Hyperparameter Tuning Research Articles

Maximizing steel slice defect detection: Integrating ResNet101 deep features with SVM via Bayesian optimization

Accurate detection of defects on steel surfaces is crucial for maintaining quality standards in steel production. This paper addresses the challenge of classifying steel sheets into distinct defect categories by presenting a robust method that leverages deep learning and advanced optimization techniques. We propose a novel approach that utilizes the ResNet101 model to extract deep features, which are then classified using a support vector machine (SVM). To enhance the SVM's performance, Bayesian optimization is employed for hyperparameter tuning. Our method is validated using the "Severstal: Steel Defect Detection" dataset from Kaggle, achieving a validation accuracy of 89.1 % and a test accuracy of 90.6 %, with a classification error of 0.10934. Additionally, the area under the curve (AUC) for each class exceeds 0.95 in both the validation and test sets, demonstrating excellent discriminatory power. Further evaluation on the DAGM dataset achieved flawless results, with an accuracy of 100 %, AUC of 1, sensitivity of 100 %, specificity of 100 %, precision of 100 %, MCC of 100 %, F1 score of 1, and kappa of 100 %. On the NEU dataset, our method achieved an accuracy of 97.92 %, sensitivity of 97.92 %, specificity of 99.58 %, precision of 98.06 %, F1 score of 0.9791, MCC of 97.55 %, and kappa of 92.50 %. These results demonstrate the robustness and adaptability of the proposed method, offering an efficient and reliable solution for automating steel defect detection and surface defect classification in industrial applications.

Hyperparameter Tuning Decision Tree and Recursive Feature Elimination Technique for Improved Chronic Kidney Disease Classification

Purpose: This study has the purpose of classifying patients with chronic kidney disease based on specific features and improving the classification models by tuning hyperparameters. This study aims to detect chronic kidney disease at an early stage. Methods: In this study, a machine learning classifier in the form of a decision tree is used to classify chronic kidney disease on the Risk Factor Prediction of Chronic Kidney Disease dataset. After that, the performance of the classifier model is improved by using feature selection, namely Recursive Feature Elimination and Hyperparameter tuning with GridSearchCV. Result: After tests were conducted 3 times namely testing with Decision Tree, Recursive Feature Elimination, and Hyperparameter tuning GridSearchCV which is the proposed method, then compared to other tests. The results from this study is using that method can improve the Decision Tree classifier in classifying chronic kidney disease patients. Novelty: Dataset that have been used in this study is from UCI machine learning repository namely Risk Factor Prediction of Chronic Kidney Disease that have 202 instances and 28 feature and after being processess and conducting test, Recursive Feature Elimination and Hyperparameter tuning GridSearchCV can improve the Decision Tree classifier in classifying chronic kidney disease.

Optimizing Currency Circulation Forecasts in Indonesia: A Hybrid Prophet- Long Short Term Memory Model with Hyperparameter Tuning

The core problem for decision-makers lies in selecting an effective forecasting method, particularly when faced with the challenges of nonlinearity and nonstationarity in time series data. To address this, hybrid models are increasingly employed to enhance forecasting accuracy. In Indonesia and other Muslim countries, monthly economic and business time series data often include trends, seasonality, and calendar variations. This study compares the performance of the hybrid Prophet-Long Short-Term Memory (LSTM) model with their individual counterparts to forecast such patterned time series. The aim is to identify the best model through a hybrid approach for forecasting time series data exhibitingtrend, seasonality, and calendar variations, using the real-life case of currency circulation in South Sulawesi. The goodness of the models is evaluated using the smallest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) values. The results indicate that the hybrid Prophet- LSTM model demonstrates superior accuracy, especially for predicting currency outflow, with lower MAPE and RMSE values than standalone models. The LSTM model shows excellent performance for currency inflow, while the Prophet model lags in inflow and outflow accuracy. This insight is valuable for Bank Indonesia’s strategic planning, aiding in better cash flow prediction and currency stock management.

Artificial intelligence and machine learning at various stages and scales of process systems engineering

AbstractWe review the utility and application of artificial intelligence (AI) and machine learning (ML) at various process scales in this work, from molecules and reactions to materials to processes, plants, and supply chains; furthermore, we highlight whether the application is at the design or operational stage of the process. In particular, we focus on the distinct representational frameworks employed at the various scales and the physics (equivariance, additivity, injectivity, connectivity, hierarchy, and heterogeneity) they capture. We also review AI techniques and frameworks important in process systems, including hybrid AI modelling, human‐AI collaborations, and generative AI techniques. In hybrid AI models, we emphasize the importance of hyperparameter tuning, especially in the case of physics‐informed regularization. We highlight the importance of studying human‐AI interactions, especially in the context of automation, and distinguish the features of human‐complements‐AI systems from those of AI‐complements‐human systems. Of particular importance in the AI‐complements‐human framework are model explanations, including rule‐based explanation, explanation‐by‐example, explanation‐by‐simplification, visualization, and feature relevance. Generative AI methods are becoming increasingly relevant in process systems engineering, especially in contexts that do not belong to ‘big data’, primarily due to the lack of high quality labelled data. We highlight the use of generative AI methods including generative adversarial networks, graph neural networks, and large language models/transformers along with non‐traditional process data (images, audio, and text).

Forget to Learn (F2L): Circumventing plasticity–stability trade-off in continuous unsupervised domain adaptation

In continuous unsupervised domain adaptation (CUDA), deep learning models struggle with the stability-plasticity trade-off—where the model must forget old knowledge to acquire new one. This paper introduces the “Forget to Learn” (F2L), a novel framework that circumvents such a trade-off. In contrast to state-of-the-art methods that aim to balance the two conflicting objectives, stability and plasticity, F2L utilizes active forgetting and knowledge distillation to circumvent the conflict’s root causes. In F2L, dual-encoders are trained, where the first encoder – the ‘Specialist’ – is designed to actively forget, thereby boosting adaptability (i.e., plasticity) and generating high-accuracy pseudo labels on the new domains. Such pseudo labels are then used to transfer/accumulate the specialist knowledge to the second encoder—the ‘Generalist’ through conflict-free knowledge distillation. Empirical and ablation studies confirmed F2L’s superiority on different datasets and against different SOTAs. Furthermore, F2L minimizes the need for hyperparameter tuning, enhances computational and sample efficiency, and excels in problems with long domain sequences—key advantages for practical systems constrained by hardware limitations.

Water quality estimates using machine learning techniques in an experimental watershed

ABSTRACT This study aims to identify the best machine learning (ML) approach to predict concentrations of biochemical oxygen demand (BOD), nitrate, and phosphate. Four ML techniques including Decision tree, Random Forest, Gradient Boosting and XGBoost were compared to estimate the water quality parameters based on biophysical (i.e., population, basin area, river slope, water level, and stream flow), and physicochemical properties (i.e., conductivity, turbidity, pH, temperature, and dissolved oxygen) input parameters. The innovation lies in the combination of on-the-spot variables with additional characteristics of the watershed. The model performances were evaluated using coefficient of determination (R2), Nash-Sutcliffe efficiency coefficient (NSE), Root Mean Squared Error (RMSE) and Kling-Gupta Efficiency (KGE) coefficient. The robust five-fold cross-validation, along with hyperparameter tuning, achieved R2 values of 0.71, 0.66, and 0.69 for phosphate, nitrate, and BOD; NSE values of 0.67, 0.65, and 0.62, and KGE values of 0.64, 0.75, and 0.60, respectively. XGBoost yielded good results, showcasing superior performance when considering all analysis performed, but his performance was closely match by other algorithms. The overall modeling design and approach, which includes careful consideration of data preprocessing, dataset splitting, statistical evaluation metrics, feature analysis, and learning curve analysis, are just as important as algorithm selection.

Mean Variance Estimation Neural Network Particle Filter for Predicting Battery Remaining Useful Life

Traditional remaining useful life (RUL) prediction methods based on particle filter (PF) require the manual tuning of hyperparameters, such as process or measurement noise, which poses challenges, particularly in real-life applications where external and operating conditions may change, potentially leading to large errors in the predictions. We address this issue by replacing the measurement equation of a PF with a mean variance estimation neural network that estimates the mean and the variance of the output distribution. As a result, the measurement noise is automatically estimated by the neural network and does not require manual setting. Through simulations and comparative analyses with state-of-the-art methods, the proposed mean variance estimation neural network particle filter (MVENN-PF) is shown to provide more stable and accurate RUL predictions, thereby potentially enhancing the robustness of battery health management systems based on it. Additionally, by eliminating the need to manually set a model hyperparameter (the measurement noise) the proposed method simplifies the modeling process, making it more accessible and adaptable to various battery systems.

CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis

Psoriasis, being a chronic, inflammatory, lifelong skin disorder, has become a major threat to the human population. The precise and effective diagnosis of psoriasis continues to be difficult for clinicians due to its varied nature. In northern India, the prevalence of psoriasis among adult population ranges from 0.44 to 2.8%. Chronic plaque psoriasis accounts for over 90% of cases. This study utilized a dataset of 325 raw images collected from a reputable local hospital using a digital camera under uniform lighting conditions. These images were processed to generate 496 image patches (both diseased and normal), which were then normalized and resized for model training. An automated psoriasis image recognition framework was developed using four state-of-the-art deep transfer learning models: VGG16, VGG19, MobileNetV1, and ResNet-50. The convolutional layers adopted various edge, shape, and color filters to generate the feature map for psoriasis detection. Each pre-trained model was adapted with two dense layers, one dropout layer, and one output layer to classify input images. Among these models, MobileNetV1 achieved the best performance, with 94.84% sensitivity, 89.37% specificity, and 97.24% overall accuracy. Hyper-parameter tuning was performed using grid search to optimize learning rates, batch sizes, and dropout rates. The AdaGrad (Adaptive gradient)) optimizer was chosen for its adaptive learning rate capabilities, facilitating quicker convergence in model performance. Consequently, the methodology’s performance improved to 94.25% sensitivity, 96.42% specificity, and 99.13% overall accuracy. The model’s performance was also compared with non-machine learning-based diagnostic methods, yielding a Dice coefficient of 0.98. However, the model’s effectiveness is dependent upon high-quality input images, as poor image conditions may affect accuracy, and it may not generalize well across diverse demographics or psoriasis variations, highlighting the need for varied training datasets for robustness.

Ensemble based high performance deep learning models for fake news detection

Social media has emerged as a dominant platform where individuals freely share opinions and communicate globally. Its role in disseminating news worldwide is significant due to its easy accessibility. However, the increase in the use of these platforms presents severe risks for potentially misleading people. Our research aims to investigate different techniques within machine learning, deep learning, and ensemble learning frameworks in Arabic fake news detection. We integrated FastText word embeddings with various machine learning and deep learning methods. We then leveraged advanced transformer-based models, including BERT, XLNet, and RoBERTa, optimizing their performance through careful hyperparameter tuning. The research methodology involves utilizing two Arabic news article datasets, AFND and ARABICFAKETWEETS datasets, categorized into fake and real subsets and applying comprehensive preprocessing techniques to the text data. Four hybrid deep learning models are presented: CNN-LSTM, RNN-CNN, RNN-LSTM, and Bi-GRU-Bi-LSTM. The Bi-GRU-Bi-LSTM model demonstrated superior performance regarding the F1 score, accuracy, and loss metrics. The precision, recall, F1 score, and accuracy of the hybrid Bi-GRU-Bi-LSTM model on the AFND Dataset are 0.97, 0.97, 0.98, and 0.98, and on the ARABICFAKETWEETS dataset are 0.98, 0.98, 0.99, and 0.99 respectively. The study’s primary conclusion is that when spotting fake news in Arabic, the Bi-GRU-Bi-LSTM model outperforms other models by a significant margin. It significantly aids the global fight against false information by setting the stage for future research to expand fake news detection to multiple languages.

Multi-Step Ahead Water Level Forecasting Using Deep Neural Networks

Stream gauge height (water level) is a significant indicator for forecasting future floods. Flooding occurs when the water level exceeds the flood stage. Predicting imminent floods can save lives, protect infrastructure, and improve road traffic management and transportation. Deep neural networks have been increasingly used in this domain due to their predictive capabilities in capturing complex features and interdependencies. This study employs four distinct models—Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), transformer, and LSTNet—with MLP serving as the baseline model to forecast water levels. The models are trained using data from 20 distinct river gages across the state of Missouri to ensure consistent performance. Random search optimization is employed for hyperparameter tuning. The prediction intervals are set at 4, 6, 8, and 10 (each interval equivalent to 30 min) to ensure that performance results are robust and not due to random weight initialization or suboptimal hyperparameters and are consistent throughout different prediction intervals. The findings of this study indicate that the LSTNet model leads to a better performance than the other models, with a median RMSE of 0.00724, 0.00959, 0.01204, and 0.01230 for the 4, 6, 8, and 10 intervals, respectively. As climate change leads to localized storms driven by atmospheric shifts, water level fluctuations are becoming increasingly extreme, further exacerbating data drift in real-world datasets. The LSTNet model demonstrates superior performance in terms of RMSE, MAE, and the correlation coefficient across all prediction intervals when forecasting water levels under data drift conditions.

AUTOMATED INDOOR ACTIVITY MONITORING FOR ELDERLY AND VISUALLY IMPAIRED PEOPLE USING QUANTUM SALP SWARM ALGORITHM WITH MACHINE LEARNING

Elderly and vision-impaired indoor activity monitoring uses sensor technology to monitor interaction and movement in the living area. This system can identify deviations from regular patterns, provide alerts, and ensure safety in case of emergencies or potential risks. These solutions enhance quality of life by promoting independent living while offering peace of mind to loved ones and caregivers. Visual impairments have become the chief part of these problems over the past few years. Usually, visually impaired people seek help from others to keep doing their daily tasks. An automated human activity recognition (HAR) technique could enhance a vision-impaired person’s transaction activity and safe movement. HAR using deep learning (DL) includes training neural networks to automatically detect and classify various activities carried out by humans based on sensor information. By leveraging DL approaches, the HAR system could accurately identify and classify activities, including sitting, standing, walking, or running, from the information captured by sensors or wearable devices. This system is integral to smart home automation, healthcare, and sports analytics. This study develops an Automated Fractal Quantum Salp Swarm Algorithm with Machine Learning based HAR (QSSA-MLHAR) for assisting elderly and visually impaired people. The QSSA-MLHAR technique uses sensory input data to identify human activities in diverse classes. In the QSSA-MLHAR technique, the min–max scalar is primarily used to scale the input data. Besides, the QSSA-MLHAR technique applies a mixed extreme learning machine (M-ELM) model to classify various human actions. The QSSA-based hyperparameter tuning process is used to improve the detection results of the M-ELM system. A wide range of simulations was performed to ensure the better performance of the QSSA-MLHAR method. The comprehensive outcomes assured that the QSSA-MLHAR technique performs well compared to other models.

HARNESSING PRIVACY-PRESERVING FEDERATED LEARNING WITH BLOCKCHAIN FOR SECURE IoMT APPLICATIONS IN SMART HEALTHCARE SYSTEMS

The Internet of Medical Things (IoMT) refers to interconnected medical systems and devices that gather and transfer healthcare information for several medical applications. Smart healthcare leverages IoMT technology to improve patient diagnosis, monitoring, and treatment, providing efficient and personalized healthcare services. Privacy-preserving Federated Learning (PPFL) is a privacy-enhancing method that allows collaborative method training through distributed data sources while ensuring privacy protection and keeping the data decentralized. In the field of smart healthcare, PPFL enables healthcare professionals to train machine learning algorithms jointly on their corresponding datasets without sharing sensitive data, thereby maintaining confidentiality. Within this framework, anomaly detection includes detecting unusual events or patterns in healthcare data like unexpected changes or irregular vital signs in patient behaviors that can represent security breaches or potential health issues in the IoMT system. Smart healthcare systems could enhance patient care while protecting data confidentiality and individual privacy by incorporating PPFL with anomaly detection techniques. Therefore, this study develops a Privacy-preserving Federated Learning with Blockchain-based Smart Healthcare System (PPFL-BCSHS) technique in the IoMT environment. The purpose of the PPFL-BCSHS technique is to secure the IoMT devices via the detection of abnormal activities and FL concepts. Besides, BC technology can be applied for the secure transmission of medical data among the IoMT devices. The PPFL-BCSHS technique employs the FL for training the model for the identification of abnormal patterns. For anomaly detection, the PPFL-BCSHS technique follows three major processes, namely Mountain Gazelle Optimization (MGO)-based feature selection, Bidirectional Gated Recurrent Unit (BiGRU), and Sandcat Swarm Optimization (SCSO)-based hyperparameter tuning. A series of simulations were implemented to examine the performance of the PPFL-BCSHS method. The empirical analysis highlighted that the PPFL-BCSHS method obtains improved security over other approaches under various measures.

Multimodal AI/ML for discovering novel biomarkers and predicting disease using multi-omics profiles of patients with cardiovascular diseases

Cardiovascular diseases (CVDs) are complex, multifactorial conditions that require personalized assessment and treatment. Advancements in multi-omics technologies, namely RNA sequencing and whole-genome sequencing, have provided translational researchers with a comprehensive view of the human genome. The efficient synthesis and analysis of this data through integrated approach that characterizes genetic variants alongside expression patterns linked to emerging phenotypes, can reveal novel biomarkers and enable the segmentation of patient populations based on personalized risk factors. In this study, we present a cutting-edge methodology rooted in the integration of traditional bioinformatics, classical statistics, and multimodal machine learning techniques. Our approach has the potential to uncover the intricate mechanisms underlying CVD, enabling patient-specific risk and response profiling. We sourced transcriptomic expression data and single nucleotide polymorphisms (SNPs) from both CVD patients and healthy controls. By integrating these multi-omics datasets with clinical demographic information, we generated patient-specific profiles. Utilizing a robust feature selection approach, we identified a signature of 27 transcriptomic features and SNPs that are effective predictors of CVD. Differential expression analysis, combined with minimum redundancy maximum relevance feature selection, highlighted biomarkers that explain the disease phenotype. This approach prioritizes both biological relevance and efficiency in machine learning. We employed Combination Annotation Dependent Depletion scores and allele frequencies to identify variants with pathogenic characteristics in CVD patients. Classification models trained on this signature demonstrated high-accuracy predictions for CVD. The best performing of these models was an XGBoost classifier optimized via Bayesian hyperparameter tuning, which was able to correctly classify all patients in our test dataset. Using SHapley Additive exPlanations, we created risk assessments for patients, offering further contextualization of these predictions in a clinical setting. Across the cohort, RPL36AP37 and HBA1 were scored as the most important biomarkers for predicting CVDs. A comprehensive literature review revealed that a substantial portion of the diagnostic biomarkers identified have previously been associated with CVD. The framework we propose in this study is unbiased and generalizable to other diseases and disorders.

Ocean wave prediction using Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) in Tuban Regency for fisherman safety

The fishing industry has a large role in the Indonesian economy, with potential profits in 2020 of around US$ 1.338 billion. Tuban Regency is one of the regions in East Java that contributes to the fisheries sector. Fisheries relate to the work of fishermen. Accidents in shipping are still a major concern. One of the natural factors that influence shipping accidents is the height of the waves. Fisherman safety regulations have been established by the Ministry of Maritime Affairs and Fisheries and the Meteorology, Climatology and Geophysics Agency. Apart from regulations, the results of wave height predictions using the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) methods can help fishermen determine shipping departures, thereby reducing the risk of accidents. In this study, the Grid Search hyperparameter tuning process was used for both methods which were carried out on four location coordinates. Based on the analysis results, LSTM is superior in predicting wave height for the next 30 days because it can predict wave height at all three locations, with results at the first location (RMSE 0.045; MAE 0.029; MAPE 8.671 %), second location (RMSE 0.051; MAE 0.035; MAPE 10.64 %), and third location (RMSE 0.044; MAE 0.027; MAPE 7.773 %), while XGBoost only has the best value at fourth location (RMSE 0.040; MAE 0.025; MAPE 7.286 %).•Hyperparameter tuning with gridsearch is used in LSTM and XGBoost to obtain optimal accuracy•LSTM outperforms in three locations, while XGBoost outperforms in the fourth location.•Advanced prediction techniques such as LSTM and XGBoost improve fishermen's safety by providing accurate wave height estimates, thereby reducing the possibility of shipping accidents.

Leveraging machine learning for preoperative prediction of supramaximal ablation in laser interstitial thermal therapy for brain tumors.

Maximizing safe resection in neuro-oncology has become paramount to improving patient survival and outcomes. Laser interstitial thermal therapy (LITT) offers similar survival benefits to traditional resection, alongside shorter hospital stays and faster recovery times. The extent of ablation (EOA) achieved using LITT is linked to patient outcomes, with greater EOA correlating with improved outcomes. However, the preoperative predictors for achieving supramaximal ablation (EOA ≥ 100%) are not well understood. By leveraging machine learning (ML) techniques, this study aimed to identify these predictors to enhance patient selection and therefore outcomes. The objective was to explore preoperative predictors for supramaximal EOA using ML in patients with glioblastoma. A retrospective study was conducted on the medical records of 254 patients undergoing LITT from 2013 to 2023 at a single tertiary center. Cohort criteria included age ≥ 18 years, diagnosis of glioblastoma, single-trajectory ablation, and a complete dataset. The study assessed preoperative clinical and radiographic factors, using EOA ≥ 100% as the endpoint. Five ML models were used: logistic regression, random forest (RF), gradient boosting, Gaussian naive Bayes, and support vector machine. Training and testing cohorts were subsequently assessed across ML models with fivefold cross-validation. Models were optimized using hyperparameter tuning. Performance was primarily quantified using the area under the curve (AUC) of the receiver operating characteristic curve. The final cohort consisted of 72 patients. Among the ML models, RF achieved the highest AUC (mean ± SD 0.94 ± 0.06). The leading models identified that lower preoperative volume, history of prior radiation therapy, history of prior craniotomy, preoperative neurological deficits, history of preoperative seizures, and distance from intracranial heat sinks were predictive of successful ablations in patients. Additionally, RF had the best mean metrics: accuracy 0.88, precision 0.87, specificity 0.87, and sensitivity 0.89. This is the first study to investigate the role of ML for optimizing ablation volumes in LITT. These ML models suggest that low preoperative volumes, previous craniotomy, previous radiation therapy, no previous neurological deficits, larger catheter-heat sink distance, and the presence of preoperative seizures are important prognostic factors for predicting successful supramaximal ablations with LITT.

An adaptive network with consecutive and intertwined slices for real-world time-series forecasting

Real-world systems are chiefly comprised of multiple sensors and devices, whose instantaneous data and upcoming tendencies are demanded by the decision makers to formulate future schemes. Accuracy and timeliness are both of paramount significance. Thereby, although the deep forecasting models are promising, the space and resources are often limited in reality, rendering their adaptability requisite. Unfortunately, the majority of current deep forecasting models are far from adaptive and acquire heavy hyper-parameter tuning processes to obtain the satisfactory performances. Moreover, their strategies to reduce the model complexities sometimes bring extra hyper-parameters. To tackle these issues, we propose AdaNS: an Adaptive Network with consecutive and intertwined Slices. The data-driven features of time-series in frequency domain are used in AdaNS to adaptively determine the model structure, as well as hyper-parameters, and categorize variables. In accordance with these frequency-based features, input sequences are first sliced in a consecutive way to extract the universal features and then in an intertwined way to extract the local features, for hierarchical and comprehensive forecasting. Extensive experiments show that AdaNS achieves state-of-the-art performances on fourteen benchmarks, virtually without any hyper-parameter tuning. The source code is available at https://github.com/OrigamiSL/AdaNS.

Explainable tuned machine learning models for assessing the impact of corrosion on bond strength in concrete

This study mainly aims to evaluate the bond strength of corroded reinforcements in reinforced concrete members. In this regard, a comprehensive dataset containing a total of 285 specimens was collected from previous experiments. All collected specimens, including normal concrete, were subjected to pull-out tests to ensure consistent results. The features evaluated are associated with both concrete and rebar characteristics, corrosion rate, and duration. Six machine learning (ML) models were used to assess the dataset: Decision Tree, Random Forest, Light Gradient-Boosting Machine, Gradient Boosting, Extreme Gradient Boosting, and Extra Tree. Hyperparameter tuning was conducted using grid search to optimize model performance and enhance predictive accuracy. Additionally, the Shapley Values technique was utilized to interpret the significance of the features on bond strength.The results show that Extreme Gradient Boosting and Extra tree methods outperformed the other models, with R2 score of 0.9 each and RSME of 2.21 and 1.87, respectively. Furthermore, tuned models resulted in more accurate performance than the default models. Evaluating the significance of studied features indicated that the elevated levels of corrosion were associated with a negative impact on bond strength. In addition, the corrosion rate is considered to be the most influential factor affecting the bond strength.

Comparison of SVM, Naive Bayes, and ELM Models in Plant Growth Classification

This study investigates the application of machine learning models to predict plant growth milestones based on environmental and treatment data. The dataset comprises categorical variables such as soil type, water frequency, and fertilizer type, alongside numerical variables including sunlight hours, temperature, and humidity. Preprocessing involved one-hot encoding for categorical variables and standard scaling for numerical features. The models employed were Support Vector Machine (SVM), Naive Bayes, and Extreme Learning Machine (ELM). The baseline SVM model achieved an accuracy of 58.97%, and hyperparameter tuning using GridSearchCV did not improve this performance, maintaining the accuracy at 58.97%. The Naive Bayes model achieved an accuracy of 51.28%, while the ELM model had an accuracy of 43.85%. Among the models, the SVM demonstrated the highest accuracy, though further improvement is required for practical implementation. The findings underscore the importance of selecting appropriate machine learning models and optimizing their parameters to enhance prediction accuracy in agricultural applications. Despite the SVM's superior performance in this context, continued refinement is essential to address the challenges posed by predicting plant growth milestones accurately.

Advanced hybrid techniques for predicting discharge coefficients in ogee-crested spillways: integrating physical, numerical, and machine learning models

Abstract The primary objective of this work was to examine the flow characteristics over an ogee spillway using both a numerical model and the Machine Learning (ML) approach. A 3D computational fluid dynamics (CFD) model was employed to simulate the flow over an ogee spillway, utilizing the Reynolds averaged Navier–Stokes equations. The simulation encompassed a wide variety of head ratios, ranging from 0.1 to 6.0, to extend the rating curve of discharge coefficient (C) and head ratio (H e /H 0). The formation of the negative pressure zone rapidly occurred, and the maximum velocity area developed from toe to top of the spillway surface as the head ratio increased. Then, four ML models—RF, FNN, ADB, and KNN—were utilized to estimate the discharge coefficient of the spillway. Hyperparameter tuning using the Tree-Structured Parzen Estimator (TPE) and five-fold cross-validation ensured robust model performance. The ML model’s efficacy was assessed by conducting 200 random seed simulations. The RF and ADB models exhibited the highest predictive accuracy and consistency, with mean correlation coefficient (CC) values of 0.979 and 0.975, respectively. FNN and KNN also performed well but showed greater variability in their prediction. The results demonstrated reasonably good agreement between the physical, numerical, and ML models. Both numerical simulation methods and ML models, particularly RF, proved to be cost-efficient and reliable tools for designing and analyzing flow over an ogee spillway. These findings highlight the potential of integrating numerical simulations and advanced ML techniques to enhance the prediction and analysis of hydraulic structures, providing valuable insights for the design and management of spillway systems.

Sandpiper optimization with hybrid deep learning model for blockchain-assisted intrusion detection in iot environment

Intrusion detection in the Internet of Things (IoTs) is a vital unit of IoT safety. IoT devices face diverse kinds of attacks, and intrusion detection systems (IDSs) play a significant role in detecting and responding to these threats. A typical IDS solution can be utilized from the IoT networks for monitoring traffic, device behaviour, and system logs for signs of intrusion or abnormal movement. Deep learning (DL) approaches are exposed to promise in enhancing the accuracy and effectiveness of IDS for IoT devices. Blockchain (BC) aided intrusion detection from IoT platforms provides many benefits, including better data integrity, transparency, and resistance to tampering. This paper projects a novel sandpiper optimizer with hybrid deep learning-based intrusion detection (SPOHDL-ID) from the BC-assisted IoT platform. The key contribution of the SPOHDL-ID model is to accomplish security via the intrusion detection and classification process from the IoT platform. In this case, the BC technology can be used for a secure data-sharing process. In the presented SPOHDL-ID technique, the selection of features from the network traffic data takes place using the SPO model. Besides, the SPOHDL-ID technique employs the HDL model for intrusion detection, which involves the design of a convolutional neural network with a stacked autoencoder (CNN-SAE) model. The beetle search optimizer algorithm (BSOA) method is used for the hyperparameter tuning procedure to increase the recognition outcomes of the CNN-SAE technique. An extensive simulation outcome is created to exhibit a better solution to the SPOHDL-ID method. The experimental validation of the SPOHDL-ID method portrayed a superior accuracy value of 99.59 % and 99.54 % over recent techniques under the ToN-IoT and CICIDS-2017 datasets.