MLP Algorithm Research Articles

Neural Network Optimization Using Hybrid Adaptive Mutation Particle Swarm Optimization and Levenberg-Marquardt in Cases of Cardiovascular Disease

Abstract. Cardiovascular disease is a condition generally characterized by the narrowing or blockage of blood vessels, which can lead to heart attacks, chest pain, or strokes. It is the leading cause of death worldwide, accounting for approximately 31% or 17.9 million deaths each year globally. Deaths caused by cardiovascular disease are projected to continue increasing until 2030, with the number of patients reaching 23.3 million. As cases of death due to cardiovascular disease become more prevalent, early detection is crucial to reduce mortality rates. Purpose: Many previous researchers have conducted studies on predicting cardiovascular disease using neural network methods. This study extends these methods by incorporating feature selection and optimization with Hybrid AMPSO-LMA. The research is designed to explore the implementation and predictive outcomes of Hybrid AMPSO-LMA in optimizing MLP for cases of cardiovascular disease. Methods/Study design/approach: The first step in conducting this research is to download the Heart Disease Dataset from Kaggle.com. The dataset is processed through preprocessing by removing duplicates and transforming the data. Then, data mining processes are carried out using the MLP algorithm optimized with Hybrid AMPSO-LMA to obtain results and conclusions. This system is designed using the Python programming language and utilizes Flask for website access in HTML. Result/Findings: The research results demonstrate that the method employed by the author successfully improves the accuracy of predicting cardiovascular disease. Predicting cardiovascular disease using the MLP algorithm yields an accuracy of 86.1%, and after optimization with Hybrid AMPSO-LMA, the accuracy increases to 86.88%. Novelty/Originality/Value: This effort will contribute to the development of a more reliable and effective cardiovascular disease prediction system, with the goal of early identification of individuals exhibiting symptoms of cardiovascular disease.

Urban Traffic Identification by Comparing Machine Learning Algorithms

The Internet of Things (IoT) applied to intelligent transport systems has become a key element for understanding the way traffic flow behaves in cities, which helps in decision-making to improve the management of the transport system by monitoring and analyzing network traffic in real time, all with the aim of daily benefiting users of the city’s road infrastructure. Traffic volume estimation in real time, with high effectiveness, may help mobility management and improve traffic flow. Moreover, machine-learning algorithms have shown effectiveness in various scientific fields and have provided a significant platform for achieving intelligent applications. Therefore, we applied various machine learning algorithms to classify the vehicular traffic status in the traffic network of two cities with more than 2 million inhabitants. It was first necessary to establish, from the attributes provided by the datasets, the object class from the LOS (Level of Services) thresholds proposed by the National Academies of Sciences, Engineering, and Medicine, for the basic segments of highways in an urban area. We then selected the attributes of interest using the Recursive Feature Elimination Method (RFE) to reduce the dimensionality of the data, and applied the DT, RF, ET, KNN, and MLP algorithms to train and classify the level of vehicular congestion, defining various volumes of training and validation data. The results show the high effectiveness of the algorithms, highlighting the MLP algorithm as the one that provides the highest effectiveness on average for the evaluated datasets, with a mean precision of 99.5%.

Secured and efficient MLP algorithm based on Sand Cat Swarm Optimization and homomorphic encryption for healthcare data

Secured and efficient MLP algorithm based on Sand Cat Swarm Optimization and homomorphic encryption for healthcare data

Novel approaches in geomechanical parameter estimation using machine learning methods and conventional well logs

ABSTRACT Today, geomechanics plays a crucial role in the oil industry, particularly in enhancing production and ensuring well stability. To achieve optimal results, accurate estimation of geomechanical parameters is essential. One of the low-cost and accurate methods for estimating geomechanical parameters is the use of intelligent methods. In this research, geomechanical parameters are estimated using conventional data logs using intelligent methods. The aim of this study is to introduce a new machine learning algorithm to estimate geomechanical parameters using conventional data logs in one of the hydrocarbon field wells in southwest Iran. In this article, the shear wave velocity and uniaxial compressive strength (UCS) were estimated using machine learning algorithms. Subsequently, other geomechanical parameters were calculated based on these estimated parameters derived from machine learning algorithms. For shear wave velocity (Vs) prediction using MLP and CLM (CNN+LSTM+MLP) algorithms, First, effective features were selected using the Auto-encoder deep learning algorithm. The selected features for Vs input into the algorithms were Vp, RHOB, CALIPER, and NPHI, and then the Vs is estimated with MLP and CLM algorithm. To evaluate the results, the model was assessed using metrics such as MAE, MAPE, MSE, RMSE, NRMSE, and R2 on the train, test, and blind datasets. The CLM algorithm consistently demonstrated superior performance across all datasets, including training, testing, and blind data sets. The R2 values for blind data were R M L P 2 = 0.8727 , R C L M 2 = 0.9274 , respectively. These outputs are crucial for estimating subsequent studies. Next, Elastic Young’s moduli and Poisson’s ratio were calculated, and the dynamic brittleness index was computed using dynamic Young’s modulus and Poisson’s ratio. Subsequently, UCS values were predicted using machine learning algorithms. Since there were 12 laboratory core samples of UCS available, UCS was initially calculated using relevant empirical relations and data from some available well logs. This process aimed to extrapolate these core results to cover the entire target depth range from 3551.072 to 3799.789 m. Subsequently, a relationship between UCS derived from well logs and laboratory results was established for the depths corresponding to where the laboratory samples were recorded. Following that, an autoencoder deep network was utilized to select effective features for predicting UCS. The selected features for UCS input into the algorithms were Vp, RHOB, and CALIPER. Subsequently, UCS was estimated using MLP and CLM algorithms. To evaluate the results, the model performance was assessed using metrics such as MAE, MAPE, MSE, RMSE, NRMSE, and R2 on the train, test, and blind datasets. Furthermore, the results were checked and evaluated using a set of statistical measures calculated for the train, test, and blind datasets, that R M L P 2 = 0.9305 , R C L M 2 = 0.9953 were obtained for blind UCS data. The results demonstrate that CLM achieves high accuracy in estimating these parameters, with deep learning algorithms showing higher determination coefficients and lower errors compared to MLP. Furthermore, UCS and tensile strength were calculated, followed by the computation of static brittleness index. The relationship between dynamic and static brittleness index was also investigated. Overall, the findings indicate that machine learning algorithms are robust and accurate methods for estimating Vs, UCS, and other geomechanical parameters using conventional logs.

Modelling thermal characteristics of cocoa butter using a feed‐forward artificial neural network based on multilayer perceptron

SummaryCocoa butter is the most important ingredient of chocolate, which determines its melting behaviour. Variations in the melting characteristics of cocoa butter can profoundly affect the performance and suitability for their industrial utilisation. Over time, researchers have been attempting to establish a logical relationship between cocoa butter's unique thermal properties and the amount of saturated to unsaturated fatty acids in mono, di and triglycerides, and fatty acids (as major components), and free fatty acids, soap, primary oxidation products, minerals, moisture, phospholipids, tocopherols, unsaponifiable matters and metals (as minor components) found in cocoa butter. In this research, the thermal behaviours of thirteen samples of cocoa butter with different origins were investigated using isothermal differential scanning calorimetry. The cocoa butters starting temperature of crystallisation, temperature of maximum heat release, temperature of completed crystallisation and the enthalpy of heat release during recrystallisation were evaluated. In addition, the chemical composition (moisture, acidity, peroxide, minerals and soap content), fatty acid and triacylglycerol composition were used to establish an MLP‐ANN with fourteen input neurons connected by two flexible, sigmoid activation function layers. The back‐propagation was used to train the artificial neural network (ANN) structure and optimise the error of prediction. The study showed that the MLP algorithm can predict the thermal behaviour of CB samples with trace error, regardless of plant growth and extract process condition.

Development of a predictive model for 1-year postoperative recovery in patients with lumbar disk herniation based on deep learning and machine learning.

The aim of this study is to develop a predictive model utilizing deep learning and machine learning techniques that will inform clinical decision-making by predicting the 1-year postoperative recovery of patients with lumbar disk herniation. The clinical data of 470 inpatients who underwent tubular microdiscectomy (TMD) between January 2018 and January 2021 were retrospectively analyzed as variables. The dataset was randomly divided into a training set (n = 329) and a test set (n = 141) using a 10-fold cross-validation technique. Various deep learning and machine learning algorithms including Random Forests, Extreme Gradient Boosting, Support Vector Machines, Extra Trees, K-Nearest Neighbors, Logistic Regression, Light Gradient Boosting Machine, and MLP (Artificial Neural Networks) were employed to develop predictive models for the recovery of patients with lumbar disk herniation 1 year after surgery. The cure rate score of lumbar JOA score 1 year after TMD was used as an outcome indicator. The primary evaluation metric was the area under the receiver operating characteristic curve (AUC), with additional measures including decision curve analysis (DCA), accuracy, sensitivity, specificity, and others. The heat map of the correlation matrix revealed low inter-feature correlation. The predictive model employing both machine learning and deep learning algorithms was constructed using 15 variables after feature engineering. Among the eight algorithms utilized, the MLP algorithm demonstrated the best performance. Our study findings demonstrate that the MLP algorithm provides superior predictive performance for the recovery of patients with lumbar disk herniation 1 year after surgery.

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases.

With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction. Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby needing the establishment of an effective CVD prediction model that can be of great significance for controlling the risk of the disease and safeguarding the physical and mental health of the population. Considering the UCI heart disease dataset as an example, initially, a single machine learning prediction model was constructed. Subsequently, six methods such as Pearson, chi-squared, RFE and LightGBM were comprehensively used for the feature screening. On the basis of the base classifiers, Soft Voting fusion and Stacking fusion was carried out to build a prediction model for cardiovascular diseases, in order to realize an early warning and disease intervention for high-risk populations. To address the data imbalance problem, the SMOTE method was adopted to process the data set, and the prediction effect of the model was analyzed using multi-dimensional and multi-indicators. In the single classifier model, the MLP algorithm performed optimally on the preprocessed heart disease dataset. After feature selection, five features eliminated. The ENSEM_SV algorithm that combines the base classifiers to determine the prediction results by soft voting on the results of the classifiers achieved the optimal value on five metrics such as Accuracy, Jaccard_Score, Hamm_Loss, AUC, etc., and the AUC value reached 0.951. The RF, ET, GBDT, and LGB algorithms were employed in the first stage sub-model composed of base classifiers. The AB algorithm was selected as the second stage model, and the ensemble algorithm ENSEM_ST, obtained by Stacking fusion of the two stages exhibited the best performance on 7 indicators such as Accuracy, Sensitivity, F1_Score, Mathew_Corrcoef, etc., and the AUC reached 0.952. Furthermore, a comparison of the algorithms' classification effects based on different training set occupancy was carried out. The results indicated that the prediction performance of both the fusion models was better than the single models, and the overall effect of ENSEM_ST fusion was stronger than the ENSEM_SV fusion. The fusion model established in this study improved the overall classification accuracy and stability of the model to a significant extent. It has a good application value in the predictive analysis of CVD diagnosis, and can provide a valuable reference in the disease diagnosis and intervention strategies.

#88 Establishment of machine learning-based risk prediction model for acute kidney injury after acute myocardial infarction

Abstract Background and Aims Acute kidney injury (AKI) is a common complication of acute myocardial infarction (AMI) with high morbidity, mortality and lack of effective treatment, so prevention is particularly important. This study intends to use machine learning to establish a precise prediction model for AKI after AMI. Method AMI patients were consecutively collected from July 2011 to December 2016 in Beijing Anzhen Hospital, Capital Medical University. First, SelectFromModel and Lasso regression model were used to select features. A predictive model (Model A) was then created using a multivariate logistic regression model in the training set and validated in the test set. At the same time, the prediction model (Model B) is created by machine learning algorithm in the training set. The process of model construction and evaluation is implemented by Python. The algorithm includes MLP, SVM, KNN and SimpleRNN, from which the model with the largest area under the ROC curve (Model B) is selected and verified in the test set. DeLong method was used to compare the model B with model A to compare whether the area under the ROC curve was better than multivariate logistic regression model and select the best model. Results A total of 6014 AMI patients were included in this study, 70% were randomly selected as the training set, and the remaining 30% were used as the test set. Males comprised 80.5% of the total population with a mean age of 58.4 ± 11.7 years. The incidence of AKI in the overall population was 11.2% (674/6014) (Fig. 1). A total of 12 important characteristics were included in the model, including the number of myocardial infarctions, ST-segment elevation myocardial infarction, ventricular tachycardia, third-degree atrioventricular block, decompensated heart failure at admission, admission serum creatinine value, admission urea nitrogen value, admission CK-MB peak value, whether diuretics were used, maximum daily dose of diuretics, days of diuretic use, and whether statins were used. Logistic regression analysis resulted in an area under the ROC curve of 0.80 (95% CI, 0.76-0.84) in the test set (Fig. 2). The models were constructed by MLP, SVM, KNN and SimpleRNN algorithms, respectively, and validated in the test set to calculate the area under the ROC curve of each model in the test set (Fig. 3), and finally the model constructed by MLP algorithm was selected as model B, and its area under the ROC curve was 0.82 (95% CI, 0.78–0.85). The area under the ROC curve of the two models was compared at p=0.363, but the machine learning algorithm constructed models with higher absolute values (Fig. 4). Conclusion The prediction model of AKI risk after AMI constructed based on machine learning is similar to that constructed by logistic regression analysis in terms of prediction ability, but the model constructed by machine learning algorithm has a better trend, indicating that the machine learning algorithm may improve the prediction ability of prediction model and provide an effective tool for early identification of these high-risk patients in clinical practice, early preventive measures, and reduction of morbidity.

A machine learning approach to evaluate coastal risks related to extreme weather events in the Veneto region (Italy)

A significant and unprecedented increase of temperature has been recorded worldwide during the last decades, leading to the occurrence of numerous extreme events. Coastal areas, with their high population density, interconnected economic activities, fragile ecosystems, are particularly vulnerable to climate change impacts. These impacts can be intensified by the interactions of multiple hazards which operate at different spatio-temporal scales and affect exposure and vulnerability patterns. An integrated approach is here proposed to assess the relationship between risk factors and to evaluate the multiplicity of impacts that may affect the coastline. A new path to tackle these multi-risk events is offered by ML algorithms to effectively handle vast amounts of heterogenous data, and model complex non-linear relationships between multiple factors and feedback mechanisms. To assess impacts caused by extreme events (storm surges, extreme precipitation, wind events) in the Veneto coastal municipalities, a ML approach was developed to understand connections between atmospheric and marine hazards and impacts recorded by the Veneto region emergency archive during the 2009–2019 timeframe, identifying the most influencing factors triggering multiple risks. Additionally, the coastal municipalities were clustered considering the intrinsic relationships between impact occurrences, exposure and vulnerability features. Several algorithms were compared to estimate daily risk of impacts to occur providing hazards, exposure and vulnerability information. The MLP algorithm showed satisfactory performances (weighted-F1-score of 0.94) to estimate the relative importance of input features. The proposed algorithm was designed as support tool to increase the understanding of impacts’ occurrence in coastal areas, thus helping the adaptation planning process.

Optimal Feature Selection in Diabetes Classification Using the MLP Algorithm

Optimal Feature Selection in Diabetes Classification Using the MLP Algorithm

Mlp4green: A Binary Classification Approach Specifically for Green Odor.

Fresh green leaves give off a smell known as "green odor." It has antibacterial qualities and can be used to attract or repel insects. However, a common method for evaluating green odor molecules has never existed. Machine learning techniques are widely used in research to forecast molecular attributes for binary classification. In this work, the green odor molecules were first trained and learned using machine learning methods, and then clustering analysis and molecular docking were performed to further explore their molecular characteristics and mechanisms of action. For comparison, four algorithmic models were employed, MLP performed the best in all metrics, including Accuracy, Precision, Average Precision, Matthews coefficient, and Area under curve. We determined by difference analysis that, in comparison to non-green odor molecules, green odor molecules have a lower molecular mass and fewer electrons. Based on the MLP algorithm, we constructed a binary classification prediction website for green odors. The first application of deep learning techniques to the study of green odor molecules can be seen as a signal of a new era in which green odor research has advanced into intelligence and standardization.

An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments.

The BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non-line-of-sight (NLOS) signals. Deep learning (DL) methods have shown strong capabilities in detecting complex and variable NLOS signals. However, these methods still suffer from the following limitations. On the one hand, supervised learning methods require labeled samples for learning, which inevitably encounters the bottleneck of difficulty in constructing databases with a large number of labels. On the other hand, the collected data tend to have varying degrees of noise, leading to low accuracy and poor generalization performance of the detection model, especially when the environment around the receiver changes. In this article, we propose a novel deep neural architecture named convolutional denoising autoencoder network (CDAENet) to detect NLOS in urban forest environments. Specifically, we first design a denoising autoencoder based on unsupervised DL to reduce the long time series signal dimension and extract the deep features of the data. Meanwhile, denoising autoencoders improve the model's robustness in identifying noisy data by introducing a certain amount of noise into the input data. Then, an MLP algorithm is used to identify the non-linearity of the BDS signal. Finally, the performance of the proposed CDAENet model is validated on a real urban forest dataset. The experimental results show that the satellite detection accuracy of our proposed algorithm is more than 95%, which is about an 8% improvement over existing machine-learning-based methods and about 3% improvement over deep-learning-based approaches.

Lung Cancer Detection Using Wavelet Transform with Deep Learning Algorithms

Lung cancer is a leading cause of mortality among all cancer-related illnesses. The primary method of diagnosis is conducting a scan examination of the patient’s lungs. The scanning analysis can encompass X-ray, CT scan, or MRI techniques. The automated categorization of lung cancer poses a formidable challenge, primarily because of the diverse imaging techniques employed to capture images of a patient’s lungs. Image processing and machine learning methodologies have demonstrated significant promise in the identification and categorization of lung cancer. We present a very efficient model in this study that accurately detects lung cancer and categorizes it as either benign or malignant. The initial phase involves the execution of many procedures to carry out the picture preprocessing process. During the second stage, the image undergoes Wavelet Transform to divide it into three levels. This division allows for the extraction of distinct properties from each level. The third step involves employing an auto-encoder technique to effectively decrease dimensions and eliminate noise, while also identifying any anomalies within the recovered features. The MLP algorithm was employed in the final section. The suggested method underwent testing on a total of 9541 photos, which were categorized into two distinct types: benign, consisting of 4044 images, and malignant, consisting of 5497 images. The proposed approach attained a remarkable accuracy rate of 100%.

Optimizing Machine Learning Models in Human Activity Recognition with the WISDM Dataset

Human Activity Recognition (HAR) is a technology with significant potential, utilizing data from various devices like smartphones and cameras. It finds applications in daily activities such as driving, cleaning, and gaming, involving fundamental movements like standing, sitting, jogging, and typing. Accurate identification of these actions is crucial for effective human-computer interaction systems. This work incorporates a HAR module to extract valuable insights from data signals. It employs Machine Learning (ML) models to automatically detect human activities using raw data from Internet of Things wearable sensors, including innovative combinations like Adagrad and ELU within the MLP algorithm. The ML models' performance is evaluated using statistical metrics such as accuracy, precision, recall, and f1-score, and comparisons are made with existing models.

An Indoor Tags Position Perception Method Based on GWO–MLP Algorithm for RFID Robot

This paper proposes a tag position perception method for scenarios such as package retrieval in unmanned warehouses and book management in libraries. This method can accurately predict the distribution of tag space positions in real–time during RFID robot inventory. Firstly, the signal strength (RSSI) and speed of identification (SoI) are used as features. The grey wolf optimization multi–layer perceptron neural network model (GWO–MLP) is employed to predict the distance of tag groups. Secondly, a tag orientation prediction algorithm is designed to estimate the orientation of the tag groups. Finally, the periodicity of the phase is determined by the characteristic of RSSI attenuation as the tag–to–antenna distance increases, solving the problem of position ambiguity caused by phase periodicity. The experiment has shown that this method achieves a high accuracy rate of 96.67% and 97% in predicting the distance and orientation of tag groups, respectively. The average error in distance perception for the single tag is less than 3 cm, enabling precise perception of RFID tag positions. This method facilitates more efficient operation management and accurate item traceability.

Research on Earthquake Data Prediction Method Based on DIN–MLP Algorithm

This paper proposes a recommendation algorithm that combines MLP with the DIN model and conducts simulation experiments in the field of earthquake missing data prediction. The original DIN model may face challenges and weaknesses in earthquake monitoring data prediction, such as a limited capability in handling data loss or anomalies in seismic monitoring stations. To overcome these issues, we innovatively treat seismic monitoring stations as special users and historical data patterns as recommended items. Based on the DIN model, we implement data processing and prediction for seismic monitoring stations and introduce an attention mechanism based on MLP neural networks in the model, while leveraging the prior knowledge base to enhance predictive capabilities. Compared to the original DIN model, our proposed approach not only recommends sequence combinations that meet the demands of seismic monitoring stations but also enhances the matching between station behavior attributes and historical data characteristics, thereby significantly improving prediction accuracy. To validate the effectiveness of our method, we conducted comparative experiments. The results show that the GAUC achieved by the DIN–MLP model reaches 0.69, which is an 11 percent point improvement over the original DIN model. This highlights the remarkable advantages of our algorithm in earthquake missing data prediction. Furthermore, our research reveals the potential of the DIN–MLP algorithm in practical applications, providing more accurate data processing and time series combination recommendations for the field of earthquake monitoring stations, thus contributing to the improvement of monitoring efficiency and accuracy.

Classification of Mammography Images using Bag of Features Model

The BoF model is a tool widely used in the fields of classification and image search, itspopularity is largely based on its simplicity. As part of our work we will be interested in an imageclassification mammography based on the BOF model with SVM algorithm application and the SIFTdescriptor. These algorithms show performance, the results have been compared with other algorithms. Inthe first phase, the SVM was used to compare the result with the MLP. In the same work, two SIFT andORB descriptors were used. To assess the effectiveness of the proposed work, the classification rate(Acouracy) and the precision rate were calculated. The best classification rates are obtained by applyingthe MLP algorithm and using the SIFT descriptor on the base images (Ultra Sounde Brest Images Dataset)with a rate of 86% a small increase compared to SVM with a rate equal to 84%. Accuracy rate with 80%for MLP and 74% for SVM respectively.

Research on Computer Network Security Protection Technology Incorporating Full Convolutional Networks

Abstract To strengthen networks’ security performance, here pose suggests a fused full convolutional approach to monitoring computer networks. This paper first analyzes the various performances of the full convolutional model for error problems rate, error reporting, and monitoring effects on various attack categories then proposes a network monitoring scheme for the full convolutional model and introduces the workflow of the full convolutional model in computer network security protection. In terms of accuracy, the full convolutional error rate of the blueprint meets the requirements rate of 96.8%, which is better than the classical network models of Lenet-5 and AlexNet, with 86.2% and 91.6%. The false alarm rate is only 2.37%, which is lower than the 5.74% MLP algorithm and 4.23% SVM algorithm. By comparison, the full convolutional calculation method is more efficient than other calculation methods in the detection rate of attack types such as Dos, Probe, U2R, and R2L. Therefore, the calculation method here is well adapted to computer network security protection requirements.

A DEEP NEURAL NETWORK FOR BODY PART-BASED CEREBRAL PALSY PREDICTION IN INFANTS TO DETECT ABNORMAL MOVEMENTS

Cerebral palsy is a neurological disorder that can be diagnosed as early as infancy. Early diagnosis and intervention can significantly improve outcomes for infants with cerebral palsy. In this study, we propose a method for predicting cerebral palsy in infants using pose-based feature sets and velocity information, and compare its performance with a Convolutional Neural Network (CNN) approach.A reliable dataset containing pose-based feature sets and velocity information related to the limbs of infants is collected and pre-processed by handling missing values, normalizing the feature sets and velocity information, and splitting the data into training and testing sets. Relevant features, such as joint orientations, displacements, and velocities in the X and Y directions, are extracted from the pose-based feature sets and velocity information.An MLP algorithm is trained using the preprocessed and normalized feature sets as inputs and the corresponding cerebral palsy diagnosis as the target output. Supervised learning is used to optimize the models parameters and weights. The performance of the trained MLP model is evaluated using various evaluation metrics, and the results show high accuracy in predicting cerebral palsy in infants.Next, a CNN approach is implemented for comparison. The pose-based feature sets and velocity information are used to train the CNN model, which consists of convolutional layers for feature extraction and pooling layers for spatial downsampling. The output from the CNN model is then fed into fully connected layers for classification. The performance of the CNN model is also evaluated using the same evaluation metrics as the MLP model.The results of the comparative analysis show that the MLP model achieves high accuracy in predicting cerebral palsy in infants, outperforming the CNN model. The MLP models accuracy compared to the CNN model. The interpretations of the MLP models predictions are validated using additional validation datasets or by comparing with existing diagnostic methods for cerebral palsy.

Machine Learning Modelling of Effective Cumin (Cuminnum cyminum L.) Genotype for Antipyretic Property Based on Secondary Metabolites

Cumin is a flowering plant that has been used as a spice in multicuisine. It has various health benefits such as weight loss, cholesterol control, anti-diabetes, and more. It also consists of dietary fibers, vitamin B, vitamin E, and minerals, especially iron and magnesium. The present study was conducted for the effective implementation of two tasks, the prediction of cumin genotype in which the inputs were total phenolic, flavonoid, and antioxidant content and the classification of anti-pyretic activity. MLP and other ML algorithm simulations were committed to executing the tasks of prediction and classification. The effectiveness of the proposed model was compared with the various classification and regression techniques like SVM, Naïve Bayes, KNN, Logistic Regression, and Decision Tree. Along with the mentioned task, this paper also exhibits the implementation of feature selection techniques like PCA in ML-based prediction and classification. It was found that MLP with PCA has outperformed other algorithms.