M. LADJAL Mohamed

Using density functional theory (DFT) with the GGA-PBESol, LDA, and TB-mBJ approximations, this paper thoroughly examines the structural, elastic, optoelectronic, and thermoelectric properties of chalcogenide-double perovskites Ba2NbBiS6 and Ba2TaSbS6, with the view to their potential use in optoelectronic and photovoltaic devices. Based on the calculation results, both compounds achieve the Born stability criteria and negative formation energy values, confirming their thermodynamic stability. Additionally, the elastic criteria analysis shows that the materials exhibit strong resistance to volume deformation while remaining ductile and demonstrate anisotropic characteristics, as seen through the ELATools software. Furthermore, the electronic band structure and density of states were investigated. The Ba2NbBiS6 compound exhibits an indirect band gap (L–X) of 1.58 eV (mBJ-GGA) and 1.45 eV (mBJ-LDA), while the Ba2TaSbS6 compound shows an indirect band gap (L–Γ) of 1.45 eV (mBJ-GGA) and 1.28 eV (mBJ-LDA). Analysis of the (DOS) and the electronic band structure revealed the contribution of 4d_Nd for Ba2NbBiS6 and 5d_Ta for Ba2TaSbS6. Furthermore, optical parameters derived from the dielectric function, including reflectivity, absorption coefficient, and refractive index were predicted. As a result, both compounds exhibit strong photon absorption extending from the visible to ultraviolet regions, with absorption coefficients of 342.03 × 104/cm for Ba2NbBiS6 and 333.92 × 104/cm for Ba2TaSbS6, indicating their high potential for optoelectronic devices. In addition, thermoelectric properties such as the Seebeck coefficient, electrical conductivity, thermal conductivity, ZT merit, and power factor were evaluated. The results provide valuable insights that may guide future experimental studies on these promising materials.

Predicting lattice constants is critical to advancing the discovery of functional materials. When dealing with highly nonlinear data, traditional techniques, such as Density Functional Theory (DFT), frequently suffer from restricted generalization and high computational cost. This study presents a hybrid predictive framework that merges an Autoregressive Type-3 Fuzzy Logic System with the Extended Kalman Filter (AR-T3FLS-EKF) to overcome these constraints and address the issue of restricted and scarce data. The autoregressive technique incorporates physical dependencies among compositional descriptors, whereas the Type-3 fuzzy system improves uncertainty modeling using three-dimensional membership functions. The extended kalman filter adaptively tunes the fuzzy model parameters, improving robustness and convergence. The proposed model is validated on three datasets of perovskite and double perovskite structures using features such as ionic radii, electronegativity, and tolerance factor. Compared with conventional machine learning methods, the AR-T3FLS-EKF achieves superior performance (R2 = 0.9999, MAE = 0.0015 Å, RMSE = 0.0012 Å). These results confirm the model's reliability for accurate lattice constant prediction, especially under limited and scarce data conditions.

Monitoring environmental data to ensure the safety and reliability of public resources has become a crucial task in data-driven systems. One key aspect of this monitoring is the detection of anomalies—data points or behaviors that significantly diverge from the norm. This study explores the use of a density-based clustering method, DBSCAN, to identify such anomalies within datasets collected from drinking water treatment facilities. DBSCAN's capability to recognize dense regions and isolate noise makes it well suited for flagging irregularities in complex, real-world data. By applying this method to extensive datasets with diverse attributes, the research aims to enhance the consistency and safety of drinking water production processes, contributing to improved public health outcomes and operational resilience in water management systems.

This study aims to examine the equilibrium Kesterite structure of Cu2BeSnS4, Cu2BeSnSe4, and Cu2BeSnTe4 by the application of density functional theory (DFT) and the Full-Potential Linearized Augmented Plane Wave (FP-LAPW) method. The study demonstrates that both Cu2BeSnS4 and Cu2BeSnSe4 compounds are semiconductors with direct band gaps at the Γ point, while Cu2BeSnTe4 has an indirect band gap (Γ→X). The electronic and optical characteristics of these materials indicate their potential utility in optoelectronic, photonic, and photovoltaic applications. Furthermore, a thorough comparison has been conducted between the obtained results and other experimental and theoretical data from the same chalcogenide family. In summary, the findings offer valuable information on the possible photovoltaic uses of these compounds.

This paper presents a new scheme for dynamical systems and time series modeling and identification. It is based on artificial neural networks (ANN) and metaheuristic algorithms. This scheme combines the strength of ANN with the dexterity of metaheuristic algorithms. This fusion is renowned for its ability to detect complex patterns, which considerably improves accuracy, computational efficiency, and robustness. The proposed scheme deals with the curve fitting and addresses ANN's local minima problem. This approach introduces the identification concept using a fresh novel identification element, referred to as the error model. The proposed framework encompasses a parallel interconnection of two models. The principal sub-model is the elementary model, characterized by standard specifications and a lower resolution, designed for the data being examined. In order to address the resolution limitation and achieve heightened precision, a second sub-model, named the error model, is introduced. This error model captures the disparities between the primary model and considered data. The parameters of the proposed scheme are adjusted using metaheuristic algorithms. This technique is tested across many benchmark data sets to determine its efficacy. A comparative study along with benchmark approaches will be provided. Extensive computer studies show that the suggested strategy considerably increases convergence and resolution.

The Ain Zada dam is experiencing a deficit in recent years due to scanty precipitation and reduced water flow, resulting in the dam’s water reserve dropping to 8.3%. Our study’s primary objective is to assess the quality of both untreated (raw) and treated water from the Ain Zada dam by conducting physico-chemical analyses on both samples. Based on the findings, the physico-chemical quality of the treated water is deemed satisfactory, as all samples adhere to Algerian standards. The treated water exhibits an organic matter concentration of 4.94 mg/l, which is the chief contributor to the unfavourable odour and taste of the dam water. To address this, enhancements will be made to the Ain Zada dam treatment station this year through the adoption of a novel ozone disinfection method (ozonation). The Water Quality Index (WQI) for treated water from the Ain Zada dam indicates a favourable suitability for drinking water production from February to May 2022. Two quality categories are discernible for each scenario based on the obtained WQI values: excellent and good for treated water, and excellent and poor for raw water. Water quality diminishes notably in April, where the treated water quality index rises (25 < WQI . 50), while the raw water’s quality classifies as poor (WQI > 50). The decline in water quality during this month can be attributed to stream variations, agricultural activities, and urban wastewater discharges. Consequently, it is imperative to prioritise the reduction of these pollution sources to safeguard water resources and enhance water quality within the watershed.

Perovskites have gained significant attention in recent years due to their unique and versatile material properties. The lattice parameters of the perovskite compounds play a crucial role in the engineering of layers and substrates for heteroepitaxial thin films. As an essential parameter in the cubic perovskite structure, the lattice constant, plays a significant role in the development of materials for specific technological applications and serves as a distinctive identifier of the crystal structure of the material. In the field of materials science, advanced Computational Intelligence (CI)-based techniques have become increasingly important for simulating the relationship between the physicochemical parameters of chemical elements and the physical properties of materials and compounds. Hence, this paper presents efficient techniques based on artificial neural network (ANN) and fuzzy logic to predict the lattice constants of pseudo-cubic and cubic perovskites. The identification of optimized parameters for the ANN and fuzzy logic models is accomplished using innovative metaheuristic algorithms such as, Particle Swarm Optimization (PSO), Invasive Weed Optimization (IWO) and Imperialist Competitive Algorithm (ICA). In the first part, the study assessed, the effectiveness of various metaheuristic algorithms (PSO-IWO-ICA) in tuning the parameters of the ANN prediction structure in order to get the optimal parameter of the ANN. Whereas in the second part, once we extracted the best optimization algorithm, we combined it with the fuzzy logic technique and then we compared the effectiveness of the two techniques, ANN and Fuzzy logic. On the basis of root mean square error (RMSE), mean absolute error (MAE) and the coefficient of determination (R2), the proposed PSO-ANN and PSO-Fuzzy based models are compared with existing and recent models such as Ubic, Sidey, and Owolabi. The proposed PSO-Fuzzy model performs better than our PSO-ANN model, the Ubic, Sidey, and Owolabi models, with performance improvement of 70.90%, 90.36%, 89.74% 84.46%, respectively on the basis of RMSE. Similarly, it attains performance improvement of 71.26%, 90.31%, 89.58%, and 85.02% on the basis of MAE. Furthermore, the developed PSO-ANN based model outperforms the Ubic, Sidey and Owolabi models with performance improvement of 66.86%, 64.74% and 46.60% respectively, on the basis of RMSE and percentage enhancement of 66.27%, 63.75%, and 47.90% when compared on the basis of MAE. Although the PSO-Fuzzy model has the best performance of all the compared models, the developed PSO-ANN based model possesses the advantage of easy implementation in addition to its moderate performance.

The classification of surface water quality status is a major environmental concern and one of the most important tasks of water sources. The Water Quality Index (WQI) describes a number of water quality variables at a certain location environment and time. Different input combinations were developed using the best dataset, and the work strategy was to demonstrate water quality variation where all or some inputs have been used.
Auto deep learning models have been applied in the current research to investigate and try to emulate WQI's relationship with water quality variables in Tilesdit dam in Bouira (Algeria). Moreover, a comprehensive analysis has been performed for the performance assessment and sensitivity analysis of the variables. Our approach was appraised using several performance metrics. With high performance accuracy in the used models, the results achieved are promising

Classification and prediction of water quality index using deep learning techniques

Operation at low speed and high torque can lead to the generation of strong ripples in the speed, which can deteriorate the system. To reduce the speed oscillations when operating a
five-phase asynchronous motor at low speed, in this article, we propose a control method based on Gray Wolf optimization (GWO) algorithms to adjust the parameters of proportional–integral (PI) controllers. Proportional–integral controllers are commonly used in control systems to regulate the speed and current of a motor. The controller parameters, such as the integral gain and proportional gain, can be adjusted to improve the control performance. Specifically, reducing the integral gain can help reduce the oscillations at low speeds. The proportional–integral controller is insensitive to parametric variations; however, when we employ a GWO optimization strategy based on PI controller parameters, and when we choose gains wisely, the system becomes more reliable. The obtained results show that the hybrid control of the five-phase induction motor (IM) offers high performance in the permanent and transient states. In addition, with this proposed strategy controller, disturbances do not affect motor performance.

Double perovskite oxides have received a lot of interest in the last ten years because of their distinctive and adaptable material properties. Among the six parameters in the cubic structure, the lattice constant is the sole changeable parameter, which plays an important role in developing materials for particular technological applications and distinctively identifies the crystal structure of the material. In this paper, the extreme learning machine (ELM) is used to correlate the lattice constant of A+22BCO6 cubic perovskite compounds, such as their ionic radii, electronegativity, oxidation state, and lattice constant. We investigated 147 compounds with lattice constants between 7.700 and 8.890Å. The prediction method has a high level of accuracy and stability and provides accurate estimates of lattice constants.

Electrocardiogram (ECG) is one of the main tools to interpret and identify cardiovascular disease. ECG signals are frequently submitted to various noises, which alter the original signal and reduce its quality. ECG signal filtering enables cardiologists to assess heart health accurately. The present paper presents a newfound approach for ECG signal denoising built on two techniques which are EMD (Empirical Mode Decomposition) and AWC (Average Wavelet Coefficient method). The basic idea behind the suggested technique initially consists of deconstructing noisy ECG signal data on a restricted number of IMFs (Intrinsic Mode Functions) and then using the AWC technique to compute each IMF’s Hurst exponent. Finally, after a thresholding operation, the clean ECG signal is recovered by adding all IMFs, excluding those considered parts of noise. The suggested approach is assessed over experiments using the MIT-BIH databases. The experimental results reveal that the suggested method efficiently extracts ECG signals from noisy data samples.

Sensor fault, outlier, and anomaly detection are essential in many fields and applications to identify anomalies, abnormal data, or outliers that are different from the usual sensor data streams, effectively guaranteeing the validity of the measurements obtained by multiple sensors. Water quality assessment applications often frequently depend on multiple sensors that are situated in remote areas. It is necessary to account for apparent sensor failures and insufficient input data to obtain useful and powerful information from evaluating the corresponding measurements. In this paper, self-organizing features maps (SFOM)-based methods and hierarchical clustering (HC) are applied to several physicochemical parameters data anomaly detection in water quality assessment. In this study, the surface water quality from Mostaganem's Cheliff Dam was advanced assessed (Algeria). The performances and the efficacy of the proposed approaches in feature selection using SFOM and sensor anomaly detection process by SFOM and HC techniques were demonstrated successfully involved in water quality assessment. This result has a major impact on our monitoring system's performance both technically (lower learning times and anomaly detection) and economically (some less sensors required).

This paper studies the application of soft-sensing modeling approach for monitoring surface water quality with artificial intelligence techniques such as SOM (Self-Organizing Maps of Kohonen) and SVM (Support Vector Machines). In the water treatment process, many monitoring parameters are expensive or difficult to measure in real-time, limiting the possibilities for highly efficient control of the water production process. In this work, an intelligent soft-sensor was developed to predict optimal coagulant dosage. It confirmed that the coagulation-flocculation unit is essential in producing drinking water. The soft sensor proposed in this paper contains SOM in feature selection and the SVR method for predicting the optimal coagulant dose values. The surface water quality from Mostaganem's Cheliff Dam was advanced assessed (Algeria). The water quality assessment successfully demonstrated the proposed approach's performance and efficacy, and it can achieve complete expertise in the study area.

Soft Sensing Modeling Based on Support Vector Machine and Self-Organaizing Maps Model Selection for Water Quality Monitoring

EMD Based Average Wavelet coefficient method for ECG Signal Denoising

The electronic band gap energy is an essential photo-electronic parameter in the energy applications of engineering materials, particularly in solar cells and photo-catalysis domains. A prediction model that can correctly predict this band gap energy is desirable. A new approach for predicting a band gap energy is suggested in this paper. The proposed structure is based on artificial neural networks (ANN) and the particle swarm optimization algorithm (PSO); this structure can solve the artificial neural network's local minima issue while preserving the fitting quality. Our technique will hasten the identification of novel chalcopyrite in photovoltaic solar cells with improved resolution. The suggested model combines two sub-systems in a parallel configuration. A conventional prediction system with a low resolution for the training data being considered makes up the first ANN sub-system. A second ANN sub-system, labelled the error model, is introduced to the primary system to address the resolution quality issue, representing uncertainty in the primary model. The particle swarm optimization algorithm is used to identify the parameters of the proposed neural system. The method's effectiveness is assessed in terms of several criteria, and the output of our system shows good performance compared to experimental and other calculated results. Several benchmark approaches were compared with the proposed system in detail. Numerous computer tests show that the suggested strategy can significantly enhance convergence and resolution.

Monitoring of water quality is one of the world’s main intentions for countries. Classification techniques based on support vector machines (SVMs) and artificial neural network (ANN) has been widely used in several applications of water research. Water quality assessment with high accuracy and efficiency with innovational approaches permitted us to acquire additional knowledge and information to obtain an intelligent monitoring system. In this paper, we present the use of principal component analysis (PCA) combined with SVM and ANN with decision templates combination data fusion method. PCA was used for features selection from original database. The multi-layer perceptron network (MLP) and the one-against-all strategy for SVM method have been widely used. Decision templates are applied to increase the accuracy of the water quality classification. The specific classification approach was employed to assess the water quality of the Tilesdit dam in Algeria as a study area, defined with a dataset of eight physicochemical parameters collected in the period 2009–2018, such as temperature, pH, electrical conductivity, and turbidity. The selection of the excellent parameters of the used models can be improving the performance of classification process. In order to assess their results, an experiment step using collected dataset corresponding to the accuracy and running time of training and test phases, and robustness to noise, is carried out. Various scenarios are examined in comparative study to obtain the most results of decision step with and without feature selection of the input data. From the results, we found that the integration of SVM and ANN with PCA yields accuracy up than 98%. The combination by decision templates of two classifiers SVM and ANN with PCA yields an accuracy of 99.24% using k-fold cross-validation. The combination data fusion enhanced expressively the results of the proposed monitoring framework that had proven a considerable ability in surface water quality assessment.

Réalisation d'un appareil de détection de fuites d'eau dans les canalisations souterraines

An appropriate hybrid technique for ECG signal denoising based on variational mode decomposition and average wavelet coefficient method

Journée en Electronique

Journée en Electromécanique

EMD based average wavelet coefficient method for ECG signal denoising

An improved ELM framework for dynamical system modeling and identification

Sensor Anomaly detection using self features organizing maps and hierarchical clustring for water quality assessment

Soft sensing modeling based on support vector machine and self organizing maps model selection for water quality monitoring

Water quality control and monitoring is an important concern of countries over the world. We present in
this work, the use the self-organizing feature maps of Kohonen (SOFM) as features selection technique and
advanced classification techniques, such as: Long Short-Term Memory (LSTM) and Support Vector Machines
(SVM). This study involved the advanced assessment of surface water quality from Tilesdit dam in Algeria.
Typically, water quality status is determined by comparing collected data with water quality standards. LSTM and
SVM have been applied with SOFM-based features selection for water quality classification. In this work, the
training step is realized using the mentioned approaches to supervise the water quality from several physicochemical
parameters. Eleven of them were collected in 4 seasons during the period (2016-2018) from study area. Experiments
step using a mentioned dataset in terms of accuracy (training and test), running time and robustness, is carried out.
The performance of our approach is optimized by regulating the parameter values using a SFOM based features
selection method. The proposed approach outperforms current conventional methods, as this approach is a
combination of strong feature selection and classification techniques. Optimal input features are selected directly
from the original datasets, aiming to reduce the computational time and complexity. The impact of this result is
significant both technically (lower learning time) and economically (reduced the number of sensors) and can
improve obviously the performance of our monitoring system. The accuracy is more than 98% in training and testing
steps with features selection process for the LSTM and SVM models. The best results of sensitivity, specificity,
precision, and F-score of the two proposed models were ranged all between 96,99 % and 100%. In a nutshell, the
two comparative machine learning methods provide very high classification accuracy and make a considerable
solution for water quality control and monitoring.

Realisation d'un appareil de mesure de l'indice de qualite de l'eau propre

La présente invention concerne la réalisation d’un système automatique de régulation de l’ammoniac dans un aquarium

the objective of this article is the study of
conventional techniques, such as Burg algorithm, for
parameter estimation of autoregressive moving average
ARMA. Then, we introduce optimization techniques based
on Genetic Algorithms to improve the parameters estimation
of ARMA model. ARMA-Burg procedure was applied and
tested on the stator current signatures MCSA in order to
detect broken rotor bar of induction motor. It provides a
good estimate of the power spectral density (PSD) and
refines the parameters estimation of an ARMA model. The
test results show the importance and value of the GA in
improving performances of parameters estimation of an
ARMA model by adjustment.

The assessment of surface water quality is a major environmental concern and one of the most important tasks in ensuring safe drinking water sources. The Water Quality Index (WQI) describes a number of water quality variables at a certain location environment and time. WQI computation takes time and is frequently affected by errors when subindex calculations are performed. Thus, it is highly necessary to provide an accurate WQI prediction model. Different input combinations were developed using the best dataset, and the work strategy was to demonstrate water quality variation where all inputs have been reduced using features selection analysis like as: principal component analysis (PCA) and self-organizing feature map (SOFM). Two machine learning methods have been applied in the current research: ANN and SVM models to investigate and try to emulate WQI’s relationship with water quality variables in Tilesdit dam in Bouira (Algeria). Moreover, a comprehensive analysis has been performed for the performance assessment and sensitivity analysis of the variables. The models were appraised using several performance metrics. With high performance accuracy in two used models, the results achieved are promising. The proposed approach also provides an efficient alternative to calculate and predict the WQI by including long computing methods, transformations, the use of various subindex formulas for every value of the water quality component variables and time consumption.

Permanent magnet synchronous motor (PMSM) plays an effective role in electric vehicle applications. Monitoring PMSM's temperature in real time is critical to its safety and reliability. The traditional method of PMSM temperature monitoring is to install temperature sensors into the motor, and it is a very expensive method. Currently, the lumped-parameter thermal networks (LPTNs) are the appropriate alternative for determining PMSM components' temperatures. However, they lack physical interpretability once the degrees of freedom are reduced in order to meet real-time requirements. The approach based on soft sensors is an efficient and economical way to solve such problems. In this paper, a soft sensor is developed to predict the stator winding temperature using an extreme learning machine (ELM). Furthermore, the Principal Component Analysis (PCA) technique is used to select effective and relevant variables. The performance of the model is evaluated based on five statistical indicators: the correlation coefficient (R 2 ), the root relative squared error (RRSE), the mean square error (MSE), the mean absolute error (MAE), and the root-mean-squared error (RMSE). The results showed that the PCA-ELM model has a high efficiency to predict the stator winding temperature with RMSE = 0.0622, MAE = 0.0480, MSE = 0.0039, RRSE = 6.73% and R2 = 0.9955. Moreover, it has low computational complexity. Due to its low computational complexity and high performance, this application could have a direct influence and economic savings on the development and design of PMSMs temperature monitoring systems.

The study and use of water is essential for assessing the quality of surface waters. Several indices
have over the years been proposed using s statistical, mathematical, and computational techniques to enhance the
understanding of the phenomena that occur in these environments. For this purpose, the variables which influence
the quality of the water should be known. Nowadays, indices need to be developed that can address climate change
in its variables, making it even more realistic. In this study, multivariate statistical techniques such as PCA are
aimed at reduce the number of variables used to recover the costs, laboratory tests and greater representativeness
of indices. Searching for improvement and accuracy in indices of water quality, certain computational artificial
intelligence techniques, such as LSVM and ANN, are increasingly utilized and achieve expressive research results.
These Two machine learning methods have been applied in the current research to investigate and try to emulate
WQI’s relationship with water quality variables in Cheliff’s dam in Mostaganem (Algeria). Moreover, a comprehensive analysis has been performed for the performance assessment and sensitivity analysis of the variables.
With high performance accuracy in two used reduced models, the results achieved are promising. The proposed
approach also provides an efficient alternative to calculate and predict the WQI by including long computing methods, transformations, the use of various subindex formulas for every value of the water quality component variables
and time consumption.

Neural Network Modeling and Identification of Dynamical Systems presents a new approach on how
to obtain the adaptive neural network models for complex systems that are typically found in real-world applications. Neural networks are used in many applications such as image recognition, classification, control and
system identification. In this paper, a new hybrid Artificial Neural Network Autoregressive Moving Average
(ANNARMA) and Artificial Neural Network Autoregressive (ANNAR) scheme applied for dynamical systems
modeling is presented. This approach will deal with local minima problem of the neuronal networks architecture
and simultaneously preserve the fitting quality. The proposed model comprises a parallel interconnection of tow
sub-ANN models. The first sub-ANN model is the primary model, which represents an ordinary model with a low
resolution for the dynamical system under consideration. To overcome resolution quality problem, and obtain a
model with higher resolution, we will introduce a second ANN sub model called Error model which will represent
a model for the error modelling between the primary model and the real nonlinear dynamic system. Identification is achieved by innovative metaheuristic algorithms such as Imperialistic Competitive Algorithm (ICA) and
Teaching–learning-based optimization (TLO). The method’s effectiveness is evaluated through testing on the three
nonlinear dynamical systems described by Narendra in the literature. In addition, a detailed comparative study with
several benchmark methods will be give. Intensive computer experimentations confirm that the proposed approach
can significantly improve convergence and resolution.

In healthcare domain, the medical information treatment is very crucial for data acquisition, archiving,
presentation and decision support services. For exploring these data, several techniques based on machine learning
are utilized to predict a decision by building models. In this paper, we aim to develop an effective medical decision
system based on machine learning techniques for heart disease detection. In this context, we used three different
classification algorithms such as Decision Tree (DT), Support Vector Machines (SVM) and Linear Discriminant
Analysis (LDA). In addition, we can seriously reduce the time, materials, and labor to get the final decision while
increasing the prediction performance by using Sequential feature selection technique (SFS). Our experiments are
conducted on real heart diseases dataset that has been collected to assess and analyze the risk factors. The obtained
results show the effectiveness of the SFS technique with each cl

Surveillance of surface water quality is a major environmental challenge. The Water Quality Index
(WQI) describes a number of water quality variables at a certain location environment and time. WQI is usually
calculated by traditional methods involving long-term calculation, a timing consumption, and accidental errors occasionally associated with subindex calculation. Thus, it is highly necessary to provide an accurate WQI prediction
model. Recently, similar prediction applications were explored in artificial neural networks (ANNs) and the capability to capture the pattern of nonlinearity between forecast and prediction is remarkable. Two machine learning
methods have been applied in the current research: ANFIS and SVM models to investigate and try to emulate
WQI’s relationship with water quality variables in Cheliff’s dam in Mostaganem (Algeria). Moreover, a comprehensive analysis has been performed for the performance assessment and sensitivity analysis of the variables. With
high performance accuracy in two used models, the results achieved are promising. The proposed approach also
provides an efficient alternative to calculate and predict the WQI by including long computing methods, transformations, the use of various subindex formulas for every value of the water quality component variables and time
consumption.

We attempt to design artificial neural networks (ANN) that can help in the automatic identification of the
Autoregressive (AR) model. Within classic time series approaches, a time series model can be studied under three
groups, namely AR (autoregressive model), MA (moving averages model) and ARMA (autoregressive moving
averages model). In this paper, a new AR-ANN scheme applied for times series modeling is presented. It is based
on neural networks. This approach will deal with local minima problem of the neuronal networks architecture
and simultaneously preserve the fitting quality. The proposed model comprises a parallel interconnection of tow
sub-ANN models. The first is primary sub-ARMA-ANN model, which represents an ordinary model with a low
resolution for the time series under consideration, the second is an AR-ANN sub-model called the error model,
which represents uncertainty in the primary model. Identification is achieved by innovative metaheuristic optimization algorithms such as The invasive weed optimization algorithm (IWO) and covariance matrix adaptation
evolution strategy (CMA-ES). The method’s effectiveness is evaluated through testing on benchmark function and
real signals. In addition, a detailed comparative study with several benchmark methods would make. Intensive
computer experimentations confirm that the proposed method can significantly improve convergence and resolution.

The cascaded integrator comb (CIC) filters are characterized by coefficient less and reduced hardware requirement, which make them an economical finite impulse response (FIR) class in many signal processing applications. They consist of an integrator section working at the high sampling rate and a comb section working at the low sampling rate. However, they don’t have well defined frequency response. To remedy this problem, several structures have been proposed but the performance is still unsatisfactory. Thence, this paper deals with the improvement of the CIC filter characteristics by optimizing its sampling rate. This solution increases the performance characteristics of CIC filters by improving the stopband attenuation and ripple as well as the passband droop. Also, this paper presents a comparison of the proposed method with some other existing structures such as the conventional CIC, the sharpened CIC, and the modified sharpened CIC filters, which has proven the effectiveness of the proposed method.

Water quality monitoring plays a vital role in the protection of water resources, environmental management, and decision-making. Artificial intelligence (AI) based on machine learning techniques has been widely used to evaluate and classify water quality for the last two decades. However, traditional machine learning techniques face many limitations, the most important of which is the inability to apply these techniques with big data generated by smart water quality monitoring stations to improve the prediction. Real-time water quality monitoring with high accuracy and efficiency for intelligent water quality monitoring stations requires new and sophisticated techniques based on machine and deep learning techniques. For this purpose, we propose a novel approach based on the integration of deep learning and feature extraction techniques to improve water quality classification. In this paper, was chosen the Tilesdit dam in Bouira (Algeria) as a case study. Moreover, we implemented the advanced deep learning method - Long Short Term Memory Recurrent Neural Networks (LSTM RNNs) to construct an intelligent model for drinking water quality classification. Furthermore, principal component analysis (PCA), linear discriminant analysis (LDA) and independent component analysis (ICA) techniques were used for features extraction and data reduction from original features. Additionally, we used three methods of cross-validation and two methods of the out-of-sample test to estimate the performance of LSTM RNNs model. From the results we found that the integration of LSTM RNNs with LDA, and LSTM RNNs with ICA yields an accuracy of 99.72%, using Random-Holdout technique.

This paper presents a novel type-2 fuzzy model for
nonlinear dynamical systems. This method can deal with the curve
fitting and computational time problems of type-2 fuzzy systems.
It is based on interval type-2 fuzzy systems and it is comprised of
a parallel interconnection of two type-2 sub fuzzy models. The first
sub fuzzy model is the primary model, which represents an
ordinary model with low resolution for the nonlinear dynamical
system under consideration. To overcome resolution quality
problem, and obtain a model with higher resolution, we will
introduce a second type-2 fuzzy sub model called error model
which will represent a model for the error modelling between the
primary model and the real nonlinear dynamical system. As the
error model represents uncertainty in the primary model, it’s
suitable to minimize this uncertainty by simple subtraction of the
error model output from the primary model output, which will
lead to a parallel interconnection between them, giving then a
unique whole final model possessing higher resolution. To apply
this approach successfully, the model’s representation and
identification are considered in this investigation using type-2
fuzzy auto regressive (T2FAR) and type-2 fuzzy auto regressive
moving average (T2FARMA) models. Identification is achieved by
innovative metaheuristic optimization algorithms, like as firefly
and biogeography-based optimization algorithms. To evaluate the
effectiveness of the proposed method, it will be tested on three
types of nonlinear dynamical systems. Computer investigations
indicate that the proposed model may significantly improves
convergence and resolution.

Optimization of SVM parameters with hybrid PCA-PSO methods for water quality monitoring

One of the key causes of premature disability and mortality in the world today is heart disease, which makes its prediction a vital problem in the field of healthcare systems. This work provides a contribution to the study and creation an intelligent system based on LSTM technique for heart disease prediction. A comparative study is presented between Multi Layer Perceptron (MLP) and Long Short Term Memory (LSTM) techniques in terms of accuracy and other predictive parameters for heart disease. The main aim is to develop an intelligent system based on LSTM technique for predicting heart disease in order to make an adapted decision to prevent and monitor heart disease and stroke. As it has better characteristics than those of the MLP technique, LSTM is shown to be the most effective technique for solving the aforementioned problems.

Water quality monitoring are fundamental tools in the management of water resources and they provide essential information characterizing status of water resources, determining trends and changes over time, and identifying emerging water quality issues. This task consists of collecting quantitative information of different water parameters through a statistical sampling. For each parameters measurement, a sensor or a specific treatment is made. This makes the quality monitoring very expensive in money, time and labor. Therefore, it is important that water quality issues need to be understood in the framework of hydrological processes based on the water quality and hydrological monitoring.
To remedy this problem, we propose in this work an efficient system for water quality classification using Minimum Redundancy Maximum Relevance (mRMR) and Extreme Learning Machine (ELM). The mRMR is an algorithm frequently used in a method to accurately identify characteristics to reduce the number of input water parameters introduced in the ELM classifier and is usually described in its pairing with relevant feature selection. These subsets often contain material which is relevant but redundant and mRMR attempts to address this problem by removing those redundant subsets. mRMR has a variety of applications in many areas such as pattern recognition. As a special case, the "correlation" can be replaced by the statistical dependency between variables. Mutual information can be used to quantify the dependency. In this case, it is shown that mRMR is an approximation to maximizing the dependency between the joint distribution of the selected features and the classification variable. The ELM which is a technique for pattern classification has been widely used in many application areas such as water quality monitoring. A multi-class problem using ELM is a typical example for solving the mentioned problem.
In this work, Experimental results conducted on real dataset collected from Tilesdit dam of Bouira state (Algeria) were selected for this study. The proposed feature selection method can efficiently reduce the number of water parameters needed to classify its quality, which consequently causes a minimization in number of required sensor/treatment. Therefore, the water quality classification is perfectly insured with the trade-off between the low-cost and a high accuracy. Its performance is more competitive when compared with artificial neural networks. Furthermore, the results demonstrated that the proposed procedure has a great potential in water quality monitoring.

In this investigation a novel type-2 fuzzy model for Time series is presented. It is based on interval type-2 fuzzy systems. The proposed method deals with the curve fitting and computational time problems of type-2 fuzzy systems. This approach will significantly reduce the number of type-2 fuzzy rules and simultaneously preserves the fitting quality. The proposed model comprises a parallel interconnection of two type-2 sub-fuzzy models. The first one is the primary model, which represents an ordinary model with a low resolution for the time series under consideration. To overcome resolution quality problem and obtain a model with higher resolution, we introduce the second model called the error model. This model represents the error modelling between the primary model and the real time series model. The error model characterizes the uncertainty in the primary model which can be minimized by a simple subtraction of the error model output from the primary model output. The result is a parallel interconnection between the two sub models. Thus, a unique and entire final model possessing higher resolution is realized. The model's representation and identification are implemented by using type-2 fuzzy auto regressive moving average (T2FARMA) models. Identification is achieved by innovative metaheuristic optimization algorithm such as biogeography-based optimization (BBO). The effectiveness of the method is evaluated by testing the proposed model with the reference time series models. In addition, a detailed comparative study with several reference methods will be presented. The results of the experiments that have been conducted confirm that the proposed method can considerably improve convergence, resolution and computation time.

In this paper, we propose a heart disease prediction system based on Neighborhood Component Analysis (NCA) and Support Vector Machine (SVM). In fact, NCA is used for selecting the most relevant parameters to make a good decision. This can seriously reduce the time, materials, and labor to get the final decision while increasing the prediction performance. Besides, the binary SVM is used for predicting the selected parameters in order to identify the presence/absence of heart disease. The conducted experiments on real heart disease dataset show that the proposed system achieved 85.43% of prediction accuracy. This performance is 1.99% higher than the accuracy obtained with the whole parameters. Also, the proposed system outperforms the state-of-the-art heart disease prediction.

A Biometrics identification system is refers to the automatic recognition of individual person based on their characteristics. Basically biometrics system has two broad areas namely unimodal biometric system and multimodal biometric system. However, a reliable recognition system requires multiple resources [1].
Although multimodality improves the accuracy of the systems, it occupies a large memory space and consumes more execution time considering the collected information from different resources. Therefore we have considered the feature selection[2], that is, the selection of the best attributes that enhances the accuracy and reduce the memory space as a solution. As a result, acceptable recognition performances with less forge and steal can be guaranteed. In this work we propose an identification system using multimodal fusion of finger-knuckle-print, fingerprint and palmprint by adopting several techniques in feature level for multimodal fusion[3]. A feature level fusion and selection is proposed for the fusion of these three biological
traits. The proposed system has been tested on the largest publicly available PolyU [4] and Delhi FKP[5] databases. It has shown good performance.

Nowadays, one of the main reasons for disability and mortality premature in the world is the
heart disease, which make its prediction is a critical challenge in the area of healthcare systems.
In this paper, we propose a heart disease prediction system based on Neighborhood Component
Analysis (NCA) and Support Vector Machine (SVM). In fact, NCA is used for selecting the
most relevant parameters to make a good decision. This can seriously reduce the time,
materials, and labor to get the final decision while increasing the prediction performance.
Besides, the binary SVM is used for predicting the selected parameters in order to identify the
presence/absence of heart disease. The conducted experiments on real heart disease dataset
show that the proposed system achieved 85.43% of prediction accuracy. This performance is
1.99% higher than the accuracy obtained with the whole parameters. Also, the proposed system
outperforms the state-of-the-art heart disease prediction.

A major problem in water treatment plants is the continuous difficulty faced in online measurement by means of dedicated measuring hardware and laboratory analysis of certain variables related to the composition of water. Actually, for several reasons, such as the high cost of some sensors, their number, the dedicated time to check out the sensors, cleaning operation, calibration routines and sensor replacement, make their proper operation hard to ensure high-quality composition of water. Furthermore, in water quality monitoring, there is a huge number of heterogeneous sensors which may be time-consuming in the measurement and processing stages. Nevertheless, soft sensor approach can provide an effective and economic way to solve this problem for any cases of sensor failure. This work presents a contribution to the study and development of a soft sensor used in water quality monitoring using chlorine. A comparative study between support vector machine (SVM) and extreme learning machine (ELM) techniques in terms of learning time and other parameters for regression and classification is presented. The main objective is to set up a system architecture based on a soft sensor for water quality in order to make an adapted decision to the control and monitoring of water quality issues. ELM is shown to be the most suitable technique to address the previously mentioned problems as it has better characteristics than those of the SVM technique. An example of application is provided to focus on the interest of using a chlorine soft sensor as it is accurate, efficient and less cost-effective tool.