Filters

2019 - 201912020 - 20254
Reset filters

Settings

Subject: Artificial Neural Network

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Article
    Citation - WoS: 7
    Citation - Scopus: 10
    Ann-Assisted Forecasting of Adsorption Efficiency To Remove Heavy Metals
    (Tubitak Scientific & Technological Research Council Turkey, 2019) Buaısha, Magdi; Balku, Şaziye; Yaman, Şeniz Özalp; Özalp Yaman, Şeniz
    In wastewater treatment, scientific and practical models utilizing numerical computational techniques suchas artificial neural networks (ANNs) can significantly help to improve the process as a whole through adsorption systems.In the modeling of the adsorption efficiency for heavy metals from wastewater, some kinetic models have been used such as pseudo first-order and second-order. The present work develops an ANN model to forecast the adsorption efficiency of heavy metals such as zinc, nickel, and copper by extracting experimental data from three case studies. To do this, we apply trial-and-error to find the most ideal ANN settings, the efficiency of which is determined by mean square error (MSE) and coefficient of determination (R2). According to the results, the model can forecast adsorption efficiency percent (AE%) with a tangent sigmoid transfer function (tansig) in the hidden layer with 10 neurons and a linear transferfunction (purelin) in the output layer. Furthermore, the Levenberg–Marquardt algorithm is seen to be most ideal for training the algorithm for the case studies, with the lowest MSE and high R2 . In addition, the experimental results and the results predicted by the model with the ANN were found to be highly compatible with each other.
  • Thumbnail Image
    Article
    Citation - WoS: 7
    Citation - Scopus: 10
    Comparison of Three Different Learning Methods of Multilayer Perceptron Neural Network for Wind Speed Forecasting
    (Gazi Univ, 2021) Bulut, Mehmet; Tora, Hakan; Buaisha, Dr.magdi; Buaisha, Magdi
    In the world, electric power is the highest need for high prosperity and comfortable living standards. The security of energy supply is an essential concept in national energy management. Therefore, ensuring the security of electricity supply requires accurate estimates of electricity demand. The share of electricity generation from renewables is significantly growing in the world. This kind of energy types are dependent on weather conditions as the wind and solar energies. There are two vital requirements to locate and measure specific systems to utilize wind power: modelling and forecasting of the wind velocity. To this end, using only 4 years of measured meteorological data, the present research attempts to estimate the related speed of wind within the Libyan Mediterranean coast with the help of ANN (artificial neural networking) with three different learning algorithms, which are Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient. Conclusions reached in this study show that wind speed can be estimated within acceptable limits using a limited set of meteorological data. In the results obtained, it was seen that the SCG algorithm gave better results in tests in this study with less data.
  • Thumbnail Image
    Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Internet of Things (iot) and Artificial Neural Networks Towards Water Pollution Forecasting
    (Middle Pomeranian Sci Soc Env Prot, 2020) Ibrahim, Thaer; Mishra, Alok; Software Engineering
    Water could be some-times a source of danger on people's lives and property. Although it is one of the most important elements of life on this planet. This article define the threat of water pollution in Tigris River in Iraq. by collecting a data that generated by sensors that installed in a water pollution sensing project in Baghdad city, also this article aimed to detect and analyze the behavior of water environment. It is an effort to predict the threat of pollution by using advanced scientific methods like the technology of Internet of Things (IoT) and Machine learning in order to avoid the threat and/or minimize the possible damages. This can be used as a proactive service provided by E-governments towards their own citizens.
  • Thumbnail Image
    Conference Object
    A Comparison of Pattern Recognition Approaches for Recognizing Handwriting in Arabic Letters
    (Institute of Electrical and Electronics Engineers Inc., 2021) Douma,A.; Ahmed,A.A.; Sengul,G.; Santhosh,J.; Jomah,O.S.M.; Ibrahim Salem,F.G.
    For Arabic letters recognition, we achieve three of pattern recognition approaches namely gray level co-occurrence matrix (GLCM), local binary pattern recognition (LBP) and artificial neural network (ANN) and compare between them to result best performance. Two of these methods level co-occurrence matrix and local binary pattern recognition are used for feature extraction whereas in artificial neural network (ANN) we use the intensity values of pixels for input of the neural network. Two classifiers are used, the K-Nearest Neighbor classifier (KNN) for the LBP, GLCM and neural network classifier for (ANN) artificial neural network. Also, we evaluate the results by using leave one person out approach, fold classification and leave one out. © 2021 IEEE.
  • Thumbnail Image
    Article
    Estimation of the Mean Radiant Temperature in Office Buildings Using an Artificial Neural Network Developed in a Phyton Environment
    (Taylor & Francis Ltd, 2025) Ozbey, Mehmet Furkan; Lotfi, Bahram; Turhan, Cihan
    Thermal comfort describes an occupant's state of mind in a thermal environment, influenced by six parameters: air velocity, relative humidity, air temperature, mean radiant temperature (MRT), clothing value, and metabolic rate. MRT is the most problematic parameter since the obtaining process is difficult and time-consuming. MRT can be acquired by several methods such as calculations, measurements, assumptions, and software programmes. However, the methods have complexities and uncertainties. Comprehensive models are needed to obtain MRT. To this aim, this study presents an alternative method using one of the artificial intelligence methods, Artificial Neural Network (ANN), to predict MRT for indoor environments to abstain from the difficulties and complexities. A case building is selected in a university office building in Ankara, T & uuml;rkiye. The proposed model is developed and coded in a Python programming environment to predict the MRT using ANN. The results indicate that the ANN model, using only four inputs, predicts MRT with an R-2 value of 0.94 compared to the globe thermometer measurement method. The model's advantages over methods include simplicity, time efficiency and learning from the limited datasets such as difficulty in calculating terms like MRT.