Multilayer Perceptron Classifier Research Articles

Identifying employee engagement drivers using multilayer perceptron classifier and sensitivity analysis

AbstractEmployee engagement is increasingly important, as it can become a competitive advantage for companies, helping them increase productivity, attract talent and improve customer satisfaction. Numerous works have studied the drivers that encourage employee engagement and have developed models to identify them. However, the existing models have limitations, and the literature demands more research on the subject since the precision of the models still needs to improve. This paper presents a computational model that can estimate the drivers of employee engagement accurately. A sample of 205 Spanish employees was used, allowing us to consider a wide sectorial heterogeneity. Different methods have been applied to the sample under study to achieve a high-precision model, selecting drivers using the Multilayer Perceptron Classifier and quantifying the impact of the drivers with Sensitivity Analysis. The results obtained in this research present important implications for the managerial improvement of human resources departments by facilitating the design of strategies and policies that foster employee engagement, which significantly influences corporate results.

Prediction of soft tissue sarcoma grading using intratumoral habitats and a peritumoral radiomics nomogram: a multi-center preliminary study

BackgroundAccurate identification of pathologic grade before operation is helpful for guiding clinical treatment decisions and improving the prognosis for soft tissue sarcoma (STS).PurposeTo construct and assess a magnetic resonance imaging (MRI)-based radiomics nomogram incorporating intratumoral habitats (subregions of clusters of voxels containing similar features) and peritumoral features for the preoperative prediction of the pathological grade of STS.MethodsThe MRI data of 145 patients with STS (74 low-grade and 71 high-grade) from 4 hospitals were retrospectively collected, including enhanced T1-weighted and fat-suppressed-T2-weighted sequences. The patients were divided into training cohort (n = 102) and validation cohort (n = 43). K-means clustering was used to divide intratumoral voxels into three habitats according to signal intensity. A number of radiomics features were extracted from tumor-related regions to construct radiomics prediction signatures for seven subgroups. Logistic regression analysis identified peritumoral edema as an independent risk factor. A nomogram was created by merging the best radiomics signature with the peritumoral edema. We evaluated the performance and clinical value of the model using area under the curve (AUC), calibration curves, and decision curve analysis.ResultsA multi-layer perceptron classifier model based on intratumoral habitats and peritumoral features combined gave the best radiomics signature, with an AUC of 0.856 for the validation cohort. The AUC of the nomogram in the validation cohort was 0.868, which was superior to the radiomics signature and the clinical model established by peritumoral edema. The calibration curves and decision curve analyses revealed good calibration and a high clinical application value for this nomogram.ConclusionThe MRI-based nomogram is accurate and effective for predicting preoperative grading in patients with STS.

Machine Learning for Automated Oil Palm Fruit Grading: The Role of Fuzzy C-Means Segmentation and Textural Features

Oil palm fruit, a high-demand and economically valuable crop, faces grading challenges in Malaysia due to labour-intensive methods, resulting in unharvested ripe fruits and yield losses. Extensive research has been conducted on outdoor palm fruit classifiers, but most high-accuracy research in this field relies heavily on large image datasets. This creates a trade-off between employing more sophisticated deep-learning approaches that require extensive data and utilising traditional techniques that have lower data requirements. Therefore, the aim is to propose an outdoor image-based fresh fruit bunch (FFB) classification system, emphasising pre-processing technique and feature extraction techniques suitable for limited datasets. To achieve this, the FFB was localised within the original images using the YOLOv4-Tiny algorithm. Subsequently, a salient segmentation method utilising superpixel-based Fast Fuzzy C-means (FFCM) clustering is employed to remove the background from the images. Next, colour moment and opposite colour local binary pattern (OCLBP) features are extracted from the segmented images to capture important information for classification. Finally, the extracted features are fed into a Multilayer Perceptron (MLP) classifier, which enables the system to predict five classes: damaged, empty, unripe, ripe, and overripe. The developed system demonstrated a commendable performance in accurately classifying fruit bunches, achieving an accuracy of 93.68%. In conclusion, the proposed system effectively addresses the issue of unripe fruit harvesting and contributes to the advancement of state-of-the-art methods in classifying outdoor FFB images.

WEKA-based machine learning for traffic congestion prediction in Amman City

<p>Traffic congestion leads to wasted time, pollution, and increased fuel consumption. Traffic congestion prediction has become a developing research topic in recent years, particularly in the field of machine learning (ML). The evaluation of various traffic parameters is used to predict traffic congestion by relying on historical data. In this study, we will predict traffic congestion in Amman City, specifically at the 8th circle, using different ML classifiers. The 8th circle links four main streets: Westbound, Northbound, Eastbound, and Southbound. Datasets were collected from the greater Amman municipality hourly. The logistic regression (LR), k-nearest neighbor (KNN), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) classifiers have been chosen to predict traffic congestion at each street linked with the 8th circle. The waikato environment for knowledge analysis (WEKA) data mining tool is used to evaluate chosen classifiers by determining accuracy, F-measure, sensitivity, and precision evaluation metrics. The results obtained from all experiments have demonstrated that SVM is the best classifier to predict traffic congestion. The accuracy of SVM to predict traffic congestion at Westbound Street, Northbound Street, Eastbound Street, and Southbound Street was 99.4%, 99.7%, 99.6%, and 99.1%, respectively.</p>

Safety in Connected Health Network: Predicting and Detecting Hidden Information in Data Using Multilayer Perception Deep Learning Model

With the tremendous growth in the use of information technology, the connected health networks are becoming more relevant, greatly improving the traditional standard of healthcare procedures from data acquisition, storage, and sharing among the medics for timely clinical diagnosis processes, therapy, and disease management. However, connected health network comes with network and cyber criminality challenges, and frequent security breach attacks on digital platforms and databases. Unfortunately, Sensitive clinical information is greatly at risk with adversaries, most clinical stakeholders find it difficult to overlook free access to the clinical records. Previously, feature aggregation networks, convolutional neural networks, residual convolutional neural networks, and machine learning models were used in different methodological approaches towards ensuring the detection of hidden information in images, unfortunately, none was able to produce optimal results. This study proposes a three-phased framework to determine the suitability of embedder networks’ feature extraction for image steganalysis, predicting and detecting hidden information in images. A Multilayer Perceptron (MLP) deep learning model was trained for pattern recognition of steganography instances in acquired digital image signals. The digital image signals used for the predictive steganalysis are publicly available images contained in two circumstances highlighted regarding clean image signals (situation of cover images, but without steganography) and the embedded situation of image signals (where images (stego) with hidden data or information). Interestingly, the results of the parameter show that the Max-iter parameter of the MLP classifier hugely determines the performance of the algorithm towards detecting steganography in digital image signals. The parameter stipulates the number of times the training set will pass through the MLP network for the training process. Significantly, in our experiment, Max-iter returned the best result at 1000 netting an accuracy of 93%, precision of 57%, and recall of 100% weighted averages. Our study does not only implement a model that detects hidden information in images, but it also discovered and tuned the multilayer perceptron to determine where it will perform best.

Advancing Healthcare: Intelligent Speech Technology for Transcription, Disease Diagnosis, and Interactive Control of Medical Equipment in Smart Hospitals

Intelligent Speech Technology (IST) is revolutionizing healthcare by enhancing transcription accuracy, disease diagnosis, and medical equipment control in smart hospital environments. This study introduces an innovative approach employing federated learning with Multi-Layer Perceptron (MLP) and Gated Recurrent Unit (GRU) neural networks to improve IST performance. Leveraging the “Medical Speech, Transcription, and Intent” dataset from Kaggle, comprising a variety of speech recordings and corresponding medical symptom labels, noise reduction was applied using a Wiener filter to improve audio quality. Feature extraction through MLP and sequence classification with GRU highlighted the model’s robustness and capacity for detailed medical understanding. The federated learning framework enabled collaborative model training across multiple hospital sites, preserving patient privacy by avoiding raw data exchange. This distributed approach allowed the model to learn from diverse, real-world data while ensuring compliance with strict data protection standards. Through rigorous five-fold cross-validation, the proposed Fed MLP-GRU model demonstrated an accuracy of 98.6%, with consistently high sensitivity and specificity, highlighting its reliable generalization across multiple test conditions. In real-time applications, the model effectively performed medical transcription, provided symptom-based diagnostic insights, and facilitated hands-free control of healthcare equipment, reducing contamination risks and enhancing workflow efficiency. These findings indicate that IST, powered by federated neural networks, can significantly improve healthcare delivery, accuracy in patient diagnosis, and operational efficiency in clinical settings. This research underscores the transformative potential of federated learning and advanced neural networks for addressing pressing challenges in modern healthcare and setting the stage for future innovations in intelligent medical technology.

Investigation of radiomic features on MRI images to identify extraprostatic extension in prostate cancer

Background and ObjectiveDetection of extraprostatic extension (EPE) preoperatively is of critical importance in the context of prostate cancer (PCa) management and outcomes. This study aimed to characterize the radiomic features of malignant prostate lesions based on multi-paramagnetic magnetic resonance imaging (mpMRI). MethodsWe analyzed 20 patients who underwent mpMRI followed by radical prostatectomy. Two experienced radiologists manually segmented the 3D lesions using the T2-weighted (T2WI) and Apparent Diffusion Coefficient (ADC) imaging sequences. A total of 210 radiomic features were extracted from each lesion. We used the Recursive Feature Elimination with Cross-Validation to select key features. Using the selected radiomic features, we developed a Multilayer Perceptron (MLP) neural network to classify the EPE and non-EPE lesions. The pathology results were accepted as gold standard for EPE. We measured the performance of the classifier, calculating the area-under-curve (AUC), sensitivity, and specificity. ResultsA total of 25 lesions were segmented, including 12 lesions with EPE and 13 lesions without EPE, based on the pathology reports. We selected 18 radiomic features (18/210). The MLP classifier using these features provided a good sensitivity (0.75), specificity (0.79), and AUC of 0.82, 95 % CL [0.59 - 0.96] in identifying the EPE lesions. ConclusionsThis pilot study presents 18 radiomic features derived from T2-weighted and ADC images and demonstrates their potential in the preoperative prediction of EPE in PCa using an MLP model.

Self-learning salp swarm algorithm for global optimization and its application in multi-layer perceptron model training

Optimization problems are common across various fields, and one effective solution is the swarm intelligence algorithm.It is essential for the algorithm to deliver high-quality solutions for problems with varying characteristics. However, most existing swarm intelligence rely on fixed and monotonic search strategies, which limits their ability to handle the diverse and complex situations encountered when solving real-world optimization problems with unknown fitness landscapes. To extend the applicability of swarm intelligence and thus offer users an efficient black-box optimizer for various applications, a novel self-learning mechanism is proposed and applied to the Salp Swarm Algorithm (SSA) to develop the self-learning salp swarm algorithm (SLSSA) in this paper. In SLSSA, four distinct search strategies, including a novel multiple food sources search strategy, are adopted to strengthen the search agents’ abilities to conquer various difficulties in the search space. To improve the efficiency of the search process, the self-learning strategy dynamically determines the execution probability of each search strategy according to the quality of solutions it produced previously. Moreover, a parameter setting method is proposed in this paper, which eliminates the need for a trial-and-error approach and allows for straightforward configuration of the parameters that optimize the performance of SLSSA. In comparison with several highly regarded state-of-the-art peer algorithms, the performance of SLSSA in solving the CEC2014 benchmark functions was thoroughly examined. Subsequently, SLSSA was applied to train multi-layer perceptron classifiers and test on the UCI machine-learning datasets. The experimental results and analysis on benchmark functions and multi-layer perceptron classifier training problems demonstrate that SLSSA outperforms the competing algorithms in terms of solution accuracy, stability, and overall convergence speed. Moreover, computational time comparisons reveal that SLSSA achieves significant performance improvement with only a marginal increase in time cost compared to the original SSA.

Enhancing machine learning multi-class fault detection in electric motors through entropy-based analysis

Abstract In the field of electric motor maintenance, this study introduces a transformative approach by integrating entropy-based algorithms with machine learning for enhanced multi-class fault detection. Employing Shannon, Renyi, and Tsallis entropy algorithms on standard fault detection measurements, the research significantly advances predictive maintenance strategies through a robust, early-indication, system-agnostic analysis. Detailed examination is conducted, comparing results derived from datasets that include statistical features (excluding entropy) against the proposed entropy-based datasets, when applied to a multi-layer perceptron classifier (MLPC). Optimization of the MLPC and all compared algorithms’ hyperparameters is done using the state-of-the-art Optuna tool to dynamically explore each search space, ensuring that each methodology performs adequately in a timely fashion while allowing for adaptation. The results showcase significant enhancement in classification accuracy of diverse electric motor operational states, facilitating the differentiation between healthy and various levels of fault conditions under assorted load scenarios. Computational analyses reveal favorable results related to execution time and memory overhead, thereby supporting the practicality in operations constrained by memory resources. Validation of the approach is achieved through laboratory experiments on a purpose-built test bench. Versatility of entropy-based measures through their proposed utilization in diverse fault indications is achieved by a demonstration in the field of mechanical fault detection with a focus on bearing faults through well-respected datasets.

Habitat-based CT radiomics enhances the ability to predict spread through air spaces in stage T1 invasive lung adenocarcinoma.

Spread through air spaces (STAS) represents a novel invasive pattern in lung adenocarcinoma (LUAD) and is a risk factor for poor prognosis in stage T1 LUAD. This study aims to develop and validate a CT habitat imaging analysis model for predicting STAS in stage T1 invasive LUAD. We retrospectively analyzed 217 patients with preoperative stage T1 invasive LUAD (115 STAS-positive and 102 STAS-negative cases, including 151 in the train set and 66 in the test set). Semi-automatic segmentation was performed on the regions of interest (ROIs) in all CT images, with an automatic 3mm expansion around the tumor, considering the intratumoral and peritumoral 3mm area. This area was divided into three sub-regions via K-means clustering, and 1197 radiomic features were extracted from each sub-region and the overall combined region. After dimension reduction through the Mann-Whitney U test, Pearson correlation analysis, and least absolute shrinkage and selection operator(LASSO), the best features for each sub-region and overall were selected. Models were then built using the selected radiomic features through the Adaptive Boosting (AdaBoost) and Multilayer Perceptron (MLP) classifiers. Four different models were established based on different sub-regions and the overall features. The performance of these models was evaluated through receiver operating characteristic curves (AUC) under the DeLong test, calibration curves via the Hosmer-Lemeshow test, and decision curve analysis to assess the performance of these features. In this study, we evaluated the predictive performance of AdaBoost and MLP classifiers on rad feature models across various subregions and the overall dataset. In the test set, the AdaBoost classifier achieved a maximum AUC of 0.871 in Habitat 3, whereas the MLP classifier demonstrated slightly superior performance with an AUC of 0.879. Both classifiers exhibited high efficiency in habitat 3, with the MLP algorithm showing enhanced model performance. CT habitat imaging analysis for the preoperative prediction of STAS in stage T1 invasive LUAD shows satisfactory diagnostic performance, with the habitat3 model exhibiting the highest efficacy, reflecting tumor heterogeneity.

Rapid diagnosis of the geospatial distribution of intertidal macroalgae using large-scale UAVs

Macroalgae have been used as indicators of the health of coastal ecosystems, they function as sinks of CO2 and are essential contributors to primary production. With the increase in anthropogenic activities, it is crucial to assess the impact of such activities on these ecosystems. As traditional surveying techniques, although accurate, are time-consuming and their area coverage is limited, novel techniques are required to monitor the coverage and diversity of intertidal macroalgae. We propose a methodology using the free-source Semi-Automatic Classification Plugin from QGIS to use UAV and multispectral cameras for the spatiotemporal monitoring of intertidal macroalgae. We also compared the performance of six classifiers: Minimum Distance (MD), Maximum Likelihood (ML), Spectral Angle Mapping (SAM), Multi-Layer Perceptron (MLP), Random Forest (RF) and Support Vector Machine (SVM), for three types of macroalgae classification: general, taxonomical groups and species. As proof of concept, an intertidal rocky shore in a marine protected area (NW Spain) was studied for four months. RF and SVM achieved similar results, with both being recommended for the general (OASVM = 97.4±1.7 and OARF = 98.3±1.7) and taxonomical groups (OASVM = 91.6±1.9 and OARF = 89.2±4.5). SVM and ML were found to be more suitable for species classification (OASVM = 77.4±11.4 and OAML = 74.2±9.7). SAM and MLP provided the least performant species classifiers because of the overlap in the macroalgae spectral signatures. The plugin showed limitations when tuning the input parameters of the MLP classifier and did not let to add a validation dataset. Additionally, we present an open-access GIS web application, Alganat 2000 GIS web, to facilitate the monitoring and management of coastal areas. We conclude that the proposed methodology using the SVM or ML classifiers is an effective tool for assessing intertidal macroalgal assemblages. Its easy and rapid implementation is beneficial for researchers who are not very familiar with coding and machine learning frameworks and reduces the time and cost of fieldwork. As future work, we propose the combination of the multispectral bands with topographic and spectral indices and to research the application of deep learning models to the classification of intertidal macroalgae.

Computer Modelling of Textures on Images with Human Skin Wound Areas

In this paper, we concentrate on the images of the wounds on the human skin and propose to consider each image as a set of smaller pieces – crops or patches containing different textures. We overview, develop and compare deep learning feature extraction methods to model image crops as 200-dimensional feature vectors using various artificial neural network architectures: convolutional autoencoders, variational convolutional autoencoders, and Siamese convolutional networks trained in the contrastive learning manner. Also, we develop a custom convolutional encoder and decoder, use them in the aforementioned architectures and compare them with the ResNet encoder and decoder alternatives. Finally, we train and evaluate k-nearest neighbors and Multi-Layer Perceptron classifiers on the features extracted with the model above options to discriminate skin, wound, and background image patches. Classification evaluation results on the features, extracted with the Siamese network, show the best test accuracy for all implementations without a significant shift between model versions (accuracy > 93%); variational autoencoders show random results for all options (accuracy around 33%), and convolutional autoencoders reached good results (accuracy > 77%) but with a noticeable difference between the custom and ResNet versions; the latter is better. Custom encoder and decoder implementations are faster and smaller than the ResNet alternatives but may be less stable on larger datasets, which still needs investigation. Possible applications of the feature vectors include an area of interest extraction during wound segmentation or classification and usage as patch embeddings while training vision transformer architectures.

Remote sensing detection of plastic-mulched farmland using a temporal approach in machine learning: case study in tomato crops.

The increasing use of plastics in rural environments has led to concerns about agricultural plastic waste (APW). However, the plasticulture information gap hinders waste management planning and may lead to plastic residue leakage into the environment with consequent microplastic formation. The location and estimated quantity of the APW are crucial for territorial planning and public policies regarding land use and waste management. Agri-plastic remote detection has attracted increased attention but requires a consensus approach, particularly for mapping plastic-mulched farmlands (PMFs) scattered across vast areas. This article tests whether a streamlined time-series approach minimizes PMF confusion with the background using less processing. Based on the literature, we performed a vast assessment of machine learning techniques and investigated the importance of features in mapping tomato PMF. We evaluated pixel-based and object-based classifications in harmonized Sentinel-2 level-2A images, added plastic indices, and compared six classifiers. The best result showed an overall accuracy of 99.7% through pixel-based using the multilayer perceptron (MLP) classifier. The 3-time series with a 30-day composite exhibited increased accuracy, a decrease in background confusion, and was a viable alternative for overcoming the impact of cloud cover on images at certain times of the year in our study area, which leads to a potentially reliable methodology for APW mapping for future studies. To our knowledge, the presented PMF map is the first for Latin America. This represents a first step toward promoting the circularity of all agricultural plastic in the region, minimizing the impacts of degradation on the environment.

Advancing the prediction of crystalline phases in glass-ceramics via machine learning

Lithium aluminosilicate (LAS) glass-ceramics are widely utilized in diverse application, owing to their outstanding properties such as high transparency, high fracture toughness and ultra-low thermal expansion. The development of LAS glass-ceramics has traditionally relied on the phase diagram to identify primary crystalline phases. However, this approach is limited by constrained composition ranges and unknown heating treatment parameters, hindering the efficient development of high-performance glass-ceramics. In this study, we establish a comprehensive small-scale database of LAS glass-ceramics, comprising 751 samples characterized by 27 compositions, nucleation temperature, nucleation time, crystallization temperature, crystallization time and 13 crystalline phases. We employ five algorithms, i.e. Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Classification and Regression Trees (CART), K-Nearest Neighbors (K-NN) and Multi-Layer Perceptron (MLP) Classifier to predict the potential crystalline phases. Our results demonstrate that RF achieves the best overall performance, with the highest accuracy of 0.8609, the lowest hamming loss of 0.0142, and the highest micro F1 score of 0.9234. This work advances the understanding and prediction of crystalline phases in LAS glass-ceramics, providing valuable insights for the development and optimization of these materials.

Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning.

To predict palatally impacted maxillary canines based on maxilla measurements through supervised machine learning techniques. The maxilla images from 138 patients were analysed to investigate intermolar width, interpremolar width, interpterygoid width, maxillary length, maxillary width, nasal cavity width and nostril width, obtained through cone beam computed tomography scans. The predictive models were built using the following machine learning algorithms: Adaboost Classifier, Decision Tree, Gradient Boosting Classifier, K-Nearest Neighbours (KNN), Logistic Regression, Multilayer Perceptron Classifier (MLP), Random Forest Classifier and Support Vector Machine (SVM). A 5-fold cross-validation approach was employed to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision and F1 Score were calculated for each model, and ROC curves were constructed. The predictive model included four variables (two dental and two skeletal measurements). The interpterygoid width and nostril width showed the largest effect sizes. The Gradient Boosting Classifier algorithm exhibited the best metrics, with AUC values ranging from 0.91 [CI95% = 0.74-0.98] for test data to 0.89 [CI95% = 0.86-0.94] for crossvalidation. The nostril width variable demonstrated the highest importance across all tested algorithms. The use of maxillary measurements, through supervised machine learning techniques, is a promising method for predicting palatally impacted maxillary canines. Among the models evaluated, both the Gradient Boosting Classifier and the Random Forest Classifier demonstrated the best performance metrics, with accuracy and AUC values exceeding 0.8, indicating strong predictive capability.

Artificial neural networks in automatic image classifications of cloud from ground‐based observations using deep learning models

AbstractCloud classification is a critical task in meteorology, with applications in weather forecasting, climate modelling, and environmental monitoring. Traditionally, cloud observations are made visually by experienced observers, which can introduce human errors and inconsistencies. This study aims to develop accurate deep learning models for automated cloud classification from ground‐based images. A dataset of over 200,000 cloud photographs was collected from professional observers at meteorological stations of the Institute of Meteorology and Water Management–National Research Institute. The images were preprocessed and annotated with cloud type labels. Convolutional neural networks and transformer models were employed for feature extraction, combined with multilayer perceptrons for classification. Different architectures were explored, including ResNet, EfficientNet, Vision Transformers, and their variants. Hyperparameter tuning and data augmentation techniques like RandAugment were applied to improve generalisation. The best‐performing model achieved 97.4% accuracy for classifying four common cloud genera: cirrus, cumulus, stratus, and clear sky. Additional experiments classified up to 11 genera, with accuracy decreasing as complexity increased, due to data limitations. Error analysis revealed confusions between visually similar classes. While promising, limitations exist from using partial cloud views versus whole‐sky imagery. We start with four classes and end with 11 classes, progressively showing subsequent errors in the cloud genera classification process, something not presented in other publications. Future work involves collecting a more balanced dataset with standardised protocols. Integration of all‐sky cameras could help address current restrictions. This research demonstrates the viability of deep learning for automated cloud observation, with opportunities to advance meteorological applications through continued methodological refinement.

Robust Face Recognition System Based on Deep Facial Feature Extraction and Machine Learning

Facial Recognition is a common challenge in research for security applications. Wide-ranging applications of this technology include biometrics, security data, access to controlled locations, smart cards, and surveillance systems. A practical approach to identifying individuals depends on factors such as partial face occlusion, illumination, age, expression, makeup, and poses. These complex face recognition variables affect most face recognition systems. In this paper, we propose a deep transfer learning for facial features based on the pose and illumination variations of celebrities’ faces in a free environment for face recognition. The new approach that combines deep learning methods for feature extraction with machine learning classification methods. Also, studies the performance of the pre-trained model (VGGFace2 with ResNet-50 model weights) for feature extraction with a Multilayer Perceptron Classifier (MLP), Decision Tree, and Bootstrap Aggregation (Bagging) to perform classification. The convolution neural network has lately achieved excellent advancement in facial recognition. The outcome indicated that VGGFace2 with MLP obtained more precision and provided the best results (Accuracy, F-measure, Recall, and Precision). The results for all metric for the proposed model is 99%. The benchmark for this model is a dataset of 105 people’s faces.

Game Difficulty Prediction Based on Facial Cues and Game Performance

Current research on game difficulty prediction mainly uses heuristic functions or physiological signals. The former does not consider user data, while the latter easily causes interference to the user. This paper proposes a difficulty prediction method based on multiple facial cues and game performance. Specifically, we first utilize various computer vision methods to detect players’ facial expressions, gaze directions, and head poses. Then, we build a dataset by combining these three kinds of data and game performance as inputs, with the subjective difficulty ratings as labels. Finally, we compare the performance of several machine learning methods on this dataset using two classification tasks. The experimental results showed that the multilayer perceptron classifier (abbreviated as MLP) achieved the highest performance on these tasks, and its accuracy increased with the increase in input feature dimensions. These results demonstrate the effectiveness of our method. The proposed method could assist in improving game design and user experience.

Predicting diabetes in adults: identifying important features in unbalanced data over a 5-year cohort study using machine learning algorithm

BackgroundImbalanced datasets pose significant challenges in predictive modeling, leading to biased outcomes and reduced model reliability. This study addresses data imbalance in diabetes prediction using machine learning techniques. Utilizing data from the Fasa Adult Cohort Study (FACS) with a 5-year follow-up of 10,000 participants, we developed predictive models for Type 2 diabetes.MethodsWe employed various data-level and algorithm-level interventions, including SMOTE, ADASYN, SMOTEENN, Random Over Sampling and KMeansSMOTE, paired with Random Forest, Gradient Boosting, Decision Tree and Multi-Layer Perceptron (MLP) classifier. We evaluated model performance using F1 score, AUC, and G-means—metrics chosen to provide a comprehensive assessment of model accuracy, discrimination ability, and overall balance in performance, particularly in the context of imbalanced datasets.Resultsour study uncovered key factors influencing diabetes risk and evaluated the performance of various machine learning models. Feature importance analysis revealed that the most influential predictors of diabetes differ between males and females. For females, the most important factors are triglyceride (TG), basal metabolic rate (BMR), and total cholesterol (CHOL), whereas for males, the key predictors are body Mass Index (BMI), serum glutamate Oxaloacetate Transaminase (SGOT), and Gamma-Glutamyl (GGT). Across the entire dataset, BMI remains the most important variable, followed by SGOT, BMR, and energy intake. These insights suggest that gender-specific risk profiles should be considered in diabetes prevention and management strategies. In terms of model performance, our results show that ADASYN with MLP classifier achieved an F1 score of 82.17 ± 3.38, AUC of 89.61 ± 2.09, and G-means of 89.15 ± 2.31. SMOTE with MLP followed closely with an F1 score of 79.85 ± 3.91, AUC of 89.7 ± 2.54, and G-means of 89.31 ± 2.78. The SMOTEENN with Random Forest combination achieved an F1 score of 78.27 ± 1.54, AUC of 87.18 ± 1.12, and G-means of 86.47 ± 1.28.ConclusionThese combinations effectively address class imbalance, improving the accuracy and reliability of diabetes predictions. The findings highlight the importance of using appropriate data-balancing techniques in medical data analysis.

IGATTLDA: Integrative graph attention and transformer-based model for predicting lncRNA-Disease associations.

Long non-coding RNAs (lncRNAs) have emerged as significant contributors to the regulation of various biological processes, and their dysregulation has been linked to a variety of human disorders. Accurate prediction of potential correlations between lncRNAs and diseases is crucial for advancing disease diagnostics and treatment procedures. The authors introduced a novel computational method, iGATTLDA, for the prediction of lncRNA-disease associations. The model utilised lncRNA and disease similarity matrices, with known associations represented in an adjacency matrix. A heterogeneous network was constructed, dissecting lncRNAs and diseases as nodes and their associations as edges. The Graph Attention Network (GAT) is employed to process initial features and corresponding adjacency information. GAT identified significant neighbouring nodes in the network, capturing intricate relationships between lncRNAs and diseases, and generating new feature representations. Subsequently, the transformer captures global dependencies and interactions across the entire sequence of features produced by the GAT. Consequently, iGATTLDA successfully captures complex relationships and interactions that conventional approaches may overlook. In evaluating iGATTLDA, it attained an area under the receiver operating characteristic (ROC) curve (AUC) of 0.95 and an area under the precision recall curve (AUPRC) of 0.96 with a two-layer multilayer perceptron (MLP) classifier. These results were notably higher compared to the majority of previously proposed models, further substantiating the model's efficiency in predicting potential lncRNA-disease associations by incorporating both local and global interactions. The implementation details can be obtained from https://github.com/momanyibiffon/iGATTLDA.