جستجوی مقالات مرتبط با کلیدواژه « شبکه عصبی پرسپترون » در نشریات گروه « عمران »

Today, a huge amount of data is transmitted around the world through the high capacity of optical telecommunication networks. In railways, optical transmission telecommunication networks play a very important role in the transmission of vital rail data and the safety of movement. Reliability stability of telecommunication infrastructure is essential in increasing productivity, maintaining safety and reducing maintenance costs. In this article, the existing reliability level and all relevant parameters (the number of network outages and the duration between network failures, MTBF) of the railway optical transmission telecommunication network to obtain the number of blocked railway lines through the block diagram method (Reliability block diagram model) created and simulated through the Monte Carlo method and then optimized with the aim of reducing line blocking, considering that with each network failure, rail lines are blocked, the number of network outages is equal to line blocking. Therefore, with optimization, the reliability of the line blocking network is reduced. Also, predicting the behavior of the network and obtaining the probability of its failure is done through perceptron three-layer neural networks and its results are presented. The network implemented in this article is an optical telecommunication transmission network. The railway zone of Azerbaijan is 654 km long.

urban population, especially in developing countries, is increasing gradually. Optimal use of land plays an important role in planning and urban development management. This principle is especially important in achieving sustainable development in urban areas. Not-principles Exploitation causing destruction and degradation of resources. Study dynamics of land use changes and their broad impacts on the environment, it is essential to understanding how these changes occur, both in terms of spatial pattern and in terms of its quantity. In this article, it was noticed to simultaneously apply spatial information and remote sensing information to study and model land use change in order to Isfahan city. land use maps using Landsat images for the years 1997, 2008 and 2017 manufacturing and maps of 1: 25000 scalewere used to better identify the area, land reference and geometric correction of satellite images. Transmission potential modeling using perceptron multi-layered artificial neural network algorithm was down. Through certain dynamic variables include distance from academic centers, distance from industrial centers, distance from residential areas, distance from passages as well as digital elevation modelas a static variable; then, The amount of each land use conversion is predicted with the Markov chain and the total map of land use change made with two models of hard prediction and soft prediction in the LCM model.The results ofland use transformation potential modeling in all submodels showed over 95% accuracy. the calculation of accuracy of the prediction model, i.e. the kappa coefficient equal to 0.9 was obtained. The results obtained from the study of changes and prediction of land use indicate the development of urban areas Isfahan. These changes also indicate that decrease of other land use classes. According to the results of the LCM model over the whole span, the urban lands have increased from 21239 hectares in 1997 to 23607 hectares in 2017; this upward trend will continue into the future. In modeling and according to the results of the Markov chain model, the urban lands will reach 24023 hectares by 2027.

Knowing the quantity of generated solid waste play a very significant role in solid waste management programs in a region. Due to lack of measured data as well as unavoidable errors in measurements, assessment of volume of generated solid waste is always challenging. Also, field measurement and continues monitoring of the volume of solid waste is usually costly, difficult and time-consuming. Accurate prediction of solid waste generation can be regarded as a key factor in future solid waste management system planning. Conventional forecasting methods in solid waste generation forecasting frequently use the demographic and socioeconomic factors in a per capita basis. In most cases, insufficient funds, the limited measuring equipment, lack of appropriate management systems and due to the lack of recorded data for the volume of generated solid waste cause many problems in integrated solid waste systems management (Dyson and Chang, 2005). In this study, three computational intelligence techniques including M5P model trees, support vector machines (SVM) and multi-layer perceptron (MLP) artificial neural network are utilized to predict solid waste generation in Hormozgan Province, Iran. After a sensitivity analysis, four more influential factors including elevation, population, urban development index (measures the level of development in cities based on infrastructure, the municipality established year, the metropolitan area, population, city product and income, health and education) and the frequency of garbage collection were considered in developing models. The performance of proposed models in solid waste generation forecasting are assessed via different error evaluation indices and finally the results are compared.