Optimal Artificial Neural Network Research Articles

Feasibility study and techno-economic optimization of an efficient renewable-based system for round-the-clock energy harvesting using machine learning approaches: A case study in Khaf city

A novel multi-generation solar-wind system is proposed in this study, uniting solar and wind renewable energy sources to enhance system reliability. The system incorporates hydrogen energy storage for continuous day and night energy harvesting, offering novel advancements in both reliability and uninterrupted energy supply. The system consists of parabolic through solar collectors (PTSCs), wind turbines (WTs), a steam Rankine cycle-thermoelectric generator (SRC-TEG), a reverse osmosis (RO) desalination unit, a proton exchange membrane (PEM) electrolyzer, hydrogen compression unit and a PEM fuel cell (PEMFC). During the day, the system produces power, fresh water and hydrogen, and at night, when the solar cycle is inactive, the system produces power using a fuel cell that consumes the hydrogen stored in the hydrogen tank. Also, the multi-generation system is fully evaluated from the point of view of energy, exergy and economy in both day and night modes. The proposed system is capable of generating 1624.7 kW of power during the day and 1290.4 kW of power at night. In addition, fresh water can be produced at a rate of 24.29 kg/s and hydrogen at a rate of 8.39 kg/h during the day. Moreover, meteorological data identifies Khaf city as highly suitable for harnessing solar and wind energy on an hourly and yearly basis. Furthermore, artificial neural network (ANN) and multi-objective optimization are used to optimize the system performance. In optimal conditions, the exergy round trip efficiency and overall cost rate of the proposed system are 42.75% and 158.93 $/h, respectively.

River system sediment flow modeling using artificial neural networks

Sediment leads to problems with navigation, agricultural productivity, and water pollution. The study of sediment flow in river reaches, which is a non-linear and complex process, is, thus, essential to addressing these issues. The application of artificial neural networks (ANN) to such problems needs to be investigated. For unsteady flow in a river system, river reach storage is an important variable that needs to be considered in data-driven models. However, previous research on sediment modeling did not involve the explicit use of storage variables in such models as is investigated in the current study. In the current study, storage variables have been explicitly (Model 2) used to predict the output state of the system at time ‘t + 1’ from the input state at time ‘t’ using ANNs. Sediment discharge at six gaging stations on the Mississippi River system, USA, has been considered as the state variable. The model has been compared with a model considering implicit variation of the storage parameter in the river system (Model 1). Dynamic ANNs are used for time-series datasets, which are more suitable for incorporating the sequential information within the dataset. Focussed gamma memory neural networks have been used in the current study. The numbers of hidden layers and hidden nodes, activation function, and learning rate have been varied step by step to obtain the optimal ANN configurations. The best selected input–output variables are those used in Model 2 as it performed slightly better than the other model in terms of Nash–Sutcliffe efficiency coefficient (CE) values. Model performance evaluated using normalized root mean square error (NRMSE) and CE shows satisfactory results. NRMSE was < 10% for all the outputs except for the Venedy and Murphysboro locations and CE values for sediment loads were > 0.45 for all locations except Murphysboro indicating acceptable performance by both the models. The models proved highly efficient (CE > 0.80, i.e., very good predictions) for predicting sediment discharge at locations along the main river channel with acceptable accuracy (CE > 0.45) for other locations and the storage change for the river system. These models can be used for real-time forecasting and management of sediment-related problems.

Forecasting the transportation energy demand with the help of optimization artificial neural network using an improved red fox optimizer (IRFO)

Transportation energy demand has a significant impact on worldwide energy consumption and greenhouse gas emissions. Accurate transportation energy demand predictions can help policymakers develop and implement successful energy policies and strategies. In this study, a novel approach to predict transportation energy demand using the Artificial Neural Network (ANN) based on the Improved Red Fox Optimizer (IRFO) has been suggested. The proposed method utilizes the ANN model to solve the complex nonlinear relationships between transportation energy demand and its effective parameters including Gross Domestic Product (GDP), population, and vehicle numbers. Also, the IRFO algorithm was utilized to modify the ANN model's parameters to improve the prediction accuracy. The experimental findings demonstrate the ANN-IRFO model performs better than the other method in terms of accuracy and effectiveness. It predicts the growth of GDP, population, and vehicles number by 5.5 %, 4.8 %, and 4.2 %, respectively. The findings demonstrate that the suggested method can provide accurate forecasts for transportation energy demand, which can help decision-makers to make informed decisions and policies regarding energy management and sustainability.

Molecular-based artificial neural networks for selecting deep eutectic solvents for the removal of contaminants from aqueous media

Computational methods for predicting a solvent’s performance in a given application, and for selecting an adequate solvent for that application, are becoming increasingly essential for separation processes. In this context, this article presents a first-of-a-kind machine learning tool based on guided molecular design of solvents to predict the performance of various solvent systems in the solvent extraction process. The tool was demonstrated herein for the extraction of aqueous boron, through the selection of neoteric solvents from a dataset that spans different types of solvents (molecular solvents, deep eutectic solvents (DESs) and ionic liquids). The model was developed by first obtaining the COSMO-RS-based molecular descriptors (σ-profiles) for each solvent system and using them as input parameters to an Artificial Neural Network (ANN), in addition to other operational parameters (e.g., pH, temperature, ion concentration, and A/O ratio), while extraction efficiency as the output. The results showed that the optimal ANN configuration (59–20-15–1) exhibited remarkable predictability for boron extraction with an R2 of 0.988 and 0.977 for the training and testing sets, respectively. The model was used to investigate different solvent systems of which six new DESs were successfully synthesized, experimentally tested, and characterized across different properties such as density, viscosity, and leachability. The combination of Decanol and 2,2,4- trimethyl-1,3-pentanediol exhibited appreciable properties and high experimental extraction efficiency of 97.22%. The experimentally validated model demonstrates the effectiveness of molecular-based descriptors and machine learning for predicting the extraction capabilities of solvents in aqueous media and allows further exploration of new solvent systems based on their extraction performance at different operational conditions. This proof-of-concept approach can be effectively adopted to predict the extraction behavior of different solvent systems towards target contaminants in aqueous environments, thereby supporting both the design of separation processes and solvent screening for future applications.

Discharge estimation in a compound channel with converging and diverging floodplains using ANN–PSO and MARS

Abstract The discharge estimation in rivers is crucial in implementing flood management techniques and essential flood defence and drainage systems. During the normal flood season, water flows solely in the main channel. During a flood, rivers comprise a main channel and floodplains, collectively called a compound channel. Computing the discharge is challenging in non-prismatic compound channels where the floodplains converge or diverge in a longitudinal direction. Various soft computing techniques have nowadays become popular in the field of water resource engineering to solve these complex problems. This paper uses a hybrid soft computing technique – artificial neural network and particle swarm optimization (ANN–PSO) and multivariate adaptive regression splines (MARS) to model the discharge in non-prismatic compound open channels. The analysis considers nine non-dimensional parameters – bed slope, relative flow depth, relative longitudinal distance, hydraulic radius ratio, angle of convergence or divergence, flow aspect ratio, relative friction factor, and area ratio – as influencing factors. A gamma test is carried out to determine the optimal combination of input variables. The developed MARS model has produced satisfactory results, with a mean absolute percentage error (MAPE) of less than 7% and an R2 value of more than 0.90.

Bounded Region for Tracking by Two Fuzzy Rules Based Perturb and Observe Technique with Fractional Order based Proportional Integral Controller for Photovoltaic Conversion System

Maximum power from PV system is tracked by using Maximum power point (MPP) tracking techniques. In this paper the Two fuzzy rules based perturb and observed (2F-P&O) with Fractional order based PI (FOPI) controller is developed to track the global MPP under Partial shading conditions (PSCs). The two rules based fuzzy systems are implemented to provide the voltage boundaries under which the P&O starts to track GMP. FOPI controller is used to minimize the error and gives an accurate response under PSCs. The performance analysis of 2F-P&O based MPP technique is showing along with cases as diagonal & column based shading patterns, irradiance change conditions under several PSCs. The 2F-P&O with FOPI based technique compared with traditional P&O, Artificial neural network and Particle swarm optimization, Moreover from the comparative analysis 2F-P&O has higher efficiency, less oscillations and convergence time. This paper is validated using Opal-RT simulator and MATLAB/ Simulink Software.

YSA ve Bukalemun Optimizasyon Algoritmalarına Dayalı DER'lerde Tekno Ekonomik için Pratik Radyal Dağıtım Besleyicisi

Distributed energy resources (DERs) are a better choice to meet load demand close to load centers. Optimal DER placement and DER ratings lead to power loss reduction, voltage profile improvement, environmental friendliness, dependability, and postponement of system changes. This study uses artificial neural networks and the Chameleon Optimization Algorithm to analyze the best integration of renewable energy sources and electric vehicles in distribution feeders to reduce power loss, regulate voltage levels, and decrease the cost and emissions under unpredictable load demand. In this study, the generated output power of the models is compared to solar photovoltaic generation systems and wind turbine generation systems. As a result, a fitness function with several objectives has been developed to reduce total active power loss while also reducing total cost and emissions generation. The study took into account the influence of EV charging/discharging behavior on the distribution system. The 28-bus rural distribution network in feeders is used to test the suggested methodology. Final analysis of the numerical results showed that the Artificial Neural Network and Chameleon Optimization Algorithms outperformed in terms of power loss (440.94 kw) and average purchase of real power (2224 kw), but these parameters do not favor the other optimization algorithms. This showed that the proposed strategy is both viable and effective.

Optimal artificial neural network configurations for hourly solar irradiation estimation

&lt;span lang="EN-US"&gt;Solar energy is widely used in order to generate clean electric energy. However, due to its intermittent nature, this resource is only inserted in a limited way within the electrical networks. To increase the share of solar energy in the energy balance and allow better management of its production, it is necessary to know precisely the available solar potential at a fine time step to take into account all these stochastic variations. In this paper, a comparison between different artificial neural network (ANN) configurations is elaborated to estimate the hourly solar irradiation. An investigation of the optimal neurons and layers is investigated. To this end, feedforward neural network, cascade forward neural network and fitting neural network have been applied for this purpose. In this context, we have used different meteorological parameters to estimate the hourly global solar irirradiation in the region of Laghouat, Algeria. The validation process shows that choosing the cascade forward neural network two inputs gives an R2 value equal to 97.24% and an normalized root mean square error (NRMSE) equals to 0.1678 compared to the results of three inputs, which gives an R2 value equaled to 95.54% and an NRMSE equals to 0.2252. The comparison between different existing methods in literature show the goodness of the proposed models.&lt;/span&gt;

Reliable detection of blast disease in rice plant using optimized artificial neural network

Early plant disease diagnosis is necessary for several purposes, including reducing yield losses, monitoring and predicting infections, detecting host resistance, and studying basic host–pathogen biological processes. However, early detection has been limited by a trained workforce and the ability to identify the problem early in the growing season. Artificial intelligence/machine learning algorithms can help fill this gap. Automatic leaf detection using machine learning is proposed in this study. The presented approach consists of three stages: pre‐processing, feature extraction, and classification. Initially, the input image is transformed into the red, green, and blue formatand the noise in the green band is removed using a median filter. Then important features of the green band are extracted. After feature extraction, the extracted features are fed to the optimized artificial neural network classifier to classify an image as normal or diseased. To improve artificial neural network (ANN) performance, the ANN parameters are chosen optimally using the adaptive sunflower optimization (ASFO) algorithm. Then, the infected region is separated using a level set segmentation algorithm. The efficiency of our work is analyzed based on accuracy, sensitivity, and specificity; the proposed method reached the maximum accuracy of 97.94% for plant disease prediction.

MOPSO-based structure optimization on RPV sealing performance with machine learning method

The structure integrity of reactor pressure vessels (RPV) plays an important role in the safety of nuclear power plants, which mainly concerns the risk of sealing failure. In the present work, a hybrid method consisting of an artificial neural network (ANN) and multi-objective particle swarm optimization (MOPSO) is proposed, aiming to find an optimized RPV structure with improved sealing performance. The ANN model provides a more accurate prediction of sealing performance than the radial basis function neural network (RBFNN) model. There is also a better generalization ability in the ANN model with R2 above 0.96 and RMSE below 0.06 in the test set. With ANN as a surrogate model, multi-objective optimization is applied in RPV structure design. Compared with that of the original RPV structure, the sealing performance can be improved by even over 25% in the optimized structure. The application of ANN surrogate models can save more than 99% computation cost, compared with optimization based on finite element analysis (FEA).

Experimental study for artificial neural network modeling on thermal and flow performances of electric traction motor with oil spray cooling

The oil spray cooling is emerging as advanced thermal management technique for next generation electric traction motor. The performance of oil spray cooling needs to be mapped and predicted based on various influential factors to develop efficient thermal management system for electric traction motors. In the present work, the thermal and flow performances are experimentally investigated and predicted using an artificial neural network (ANN) for electric traction motor with oil spray cooling. The thermal and flow performances are extracted in terms of maximum temperature, heat transfer coefficient, Nusselt number, spray pressure and spray power consumption. The effects of nozzle types, spray heights, volume flow rates and chiller temperatures are analyzed as operating factors. The ANNs are modeled considering Levenberg-Marquardt (LM) training variant, 10 hidden neurons and Tangential-sigmoidal (Tan) and Logarithmic-sigmoidal (Log) as transfer functions. The thermal and flow performances are superior for full cone followed by hollow cone and spiral nozzles in decreasing order. The higher spray height, higher volume flow rate and lower chiller temperature show optimum values of maximum temperature and heat transfer coefficient. The spray power consumption is maximum in case of higher volume flow rate, reported less variation with change in spray height and chiller temperature. The ANN model comprising of LM-Tan algorithm is recommended as the best model with prediction error within ±1% for all thermal and flow performances. The predicted results from the optimum ANN model are validated with experiments with maximum coefficient of determination (R2) and coefficient of variance (COV) as 0.99 and 3.20, respectively. The correlations for thermal and flow performances in terms of all influential factors are proposed using the optimum ANN model.

Biodiesel Production from Waste Cooking Oil Using Extracted Catalyst from Plantain Banana Stem via RSM and ANN Optimization for Sustainable Development

Biodiesel is a promising sector worldwide and is experiencing significant and rapid growth. Several studies have been undertaken to utilize homogeneous base catalysts in the form of KOH to develop biodiesel in order to establish a commercially viable and sustainable biodiesel industry. This research centers around extracting potassium hydroxide (KOH) from banana trunks and employing it in the transesterification reaction to generate biodiesel from waste cooking oil (WCO). Various operational factors were analyzed for their relative impact on biodiesel output, and after optimizing the reaction parameters, a conversion rate of 95.33% was achieved while maintaining a reaction period of 2.5 h, a methanol-to-oil molar ratio of 15:1, and a catalyst quantity of 5 wt%. Response surface methodology (RSM) and artificial neural network (ANN) models were implemented to improve and optimize these reaction parameters for the purpose of obtaining the maximum biodiesel output. Consequently, remarkably higher yields of 95.33% and 95.53% were achieved by RSM and ANN, respectively, with a quite little margin of error of 0.0003%. This study showcases immense promise for the large-scale commercial production of biodiesel.

Inversion of Rayleigh Wave Dispersion Curve Extracting from Ambient Noise Based on DNN Architecture

The inversion of the Rayleigh wave dispersion curve is a crucial step in obtaining the shear wave velocity (VS) of near-surface structures. Due to the characteristics of being ill-posed and nonlinear, the existing inversion methods presented low efficiency and ambiguity. To address these challenges, we describe a six-layer deep neural network algorithm for the inversion of 1D VS from dispersion curves of the fundamental mode Rayleigh surface waves. Our method encompasses several key advancements: (1) we use a finer layer to construct the 1-D VS model of the subsurface, which can describe a more complex near-surface geology structure; (2) considering the ergodicity and orderliness of strata evolution, the constrained Markov Chain was employed to reconstruct the complex velocity model; (3) we build a practical and complete dispersion curve inversion process. Our model tested the performance using a random synthetic dataset and the influence of different factors, including the number of training samples, learning rate, and the selection of optimal artificial neural network architecture. Finally, the field test dispersion data were used to further verify the method’s effectiveness. Our synthetic dataset proved the diversity and rationality of the random VS model. The results of training and predicting showed higher accuracy and could speed the inversion process (only ~15 s), and we proved the important effect of different factors. The outcomes derived from the application of this technique to the measured dispersion data in the Yellow River Delta exhibit a strong correlation with the outcomes obtained from the integration of the very fast simulated annealing method and the downhill simplex method, as well as the statistically derived shear wave velocity data of the sedimentary layers in the Yellow River Delta. From a long-term perspective, our method can provide an alternative for deriving VS models for complex near-surface structures.

Designing soft computing algorithms to study heat transfer simulation of ternary hybrid nanofluid flow between parallel plates in a parabolic trough solar collector: Case of artificial neural network and particle swarm optimization

This study inspects the heat transport of a ternary hybrid nanofluid flow inside a receiver tube in a parabolic trough solar collector. The mathematical model of the flow is modeled inside the receiver tube using rotating parallel plates. The analysis discusses the influence of the Hall effect, the Cattaneo-Christov model, suction/injection, and thermal radiation (linear and quadratic). Traditional approaches to the parametric study which involve a large number of parameters sometimes fail to infer meaningful outcomes due to the high complexity of the model and numerical methods. To resolve this matter, this study evaluates the capability of soft computing techniques to foresee the behavior of a problem with various interrelated parameters. The data obtained by simulation is used to train the artificial neural network and particle swarm optimization algorithm. Thereafter artificial neural network and particle swarm optimization algorithm is utilized to precisely estimate the values of the Nusselt number at the lower and upper plates. The prediction performance of the developed algorithms is analyzed with the help of mean squared error, average forecasting error rate, and coefficient of correlation. The analysis shows the advantages of soft computing techniques to study the behavior of complex flow models with high accuracy.

Using the numerical simulation and artificial neural network (ANN) to evaluate temperature distribution in pulsed laser welding of different alloys

The temperature field during laser welding process plays an important role on determining the quality and quantity of the weld bead size, microstructure characterizations and mechanical properties of the welding interface in the thermal engineering applications. In this study, using the numerical simulation, the influence of pulse duration and frequency on the temperature distribution and velocity field in distinctive laser welding of stainless steel 420 (S.S 420)/stainless steel 304 (S.S 304), and Bohler 303 (B 303)/stainless steel 304 (S.S 304) was examined. The results of numerical modeling illustrated that shear stress of Marangoni and buoyancy force are the most curtail aspects in the formation of the flow of liquid metal. A novel artificial intelligence method is proposed to optimally predict the melting ratio, and maximum temperature of the materials. To this end, a combination of ANN and Particle Swarm Optimization (PSO) algorithms are employed. The PSO algorithm is used to optimize the architecture and training algorithm of the ANN, while the ANN is employed for the regression problem. Based on the results, a three-layer feed-forward architecture with sigmoid transfer functions having 17 and 8 neurons in the hidden layers combined with the scaled conjugate gradient backpropagation training scheme is recognized by the PSO as the optimal configuration. Application of optimal ANN to the regression problem results in an acceptable level of error for the training, validation, and test datasets. Finally, the optimized ANN can be utilized to anticipate the melting ratio and thereby the resultant temperature.

Towards optimal reliability-based design of wind turbines towers using artificial intelligence

Metaheuristic Optimization Techniques and Artificial Neural Networks (ANNs) have proven to be useful tools to find the best design solutions for different structural systems. However, the application of both techniques oriented toward the optimal design of wind turbine towers still requires further research. A methodology is presented to obtain the best design solutions for onshore wind turbine steel towers using the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm and ANNs. The proposed methodology is applied to steel towers with heights of 70, 75, 80, and 85 m. Case studies are assumed to be located in La Ventosa, Oaxaca. Three design objectives are defined: minimize the mass of the structure, maximize the structural reliability, and maximize the wind power. In order to avoid high computational costs, ANNs are trained and used to obtain the structural reliability index β. First, the design variables and constraints are defined; subsequently, a metaheuristic swarm intelligence-based optimization (MOPSO) technique is implemented. As a result of the optimization process using the MOPSO algorithm, a Pareto Front that includes the best design solutions is efficiently obtained. Finally, graphs are generated in order to recommend initial parameters for pre-design of steel towers, satisfying three design objectives.

Impact of thermal pasteurization and thermosonication treatments on black grape juice (Vitis vinifera L): ICP-OES, GC–MS/MS and HPLC analyses

Grape juice is a widely consumed fruit due to its bioactive compounds, minerals, and aroma components. Our objective was to investigate ultrasound treatment of black grape juice affects its bioactive components due to using response surface methodology (RSM) and artificial neural network (ANN) optimization. At the same time, mineral components, sugar components, organic acids, and volatile aroma profiles were compared in black grape juice treated with thermal and ultrasound pasteurization. ANN showed superior predictive values (>99%) to RSM. Optimal combinations were obtained at 40 °C, 12 min, and 65% amplitude for thermosonication. Under these conditions, phenolic, flavonoid, antioxidant activity, and anthocyanin values were 822.80 mg GAE/L, 97.50 mg CE/L, 24.51 mmol Trolox/L, and 368, 81 mg of mv-3-glu/L, respectively. Thermosonicated grape juice (TT-BGJ) was tested against black grape juice (P-BGJ) produced with conventional thermal methods. This study investigated the effects of thermal pasteurization and thermosonication on black grape juice bioactive compounds and minerals, aroma profile, and sensory evaluation. Thermosonication affected the aroma profile less, 329.98 μg/kg (P-BGJ) and 495.31 μg/kg (TT-BGJ). TT-BGJ was detected to contain seven different mineral elements (Mn, K, Fe, Mg, Cu, Zn, and Na). Thermosonication caused an increase in Fe, Zn, Mn, and K minerals. Panelists generally liked the TT-BGJ sample. These results suggest that the thermosonication process may potentially replace the traditional black grape juice processing thermal process.

Intelligent Design of Hairpin Filters Based on Artificial Neural Network and Proximal Policy Optimization

Microstrip filters are widely used in high-frequency circuit design for signal frequency selection. However, designing these filters often requires extensive trial and error to achieve the desired performance metrics, leading to significant time costs. In this work, we propose an automated design flow for hairpin filters, a specific type of microstrip filter. We employ artificial neural network (ANN) modeling techniques to predict the circuit performance of hairpin filters, and leverage the efficiency of low-cost models to deploy reinforcement learning agents. Specifically, we use the proximal policy optimization (PPO) reinforcement learning algorithm to learn abstract design actions for the filters, allowing us to achieve automated optimization design. Through simulation results, we demonstrate the effectiveness of the proposed approach. By optimizing the geometric dimensions, we significantly improve the performance metrics of hairpin filters, and the trained agent successfully meets our specified design goals within 5 to 15 design steps. This work serves as a conceptual validation attempt to apply reinforcement learning techniques and pre-trained ANN models to automate MMIC filter design. It exhibits clear advantages in terms of time-saving and performance efficiency when compared to other optimization algorithms.

Prediction model of long-term tensile strength of glass fiber reinforced polymer bars exposed to alkaline solution based on Bayesian optimized artificial neural network

The present study presents a model for predicting the long-term tensile strength of glass reinforced thermoset polymer (GFRP) bars based on the artificial neural network (ANN) algorithm, for bars which were exposed to alkaline solutions with different temperatures, different chloride ions concentration, and different applied stress levels. 272 groups of durability data of GFRP bars were collected from the literature. The correlation coefficients between each input feature and the target variable were calculated to analyze their relationships. The principal component analysis (PCA) method was performed to identify possible opportunities to reduce the input dimensions. Bayesian optimized search and randomized search were used and compared to tune and optimize the hyperparameters of the ANN model. Once the optimal ANN model was built, permutation feature importance, partial dependence plot (PDP), and SHapley Additive exPlanations (SHAP) value methods were used to interpret the optimal model. Results indicate that only the ultimate tensile strength has a high potential of being linearly changing with the long-term tensile strength of GFRP bars. PCA results show that the input dimensions cannot be reduced if 99% explained variance needs to be retained. The optimal ANN model trained through the Bayesian optimized search method can achieve a determination coefficient R2 and a mean absolute percentage error of 0.941 and 7.11%. Permutation feature importance and SHAP importance both ranked the initial ultimate tensile strength of GFRP bars as the most important input feature, followed by temperature, ageing time, diameter, applied stress level, pH value, and chloride ions concentration based on their SHAP values. On average, the PDP result of the ageing time tended to show that there will be a certain residual tensile strength of GFRP bars after ageing for a long period.

Efficient classification of kidney disease detection using Heterogeneous Modified Artificial Neural Network and Fruit Fly Optimization Algorithm

Chronic kidney disease (CKD), a significant issue for public health, affects millions of individuals globally. The course of end-stage renal disease must be stopped or reversed, hence it is crucial to find chronic kidney disease early in order to receive therapy. Prediction of CKD is a second source of treatment, as machine learning techniques, with their high classification accuracy, are becoming increasingly significant in medical diagnosis. To learn about CKD and associated issues in this situation, deep learning is used. The sole inputs used to construct the three distinct types of models were the retinal fundus image alone (test model), the covariate only (the reference model), and the retinal fundus image plus covariate (hybrid model). To maintain the accuracy of contemporary classification systems, feature selection techniques must be applied correctly in order to reduce data size. Here, recommend the Fruit fly optimisation algorithm (FFOA) and the heterogeneous artificial neural network (HMANN) in this paper for efficient disease categorization. An Internet of Medical Things (IoMT) platform is presented for the early detection, segmentation, and diagnosis of chronic renal failure using a heterogeneous modified artificial neural network (HMANN). The Multilayer Perceptron (MLP) and Support Vector Machine (SVM) algorithms are used to classify the suggested HMANN. The ideal feature is chosen using an FFOA from a large pool of candidate features. The proposed method uses ultrasound pictures as its foundation and, as a first step in processing, slices a region of interest in the kidney in the ultrasound image. The accuracy, sensitivity, specificity, positive predictive power, negative predictive power, false positive rate, and false negative rate of the suggested CKD classification system were all taken into consideration when evaluating its performance.