Feature Engineering Approach Research Articles

OP08 Histology-derived cell-cell interaction networks, linked to transcriptome profiling, define path to resolution in UC

Abstract Background Despite therapeutic advancements, the cellular and molecular heterogeneity of UC hinders effective treatment. We applied machine learning-based approaches to whole scanned images (WSI) of H&E stained slides prepared from formalin-fixed, paraffin embedded intestinal mucosal biopsies from the etrolizumab clinical trials, aiming to identify cellular interactions and molecular signatures that define disease subtypes and treatment responses. We hypothesised that the cellular-basis of non-response could be derived by linking cell-cell relationships with paired transcriptomic profiles. Methods We analysed 2297 WSI paired with molecular data from 1272 UC patients from the etrolizumab PhIII clinical trial including various cohorts, treatment arms, and timepoints. Sections were segmented using a convolutional neural network, extracting 8 cell types and their coordinates. For each WSI, ~500 interaction features from an overlaid network were engineered using our developed software, CellMaskProfiler. The topology of the cell-cell interaction networks allowed clustering of WSI with similar profiles. Cell count features and clinical data enabled the annotation of clusters. Paired molecular data was used to perform differential expression. Results Using the cell-cell topology, we identified 7 distinct UC subtypes characterised by specific cellular interactions, molecular profiles and clinical features resolving into, intact, and neutrophil, eosinophil, plasma, or lymphocyte dominated profiles. WSI with a high proportion of epithelial cells and more connections between epithelial cells types were strongly associated with lower Robarts Histology Index, indicating milder disease or intact epithelium, while strong interaction with neutrophils showed the opposite effect. Looking at different treatment arms allowed to relate baseline biopsy WSI characteristics with probability of treatment response highlighting the probability of response based on initial WSI subtype. Using the cellular topology allowed to characterise the transition between diseased and healthier clusters. Adjusting for cellularity effects and comparing baseline data for response at induction revealed genes characterising response. Looking at transitions between clusters revealed similar genes. Conclusion This study introduces a novel feature engineering approach to unravel the cellular and molecular complexity of WSI in UC. The findings underscore the significance of cellular interactions in UC pathology and provide new insights into the molecular mechanisms underlying different disease states and demonstrates that the structural topology (form) derived from WSI can be effectively linked to the transcriptomic profiles (function) to define probability of remission.

Machine Learning and Deep Learning Approaches for Detecting DDoS Attacks in Cloud Environments

Distributed Denial of Service (DDoS) attacks pose a significant threat to cloud computing environments, necessitating advanced detection methods. This review examines the application of Machine Learning (ML) and Deep Learning (DL) techniques for DDoS detection in cloud settings, focusing on research from 2019 to 2024. It evaluates the effectiveness of various ML and DL approaches, including traditional algorithms, ensemble methods, and advanced neural network architectures, while critically analyzing commonly used datasets for their relevance and limitations in cloud-specific scenarios. Despite improvements in detection accuracy and efficiency, challenges such as outdated datasets, scalability issues, and the need for real-time adaptive learning persist. Future research should focus on developing cloud-specific datasets, advanced feature engineering, explainable AI, and cross-layer detection approaches, with potential exploration of emerging technologies like quantum machine learning.

Harnessing Machine Learning for High-Throughput Screening of High Thermal Conductivity Polyimides: A Multiscale Feature Engineering Approach

Polyimides are known for their exceptional thermal stability and are widely utilized in high-temperature and electronic applications. To further explore and broaden their application in electronic packaging and thermal management, developing polyimide with high thermal conductivity remains a significant challenge. In this study, we present a machine learning technique with novel multiscale feature engineering approach to predict and identify high thermal conductivity polyimide efficiently. Our workflow involves digitally representing chemical structures using physical insights and refining these representations through the Statistical – Tree – Recursive feature engineering pipeline, which includes three steps--statistical selection, tree-based cascading feature selection, and recursive feature elimination. This process results in the creation of a comprehensive combinational feature set. Multiple machine learning models were trained and validated, demonstrating high predictive accuracy and generalizability. High-throughput screening identified polyimide candidates with thermal conductivity values exceeding 0.4W/(m⋅K), and these predictions were validated using non-equilibrium molecular dynamics simulation. This workflow provides valuable insights into structure-property relationships, offering a robust framework for designing polymer materials with improved thermal properties for applications in electronics packaging, flexible sensors, and other high-performance devices.

The meta-aggregation approaches: Correctly choosing how to choose correctly in groups

Aggregating the choices regarding a given decision problem made by multiple individuals into a single solution is essential for exploiting the collective’s intelligence and effective crowdsourcing. There are various aggregation techniques, some of which come down to a simple aggregation rule, such as the majority rule. We propose two one-shot machine-learning-based aggregation approaches, which also exploit the existence of meta-cognitive features such as confidence. The first predicts which aggregation method will be best for a given collective decision-making case. The second directly predicts which decision is optimal given the selection made by each method. We offer a meta-cognitive feature-engineering approach for characterizing a collective decision-making case in a context-sensitive fashion. Experimental results show that using either of our proposed approaches increases the percentage of successfully aggregated cases, compared to the uniform application of the best rule-based aggregation method, by 5.8% and 6%. Furthermore, when an aggregation method is selected by our classifier, its effectiveness increases by an absolute percentage of 6.5% to 32.6%. We also offer a new aggregation method, the Devil’s-Advocate aggregator, to deal with cases in which standard aggregation methods fail. Ablation experiments demonstrate that removing the Devil’s Advocate aggregator decreases the success rate by 5.2%.

Enhanced forecasting of emergency department patient arrivals using feature engineering approach and machine learning

BackgroundEmergency department (ED) overcrowding is an important problem in many countries. Accurate predictions of ED patient arrivals can help management to better allocate staff and medical resources. In this study, we investigate the use of calendar and meteorological predictors, as well as feature-engineered variables, to predict daily patient arrivals using datasets from eleven different EDs across three countries.MethodsSix machine learning (ML) algorithms were tested on forecasting horizons of 7 and 45 days. Three of them – Light Gradient Boosting Machine (LightGBM), Support Vector Machine with Radial Basis Function (SVM-RBF), and Neural Network Autoregression (NNAR) – were never before reported for predicting ED patient arrivals. Algorithms’ hyperparameters were tuned through a grid-search with cross-validation. Prediction performance was assessed using fivefold cross-validation and four performance metrics.ResultsThe eXtreme Gradient Boosting (XGBoost) was the best-performing model on both prediction horizons, also outperforming results reported in past studies on ED arrival prediction. XGBoost and NNAR achieved the best performance in nine out of the eleven analyzed datasets, with MAPE values ranging from 5.03% to 14.1%. Feature engineering (FE) improved the performance of the ML algorithms.ConclusionAccuracy in predicting ED arrivals, achieved through the FE approach, is key for managing human and material resources, as well as reducing patient waiting times and lengths of stay.

The Improved Network Intrusion Detection Techniques Using the Feature Engineering Approach with Boosting Classifiers

In the domain of cybersecurity, cyber threats targeting network devices are very crucial. Because of the exponential growth of wireless devices, such as smartphones and portable devices, cyber risks are becoming increasingly frequent and common with the emergence of new types of threats. This makes the automatic and accurate detection of network-based intrusion very essential. In this work, we propose a network-based intrusion detection system utilizing the comprehensive feature engineering approach combined with boosting machine-learning (ML) models. A TCP/IP-based dataset with 25,192 data samples from different protocols has been utilized in our work. To improve the dataset, we used preprocessing methods such as label encoding, correlation analysis, custom label encoding, and iterative label encoding. To improve the model’s accuracy for prediction, we then used a unique feature engineering methodology that included novel feature scaling and random forest-based feature selection techniques. We used three conventional models (NB, LR, and SVC) and four boosting classifiers (CatBoostGBM, LightGBM, HistGradientBoosting, and XGBoost) for classification. The 10-fold cross-validation methods were employed to train each model. After an assessment using numerous metrics, the best-performing model emerged as XGBoost. With mean metric values of 99.54 ± 0.0007 for accuracy, 99.53 ± 0.0013 for precision, 99.54 ± 0.001 for recall, and an F1-score of 99.53 ± 0.0014, the XGBoost model produced the best performance overall. Additionally, we showed the ROC curve for evaluating the model, which demonstrated that all boosting classifiers obtained a perfect AUC value of one. Our suggested methodologies show effectiveness and accuracy in detecting network intrusions, setting the stage for the model to be used in real time. Our method provides a strong defensive measure against malicious intrusions into network infrastructures while cyber threats keep varying.

Post-GWAS Prioritization of Genome–Phenome Association in Sorghum

Genome-wide association studies (GWAS) are widely used to infer the genetic basis of traits in organisms; however, selecting appropriate thresholds for analysis remains a significant challenge. In this study, we introduce the Sequential SNP Prioritization Algorithm (SSPA) to investigate the genetic underpinnings of two key phenotypes in Sorghum bicolor: maximum canopy height and maximum growth rate. Using a subset of the Sorghum Bioenergy Association Panel cultivated at the Maricopa Agricultural Center in Arizona, we performed GWAS with specific permissive-filtered thresholds to identify genetic markers associated with these traits, enabling the identification of a broader range of explanatory candidate genes. Building on this, our proposed method employed a feature engineering approach leveraging statistical correlation coefficients to unravel patterns between phenotypic similarity and genetic proximity across 274 accessions. This approach helps prioritize Single Nucleotide Polymorphisms (SNPs) that are likely to be associated with the studied phenotype. Additionally, we conducted a complementary analysis to evaluate the impact of SSPA by including all variants (SNPs) as inputs, without applying GWAS. Empirical evidence, including ontology-based gene function, spatial and temporal expression, and similarity to known homologs demonstrates that SSPA effectively prioritizes SNPs and genes influencing the phenotype of interest, providing valuable insights for functional genetics research.

Learning global and local features of power load series through transformer and 2D-CNN: An image-based multi-step forecasting approach incorporating phase space reconstruction

As modern power systems continue to evolve, accurate power load forecasting remains a critical issue in energy management. The phase space reconstruction (PSR) method can effectively retain the inner chaotic property of power load from a system dynamics perspective and thus is a promising knowledge-based method for power load forecasting. To fully leverage the PSR method’s capability in modeling this high-dimensional, non-stationary characteristics of power load data, and to address the challenges faced by its classical mathematical prediction algorithms in effectively solving contemporary prediction scenarios characterized by massive volumes of data. This study proposes a novel learning-based multi-step forecasting approach that utilizes an image-based modeling perspective for the reconstructed phase trajectories. Firstly, the feature engineering approach that simultaneously utilizes dynamic evolution features and temporal locality features in the trajectory image is proposed. Through mathematical derivation, the equivalent characterization of the PSR method and another time series modeling approach, patch segmentation (PS), is demonstrated for the first time. Building on this prior knowledge, a novel image-based modeling perspective incorporating a global and local feature extraction strategy is introduced to fully leverage these valuable features. Subsequently, within this framework, a novel deep learning model, termed PSR-GALIEN, is designed for end-to-end processing. This model employs a Transformer Encoder and 2D convolutional neural networks (CNNs) to extract global and local patterns from the image, while a multi-layer perceptron (MLP)-based predictor is utilized for efficient correlation modeling. Extensive experiments on five real-world datasets show that PSR-GALIEN consistently outperforms six state-of-the-art deep learning models in short-term load forecasting scenarios with varying characteristics, demonstrating its great robustness. Ablation studies further confirm that the image-based modeling approach captures more relevant features than traditional sequential methods, improving the overall forecasting accuracy. Additionally, the attributions of the forecasting results of PSR-GALIEN can be explained through the proposed visualization-based method, which significantly enhances its interpretability.

Contrastive Learning for Morphological Disambiguation Using Large Language Models in Low-Resource Settings

In this paper, a contrastive learning approach for morphological disambiguation (MD) using large language models (LLMs) is presented. A contrastive loss function is introduced for training the approach, which reduces the distance between the correct analysis and contextual embeddings while maintaining a margin between correct and incorrect embeddings. One of the aims of the paper is to analyze the effects of fine-tuning an LLM on MD in morphologically complex languages (MCLs) with special reference to low-resource languages such as Kazakh, as well as Turkish. Another goal of the paper is to consider various distance measures for this contrastive loss function, aiming to achieve better results when performing disambiguation by computing the distance between the context and the analysis embeddings. The existing approaches for morphological disambiguation, such as HMM-based and feature-engineering approaches, have limitations in modeling long-term dependencies and in the case of large, sparse tagsets. These challenges are mitigated in the proposed approach by leveraging LLMs, thus achieving better accuracy in handling the cases of ambiguity and OOV tokens without the need to rely on other features. Experiments were conducted on three datasets for two MCLs, Kazakh and Turkish—the former is a typical low-resource language. The results revealed that the proposed approach with contrastive loss improves MD performance when integrated with knowledge from large language models.

Enhanced detection of diabetes mellitus using novel ensemble feature engineering approach and machine learning model

Diabetes is a persistent health condition led by insufficient use or inappropriate use of insulin in the body. If left undetected, it can lead to further complications involving organ damage such as heart, lungs, and eyes. Timely detection of diabetes helps obtain the right medication, diet, and exercise plan to lead a healthy life. ML approach has been utilized to obtain rapid and reliable diabetes detection, however, existing approaches suffer from the use of limited datasets, lack of generalizability, and lower accuracy. This study proposes a novel feature extraction approach to overcome these limitations by using an ensemble of convolutional neural network (CNN) and long short-term memory (LSTM) models. Multiple datasets are combined to make a larger dataset for experiments and multiple features are utilized for investigating the efficacy of the proposed approach. Features from the extra tree classifier, CNN, and LSTM are also considered for comparison. Experimental results reveal the superb performance of CNN-LSTM-based features with random forest model obtaining a 0.99 accuracy score. This performance is further validated by comparison with existing approaches and k-fold cross-validation which shows the proposed approach provides robust results.

Classification of Shoulder Implant Manufacturer Using Pre-Trained DenseNet201 Combined With Capsule Network.

This study aims to accelerate revision surgery and treatment using X-ray imaging and deep learning to identify shoulder implant manufacturers in advance. A feature engineering approach based on principal component analysis and a k-means algorithm was used to cluster shoulder implant data. In addition, a pre-trained DenseNet201 combined with a capsule network (DenseNet201-Caps) shoulder implant classification model was proposed. DenseNet201-Caps was the most effective classification model on the clustered dataset with an accuracy of 94.25% and an F1 score of 96.30%. Notably, clustering the dataset in advance improved the accuracy and the Caps implementations successfully enhanced the performance of all convolutional neural network models. The analysed results indicate that DenseNet201-Caps struggled to distinguish between the Cofield and Depuy manufacturers. Hence, a multistage classification approach was developed with an improved accuracy of 96.55% achieved. The DenseNet201-Caps method enables the accurate identification of shoulder implant manufacturers.

DeepPBI-KG: a deep learning method for the prediction of phage-bacteria interactions based on key genes.

Phages, the natural predators of bacteria, were discovered more than 100years ago. However, increasing antimicrobial resistance rates have revitalized phage research. Methods that are more time-consuming and efficient than wet-laboratory experiments are needed to help screen phages quickly for therapeutic use. Traditional computational methods usually ignore the fact that phage-bacteria interactions are achieved by key genes and proteins. Methods for intraspecific prediction are rare since almost all existing methods consider only interactions at the species and genus levels. Moreover, most strains in existing databases contain only partial genome information because whole-genome information for species is difficult to obtain. Here, we propose a new approach for interaction prediction by constructing new features from key genes and proteins via the application of K-means sampling to select high-quality negative samples for prediction. Finally, we develop DeepPBI-KG, a corresponding prediction tool based on feature selection and a deep neural network. The results show that the average area under the curve for prediction reached 0.93 for each strain, and the overall AUC and area under the precision-recall curve reached 0.89 and 0.92, respectively, on the independent test set; these values are greater than those of other existing prediction tools. The forward and reverse validation results indicate that key genes and key proteins regulate and influence the interaction, which supports the reliability of the model. In addition, intraspecific prediction experiments based on Klebsiella pneumoniae data demonstrate the potential applicability of DeepPBI-KG for intraspecific prediction. In summary, the feature engineering and interaction prediction approaches proposed in this study can effectively improve the robustness and stability of interaction prediction, can achieve high generalizability, and may provide new directions and insights for rapid phage screening for therapy.

Optimizing underwater connectivity through multi-attribute decision-making for underwater IoT deployments using remote sensing technologies

The underwater Internet of Things (UIoT) and remote sensing are significant for biodiversity preservation, environmental protection, national security, disaster assistance, and technological innovation. Assigning tasks to autonomous underwater vehicles (AUVs) is a fundamental challenge in underwater technology and exploration. Remote sensing and AUVs are vital for pollution detection, disaster prevention, marine observation, and ocean monitoring. This work presents an optimized network connectivity using a multi-attribute decision-making approach for underwater IoT deployment. A feature engineering approach highlights the significant characteristics of underwater things, incorporating remote sensing data, and a multi-objective optimization method is used to select optimal UIoT for effective task allocation in deep-sea environments. A balance between data transmission, energy economy, and operational performance is necessary for efficient task distribution. Effective communication algorithms and protocols are needed to maintain environmental sustainability, protect marine ecosystems, and improve underwater monitoring enhanced by remote sensing technologies. Multi-criteria decision-making (MCDM) is beneficial for addressing various challenges in underwater technology, considering factors such as mission objectives, energy efficiency, environmental conditions, vehicle performance, safety, and much more. The proposed criteria importance through intercriteria correlation (CRITIC) methodology will assess technical competencies like communication, resilience, navigation, and safety in an underwater environment, leveraging remote sensing and aiding decision-makers in selecting appropriate undersea devices and vehicles for enhancing communication and transportation. This method prioritizes characteristics and aligns them with specific objectives, improving decision-making quality in the marine environment.

Efficient Intrusion Detection in Patient Health Records Based on LSTM-Based RNN

Advancements in Information and Communication Technology applications play an important role in the field of healthcare and bio-medical engineering. The process of image processing and analysis starts from receiving visual information to giving out the description of the scene for improving the visual appearance of the human viewer and extract the features of the data. Moreover, IDS can be deployed along with other security mechanisms as a line of defence to ensure security of system and network resources. There have been various efforts in designing IDS using Machine Learning (ML) techniques. Additionally, by developing a hybrid strategy for intrusion detection and classification and using feature engineering approaches to extract significant features for learning, among other things, efforts have been made to improve the classification performance of ML-based IDS. However, as networking technology have advanced, attack types have evolved as well. For this reason, an efficient and successful intrusion detection and classification system must be created. To address the issue and achieve good generalization ability for intrusion detection and classification, the paper presents empirical analysis of LSTM based RNN classifiers. The suggested methods' effectiveness is assessed using a range of performance metrics, such as recall, f-score, accuracy, precision, and False Positive Rate (FPR). The LSTM based RNN method recognize attacks with 99.2% accuracy with minimum time complexity (5 s).

Enhancing FRP-concrete interface bearing capacity prediction with explainable machine learning: A feature engineering approach and SHAP analysis

This study introduces a novel approach to predict the shear bearing capacity of FRP-concrete interfaces using explainable machine learning. Eight algorithms are employed: three standalone models (Artificial Neural Network, Support Vector Regression, and Decision Tree) and five ensemble learning models (Bagging, Random Forest, Adaptive Boosting, Gradient Boosting, and Extreme Gradient Boosting). Four scenarios with varying input features, including engineered features inspired by mechanics-based bearing capacity equations, are examined. Notably, the inclusion of engineered features such as the stiffness of the FRP strip (Kf) significantly enhanced prediction accuracy and efficiency, although the width correction coefficient (bf/bc) did not yield significant benefits, contrary to findings in mechanics-based models. The Extreme Gradient Boosting (XGBoost) algorithm emerged as the top-performing model, achieving an impressive R-square value of 0.949. In terms of explainability, the study utilized the Shapley Additive Explanation (SHAP) technique to comprehensively elucidate the significance, dependency, and interaction effects of features within the best-performing model. Remarkable, approximately 75 % of the total mean absolute SHAP values were attributed to Kf and bf of the FRP, highlighting their pivotal role in the prediction process. This detailed explanation of the model using SHAP instills trust in the predictions and facilitates its practical implementation in real-world scenarios.

Early Detection of Stunting Based on Feature Engineering Approach

The stunting problem in Indonesia is still an extensive issue for the government. Around 22% of cases of stunting affect brain development, resulting in reduced intellectual capacity and permanent disruption of the structure and function of nerves and brain cells. This research describes early detection of stunting using an feature selection approach. So, datasets related to stunting are valuable in providing complete insight or information in detecting early symptoms of stunting in toddlers. Machine learning modelling for early detection of stunting in this study shows that of the 14 features predicting the value of detecting stunting, only seven features are influential based on their correlation values. When testing continues using Machine Learning algorithms with various variants, the Multilayer Perceptron algorithm can produce an accuracy value of 98%.

Predicting the Pathway Involvement of Metabolites in Both Pathway Categories and Individual Pathways.

Metabolism is the network of chemical reactions that sustain cellular life. Parts of this metabolic network are defined as metabolic pathways containing specific biochemical reactions. Products and reactants of these reactions are called metabolites, which are associated with certain human-defined metabolic pathways. Metabolic knowledgebases, such as the Kyoto Encyclopedia of Gene and Genomes (KEGG) contain metabolites, reactions, and pathway annotations; however, such resources are incomplete due to current limits of metabolic knowledge. To fill in missing metabolite pathway annotations, past machine learning models showed some success at predicting KEGG Level 2 pathway category involvement of metabolites based on their chemical structure. Here, we present the first machine learning model to predict metabolite association to more granular KEGG Level 3 metabolic pathways. We used a feature and dataset engineering approach to generate over one million metabolite-pathway entries in the dataset used to train a single binary classifier. This approach produced a mean Matthews correlation coefficient (MCC) of 0.806 ± 0.017 SD across 100 cross-validations iterations. The 172 Level 3 pathways were predicted with an overall MCC of 0.726. Moreover, metabolite association with the 12 Level 2 pathway categories were predicted with an overall MCC of 0.891, representing significant transfer learning from the Level 3 pathway entries. These are the best metabolite-pathway prediction results published so far in the field.

A Hybrid Scene Text Script Identification Network for Regional Indian Languages

In this work, we introduce WAFFNet, an attention-centric feature fusion architecture tailored for word-level multi-lingual scene text script identification. Motivated by the limitations of traditional approaches that rely exclusively on feature-based methods or deep learning strategies, our approach amalgamates statistical and deep features to bridge the gap. At the core of WAFFNet, we utilized the merits of Local Binary Pattern—a prominent descriptor capturing low-level texture features with high-dimensional, semantically-rich convolutional features. This fusion is judiciously augmented by a spatial attention mechanism, ensuring targeted emphasis on semantically critical regions of the input image. To address the class imbalance problem in multi-class classification scenarios, we employed a weighted objective function. This not only regularizes the learning process but also addresses the class imbalance problem. The architectural integrity of WAFFNet is preserved through an end-to-end training paradigm, leveraging transfer learning to expedite convergence and optimize performance metrics. Considering the under-representation of regional Indian languages in current datasets, we meticulously curated IIITG-STLI2023, a comprehensive dataset encapsulating English alongside six under-represented Indian languages: Hindi, Kannada, Malayalam, Telugu, Bengali, and Manipuri. Rigorous evaluation of the IIITG-STLI2023, as well as the established MLe2e and SIW-13 datasets, underscores WAFFNet’s supremacy over both traditional feature-engineering approaches as well as state-of-the-art deep learning frameworks. Thus, the proposed WAFFNet framework offers a robust and effective solution for language identification in scene text images.

Genetic Algorithm-based Convolutional Neural Network Feature Engineering for Optimizing Coronary Heart Disease Prediction Performance.

This study aimed to optimize early coronary heart disease (CHD) prediction using a genetic algorithm (GA)-based convolutional neural network (CNN) feature engineering approach. We sought to overcome the limitations of traditional hyperparameter optimization techniques by leveraging a GA for superior predictive performance in CHD detection. Utilizing a GA for hyperparameter optimization, we navigated a complex combinatorial space to identify optimal configurations for a CNN model. We also employed information gain for feature selection optimization, transforming the CHD datasets into an image-like input for the CNN architecture. The efficacy of this method was benchmarked against traditional optimization strategies. The advanced GA-based CNN model outperformed traditional methods, achieving a substantial increase in accuracy. The optimized model delivered a promising accuracy range, with a peak of 85% in hyperparameter optimization and 100% accuracy when integrated with machine learning algorithms, namely naïve Bayes, support vector machine, decision tree, logistic regression, and random forest, for both binary and multiclass CHD prediction tasks. The integration of a GA into CNN feature engineering is a powerful technique for improving the accuracy of CHD predictions. This approach results in a high degree of predictive reliability and can significantly contribute to the field of AI-driven healthcare, with the possibility of clinical deployment for early CHD detection. Future work will focus on expanding the approach to encompass a wider set of CHD data and potential integration with wearable technology for continuous health monitoring.

A semantic-based model with a hybrid feature engineering process for accurate spam detection

Detecting spam emails is essential to maintaining the security and integrity of email communication. Existing research has made significant progress in developing effective spam detection models, but challenges remain in improving classification performance and adaptability to evolving spamming techniques. In this study, we propose a novel spam detection model with a comprehensive feature engineering approach that combines term frequency-inverse document frequency (TF-IDF) vectorizer and word embedding features to optimize the feature space. Our contribution lies in integrating semantic-based word embeddings, leveraging pre-existing knowledge to capture the semantic meaning of words and enhance the representation of email texts. To identify the most suitable word embedding technique for our model, we evaluated GloVe, Word2Vec, and FastText. GloVe was selected for its better performance, which is the result of its pre-training on a large and diverse text corpus. Furthermore, the model was evaluated without word embeddings, which did not exhibit the same effectiveness level as our word embedding-based model. Additionally, we utilized the support vector machine as a classifier and hyperparameter tuning technique to identify our model’s most effective parameter values. The proposed model was tested on two datasets. The experimental results showed that our model outperformed the other models discussed in the literature, achieving an accuracy of 99.5% on the SpamAssassin dataset, and 99.28% on the Enron-Spam dataset.