Multilayer Perceptron

In this research, feedforwardANN (Artificial Neural Network) model is developed and validated for predicting the pH at 10 different locations of the distribution system of drinking water of Hyderabad city. The developed model is MLP (Multilayer Perceptron) ...

In this study, the performance data of a moving-bed sequencing batch biofilm reactor (MBSBBR) treating synthetic wastewater were simulated using multi-layer perceptron neural-network technique. Multi-linear regression (MLR) technique is also used for a comparison. The performance of MBSBBR was evaluated using these models for a set of experimental results obtained from a model reactor operated with different cycle times and temperatures. The experimental data were retrieved from a previous reported work. Operational time, temperature, ammonium nitrogen, and pH were used as inputs for modeling, whereas nitrate concentration was the output variable. The results of the models were compared using statistical criteria, such as mean square error, mean absolute error, mean absolute relative error, and determination coefficient (R 2). The results showed that the multi-layer perceptron neural-network produced more accurate results than those of MLR, although the latter gave reasonable results.

Accurate localization in indoor environments with ultra-wideband (UWB) technology has long attracted much attention. However, due to the presence of multipath components or non-line of sight (NLOS) propagation of the radio signals, it has been converted to a critical challenge. Existing solutions use many fixed anchors in the indoor environment. Particularly, large areas require many anchor points and in the case of unexpected events that lead to the destruction of existing infrastructures, the fixed anchor points cannot be used. In this paper, a novel localization framework based on the transmitting signal from a mobile UWB sensor on the outside of the building and its received signal regarding the modified Saleh Valenzuela (SV) channel model is presented. After preprocessing the received signals, two new procedures to reduce the ranging error caused by multipath components are proposed. In the first procedure, two machine learning algorithms including multi-layer perceptron (MLP) and support vector machine (SVM) using the extracted features from the received UWB signal time and power vectors are implemented. Moreover, in the second procedure, two deep learning algorithms including MLP and convolutional neural networks (CNNs) using the received UWB signal time and power vectors are implemented to improve the performance of the indoor localization system. The simulation results show that the architecture designed for the convolutional neural network based on the hybrid dataset (the combination of the dataset related to received UWB signal time and power vectors) provides a mean absolute error (MAE) of about 3 cm.

Ambient assisted living is good way to look after ageing population that enables us to detect human's activities of daily living (ADLs) and postures, as number of older adults are increasing at rapid pace. Posture detection is used to provide the assessment for monitoring the activity of elderly people. Most of the existing approaches exploit dedicated sensing devices as as cameras, thermal sensors, accelerometer, gyroscope, magnetometer and so on. Traditional methods such as recording data using these sensors, training and testing machine learning classifiers to identify various human postures. This paper exploits data recorded using ubiquitous devices such as smart phones we use on daily basis and classify different human activities such as standing, sitting, laying, walking, walking downstairs and walking upstairs. Moreover, we have used machine learning and deep learning classifiers including random forest, KNN, logistic regression, multilayer perceptron, decision tree, QDA and SVM, convolutional neural network and long short-term memory as ground truth and proposed a novel ensemble classification algorithm to classify each human activity. The proposed algorithm demonstrate classification accuracy of 98% that outperforms other algorithms.

The potential for geothermal energy is very abundant, but its utilization is still minimal. Therefore, the utilization of geothermal energy facility that has been installed must be optimized. This study aims to predict drilling rate of penetration using the first-order Sugeno's fuzzy system. Fuzzy c-mean and singular value decomposition were used to form the rules and determined the parameters respectively. This study used in total of 6738 data of geothermal wells drilling in Indonesia. The results show that the rate of penetration prediction has accuracy 85.76% for data training and 87.72% for data testing, and it is better than the radial basis function neural networks (RBFNN) and RBFNN-singular value decomposition (SVD) methods.

Mapping the suitability of landfill sites is a complex field and is involved with multidiscipline. The purpose of this research is to create an ArcGIS spatial data mining toolbox for mapping the suitability of landfill sites at a regional scale using neural networks. The toolbox is constructed from six sub-tools to prepare, train, and process data. The employment of the toolbox is straightforward. The multilayer perceptron (MLP) neural networks structure with a backpropagation learning algorithm is used. The dataset is mined from the north states in Malaysia. A total of 14 criteria are utilized to build the training dataset. The toolbox provides a platform for decision makers to implement neural networks for mapping the suitability of landfill sites in the ArcGIS environment. The result shows the ability of the toolbox to produce suitability maps for landfill sites.

Today, Metabolic Syndrome in the age group of children and adolescents has become a global concern. In this paper, a data mining model is used to determine a continuous Metabolic Syndrome (cMetS) score using Linear Discriminate Analysis (cMetS-LDA). The decision tree model is used to specify the calculated optimal cut-off point cMetS-LDA. In order to evaluate the method, multilayer perceptron neural network (NN) and Support Vector Machine (SVM) models were used and statistical significance of the results was tested with Wilcoxon signed-rank test. According to the results of this test, the proposed CART is significantly better than the NN and SVM models. The ranking results in this study showed that the most important risk factors in making cMetS-LDA were WC, SBP, HDL and TG for males and WC, TG, HDL and SBP for females. Our research results show that high TG and central obesity have the greatest impact on MetS and FBS has no effect on the final prognosis. The results also indicate t...

Semantic stochastic sentence realization is still in its fledgling stage. Most of the available stochastic realizers start from syntactic structures or shallow semantic input structures which still contain numerous syntactic features. This is unsatisfactory since sentence generation traditionally starts from abstract semantic or conceptual structures. However, a change of this state of affairs requires first a change of the annotation of available corpora: even multilevel annotated corpora of the CoNLL competitions contain syntaxinfluenced semantic structures. We address both tasks-the amendment of an existing annotation with the purpose to make it more adequate for generation and the development of a semantic stochastic realizer. We work with the English CoNLL 2009 corpus, which we map onto an abstract semantic (predicateargument) annotation and into which we introduce a novel "deep-syntactic" annotation, which serves as intermediate structure between semantics and (surface-)syntax. Our realizer consists of a chain of decoders for mappings between adjacent levels of annotation: semantic → deep-syntactic → syntactic → linearized → morphological.

Most of the known stochastic sentence generators use syntactically annotated corpora, performing the projection to the surface in one stage. However, in full-fledged text generation, sentence realization usually starts from semantic (predicate-argument) structures. To be able to deal with semantic structures, stochastic generators require semantically annotated, or, even better, multilevel annotated corpora. Only then can they deal with such crucial generation issues as sentence planning, linearization and morphologization. Multilevel annotated corpora are increasingly available for multiple languages. We take advantage of them and propose a multilingual deep stochastic sentence realizer that mirrors the state-ofthe-art research in semantic parsing. The realizer uses an SVM learning algorithm. For each pair of adjacent levels of annotation, a separate decoder is defined. So far, we evaluated the realizer for Chinese, English, German, and Spanish.

Criteria for evaluating the classification reliability of a neural classifier and for accordingly making a reject option are proposed. Such an option, implemented by means of two rules which can be applied independently of topology, size, and training algorithms of the neural classifier, allows to improve the classification reliability. It is assumed that a performance function P is defined which, taking into account the requirements of the particular application, evaluates the quality of the classification in terms of recognition, misclassification, and reject rates. Under this assumption the optimal reject threshold value, determining the best trade-off between reject rate and misclassification rate, is the one for which the function P reaches its absolute maximum. No constraints are imposed on the form of P , but the ones necessary in order that P actually measures the quality of the classification process. The reject threshold is evaluated on the basis of some statistical distributions characterizing the behavior of the classifier when operating without reject option; these distributions are computed once the training phase of the net has been completed. The method has been tested with a neural classifier devised for handprinted and multifont printed characters, by using a database of about 300000 samples. Experimental results are discussed.

Artificial neural networks (ANNs) constitute a promising modeling approach that may be used in control systems for postharvest preservation and storage processes. The study investigated the ability of multilayer perceptron and radial-basis function ANNs to predict fungal population levels in bulk stored rapeseeds with various temperatures (T = 12-30 • C) and water activity in seeds (a w = 0.75-0.90). The neural network model input included a w , temperature, and time, whilst the fungal population level was the model output. During the model construction, networks with a different number of hidden layer neurons and different configurations of activation functions in neurons of the hidden and output layers were examined. The best architecture was the multilayer perceptron ANN, in which the hyperbolic tangent function acted as an activation function in the hidden layer neurons, while the linear function was the activation function in the output layer neuron. The developed structure exhibits high prediction accuracy and high generalization capability. The model provided in the research may be readily incorporated into control systems for postharvest rapeseed preservation and storage as a support tool, which based on easily measurable on-line parameters can estimate the risk of fungal development and thus mycotoxin accumulation.

This study analyzes Türkiye's trade volume with Balkan countries using the gravity model and aims to compare the performance of machine learning methods in predicting the trade volume between Türkiye and these countries. For this purpose, data from 2004 to 2023 have been utilized. However, due to the dissolution of Serbia and Montenegro into two independent countries in 2006, and Kosovo's unilateral declaration of independence from Serbia in 2008, the data for these three countries exhibit discontinuous and inconsistent patterns, leading to their exclusion from the analysis. The data used in the study includes numerical variables such as the export and import figures between Türkiye and Balkan countries, the GDP of the countries, and the distance between them. The dummy variables include whether the countries share a border, a common language, their landlocked status, and their memberships in the World Trade Organization (WTO) and the European Customs Union. These data have been analyzed using seven different machine learning models  to predict the trade volume. The analysis was conducted using four different train-test data splits and cross-validation with 10 iterations. The performance of the applied machine learning models was compared based on MAPE (Mean Absolute Percentage Error) and R2 values. The findings revealed that the best prediction method varies depending on the country analyzed and the train-test split ratios. These differences in results contribute significantly to a better understanding of trade relations  between Türkiye and the Balkan countries, forecasting the future course of these relations, and shaping regional economic policies. Therefore, the study is important in determining strategies for the development of trade with these countries.

This study aims to analyze Turkey's trade volume with the Turkic Republics (Azerbaijan, Kazakhstan, Kyrgyzstan, Uzbekistan, and Turkmenistan) within the framework of the international trade gravity model and to predict the trade volume with these countries for the years 2024 and 2025. Export and import data between Turkey and the Turkic Republics from 1992 to 2023 were used, with countries' GDPs and distances as numerical variables, and border, language, landlocked status, and World Trade Organization (WTO) memberships as dummy variables. These data were processed using different machine learning models, including Linear Regression, Gaussian Process Regression, and Multilayer Perceptron, to predict trade volumes. The success of the applied machine learning models was compared based on MAPE (Mean Absolute Percentage Error) values. The analysis results indicated that the Multilayer Perceptron model provided the most accurate predictions. This finding demonstrates the effectiveness of advanced machine learning methods in understanding complex trade dynamics and forecasting future trade trends. A better understanding of trade relations between Turkey and the Turkic Republics and predicting the future trajectory of these relations will significantly contribute to the formulation of regional economic policies. The study also provides valuable insights for developing strategies to enhance trade with these countries.

We are interested in a null controllability problem for a class of strongly degenerate heat equations. Heat equation parameters are represented graphically (temperature, heat flux) for a particular situation. Then, first for all T>0, we prove a regional null controllability result at time T at least in the region where the equation is not degenerate. The proof is based on an adequate observability inequality for the homogeneous adjoint problem. This inequality is obtained by application of Carleman estimates combined with the introduction of cutoff functions. Then we improve this result: for all T`>T, we obtain a result of persistent regional null controllability during the time interval [T,T]. We give similar results for the (non degenerate) heat equation in unbounded domain. Analysis by numerical simulation of the heating room space has highlighted that the use of composite materials instead of the usual materials of construction is more advantageous in terms of achieving the microclimate conditions, making possible, within certain limits of temperature exterior, a passive air conditioning, which involves reducing energy consumption.

This paper presents the development and performance evaluation of a particular Multi-Layer Perceptron neural network (MLP) classifier for radar target detection in a noisy, non-Gaussian environment using CFAR (Constant False Alarm Rate). The Technique, architecture details and principle of working of the MLP-CFAR detector training algorithm are presented. A comparison of the MLP-CFAR performances is also described according to different target scenarios. The principles results show that the detector performances are deteriorating by increasing the number of targets considered. Résumé. Ce présent travail, s'intéresse au développement et l'analyse de performances d'un détecteur classifieur particulier, sous forme d'un Perceptron Multi-Couches (PMC), de cibles radar dans un environnement (Fouillis) nongaussien, en utilisant le modèle CFAR. La technique, le détail de l'architecture et le principe de fonctionnement de l'algorithme d'apprentissage du détecteur MLP-CFAR, sont présentés. Une comparaison de performances du MLP-CFAR selon plusieurs scenarios de nombre de cibles considérées est aussi présentée. Les principaux résultats montrent que les performances du détecteur se dégradent en augmentant le nombre de cibles considérés.

This paper presents the development and performance evaluation of a particular Multi-Layer Perceptron neural network (MLP) classifier for radar target detection in a noisy, non-Gaussian environment using CFAR (Constant False Alarm Rate). The Technique, architecture details and principle of working of the MLP-CFAR detector training algorithm are presented. A comparison of the MLP-CFAR performances is also described according to different target scenarios. The principles results show that the detector performances are deteriorating by increasing the number of targets considered. Résumé. Ce présent travail, s'intéresse au développement et l'analyse de performances d'un détecteur classifieur particulier, sous forme d'un Perceptron Multi-Couches (PMC), de cibles radar dans un environnement (Fouillis) nongaussien, en utilisant le modèle CFAR. La technique, le détail de l'architecture et le principe de fonctionnement de l'algorithme d'apprentissage du détecteur MLP-CFAR, sont présentés. Une comparaison de performances du MLP-CFAR selon plusieurs scenarios de nombre de cibles considérées est aussi présentée. Les principaux résultats montrent que les performances du détecteur se dégradent en augmentant le nombre de cibles considérés.

Healthprofessionals,especiallynurses,areoftencompelledtomakedecisionsinfaceofbioethicalissuescommonlyrelatedtointensivecareenvironments.Duetotheircomplexitiesandparticularities,theseissuesendupgeneratinggreatphysicalandemotionalstrainontheprofessional.Therefore,thisstudyraisedthehypothesisthatartificialintelligencetechniquescouldassistnursesinmakingbioethicaldecisions.Forthis,agroupoffourspecialistsinthefieldofnursingpreparedandansweredaquestionnairebasedonahypotheticalICUscenario.Thedatacollectedfromtheresponseswerethenusedinthetrainingandevaluationoffivemachinelearning(ML)algorithms.Theresultsculminatedfromacomparativestudybetweenthealgorithmspointtotheveracityofthehypothesisraisedinthisresearch,byshowingthatitispossibletoadoptMLalgorithmstosupportbioethicaldecisionmaking

In this paper, we present concepts in artificial neural networks (ANN) to help detect intrusion attacks against network computers, and introduce and compare a multi-layer perceptron ANN (MLPANN) with Snort, an open-source tool for intrusion detection systems (IDS). To conduct these comparison experiments, we inserted malicious traffic into the MLPANN to train our ANN, with results indicating that our ANN detected 99% of these input attacks.

In this paper, we described generation and performances of feedforward neural network models that could be used for a day ahead predictions of the daily maximum 1-h ozone concentration (1hO 3) and 8-h average ozone concentration (8hO 3) at one traffic and one background station in the urban area of Novi Sad, Serbia. The six meteorological variables for the day preceding the forecast and forecast day, ozone concentrations in the day preceding the forecast, the number of the day of the year, and the number of the weekday for which ozone prediction was performed were utilized as inputs. The three-layer perceptron neural network models with the best performance were chosen by testing with different numbers of neurons in the hidden layer and different activation functions. The mean bias error, mean absolute error, root mean squared error, correlation coefficient, and index of agreement or Willmott's Index for the validation data for 1hO 3 forecasting were 0.005 μg m −3 , 12.149 μg m −3 , 15.926 μg m −3 , 0.988, and 0.950, respectively, for the traffic station (Dnevnik), and − 0.565 μg m −3 , 10.101 μg m −3 , 12.962 μg m −3 , 0.911, and 0.953, respectively, for the background station (Liman). For 8hO 3 forecasting, statistical indicators were − 1.126 μg m −3 , 10.614 μg m −3 , 12.962 μg m −3 , 0.910, and 0.948 respectively for the station Dnevnik and − 0.001 μg m −3 , 8.574 μg m −3 , 10.741 μg m −3 , 0.936, and 0.966, respectively, for the station Liman. According to the Kolmogorov-Smirnov test, there is no significant difference between measured and predicted data. Models showed a good performance in forecasting days with the high values over a certain threshold.

Artificial Neural Networks (ANN) have been applied to many interesting problems in different areas of science, medicine and engineering and in some cases, they provide stateof-the-art solutions. This paper investigates the application of an ANN model in mining to predict the Drillability Index (DI) of a rock mass given rock parameters such as uniaxial compressive strength, shear strength, tensile strength, abrasion and hardness. Drillability indicates whether penetration is easy or hard while penetration rate indicates whether it is fast or slow. Therefore, prediction of the drillability and penetration rate is very important in rock drilling. Penetration rate is a necessary value for the cost estimation and the planning of the drilling project. According to results of this study, Uniaxial Compressive Strength (UCS) rating has the highest weight of 0.051083 among the three parameters studied which reconfirms the literature review finding which indicates that UCS is the most important parameter in predicting drillability.

A new modeling framework combining neuralnetwork-based models, passive microwave data, and geostatistics is proposed for snow water equivalent (SWE) retrieval and mapping. Brightness temperature data from the seven-channel Special Sensor Microwave/Imager and the interpolated minimum temperature are the inputs of a multilayer feedforward neural network (MFF). Kriging with an External Drift algorithm is applied to ground-based SWE data to produce gridded SWE data that are used as the target of the neural network. An optimal division of the sample of available pixels is achieved by a self-organizing feature map. Prediction error is used for model selection and is assessed by bootstrap. It is shown that a committee of a network containing neural networks with different architectures can provide consistent SWE retrievals. This modeling framework is applied for SWE retrieval and mapping over La Grande River basin in north eastern Quebec (Canada). The results are very promising for operational purposes particularly for SWE mapping during periods with no ground measurements and operational streamflow forecasting. Index Terms-Bootstrap, Kriging with an External Drift (KED), multilayer perceptrons (MLPs), passive microwave, selforganizing feature map (SOFM), snow water equivalent (SWE), Special Sensor Microwave/Imager (SSM/I). Noël Dacruz Evora was born to Cape Verdean parents in Dakar, Sénégal. He received the degree in civil engineering from the Ecole Polytechnique de Thiès, Thiès, Sénégal, in 1987, the complementary degree of civil engineer in hydrology and M.Sc. degree from the Faculté Polytechnique de Mons, Mons, Belgium, in 1990, and the Ph.D. degree in civil engineering (stochastic hydrology) from the Ecole Polytechnique de Montréal, Montréal, QC, Canada, in 1997. Since December 2000, he has been with Hydro-Québec Research Institute, Varennes, QC, where he is currently a Research Scientist in hydrology and hydrometeorology. His research interests are in surface-water hydrology and primarily cover the methods of improving water resources management and environmental risk assessment (floods and droughts). His specific research areas include hydrologic modeling, hydrometeorology, neural networks, and genetic programming applications to water resources. Dr. Evora is a member of American Geophysical Union. Dominique Tapsoba was born in Ouagadougou, Dagnoën, Burkina Faso. He received the B.Sc. degree in fundamental and applied geology from the University of Ouagadougou, Ouagadougou, and the M.Sc. degree in hydrology and water resources management and the Ph.D. degree in hydrology from the

A neural network model for spectrogram magnitude prediction is presented. It has one convolutional layer that computes the shorttime Fourier transform. By choosing the magnitude of the spectrum as output and discarding the phase, it is possible to avoid complex number operations. The structure of the network and coefficients computation for this alternative are presented in detail. The model coefficients can be directly computed or trained with the gradient descent algorithm. In both cases, the results are satisfactory, but the obtained weights are different. An analysis of the differences is made. The main contribution of this article is to show that the proposed model is trainable. Consequently, the coefficients can be adapted to particular problems.

The coronavirus has caused the deaths of millions of people and has endangered the entire healthcare system. In order to count positive cases and stop the disease from spreading, Rapid clinical results may prevent the COVID-19 from spreading and help medical professionals treat patients while working under challenging circumstances.. Normal disease diagnosis using a laboratory test requires equipment and takes some time with the use of X-ray and chest CT Scan images, artificial intelligence techniques are extensively used to categorize the COVID-19. In this study we present an automatic detection approach for COVID-19 infection based on Chest CT and X-ray images using a Multilayer Perceptron (MLP) Neurons Network and a Convolutional Neural Network (CNN). The two models are evaluated in two classes, COVID-19 and normal images, for detection by Chest X-ray images we obtained 95,7% accuracy using MLP model and 90% accuracy using CNN model. For detection by Chest CT image we obtained, 80,60 % accuracy using the MLP model and 88,49 % accuracy using the CNN. The experimental results indicate that the proposed approach can achieve high accuracy in detecting COVID-19 from X-ray images, demonstrating the potential of using machine learning techniques in medical diagnosis.

In this paper, an automated vision system is presented to detect and classify surface defects on leather fabric. Visual defects in a gray-level image are located through thresholding and morphological processing, and their geometric information is immediately reported. Three input feature sets are proposed and tested to find the best set to characterize five types of defects: lines, holes, stains,

Lack of safe drinking water is a growing concern in the present day and age. Since missing data is commonly found among most of the available datasets, the main purpose of this study is to find the best algorithm that works in the dataset that is statistically imputed and find the algorithm that gives the best prediction on whether water is potable or not. Water potability is predicted using its datasets with the help of the four algorithms evaluating nine features. Some values of the three features, specifically pH, chloramine, and trihalomethane, are found to be missing in the dataset. Missing values are filled in by the median of that particular feature. The performance of machine learning algorithms called LR, K-NN, RF, and ANN is compared in these given conditions. As per our research, RF, with 700 decision trees at a maximum depth of 30, is found to be the best-performing algorithm for the statically imputed water potability dataset. The study most certainly answers the question concerning the best algorithm, but still, further study is needed to optimize the algorithm in order to provide the best prediction.

Diabetes is a serious, chronic disease that has been seeing a rise in the number of cases and prevalence over the past few decades. It can lead to serious complications and can increase the overall risk of dying prematurely. Data-oriented prediction models have become effective tools that help medical decision-making and diagnoses in which the use of machine learning in medicine has increased substantially. This research introduces the Recursive General Regression Neural Network Oracle (R-GRNN Oracle) and is applied on the Pima Indians Diabetes dataset for the prediction and diagnosis of diabetes. The R-GRNN Oracle (Bani-Hani, 2017) is an enhancement to the GRNN Oracle developed by Masters et al. in 1998, in which the recursive model is created of two oracles: one within the other. Several classifiers, along with the R-GRNN Oracle and the GRNN Oracle, are applied to the dataset, they are: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Probabilistic Neural Network (PNN), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor (KNN), and Random Forest (RF). Genetic Algorithm (GA) was used for feature selection as well as the hyperparameter optimization of SVM and MLP, and Grid Search (GS) was used to optimize the hyperparameters of KNN and RF. The performance metrics accuracy, AUC, sensitivity, and specificity were recorded for each classifier.

Diabetes is a serious, chronic disease that has been seeing a rise in the number of cases and prevalence over the past few decades. It can lead to serious complications and can increase the overall risk of dying prematurely. Data-oriented prediction models have become effective tools that help medical decision-making and diagnoses in which the use of machine learning in medicine has increased substantially. This research introduces the Recursive General Regression Neural Network Oracle (RGRNN Oracle) and is applied on the Pima Indians Diabetes dataset for the prediction and diagnosis of diabetes. The R-GRNN Oracle (Bani-Hani, 2017) is an enhancement to the GRNN Oracle developed by Masters et al. in 1998, in which the recursive model is created of two oracles: one within the other. Several classifiers, along with the R-GRNN Oracle and the GRNN Oracle, are applied to the dataset, they are: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Probabilistic Neural Network (PNN), G...

In pipeline management the accurate prediction of weak displacements is a crucial factor in drawing up a prevention policy since the accumulation of these displacements over a period of several years can lead to situations of high risk. This work addresses the specific problem related to the prediction of displacements induced by rainfall in unstable areas, of known geology, and crossed by underground pipelines. A neural model has been configured which learns of displacements from instrumented sites (where inclinometric measurements are available) and is able to generalise to other sites not equipped with inclinometers.

The network providers are now being challenged with their inability to accurate estimate and characterize traffic in a particular area, due to the increasing number of mobile communication services being rendered by the network providers Hence, this has been greatly undermining their design and planning processes and as such increasingly affected the Quality of Service(QoS).This research work addresses the traffic estimation in mobile communication network using Artificial Neural Network (ANN) approach using measured data collected in Lagos State,Nigeria.The Multilayer Perceptron (MLP) and Radial Basis Function (RBF) ANN techniques were used in the traffic modeling. The results of the ANN modeling showed that the Model 1 of MLP performed better than other models with Coefficient of Determination (R2) of 99%, Root Mean Square Error(RMSE) of 5.456 and Mean Bias Error(MBE) of 0.94.It is recommended that the dataset used in developing the ANN models be increased by collecting and using ...

Aiming at effectively improving photovoltaic (PV) park operation and the stability of the electricity grid, the current paper addresses the design and development of a novel system achieving the short-term irradiance forecasting for the PV park area, which is the key factor for controlling the variations in the PV power production. First, it introduces the Xception long short-term memory (XceptionLSTM) cell tailored for recurrent neural networks (RNN). Second, it presents the novel irradiance forecasting model that consists of a sequence-to-sequence image regression NNs in the form of a spatio-temporal encoder–decoder including Xception layers in the spatial encoder, the novel XceptionLSTM in the temporal encoder and decoder and a multilayer perceptron in the spatial decoder. The proposed model achieves a forecast skill of 16.57% for a horizon of 5 min when compared to the persistence model. Moreover, the proposed model is designed for execution on edge computing devices and the rea...

We present a comprehensive comparative analysis of classical Fuzzy C-Means (FCM) clustering and kernel –based Fuzzy C-Means clustering. While Fuzzy C-Means is a popular soft-clustering method, its effectiveness is largely limited to hyper spherical clusters that are linearly separable. If the clusters are not linearly separable, the FCM is not particularly effective. By applying the kernel trick, the kernelised fuzzy c-means algorithm attempts to address this problem. The Kernel FCM operates by first non-linearly mapping the data to appropriate and sufficiently high-dimensional feature spaces, where according to the Mercer’s theorem the data are likely to be linearly separable, and then applying the classical FCM algorithm. We first present the Hard C-Means clustering algorithm and a generalization of it called the Fuzzy C-Means. Then we explore the mathematical basis behind the kernel trick, both in general and especially in the setting of clustering. Following this we evaluate the...

This work presents quantitative prediction of severity of the disease caused by Phytophthora infestans in potato crops using machine learning algorithms such as multilayer perceptron, deep learning convolutional neural networks, support vector regression, and random forests. The machine learning algorithms are trained using datasets extracted from multispectral data captured at the canopy level with an unmanned aerial vehicle, carrying an inexpensive digital camera. The results indicate that deep learning convolutional neural networks, random forests and multilayer perceptron using band differences can predict the level of Phytophthora infestans affectation on potato crops with acceptable accuracy.

The objective of this study is to establish a thorough comprehension of the interaction of population dynamics, poverty rates, minimum wage levels, and regional GDP in relation to household electricity consumption. The main objective is to improve the precision of electricity demand predictions and prevent planning mistakes, such as the considerable surplus of 6-7 GW in the Java Bali system between 2020 and 2023, resulting in major financial losses. We evaluate and compare the models by employing several approaches, such as ordinary least square (OLS) and geographically weighted regression (GWR) with fixed and adaptive bandwidths. We use modified R-squared and corrected Akaike Information Criterion (AICc) values for this assessment. The GWR with adaptive bandwidth is shown to be the most resilient method and is subsequently chosen for modeling. The results indicate that there is a strong correlation between the number of impoverished individuals and electricity use, with a coefficient range of 0.35-0.55. Furthermore, the correlation between poverty rates and power usage is defined by a coefficient that varies between -0.0010 and -0.0030. There is a direct relationship between regional GDP and power growth, as indicated by coefficients ranging from 1,000,000 to 5,000,000. Moreover, the impact of minimum wage levels differs among different locations.