MLP Classifier Research Articles

A Decision Support System for Machine Learning-Based Determination of Zinc Deficiency: A Study in Adolescent Patients

Background: Over the past three years, zinc deficiency among adolescents has varied based on region and access to healthcare. Globally, zinc deficiency affects approximately 2 billion people, leading to serious issues such as immune problems and growth delays, particularly in developing countries. In the U.S., around 10% of adolescents experienced zinc deficiency in 2021, with a higher prevalence among teenage girls. In Europe, deficiency rates are generally low but can be significant in Eastern Europe and Central Asia. In Asia, particularly in rural and low-income areas, deficiency rates range from 20 - 30%. In Turkey, the prevalence is high due to poor nutrition. Objectives: This study aimed to develop a machine learning-based decision support system to determine zinc deficiency in children and adolescents aged 10 - 18 years. Methods: This machine learning-based study was conducted with 370 adolescents aged 10 - 18 years to assess their zinc deficiency. The dataset consists of 8 feature vectors and an output vector. The machine learning methods used in the analysis include Logistic Regression, Naive Bayes, Decision Tree (CART), K-NN (K-Nearest Neighbors), SVM (Support Vector Machine), Gradient Boosting Classifier, AdaBoost Classifier, Bagging Classifier, Random Forest Classifier, MLP Classifier (Multilayer Perceptron), and XGB Classifier (XGBoost Classifier). Evaluation metrics such as accuracy, precision, recall, and F1 score were used to assess the performance of these methods. Including specific values for these metrics, such as "SVM achieved 94.6% accuracy," would allow readers to quickly compare the effectiveness of the models. Different metrics serve various purposes: Accuracy provides an overall view of performance, precision and recall highlight specific aspects, and the F1 score balances precision and recall. Results: The mean age of the patients in the dataset was 13.79 ± 1.18 years. Of the children, 64.32% (n = 238) were female and 35.68% (n = 132) were male. It was found that 62.7% (n = 232) of the children had low zinc levels, while 37.3% (n = 138) did not require zinc supplementation. Thirteen different machine learning methods were applied to a 70% training and 30% testing set. As a result, the SVM method provided the most successful outcome with 94.6% accuracy. Implementing the SVM-based system in pediatric clinics could improve efficiency and patient care by automatically detecting high-risk zinc deficiency patients based on lab results, providing early intervention alerts for faster treatment, and improving health outcomes. Highlighting these practical applications could increase the study’s appeal to healthcare professionals by demonstrating its real-world benefits. Providing detailed information on these applications would enhance the study’s clarity and practical value, making it more valuable for researchers and healthcare providers interested in AI tools for adolescent health. Conclusions: This study concluded that machine learning methods can effectively determine zinc deficiency in children. The SVM method demonstrated superior classification performance compared to the other methods. An SVM-based decision support system could be integrated into pediatric outpatient clinics to enhance diagnostic accuracy and patient care.

Emotion Classification from Speech Waveform Using Machine Learning and Deep Learning Techniques

Emotions play a key role in determining the human mental state and indirectly express an individual’s well- being. A speech emotion recognition system can extract a person’s emotions from his/her speech inputs. There are some universal emotions such as anger, disgust, fear, happiness, pleasantness, sadness and neutral. These emotions are of significance especially in a situation like the Covid pandemic, when the aged or sick are vulnerable to depression. In the current paper, we examined various classification models with finite computational strength and resources in order to determine the emotion of a person from his/her speech. Speech prosodic features like pitch, loudness, and tone of speech, and work spectral features such as Mel Frequency Capstral Coefficients (MFCCs) of the voice were used to analyze the emotions of a person. Although sequence to sequence state of the art models for speech detection that offer high levels of accuracy and precision are currently in use, the computational needs of such approaches are high and inefficient. Therefore, in this work, we emphasised analysis and comparison of different classification algorithms such as multi layer perceptron, decision tree, support vector machine, and deep neural networks such as convolutional neural network and long short term memory. Given an audio file, the emotions that were exhibited by the speaker were recognized using machine learning and deep learning techniques. A comparative study was performed to identify the most appropriate algorithms that could be used to recognize emotions. Based on the experiment results, the MLP classifier and convolutional neural network model offered better accuracy with smaller variations when compared with other models used for the study.

Predicting business bankruptcy: A comparative analysis with machine learning models

Business failure prediction has become crucially important for today's firms, enabling them to reduce financial risks and make informed decisions. This study uses a dataset of 6819 companies and 96 financial and macroeconomic variables to present a comparative analysis of machine learning (ML) models for predicting corporate bankruptcies. Behind this research is to improve the accuracy of bankruptcy prediction, which can help companies make more informed decisions and reduce financial risks. This study aims to evaluate the effectiveness of 16 ML algorithms in terms of accuracy, sensitivity, and other relevant metrics. The work uses methodologies that include data collection and cleaning, exploratory data analysis, model preprocessing and training, and model performance evaluation. Data preprocessing and hyperparameter optimization techniques were used to improve model performance. The evaluated algorithms include Classifiers such as Stacking Classifier (SCC), Randomized Search Classifier (RCV), Historical Gradient Boosting Classifier (HGBC), MLP Classifier (MLPC), K-Neighbors Classifier (KNC), Decision Tree Classifier (DTC), XGBRF Classifier (XGBRFC), Support Vector Classifier (SVC), Logistic Regression Classifier (LR), Linear SVC Classifier (LSVC). With an accuracy of 97.63 %, recall of 97.63 %, and F1-score of 97.63 %, the results show that the SCC algorithm was the best. Other models, such as RCV and DTC, also showed good results, with accuracies above 97 %. However, models such as PAC and BNB had lower performance and accuracy below 90 %. Finally, this study compares the results of ML models in predicting business failures and highlights their effectiveness. The SCC algorithm is considered the most suitable model for this task, as it suggests that it can help economic actors make more informed decisions and reduce financial risks in the context of firms.

Fake News Detection Using Machine Learning

Abstract: The pervasive spread of misinformation in today's digital environment presents a daunting problem, influencing public opinion and possibly causing unfavorable social consequences. This paper conducts a thorough investigation into the effectiveness includes a broad variety of false information in text, images, and video formats. Our study carefully assesses SVM, random forest, MLP, and naive Bayes classifiers using a large and painstakingly selected dataset. We provide a classifier of voting to improve accuracy and consistency by integrating the forecasts from these several models. Voting Classifier's outstanding performance, attaining a perfect accuracy rate and highlighting the ensemble approach's inherent robustness. The research emphasizes the vital ensemble methods' key part in strengthening the foundation the identification of bogus news systems and providing a strong barrier against the unrelenting propagation of fake information.

Prediction of geogenic source of groundwater fluoride contamination in Indian states: A comparative study of different supervised machine learning algorithms.

India has been dealing with fluoride contamination of groundwater for the past few decades. Long-term exposure of fluoride can cause skeletal and dental fluorosis. Therefore, an in-depth exploration of fluoride concentrations in different parts of India is desirable. This work employs machine learning algorithms to analyze the fluoride concentrations in five major affected Indian states (Andhra Pradesh, Rajasthan, Tamil Nadu, Telangana and West Bengal). A correlation matrix was used to identify appropriate predictor variables for fluoride prediction. The various algorithms used for predictions included K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector classifier (SVC), Gaussian NB, MLP classifier, decision tree classifier, gradient boosting classifier, voting classifier soft and voting classifier hard. The performance of these models is assessed over accuracy, precision, recall and error rate and receiver operating curve. As the dataset was skewed, the performance of models was evaluated before and after resampling. Analysis of results indicates that the RF model is the best model for predicting fluoride contamination in groundwater in Indian states.

Diagnosis of Multiple Sclerosis Lesion using Deep Learning Models

Exploring the identification of Multiple Sclerosis (MS) lesions involves leveraging diverse machine learning classifiers. Using Magnetic Resonance Imaging (MRI) scans, the study aims to detect and characterize these lesions, evaluating their attributes, progression stages, and the pivotal role of Artificial Intelligence (AI) in diagnosis. The focus is on analyzing automated detection algorithms, particularly Deep Learning techniques. Through comprehensive assessment, various classifiers including MLP Classifier, Random Forest (RF), Support Vector Machine (SVM), and DL are evaluated using metrics like precision, recall, F1-score, and accuracy. The DL classifier stands out, achieving remarkable precision (99%), recall (99%), and overall accuracy (99.5%). Comparative analysis confirms its superiority, reinforcing its efficacy over alternative methods. The research underscores the DL model's potential in generalizing to new samples due to its robustness and precision. This study significantly advances automated MS lesion detection, highlighting the promise of AI-based methodologies in medical image analysis.

LCASPMDA: a computational model for predicting potential microbe-drug associations based on learnable graph convolutional attention networks and self-paced iterative sampling ensemble

IntroductionNumerous studies show that microbes in the human body are very closely linked to the human host and can affect the human host by modulating the efficacy and toxicity of drugs. However, discovering potential microbe-drug associations through traditional wet labs is expensive and time-consuming, hence, it is important and necessary to develop effective computational models to detect possible microbe-drug associations.MethodsIn this manuscript, we proposed a new prediction model named LCASPMDA by combining the learnable graph convolutional attention network and the self-paced iterative sampling ensemble strategy to infer latent microbe-drug associations. In LCASPMDA, we first constructed a heterogeneous network based on newly downloaded known microbe-drug associations. Then, we adopted the learnable graph convolutional attention network to learn the hidden features of nodes in the heterogeneous network. After that, we utilized the self-paced iterative sampling ensemble strategy to select the most informative negative samples to train the Multi-Layer Perceptron classifier and put the newly-extracted hidden features into the trained MLP classifier to infer possible microbe-drug associations.Results and discussionIntensive experimental results on two different public databases including the MDAD and the aBiofilm showed that LCASPMDA could achieve better performance than state-of-the-art baseline methods in microbe-drug association prediction.

E-CLEAP: An ensemble learning model for efficient and accurate identification of antimicrobial peptides.

With the increasing problem of antimicrobial drug resistance, the search for new antimicrobial agents has become a crucial task in the field of medicine. Antimicrobial peptides, as a class of naturally occurring antimicrobial agents, possess broad-spectrum antimicrobial activity and lower risk of resistance development. However, traditional screening methods for antimicrobial peptides are inefficient, necessitating the development of an efficient screening model. In this study, we aimed to develop an ensemble learning model for the identification of antimicrobial peptides, named E-CLEAP, based on the Multilayer Perceptron Classifier (MLP Classifier). By considering multiple features, including amino acid composition (AAC) and pseudo amino acid composition (PseAAC) of antimicrobial peptides, we aimed to improve the accuracy and generalization ability of the identification process. To validate the superiority of our model, we employed five-fold cross-validation and compared it with other commonly used methods for antimicrobial peptide identification. In the experimental results on an independent test set, E-CLEAP achieved accuracies of 97.33% and 84% for the AAC and PseAAC features, respectively. The results demonstrated that our model outperformed other methods in all evaluation metrics. The findings of this study highlight the potential of the E-CLEAP model in enhancing the efficiency and accuracy of antimicrobial peptide screening, which holds significant implications for drug development, disease treatment, and biotechnology advancement. Future research can further optimize the model by incorporating additional features and information, as well as validating its reliability on larger datasets and in real-world environments. The source code and all datasets are publicly available at https://github.com/Wangsicheng52/E-CLEAP.

A Monitoring, Evaluation, and Prediction System for Slight Water Stress in Citrus Seedlings Based on an Improved Multilayer Perceptron Model

To address the lack of effective monitoring, evaluation, and prediction methods for water stress in citrus seedlings, we conducted 10 sets of water stress gradient experiments. Based on the experimental dataset, we constructed, trained, and improved an MLP classification model for citrus seedling water stress. In addition, we developed a monitoring, evaluation, and prediction system based on this model. The experiments demonstrated that 7 days of slight water stress can induce changes in overall root wilting and growth stagnation, and the chlorophyll content in the leaves can decrease by up to 11.78%. Furthermore, the optimal VWC for seedlings was [45%, 50%], the boundary of drought was [20%, 25%], and the boundary of waterlogging was [50%, 55%]. We validated the effectiveness of the system in assessing the growth status of seedlings over the past 7 days and predicting it after 7 days through testing sets and experiments on slight water stress. We found that the system achieved non-destructive remote monitoring, evaluation, and prediction of slight water stress in citrus seedlings, thus enhancing seedling quality. These research findings provide valuable insights into water stress management in citrus seedlings and other crops.

Applied of color image processing system to detect plant disease using clustering algorithms

In recent times, after the changing of weather conditions and the pollution of water resources and air, the green cover of the earth has got many infections and the agricultural crop started to suffer many diseases. These diseases are able to catch and decide the suitable medicine in many ways. Maybe one of the most important ways is to check the change of plants' leaves. Plant leave disease detection uses several methods like image processing and deep learning. All of these methods suffer from the high similarity of some diseases, the different sizes of leaves, and the colors of them. Which caused the lower accuracy of detecting the right disease. Neural network methods were used too, but needed a higher computation time and more computation power. All of above provides image processing techniques superior advantages over other techniques. Other techniques, such those employing KNN, MLP, and Gaussian classifiers, provide accuracy that is lower than that of SVM techniques when using applications.

Assessment of pulmonary embolism probability using a machine learning model

Aim. To develop and validate a machine learning model designed to identify suspected pulmonary embolism (PE) based on various clinical features from electronic health records (EHRs) of out- and inpatients.Material and methods. Data from 19730 patients from 7 Russian regions were taken for analysis. EHR data were analyzed for the period from March 21, 2007 to February 4, 2022. Complaints, clinical and laboratory data, and concomitant diseases were used as diagnostic signs. PE was diagnosed in 1379 patients. Diagnosis of PE was based on ICD-10 codes. Seven machine learning algorithms were applied to diagnose pulmonary embolism: XGBoost, LightGBM, CatBoost, Logistic Regression, MLP Classifier, Random Forest Classifier, Gradient Boosting Classifier.Results. The Gradient Boosting Classifier-based model was selected for further prospective testing with the sensitivity of 0,899 (95% confidence interval (CI), 0,864-0,932), specificity of 0,875 (95% CI, 0,863-0,86), area under the ROC curve of 0,952 (95% CI, 0,938-0,964). The following signs had the greatest prediction value: cough, respiratory disorders, blood creatinine, body temperature, general weakness, heart rate, respiratory rate, edema, antihypertensive therapy, saturation and age.Conclusion. The model is designed for the initial encounter of patients with complaints and suspected PE, regardless of the type of care.

Applying Common Spatial Pattern and Convolutional Neural Network to Classify Movements via EEG Signals.

Developing an electroencephalography (EEG)-based brain-computer interface (BCI) system is crucial to enhancing the control of external prostheses by accurately distinguishing various movements through brain signals. This innovation can provide comfortable circumstances for the populace who have movement disabilities. This study combined the most prospering methods used in BCI systems, including one-versus-rest common spatial pattern (OVR-CSP) and convolutional neural network (CNN), to automatically extract features and classify eight different movements of the shoulder, wrist, and elbow via EEG signals. The number of subjects who participated in the experiment was 10, and their EEG signals were recorded while performing movements at fast and slow speeds. We used preprocessing techniques before transforming EEG signals into another space by OVR-CSP, followed by sending signals into the CNN architecture consisting of four convolutional layers. Moreover, we extracted feature vectors after applying OVR-CSP and considered them as inputs to KNN, SVM, and MLP classifiers. Then, the performance of these classifiers was compared with the CNN method. The results demonstrated that the classification of eight movements using the proposed CNN architecture obtained an average accuracy of 97.65% for slow movements and 96.25% for fast movements in the subject-independent model. This method outperformed other classifiers with a substantial difference; ergo, it can be useful in improving BCI systems for better control of prostheses.

A Comparative Analysis of Machine Learning and Deep Learning Approaches for Prediction of Chronic Kidney Disease Progression

Chronic kidney disease is a significant health problem worldwide that affects millions of people, and early detection of this disease is crucial for successful treatment and improved patient outcomes. In this research paper, we conducted a comprehensive comparative analysis of several machine learning algorithms, including logistic regression, Gaussian Naive Bayes, Bernoulli Naive Bayes, Support Vector Machine, X Gradient Boosting, Decision Tree Classifier, Grid Search CV, Random Forest Classifier, AdaBoost Classifier, Gradient Boosting Classifier, XgBoost, Cat Boost Classifier, Extra Trees Classifier, KNN, MLP Classifier, Stochastic gradient descent, and Artificial Neural Network, for the prediction of kidney disease. In this study, a dataset of patient records was utilized, where each record consisted of twenty-five clinical features, including hypertension, blood pressure, diabetes mellitus, appetite and blood urea. The results of our analysis showed that Artificial Neural Network (ANN) outperformed other machine learning algorithms with a maximum accuracy of 100%, while Gaussian Naive Bayes had the lowest accuracy of 94.0%. This suggests that ANN can provide accurate and reliable predictions for kidney disease. The comparative analysis of these algorithms provides valuable insights into their strengths and weaknesses, which can help clinicians choose the most appropriate algorithm for their specific requirements.

Classification of Early Breast Cancer using Convolutional Neural Networks

Breast cancer is a life-threatening disease that impacts millions of people worldwide, necessitating heightened awareness and effective early detection strategies. Current methods for determining the presence and type of breast cancer in a clinical breast exam conducted by healthcare providers may be inaccurate, imprecise, and prone to error. The goal of this research project is to offer a second opinion for physicians to predict whether or not a patient has early onset breast cancer through a machine learning model developed from an image dataset, to significantly reduce the error in breast cancer staging, making the process more efficient in healthcare. Early detection is crucial for successful treatments of breast cancer, as treatment options in late-stage diagnosis of breast cancer can have a much worse prognosis. In the US, 240,000 cases of breast cancer are diagnosed per year in both men and women with a mortality rate of approximately 42,000 per year. [1] To approach this problem, I have tested an MLP Classifier, Logistic Regression, Ridge Classifier, Random Forest Classifier, Decision Tree Classifier, Support Vector Classifier, and trained a Convolutional Neural Network to compare various results and determine the best accuracy. The Convolutional Neural Network yielded impressive outcomes, reaching up to 79% testing accuracy and 98% training accuracy. The final model exhibits the capability to identify early signs of breast cancer and differentiate between malignant and benign tumours with relatively high accuracy showing the potential of AI in combination with medical imaging that can assist medical staff in diagnosis.

Crow search algorithm with deep transfer learning driven skin lesion detection on dermoscopic images

The early diagnosis of skin cancer is of paramount importance for effective patient treatment. Dermoscopy, a non-surgical technique, utilizes precise equipment to examine the skin and plays a crucial role in identifying specific features and patterns that may indicate the presence of skin carcinoma. In recent times, machine learning (ML) methods have been developed to recognize and classify dermoscopic images as either malignant or benign. Deep learning (DL) systems, including Convolutional Neural Networks (CNNs), as well as various ML models like Random Forest (RF) classifiers and Support Vector Machine (SVM), are employed to extract relevant features from these images. This study introduces the Crow Search Algorithm with Deep Transfer Learning Driven Skin Lesion Detection on Dermoscopic Images (CSADTL-SLD) technique. The CSADTL-SLD method starts with the application of a median filter (MF) to remove noise from the images and utilizes the GoogleNet model for feature extraction. GoogleNet is well-regarded for its capacity to capture intricate and meaningful patterns within the data, which are essential for accurate lesion characterization. Furthermore, the CSADTL-SLD technique applies the Crow Search Algorithm (CSA) for parameter tuning of the GoogleNet model. After feature selection, the system employs the MLP classification model for precise lesion categorization. The comprehensive results of this research demonstrate the superiority of the CSADTL-SLD algorithm, showing significant enhancements in skin lesion detection accuracy and robustness when compared to existing methods. This approach holds promise as an effective solution for automating the detection and classification of skin lesions in dermoscopic images.

Classification of yoga, meditation, combined yoga–meditation EEG signals using L-SVM, KNN, and MLP classifiers

Classification of yoga, meditation, combined yoga–meditation EEG signals using L-SVM, KNN, and MLP classifiers

Faults detection and diagnosis of PV systems based on machine learning approach using random forest classifier

Accurate and reliable fault detection procedures are crucial for optimizing photovoltaic (PV) system performance. Establishing a trustworthy PV array model is the primary step and a vital tool for monitoring and diagnosing PV systems. This paper outlines a two-step approach for creating a reliable PV array model and implementing a fault detection procedure using Random Forest Classifiers (RFCs).Firstly, we extracted the five unknown parameters of the one-diode model (ODM) by combining the current–voltage translation method to predict the reference curve and employing the modified grey wolf optimization (MGWO) algorithm. In the second step, we simulated the PV array to obtain maximum power point (MPP) coordinates and construct operational databases through co-simulations in PSIM/MATLAB. We developed two RFCs: one for fault detection (a binary classifier) and another for fault diagnosis (a multiclass classifier).Our results confirmed the accuracy of the PV array modeling approach. We achieved a root mean square error (RMSE) value of 0.0122 for the ODM parameter extraction and RMSEs lower than 0.3 in dynamic PV array output current simulations under cloudy conditions. Regarding the fault detection procedure, our results demonstrate exceptional classification accuracy rates of 99.4% for both fault detection and diagnosis, surpassing other tested models like Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Neural Networks (MLP Classifier), Decision Trees (DT), and Stochastic Gradient Descent (SGDC).

Efficient lung cancer detection using computational intelligence and ensemble learning.

Lung cancer emerges as a major factor in cancer-related fatalities in the current generation, and it is predicted to continue having a long-term impact. Detecting symptoms early becomes crucial for effective treatment, underscoring innovative therapy's necessity. Many researchers have conducted extensive work in this area, yet challenges such as high false-positive rates and achieving high accuracy in detection continue to complicate accurate diagnosis. In this research, we aim to develop an ecologically considerate lung cancer therapy prototype model that maximizes resource utilization by leveraging recent advancements in computational intelligence. We also propose an Internet of Medical Things (IoMT)-based, consumer-focused integrated framework to implement the suggested approach, providing patients with appropriate care. Our proposed method employs Logistic Regression, MLP Classifier, Gaussian NB Classifier, and Intelligent Feature Selection using K-Means and Fuzzy Logic to enhance detection procedures in lung cancer dataset. Additionally, ensemble learning is incorporated through a voting classifier. The proposed model's effectiveness is improved through hyperparameter tuning via grid search. The proposed model's performance is demonstrated through comparative analysis with existing NB, J48, and SVM approaches, achieving a 98.50% accuracy rate. The efficiency gains from this approach have the potential to save a significant amount of time and cost. This study underscores the potential of computational intelligence and IoMT in developing effective, resource-efficient lung cancer therapies.

COVID19 detection in chest x-ray using vision-transformer with different patch dimensions

Computerized disease detection systems (CDDs) have proven effective for automatic screening in recent years. Among the standard procedures in hospitals for faster and more accurate diagnosis is medical imaging-based disease screening. We aim to develop a CDD that detects COVID-19 using chest X-rays pre-trained vision transformers (PVTs). This scheme includes the following steps: (1) collecting images and resizing them, (2) implementing PVT for feature extraction, and (3) binary classifying the results and validating the proposed schemes. To prove the merit of the developed scheme, 4800 images (2400 normal and 2400 COVID-19) are analyzed. MLP classifiers verify the PVT performance using patch sizes of 6, 12, and 24. A patch size 24 results in 97.5% accuracy for the proposed CDD system.When patch sizes are increased to 12, accuracy increases to over 98%. For this specific task, smaller patch sizes are more effective. These high-accuracy results demonstrate the effectiveness of the developed scheme for detecting COVID-19 in chest X-rays.

A Novel Brain-Machine Safety System Based on Drowsiness Detection using the PNN and MLP Algorithms

This work aims to develop a safety system capable of detecting drowsiness, in order to reduce the accident rate, the main idea is based on the classification of the cerebral signal captured by the electroencephalograph, after processing to eliminate all noise, the resulting data will then be segmented into two classes, the first category is devoted to the state of wakefulness and the second will be devoted to drowsiness. This categorization is based on the combination of features such as mean and standard deviation, and performed by two neural network algorithms, the probabilistic neural network and the multilayer perceptron, whose performance is evaluated according to machine learning metrics such as accuracy, error, specificity, sensitivity, F1 indicator and ROC curve representation. The binary classification results are highly significant in terms of class discrimination, with both models achieving excellent performance, with the MLP classifier outperforming the PNN model with an accuracy of 96.10% and an accuracy rate of 98.43%. This suggests that the MLP model can be effectively applied to critical tasks where good discrimination is required, such as detecting drowsiness in drivers to avoid accidents.