Hybrid Artificial Intelligence Model Research Articles

Stacking Ensemble Artificial Intelligence Model for Heart Disease Diagnosis

Personalized treatment plans, predictive analytics, and artificial intelligence (AI)-driven diagnostics are becoming more and more popular as a way to improve decision-making, expedite operations, and improve patient care. But there are still a number of substantial barriers to overcome, which includes but not limited to issues with user adoption, trust, prejudice, and fairness brought on by resistance from healthcare providers and a lack of confidence in the system's recommendations. To overcome these challenges and realize the full potential of AI-driven solutions, the system's accuracy and safety through meticulous testing and validation of AI algorithms becomes indispensable. This research provides a hybrid AI model that blends three base models with a Meta model in order to diagnose heart disease effectively. The essence is to revalidate the existing AI diagnostic models for cardiac diseases diagnostics and to tackle the concerns impeding the full utilization of the available AI diagnostic system. The study makes use of each model's advantages by merging these various and complimentary algorithms into a stacking ensemble model to create a diagnostic system that is more potent. Using publicly available heart disease data, the model performs remarkably well; it achieves 89% accuracy, 85% recall (sensitivity), 92% specificity, and 89% precision. This hybrid model's performance and proven efficacy are expected to boost trust in the system's recommendations and encourage broader implementation in clinical practice.

Modeling flow resistance and geometry of dunes bed form in alluvial channels using hybrid RANN–AHA and GEP models

Dunes formation in sandy rivers significantly impacts flow resistance, subsequently affecting water levels, flow velocity, river navigation, and hydraulic structures performance. Accurate prediction of flow resistance and dune geometry (length and height) is essential for environmental engineering and river management. The current paper introduces two models to evaluate the flow resistance and geometry of dunes formed in sand-bed channels. The first model, RANN–AHA is a hybrid artificial intelligence model using the recurrent artificial neural network (RANN) linked with the artificial hummingbird optimization algorithm (AHA) to optimize the biases and weights of the neural network model. The second model uses gene expression programming (GEP) as a nonlinear approach based on a genetic algorithm (GA) and genetic programming (GP) to explicitly determine dune characteristics. For both models, the input parameters include flow and sediment characteristics, while Manning's roughness coefficient (nM), and relative dune height, h/H or h/L, were used as output parameters where h is the dune height, H is the flow depth above the dune crest, and L is the dune length. Five different published flume data sets were compiled for the analysis. Sensitivity analysis was done using different combinations of input parameters. It was found that the combination of hydraulic radius divided by median diameter (RH/d50), Reynolds number (Re), Particle densimetric Froude number (F∗), and grain Froude number (FG) yielded the best prediction accuracy for estimating Manning nM and relative height, h/H or h/L, with a root mean square error (RMSE) = 0.00027, 0.0504, and 0.0078 and a correlation coefficient (R) = 0.9989, 0.942, and 0.9272, respectively. Model verification proved that the RANN–AHA model outperformed the GEP model and most of the previous studies available in the literature when predicting the roughness coefficient and dune geometry in sand bed channels.

Multimodal breast cancer hybrid explainable computer-aided diagnosis using medical mammograms and ultrasound Images

Breast cancer is a prevalent global disease where early detection is crucial for effective treatment and reducing mortality rates. To address this challenge, a novel Computer-Aided Diagnosis (CAD) framework leveraging Artificial Intelligence (AI) techniques has been developed. This framework integrates capabilities for the simultaneous detection and classification of breast lesions. The AI-based CAD framework is meticulously structured into two pipelines (Stage 1 and Stage 2). The first pipeline (Stage 1) focuses on detectable cases where lesions are identified during the detection task. The second pipeline (Stage 2) is dedicated to cases where lesions are not initially detected. Various experimental scenarios, including binary (benign vs. malignant) and multi-class classifications based on BI-RADS scores, were conducted for training and evaluation. Additionally, a verification and validation (V&V) scenario was implemented to assess the reliability of the framework using unseen multimodal datasets for both binary and multi-class tasks. For the detection tasks, the recent AI detectors like YOLO (You Only Look Once) variants were fine-tuned and optimized to localize breast lesions. For classification tasks, hybrid AI models incorporating ensemble convolutional neural networks (CNNs) and the attention mechanism of Vision Transformers were proposed to enhance prediction performance. The proposed AI-based CAD framework was trained and evaluated using various multimodal ultrasound datasets (BUSI and US2) and mammogram datasets (MIAS, INbreast, real private mammograms, KAU-BCMD, and CBIS-DDSM), either individually or in merged forms. Visual t-SNE techniques were applied to visually harmonize data distributions across ultrasound and mammogram datasets for effective various datasets merging. To generate visually explainable heatmaps in both pipelines (stages 1 and 2), Grad-CAM was utilized. These heatmaps assisted in finalizing detected boxes, especially in stage 2 when the AI detector failed to automatically detect breast lesions. The highest evaluation metrics achieved for merged dataset (BUSI, INbreast, and MIAS) were 97.73% accuracy and 97.27% mAP50 in the first pipeline. In the second pipeline, the proposed CAD achieved 91.66% accuracy with 95.65% mAP50 on MIAS and 95.65% accuracy with 96.10% mAP50 on the merged dataset (INbreast and MIAS). Meanwhile, exceptional performance was demonstrated using BI-RADS scores, achieving 87.29% accuracy, 91.68% AUC, 86.72% mAP50, and 64.75% mAP50-95 on a combined dataset of INbreast and CBIS-DDSM. These results underscore the practical significance of the proposed CAD framework in automatically annotating suspected lesions for radiologists.

Artificial Intelligence in Early Detection of Cervical Intraepithelial Neoplasia

Artificial Intelligence (AI) is a quickly evolving field of technology used to develop intelligent machines capable of performing tasks such as problem solving, decision making , perception, language processing, and learning. This paper explores the application of AI in the field of gynecological oncology, specifically in the diagnosis of cervical cancer. The paper proposes a hybrid AI model that uses a Gaussian mixture model and a deep learning model to segment and classifies colposcope images. The model performed with satisfactory segmentation metrics of sensitivity, specificity, dice index, and Jaccard index of 0.976, 0.989, 0.954, and 0.856, respectively. This model aims to accurately classify cancer and non-cancer cases from a colposcope image. The results showed that this method could effectively segment the colposcopy images and extract the cervix region. This can be a valuable tool for automated cancer diagnosis and can help improve the diagnosis's accuracy.

A Review on the Current Trends in Crop Yield Forecasting Using Artificial Intelligence

In the face of escalating global food demands and the increasing unpredictability of climate conditions, the importance of precise crop yield forecasting has never been more critical. This paper provides a comprehensive review of the current trends in leveraging Artificial Intelligence (AI) to enhance crop yield predictions, which is pivotal for strategic agricultural planning and ensuring food security. Our review covers a range of AI methodologies, including machine learning, deep learning, and hybrid models, that have been employed to predict crop yields with increasing accuracy. Recent advancements have demonstrated that machine learning techniques, such as support vector machines and random forests, are effective in modeling complex agricultural data sets with a notable degree of precision. However, deep learning approaches, including convolutional and recurrent neural networks, have started to outperform traditional machine learning models, owing to their ability to process large-scale spatial-temporal data from remote sensing and IoT-based agricultural sensors. We also explore the emergence of hybrid AI models that combine the strengths of both machine learning and deep learning technologies, providing enhanced accuracy and robustness in yield prediction under varying climatic conditions. Additionally, this review discusses the integration of AI with geographic information systems (GIS) and remote sensing technologies, which has significantly improved the spatial resolution of yield predictions. We highlight several key challenges that remain, such as data scarcity, the need for model generalization, and the integration of socioeconomic factors into yield prediction models. In conclusion, AI presents transformative potential for crop yield forecasting. By harnessing cutting-edge AI technologies and addressing existing challenges, significant strides can be made towards more sustainable and efficient agricultural practices. This paper aims to inspire continued research and innovation in this critical field.

Enhancement of Power Quality through the Implementation of a Hybrid Artificial Intelligence Model within Solar-Wind Energy Systems

The generation of electricity is significantly assisted by hybrid solar-wind power systems, which also play a crucial role in the advancement of intelligent grids. Furthermore, the integration of wind and solar energy storage control systems, in conjunction with energy markets, has rendered the electricity grid more economically feasible. To meet the growing demand for electricity, hybrid renewable energy systems connected to microgrids consist of substantial identifying elements. The issue of harmonic distortion in microgrids arising from nonlinear loads is a fundamental area of research. Understanding the impact of microgrids on power quality is also of great importance. This study focuses on enhancing power quality in solar-wind hybrid systems by incorporating emerging Artificial Intelligence (AI) methodologies. The proposed approach comprises two main components: (i) detection of distortions caused by voltage fluctuations and (ii) improvement of power quality through an AI-based control system. Initially, power distortions are identified and eliminated using the Enhanced Kalman Filter (EKF) algorithm. A Hybrid Artificial Neural Network with Fuzzy Intelligence (HANFI) model is then developed based on this power data. This model integrates two prominent neural network architectures with fuzzy systems. Experimental validation of the system is conducted using MATLAB, which facilitates the simulation of hybrid energy systems.

New formulation for predicting total dissolved gas supersaturation in dam reservoir: application of hybrid artificial intelligence models based on multiple signal decomposition

Total dissolved gas (TDG) concentration plays an important role in the control of the aquatic life. Elevated TDG can cause gas-bubble trauma in fish (GBT). Therefore, controlling TDG fluctuation has become of great importance for different disciplines of surface water environmental engineering.. Nowadays, direct estimation of TDG is expensive and time-consuming. Hence, this work proposes a new modelling framework for predicting TDG based on the integration of machine learning (ML) models and multiresolution signal decomposition. The proposed ML models were trained and validated using hourly data obtained from four stations at the United States Geological Survey. The dataset are composed from: (i) water temperature (Tw), (ii) barometric pressure (BP), and (iii) discharge (Q), which were used as the input variables for TDG prediction. The modelling strategy is conducted based on two different steps. First, six singles ML model namely: (i) multilayer perceptron neural network, (ii) Gaussian process regression, (iii) random forest regression, (iv) random vector functional link, (v) adaptive boosting, and (vi) Bootstrap aggregating (Bagging), were developed for predicting TDG using Tw, BP, and Q, and their performances were compared. Second, a new framework was introduced based on the combination of empirical mode decomposition (EMD), the variational mode decomposition (VMD), and the empirical wavelet transform (EWT) preprocessing signal decomposition algorithms with ML models for building new hybrid ML models. Hence, the Tw, BP, and Q signals were decomposed to extract the intrinsic mode functions (IMFs) by using the EMD and VMD methods and the multiresolution analysis (MRA) components by using the EWT method. Then after, the IMFs and MRA components were selected and regraded as new input variables for the ML models and used as an integral part thereof. The single and hybrid prediction models were compared using several statistical metrics namely, root mean square error, mean absolute error, coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). The single and hybrid models were trained several times with high number of repetitions, depending on the kind of modeling process. The obtained results using single models gave good agreement between the predicted TDG and the situ measured dataset. Overall, the Bagging model performed better than the other five models with R2 and NSE values of 0.906 and 0.902, respectively. However, the extracted IMFs and MRA components using the EMD, VMD and the EWT have contributed to an improvement of the hybrid models’ performances, for which the R2 and NSE were significantly increased reaching the values of 0.996 and 0.995. Experimental results showed the superiority of hybrid models and more importantly the importance of signal decomposition in improving the predictive accuracy of TDG.Graphical abstract

Hybrid artificial intelligence models based on adaptive neuro fuzzy inference system and metaheuristic optimization algorithms for prediction of daily rainfall

In this study, our primary objective is the accurate prediction of daily rainfall through the application of various hybrid Artificial Intelligence (AI) methods. These methods are grounded in the Adaptive Neuro Fuzzy Inference System (ANFIS) and employ metaheuristic optimization algorithms, specifically the Artificial Bee Colony (ABC), Genetic Algorithm (GA), and Simulated Annealing (SA). The meteorological data utilized for modeling rainfall prediction is sourced from Hoa Binh province in Vietnam. To enhance the datasets, we employed the Savitzky-Golay filtering as a preprocessing noise reduction technique. The performance of the models was assessed using well-established statistical error criteria, including the Correlation Coefficient (R), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other contingency scores. Our findings indicate that the ANFIS-ABC hybrid model outperforms other models, such as ANFIS-SA and ANFIS-GA, in predicting daily rainfall, achieving an R value of 0.82 with raw data and 0.9 with preprocessed data. Notably, the results underscore the positive impact of employing noise reduction through data preprocessing, enhancing the predictive quality of the hybrid models. This study holds significance in the realm of water resource and land management, offering valuable insights for the accurate prediction of daily rainfall.

Hybridized artificial intelligence models with nature-inspired algorithms for river flow modeling: A comprehensive review, assessment, and possible future research directions

River flow (Qflow) is a hydrological process that considerably impacts the management and sustainability of water resources. The literature has shown great potential for nature-inspired optimized algorithms (NIOAs), like hybrid artificial intelligence (HAI) models, for Qflow modeling. Qflow forecasting needs to be accurate, robust, reliable, and capable of resolving complex non-linear problems to support the decision authority in local and national governments and NGOs. This extensive survey provides a literature review of 100-plus high-impact factor journal articles on developing NIOAs models during 2000–2022. This encompasses a comprehensive review of the established research in different climatic zones, NIOA types, artificial intelligence (AI) models, the input parameters used for model development, Qflow on different time scales, and model evaluation using a wide range of performance metrics. The review also assessed and evaluated several components of relevant literature, along with detailing the existing research gaps. Moreover, the global research gap with future direction is discussed based on current research limitations and possibilities. The data availability evaluation and futuristic suggestions are drafted logically. The review revealed the superiority of the NIOAs among all applied algorithms in the literature. Further, the review concludes that there is a need to improve technical aspects of Qflow forecasting and bridge the gap between scientific research, hydrometeorological model development, and real-world flood and drought management using probabilistic nature inspired (NI) forecasts, especially through effective communication.

Adaptive tourism forecasting using hybrid artificial intelligence model: a case study of Xi’an international tourist arrivals

Accurate forecasting of tourist demand is important to both business practitioners and government policymakers. In the past decade of rapid development of deep learning, many artificial intelligence methods or deep learning models have been built to improve prediction accuracy. But data-driven end-to-end deep network models usually require large data sets to support. For tourism forecasting, the sample is insufficient and many models are difficult to apply. In this article, we propose a novel hybrid model GM-LSTM, which combines the advantages of gray models and neural networks to achieve self-adaptive prediction with small samples. Specifically, the overall trend of tourism demand is captured by a first-order gray model and the non-linear residual fluctuation is characterized using a long short-term memory (LSTM) network with a rolling mechanism. The model is validated through a case study of up to 38 years of data on annual international tourist arrivals in Xi’an, China. The proposed GM-LSTM model achieved a predicted MAPE value of 11.88%, outperforming other time series models. The results indicate that our proposed hybrid model is accurate and efficient.

Advancements in AI-Enhanced Just-In-Time Inventory: Elevating Demand Forecasting Accuracy

The landscape of global supply chains is undergoing a transformation characterized by increasing complexity and the need for agile response to demand fluctuations. At the forefront of addressing these challenges is the strategic alignment of inventory levels with volatile demand, a task that has become more sophisticated within the Just-In-Time (JIT) inventory management paradigm. This paper explores the integration of Artificial Intelligence (AI) into JIT systems, with a focus on enhancing the accuracy of demand forecasting—a critical component for inventory optimization. We present a groundbreaking hybrid AI model that combines the forward-thinking capabilities of neural networks with the reliability of classical statistical forecasting methods. This innovative approach seeks to elevate forecasting reliability and reduce errors that lead to either inventory shortfalls or surpluses. Through a series of case studies spanning various industries, the versatility and effectiveness of the hybrid model are demonstrated, highlighting improvements in forecasting accuracy and the resulting operational benefits.

Enhancing daily rainfall prediction in urban areas: a comparative study of hybrid artificial intelligence models with optimization algorithms

Forecasting precipitation is a crucial input to hydrological models and hydrological event management. Accurate forecasts minimize the impact of extreme events on communities and infrastructure by providing timely and reliable information. In this study, six artificial intelligent hybrid models are developed to predict daily rainfall in urban areas by combining the firefly optimization algorithm (FA), invasive weed optimization algorithm (IWO), genetic particle swarm optimization algorithm (GAPSO), neural network (ANN), group method of data handling (GMDH), and wavelet transformation. Optimization algorithms increase forecasting accuracy by controlling all stages. A variety of criteria are used for validating the models, including correlation coefficient (R), root-mean-square error (RMSE), mean absolute error (MAE), critical success index (CSI), probability of detection (POD), and false alarm ratio (FAR). The proposed models are also evaluated in an urban area in Ahvaz, Iran. The GAPSO-Wavelet-ANN model is superior to other models for predicting daily rainfall, with an RMSE of 1.42 mm and an R of 0.9715.

Study on prediction of ocean effective wave height based on hybrid artificial intelligence model

Accurate and effective wave height prediction plays a crucial role in harnessing marine energy, ensuring navigation safety, mitigating and preventing disasters, advancing scientific research, and so on. A hybrid Artificial Intelligence (AI) model Prophet_LSTM was proposed for effective wave height prediction in this study. First, the Prophet model is used to smooth the outliers in the original time series samples, and a large number of potential features were deeply mined. Then, the extracted information was used as a valuable source of augmented data, enhancing the training quality of the LSTM to improve its overall performance. Next, a sequence of procedures, encompassing normalization, grid search, and random search, was employed to identify the optimal parameters for the hybrid model in the wave height prediction. Finally, experiments were carried out based on seven years of data from station 44,025, 44,013, and 51,101 of the National Data Buoy Center (NDBC). The results show that the evaluation metrics of the Prophet_LSTM hybrid model are significantly improved compared with the traditional 1-h predictions technique and model.

Applicability of denoising-based artificial intelligence to forecast the environmental externalities

The current study attempts to compare the hybrid artificial intelligence models to forecast the environmental externalities in Saudi Arabia. We have used the denoising based artificial intelligence models to construct hybrid models. While comparing the denoising techniques, the CSD-based denoising has outperformed. However, we have used the CSD-based hybrid models. CSD-ANN and CSD-RNN are used for denoising-based artificial intelligence models, whereas CSD-ARIMA is used for denoising-based traditional models. All these models are used to check and compare their performance in terms of level and direction of prediction for PM10. The results show that the CSD-based ANN model has a higher predictability for PM10 levels in Saudi Arabia due to low error values and higher Dstat values. In comparing original and forecasted data, the superiority of CSD-ANN is evident in predicting the PM10 in Saudi Arabia. Hence, this hybrid model can predict the environmental externalities for non-linear and highly noised data. Moreover, the findings can be useful in achieving the sustainable development goal.

Optimal hybrid artificial intelligence models for predicting the adsorptive removal of dyes and phenols from aqueous solutions using an amine-functionalized graphene oxide/layered triple hydroxide nanocomposite

Water pollution is a serious environmental problem with a significant negative impact on human health and the ecosystem. Adsorption is an attractive process for water decontamination. Developing artificial intelligence models capable of predicting the adsorption performance of newly developed materials could save huge amounts of resources and efforts. In the present study, a novel polyethyleneimine/graphene oxide/layered triple hydroxide (PEI/GO/LTH) nanocomposite was synthesized, characterized, and applied to adoptively remove harmful phenolic (bisphenol A) and azo dye (acid red 1) from wastewater samples. The results revealed that the PEI/GO/LTH nanocomposite is highly effective in removing these two pollutants. The adsorption isotherms and kinetics of these two pollutants are best fitted by the Langmuir isotherm and pseudo-second-order models, respectively. Additionally, the synthesized nanocomposite is easily and highly regenerable with an insignificant loss in performance when repeatedly used. Besides the above investigations, the present study also employs support vector machines (SVM) and Bayesian optimization as tools for predicting the adsorptive removal of acid red 1 (AR1) dye and bisphenol A (BPA) from contaminated water samples by the synthesized PEI/GO/LTH nanocomposite. The models achieved promising results as the correlation coefficients, during the testing phase, reached 97.3 and 96.6 % for the AR1 and BPA data using BO-SVM models, respectively.

Investigating Landfill Leachate and Groundwater Quality Prediction Using a Robust Integrated Artificial Intelligence Model: Grey Wolf Metaheuristic Optimization Algorithm and Extreme Learning Machine

The likelihood of surface water and groundwater contamination is higher in regions close to landfills due to the possibility of leachate percolation, which is a potential source of pollution. Therefore, proposing a reliable framework for monitoring leachate and groundwater parameters is an essential task for the managers and authorities of water quality control. For this purpose, an efficient hybrid artificial intelligence model based on grey wolf metaheuristic optimization algorithm and extreme learning machine (ELM-GWO) is used for predicting landfill leachate quality (COD and BOD5) and groundwater quality (turbidity and EC) at the Saravan landfill, Rasht, Iran. In this study, leachate and groundwater samples were collected from the Saravan landfill and monitoring wells. Moreover, the concentration of different physico-chemical parameters and heavy metal concentration in leachate (Cd, Cr, Cu, Fe, Ni, Pb, Mn, Zn, turbidity, Ca, Na, NO3, Cl, K, COD, and BOD5) and in groundwater (Cd, Cr, Cu, Fe, Ni, Pb, Mn, Zn, turbidity, EC, TDS, pH, Cl, Na, NO3, and K). The results obtained from ELM-GWO were compared with four different artificial intelligence models: multivariate adaptive regression splines (MARS), extreme learning machine (ELM), multilayer perceptron artificial neural network (MLPANN), and multilayer perceptron artificial neural network integrated with grey wolf metaheuristic optimization algorithm (MLPANN-GWO). The results of this study confirm that ELM-GWO considerably enhanced the predictive performance of the MLPANN-GWO, ELM, MLPANN, and MARS models in terms of the root-mean-square error, respectively, by 43.07%, 73.88%, 74.5%, and 88.55% for COD; 23.91%, 59.31%, 62.85%, and 77.71% for BOD5; 14.08%, 47.86%, 53.43%, and 57.04% for turbidity; and 38.57%, 59.64%, 67.94%, and 74.76% for EC. Therefore, ELM-GWO can be applied as a robust approach for investigating leachate and groundwater quality parameters in different landfill sites.

AI-enabled case detection model for infectious disease outbreaks in resource-limited settings

IntroductionThe utility of non-contact technologies for screening infectious diseases such as COVID-19 can be enhanced by improving the underlying Artificial Intelligence (AI) models and integrating them into data visualization frameworks. AI models that are a fusion of different Machine Learning (ML) models where one has leveraged the different positive attributes of these models have the potential to perform better in detecting infectious diseases such as COVID-19. Furthermore, integrating other patient data such as clinical, socio-demographic, economic and environmental variables with the image data (e.g., chest X-rays) can enhance the detection capacity of these models.MethodsIn this study, we explore the use of chest X-ray data in training an optimized hybrid AI model based on a real-world dataset with limited sample size to screen patients with COVID-19. We develop a hybrid Convolutional Neural Network (CNN) and Random Forest (RF) model based on image features extracted through a CNN and EfficientNet B0 Transfer Learning Model and applied to an RF classifier. Our approach includes an intermediate step of using the RF's wrapper function, the Boruta Algorithm, to select important variable features and further reduce the number of features prior to using the RF model.Results and discussionThe new model obtained an accuracy and recall of 96% for both and outperformed the base CNN model and four other experimental models that combined transfer learning and alternative options for dimensionality reduction. The performance of the model fares closely to relatively similar models previously developed, which were trained on large datasets drawn from different country contexts. The performance of the model is very close to that of the “gold standard” PCR tests, which demonstrates the potential for use of this approach to efficiently scale-up surveillance and screening capacities in resource limited settings.

Performance prediction of aluminum and polycarbonate solar stills with air cavity using an optimized neural network model by golden jackal optimizer

Solar stills (SS) are simple eco-friendly desalination devices that exploit solar energy to obtain freshwater from seawater. In this study, a hybrid artificial intelligence model is proposed to predict the thermal behavior of two designs of SSs. Two SSs with a basin and absorber plate made of aluminum for the first SS (ALSS)and polycarbonate for the second SS (PCSS) were established and tested. Both SSs have a modified absorber plate with an air cavity. The hybrid model was composed of an optimized Artificial Neural Network (ANN) model by Golden Jackal Optimizer (GJO). To prove the capability of the proposed model to predict the SSs performance, it was compared with the conventional ANN model as well as two other optimized models with Genetic Algorithm (GA) or Particle Swarm Optimizer (PSO). The results showed that ANN-GJO had better accuracy than ANN, ANN-GA, and ANN-PSO to predict overall heat transfer coefficient, energy efficiency, exergy efficiency, and distillate output. Moreover, ALSS showed better thermal performance compared with PCSS regarding water productivity, exergy efficiency, and energy efficiency. The average exergy efficiency and energy efficiency of PCSS and ALSS were 2.30%, 42.40%, and 3.44%, 48.80%, respectively. The maximum distillate output for PCSS and ALSS were 3.40 l/m2/day and 3.80 l/m2/day, respectively.

Revolutionizing Groundwater Management with Hybrid AI Models: A Practical Review

Developing precise soft computing methods for groundwater management, which includes quality and quantity, is crucial for improving water resources planning and management. In the past 20 years, significant progress has been made in groundwater management using hybrid machine learning (ML) models as artificial intelligence (AI). Although various review articles have reported advances in this field, existing literature must cover groundwater management using hybrid ML. This review article aims to understand the current state-of-the-art hybrid ML models used for groundwater management and the achievements made in this domain. It includes the most cited hybrid ML models employed for groundwater management from 2009 to 2022. It summarises the reviewed papers, highlighting their strengths and weaknesses, the performance criteria employed, and the most highly cited models identified. It is worth noting that the accuracy was significantly enhanced, resulting in a substantial improvement and demonstrating a robust outcome. Additionally, this article outlines recommendations for future research directions to enhance the accuracy of groundwater management, including prediction models and enhance related knowledge.

A hybrid artificial intelligence model leverages multi-centric clinical data to improve fetal heart rate pregnancy prediction across time-lapse systems.

Can artificial intelligence (AI) algorithms developed to assist embryologists in evaluating embryo morphokinetics be enriched with multi-centric clinical data to better predict clinical pregnancy outcome? Training algorithms on multi-centric clinical data significantly increased AUC compared to algorithms that only analyzed the time-lapse system (TLS) videos. Several AI-based algorithms have been developed to predict pregnancy, most of them based only on analysis of the time-lapse recording of embryo development. It remains unclear, however, whether considering numerous clinical features can improve the predictive performances of time-lapse based embryo evaluation. A dataset of 9986 embryos (95.60% known clinical pregnancy outcome, 32.47% frozen transfers) from 5226 patients from 14 European fertility centers (in two countries) recorded with three different TLS was used to train and validate the algorithms. A total of 31 clinical factors were collected. A separate test set (447 videos) was used to compare performances between embryologists and the algorithm. Clinical pregnancy (defined as a pregnancy leading to a fetal heartbeat) outcome was first predicted using a 3D convolutional neural network that analyzed videos of the embryonic development up to 2 or 3 days of development (33% of the database) or up to 5 or 6 days of development (67% of the database). The output video score was then fed as input alongside clinical features to a gradient boosting algorithm that generated a second score corresponding to the hybrid model. AUC was computed across 7-fold of the validation dataset for both models. These predictions were compared to those of 13 senior embryologists made on the test dataset. The average AUC of the hybrid model across all 7-fold was significantly higher than that of the video model (0.727 versus 0.684, respectively, P = 0.015; Wilcoxon test). A SHapley Additive exPlanations (SHAP) analysis of the hybrid model showed that the six first most important features to predict pregnancy were morphokinetics of the embryo (video score), oocyte age, total gonadotrophin dose intake, number of embryos generated, number of oocytes retrieved, and endometrium thickness. The hybrid model was shown to be superior to embryologists with respect to different metrics, including the balanced accuracy (P ≤ 0.003; Wilcoxon test). The likelihood of pregnancy was linearly linked to the hybrid score, with increasing odds ratio (maximum P-value = 0.001), demonstrating the ranking capacity of the model. Training individual hybrid models did not improve predictive performance. A clinic hold-out experiment was conducted and resulted in AUCs ranging between 0.63 and 0.73. Performance of the hybrid model did not vary between TLS or between subgroups of embryos transferred at different days of embryonic development. The hybrid model did fare better for patients older than 35 years (P < 0.001; Mann-Whitney test), and for fresh transfers (P < 0.001; Mann-Whitney test). Participant centers were located in two countries, thus limiting the generalization of our conclusion to wider subpopulations of patients. Not all clinical features were available for all embryos, thus limiting the performances of the hybrid model in some instances. Our study suggests that considering clinical data improves pregnancy predictive performances and that there is no need to retrain algorithms at the clinic level unless they follow strikingly different practices. This study characterizes a versatile AI algorithm with similar performance on different time-lapse microscopes and on embryos transferred at different development stages. It can also help with patients of different ages and protocols used but with varying performances, presumably because the task of predicting fetal heartbeat becomes more or less hard depending on the clinical context. This AI model can be made widely available and can help embryologists in a wide range of clinical scenarios to standardize their practices. Funding for the study was provided by ImVitro with grant funding received in part from BPIFrance (Bourse French Tech Emergence (DOS0106572/00), Paris Innovation Amorçage (DOS0132841/00), and Aide au Développement DeepTech (DOS0152872/00)). A.B.-C. is a co-owner of, and holds stocks in, ImVitro SAS. A.B.-C. and F.D.M. hold a patent for 'Devices and processes for machine learning prediction of in vitro fertilization' (EP20305914.2). A.D., N.D., M.M.F., and F.D.M. are or have been employees of ImVitro and have been granted stock options. X.P.-V. has been paid as a consultant to ImVitro and has been granted stocks options of ImVitro. L.C.-D. and C.G.-S. have undertaken paid consultancy for ImVitro SAS. The remaining authors have no conflicts to declare. N/A.