Classification Approach Research Articles

A Novel Two-Channel Classification Approach Using Graph Attention Network with K-Nearest Neighbor

A Novel Two-Channel Classification Approach Using Graph Attention Network with K-Nearest Neighbor

A machine learning classifier-based approach for diabetes mellitus risk prediction.

Currently, Diabetes Mellitus (DM) can be life-threatening due to the dietary habits and lifestyle choices of individuals. Diabetes is characterised by elevated levels of glucose in the blood and an excess of protein in the blood. Poor eating habits and lifestyles are largely responsible for the rise in overweight, obesity, and various related conditions. This study investigated many diabetes-related risk forecasting techniques and algorithms. The eight machine learning (ML) algorithms used the diabetes dataset to test various prediction techniques, including a Support Vector Classifier, gradient-boosting, multilayer perceptron, random forest, K-nearest neighbors, logistic regression, extreme gradient boosting, and decision tree. To enhance the diabetic prediction ability of the model, we suggested using Feature Engineering (FE) and feature scaling. For our investigation, we utilized the Mendeley dataset on diabetes to assess the capacity of the model to predict diabetes. We developed a model by using Python programming and eight classification techniques. The Random Forest with 99.21%, Gradient Boosting with 99.61%, Extreme Gradient Boosting, and Decision Tree achieved the highest F1 score (99.81%), accuracy rate (99.80%), precision (99.81%), and recall (99.81%) of all classification approaches.

Automated Classification of Coronary Plaque on Intravascular Ultrasound by Deep Classifier Cascades.

Intravascular ultrasound (IVUS) is the gold standard modality for in vivo visualization of coronary arteries and atherosclerotic plaques. Classification of coronary plaques helps to characterize heterogeneous components and evaluate the risk of plaque rupture. Manual classification is time-consuming and labor-intensive. Several machine learning-based classification approaches have been proposed and evaluated in recent years. In the current study, we develop a novel pipeline composed of serial classifiers for distinguishing IVUS images into five categories: normal, calcified plaque, attenuated plaque, fibrous plaque, and echolucent plaque. The cascades comprise densely connected classification models and machine learning classifiers at different stages. Over 100,000 IVUS frames of five different lesion types were collected and labeled from 471 patients for model training and evaluation. The overall accuracy of the proposed classifier is 0.877, indicating that the proposed framework has the capacity to identify the nature and category of coronary plaques in IVUS images. Further, it may provide real-time assistance on plaque identification and facilitate clinical decision-making in routine practice.

Advancing UAV Security with ALBERT: A Novel Attack Classification Approach

Advancing UAV Security with ALBERT: A Novel Attack Classification Approach

Empirical Approach to Quantifying Sensitivity in Different Chemical Ionization Techniques for Organonitrates and Nitroaromatics Constrained by Ion-Molecule Reaction and Transmission Efficiency.

Accurate identification and quantification of nitro-containing species are of great significance to understanding their chemical behaviors in the atmosphere. By optimizing the operational conditions of the H3O+ and NO+ ionization modes in a proton-transfer-reaction time-of-flight mass spectrometer (PTR-TOF-MS) and evaluating the performance of an iodide chemical ionization mass spectrometer (I- CIMS), this study leveraged the individual advantages of each ionization mode to effectively detect a diverse array of nitroaromatics and organonitrates (ONs). The H3O+ ionization mode largely fulfilled the criteria for real-time monitoring of gas-phase alkyl-, aryl-, and hydroxy-nitrates, and nitrophenols, albeit its reduced sensitivity toward ONs due to extensive fragmentation. In contrast, the NO+ mode demonstrated enhanced sensitivity for ONs with less fragmentation than the H3O+ mode. The I- CIMS featured distinguished sensitivity toward oxidized compounds containing polar functional groups, particularly increasing with the incorporation of hydroxyl, carboxyl, or nitrate groups. Further, we developed a calibration-based semiquantitative framework to enhance the accuracy of sensitivity estimation, constrained by ion-molecule reaction, transmission efficiency, along with possible decomposition of ion-clusters, with uncertainties ranging from 21% to 41% for H3O+ and 21-43% for NO+. Given considerable discrepancies (up to 1 order of magnitude) between measured and predicted sensitivity in I- CIMS using previously reported log-linear fitting, a declustering voltage (dV50)-based categorization approach was introduced, leading to a 5-fold improvement in measurement accuracy and an overall uncertainty of I- CIMS in quantifying nitro-containing species varying from 27% to 60%.

Exploring Recent NLP Advances for Tamil: Word Vectors and Hybrid Deep Learning Architectures

The advancements of deep learning methods and the availability of large corpora and data sets have led to an exponential increase in the performance of Natural Language Processing (NLP) methods resulting in successful NLP applications for various day-to-day tasks such as Language translation, Voice to text, Grammar checking, Sentiment analysis, etc. These advancements enabled the well-resourced languages to adapt themselves to the digital era while the gap for the low-resource languages widened. This research work explores the suitability of the recent advancements in NLP for Tamil, a low-resource language spoken mainly in South India, Sri Lanka, and Malaysia. From the literature survey, it has been found that there is a lack of comprehensive study on the effect of the recent advancements of NLP for the Tamil text. To fill this gap, this research work analysed the performance of deep learning based text representation and classification approaches namely word embedding, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) for Tamil text classification tasks. Different dimensional pretrained word2Vec and FastText word vectors were built for Tamil and their effectiveness on Text classification was evaluated. The study found that the pre-trained 300- dimensional FastText word vector showed better performance than other pre-trained word vectors for Tamil text classification. Further, in this study, four simple hybrid CNN and Bi-GRU models were proposed for Tamil text classification and their performances were evaluated. The study found that hybrid CNN and Bi-GRU models perform better compared to the classical machine learning models, individual CNN and RNN models, and the Multilingual BERT model. These results confirm that the jointly learned embeddings with different deep learning architectures like CNN and RNN can achieve remarkable results for Tamil text classification, thus ensuring that the deep learning approaches can be successful for NLP on Tamil text.

Machine learning approaches in non-contact autofluorescence spectrum classification.

Manual surgical resection of soft tissue sarcoma tissue can involve many challenges, including the critical need for precise determination of tumor boundary with normal tissue and limitations of current surgical instrumentation, in addition to standard risks of infection or tissue healing difficulty. Substantial research has been conducted in the biomedical sensing landscape for development of non-human contact sensing devices. One such point-of-care platform, previously devised by our group, utilizes autofluorescence-based spectroscopic signatures to highlight important physiological differences in tumorous and healthy tissue. The following study builds on this work, implementing classification algorithms, including Artificial Neural Network, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors, to diagnose freshly resected murine tissue as sarcoma or healthy. Classification accuracies of over 93% are achieved with Logistic Regression, and Area Under the Curve scores over 94% are achieved with Support Vector Machines, delineating a clear way to automate photonic diagnosis of ambiguous tissue in assistance of surgeons. These interpretable algorithms can also be linked to important physiological diagnostic indicators, unlike the black-box ANN architecture. This is the first known study to use machine learning to interpret data from a non-contact autofluorescence sensing device on sarcoma tissue, and has direct applications in rapid intraoperative sensing.

Fusion of spectral and topographic features for land use mapping using a machine learning framework for a regional scale application.

This study investigated the dynamics of land use and land cover (LULC) modelling, mapping, and assessment in the Kegalle District ofSri Lanka, where policy decision-making is crucial in agricultural development where LULC temporal datasets are not readily available.Employing remotely sensed datasets and machine learning algorithms, the work presented here aims to compare the accuracy of three classification approaches in mapping LULC categories across the time in the study area primarily using the Google Earth Engine (GEE). Three classifiers namely random forest (RF), support vector machines (SVM), and classification and regression trees (CART) were used in LULC modelling, mapping, and change analysis. Different combinations of input features were investigated to improve classification performance. Developed models were optimised using the grid search cross-validation (CV) hyperparameter optimisation approach. It was revealed that the RF classifier constantly outstrips SVM and CART in terms of accuracy measures, highlighting its reliability in classifying the LULC. Land cover changes were examined for two periods, from 2001 to 2013 and 2013 to 2022, implying major alterations such as the conversion of rubber and coconut areas to built-up areas and barren lands. For suitable classification with higher accuracy, the study suggests utilising high spatial resolution satellite data, advanced feature selection approaches, and a combination of several spatial and spatial-temporal data sources. The study demonstrated practical applications of derived temporal LULC datasets for land management practices in agricultural development activities in developing nations.

Hybrid Deep Learning Framework for Melanoma Diagnosis Using Dermoscopic Medical Images

Background: Melanoma, or skin cancer, is a dangerous form of cancer that is the major cause of the demise of thousands of people around the world. Methods: In recent years, deep learning has become more popular for analyzing and detecting these medical issues. In this paper, a hybrid deep learning approach has been proposed based on U-Net for image segmentation, Inception-ResNet-v2 for feature extraction, and the Vision Transformer model with a self-attention mechanism for refining the features for early and accurate diagnosis and classification of skin cancer. Furthermore, in the proposed approach, hyperparameter tuning helps to obtain more accurate and optimized results for image classification. Results: Dermoscopic shots gathered by the worldwide skin imaging collaboration (ISIC2020) challenge dataset are used in the proposed research work and achieved 98.65% accuracy, 99.20% sensitivity, and 98.03% specificity, which outperforms the other existing approaches for skin cancer classification. Furthermore, the HAM10000 dataset is used for ablation studies to compare and validate the performance of the proposed approach. Conclusions: The achieved outcome suggests that the proposed approach would be able to serve as a valuable tool for assisting dermatologists in the early detection of melanoma.

Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia, Hypoglycemia, and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring.

The aim of this study was to develop and validate explainable prediction models based on continuous glucose monitoring (CGM) and baseline data to identify a week-to-week risk of CGM key metrics (hyperglycemia, hypoglycemia, glycemic variability). By having a weekly prediction of CGM key metrics, it is possible for the patient or health care personnel to take immediate preemptive action. We analyzed, trained, and internally tested three prediction models (Logistic regression, XGBoost, and TabNet) using CGM data from 187 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach combined with feature engineering deployed on the CGM signals was used to predict hyperglycemia, hypoglycemia, and glycemic variability based on consensus targets (time above range ≥5%, time below range ≥4%, coefficient of variation ≥36%). The models were validated in two independent cohorts with a total of 223 additional patients of varying ages. A total of 46 593 weeks of CGM data were included in the analysis. For the best model (XGBoost), the area under the receiver operating characteristic curve (ROC-AUC) was 0.9 [95% confidence interval (CI) = 0.89-0.91], 0.89 [95% CI = 0.88-0.9], and 0.8 [95% CI = 0.79-0.81] for predicting hyperglycemia, hypoglycemia, and glycemic variability in the interval validation, respectively. The validation test showed good generalizability of the models with ROC-AUC of 0.88 to 0.95, 0.84 to 0.89, and 0.80 to 0.82 for predicting the glycemic outcomes. Prediction models based on real-world CGM data can be used to predict the risk of unstable glycemic control in the forthcoming week. The models showed good performance in both internal and external validation cohorts.

MRI-Based Multi-Class Relevance Vector Machine Classification of Neurodegenerative Diseases.

Machine learning algorithms are a promising automated candidate that can help mitigate the growing need for dementia experts. Despite the substantial development in MRI-based machine learning analyses, case misclassification is a universal finding, yet the reasons behind misclassification are poorly understood. We implemented a multi-class classification approach that uses relevance vector machine and logistic classification to classify research participants based on their whole-brain T1-weighted MRI scans. A total of 468 participants from seven diagnostic classes were included: 144 healthy controls, 84 Alzheimer's disease, 108 behavioral variant frontotemporal dementia (bvFTD), 30 semantic variant primary progressive aphasia (svPPA), 30 non-fluent variant primary progressive aphasia (nfvPPA), 30 corticobasal syndrome (CBS), and 42 progressive supranuclear palsy syndrome (PSPS). We compared the algorithm's diagnostic accuracy against the clinical, pathological, genetic, and quantitative imaging data. The exact neurodegenerative syndrome was predicted in 71% of the cases, the neurodegenerative disease spectrum was predicted in 80% of the cases, and the algorithm distinguished controls from any dementia in 85% of the cases. The algorithm showed high performance in diagnosing healthy controls, moderate performance in diagnosing AD, bvFTD, and svPPA, and low performance in diagnosing CBS, nfvPPA, and PSPS. Based on the quantitative imaging data, most of the misclassified neurodegenerative cases had minimal atrophy and brain volumes comparable to healthy controls. In AD, early-onset AD cases with minimal brain atrophy represented most of the misclassified cases. In bvFTD, FTD genetic mutation carriers (predominantly C9orf72 repeat expansion), FTD phenocopy, patients meeting only possible bvFTD criteria represented most misclassified cases. Case misclassification in machine learning studies in neurodegenerative diseases results from neurodegenerative disease heterogeneity and the limitations of structural MRI's ability to capture the whole gamut of biological changes. Larger and more inclusive datasets that are representative of population biologic heterogeneity are needed to train better machine learning techniques, and a margin of error is expected and should be acceptable, like the uncertainty of a clinical diagnosis by a dementia expert.

An SCA-based classifier for motor imagery EEG classification

Efficient and accurate multi-class classification of electroencephalogram (EEG) signals poses a significant challenge in the development of motor imagery-based brain–computer interface (MI-BCI). Drawing inspiration from the sine cosine algorithm (SCA), a widely employed swarm intelligence algorithm for optimization problems, we proposed a novel population-based classification algorithm for EEG signals in this article. To fully leverage the characteristics contained in EEG signals, multi-scale sub-signals were constructed in terms of temporal windows and spectral bands simultaneously, and the common spatial pattern (CSP) features were extracted from each sub-signal. Subsequently, we integrated the multi-center optimal vectors mechanism into the classical SCA, resulting in the development of a multi-center SCA (MCSCA) classifier. During the classification stage, the label was assigned to the test trials by evaluating the Euclidean distance between their feature vectors and each optimal vector in MCSCA. Additionally, the weights of feature vectors were exploited to select the sub-signal of specific temporal windows and spectral bands for feature reduction, thereby declining computational effort and eliminating data redundancy. To validate the performance of the MCSCA classifier, we conducted four-class classification experiments using the BCI Competition IV dataset 2a, achieving an average classification accuracy of 71.89%. The experimental results show that the proposed algorithm offers a novel and effective approach for EEG classification.

Semi-Supervised Subcategory Centroid Alignment-Based Scene Classification for High-Resolution Remote Sensing Images

It is usually hard to obtain adequate annotated data for delivering satisfactory scene classification results. Semi-supervised scene classification approaches can transfer the knowledge learned from previously annotated data to remote sensing images with scarce samples for satisfactory classification results. However, due to the differences between sensors, environments, seasons, and geographical locations, cross-domain remote sensing images exhibit feature distribution deviations. Therefore, semi-supervised scene classification methods may not achieve satisfactory classification accuracy. To address this problem, a novel semi-supervised subcategory centroid alignment (SSCA)-based scene classification approach is proposed. The SSCA framework is made up of two components, namely the rotation-robust convolutional feature extractor (RCFE) and the neighbor-based subcategory centroid alignment (NSCA). The RCFE aims to suppress the impact of rotation changes on remote sensing image representation, while the NSCA aims to decrease the impact of intra-category variety across domains on cross-domain scene classification. The SSCA algorithm and several competitive approaches are validated on two datasets to demonstrate its effectiveness. The results prove that the proposed SSCA approach performs better than most competitive approaches by no less than 2% overall accuracy.

A Deep Learning Approach for Automatic Music Genre Classification

A Deep Learning Approach for Automatic Music Genre Classification

Characterizing long-term tree species dynamics in Canada’s forested ecosystems using annual time series remote sensing data

Mapping tree species and changes in species distribution over time enables monitoring of successional dynamics and linking of realized species distributions to regional, climatic, and disturbance processes. Such knowledge is valuable for informing forest management activities regarding the role of climate change and various types of forest disturbances on tree species distributions and successional processes. In this study, we used time-series Landsat imagery to produce annual maps of dominant tree species (n = 37 tree species classes) from 1984 to 2022 at a 30-m spatial resolution for the 650 Mha of Canada’s forested ecosystems. The classification approach was based on spectral, geographic, climatic, and topographic descriptive metrics and was independently calibrated and validated with data from Canada’s National Forest Inventory. Preliminary results were informed by disturbance events and post-processed to ensure consistency of the annual species maps. Assessment of the resulting annual species maps using independent validation data resulted in an overall accuracy of 86.1 % ± 0.14 % (95 %-confidence interval). Over the study period, Canada’s treed area increased from 335 to 359 Mha. The area dominated by conifers increased in absolute terms but decreased in relative terms (from 86 % to 84.9 %), especially in western ecozones where wildfire is the main agent of disturbance. The area dominated by black spruce (Picea mariana), the most common tree species in Canada, remained stable, but its relative area decreased by 4.6 %. The area dominated by balsam fir (Abies balsamea, 1.5 %), trembling aspen (Populus tremuloides, 0.9 %), jack pine (0.5 %), and sugar maple (Acer saccharum, 0.4 %) increased. In burned areas, the prevalence of black spruce (74.7 %) and jack pine (Pinus banksiana, 14.6 %) was greater than their prevalence in Canada’s forested ecosystems overall (58.7 % and 3.8 %, respectively), while trembling aspen (2.4 % vs. 10 %) and subalpine fir (1.1 % vs. 4.6 %; Abies lasiocarpa) were underrepresented in burned areas. The area dominated by black spruce was underrepresented in harvested areas (46.8 % vs. 58.7 %) whereas balsam fir (6.9 % vs. 3 %), Engelmann spruce (5.5 % vs. 2 %; Picea engelmannii), red spruce (1.8 % vs. 0.4 %; Picea rubens), lodgepole pine (11.2 % vs. 5.6 %; Pinus contorta), Douglas-fir (2.7 % vs. 1.3 %; Pseudotsuga menziesii), and western hemlock (4.8 % vs. 2 %; Tsuga heterophylla) were found to be overrepresented. Both post-fire and post-harvest dynamics indicated a general trend of regeneration to the same pre-disturbance tree species, with post-harvest landscapes exhibiting a greater variety of different dominant tree species. These results provide valuable information for sustainable forest management and can inform conservation strategies by helping to better understand the short- and long-term effects of forest disturbances on species presence and distribution.

Text mining approach for feature extraction and cartilage disease grade classification using knee MRI radiology reports

MRI radiology reporting processes can be improved by exploiting structured and semantically labelled data that can be fed to artificial intelligence (AI) tools. AI-based tools assisting radiology reporting can help to automatically individuate cartilage grading in textual magnetic resonance imaging (MRI) reports, thus supporting clinicians' decisions regarding medical imaging utilisation, diagnosis and treatment. In this study, we extracted information (clinical findings, observations, anatomical regions, etc.) and classified knee cartilage degradation from medical reports utilising transfer-learning techniques applied to the Bidirectional Encoder Representations from Transformers (BERT) model and its variants, pre-trained on an Italian-language corpus. To realise this objective, we used a dataset of 750 MRI knee reports written by three radiologists who contributed to a manual annotation process to perform text classification (TC) and named entity recognition (NER) tasks. The dataset was obtained from an internal database of the IRCCS SYNLAB SDN. Seventy percent of the dataset was used for training, 10% was used for validation and 20% was used for testing. The best-performing configurations for NER and TC tasks were based on the pre-trained BERT model. The macro F1-scores obtained with the NER and TC models are 0.89 and 0.81, respectively. The accuracies calculated on the test set for both tasks are 0.96 and 0.99, respectively.

Hybridization of Machine Learning Models for Alzheimers Disease Classification

Alzheimer's disease (AD), is a gradual cognitive decline and memory impairment. It is a major health concern worldwide. Despite intensive research efforts, accurate and early diagnosis remains difficult to achieve, largely due to the complexity of AD pathology and the absence of definitive biomarkers. Existing diagnostic approaches often rely on costly and invasive procedures, leading to delays in diagnosis and treatment initiation, and limiting the effectiveness of therapeutic interventions. To overcome these issues, this work suggests a novel approach for AD classification using EEG signals. EEG signals offer a non-invasive and cost-effective means of assessing brain activity, making them an attractive candidate for biomarker discovery and disease classification. The proposed work integrates preprocessing, feature extraction, and classification methodologies to accurately differentiate between AD, normal/healthy states, and Frontotemporal Dementia (FTD). The proposed solution begins with Sequential Savitzky-Golay filtering (SEQ-SG) to enhance the quality of EEG signals by reducing noise and enhancing relevant features. Subsequently, an Improved Principal Component Analysis (IPCA) approach is employed for feature extraction, incorporating feature scaling using StandardScaler to ensure uniform contribution from all features. Finally, classification is achieved using a hybrid approach named HMLCAD (Hybridization of Machine Learning for Classification of Alzheimer's Disease), which combines Random Forest and Gradient Boosting through a voting classifier ensemble. This methodology offers a promising framework for accurate and early detection of AD, enabling timely intervention and improved patient outcomes.

A comparative study on machine learning approaches for rock mass classification using drilling data

Current rock engineering design in drill and blast tunnelling primarily relies on engineers' observational assessments. Measure While Drilling (MWD) data, a high-resolution sensor dataset collected during tunnel excavation, is underutilised, mainly serving for geological visualisation. This study aims to automate the translation of MWD data into actionable metrics for rock engineering. It seeks to link data to specific engineering actions, thus providing critical decision support for geological challenges ahead of the tunnel face. Leveraging a large and geologically diverse dataset of ∼500,000 drillholes from 15 tunnels, the research introduces models for accurate rock mass quality classification in a real-world tunnelling context. Both conventional machine learning and image-based deep learning are explored to classify MWD data into Q-classes and Q-values—examples of metrics describing the stability of the rock mass—using both tabular- and image data. The results indicate that the K-nearest neighbours algorithm in an ensemble with tree-based models using tabular data effectively classifies rock mass quality. It achieves a cross-validated balanced accuracy of 0.86 in classifying rock mass into the Q-classes A, B, C, D, E1, E2, and 0.95 for a binary classification with E versus the rest. Classification using a CNN with MWD-images for each blasting round resulted in a balanced accuracy of 0.82 for binary classification. Regressing the Q-value from tabular MWD-data achieved cross-validated R2 and MSE scores of 0.80 and 0.18 for a similar ensemble model as in classification. High performance in regression and classification boosts confidence in automated rock mass assessment. Applying advanced modelling on a unique dataset demonstrates MWD data's value in improving rock mass classification accuracy and advancing data-driven rock engineering design, reducing manual intervention.

Hybrid Naïve Bayes Gaussian mixture models and SAR polarimetry based automatic flooded vegetation studies using PALSAR-2 data

Flood mapping using Synthetic Aperture Radar (SAR) data impose limitations in fully distinguishing flood under vegetation due to false double bounce returns from inundated tree trunks along with seasonal heterogeneities devised from changing land cover settings. In addition, rapid mapping of flooded vegetation is challenging during near real time applications. In this paper a fully automatic novel supervised classification approach called polarimetric Naïve Bayes is proposed that combines polarimetric information with series of Gaussian mixture models in Naïve Bayes framework to detect various flooded vegetation classes. It also allows the user to choose class configuration and eliminates creation of Region of Interest (ROI) for supervised training. The proposed approach uses scattering information from pre monsoon PolSAR dataset in training step to create ROIs for buildings and other features. In the next step series of Gaussian Mixtures are used for density estimation for different features in Bayesian multiclass problem. The newly developed classifier applied on 2016 Assam flood event resulted in precise mapping of at least three different vegetation classes under flood such as submerged vegetation, wetlands and floating vegetation. Under optimal class configuration, the approach showed better performance compared to other supervised techniques applied on the same data set such as MLE, Mahalanobis, Minimum Euclidean distance, and SVM classifications in delineating flood, submerged vegetation, wetlands and floating vegetation with Producer’s Accuracy of 98.6%, 81.1%, 94% and 51.5% respectively and combined Overall accuracy of 95.5% for flooded vegetation class. This method also detected multiple vegetation classes with better accuracy compared to similar methods.

Deep Learning and Recurrent Signature Based Classification for Sensor-Based HAR: Addressing Explainability and Complexity in 5G Networks

When it comes to clinical applications, sensor-based human activity recognition (HAR) is invaluable, and numerous machine learning algorithms have effectively used to obtain excellent presentation. Using a variety of on-body sensors, these systems attempt to ascertain the subject's status relative to their immediate surroundings. There was a time when feature extraction was done by hand, but now more and more people are using Artificial Neural Networks (ANNs). A number of innovative approaches to HAR have surfaced since the advent of deep learning. Problems arise, however, for sensor-based HAR classification algorithms in today's communication networks. Among these, you can find solutions to problems like deal with complicated and large-scale data signals, extract characteristics from complicated datasets, and meet explainability standards. For complicated 5G networks, these difficulties become even more apparent. In particular, explainability is now critical for the broad use of sensor-based HAR in 5G networks and beyond. The research suggests a classification approach based on path signatures, recurrent signature (ReS), to address these issues. This cutting-edge model employs deep-learning (DL) approaches to circumvent the tedious feature selection challenge. Furthermore, the study investigates how to improve the ReS model's classification accuracy by using graph-based optimisation methods. To test how well the suggested framework worked, to dug deep into the publicly available dataset, which included a separate set of tasks. The paper's empirical results on AReM datasets achieved an average accuracy of 96%.