Transportation networks respond differently to applied policies. The Tehran Metropolitan Area has one of the most complex networks with complex users, which has experienced many of these policies change within the past decades. In this study, some of these policies and their effect on air pollution is investigated. The goal is to pinpoint the variables which have the most effect on various transportation models and investigate how new policies should be focused. In order to do so, long-term variations of air pollution monitoring stations were analyzed. Results show that the most significant parameter that may affect air pollution is users' behavior due to the lack of a public transportation network and its level of comfort. The results of this study will be useful in developing new policies and evaluating their long-term consequences in appropriate models.
One of the basic parameters which describes road traffic is Annual Average Daily Traffic (AADT). Its accurate determination is possible only on the basis of data from the continuous measurement of traffic. However, such data for most road sections is unavailable, so AADT must be determined on the basis of short periods of random measurements. This article presents different methods of estimating AADT on the basis of daily traffic (VOL), and includes the traditional Factor Approach, developed Regression Models and Artificial Neural Network models. As explanatory variables, quantitative variables (VOL and the share of heavy vehicles) as well as qualitative variables (day of the week, month, level of AADT, the cross-section, road class, nature of the area, spatial linking, region of Poland and the nature of traffic patterns) were used. Based on comparisons of the presented methods, the Factor Approach was identified as the most useful.
The aim of this study is to find the cost design of RC tension with varying conditions using the Artificial Neural Network. Design constraints were used to cover all reliable design parameters, such as limiting cross sectional dimensions and; their reinforcement ratio and even the beahviour of optimally designed sections. The design of the RC tension members were made using Indian and European standard specifications which were discussed. The designed tension members according to both codes satisfy the strength and serviceability criteria. While no literature is available on the optimal design of RC tension members, the cross-sectional dimensions of the tension membersfor different grades of concrete and steel, and area of formwork are considered as the variables in the present optimum design model. A design example is explained and the results are presented. It is concluded that the proposed optimum design model yields rational, reliable, and practical designs.
Journal bearings are the most common type of bearings in which a shaft freely rotates in a metallic sleeve. They find a lot of applications in industry, especially where extremely high loads are involved. Proper analysis of the various bearing faults and predicting the modes of failure beforehand are essential to increase the working life of the bearing. In the current study, the vibration data of a journal bearing in the healthy condition and in five different fault conditions are collected. A feature extraction method is employed to classify the different fault conditions. Automatic fault classification is performed using artificial neural networks (ANN). As the probability of a correct prediction goes down for a higher number of faults in ANN, the method is made more robust by incorporating deep neural networks (DNN) with the help of autoencoders. Training was done using the scaled conjugate gradient algorithm and the performance was calculated by the cross entropy method. Due to the increased number of hidden layers in DNN, it is possible to achieve a high efficiency of 100% with the feature extraction method.
The 802.11ax standard final specification is expected in 2019, however first parameters are just released. The target of the new standard is four times improvement of the average throughput within the given area. This standard is dedicated for usage in dense environment such as stadiums, means of municipal communication, conference halls and others. The main target is to support many users at the same time with the single access point. The question arises if the new standard will have higher throughput then previous ones in the single user mode. The author calculated the maximal theoretical throughput of the 802.11ax standard and compared the results with the throughput of older 802.11 standards such as 802.11n and 802.11ac. The new he-wifi-network example included in the ns-3.27 release of the NS-3 simulator was used to simulate the throughput between the access point and the user terminal. The results indicate that in some conditions the 802.11ac standard has higher throughput than the new 802.11ax standard.
Wireless Sensor Networks (WSNs) have existed for many years and had assimilated many interesting innovations. Advances in electronics, radio transceivers, processes of IC manufacturing and development of algorithms for operation of such networks now enable creating energy-efficient devices that provide practical levels of performance and a sufficient number of features. Environmental monitoring is one of the areas in which WSNs can be successfully used. At the same time this is a field where devices must either bring their own power reservoir, such as a battery, or scavenge energy locally from some natural phenomena. Improving the efficiency of energy harvesting methods reduces complexity of WSN structures. This survey is based on practical examples from the real world and provides an overview of state-of-the-art methods and techniques that are used to create energyefficient WSNs with energy harvesting.
The prediction of machined surface parameters is an important factor in machining centre development. There is a great need to elaborate a method for on-line surface roughness estimation [1-7]. Among various measurement techniques, optical methods are considered suitable for in-process measurement of machined surface roughness. These techniques are non-contact, fast, flexible and tree-dimensional in nature.
The optical method suggested in this paper is based on the vision system created to acquire an image of the machined surface during the cutting process. The acquired image is analyzed to correlate its parameters with surface parameters. In the application of machined surface image analysis, the wavelet methods were introduced. A digital image of a machined surface was described using the one-dimensional Digital Wavelet Transform with the basic wavelet as Coiflet. The statistical description of wavelet components made it possible to develop the quality measure and correlate it with surface roughness [8-11].
For an estimation of surface roughness a neural network estimator was applied [12-16]. The estimator was built to work in a recurrent way. The current value of the Ra estimation and the measured change in surface image features were used for forecasting the surface roughness Ra parameter. The results of the analysis confirmed the usability of the application of the proposed method in systems for surface roughness monitoring.
In this paper an artificial neural network, which realizes a nonlinear adaptive control algorithm, has been applied in a control system of variable speed generating system. The speed is adjusted automatically as a function of load power demand. The controller employs a single layer neural network to estimate the unknown plant nonlinearities online. Optimization of the controller is difficult because the plant is nonlinear and no stationary. Furthermore, it deals with the situation where the plant becomes uncontrollable without any restrictive assumptions. In contrast to previous work [1] on the same subject, the number of neural networks has been reduced to only one network. The number of the neurons in a network structure as well as choosing certain design parameters was specified a priori. The computer test results have been presented to show performance of proposed neural controller.
The paper deals with linear circuits synthesis with periodic parameters. It was proved that the time-varying voltages and currents of inner branches of such circuits can be calculated using linear recursive equations with periodic coefficients if signals on port are given. The stability theorem of periodic solution was formulated. Hereby described the synthesis problems appear when compensation of power supply systems is considered.
This article describes queueing systems and queueing networks which are successfully used for performance analysis of different systems such as computer, communications, transportation networks and manufacturing. It incorporates classical Markovian systems with exponential service times and a Poisson arrival process, and queueing systems with individual service. Oscillating queueing systems and queueing systems with Cox and Weibull service time distribution as examples of non-Markovian systems are studied. Jackson's, Kelly's and BCMP networks are also briefly characterized. The model of Fork-Join systems applied to parallel processing analysis and the FES approximation making possible of Fork-Join analysis is also presented. Various types of blocking representing the systems with limited resources are briefly described. In addition, examples of queueing theory applications are given. The application of closed BCMP networks in the health care area and performance evaluation of the information system is presented. In recent years the application of queueing systems and queueing networks to modelling of human performance arouses researchers' interest. Hence, in this paper an architecture called the Queueing Network-Model Human Processor is presented.
In the paper the squared voltage-current functionals are minimized, which represent the global power losses in the network. In that way it is possible to find the voltage-current distributions on the net without the use of immitance operators and basing only on the Kirchhoff laws. Farther the individual branch parameters are defined in the syntheses process. Many optimal power analysis examples are also shown to illustrate the thesis included in the paper.
Malignant melanomas are the most deadly type of skin cancer, yet detected early have high chances of successful treatment. In the last twenty years, the interest in automatic recognition and classification of melanoma dynamically increased, partly because of appearing public datasets with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task due to uneven sizes of datasets, huge intra-class variation with small interclass variation, and the existence of many artifacts in the images. One of the most recognized methods of melanoma diagnosis is the ABCD method. In the paper, we propose an extended version of this method and an intelligent decision support system based on neural networks that uses its results in the form of hand-crafted features. Automatic determination of the skin features with the ABCD method is difficult due to the large diversity of images of various quality, the existence of hair, different markers and other obstacles. Therefore, it was necessary to apply advanced methods of pre-processing the images. The proposed system is an ensemble of ten neural networks working in parallel, and one network using their results to generate a final decision. This system structure enables to increase the efficiency of its operation by several percentage points compared with a single neural network. The proposed system is trained on over 5000 and tested afterwards on 200 skin moles. The presented system can be used as a decision support system for primary care physicians, as a system capable of self-examination of the skin with a dermatoscope and also as an important tool to improve biopsy decision making.