Artificial Neural Network Technique Research Articles

A review on soft computing techniques used in induction motor drive application

<div align="center"><table width="590" border="1" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="387"><p>In this paper, hybrid models based on fuzzy systems and neural networks are reviewed. A fuzzy inference system is explicitly represented by expertise for induction motor drives, incorporating the learning capability of artificial neural networks. Researchers have been attracted to neuro-fuzzy techniques for training and inference in induction motor drives due to their efficiency. According to the classification of research articles from 2000 to 2020, this article presents a review of different artificial neural network techniques, fuzzy and neuro-fuzzy systems. The main objective is to provide a concise overview of current neuro-fuzzy research and to enable readers to identify appropriate methods according to their research interests.</p><p> </p></td></tr></tbody></table></div>

Modelling and prediction of aeration efficiency of the venturi aeration system using ANN-PSO and ANN-GA

The significance of this study involves the optimisation of the aeration efficiency (AE) of the venturi aerator using an artificial neural network (ANN) technique integrated with an optimisation algorithm, i.e., particle swarm optimisation (PSO) and genetic algorithm (GA). To optimise the effects of operational factors on aeration efficiency by utilising a venturi aeration system, aeration experiments were conducted in an experimental tank with dimensions of 90cm×55cm×45cm. The operating parameters of the venturi aerator include throat length (TL), effective outlet pipe (EOP), and flow rate (Q) to estimate the efficacy of the venturi aerator in terms of AE. A 3–6-1 ANN model was developed and integrated with the PSO and GA techniques to find out the best possible optimal operating variables of the venturi aerator. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) determined from the experimental and estimated data were used to assess and compare the performance of the ANN-PSO and ANN-GA modelling. It is shown that ANN-PSO provides a better result as compared to ANN-GA. The operational parameters, TL, EOP, and Q, were determined to have the most optimum values at 50 mm, 6 m, and 0.6 L/s, respectively. The optimised aeration efficiency of the venturi was found to be 0.105 kg O2/kWh at optimum operational circumstances. In fact, the neural network having an ideal design of (3-6-1) and a correlation coefficient value that is extremely close to unity has validated the results indicated above.

Estimation of calorific value using an artificial neural network based on stochastic ultimate analysis

The main aim of the present study was to estimate the calorific value (CV) by considering the uncertainty in municipal solid waste (MSW) generation using a cohesive Artificial Neural Network (ANN) technique. The parameters from ultimate analysis are taken as input data and CV as output data for 300 samples and seasonal variation is considered for predicting CV. Monte Carlo Simulation Technique is applied to deal with the uncertainty in MSW characteristics and the Simultaneous Backward Reduction (SBR) approach is used to tackle scenarios into a manageable number. Various ANN models were built based on the seasonal variation for three cities: ANNMS, ANNMW, ANNUS, ANNUW, ANNBS and ANNBW. The results depicted that network ANNMS for the architecture (9-21-1) has a minimum MAPE value of 1.22% with an estimation accuracy of 94.61%. The network ANNUS has a minimum MAPE of 1.62% has an estimation accuracy of 93.2% for the architecture (9-23-1). The network ANNBW Baddi City has a minimum MAPE is 2.23% for the network (9-21-1) with an estimation accuracy of 91.77% respectively. The developed ANNs model in the present study is beneficial to estimate the CV of MSW samples using elemental composition considering the uncertainty in the data, leading to more accuracy in the prediction models. It helps to minimize experimental costs and gives a theoretical background for modeling MSW's energy potential based on Waste to Energy (WTE) technologies.

Identifying and analysing the phonetics of low resources Nyishi language using artificial neural network technique

Phonemic identification is an analysis and classification based on sounds. Phonetics can be categorized into three various types based on how it is articulated, perceived, and produced. The study introduces new Niyshi phonetic identification approaches based on artificial neural networks to improve the detectability of the system. This work has the goal of coming up with an effective technique that can be used to detect both non-nasalized and nasalized phonemes; by classifying phonemes into those belonging or not originating from the Nyishi dialect. The model that can be used to train, test, and validate can include a multilayer-based perceptron classifier. The proposed model identifies a complex old language with an accuracy as high as 87% through Multi-Layer Perceptron (MLP). To end, a confusion matrix analysis for ten trials involving an average of 89% accuracy for 20% trained dataset validation purposes confirms the efficiency and efficacy of the methodologies employed.

The bold decision to go “all in”: Understanding the reasons behind consumers' willingness to migrate to the metaverse

AbstractThe study explores the reasons that drive and hinder consumers' willingness to migrate to the metaverse. To determine them, a mixed‐methods approach is used: phase 1 (qualitative) involves conceptual development of a model based on in‐depth consumer interviews, and in phase 2, the conceptual model is empirically tested via structural equation modeling. Results show that social presence is a crucial enabler, while realistic and symbolic threats are significant inhibitors of the willingness to migrate. Preusage cognitive dissonance significantly mediates the relationships between social escapism, social pressure, realistic threat, symbolic threat, and willingness to migrate. Specifically, the mediating influence between empowerment and willingness to migrate is higher for individuals with low metaverse anxiety. Results of the artificial neural network technique indicate that social presence is the most significant antecedent of willingness to migrate, and results of the fuzzy‐set qualitative comparative analysis highlight the presence of six distinct configurations that indicate a high willingness to migrate. This study enriches the behavioral reasoning theory by examining the interplay of the reasons influencing the willingness to migrate. Further, it contributes to the intergroup threat theory by investigating the potential link between willingness to migrate and the presence of realistic and symbolic threats.

Machine learning‐based wind‐induced response analysis in rectangular building models with limbs

SummaryThis study investigates the impact of different positions of two limbs on the structural response of a rectangular building model to wind forces. The building's geometry assumes Z and + shapes based on specific limb configurations. Computational fluid dynamics (CFD) simulations are performed to quantify wind‐induced pressures, resulting in wind force coefficients. These coefficients are used to develop predictive machine learning models through Gene Expression Programming, Group Method of Data Handling‐combinatorial (GMDH‐Combi), Model Tree, and Artificial Neural Network (ANN) techniques. The ANN analysis explores various combinations of training algorithms, adaptation functions, activation functions, and performance functions to enhance model accuracy. Among these, the Levenberg–Marquardt (LM) with gradient descent with momentum (GDM) adaptation function and sigmoid activation function exhibit superior performance with high R‐squared values. These predictive models are then employed for a comprehensive comparative assessment of the maximum wind force coefficient (CF, max) concerning different limb positions and angles of attack (AOA). For CF, max vs Limb position, variations of limb position are examined for most critical cases of AOA. Similarly, the study of CF, max vs AOA involves an exhaustive investigation into the variation of AOA for the building with the worst limb position. The analysis reveals that changes in AOA have a more pronounced effect on CF, max compared to alterations in limb position. Interestingly, within the AOA range of 1.5 to 2.5, the CF, max consistently reaches a minimum across all models. However, the relationship between CF, max and the critical structural parameter ‘S' (representing limb position) remains less conclusive for the most significant AOAs.

The neural network approach for estimation of heat transfer coefficient in heat exchangers considering the fouling formation dynamic

Routine maintenance for plate heat exchanger (PHE) cleaning improves the effectiveness of heat exchange network operation. Until recently, complex mathematical modelling was used to predict the value of the heat transfer coefficient after a certain period of operation of the heat exchanger, as well as the point in time when the coefficient reached the allowable limit. The applied mathematical tools included the systems of differential equations, matrices of heuristic coefficients, which needed a lot of computer resources. This paper offers an artificial neural network (ANN) technique for forecasting the following values: heat transfer coefficient at any time points during the operating period of PHEs; the time point, when the heat transfer coefficient reaches its lower permitted value. In this method, ANN uses the fuzzy logic techniques to expand the set of training parameters for the model, working with data of industrial measurements and data obtained from the mathematical modelling of the process. It allowed to train the developed feed-forward neural network (FFNN) with the coefficient of determination R2 equal to 0.99 and can predict the thermal resistance in PHE based on measurement data. To adequately predict the time-point to reach the limiting value of the heat transfer coefficient, it was proposed a recurrent neural network (RNN) with a hidden layer of long short-term memory (LSTM), where R2 value came up to 0.89.

Prediction of hospital-acquired influenza using machine learning algorithms: a comparative study

BackgroundHospital-acquired influenza (HAI) is under-recognized despite its high morbidity and poor health outcomes. The early detection of HAI is crucial for curbing its transmission in hospital settings.AimThis study aimed to investigate factors related to HAI, develop predictive models, and subsequently compare them to identify the best performing machine learning algorithm for predicting the occurrence of HAI.MethodsThis retrospective observational study was conducted in 2022 and included 111 HAI and 73,748 non-HAI patients from the 2011–2012 and 2019–2020 influenza seasons. General characteristics, comorbidities, vital signs, laboratory and chest X-ray results, and room information within the electronic medical record were analysed. Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) techniques were used to construct the predictive models. Employing randomized allocation, 80% of the dataset constituted the training set, and the remaining 20% comprised the test set. The performance of the developed models was assessed using metrics such as the area under the receiver operating characteristic curve (AUC), the count of false negatives (FN), and the determination of feature importance.ResultsPatients with HAI demonstrated notable differences in general characteristics, comorbidities, vital signs, laboratory findings, chest X-ray result, and room status compared to non-HAI patients. Among the developed models, the RF model demonstrated the best performance taking into account both the AUC (83.3%) and the occurrence of FN (four). The most influential factors for prediction were staying in double rooms, followed by vital signs and laboratory results.ConclusionThis study revealed the characteristics of patients with HAI and emphasized the role of ventilation in reducing influenza incidence. These findings can aid hospitals in devising infection prevention strategies, and the application of machine learning-based predictive models especially RF can enable early intervention to mitigate the spread of influenza in healthcare settings.

Effective optimization strategies for abrasive water jet machining of glass-carbon fiber reinforced composites: A comparative study of evolutionary optimization techniques

This study applied evolutionary optimization techniques and neural networks to predict optimum machining parameters of Abrasive Water Jet Machining (AWJM) for machining Glass-Carbon Fiber Reinforced Composite (GCFRC) materials. Several researchers have employed different optimization techniques; however, evolving computational capabilities further open avenues to optimize such parameters. Five evolutionary techniques, namely Artificial Neural Network (ANN), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), and Nonlinear Least Square Error (LSE), were applied to minimize surface roughness (Ra) and maximize kerf width (Kw) and material removal rate (MRR). The output performance parameters (Ra, Kw, and MRR) were formulated as a linear mathematical function of machining parameters: tool feed rate (TFR), cutting speed rate (CSR), and stand-off distance (SOD). Though this study solves linear optimization problems, the proposed technique will be a strong tool for solving complex associations of machining and performance parameters in the future. A dataset of machining parameters and subsequent performance parameters was adopted from the available literature. The results indicated that the LSE method outperformed other techniques, yielding the lowest Root Mean Square Error (RMSE) in predicting Ra, Kw, and MRR, thus ensuring high machining accuracy. LSE technique reported relatively least RMSE values of 0.37 µm, 0.149Mm, and 237.23 mm3/min for Ra, Kw, and MRR, respectively. SA and PSO displayed identical and competitive RMSE values, slightly higher than LSE (up to 20 % higher). ANN and GA techniques were not effective relative to other considered techniques. LSE, SA, and PSO provide superior performance in optimizing AWJM parameters. The significant contribution of this research is the proposed optimization technique, offering a clear direction for solving complex associations between the performances and machining parameters of AWJM. This work also provides a foundation for future research to optimize such associations for other machining setups.

Why to purchase health knowledge on online platforms? A two-phased SEM-ANN approach

ABSTRACT Previous research on online health knowledge payment has mainly focused on the health consultation context and knowledge contributors-related characteristics. However, less attention has been given to the roles of health knowledge itself and the underlying platforms. Based on the perceived value theory and S-O-R framework, this study investigated how health knowledge and platform characteristics influence consumers’ purchase intention. Through a survey of 432 Chinese respondents, we employed a multi-analytical approach, combining structural equation modelling (SEM) with artificial neural network (ANN) techniques. SEM results indicate that knowledge personalisation, platform information quality, and platform service quality positively influence both utilitarian and hedonic values, subsequently affecting purchase intention. Furthermore, our findings support the partial mediation role of perceived value. ANN results highlight platform information quality as the most influential stimulus factor. Our study broadens the research scope of online health knowledge payment and offers theoretical and practical insights for its further advancement.

Classification model for reducing absenteeism of nurses at hospitals using machine learning and artificial neural network techniques

Classification model for reducing absenteeism of nurses at hospitals using machine learning and artificial neural network techniques

Flood classification and prediction in South Sudan using artificial intelligence models under a changing climate

This study used Artificial Intelligence (AI) techniques as a modeling tool to estimate the risk of Nile flooding in the cities of southern Sudan. Climatic records, and precipitation, from stations along the area were used between 2010 and 2019. To test how well the models worked, the forecast was done using a variety of stations. To determine the flood rate in southern Sudan with the highest degree of accuracy, various artificial neural network techniques were investigated. Six artificial neural network (ANN) models were created and compared to show flood prediction to reach the maximum level of accuracy and to improve the results (NN, GRNN, RNN, CFNN, PNN, FFNN). The artificial neural network (FFNN) produced the best results in the first test, reaching a 95 % accuracy rate. Three further strategies were evaluated by increasing the neural network's hidden layer count to ten. Tests with 15 and 25 hidden layers also showed that the accuracy changes with the increase of hidden layers. Also, six other algorithms were applied to reach the highest value expected from Using one of the artificial intelligence techniques (AI), in predicting the flood by machine learning methods (ML). The highest expected value of flooding was reached through the (Gradient Boosting) model, where it was Classification Accuracy (CA) 0.937, followed by (AdaBoost), (CA 0.916).

Spike-Weighted Spiking Neural Network with Spiking Long Short-Term Memory: A Biomimetic Approach to Decoding Brain Signals

Background. Brain–machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs.

Multivariate modelling of AA6082-T6 drilling performance using RSM, ANN and response optimization

The AA6082-T6 was experimentally studied in the present research with respect to the drilling performance. Drill diameter, cutting speed and feed rate were examined, using a full factorial design. Mathematical modelling of the process was carried out using the Response Surface Methodology (RSM) as well as the Artificial Neural Network (ANN) techniques. The output results in terms of cutting force, torque and surface roughness, revealed high levels of correlation between the experimental and the predicted data. Specifically, the Mean Absolute Percentage Error (MAPE) values using RSM compared to the ones of the experiments, were equal to 2.14%, 3.49% and 6.16% for Fz, Mz and Ra respectively. The equivalent MAPE between the ANN and the experiments were found to be 2.19%, 1.82% and 2.85% accordingly. Moreover, the most significant terms were revealed, being the interaction D × f for the thrust force and the torque with contribution percentages equal to approximately 44% and 42% respectively, and the term D2 for the surface roughness with 51%. The evaluation of the machining parameters, identified their significance, enabling the selection of the optimal cutting parameters, which were obtained by the desirability function, taking into account the importance of the generated surface quality and the reduction of cost. The solutions given by this approach, pointed out the Ø9 tool, coupled with Vc = 50 m/min and f = 0.15mm/rev as a well-balanced combination, whereas the Ø9.9 tool used under the same conditions, yielded the best possible surface quality (appr. 0.2 μm).

Optimizing Neuroprotective Nano-structured Lipid Carriers for Transdermal Delivery through Artificial Neural Network.

Dementia associated with Alzheimer's disease (AD) is a neurological disorder. AD is a progressive neurodegenerative condition that predominantly impacts the elderly population, although it can also manifest in younger people through the impairment of cognitive functions, such as memory, cognition, and behaviour. Donepezil HCl and Memantine HCl are encapsulated in Nanostructured Lipid Carriers (NLCs) to prolong systemic circulation and minimize the systemic side effects. This work explores the use of data mining tools to optimize the formulation of NLCs comprising of Donepezil HCl and Memantine HCl for transdermal drug delivery. Neuroprotective drugs and excipients are utilized for protecting the nervous system against damage or degeneration. The NLCs were formulated using a high-speed homogenization technique followed by ultrasonication. NLCs were optimized using Box Behnken Design (BBD) in Design Expert Software and artificial neural network (ANN) in IBM SPSS statistics. The independent variables included the ratio of solid lipid to liquid lipid, the percentage of surfactant, and the revolutions per minute (RPM) of the high-speed homogenizer. The NLCs that were formulated had a mean particle size ranging from 67.0±0.45 to 142.4±0.52nm. Both drugs have a %EE range over 75%, and Zeta potential was determined to be - 26±0.36mV. CryoSEM was used to do the structural study. The permeation study showed the prolonged release of the formulation. The results indicate that NLCs have the potential to be a carrier for transporting medications to deeper layers of the skin and reaching systemic circulation, making them a suitable formulation for the management of Dementia. Both ANN and BBD techniques are effective tools for systematically developing and optimizing NLC formulation.

Catalytic pyrolysis of pine needles using metal functionalized spent adsorbent derived catalysts: Kinetics, thermodynamics and prediction modelling using artificial neural network (ANN) approach

The current study was indented towards the evaluation of synergism of spent aluminum hydroxide nanoparticle (AHNP) adsorbent derived catalysts in the degradation of pine (Pinus roxburghii) needles through kinetics and thermodynamics analysis. Distinct kinetic (such as activation energy and pre-exponential factors) and thermodynamic (such as entropy, enthalpy, and Gibbs free energy) parameters were estimated through isoconversional (OFA and KAS) models. The study also aimed to envisage the reaction mechanism for all the distinct processes via Criado z master plots. Results illustrated the significant impact of all the different AHNP-derived catalysts in easing up the biomass degradation process. The KAS method evaluated the average activation energy for non-catalytic degradation as 130.01 kJ/mol, while the values changed to 120.95, 121.69, 125.99, 148.47 and 127.37 kJ/mol for Ni/AO, Fe/AO, Cu/AO, Zn/AO and Mo/AO catalyzed degradation, respectively. Amongst all, nickel (Ni/AO) and iron-doped (Fe/AO) catalysts brought the highest reduction in activation energy owing to the provision of strong acidic sites, high specific surface area, and better metal dispersion; subsequently leading to the increased rate of molecular scission and cracking reactions. Values of pre-exponential factor and thermodynamic parameter also displayed the positive impact of catalysts in terms of lowering down the molecular collisions, enthalpy, and disorderness of the system. Furthermore, artificial neural network (ANN) was also employed for the prediction of the biomass degradation where high regression (∼0.99) as well as low mean squared error (<10−5) illustrated the accurate prediction of complex biomass degradation by the ANN technique. Thus, the waste AHNP-derived catalysts have significant potential to be employed for the catalytic pyrolysis of pine needles together with aiding the cost-competitiveness, environmental sustainability, and renewability of the process.

The adsorption of Pb2+ and Ni2+ ions utilizing modified chitosan beads: A response surface methodology and neural network modelling study

This work investigates the application of artificial neural networks (ANN) and response surface methodology (RSM) in developing a technique for the removal of Pb2+ and Ni2+ ions from wastewater using chitosan derivative. Briefly, chitosan beads were formulated from their powdered form and thereafter grafted with aniline to provide more binding sites. The chitosan beads (CS) and grafted chitosan beads (MCS) were analyzed using infrared spectroscopy (FTIR) and a scanning electron microscope (SEM). However, during the adsorption studies, variables such as pH, adsorbent dose, contact duration, temperature, and concentration were considered as the input layer feed data, while two neurons were used as output layers, which correspond to the adsorption of Pb2+ and Ni2+ ions. The RSM and ANN models were measured using statistical metrics like average relative errors (ARE), coefficient of determination (R2), Marquart's percentage standard deviation (MPSD), mean squared error (MSE), Pearson's Chi-square (χ2), root means square errors (RMSE), and the sum of squares of errors (SSE). The ideal trained neural network depicts the training, validation, and testing phases, with R2 values of 1.0, 0.968, and 0.961, respectively. The findings, however, showed that the ANN technique is superior to the RSM-CCD model approach. the RSM-CCD model optimization results for the process variables were achieved at pH 5, a starting concentration of 100 mg/L, an adsorbent mass of 6.0 g, a reaction time of 55 min, and a temperature °f 40 °C and the greatest removal percentages for Pb2+ and Ni2+ ions were 98.14 % and 98.12 %, respectively. These findings suggest that ANN can be utilized in forecasting the removal of adsorbates from wastewater.

Heat transfer analysis for magnetohydrodynamic peristalsis of Reiner–Philippoff fluid: Application of an artificial neural network

Present communication explores a novel application of the computational intelligence technique, namely, the Levenberg–Marquardt scheme under a Backpropagated Neural Network (LM-BNN) to solve the mathematical model for the magnetohydrodynamic peristaltic transport of Reiner–Philippoff (R–Ph) pseudoplastic fluid considering the influences of Ohmic heating, mixed convection, and viscous dissipation through a symmetric channel. The R–Ph fluid model is used in this investigation to elucidate the non-Newtonian behavior of the fluid under consideration. The Reiner–Philippoff fluid model delineates the intricate relationship between stress and deformation rate within the fluid. There are a few studies available on the peristaltic transport of the Reiner–Philippoff fluid that do not incorporate Joule heating, mixed convection, and magnetic field effects. Therefore, a novel mathematical model is developed to employ an artificial neural network technique with a different approach that has not been examined before. The governing equations of the problem are simplified using long wavelength and low Reynolds number approximations, and the resulting system is numerically solved using the BVP4c scheme in MATLAB based on the shooting algorithm. Furthermore, a dataset is constructed through the BVP4c technique for the proposed LM-BNN, considering eight scenarios of peristaltic motion of the Reiner–Philippoff fluid model by varying the Bingham number, the Brinkman number, the Grashof number, the R–Ph fluid parameter, and the Hartmann number. The numerical dataset is divided into 15% for testing, 15% for training, and 70% for validation, which are utilized in LM-BNN to analyze the numerical solutions and Levenberg–Marquardt neural networks (LM-NNs) predicted results. The consistency and effectiveness of LM-BNN are validated through regression analysis, stresses at the wall, error histogram, correlation index, heat transfer, and mean squared error based fitness curves, which vary from 10−3→10−11. Variations in several flow parameters affecting temperature and velocity profiles are explained physically through graphs. Additionally, an analysis of heat transfer and stresses at the wall, including absolute errors, is provided through tables. The outcomes reveal that the improving Grashof number and the Hartmann number tend to increase the temperature profile. Tabular results indicate that rates of heat transfer improve when assigning higher values to the Hartmann number, the Brinkman number, and the Grashof number, whereas stresses at the wall decrease for the Reiner–Philippoff fluid parameter and the Bingham number. The error analysis of numerical simulations is a valuable step in determining whether the data obtained are reliable and accurate. In terms of absolute error, the disagreement between numerical solutions and those predicted by LM-NNs is approximately 10−5→10−11. It is clear from this error analysis that LM-NNs predicted results are consistent and reliable.

Flood Prediction System Using IOT &amp; Artificial Neural Network

Floods pose significant challenges as one of nature's most devastating disasters, making the development of accurate forecast model’s complex. This issue has led to severe consequences such as crop loss, population displacement, damage to infrastructure, and disruption of essential services. Advanced research on flood prediction models has played a crucial role in providing policy recommendations, mitigating risks, reducing human casualties, and minimizing property damage caused by floods. In this context, we propose an Internet of Things (IoT)-based flood prediction and forecasting model that prioritizes energy efficiency. Given the limited battery and memory capacity of IoT sensor nodes, we employ an energy-saving strategy within the fog layer, leveraging data diversity to minimize energy consumption. Additionally, cloud technology offers an effective storage solution. To accurately calibrate flood phases, we investigate climatic factors such as humidity, temperature, rainfall, as well as water body parameters including water flow and elevation. Neural networks are commonly used in constructing forecast systems, as they can replicate the complex calculations involved in flood physical processes, resulting in improved performance and cost-effectiveness. In our approach, the Artificial Neural Network (ANN) technique is employed for flood forecasting, and the effectiveness of different algorithms, such as Logistic Regression and Decision Tree, is assessed by comparing them to ANN. Accuracy values are computed using a classification report assessment, and graph parameters are carefully evaluated. Ultimately, our proposed system utilizes the ANN technique to train a predictive model by examining the dataset. This model generates real-time flood risk forecasts through a user-friendly graphical interface.

Assessment of Climate Change Impact on Reservoir Inflow

Abstract: Evaluating the effects of climate change is crucial in regions grappling with water scarcity. The Ujjani dam, a significant structure in Maharashtra, India, erected on the Bhima river in 1980, serves as a vital water source for the agricultural lands downstream in Solapur and Pune districts. Assessing climate change's impact involves analysing data from General Circulation Models (GCMs), which project climate parameters under various emission scenarios but often at a broader scale. Since hydrological models necessitate finer-scale climate data, a downscaling technique is employed to derive localized variables from GCM outputs. This study employs Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) techniques for downscaling. By utilizing projected temperature and rainfall data, three distinct models are developed to predict reservoir inflow: multiple linear regression, artificial neural network, and wavelet neural network. The findings indicate significant alterations in rainfall distribution patterns, with a decline during the monsoon season and an increase post-monsoon