Traditional Machine Learning Classifiers Research Articles

Identification of Membrane Protein Types Based Using Hypergraph Neural Network

Introduction: Membrane proteins play an important role in living organisms as one of the main components of biological membranes. The problem in membrane protein classification and prediction is an important topic of membrane proteomics research because the function of proteins can be quickly determined if membrane protein types can be discriminated. Methods: Most current methods to classify membrane proteins are labor-intensive and require a lot of resources. In this study, five methods, Average Block (AvBlock), Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Histogram of Orientation Gradient (HOG), and Pseudo-PSSM (PsePSSM), were used to extract features in order to predict membrane proteins on a large scale. Then, we combined the five obtained feature matrices and constructed the corresponding hypergraph association matrix. Finally, the feature matrices and hypergraph association matrices were integrated to identify the types of membrane proteins using a hypergraph neural network model (HGNN). Results: The proposed method was tested on four membrane protein benchmark datasets to evaluate its performance. The results showed 92.8%, 88.6%, 88.2%, and 99.0% accuracy on each of the four datasets. Conclusion: Compared to traditional machine learning classifier methods, such as Random Forest (RF), Support Vector Machine (SVM), etc., HGNN prediction performance was found to be better.

Deep learning approach for recognizing cold and warm thermal discomfort cues from videos

Reducing building energy consumption while maintaining individual thermal comfort levels is a challenge. Energy-efficiency strategies that control indoor conditions, with the aim of reducing energy waste and increasing occupant comfort, require the capture of personal thermal comfort preferences in their feedback loop. However, direct feedback from surveys and invasive methods, which have been proposed to collect personal thermal comfort preferences, are impractical in real-world settings due to the decay of commitment, need for repeated feedback, and invasiveness. To address this challenge, this paper proposes a novel non-invasive approach for automated thermal discomfort detection using a deep learning-based model for thermal discomfort cue recognition. The model recognizes nine discomfort cues from video recordings of occupants in indoor work settings, which could be associated with the cold or warm thermal discomfort states. In developing the model, the architectures of two different residual neural networks (ResNets) that learn spatial and local information were tested using data augmentation and transfer learning techniques, and then compared with the performance of (1) traditional machine learning classifiers that used video frames mapped to the feature space of the ResNets; and (2) the ResNets extended with a long short-term memory (LSTM) layer that learns temporal information from the frame sequence. Approaches that accounted for temporal and spatial information outperformed those that only took spatial information into consideration. The final thermal discomfort cue recognition model achieved a weighted F1-measure of 85% in correctly classifying the cues. The proposed approach could help provide rapid and effortless feedback in building energy management systems to reduce building energy waste while providing comfortable indoor conditions towards increased occupant health and productivity.

Large-scale quantification of groundwater recharge threshold conditions using machine learning classifications: An attempt over the Australian continent

The large-scale quantification of groundwater recharge threshold conditions is a bottleneck in the field of research, considering that groundwater recharge processes can be quite complex and affected by different factors in different regions. Traditional statistical approaches have either focused on local to regional scales or are limited to a single factor such as rainfall, resulting in a lack of a comprehensive understanding of groundwater recharge mechanisms on large scales. Considering that finding a threshold to instantly determine whether the groundwater is in the state of recharge or discharge is a classification task involving multiple factors, machine learning techniques with self-learning capabilities, efficient processing of big data, and mining relationships between multiple factors is, thus, applied to this study. In this study, three traditional machine learning classification techniques are explored; Classification and Regression Tree (CART), Random Forest (RF), and Logistical Regression (LR), to quantify specific threshold values for each condition (including rainfall, evaporation, soil moisture, runoff and vegetation) since they are more interpretable compared to advanced machine learning techniques such as neural networks. Using the Australian continent as an example, CART is the fastest method and provides an average classification accuracy (76%) at almost the same levels compared to RF (77–78%) and LR (79–80%). Meanwhile, CART is the only method to rank the importance of conditions while providing a specific threshold for each condition. When inferring the groundwater recharge mechanism through threshold conditions, the CART method suggests that a primary (the most important) threshold condition is sufficient for most parts of the Australian continent, e.g., rainfall as the primary threshold condition in northern Australia indicates a direct recharge mechanism. Only the coastal areas of southeastern and southwestern Australia are dominated by multiple threshold conditions, showing the complex groundwater recharge mechanism. Overall, the significance of this work is to provide the spatial maps of threshold conditions that mainly control groundwater recharge and their specific threshold values, which are crucial for managers to carry out a good plan over a large area. More importantly, this study demonstrates the potential of traditional machine learning methods to reveal groundwater recharge mechanisms, which may help further refine the development of groundwater models in the future.

ECG Heartbeat Classification Using Machine Learning and Metaheuristic Optimization for Smart Healthcare Systems.

Early diagnosis and classification of arrhythmia from an electrocardiogram (ECG) plays a significant role in smart healthcare systems for the health monitoring of individuals with cardiovascular diseases. Unfortunately, the nonlinearity and low amplitude of ECG recordings make the classification process difficult. Thus, the performance of most traditional machine learning (ML) classifiers is questionable, as the interrelationship between the learning parameters is not well modeled, especially for data features with high dimensions. To address the limitations of ML classifiers, this paper introduces an automatic arrhythmia classification approach based on the integration of a recent metaheuristic optimization (MHO) algorithm and ML classifiers. The role of the MHO is to optimize the search parameters of the classifiers. The approach consists of three steps: the preprocessing of the ECG signal, the extraction of the features, and the classification. The learning parameters of four supervised ML classifiers were utilized for the classification task; support vector machine (SVM), k-nearest neighbors (kNNs), gradient boosting decision tree (GBDT), and random forest (RF) were optimized using the MHO algorithm. To validate the advantage of the proposed approach, several experiments were conducted on three common databases, including the Massachusetts Institute of Technology (MIT-BIH), the European Society of Cardiology ST-T (EDB), and the St. Petersburg Institute of Cardiological Techniques 12-lead Arrhythmia (INCART). The obtained results showed that the performance of all the tested classifiers were significantly improved after integrating the MHO algorithm, with the average ECG arrhythmia classification accuracy reaching 99.92% and a sensitivity of 99.81%, outperforming the state-of the-art methods.

TALK: Tracking Activities by Linking Knowledge

Dependable and accurate monitoring of elderly at home becomes crucial to limit both the costs and human efforts of following up elderly for establishing a healthy care system. Human Activity Recognition (HAR) tools, based on sensors installed in smart homes, will become an important tool to provide useful information to the caregiver when something happens in the house of an elderly and care is required. The current available detection tools either exist out of interpretable knowledge-driven techniques or scalable data-driven ones. In this paper, a hybrid methodology that combines both approaches is designed and evaluated to Track Activities by Linking Knowledge (TALK). Both sensor data and their link to the relevant domain knowledge about where those sensors are installed, the performed activities that occur, and how the household is constructed, are generalized in a specific knowledge graph (KG) structure to represent continuous events. The interpretable knowledge graph embedding technique Instance Neighboring using Knowledge (INK) is then used to transform these events inside the KG to a tabular format, which can be used by any traditional machine learning classifier to create a HAR tool. The TALK methodology is evaluated on two HAR datasets and shows (a) that TALK outperforms both traditional automated data-driven as well as knowledge-driven techniques in terms of predictive performance, and (b) how TALK can be easily used in a more out of lab environment. All these results and the interpretable aspects show that TALK can become an important tool to monitor elderly in their homes efficiently, effectively and with less intrusive techniques.

ARNLI: ARABIC NATURAL LANGUAGE INFERENCE ENTAILMENT AND CONTRADICTION DETECTION

Natural Language Inference (NLI) is a hot topic research in natural language processing, contradiction detection between sentences is a special case of NLI. This is considered a difficult NLP task which has a big influence when added as a component in many NLP applications, such as Question Answering Systems, text Summarization. Arabic Language is one of the most challenging low-resources languages in detecting contradictions due to its rich lexical, semantics ambiguity. We have created a dataset of more than 12k sentences and named ArNLI, that will be publicly available. Moreover, we have applied a new model inspired by Stanford contradiction detection proposed solutions on English language. We proposed an approach to detect contradictions between pairs of sentences in Arabic language using contradiction vector combined with language model vector as an input to machine learning model. We analyzed results of different traditional machine learning classifiers and compared their results on our created dataset (ArNLI) and on an automatic translation of both PHEME, SICK English datasets. Best results achieved using Random Forest classifier with an accuracy of 99%, 60%, 75% on PHEME, SICK and ArNLI respectively.

Soft reordering one-dimensional convolutional neural network for credit scoring

Credit scoring systems have seen revolutionary development in recent decades, with many classification algorithms being proposed. However, with the increase in the data volume, the performance of traditional algorithms tends to encounter bottlenecks. Although deep learning methods have advantages in handling big data, they are not commonly applied in credit scoring. As one of the most frequently used methods in deep learning, convolutional neural network (CNN) use convolutional kernels as feature extraction tools and has been very successful in tasks related to images or text. This is because image and text data naturally have a structural characteristic called spatial local correlation, which means that the pixels or tokens covered by the same convolutional kernel are highly correlated, and they can be jointly processed to extract meaningful feature representations. However, the tabular data used for credit scoring do not naturally have such a characteristic. The main contribution of this paper is to propose a novel end-to-end soft reordering one-dimensional CNN (SR-1D-CNN), which can adaptively reorganize the original tabular data and make them more conducive to CNN learning. Several real-world credit scoring datasets of different sizes are used for a comprehensive comparison with traditional machine learning classifiers and other deep learning methods. The experimental results demonstrate that the soft reordering mechanism can effectively improve the classification effect of the CNN for tabular data. With the increase in the data scale, the proposed approach obtains superior results to those of other benchmark models.

A Quantitative Plant Type Recognition algorithm based on Gene Expression Programming

Efficient and accurate plant type identification is an important foundation for biological research. The existing traditional machine learning classification algorithms have the defects of low classification accuracy in solving plant type recognition and cannot quantitatively give the corresponding class recognition model. In this paper, we propose a Quantitative Plant Type Recognition algorithm based on Gene Expression Programming (QPTR-GEP). Firstly, the plant type data set to be processed is preprocessed; then, the GEP population corresponding to plant type identification is constructed, and the corresponding quantitative identification function expressions are obtained after genetic operations such as mutation, recombination and transposition; finally, the classification expression with the highest fitness is used as the classifier corresponding to a single plant type, and the classifier model integrating the data set containing all plant type is put into the data set for plant type identification. Experimental results on the open source Iris demonstrate that our proposed algorithm outperforms SVM and Decision Tree algorithms for plant type identification.

Lexical Complexity Prediction: An Overview

The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modeling has been applied to identify complex words in texts and substitute them for simpler alternatives. In this article, we present an overview of computational approaches to lexical complexity prediction focusing on the work carried out on English data. We survey relevant approaches to this problem which include traditional machine learning classifiers (e.g., SVMs, logistic regression) and deep neural networks as well as a variety of features, such as those inspired by literature in psycholinguistics as well as word frequency, word length, and many others. Furthermore, we introduce readers to past competitions and available datasets created on this topic. Finally, we include brief sections on applications of lexical complexity prediction, such as readability and text simplification, together with related studies on languages other than English.

Accurate Encrypted Malicious Traffic Identification via Traffic Interaction Pattern Using Graph Convolutional Network

Telecommuting and telelearning have gradually become mainstream lifestyles in the post-epidemic era. The extensive interconnection of massive terminals gives attackers more opportunities, which brings more significant challenges to network traffic security analysis. The existing attacks, often using encryption technology and distributed attack methods, increase the number and complexity of attacks. However, the traditional methods need more analysis of encrypted malicious traffic interaction patterns and cannot explore the potential correlations of interaction patterns in a macroscopic and comprehensive manner. Anyway, the changes in interaction patterns caused by attacks also need further study. Therefore, to achieve accurate and effective identification of attacks, it is essential to comprehensively describe the interaction patterns of malicious traffic and portray the relations of interaction patterns with the appearance of attacks. We propose a method for classifying attacks based on the traffic interaction attribute graph, named G-TIAG. At first, the G-TIAG studies interaction patterns of traffic describes the construction rule of the graphs and selects the attributive features of nodes in each graph. Then, it uses a convolutional graph network with a GRU and self-attention to classify benign data and different attacks. Our approach achieved the best classification results, with 89% accuracy and F1-Score, 88% recall, respectively, on publicly available datasets. The improvement is about 7% compared to traditional machine learning classification results and about 6% compared to deep learning classification results, which finally successfully achieved the classification of attacks.

RETAD

Due to the rapid advancement of wireless sensor and location technologies, a large amount of mobile agent trajectory data has become available. Intelligent city systems and video surveillance all benefit from trajectory anomaly detection. The authors propose an unsupervised reconstruction error-based trajectory anomaly detection (RETAD) method for vehicles to address the issues of conventional anomaly detection, which include difficulty extracting features, are susceptible to overfitting, and have a poor anomaly detection effect. RETAD reconstructs the original vehicle trajectories through an autoencoder based on recurrent neural networks. The model obtains moving patterns of normal trajectories by eliminating the gap between the reconstruction results and the initial inputs. Anomalous trajectories are defined as those with a reconstruction error larger than anomaly threshold. Experimental results demonstrate that the effectiveness of RETAD in detecting anomalies is superior to traditional distance-based, density-based, and machine learning classification algorithms on multiple metrics.

A novel application of machine learning and zero-shot classification methods for automated abstract screening in systematic reviews

Zero-shot classification refers to assigning a label to a text (sentence, paragraph, whole paper) without prior training. This is possible by teaching the system how to codify a question and find its answer in the text. In many domains, especially health sciences, systematic reviews are evidence-based syntheses of information related to a specific topic. Producing them is demanding and time-consuming in terms of collecting, filtering, evaluating and synthesising large volumes of literature, which require significant effort performed by experts. One of its most demanding steps is abstract screening, which requires scientists to sift through various abstracts of relevant papers and include or exclude papers based on pre-established criteria. This process is time-consuming and subjective and requires a consensus between scientists, which may not always be possible. With the recent advances in machine learning and deep learning research, especially in natural language processing, it becomes possible to automate or semi-automate this task. This paper proposes a novel application of traditional machine learning and zero-shot classification methods for automated abstract screening for systematic reviews. Extensive experiments were carried out using seven public datasets. Competitive results were obtained in terms of accuracy, precision and recall across all datasets, which indicate that the burden and the human mistake in the abstract screening process might be reduced.

A Novel Sleep Staging Method based on EEG and ECG Multimodal Features Combination.

Accurate sleep staging evaluates the quality of sleep, supporting the clinical diagnosis and intervention of sleep disorders and related diseases. Although previous attempts to classify sleep stages have achieved high classification performance, little attention has been paid to integrating the rich information in brain and heart dynamics during sleep for sleep staging. In this study, we propose a generalized EEG and ECG multimodal feature combination to classify sleep stages with high efficiency and accuracy. Briefly, a hybrid features combination in terms of multiscale entropy and intrinsic mode function are used to reflect nonlinear dynamics in multichannel EEGs, along with heart rate variability measures over time/frequency domains, and sample entropy across scales are applied for ECGs. For both the max-relevance and min-redundancy method and principal component analysis were used for dimensionality reduction. The selected features were classified by four traditional machine learning classifiers. Macro-F1 score, macro-geometric mean, and Cohen kappa value are adopted to evaluate the classification performance of each class in an imbalanced dataset. Experimental results show that EEG features contribute more to wake stage classification while ECG features contribute more to deep sleep stages. The proposed combination achieves the highest accuracy of 84.3% and the highest kappa value of 0.794 on the support vector machine in the ISRUC-S3 dataset, suggesting the proposed multimodal features combination is promising in accuracy and efficiency compared to other state-of-the-art methods.

Securing healthcare data management using machine learning and blockchain technology: A comparative performance evaluation of support vector machine and conventional classifiers

As access to healthcare has become more central to people’s daily lives, the amount of medical big data has grown exponentially. Wearable Internet of Things (IoT)-reliant technology is gaining popularity in the medical field as a means to improve patient care and reduce wait times. In recent years, billions of sensors, devices, and machines have been hooked up to the web. One such technology, remote patient monitoring, is increasingly used in modern patient care and treatment. In addition, these developments pose substantial security issues about the recording of transaction data and the transmission of information itself, and pose considerable dangers to users’ privacy. Concerns about the privacy of a patient’s medical records have the ability to discontinue treatment, putting the patient’s life in threat. Thus, a system is proposed using machine learning in combination with blockchain technology to allow secure management as well as analysis of large amounts of healthcare data. With the help of machine learning, it is feasible to sort through all of the data and extract out only the most pertinent information. This is accomplished with the help of trained methodologies. After this data has been saved, the next issue will be the exchange of data and ensuring its trustworthiness. The concept of blockchain is introduced at this point. The Blockchain technology relies on consensus to ensure that all data is accurate and that all transactions are conducted in a safe manner. The management of healthcare is one area where blockchain technology offers the ability to have a huge impact by placing patients at the center of the system and improving the privacy and portability of health records. This study is primarily concerned with finding solutions to issues relating to the administration of healthcare data by utilizing Blockchain technology and incorporating some crucial characteristics developed with Machine Learning. The performance evaluation of proposed Support Vector Machine is compared with the other conventional machine learning classifiers. It is observed from the experimental finding that performance accuracy of Support vector machine is 98% which is better as compared to other traditional machine learning classifiers.

Investigation of Android Malware Using Deep Learning Approach

In recent days the usage of android smartphones has increased extensively by end-users. There are several applications in different categories banking/finance, social engineering, education, sports and fitness, and many more applications. The android stack is more vulnerable compared to other mobile platforms like IOS, Windows, or Blackberry because of the open-source platform. In the Existing system, malware is written using vulnerable system calls to bypass signature detection important drawback is might not work with zero-day exploits and stealth malware. The attackers target the victim with various attacks like adware, backdoor, spyware, ransomware, and zero-day exploits and create threat hunts on the day-to-day basics. In the existing approach, there are various traditional machine learning classifiers for building a decision support system with limitations such as low detection rate and less feature selection. The important contents taken for building model from android applications like Intent Filter, Permission Signature, API Calls, and System commands are taken from the manifest file. The function parameters of various machine and deep learning classifiers like Nave Bayes, k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), Ada Boost, and Multi-Layer Perceptron (MLP) are done for effective results. In our proposed work, we have used an unsupervised learning multilayer perceptron with multiple target labels and built a model with a better accuracy rate compared to logistic regression, and rank the best features for detection of applications and classify as malicious or benign can be used as threat model by online antivirus scanners.

Accurate, timely, and portable: Course-agnostic early prediction of student performance from LMS logs

In higher education, providing personalized feedback and support to students is a significant challenge. Early warning systems can help by identifying both at-risk and high-performing students, allowing for timely interventions and enhanced learning opportunities. In our study, we used a year's worth of data from an information management school to build predictive models for two binary classification problems: identifying at-risk students and high-performing students. We employed traditional machine learning classifiers and long-short term memory units (LSTM), testing them at various stages of course completion. The best performance was achieved using all course data, with an AUC of 0.756 for at-risk students and 78.2% accuracy for high-performing students using Random Forest and Extremely Randomized Trees, respectively. We found that early prediction was possible as early as 25% course completion. Although LSTM showed inferior performance, it offered practical advantages for early prediction. Our findings suggest that static LMS logs can be reliable indicators of student success early in a course, and a course-agnostic time-dependent representation of the number of clicks can offer a worthwhile tradeoff between predictive performance and simplicity in implementation in some instances. These findings have important implications as they suggest the potential for automated early warning systems that can help educators identify students of interest and allocate resources where they are most needed. However, implementing these systems in real-time requires clear protocols and responsible policies. Further research should explore the generalizability of findings across different contexts and continuously evaluate their real-world effectiveness.

Evaluation of Attention-Based LSTM and Bi-LSTM Networks For Abstract Text Classification in Systematic Literature Review Automation

Systematic Review (SR) presents the highest form of evidence in research for decision and policy-making. Nonetheless, the structured steps involved in carrying out SRs make it demanding for reviewers. Many studies have projected the abstract screening stage in the SR process to be the most burdensome for reviewers, thus automating this stage with artificial intelligence (AI). However, majority of these studies focus on using traditional machine learning classifiers for the abstract classification. Thus, there remain a gap to explore the potential of deep learning techniques for this task. This study seeks to bridge the gap by exploring how LSTM and Bi-LSTM models together with GloVe for vectorisation can accelerate this stage. As a further aim to increase precision while sustaining a recall >= 95% due to precision-recall trade-off, attention mechanics is added to these classifiers. The final experimental results obtained showed that Bi-LSTM with attention has the capacity to expedite citation screening.

Drug Recommendation from Diagnosis Codes: Classification vs. Collaborative Filtering Approaches.

Over time, large amounts of clinical data have accumulated in electronic health records (EHRs), making it difficult for healthcare professionals to navigate and make patient-centered decisions. This underscores the need for healthcare recommendation systems that help medical professionals make faster and more accurate decisions. This study addresses drug recommendation systems that generate an appropriate list of drugs that match patients' diagnoses. Currently, recommendations are manually prepared by physicians, but this is difficult for patients with multiple comorbidities. We explored approaches to drug recommendations based on elderly patients with diabetes, hypertension, and cardiovascular disease who visited primary-care clinics and often had multiple conditions. We examined both collaborative filtering approaches and traditional machine-learning classifiers. The hybrid model between the two yielded a recall at 5 of 76.61%, a precision at 5 of 46.20%, a macro-averaged area under the curve of 74.52%, and an average physician agreement of 47.50%. Although collaborative filtering is widely used in recommendation systems, our results showed that it consistently underperformed traditional classification. Collaborative filtering was sensitive to class imbalances and favored the more popular classes. This study highlighted challenges that need to be addressed when developing recommendation systems in EHRs.

Addressing religious hate online: from taxonomy creation to automated detection.

Abusive language in online social media is a pervasive and harmful phenomenon which calls for automatic computational approaches to be successfully contained. Previous studies have introduced corpora and natural language processing approaches for specific kinds of online abuse, mainly focusing on misogyny and racism. A current underexplored area in this context is religious hate, for which efforts in data and methods to date have been rather scattered. This is exacerbated by different annotation schemes that available datasets use, which inevitably lead to poor repurposing of data in wider contexts. Furthermore, religious hate is very much dependent on country-specific factors, including the presence and visibility of religious minorities, societal issues, historical background, and current political decisions. Motivated by the lack of annotated data specifically tailoring religion and the poor interoperability of current datasets, in this article we propose a fine-grained labeling scheme for religious hate speech detection. Such scheme lies on a wider and highly-interoperable taxonomy of abusive language, and covers the three main monotheistic religions: Judaism, Christianity and Islam. Moreover, we introduce a Twitter dataset in two languages-English and Italian-that has been annotated following the proposed annotation scheme. We experiment with several classification algorithms on the annotated dataset, from traditional machine learning classifiers to recent transformer-based language models, assessing the difficulty of two tasks: abusive language detection and religious hate speech detection. Finally, we investigate the cross-lingual transferability of multilingual models on the tasks, shedding light on the viability of repurposing our dataset for religious hate speech detection on low-resource languages. We release the annotated data and publicly distribute the code for our classification experiments at https://github.com/dhfbk/religious-hate-speech.

Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models.

Recently, many diseases have negatively impacted people's lifestyles. Among these, knee osteoarthritis (OA) has been regarded as the primary cause of activity restriction and impairment, particularly in older people. Therefore, quick, accurate, and low-cost computer-based tools for the early prediction of knee OA patients are urgently needed. In this paper, as part of addressing this issue, we developed a new method to efficiently diagnose and classify knee osteoarthritis severity based on the X-ray images to classify knee OA in (i.e., binary and multiclass) in order to study the impact of different class-based, which has not yet been addressed in previous studies. This will provide physicians with a variety of deployment options in the future. Our proposed models are basically divided into two frameworks based on applying pre-trained convolutional neural networks (CNN) for feature extraction as well as fine-tuning the pre-trained CNN using the transfer learning (TL) method. In addition, a traditional machine learning (ML) classifier is used to exploit the enriched feature space to achieve better knee OA classification performance. In the first one, we developed five classes-based models using a proposed pre-trained CNN for feature extraction, principal component analysis (PCA) for dimensionality reduction, and support vector machine (SVM) for classification. While in the second framework, a few changes were made to the steps in the first framework, the concept of TL was used to fine-tune the proposed pre-trained CNN from the first framework to fit the two classes, three classes, and four classes-based models. The proposed models are evaluated on X-ray data, and their performance is compared with the existing state-of-the-art models. It is observed through conducted experimental analysis to demonstrate the efficacy of the proposed approach in improving the classification accuracy in both multiclass and binary class-based in the OA case study. Nonetheless, the empirical results revealed that the fewer multiclass labels used, the better performance achieved, with the binary class labels outperforming all, which reached a 90.8% accuracy rate. Furthermore, the proposed models demonstrated their contribution to early classification in the first stage of the disease to help reduce its progression and improve people's quality of life.