This paper presents the development of an artificial neural network (ANN) model based on multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied ANN to analyze a time series measured response evaluation. For this reason, we used input and output networks identify model, studied performance some training algorithms estimate weights neuron. The comparison between demonstrates efficiency accu-racy Levenberg-Marquardt (LM) Resilient back propagation (Rp) in...

The increasing global demand for agricultural products, particularly grains, highlights the need effective pest management. Cereal vital meeting nutritional demands by providing more than 50% of energy and protein intake, are stored annually to maintain a consistent supply. Integrating YOLOv8 model with Remote-Controlled Robot Car, this research revolutionizes grain management through technology. This innovative solution, combining deep learning, IoT, precision agriculture, enables real-time...

ABSTRACT Recently, many fundamental technologies have emerged to boost and improve the performance of existing future wireless communication systems, one these being utilization intelligent reflecting surfaces (IRS). This work investigates channel estimation spectral efficiency (SE) a Massive multiple‐input multiple‐output (M‐MIMO) system based on an IRS for spatially correlated channels. The system's is evaluated in terms both SE, utilizing minimum mean square error (MMSE) estimator....

This paper presents a study of feature selection methods effect, using filter approach, on the accuracy and error supervised classification cancer. A comparative evaluation between different methods: Fisher, T-Statistics, SNR ReliefF, is carried out, dataset cancers; leukemia cancer, prostate cancer colon The results k nearest neighbors (KNN) support vector machine (SVM) classifiers show that combination SNR's method SVM classifier can present highest accuracy.

The global energy demand of buildings is on the rise, driven by factors such as rapid population growth, increasing comfort, technological advances, and ongoing developments in building construction. This escalating consumption a major contributor to crisis climate change. Accurate prediction essential for gaining insight into utilization, reducing waste, enhancing comfort conditions. study aimed introduce reliable technique predicting optimizing residential buildings, with focus case...

Abstract The main concern of this paper is to present a new method based on the Takagi–Sugeno (TS) fuzzy systems, for modelling daily global solar radiation recorded in Marrakesh, Morocco. TS models are non-linear techniques, defined by set If-Then rules with linear consequent parts, each which establishes local input–output relationship between variables model. structure and parameters developed model identified using clustering combined least square algorithm. applied prediction...

Abstract Channel estimation (CE) and spectral efficiency (SE) are two processes that have a major influence on system performance, especially in more practical channel scenario with spatially correlated Rayleigh fading. During this work, we address the uplink phase CE process SE for fading cell‐free (CF) massive multiple‐input multiple‐output (M‐MIMO) network conventional M‐MIMO operating under time‐division duplex protocol. Since channels fading; thereby, work addresses both networks using...

Solar systems are influenced by their functioning temperature, which is mainly a result of the ambient air temperature as well level sunlight. For this reason, we have proposed an intelligent autoregressive model based on multilayer neural networks with delayed exogenous input sequence representing Global Radiation (GSR) data to forecast Air Temperature (AT) values half hour scale in Marrakesh, Morocco, recorded during 2014. The developed will helps us monitor and overcome such problem...

Nowadays, millimeter-wave frequencies present a catchy solution to securing the colossal data rate needed for 5G communications. Accordingly, this research deals with conception of novel orthogonal 2×2 multiple input, output (MIMO) antenna design operating in millimeter wave spectrum quite small dimensions 11×6×0.8 mm 3 . The single element consists trapezoidal microstrip patch built on Rogers RT5880 laminate permittivity 2.2 and tangent loss 0.0009. A trapezoidal-slot ground plane is used...

In this paper we have applied the adaptive neuro-fuzzy inference system (ANFIS) which is realized by an appropriate combination of fuzzy systems and neural networks for forecasting a set input output data Internet traffic time series. Several statistical criteria are to provide effectiveness model. The obtained results demonstrate that ANFIS model present good precision in prediction process internet terms indicators. This fits well real provides effective description network condition at...

In machine learning, feature subset selection phase is the process of selecting a small most relevant features for use in model construction. The main goal this paper to perform comparative study between methods applied DNA microarray dataset and investigate strength each method. studied are: F test, T Signal noise ratio (S/R), ReliefF Pearson product-moment correlation coefficient (CC). This carried out using five cancers; Leukemia, Lung, Lymphoma, Central Nervous System Ovarian cancers....

Controlling the random nature of renewable energy sources such as solar radiation at ground, allows electric grid operators to better integrate it.In this paper, an intelligent datadriven model based on artificial neural network with autoregressive input sequence is developed forecast global (GSR) time series a half hour resolution in site Agdal, Marrakesh, Morocco.The database that used create was divided into two subsets.The first subset for training proposed data measured during year 2008...