Feature Engineering Approach Research Articles

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.

HAPI: An efficient Hybrid Feature Engineering-based Approach for Propaganda Identification in social media.

Social media platforms serve as communication tools where users freely share information regardless of its accuracy. Propaganda on these platforms refers to the dissemination of biased or deceptive information aimed at influencing public opinion, encompassing various forms such as political campaigns, fake news, and conspiracy theories. This study introduces a Hybrid Feature Engineering Approach for Propaganda Identification (HAPI), designed to detect propaganda in text-based content like news articles and social media posts. HAPI combines conventional feature engineering methods with machine learning techniques to achieve high accuracy in propaganda detection. This study is conducted on data collected from Twitter via its API, and an annotation scheme is proposed to categorize tweets into binary classes (propaganda and non-propaganda). Hybrid feature engineering entails the amalgamation of various features, including Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words (BoW), Sentimental features, and tweet length, among others. Multiple Machine Learning classifiers undergo training and evaluation utilizing the proposed methodology, leveraging a selection of 40 pertinent features identified through the hybrid feature selection technique. All the selected algorithms including Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression (LR) achieved promising results. The SVM-based HaPi (SVM-HaPi) exhibits superior performance among traditional algorithms, achieving precision, recall, F-Measure, and overall accuracy of 0.69, 0.69, 0.69, and 69.2%, respectively. Furthermore, the proposed approach is compared to well-known existing approaches where it overperformed most of the studies on several evaluation metrics. This research contributes to the development of a comprehensive system tailored for propaganda identification in textual content. Nonetheless, the purview of propaganda detection transcends textual data alone. Deep learning algorithms like Artificial Neural Networks (ANN) offer the capability to manage multimodal data, incorporating text, images, audio, and video, thereby considering not only the content itself but also its presentation and contextual nuances during dissemination.

MobileDenseNeXt: Investigations on biomedical image classification

Background and objectiveWe are living in the information era. Therefore, intelligence-based researchers are hot-topic such as artificial intelligence. In the artificial intelligence research area, machine learning and deep learning models have frequently used to create intelligence assistants and deep learning is the shining star of the AI. Specifically, in the computer vision, numerous deep learning models have been proposed, leading to a competition between transformers and convolutional neural networks (CNNs). Since the introduction of Vision Transformers (ViT), many transformer models have been advocated for computer vision, often overshadowing CNNs. Therefore, it is crucial to propose CNNs to showcase their prowess in image classification. This research introduces a lightweight CNN named MobileDenseNeXt. Materials and methodsThe proposed MobileDenseNeXt comprises four main blocks: (i) input, (ii) main, (iii) average pooling-based downsampling, and (iv) output. This research also incorporates convolution-based residual blocks and uses a depth concatenation layer to increase the number of filters. For downsampling, an average pooling operation has been employed, similar to the original DenseNet. Furthermore, the swish activation function is utilized in the presented CNN. MobileDenseNeXt has approximately 1.4 million learnable parameters, categorizing it as a lightweight CNN model. Additionally, a deep feature engineering approach has been developed using MobileDenseNeXt, incorporating two feature extractors with global average pooling and dropout layers, along with 10 feature selectors, to demonstrate the transfer learning capabilities of MobileDenseNeXt. ResultsThe recommended models achieved over 95% test classification accuracy on the used three datasets, unequivocally demonstrating the high image classification proficiency of the proposed MobileDenseNeXt. Moreover, to show general classification ability of the proposed model, MobileDenseNeXt was trained on the CIFAR10 dataset and reached 98.62% accuracy. ConclusionsThis research not only highlights the efficiency and effectiveness of MobileDenseNeXt in biomedical image classification but also highlights the competitive potential of this model for computer vision.

Prediction of forming accuracy in incremental sheet forming using artificial neural networks on local surface representations

While incremental sheet metal forming offers the potential for producing sheet metal parts in small lot sizes, the relatively low forming accuracy prevents widespread industrial use. For improving the forming accuracy, research institutes are using machine learning techniques to predict the geometric accuracy and modify the toolpath based on the prediction. A critical challenge is it to ensure the generalizability of the prediction model as only a small amount of process data is available to train the model due to the lack of industrial collaborations. This publication presents a highly transferable feature engineering approach where surface representations of the part’s geometry around each toolpath point are transferred into a standardized coordinate system. Several artificial neural networks were trained and used for predicting the forming accuracy and modifying the toolpath. During the validation experiments, the forming errors of parts which were independent of the training process were reduced by up to 68.5 %. The framework for computing the surface representations alongside with several pre-trained artificial neural networks is publicity available for download.

Multitimescale Template Matching: Discovering Eruption Precursors across Diverse Volcanic Settings

Abstract Volcanic eruptions pose significant risks, demanding precise monitoring for timely hazard mitigation. However, interpreting noisy seismic data for eruptive precursors remains challenging. This study introduces a novel methodology that extends an earlier time-series feature engineering approach to include template matching against prior eruptions. We aim to identify subtle signals within seismic data to enhance our understanding of volcanic activity and future hazards. To do this, we analyze the continuous seismic record at a volcano and identify the time-series elements that regularly precede eruptions and the timescales over which these are observable. We conduct tests across various time lengths, ranging from 1 to 60 days. For Copahue (Chile/Argentina), Pavlof (Alaska), Bezymianny (Russia), and Whakaari (New Zealand) volcanoes, we confirm statistically significant eruption precursors. In particular, a feature named change quantiles (0.2–0.8), which is related to the conditional dynamics of surface acceleration at the volcano, emerges as a key indicator of future eruptions over 14-day timescales. This research offers new methods for real-time seismovolcanic monitoring, minimizing the effects of unknown, spurious noise, and discerning recurrent patterns through template matching. By providing deeper insights into pre-eruptive behavior, it may lead to more effective hazard reduction strategies, enhancing public safety around active volcanoes.

Stories behind decisions: Towards interpretable malware family classification with hierarchical attention

Malware family classification is essential for understanding malware code and behavioral characteristics, significantly reducing analysis time and response time for emerging malware. However, existing malware family classification methods are limited for two reasons. (1) The feature representation learned from a single information source is not sufficiently discriminative for large-scale malware family classification. (2) The lack of interpretability of classification results makes it difficult to provide intuitive guidance for malware analysis. To tackle the issues, we propose MalAtt, a novel malware family classification method for interpretable and large-scale classification. Specifically, a unified feature engineering approach is proposed to obtain integrated embedding from heterogeneous static and dynamic information. Then, a hierarchical attention encoder module is employed to progressively extract semantic features from the static and dynamic embedding. A collaborative attention module is introduced to model the association between high-level static and dynamic features. Finally, MalAtt is pluggable for different classifiers, such as SVM and RF, to implement malware family classification. For evaluations, we carefully collected a dataset from 62 malware families containing over 20,070 in-the-wild samples. MalAtt is proved to be effective when classifying large-scale malware families, with an accuracy of 93.26%. Besides, the ablation study demonstrates the rationality of the proposed modules. Additionally, we provide a case study to show how MalAtt intuitively guides in-depth malware analysis by highlighting partial input features with high attention scores.

CVG-Net: novel transfer learning based deep features for diagnosis of brain tumors using MRI scans

Brain tumors present a significant medical challenge, demanding accurate and timely diagnosis for effective treatment planning. These tumors disrupt normal brain functions in various ways, giving rise to a broad spectrum of physical, cognitive, and emotional challenges. The daily increase in mortality rates attributed to brain tumors underscores the urgency of this issue. In recent years, advanced medical imaging techniques, particularly magnetic resonance imaging (MRI), have emerged as indispensable tools for diagnosing brain tumors. Brain MRI scans provide high-resolution, non-invasive visualization of brain structures, facilitating the precise detection of abnormalities such as tumors. This study aims to propose an effective neural network approach for the timely diagnosis of brain tumors. Our experiments utilized a multi-class MRI image dataset comprising 21,672 images related to glioma tumors, meningioma tumors, and pituitary tumors. We introduced a novel neural network-based feature engineering approach, combining 2D convolutional neural network (2DCNN) and VGG16. The resulting 2DCNN-VGG16 network (CVG-Net) extracted spatial features from MRI images using 2DCNN and VGG16 without human intervention. The newly created hybrid feature set is then input into machine learning models to diagnose brain tumors. We have balanced the multi-class MRI image features data using the Synthetic Minority Over-sampling Technique (SMOTE) approach. Extensive research experiments demonstrate that utilizing the proposed CVG-Net, the k-neighbors classifier outperformed state-of-the-art studies with a k-fold accuracy performance score of 0.96. We also applied hyperparameter tuning to enhance performance for multi-class brain tumor diagnosis. Our novel proposed approach has the potential to revolutionize early brain tumor diagnosis, providing medical professionals with a cost-effective and timely diagnostic mechanism.

Securing IoT Healthcare Data Using Machine Learning Techniques

The internet of Things has become a crucial technology, enabling the interconnection of everyday devices like home appliances, medical equipment and vehicles. However, the sensitive data handled by IoT systems, particularly in the healthcare sector, requires robust security measures to prevent tampering or theft. Detecting security threats in IoT environments requires sophisticated techniques. Different machine learning algorithms are used to identify the attacks in IoT network traffic and predict snooping behavior based on unidentified patterns. This paper proposed a method to identify network traffic attacks by employing different strategies utilizing the NT-ToN-IoT dataset. The classifier utilized Naïve Bayes(NB), Random Forest(RF), Support Vector Machine, Artificial Neural Network. These algorithms favoured over centralized methods to construct streamlined security system for IoT devices. Prior to analysis the dataset underwent preprocessing to eliminate irrelevant or missing data. Following this, a feature engineering approach is applied to extract crucial features. The results from applying each classifier demonstrated a significant maximum classification accuracy of 98% achieved by the RF model.

Enhancing geospatial prediction models with feature engineering from road networks: a graph-driven approach

Traditional geospatial predictive models for property valuation have naturally relied on coordinates as well as ‘hedonic’ (internal and external) features. In particular, location-centric methods such as Geographically Weighted Regression (GWR) and Kriging have focused on intrinsic target characteristics together with distances between individual targets. However, especially in the context of heavily urbanized areas, these approaches might overlook crucial aspects arising from the underlying topological structure that presents itself in such areas. Concretely, in this work, we focus on the structure arising from the road network connecting properties. We introduce a novel though straightforward technique for feature engineering based on graphs constructed on a road network. We then extract relevant features from these and utilize those as inputs for predictive models and assess their performance benefits when used together with a variety of both well-known geospatial models and state-of-art machine learning models. To this end, we present an exhaustive experiment using four different real-life data sets across various regions and exhibiting sizes outperforming many comparative works in the field. Our findings reveal that our feature engineering approach offers significant improvements in predictive performance. Finally, we apply Shapley values as an interpretability technique to confirm the reliability and effectiveness of our approach.