This paper proposes a novel approach to analyzing and managing electricity consumption using a clustering algorithm and a high-accuracy classifier for smart meter data. The proposed method utilizes a multilayer Perceptron neural network classifier optimized by an Imperialist Competitive Algorithm (ICA) called ICA-optimized MLP, and a CD Index based on Fuzzy c-means to optimally determine representative load curves. A case study involving a real dataset of residential smart meters is conducted to validate the effectiveness of the proposed method, and the results demonstrate that the ICA-optimized MLP method achieves an accuracy of 98.62%, outperforming other classification methods. This approach has the potential to improve energy efficiency and reduce costs in the power system, making it a promising solution for analyzing and managing electricity consumption.

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 critical a large amount of rail data. Reliability of telecommunication infrastructure is required to increase productivity, maintain safety and reduce maintenance costs. In this article, the existing reliability level and all relevant parameters (the number of network outages and the time between network failures, MTBF) of the railway optical transmission telecommunication network are obtained through the Reliability block diagram method and simulated through the Monte Carlo method and then optimized. Also, prediction of the network's behavior and obtaining the probability of its failures are done through three-layer Perceptron neural networks and the results are presented. The network implemented in this article is the 654 km long optical telecommunication transmission network of the railway region of Azerbaijan.

neural network is one of the most widely used algorithms in the field of machine learning, On the other hand, neural network training is a complicated and important process. Supervised learning needs to be organized to reach the goal as soon as possible. A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. Hence, in this paper, it is attempted to use improve Stud GA to find optimal weights for multi-layer Perceptron neural network. Stud GA is improved from genetic algorithms that perform information sharing in a particular way. In this study, chaotic system will be used to improve Stud GA. The comparison of proposed method with Imperialist Competitive Algorithm, Quad Countries Algorithm, Stud GA, Cuckoo Optimization Algorithm and Chaotic Cuckoo Optimization Algorithm on tested data set (Wine, Abalone, Iris, WDBC, PIMA and Glass) with determined parameters, as mentioned the proposed method has a better performance.

This paper shows how we can make advantage of using genetic programming in selection of suitable features for automatic modulation recognition. Automatic modulation recognition is one of the essential components of modern receivers. In this regard, selection of suitable features may significantly affect the performance of the process. In this research we implemented our model by using appropriate software and hardware platforms. Simulations were conducted with 5db and 10db SNRs. We generated test and training data from real ones recorded in an actual communication system. For performance analysis of the proposed method a set of experiments were conducted considering signals with 2ASK, 4ASK, 2PSK, 4PSK, 2FSK and 4FSK modulations. The results show that the selected features by the suggested model improve the performance of automatic modulation recognition considerably. During our experiments we also reached the optimum values and forms for mutation and crossover ratio, elitism policy, fitness function as well as other parameters for the proposed model.

Introduction Population growth and migration of (from or to) cities has led to the construction of unstructured and large changes in the spatial structure and expansion of cities. This causes changes in the surface of the earth and the conversion of natural effects of the earth such as soil and vegetation to the urban texture. So, the first consequence of the expansion of cities is land use change. Today, land use change and land cover have become a major challenge in many countries. Hence, the study of these changes plays a major role in the world's environmental studies. In order to better manage natural and human ecosystems and develop long-term planning, it is necessary to model land use changes and predict future changes. Methodology The research method is applied in terms of purpose and the nature and method of descriptive-analytic research, and the method of data collection in this study is also a library research. In this study, for land use changes during the 29-year period, images were first provided from the website of the Geological Survey of the United States. Then, using ENVI software, the pre-processing operation was performed to apply atmospheric and radiometric corrections. Also, the specimens of educational and supervised classification of images for land use in four levels (lands, rice field, forests, gardens and Water zone) were studied. Then, in the IDRISI SELVA software, simulation was used to predict future changes using the Perceptron neural network. Results and Discussion Before the main analysis of the data and the extraction of the information, it is necessary to perform the pre-processing operation. Then several time satellite images used in the research after atmospheric and radiometric corrections were used to prepare the land use map and Maximum likelihood algorithm was used to classify the desired classes. The selection of effective variables in predicting urban growth is an important and useful information for the user to understand the desirability of land use change. Therefore, in the present study, distance variables from the road are considered as independent static variables, and distance from the landfill, distance from the land, and the distance from the forest and gardens are considered as independent variables were used. Among the models that are used in the simulation of land use change, neural networks are multilayered Perceptron. Therefore, this model was used to simulate land use changes in this study. Finally, according to the Kramer coefficient, the distance from the road has the least effect and the distance variable of the land has the greatest impact on land use change and transmission potential modeling. Then, user-potential mapping maps were generated through multi-layer Perceptron neural networks for an 8-year time span. Also, in the maps produced, regions with a warm color spectrum have the greatest potential for change, and are more vulnerable to areas with a cool color spectrum. Conclusion Today, land use change and land cover have become a major challenge in many countries. These changes have a direct impact on environmental components such as soil, water and atmosphere. Which This causes changes in the surface of the earth and the conversion of natural effects of the earth such as soil and vegetation to the urban texture. Due to the fact that the city of Lahijan, like many other cities in Iran, has faced expansion of construction in recent years, so, today, the city has undergone significant changes in land use. The purpose of this study is to model and predict land use changes using the Multilayer Perceptron, . In this regard, in order to implement this model, Landsat classified satellite images for the four periods of 1989, 2000, 2010 and 2018, as well as four independent variables including distance from the road, distance from Shalizar, distance from the forest and gardens, And and distance from the land, were built to simulate land use changes. The study resulted in the generation of transmission potential mapping with the 84. 58 accuracy index, which shows that the distance from the land constructed the greatest impact and the distance from the road has the least effect on land use change variations.

Revealing the faults, one of the essential steps in seismic interpretation, provides valuable information for modeling static and dynamic characteristics of hydrocarbon reservoirs. Several methods developed for automatic fault and fracture detection, which seismic attributes integrated with artificial neural networks, and fuzzy systems are the most common ones. In this study, a 3D seismic data set of the F3 Block, offshore Netherland, was utilized for enhanced fault detection using an artificial neural network and unconventional seismic attributes integration. A steering cube was computed using a phase-based dip calculation technique to enhance seismic attributes’ accuracy and target detection capability. The fault enhancement filter, as a combination of the diffusion and median filters, and conventional attributes are modified and redefined along with the dip and azimuth information. A supervised, fully connected multi-layer Perceptron neural network was constructed to integrate the previous traditional seismic attributes with optimum parameters to generate a fault probability cube. For an improved interpretation, the fault probability cube is then treated through the unconventional seismic attributes. Finally, the end product is subjected to the voxel connectivity filter to visualize the detected faults’ three-dimensional nature. Our proposed workflow results were superposed with the ones derived from the color-based inversion cube as an accurate inversion method. The proposed automatic fault extraction workflow can yield considerable savings in time and result in a highly detailed mapping of discontinuities.

Introduction: Acute appendicitis is the most common cause of admittance of patients with abdominal pain to hospital and appendectomy is the most commonly performed emergency surgery. Despite significant advances in the field of diagnosis, a significant number of negative appendectomies are reported. In this study, the design and evaluation of artificial neural networks to help diagnose acute appendicitis was investigated.Methods: In this descriptive study, variables affecting the diagnosis were identified through literature review. Then, these variables were categorized in the form of a checklist, and evaluated and prioritized by general surgery specialists. The sample size was determined as 181 cases to train and evaluate the performance of neural networks. The database was created using records of patients who had undergone appendectomy during 2015 in Modarres Hospital, Tehran, Iran. Then, different architectures of artificial multilayer Perceptron (MLP) neural network were implemented and compared in MATLAB environment to determine the optimal diagnostic performance. Parameters such as specificity, sensitivity, and accuracy were used for network assessment.Results: Comparison of the optimal output of the MLP with pathological results showed that the sensitivity, specificity, and accuracy of the diagnosis network were 68.8%, 82%, and 78.5%, respectively. Based on the existing standards and the general surgeons’ opinions, the MLP network improved diagnostic accuracy for acute appendicitis.Conclusion: The designed MLP can model the performance of an expert with acceptable accuracy. The use of this MLP in clinical decision support systems can be useful in the reduction of negative references to medical centers, timely diagnosis, prevention of negative appendectomy, reduction of the duration of hospitalization, and reduction of medical expenses.

Prediction of temperature as one of the most important climate parameters in different management areas and natural water resources, droughts, environmental studies, flood risk, food shortages, development of pests and diseases, transportation and etc., of special importance in determine future policy for the optimization of resources and spending costs, control and prevent crisis and has use of resources. In this study, through information monthly average temperature of Sanandaj Synoptic Stations in 38-year statistical period (2001-1964), as input Multilayer Perceptron network, the monthly average temperature was predicted during the years (2005-2002) to determine error model. For this purpose, used the features and functions available in environment programming MATLAB software, advantage was taken. Then the performance evaluation model by statistical criteria, including regression and correlation relationships between observed and predicted values of temperature and addressed the relative mean error percent. The results show good efficiency and acceptable accuracy of artificial neural networks in predicting the temperature. So that the correlation coefficient equal to 0/99 and the mean percentage error of the model with 1/97 percent., ie prediction is network true, the temperature difference of less than one degree Celsius temperature Therefore, using this method, temperature conditions can be defined beforehand, and involved water and natural resources management.

Stock market forecasting is a challenging task for investors and researchers in the financial market due to highly noisy, nonparametric, volatile, complex, non-linear, dynamic and chaotic nature of stock price time series. With the development of computationally intelligent method, it is possible to predict stock price time series more accurately. Artificial neural networks (ANNs) are one of the most promising biologically inspired techniques. ANNs have been widely used to make predictions in various research. The performance of ANNs is very dependent on the learning technique utilized to train the weight and bias vectors. The proposed study aims to predict daily Tehran Exchange Dividend Price Index (TEDPIX) via the hybrid multilayer Perceptron (MLP) neural networks and metaheuristic algorithms which consist of genetic algorithm (GA), particle swarm optimization (PSO), black hole (BH), grasshopper optimization algorithm (GOA) and grey wolf optimization (GWO). We have extracted 18 technical indicators based on the daily TEDPIX as input parameters. Therefore, the experimental result shows that grey wolf optimization has superior performance to train MLPs for predicting the stock market in metaheuristic-based.