Search

This paper presents the dynamic modeling of an interconnected two equal area of conventional combined cycle gas turbine. In addition, fuzzy logic controllers have been designed and applied to improve speed/load control, temperature control, and air flow control. The coordination between fuzzy- controlled speed signal and fuzzy-controlled temperature control signal has been considered in the design process using fuzzy fuel controller in order to compute the accurate control signal to the fuel system for fast response against the system disturbance. On the other hand, the adaptive neuro-fuzzy inference system (ANFIS) controller is investigated for controlling the model parameter and selection of the proper rule base in order to improve the proposed controller performance. The results demonstrate the superiority of the proposed model with fuzzy logic controller and ANFIS over the conventional model under normal and abnormal conditions. Moreover, the proposed controllers improve effectively the system damping characteristics after a load deviation as the settling time is greatly reduced. [ABSTRACT FROM AUTHOR]

Set Partitioning In Hierarchical Tree (SPIHT) is considered one of the most important algorithms for reducing the size of the vision data collected by the sensor node within wireless multimedia sensor network (WMSN). The traditional SPIHT algorithm suffers from image coders complexity due to large memory requirement. This is an essential problem for the implementation on limited resource environments such as WMSN. The main objective of this paper is to introduce a listless pipelined strip based SPIHT for WMSN to reduce system complexity and minimize processing time and memory usage. The proposed algorithm is implemented using discrete wavelet transform (DWT) lifting-based instead of DWT convolution-based filter. The experimental results show the superiority of the proposed algorithm in terms of peak signal-to-noise ratio (PSNR) which reaches 1 dB for all bit rates. In addition, the memory requirement is reduced to 71% with 27% of energy saving. [ABSTRACT FROM AUTHOR]

The Competitive Swarm Optimizer (CSO) has emerged as a prominent technique for solving intricate optimization problems by updating only half of the population in each iteration. Despite its effectiveness, the CSO algorithm often exhibits a slow convergence rate and a tendency to become trapped in local optimal solutions, as is common among metaheuristic algorithms. To address these challenges, this paper proposes a hybrid approach combining the CSO with the Salp Swarm algorithm (SSA), CL-SSA, to increase the convergence rate and enhance search space exploration. The proposed approach involves a two-step process. In the first step, a pairwise competition mechanism is introduced to segregate the solutions into winners and losers. The winning population is updated through strong exploitation using the SSA algorithm. In the second step, non-winning solutions learn from the winners, achieving a balance between exploration and exploitation. The performance of the CL-SSA is evaluated on various benchmark functions, including the CEC2017 benchmark with dimensions 50 and 100, the CEC2008lsgo benchmark with dimensions 200, 500 and 1000, as well as a set of seven well-known constrained design challenges in various engineering domains defined in the CEC2020 conference. The CL-SSA is compared to other metaheuristics and advanced algorithms, and its results are analyzed through statistical tests such as the Friedman and Wilcoxon rank-sum tests. The statistical analysis demonstrates that the CL-SSA algorithm exhibits improved exploitation, exploration, and convergence patterns compared to other algorithms, including SSA and CSO, as well as popular algorithms. Furthermore, the proposed hybrid approach performs better in solving most test functions. [ABSTRACT FROM AUTHOR]

The oil and gas business has high operating costs and frequently has significant difficulties due to asset, process, and operational failures. Remote monitoring and management of the oil field operations are essential to ensure efficiency and safety. Oil field operations often use SCADA or wireless sensor network (WSN)-based monitoring and control systems; both have numerous drawbacks. WSN-based systems are not uniform or are incompatible. Additionally, they lack transparent communication and coordination. SCADA systems also cost a lot, are rigid, are not scalable, and deliver data slowly. Edge computing and the Industrial Internet of Things (IIoT) help to overcome SCADA's constraints by establishing an automated monitoring and control system for oil and gas operations that is effective, secure, affordable, and transparent. The main objective of this study is to exploit the IIOT and Edge Computing (EC). This study introduces an I2OT-EC framework with flowcharts, a simulator, and system architecture. The validity of the I2OT-EC framework is demonstrated by experimental findings and implementation with an application example to verify the research results as an additional verification and testing that proves the framework results were satisfactory. The significant increase of 12.14% in the runtime for the crude well using the proposed framework, coupled with other advantages, such as reduced operational costs, decentralization, and a dependable platform, highlights the benefits of this solution and its suitability for the automatic monitoring and control of oil field operations. [ABSTRACT FROM AUTHOR]

The human brain can effortlessly perform vision processes using the visual system, which helps solve multi-object tracking (MOT) problems. However, few algorithms simulate human strategies for solving MOT. Therefore, devising a method that simulates human activity in vision has become a good choice for improving MOT results, especially occlusion. Eight brain strategies have been studied from a cognitive perspective and imitated to build a novel algorithm. Two of these strategies gave our algorithm novel and outstanding results, rescuing saccades and stimulus attributes. First, rescue saccades were imitated by detecting the occlusion state in each frame, representing the critical situation that the human brain saccades toward. Then, stimulus attributes were mimicked by using semantic attributes to reidentify the person in these occlusion states. Our algorithm favourably performs on the MOT17 dataset compared to state-of-the-art trackers. In addition, we created a new dataset of 40,000 images, 190,000 annotations and 4 classes to train the detection model to detect occlusion and semantic attributes. The experimental results demonstrate that our new dataset achieves an outstanding performance on the scaled YOLOv4 detection model by achieving a 0.89 mAP 0.5. [ABSTRACT FROM AUTHOR]

The need for non-interactive human recognition systems to ensure safe isolation between users and biometric equipment has been exposed by the COVID-19 pandemic. This study introduces a novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication (MSDCS-PHGA). The proposed MSDCS-PHGA involves segmenting, preprocessing, and resizing silhouette images into three scales. Gait features are extracted from these multi-scale images using custom convolutional layers and fused to form an integrated feature set. This multi-scaled deep convolutional approach demonstrates its efficacy in gait recognition by significantly enhancing accuracy. The proposed convolutional neural network (CNN) architecture is assessed using three benchmark datasets: CASIA, OU-ISIR, and OU-MVLP. Moreover, the proposed model is evaluated against other pre-trained models using key performance metrics such as precision, accuracy, sensitivity, specificity, and training time. The results indicate that the proposed deep CNN model outperforms existing models focused on human gait. Notably, it achieves an accuracy of approximately 99.9% for both the CASIA and OU-ISIR datasets and 99.8% for the OU-MVLP dataset while maintaining a minimal training time of around 3 min. [ABSTRACT FROM AUTHOR]

Perovskite solar cells (PSCs) exhibit hysteresis in their J-V characteristics, complicating the identification of appropriate electrical models and the determination of the maximum power point. Given the rising prominence of PSCs due to their potential for superior performance, there is a pressing need to address this challenge. Existing solutions in the literature have not fully addressed the hysteresis issue, especially in the context of dynamic modeling. To bridge this gap, this study introduces Artificial Rabbits Optimization (ARO) as an innovative method for optimizing the parameters of an enhanced PSC dynamic model. The proposed model is constructed based on experimental J-V data sets of PSCs, ensuring that it accounts for the hysteresis characteristics observed in both forward and backward scans. The study conducted a rigorous statistical analysis to validate the Modified Two-Diode Model performance with that of the Energy Balance (MTDM_E) optimized using the innovative ARO algorithm. The performance metric utilized for validation was the Root mean square error (RMSE), a widely recognized degree of the differences between values predicted by a model and the values observed. The statistical analysis encompassed 30 independent runs to ensure the robustness and reliability of the results. The summary statistics for the MTDM_E model under the ARO algorithm demonstrated a minimum RMSE of 4.84E−04, a maximum of 6.44E−04, and a mean RMSE of 5.14E−04. The median RMSE was reported as 5.07E−04, with a standard deviation of 3.17E−05, indicating a consistent and tight clustering of results around the mean, which suggests a high level of precision in the model's performance. Validated using root mean square error (RMSE) across 30 runs, the ARO algorithm showcased superior precision in parameter determination for the MTDM_E model, with a mean RMSE of 5.14E−04, outperforming other algorithms like GWO, PSO, SCA, and SSA. This affirms ARO's robustness in optimizing solar cell models. [ABSTRACT FROM AUTHOR]

The early detection of oral cancer is pivotal for improving patient survival rates. However, the high cost of manual initial screenings poses a challenge, especially in resource-limited settings. Deep learning offers an enticing solution by enabling automated and cost-effective screening. This study introduces a groundbreaking empirical framework designed to revolutionize the accurate and automatic classification of oral cancer using microscopic histopathology slide images. This innovative system capitalizes on the power of convolutional neural networks (CNNs), strengthened by the synergy of transfer learning (TL), and further fine-tuned using the novel Aquila Optimizer (AO) and Gorilla Troops Optimizer (GTO), two cutting-edge metaheuristic optimization algorithms. This integration is a novel approach, addressing bias and unpredictability issues commonly encountered in the preprocessing and optimization phases. In the experiments, the capabilities of well-established pre-trained TL models, including VGG19, VGG16, MobileNet, MobileNetV3Small, MobileNetV2, MobileNetV3Large, NASNetMobile, and DenseNet201, all initialized with 'ImageNet' weights, were harnessed. The experimental dataset consisted of the Histopathologic Oral Cancer Detection dataset, which includes a 'normal' class with 2494 images and an 'OSCC' (oral squamous cell carcinoma) class with 2698 images. The results reveal a remarkable performance distinction between the AO and GTO, with the AO consistently outperforming the GTO across all models except for the Xception model. The DenseNet201 model stands out as the most accurate, achieving an astounding average accuracy rate of 99.25% with the AO and 97.27% with the GTO. This innovative framework signifies a significant leap forward in automating oral cancer detection, showcasing the tremendous potential of applying optimized deep learning models in the realm of healthcare diagnostics. The integration of the AO and GTO in our CNN-based system not only pushes the boundaries of classification accuracy but also underscores the transformative impact of metaheuristic optimization techniques in the field of medical image analysis. [ABSTRACT FROM AUTHOR]

Credit scoring models serve as pivotal instruments for lenders and financial institutions, facilitating the assessment of creditworthiness. Traditional models, while instrumental, grapple with challenges related to efficiency and subjectivity. The advent of machine learning heralds a transformative era, offering data-driven solutions that transcend these limitations. This research delves into a comprehensive analysis of various machine learning algorithms, emphasizing their mathematical underpinnings and their applicability in credit score classification. A comprehensive evaluation is conducted on a range of algorithms, including logistic regression, decision trees, support vector machines, and neural networks, using publicly available credit datasets. Within the research, a unified mathematical framework is introduced, which encompasses preprocessing techniques and critical algorithms such as Particle Swarm Optimization (PSO), the Light Gradient Boosting Model, and Extreme Gradient Boosting (XGB), among others. The focal point of the investigation is the LIME (Local Interpretable Model-agnostic Explanations) explainer. This study offers a comprehensive mathematical model using the LIME explainer, shedding light on its pivotal role in elucidating the intricacies of complex machine learning models. This study's empirical findings offer compelling evidence of the efficacy of these methodologies in credit scoring, with notable accuracies of 88.84%, 78.30%, and 77.80% for the Australian, German, and South German datasets, respectively. In summation, this research not only amplifies the significance of machine learning in credit scoring but also accentuates the importance of mathematical modeling and the LIME explainer, providing a roadmap for practitioners to navigate the evolving landscape of credit assessment. [ABSTRACT FROM AUTHOR]

In the evolving landscape of targeted marketing, integrating deep learning (DL) and explainable AI (XAI) offers a promising avenue for enhanced customer segmentation. This paper introduces a groundbreaking approach, DeepLimeSeg, which synergizes DL methodologies with Lime-based Explainability to segment customers effectively. The approach employs a comprehensive mathematical model to harness demographic data, behavioral patterns, and purchase histories, categorizing customers into distinct clusters aligned with their preferences and needs. A pivotal component of this research is the mathematical underpinning of the DeepLimeSeg approach. The Lime-based Explainability module ensures that the segmentation results are accurate and interpretable. The mathematical rigor facilitates businesses tailoring their marketing strategies with precision, optimizing sales outcomes. To validate the efficacy of DeepLimeSeg, we employed two real-world datasets: Mall-Customer Segmentation Data and an E-Commerce dataset. A comparative analysis between DeepLimeSeg and the traditional Recency, Frequency, and Monetary (RFM) analysis is presented. The RFM analysis, grounded in its mathematical modeling, segments customers based on purchase recency, frequency, and monetary value. Our preprocessing involved computing RFM scores for each customer, followed by K-means clustering to delineate customer segments. Empirical results underscored the superiority of DeepLimeSeg over other models in terms of MSE, MAE, and R 2 metrics. Specifically, the model registered an MSE of 0.9412, indicative of its robust predictive accuracy concerning the spending score. The MAE value stood at 0.9874, signifying minimal deviation from actual values. This paper accentuates the importance of mathematical modeling in enhancing customer segmentation. The DeepLimeSeg approach, with its mathematical foundation and explainable AI integration, paves the way for businesses to make informed, data-driven marketing decisions. [ABSTRACT FROM AUTHOR]

Terminal neurological conditions can affect millions of people worldwide and hinder them from doing their daily tasks and movements normally. Brain computer interface (BCI) is the best hope for many individuals with motor deficiencies. It will help many patients interact with the outside world and handle their daily tasks without assistance. Therefore, machine learning-based BCI systems have emerged as non-invasive techniques for reading out signals from the brain and interpreting them into commands to help those people to perform diverse limb motor tasks. This paper proposes an innovative and improved machine learning-based BCI system that analyzes EEG signals obtained from motor imagery to distinguish among various limb motor tasks based on BCI competition III dataset IVa. The proposed framework pipeline for EEG signal processing performs the following major steps. The first step uses a meta-heuristic optimization technique, called the whale optimization algorithm (WOA), to select the optimal features for discriminating between neural activity patterns. The pipeline then uses machine learning models such as LDA, k-NN, DT, RF, and LR to analyze the chosen features to enhance the precision of EEG signal analysis. The proposed BCI system, which merges the WOA as a feature selection method and the optimized k-NN classification model, demonstrated an overall accuracy of 98.6%, outperforming other machine learning models and previous techniques on the BCI competition III dataset IVa. Additionally, the EEG feature contribution in the ML classification model is reported using Explainable AI (XAI) tools, which provide insights into the individual contributions of the features in the predictions made by the model. By incorporating XAI techniques, the results of this study offer greater transparency and understanding of the relationship between the EEG features and the model's predictions. The proposed method shows potential levels for better use in controlling diverse limb motor tasks to help people with limb impairments and support them while enhancing their quality of life. [ABSTRACT FROM AUTHOR]

Recently, the concept of green building has become popular, and various renewable energy systems have been integrated into green buildings. In particular, the application range of fuel cells (FCs) has become widespread due to the various government plans regarding green hydrogen energy systems. In particular, proton exchange membrane fuel cells (PEMFCs) have proven superiority over other existing FCs. However, the uniqueness of the operating maximum power point (MPP) of PEMFCs represents a critical issue for the PEMFC control systems. The perturb and observe, incremental conductance/resistance, and fuzzy logic control (FLC) represent the most used MPP tracking (MPPT) algorithms for PEMFC systems, among which the FLC-based MPPT methods have shown improved performance compared to the other methods. Therefore, this paper presents a modified FLC-based MPPT method for PEMFC systems in green building applications. The proposed method employs the rate of change of the power with current ( d P / d I ) instead of the previously used rate of change of power with voltage ( d P / d V ) in the literature. The employment of d P / d I in the proposed method enables the fast-tracking of the operating MPP with low transient oscillations and mitigated steady-state fluctuations. Additionally, the design process of the proposed controller is optimized using the enhanced version of the success-history-based adaptive differential evolution (SHADE) algorithm with linear population size reduction, known as the LSHADE algorithm. The design optimization of the proposed method is advantageous for increasing the adaptiveness, robustness, and tracking of the MPP in all the operating scenarios. Moreover, the proposed MPPT controller can be generalized to other renewable energy and/or FCs applications. The proposed method is implemented using C-code with the PEMFC model and tested in various operating cases. The obtained results show the superiority and effectiveness of the proposed controller compared to the classical proportional-integral (PI) based d P / d I -based MPPT controller and the classical FLC-based MPPT controller. Moreover, the proposed controller achieves reduced output waveforms ripple, fast and accurate MPPT operation, and simple and low-cost implementation. [ABSTRACT FROM AUTHOR]

Traditionally, the Economic Dispatch Model (EDM) integrating Combined Heat and Power (CHP) units aims to reduce fuel costs by managing power-only, CHP, and heat-only units. Today, reducing pollutant emissions to the environment is of paramount concern. This research presents a novel honey badger optimization algorithm (HBOA) for EDM-integrated CHP units. HBOA is a novel meta-heuristic search strategy inspired by the honey badger's sophisticated hunting behavior. In HBOA, the dynamic searching activity of the honey badger, which includes digging and honing, is separated into exploration and exploitation phases. In addition, several modern meta-heuristic optimization algorithms are employed, which are the African Vultures Algorithm (AVO), Dwarf Mongoose Optimization Algorithm (DMOA), Coot Optimization Algorithm (COA), and Beluga Whale Optimization Algorithm (BWOA). These algorithms are applied in a comparative manner considering the seven-unit test system. Various loading levels are considered with different power and heat loading. Four cases are investigated for each loading level, which differ based on the objective task and the consideration of power losses. Moreover, considering the pollutant emissions minimization objective, the proposed HBOA achieves reductions, without loss considerations, of 75.32%, 26.053%, and 87.233% for the three loading levels, respectively, compared to the initial case. Moreover, considering minimizing pollutant emissions, the suggested HBOA achieves decreases of 75.32%, 26.053%, and 87.233%, relative to the baseline scenario, for the three loading levels, respectively. Similarly, it performs reductions of 73.841%, 26.155%, and 92.595%, respectively, for the three loading levels compared to the baseline situation when power losses are considered. Consequently, the recommended HBOA surpasses the AVO, DMOA, COA, and BWOA when the purpose is to minimize fuel expenditures. In addition, the proposed HBOA significantly reduces pollutant emissions compared to the baseline scenario. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a chronic disease that affects the elderly. There are many different types of dementia, but Alzheimer's disease is one of the leading causes of death. AD is a chronic brain disorder that leads to problems with language, disorientation, mood swings, bodily functions, memory loss, cognitive decline, mood or personality changes, and ultimately death due to dementia. Unfortunately, no cure has yet been developed for it, and it has no known causes. Clinically, imaging tools can aid in the diagnosis, and deep learning has recently emerged as an important component of these tools. Deep learning requires little or no image preprocessing and can infer an optimal data representation from raw images without prior feature selection. As a result, they produce a more objective and less biased process. The performance of a convolutional neural network (CNN) is primarily affected by the hyperparameters chosen and the dataset used. A deep learning model for classifying Alzheimer's patients has been developed using transfer learning and optimized by Gorilla Troops for early diagnosis. This study proposes the A 3 C-TL-GTO framework for MRI image classification and AD detection. The A 3 C-TL-GTO is an empirical quantitative framework for accurate and automatic AD classification, developed and evaluated with the Alzheimer's Dataset (four classes of images) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). The proposed framework reduces the bias and variability of preprocessing steps and hyperparameters optimization to the classifier model and dataset used. Our strategy, evaluated on MRIs, is easily adaptable to other imaging methods. According to our findings, the proposed framework was an excellent instrument for this task, with a significant potential advantage for patient care. The ADNI dataset, an online dataset on Alzheimer's disease, was used to obtain magnetic resonance imaging (MR) brain images. The experimental results demonstrate that the proposed framework achieves 96.65% accuracy for the Alzheimer's Dataset and 96.25% accuracy for the ADNI dataset. Moreover, a better performance in terms of accuracy is demonstrated over other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The Particle Swarm Optimization technique (PSO) is widely used in practical applications due to its flexibility and strong optimization performance. However, like other metaheuristic algorithms, PSO has limitations, such as a propensity to become trapped in local minima and an uneven distribution of effort between exploration and exploitation stages. A novel local search technique called QPSOL, based on PSO is the proposed solution to mitigate these issues. QPSOL aims to increase diversity and achieve a closer balance between the exploration and exploitation phases. The QPSOL incorporates a dynamic optimization strategy to enhance the method's efficiency. Unlike the novel local search strategy, which uses a new local search approach (LSA) to break out of local optima, QPSOL employs quadratic interpolation around the optimal search agent to enhance its exploitation capability and solution accuracy. These strategies complement each other and contribute to boosting PSO's convergence efficiency while seeking to balance exploration and exploitation. The proposed method is assessed using the IEEE CEC'2021 test suite, and its efficacy is evaluated against other metaheuristics and cutting-edge algorithms to determine its trustworthiness. The optimal parameters of three PV models are determined using the proposed technique and compared to different well-established algorithms. Systematic comparisons show that QPSOL is competitive with, and often outperforms, commonly used methods in research for predicting model parameters. [ABSTRACT FROM AUTHOR]

Optimizing, regulating, and simulating photovoltaic systems are crucial for producing solar energy. The performance of PV systems is greatly affected by model parameters, which can be variable and not always easily accessible. As a result, finding these model parameters is a constant goal. Current-voltage data is needed to extract characteristics of solar modules and construct high-accuracy models for the modeling, control, and optimization of photovoltaic systems. This paper introduces an Improved Moth Flame algorithm with Local escape operators (IMFOL). The LEO technique improves the MFO algorithm's efficiency and the results' precision. Furthermore, the LEO mechanism enhances both the diversity of the population and the MFO's exploration efficiency. This keeps the exploration and exploitation rates in equilibrium. The IMFO achieved the lowest RMSE for a double diode module, 9.8252542E-04, while IMFOL and JADE had the best RMSE for a single diode module, 9.8602E-04. Additionally, IMFOL obtained 2,42521000E-03 for the Photowatt-PWP 201 model and 1,72981457E-03 for the STM6-40/36 model. The proposed method surpasses the state-of-the-art in terms of accuracy, reliability, and output. IMFOL is a reliable tool for evaluating solar cell and PV module data. [ABSTRACT FROM AUTHOR]

The growth of abnormal cells in the brain causes human brain tumors. Identifying the type of tumor is crucial for the prognosis and treatment of the patient. Data from cancer microarrays typically include fewer samples with many gene expression levels as features, reflecting the curse of dimensionality and making classifying data from microarrays challenging. In most of the examined studies, cancer classification (Malignant and benign) accuracy was examined without disclosing biological information related to the classification process. A new approach was proposed to bridge the gap between cancer classification and the interpretation of the biological studies of the genes implicated in cancer. This study aims to develop a new hybrid model for cancer classification (by using feature selection mRMRe as a key step to improve the performance of classification methods and a distributed hyperparameter optimization for gradient boosting ensemble methods). To evaluate the proposed method, NB, RF, and SVM classifiers have been chosen. In terms of the AUC, sensitivity, and specificity, the optimized CatBoost classifier performed better than the optimized XGBoost in cross-validation 5, 6, 8, and 10. With an accuracy of 0.91 ± 0.12 , the optimized CatBoost classifier is more accurate than the CatBoost classifier without optimization, which is 0.81 ±   0.24 . By using hybrid algorithms, SVM, RF, and NB automatically become more accurate. Furthermore, in terms of accuracy, SVM and RF ( 0.97 ± 0.08 ) achieve equivalent and higher classification accuracy than NB ( 0.91 ± 0.12 ). The findings of relevant biomedical studies confirm the findings of the selected genes. [ABSTRACT FROM AUTHOR]

There is a crucial need to process patient's data immediately to make a sound decision rapidly; this data has a very large size and excessive features. Recently, many cloud-based IoT healthcare systems are proposed in the literature. However, there are still several challenges associated with the processing time and overall system efficiency concerning big healthcare data. This paper introduces a novel approach for processing healthcare data and predicts useful information with the support of the use of minimum computational cost. The main objective is to accept several types of data and improve accuracy and reduce the processing time. The proposed approach uses a hybrid algorithm which will consist of two phases. The first phase aims to minimize the number of features for big data by using the Whale Optimization Algorithm as a feature selection technique. After that, the second phase performs real-time data classification by using Naïve Bayes Classifier. The proposed approach is based on fog Computing for better business agility, better security, deeper insights with privacy, and reduced operation cost. The experimental results demonstrate that the proposed approach can reduce the number of datasets features, improve the accuracy and reduce the processing time. Accuracy enhanced by average rate: 3.6% (3.34 for Diabetes, 2.94 for Heart disease, 3.77 for Heart attack prediction, and 4.15 for Sonar). Besides, it enhances the processing speed by reducing the processing time by an average rate: 8.7% (28.96 for Diabetes, 1.07 for Heart disease, 3.31 for Heart attack prediction, and 1.4 for Sonar). [ABSTRACT FROM AUTHOR]