Hybrid Optimization Model Research Articles

A Novel Approach for Air Quality Index Prognostication using Hybrid Optimization Techniques

This research presents an innovative deep learning approach for forecasting the Air Quality Index (AQI), a crucial public health concern in both developed and developing countries. The proposed methodology encompasses four stages: (a) Pre-processing, involving data cleaning and transformation; (b) Feature Extraction, capturing central tendency, dispersion, higher order statistics, and Spearman's rank correlation; (c) Feature Selection, using a novel hybrid optimization model, Particle Updated Grey Wolf Optimizer (PUGWO); and (d) an ensembled deep learning model for AQI prediction, integrating a Convolutional Neural Network (CNN), an optimized Bi-directional Long Short-Term Memory (Bi-LSTM), and an Auto-encoder. The CNN and Auto-encoder are trained on the extracted features, and their outputs are fed into the optimized Bi-LSTM for final AQI prediction. Implemented on the PYTHON platform, this model is evaluated through R^2, MAE, and RMSE error metrics. The proposed HRFKNN model demonstrates superior performance with an R-Square of 0.961, RMSE of 11.92, and MAE of 10.29, outperforming traditional models like Logistic Regression, HRFLM, and HRFDT. This underscores its effectiveness in delivering precise and reliable AQI predictions.

Development of Hybrid Optimization Model Using Grey-ANFIS-Jaya Algorithm for CNC Drilling of Aluminium Alloy

Aluminium alloys are gaining popularity in a diversity of engineering applications because of their extraordinary features such as strength, resistance to oxidation, and so on. AA5052 (Al-Mg series) is generally used in antirust uses, particularly in desalination related activities, due to its better resistance to corrosion in marine applications at temperature ranges up to 125°C, lower cost, better heat-carrying capacity, and nontoxicity of its corrosion components. Drilling is one of the most commonly adopted material removal processes that is adopted in numerous engineering uses. Taguchi’s technique is engaged to arrange and examine the tests, by treating the drilling diameter and speed and as independent process factors. The studies were carried out using an L27 orthogonal array. Material removal rate (MRR), surface roughness (SR), and form/orientation error are deemed as output characteristics. Taguchi’s analysis was engaged to discover the best process factors. ANOVA is used to examine the influence of process variables. Suitable application of artificial intelligence tools for making effective decision assists the manufacturer in accomplishing the benefits in numerous engineering domains. To obtain the maximum material removal and minimum roughness, circularity (circ), and perpendicularity errors (perp), the process variables have been optimized with the help of grey-ANFIS-amalgamated with Jaya algorithm. The multiperformance index was developed using grey theory. Statistical error analysis is used to estimate the performance of the established optimization model. Based on the investigative outcomes, the best-suited process variable combinations will be used to provide improved and enhanced multiperformance characteristics.

Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization

This article presents a new type of hybrid model for Bayesian optimization (BO) adept at managing mixed variables, encompassing both quantitative (continuous and integer) and qualitative (categorical) types. Our proposed new hybrid models (named hybridM) merge the Monte Carlo Tree Search structure (MCTS) for categorical variables with Gaussian Processes (GP) for continuous ones. hybridM leverages the upper confidence bound tree search (UCTS) for MCTS strategy, showcasing the tree architecture’s integration into Bayesian optimization. Our innovations, including dynamic online kernel selection in the surrogate modeling phase and a unique UCTS search strategy, position our hybrid models as an advancement in mixed-variable surrogate models. Numerical experiments underscore the superiority of hybrid models, highlighting their potential in Bayesian optimization. Supplementary materials for this article are available online.

Heat pipes and nanofluids utilization for cooling photovoltaic panels: an application of hybrid machine learning and optimization models

Abstract This study explores the synergies between advanced cooling technologies and photovoltaic systems, seeking to improve their overall efficiency and contribute to the broader goal of mitigating greenhouse gas emissions. To cool photovoltaic panels in more efficiently maner, understanding heat pipes, nanofluids, and panels interaction play key roles. For analysis and optimization, hybrid models of convolutional neural network (CNN) and firefly optimization algorithm are employed. The firefly optimization algorithm is used to optimize the thermosiphon heat pipe’s operational conditions, taking into account inputs such as the filling ratio, nanofluid concentration and panel angle. The study compared the predicted outcomes of a classic CNN model to laboratory experiments. While the CNN model was consistent with experimental findings, it struggled to predict high power values with precision. The proposed model improved high power value predictions by 4.05 W root mean square error (RMSE). The proposed model outperformed the classic CNN model for values greater than 50 W, with an RMSE of 3.95 W. The optimal values for the filling ratio, nanofluid concentration and panel angle were determined after optimization with the firefly algorithm. The research contributes to the advancement of renewable energy technologies and the optimization of photovoltaic panel cooling and energy production. Nanofluid with 1% mass concentration improves photovoltaic collector thermal efficiency due to its higher thermal conductivity coefficient. The photovoltaic collector’s electrical efficiency peaks in the morning, drops at noon due to temperature and radiation and recovers by morning. Electrical efficiency is best with nanofluid at 0.86%. Exergy efficiency closely matches electrical efficiency, with nanofluid at the optimal percentage achieving the highest efficiency and water cooling the lowest.

Feasibility of hydrogen hybrid energy systems for sustainable on- and off-grid integration: An Australian REZs case study

The escalating effects of climate change and the finite nature of fossil fuels underscore the imperative for transitioning to renewable energy. This study assesses the feasibility of hybrid energy systems that harness renewable sources, such as solar and wind power, alongside hydrogen technologies and solid-state lithium-ion batteries in diverse energy landscapes. Concentrating on five of Australia's renewable energy zones (REZs)—Broken Hill in New South Wales, Murray River in Victoria, Darling Downs in Queensland, Riverland in South Australia, and North East Tasmania—the research employs the Hybrid Optimization Model for Multiple Energy Resources (HOMER Pro) microgrid software. This software optimizes the sizing of system components to ascertain the most cost-effective configurations for each REZ, considering varied scenarios, including resource availability and demand patterns. The findings indicate that Broken Hill and Murray River exhibit the lowest levelized cost of energy (LCOE) for off-grid and on-grid configurations, respectively, at $0.32/kWh and $0.030/kWh. Conversely, North East Tasmania has the highest LCOE for both configurations, at $0.38/kWh and $0.034/kWh, respectively. Furthermore, the study suggests that beyond grid extension distances of 350–530 km, off-grid solutions may be more economically viable than grid extensions. Moreover, on-grid configurations demonstrate the lowest net present cost (NPC), benefiting from the option to sell surplus electricity back to the utility grid, thereby enhancing their economic advantage over off-grid options. The strategic implications of these results are significant for global energy planning, advocating for a portfolio approach that incorporates a mix of on-grid, off-grid, and extended-grid systems, crucial for sustainably meeting future energy demands. These insights have the potential to guide research, policy, and investment decisions, promoting the cost-efficient deployment of renewable hydrogen hybrid energy systems. The outcomes of this study reinforce that a sustainable energy economy is necessary and achievable through the informed and strategic deployment of technology tailored to geographical and economic specificities.

Performance Investigation of Wind/Photovoltaic/Fuel cell Hybrid Energy System for Stand-alone Power Supply

Large numbers of households in isolated areas in Nigeria were reported to have lacking access to national grid. Their basic electricity demand is served through fossil fuel generators which are costly and environmentally unfriendly. The fact that extension of national grid lines to those areas becomes difficult, renewable energy resources exploitation is the best alternatives. Wind and solar energy as clean abundantly available resources could be harnessed in a hybrids form with long-term storage devices for enhancing energy optimization and power stability. This paper investigated the performance of Wind-PV-Fuel cell Hybrid Energy Systems for stand-alone application. The performances of Wind-Battery-Fuel cell and PV-Battery-Fuel cell Hybrid Energy Systems were investigated by using Hybrid Optimization Models for Energy Renewable (HOMER), through cycle charging controls. The techno-economic Figure of merits for the optimal configurations from these systems was compared. The results revealed that Wind-Battery-Fuel cell Hybrid had been the best system for serving4.37kWh/day (1595kWh/yr) residential load demand. The system was reported with 321 kWh/yr excess electricity, 8.59 kWh/y unmet load and 10.5 kWh/yr capacity shortage. While, the Net Present Cost (NPC), Operation and Maintenance Cost (O&MC) and Cost of Energy (COE) were $25,951, $185 /yr and $1.229/kWh respectively. The result of sensitivity analysis, predicted the unmet load and capacity shortage to be declined by 0.0% each, with system autonomy of 7.9 days. Meanwhile, the NPC, O&MC and COE have decreased by 24.6 %, 8.1 % and 25.06 % respectively. This analysis confirmed that Wind-Battery-Fuel cell-Hybrid Energy System could be an economically viable and technically feasible for stand-alone power supply for isolated areas.

Estimating maize evapotranspiration based on hybrid back-propagation neural network models and meteorological, soil, and crop data.

Crop evapotranspiration is a key parameter influencing water-saving irrigation and water resources management of agriculture. However, current models for estimating maize evapotranspiration primarily rely on meteorological data and empirical coefficients, and the estimated evapotranspiration contains uncertainties. In this study, the evapotranspiration data of summer maize were collected from typical stations in Northern China (Yucheng Station), and a back-propagation neural network (BP) model for predicting maize evapotranspiration was constructed based on meteorological data, soil data, and crop data. To further improve its accuracy, the maize evapotranspiration model was optimized using three bionic optimization algorithms, namely the sand cat swarm optimization (SCSO) algorithms, hunter-prey optimizer (HPO) algorithm, and golden jackal optimization (GJO) algorithm. The results showed that the fusion of meteorological, soil moisture, and crop data can effectively improve the accuracy of the maize evapotranspiration model. The model showed higher accuracy with the hybrid optimization model SCSO-BP compared to the stand-alone BP neural network model, with improvements of 2.7-4.8%, 17.2-25.5%, 13.9-26.8%, and 3.3-5.6% in terms of R2, RMSE, MAE, and NSE, respectively. Comprehensively compared with existing maize evapotranspiration models, the SCSO-BP model presented the highest accuracy, with R2 = 0.842, RMSE = 0.433 mm/day, MAE = 0.316 mm/day, NSE = 0.840, and overall global evaluation index (GPI) ranking the first. The results have reference value for the calculation of daily evapotranspiration of maize in similar areas of northern China.

Hybrid optimization model with Neural Network approach for renewable energy prediction and scheduling in large scale systems

Climate change demands clean energy solutions, and renewable sources such as solar and wind are prime candidates. However, their variability poses challenges for their integration into large-scale power systems. This paper addresses this issue by proposing a novel hybrid mathematical model. The proposal integrates both fossil and renewable sources, considering real-world constraints such as system demand, reserves, and transmission dynamics. The model combines several approaches. By using a novel block composition technique, the computational complexity is reduced, making the model applicable to large-scale systems. A neural network is also developed to improve the forecasting of renewable energy production, which is crucial for managing its intermittency. The effectiveness of the proposed model is tested by considering the large Argentinean electricity system, demonstrating its practical applicability. The results show that acceptable forecasts can be obtained for the generation and transmission scheduling of the whole system.

Feasibility Study of Using Wave-PV-Wind Hybrid System for AL Hallaniyat Island

Al Hallaniyat Island is located in the southern part of Oman. The island has a low number of population and is currently fed by a number of diesel generators with a capacity of 1568 kW. Decreasing the emission of greenhouse gases is one of the main goals for the country’s vision of 2040 as well as Oman’s commitment to net-zero emissions by 2050, in line with the Paris Agreement of limiting global warming to 1.5°C. The purpose of this paper is to study the feasibility of replacing diesel generators with 100% renewable energy sources. The proposed energy source for the Island will be a hybrid system consisting of the wave energy converter, PV, wind and battery storage system. Real load data was used in the model with measured wind speed and solar radiation. The Hybrid Optimization Model for Electric Renewables software is used in this study. Several systems were proposed but the most economical one is PV-Wind-Wave-Battery system that resulted in levelized cost of energy of US$/kWh 0.1586 and Net Present Cost (NPC) of US$ 5,010,594. Having PV-Wave-Battery will result in levelized cost of energy of US$/kWh 0.174 whereas having Wind-Wave-Battery will increase the energy cost to US$/kWh 0.42.

Presenting an Optimized Hybrid Model for Stock Price Prediction

Presenting an Optimized Hybrid Model for Stock Price Prediction

Prediction of Financial Markets Utilizing an Innovatively Optimized Hybrid Model: A Case Study of the Hang Seng Index

Prediction of Financial Markets Utilizing an Innovatively Optimized Hybrid Model: A Case Study of the Hang Seng Index

Modeling strategies and influencing factors in retrieving canopy equivalent water thickness of mangrove forest with Sentinel-2 image

Canopy equivalent water thickness (EWT) is an essential indicator of plant water status related to plant growth, temperature maintenance and transpiration. To our knowledge, this study was the first to map the mangrove canopy EWT using Sentinel-2 image at the reserve scale, aiming to explore three modeling strategies in retrieving mangrove canopy EWT, including machine learning models (Random Forest Regression (RFR) and Adaptive Boosting (Adaboost)), radiative transfer models (RTMs, PROSAIL-D and biophysical processor in Sentinel application platform) and hybrid models (PROSAIL-D + RFR and PROSAIL-D + Adaboost). We further investigated the impacts of four ecogeographical factors (species distribution, slope, elevation and distance to dam) on the spatial distribution of canopy EWT using Geodetector method. The results showed that Adaboost (R2 = 0.593, RMSE = 0.771 kg/m2 and RPIQ = 1.820), PROSAIL-D (R2 = 0.451, RMSE = 0.937 kg/m2 and RPIQ = 1.537) and PROSAIL-D + Adaboost (R2 = 0.501, RMSE = 0.890 kg/m2 and RPIQ = 0.887) was the optimal machine learning, RTM and hybrid model in retrieving mangrove canopy EWT, respectively. The red-edge3, NIR and SWIR bands of Sentinel-2 imagery were sensitive to canopy EWT. Moreover, Geodetector analysis demonstrated that species distribution had the most significant impact on canopy EWT, with the interaction between species and distance to dams contributing the most to the spatial difference of canopy EWT. In conclusion, this study suggests that Adaboost model and the hybrid method of PROSAIL-D and Adaboost were promising to map large-scale canopy water conditions in mangrove ecosystems using Sentinel-2 imagery.

Optimized Hybrid Model for COVID-19 Vaccine Sentiment Analysis for Hindi Text

Optimized Hybrid Model for COVID-19 Vaccine Sentiment Analysis for Hindi Text

Telemedicine in specialist outpatient care during COVID-19: a qualitative study.

COVID-19 accelerated healthcare changes, introducing various telehealth services. Work is needed to determine the suitability of telemedicine in the post-pandemic era. To explore perceptions and experiences of telemedicine among patients and providers (clinicians and health administrators) who were involved in telemedicine appointments in hospital outpatient clinics in 2020-2022. Qualitative study: semi-structured interviews were conducted with 37 participants (16 patients and 21 providers) in various hospital specialist outpatient clinics in a New South Wales local health district. Patients were generally satisfied with telemedicine consultations, especially during COVID restrictions, because of the convenience of accessing care from home and minimising the risk of COVID exposure. However, patients considered that the inability to receive a physical examination was a significant disadvantage of telemedicine. Providers had ambivalent perceptions and expressed concerns about mis- and under-diagnoses because of the inability to conduct physical examinations. They considered telemedicine suitable for review appointments but noted an associated increased workload and stressed the need for sustainable funding models (Medicare items). Both patients and providers recognised the need for education/training and better integration of telemedicine platforms into existing infrastructure to facilitate an optimal hybrid model of care. Despite expressing some concerns over its limitations, patients valued telemedicine for its convenience and for meeting their needs during the pandemic. While acknowledging that patients experienced some benefits from telemedicine, clinicians expressed concerns about potential missed diagnoses, uncertain clinical outcomes and lack of administrative and technological infrastructure. The ultimate test of telemedicine will be its impact on clinical outcomes versus longstanding models of in-person care.

Deep federated learning hybrid optimization model based on encrypted aligned data

Federated learning can achieve multi-party data-collaborative applications while safeguarding personal privacy. However, the process often leads to a decline in the quality of sample data due to a substantial amount of missing encrypted aligned data, and there is a lack of research on how to improve the model learning effect by increasing the number of samples of encrypted aligned data in federated learning. Therefore, this paper integrates the functional characteristics of deep learning models and proposes a Variational AutoEncoder Gaussian Mixture Model Clustering Vertical Federated Learning Model (VAEGMMC-VFL), which leverages the feature extraction capability of the autoencoder and the clustering and pattern discovery capabilities of Gaussian mixture clustering on diverse datasets to further explore a large number of potentially usable samples. Firstly, the Variational AutoEncoder is used to achieve dimensionality reduction and sample feature reconstruction of high-dimensional data samples. Subsequently, Gaussian mixture clustering is further employed to partition the dataset into multiple potential Gaussian-distributed clusters and filter the sample data using thresholding. Additionally, the paper introduces a labeled sample attribute value finding algorithm to fill in attribute values for encrypted unaligned samples that meet the requirements, allowing for the full recovery of encrypted unaligned data. In the experimental section, the paper selects four sets of datasets from different industries and compares the proposed method with three federated learning clustering methods in terms of clustering loss, reconstruction loss, and other metrics. Tests on precision, accuracy, recall, ROC curve, and F1-score indicate that the proposed method outperforms similar approaches.

Optimal waste load allocation in river systems based on a new multi-objective cuckoo optimization algorithm.

Water pollution escalates with rising waste discharge in river systems, as the rivers' limited pollution tolerance and constrained self-cleaning capacity compel the release of treated pollutants. Although several studies have shown that the non-dominated sorting genetic algorithm-II (NSGA-II) is an effective algorithm regarding the management of river water quality to reach water quality standards, to our knowledge, the literature lacks using a new optimization model, namely, the multi-objective cuckoo optimization algorithm (MOCOA). Therefore, this research introduces a new optimization framework, including non-dominated sorting and ranking selection using the comparison operator densely populated towards the best Pareto front and a trade-off estimation between the goals of discharges and environmental protection authorities. The suggested algorithm is implemented for a waste load allocation issue in Jajrood River, located in the North of Iran. The limitation of this research is that discharges are point sources. To analyze the performance of the new optimization algorithm, the simulation model is linked with a hybrid optimization model using a cuckoo optimization algorithm and non-dominated sorting genetic algorithms to convert a single-objective algorithm to a multi-objective algorithm. The findings indicate that, in terms of violation index and inequity values, MOCOA's Pareto front is superior to NSGA-II, which highlights the MOCOA's effectiveness in waste load allocation. For instance, with identical population sizes and violation indexes for both algorithms, the optimal Pareto front ranges from 1.31 to 2.36 for NSGA-II and 0.379 to 2.28 for MOCOA. This suggests that MOCOA achieves a superior Pareto front in a more efficient timeframe. Additionally, MOCOA can attain optimal equity in the smaller population size.

Breast Cancer Detection and Classification Using Hybrid Feature Selection and DenseXtNet Approach

Breast Cancer (BC) detection and classification are critical tasks in medical diagnostics. The lives of patients can be greatly enhanced by the precise and early detection of BC. This study suggests a novel approach for detecting BC that combines deep learning models and sophisticated image processing techniques to address those shortcomings. The BC dataset was pre-processed using histogram equalization and adaptive filtering. Data augmentation was performed using cycle-consistent GANs (CycleGANs). Handcrafted features like Haralick features, Gabor filters, contour-based features, and morphological features were extracted, along with features from deep learning architecture VGG16. Then, we employed a hybrid optimization model, combining the Sparrow Search Algorithm (SSA) and Red Deer Algorithm (RDA), called Hybrid Red Deer with Sparrow optimization (HRDSO), to select the most informative subset of features. For detecting BC, we proposed a new DenseXtNet architecture by combining DenseNet and optimized ResNeXt, which is optimized using the hybrid optimization model HRDSO. The proposed model was evaluated using various performance metrics and compared with existing methods, demonstrating that its accuracy is 97.58% in BC detection. MATLAB was utilized for implementation and evaluation purposes.

Automated Deep Learning Model with Optimization Mechanism for Segmenting Leukemia from Blood Smear Images

The advancement of digital microscopic scanning has made the study of image processing as well as categorization an exciting field of diagnostic studies. The literature describes a number of methods for detecting acute lymphocytic leukemia (ALL) using blood smear pictures. The goal of this research is to create an efficient approach for segmenting and detecting leukemia. This research has created a leukemia diagnosis module predicated on deep learning (DL) using blood smear pictures. Pre-processing, segmentation, extraction of features, and classification are performed here by the identification scheme. The presented hybrid model of African Buffalo and African Vulture Optimization (AB-AVO) performs the segmentation process, in which cytoplasm and nucleus regions are segmented. The Local Directional Pattern (LDP) and color histogram characteristics have been then retrieved from the segmented pictures and given into the presented Recurrent Neural Network (RNN) for categorization. The ALL-IDB1 and ALL-IDB2 databases’ blood smear pictures are taken into account for the investigation and assessed using metrics including F1-score, sensitivity, dice coefficient, precision, specificity, recall, and accuracy. The presented AB-AVO-RNN approach exhibits 100% accuracy, according to simulation data. Modern methodologies are used to compare the effectiveness of the suggested AB-AVO-RNN methodology. The investigation demonstrates that the suggested classifier performs comparably better and can identify leukemia from blood smear pictures.

A case study of a neighborhood in Douala examining the technical feasibility of a hybrid renewable energy system connected to the grid for energy and oxygen production in the fight against respiratory diseases

The world is increasingly focusing its attention on the rapid growth in electricity consumption, a concern shared by both industrialized and emerging nations. Meeting this escalating demand has become crucial, necessitating a shift towards sustainable energy use. Renewable energy sources have emerged as a popular choice for both off-grid and grid-connected installations as a means to bridge the efficiency gap. In this context, the present paper explores the potential of supplying electricity to a neighborhood in Cameroon comprising 100 homes through the integration of solar photovoltaic cells and electrolyzers. It is worth noting that Cameroon as a whole continues to grapple with severe social, economic, and physical challenges. Some regions within the country face significant obstacles in accessing quality healthcare, particularly for conditions like respiratory illnesses. This study employs an intelligent energy management method to design an optimal power flow control system, aimed at enhancing system stability during power outages and load fluctuations by effectively utilizing available storage capacity. The analysis was conducted using the Hybrid Optimization Model for Electric Renewable (HOMER) program. Our calculations reveal that a daily output of 0.123 kg mass of oxygen is produced, with renewable factor (RF) values indicating an 85.1 % integration of renewable sources, and the crucial parameter of Loss of Power Supply Probability (LPSP) reaching 0 %. These findings demonstrate that it is feasible for 100 homes to reliably generate and connect to the grid for electricity. Moreover, this research can serve as a solid foundation for the development of hybrid renewable energy systems to address the challenge of treating respiratory disorders such as COVID-19. These results underscore the significance of this study for various stakeholders, including decision-makers, policymakers, and investors in Cameroon and beyond. The ultimate goal is to promote national growth by improving socio-medical conditions.

Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task.

To design and develop an approach named HC+SMA-SSA scheme for classifying motor imagery task. The offered model employs a new method for classifying motor imagery task. Initially, down sampling is deployed to pre-process the incoming signal. Subsequently, "Modified Stockwell Transform (ST) and common spatial pattern (CSP) based features are extracted". Then, optimal channel selection is made by a novel hybrid optimization model named as Spider Monkey Assisted SSA (SMA-SSA). Here, "Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Unit (BI-GRU)" models are used for final classification, whose outcomes are averaged at the end. At last, the improvement of SMA-SSA based model is proven over different metrics. A superior sensitivity of 0.939 is noted for HC+SMA-SSA that was higher over HC with no optimization and proposed with traditional ST. The proposed method achieved effective classification performance in terms of performance measures.