traffic video for the vehicles can be appealing. This paper addresses a new application in vehicular networks and ITS which can provide this videos for drivers in a city. Each driver request timely traffic video of a location from a web server and the web server forward this request to a stream management server. This server based on current location of the requester vehicle, its speed and its direction calculates appropriate video chunks for each RSU along vehicle destination. This study aims to present a system which can bring a high accessibility for content and can provide it with an appropriate bandwidth and quality for vehicles. Due to the scalability and bandwidth limitations for its content and streaming, vehicular networks are used in this system.     

Palladium(II)‐Catalyzed Decarboxylative Heck Arylations of Acyclic Electron‐Rich Olefins with Internal Selectivity

Despite the recent emergence of decarboxylative C C bond forming reactions, methodologies providing internally arylated electron‐rich olefins are still lacking. We herein report on palladium(II)‐catalyzed decarboxylative Heck arylations of linear electron‐rich olefins with excellent selectivity for the internal position. The method allows a variety of electron‐rich linear olefins to undergo arylation with ortho‐functionalized aromatic carboxylic acids, including heterocycles. The reaction mechanism has been explored with ESI‐MS studies to confirm previous findings, and to reveal the formation of a highly stable palladium complex as a result of the Heck product reacting with the catalyst.

     

Gradient‐based back‐propagation dynamical iterative learning scheme for the neuro‐fuzzy inference system

In this paper, a gradient‐based back propagation dynamical iterative learning algorithm is proposed for structure optimization and parameter tuning of the neuro‐fuzzy system. Premise and consequent parameters of the neuro‐fuzzy model are initialized randomly and then tuned by the proposed iterative algorithm. The learning algorithm is based on the first order partial derivative of the output with respect to the structure parameters. The first order derivative of the model output with respect to the structure parameters determines the sensitivity of the model to structure parameters. The sensitivity values are then used to set the tuning factors and parameters updating step sizes. Therefore, an adaptive dynamical iterative scheme is achieved which adapts the learning procedure to the current state of the performance during the optimization process. Larger tuning step sizes make the convergence speed higher and vice versa. In this regard, this parameter is treated according to the calculated sensitivity of the model to the parameter. The proposed learning algorithm is compared with the least square back propagation method, genetic algorithm and chaotic genetic algorithm in the neuro‐fuzzy model structure optimization. Smaller mean square error and shorter learning time are sought in this paper, and the performance of the proposed learning algorithm is versified regarding these criteria.     

Design,Synthesis, and Fabrication of Chitosan/Hydroxyapatite Composite Scaffold for Use as Bone Replacement Tissue by Sol–Gel Method

Journal of Inorganic and Organometallic Polymers and Materials - Injuries or bone defects are phenomena that are harmful to human health. In the field of bone scaffold tissue engineering,...     

Effect of carbon nanotube network morphology on thin film transistor performance

The properties of electronic devices based on carbon nanotube networks (CNTNs) depend on the carbon nanotube (CNT) deposition method used, which can yield a range of network morphologies. Here, we synthesize single-walled CNTs using an aerosol (floating catalyst) chemical vapor deposition process and deposit CNTs at room temperature onto substrates as random networks with various morphologies. We use four CNT deposition techniques: electrostatic or thermal precipitation, and filtration through a filter followed by press transfer or dissolving the filter. We study the mobility using pulsed measurements to avoid hysteresis, the on/off ratio, and the electrical noise properties of the CNTNs, and correlate them to the network morphology through careful imaging. Among the four deposition methods thermal precipitation is found to be a novel approach to prepare high-performance, partially aligned CNTNs that are dry-deposited directly after their synthesis. Our results provide new insight into the role of the network morphologies and offer paths towards tunable transport properties in CNT thin film transistors.      

GA and ICA approaches to job rotation scheduling problem: considering employee’s boredom

This paper presents a new model dealing with the job rotation scheduling problem, which is less studied, focusing on human characteristics such as boredom. Existing literature on conceptualizing boredom shows that researchers evaluate boredom in terms of exposure to the same tasks. We developed it to “exposure to similar tasks” and defined its functionality based on the need of assigning jobs with more similarity to each worker in the smallest period of planning which lowers the external interruption effect on worker’s concentration. To address the imbalance between number of jobs and that of workers in many industrial settings, we developed a multi-period imbalance assignment model. The proposed model is to rotate workers during a given planning horizon such that the total cost including assignment and boring cost will be minimized. The applicability of the model is described by presenting some real cases and validated through solving several randomly produced test problems by using Lingo software. Two search algorithms, genetic algorithm (GA) and imperialist competitive algorithm (ICA), designed to conquer the algorithmic complexity of model and their parameters adjusted using Taguchi’s method were used. The efficiency of algorithms is shown, comparing it with Lingo computation times, and it is shown that ICA solutions have better quality than GA solutions as well.