Multi-classification Model Research Articles

A Multiclassification Model for Skin Diseases Using Dermatoscopy Images with Inception-v2

Skin cancer represents a significant global public health concern, with over five million new cases diagnosed annually. If not diagnosed at an early stage, skin diseases have the potential to pose a significant threat to human life. In recent years, deep learning has increasingly been used in dermatological diagnosis. In this paper, a multiclassification model based on the Inception-v2 network and the focal loss function is proposed on the basis of deep learning, and the ISIC 2019 dataset is optimised using data augmentation and hair removal to achieve seven classifications of dermatological images and generate heat maps to visualise the predictions of the model. The results show that the model has an average accuracy of 89.04%, a precision of 87.37%, recall of 90.15%, and an F1-score of 88.76%, The accuracy rates of ResNext101, MobileNetv2, Vgg19, and ConvNet are 88.50%, 85.30%, 88.57%, and 86.90%, respectively. These results show that our proposed model performs better than the above models and performs well in classifying dermatological images, which has significant application value.

Geographical Entity Management Model Based on Multi-Classification

Scientific and logical classification is crucial for efficient information storage, management, and sharing. However, there are numerous existing classification systems for geographical entities, and the categories to which the same geographical entity belongs are often different in the business databases constructed according to different classification systems, which brings great obstacles to the management and sharing of geographical information. This study analyzes the complexities of multiple classifications of geographical entities and proposes a multi-classification model for geographical entities based on directed hypergraph theory. This model integrates and transforms different classification systems for the same geographical entity, creating a unified method for expressing multiple classifications. We also designed a data structure to support this unified expression. By implementing this model, the study enables the effective management of geographical entity data, facilitating improved sharing and the exchange of geographical information across different industries and applications. In practical, the multi-classification model proposed in this paper allows geographical entities from different classification systems to be stored and managed within a single geographical database. Data views are then used to provide tailored services to various industry sectors and business applications. This approach effectively reduces data duplication and enhances the efficiency of managing and sharing geographical information. Using land use classification as an example, this study constructs a unified expression of three different land use classification systems based on the multi-classification model. An experiment managing land use data for a specific city was conducted using this model in PostgreSQL. The results indicate that the proposed method not only reduces data redundancy but also improves the query efficiency by over 10% on average compared to the mainstream relational database management mode. This confirms the effectiveness and practical value of the proposed method.

MKELM based multi-classification model for foreign accent identification

The automatic identification of foreign accents can play a crucial role in various speech systems, including speaker identification, e-learning, telephone banking, and more. Additionally, it can greatly enhance the robustness of Automatic Speech Recognition (ASR) systems. Non-native accents in speech signals are characterized by distinct pronunciations, prosody, and voice characteristics of the speaker. However, automatically identifying foreign accents poses significant challenges, particularly in the context of multi-class modeling. Multi-classification models face difficulties in achieving high performance and dealing with computational challenges when confronted with multi-dimensional and unbalanced datasets, such as those with more than two accents. Furthermore, the choice of features remains a bottleneck problem for Foreign Accent Identification (FAID), further hindering performance in these tasks. Consequently, the accuracy of current systems is typically low. To address these challenges, this paper proposes a framework based on the Multi-Kernel Extreme Learning Machine (MKELM) model for the multi-classification of FAID. The MKELM model utilizes a novel weighted scheme to classify various non-native English accents, including Arabic, Chinese, Korean, French, and Spanish. The model first combines Mel-frequency cepstral coefficients (MFCCs) and prosodic features as input, trains pairwise binary classifiers independently, and subsequently employs a weighting scheme to distinguish between classes and identify accents. Through experiments, the proposed model achieves an accuracy rate of 84.72% using a paired weighting scheme. In contrast, the accuracy rate drops to 66.5% when employing the traditional non-weighted multi-classification scheme. A comparison with other models demonstrates the significant advantages of the proposed model in FAID multi-class classification, showcasing improved accuracy, reduced computational complexity (requiring fewer computations, faster learning rates, and shorter training time), and enhanced stability compared to state-of-the-art classification methods.

Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images

BackgroundUltrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD. MethodWe propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images. Result and conclusionOur proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.

Broiler health monitoring technology based on sound features and random forest

The existing broiler health monitoring technology has problems such as low automation, unstable monitoring results, and low practical value, making it difficult to provide timely and reliable broiler health monitoring results. The broiler sound signal can provide feedback on their health. A widely validated and correct experience is to analyze the frequency of coughs in a segment of broiler sound signal to determine the health of the broiler group. Based on this, in this paper, the authors proposed a new broiler health monitoring technology based on sound detection. The broiler health monitoring problem is cleverly transformed into a multi-classification problem, which can be solved by identifying the sound types in broiler sound signals. Specifically, the audio signal collection system was designed to complete signal collection and preliminary signal filtering. Wiener filtering was used for deep signal filtering. The 60-dimensional sound features with good performance from three aspects, time-frequency domain, Mel-Frequency Cepstral Coefficients, and sparse representation were extracted, and a preliminary data set was created. Min-max normalization was used to align the numerical distribution of the data set, and a high-quality data set was created. Multi-classification models based on different classification algorithms and neural networks were trained, and the best-performing Random Forest was obtained, thus parameter optimization was carried out, and the optimal multi-classification model was obtained, achieving a classification accuracy of 91.14%. The visualization platform was built to process the classification results of the multi-classification model, completing majority voting processing and cough rate calculation, thereby achieving broiler health monitoring. In addition, the definitions of cough rate and prediction accuracy were newly proposed. A large number of experiments have verified the feasibility of the broiler health monitoring technology proposed in this paper, with an average prediction accuracy of 98.97% achieved.

Weakly Supervised anomaly detection with privacy preservation under a Bi-Level Federated learning framework

Training a Machine Learning (ML) model in the industrial field faces special challenges, such as data privacy, lack of data, data imbalance, and unlabeled data. Therefore, it is not realistic to gather production data directly from various companies and use them to train a machine learning model. In this paper, we proposed a novel framework named Bi-level Federated Learning (BFL) to tackle the above challenges. In the first level, a Weakly Supervised Anomaly Detection method named Pairwise Relation prediction-based Ordinal regression Network (PRO) is utilized for training a Deep Anomaly Detection (DAD) model under Federated Learning (FL) mechanism. According to the DAD model, anomalies are identified and labeled with ‘anomaly’ tags. In order to train a multi-classification model that can identify different types of defects not just anomalies, the anomalies are manually labeled according to their respective defect types. In the second level, labeled anomaly and normal data are applied to train a multi-classification model under the FL mechanism. A framework is proposed to classify defects in pre-baked carbon anodes. Its performance is verified through a real case study. The results show that the DAD model achieved an acceptable performance with a 0.988 recall and 0.866 F1 score. The multi-classification model has shown good performance on 0.942 accuracy, 0.913 precision, 0.903 recall, and 0.906 F1. The results of the BFL exhibit improved performance compared to our previous work and classical ML methods.

Adopting combination machine learning models could reduce hospital length of stay for oncology patients.

11084 Background: Integra Connect previously created in-patient (IP) admission prediction model based on OCM data. One of the challenges for practices in a value-based care (VBC) program is to provide continuous care-coordination during and after an IP admission. Our objective is to show how adopting combination machine learning (ML) models can predict IP length of stay (LOS). Potential benefits include an overall reduction in LOS which could minimize the risk of hospital acquired conditions. Methods: ML models were trained on 5 major cancer types (Lung Cancer, Multiple Myeloma, Lymphoma, Small Intestine / Colorectal Cancer, High-risk Breast Cancer') from 7 OCM practices of PP4-PP9 data, excluding surgery IP admission. The top 5 cancer types accounted for ~50% of total in-patient admissions and ~50% of total LOS in days. The IP admissions were divided into 4 major cohorts in terms of LOS in days (1-3: class 1, 4-8: class 2, 9-15: class 3, and more than 15: class 4). To reduce the overall LOS, we adopted two ML models: 1) To classify LOS, a multi-classification model (Model1, an eXtreme Gradient Boosted Trees Classifier) and 2) To predict the LOS for classes 1-3, a regression-based model (Model2, an eXtreme Gradient Boosted Trees Regressor with Early Stopping). Class 4 cohort had a wide range (16- 90+ days) for LOS and therefore was excluded from Model2. The other three cohorts belonged to Q1, IQR, and Q4, respectively. Model1 was trained on 4,280 randomly selected sample IP admissions to balance each class and Model2 was trained on 19,636 IP admissions, both with 102 features. Results: The models were tested on PP10-PP11 claims excluding 0 days LOS. Model1 predicted 296 (3,945) IP admissions in class 4 of which 88 were true positives. Assuming at least a 10% reduction in associated total LOS translated to lower LOS of 1-3% for 5 (7) practices. The remaining 3,649 IP admissions were used to predict LOS by Model2. The difference between actual LOS and Predicted LOS was found as 18%-24%. To address model prediction errors, we defined the target LOS to be predicted LOS with an upper bound of at least 10%. This led to reductions of 6% -16% across practices. Finally, combining the results of both ML models we determined that the potential to lower LOS was at least 6% and at most 19%. Conclusions: Our ML models identified opportunities to reduce LOS across multiple OCM cancer practices for 5 major cancer types. We also identified a cohort of patients with critical condition (class 4) that is vital for practice transformation initiatives. These identified reduction in LOS for oncology patients provides cost reduction and quality improvement opportunities in VBC programs. In the future, more opportunities to lower LOS will be explored with a re-admission prediction model.

Rapid detection and quantification of melamine, urea, sucrose, water, and milk powder adulteration in pasteurized milk using Fourier transform infrared (FTIR) spectroscopy coupled with modern statistical machine learning algorithms

There is an evident requirement for a rapid, efficient, and simple method to screen the authenticity of milk products in the market. Fourier transform infrared (FTIR) spectroscopy stands out as a promising solution. This work employed FTIR spectroscopy and modern statistical machine learning algorithms for the identification and quantification of pasteurized milk adulteration. Comparative results demonstrate modern statistical machine learning algorithms will improve the ability of FTIR spectroscopy to predict milk adulteration compared to partial least square (PLS). To discern the types of substances utilized in milk adulteration, a top-performing multiclassification model was established using multi-layer perceptron (MLP) algorithm, delivering an impressive prediction accuracy of 97.4 %. For quantification purposes, bayesian regularized neural networks (BRNN) provided the best results for the determination of both melamine, urea and milk powder adulteration, while extreme gradient boosting (XGB) and projection pursuit regression (PPR) gave better results in predicting sucrose and water adulteration levels, respectively. The regression models provided suitable predictive accuracy with the ratio of performance to deviation (RPD) values higher than 3. The proposed methodology proved to be a cost-effective and fast tool for screening the authenticity of pasteurized milk in the market.

Application of inertial navigation high precision positioning system based on SVM optimization

With the advancement of semiconductor technology, pedestrian navigation and positioning technology based on smartphones is becoming increasingly important in people's travel. However, precise positioning is challenging due to the use of inertial measurement units in low-cost smartphones and the complex motion states of pedestrians. To navigate and locate pedestrians in complex motion states, a method for converting between smartphone coordinate systems and navigation coordinate systems was studied and designed, and the errors of the built-in sensors of smartphones were analyzed and calibrated. In addition, support vector machines were used to optimize pedestrian trajectory prediction algorithms, and a pedestrian motion state recognition algorithm was designed based on this. To solve the classification problem of multiple human motion states, a multi classification model was constructed and adjacent gait correlation constraints were introduced to correct the classification results. Experiments indicated that the sum of squared errors for traditional algorithms estimating pedestrian trajectories was 0.92, whereas the optimized algorithms produced an improved sum of squared errors of 0.26. Consequently, the average sum of squared errors was reduced by 71.74 %, and the convergence speed increased by 55.56 %. The pedestrian trajectory prediction algorithm optimized by support vector machine could significantly lift the positioning and navigation efficiency, with a correct recognition rate of over 93 % and a position recognition accuracy of 78.8 % - 88.4 %. By optimizing recognition of the motion state of pedestrians, more accurate determination of their position and motion state can be achieved.

An effective parallel convolutional anomaly multi-classification model for fault diagnosis in microservice system

An effective parallel convolutional anomaly multi-classification model for fault diagnosis in microservice system

Ensemble multiclassification model for predicting developmental toxicity in zebrafish

In recent years, with the rapid development of society, organic compounds have been released into aquatic environments in various forms, posing a significant threat to the survival of aquatic organisms. The assessment of developmental toxicity is an important part of environmental safety risk systems, helping to identify the potential impacts of organic compounds on the embryonic development of aquatic organisms and enabling early detection and warning of potential ecological risks. Additionally, binary classification models cannot accurately classify organic compounds. Therefore, it is crucial to construct a multiclassification model for predicting the developmental toxicity of organic compounds. In this study, binary and multiclassification models were developed based on the ToxCast™ Phase I chemical library and literature data. The random forest, support vector machine, extreme gradient boosting, adaptive gradient boosting, and C5.0 decision tree algorithms, as well as 8 types of molecular fingerprint were used to establish a multiclassification base model for predicting developmental toxicity through 5-fold cross-validation and external validation. Ultimately, a multiclassification ensemble model was derived through a voting method. The performance of the binary ensemble model, as measured by the balanced accuracy, was 0.918, while that of the multiclassification model was 0.819. The developmental toxicity voting ensemble model (DT-VEM) achieved accuracies of 0.804, 0.834, and 0.855. Furthermore, by utilizing the XGBoost machine learning algorithm to construct separate models for molecular descriptors and substructure molecular fingerprints, we identified several substructures and physical properties related to developmental toxicity. Our research contributes to a more detailed classification of developmental toxicity, providing a new and valuable tool for predicting the developmental toxicity effects of unknown compounds. This supplement addresses the limitations of previous tools, as it offers an enhanced ability to predict potential developmental toxicity in novel compounds.

UroAngel: a single-kidney function prediction system based on computed tomography urography using deep learning.

Accurate estimation of the glomerular filtration rate (GFR) is clinically crucial for determining the status of obstruction, developing treatment strategies, and predicting prognosis in obstructive nephropathy (ON). We aimed to develop a deep learning-based system, named UroAngel, for non-invasive and convenient prediction of single-kidney function level. We retrospectively collected computed tomography urography (CTU) images and emission computed tomography diagnostic reports of 520 ON patients. A 3D U-Net model was used to segment the renal parenchyma, and a logistic regression multi-classification model was used to predict renal function level. We compared the predictive performance of UroAngel with the Modification of Diet in Renal Disease (MDRD), Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equations, and two expert radiologists in an additional 40 ON patients to validate clinical effectiveness. UroAngel based on 3D U-Net convolutional neural network could segment the renal cortex accurately, with a Dice similarity coefficient of 0.861. Using the segmented renal cortex to predict renal function stage had high performance with an accuracy of 0.918, outperforming MDRD and CKD-EPI and two radiologists. We proposed an automated 3D U-Net-based analysis system for direct prediction of single-kidney function stage from CTU images. UroAngel could accurately predict single-kidney function in ON patients, providing a novel, reliable, convenient, and non-invasive method.

Deep learning-powered multimodal biometric authentication: integrating dynamic signatures and facial data for enhanced online security

The significant increase in online activities in the wake of recent global events has underlined the importance of biometric person authentication on digital platforms. Although many biometric devices may be used for precise biometric authentication, acquiring the necessary technology, such as 3D sensors or fingerprint scanners, can be prohibitively expensive and logistically challenging. Addressing the demands of online environments, where access to specialized hardware is limited, this paper introduces an innovative approach. In this work, by fusing static and dynamic signature data with facial data captured through regular computer cameras, a dataset of 1750 samples from 25 individuals is constructed. Deep learning models, including convolutional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and temporal convolutional networks (TCN), are employed to craft a robust multi-classification model. This integration of various deep learning algorithms has demonstrated remarkable performance enhancements in biometric authentication. This research also underscores the potential of merging dynamic and static biometric features, derived from readily available sources, to yield a high-performance recognition framework. As online interactions continue to expand, the combination of various biometric modalities holds potential for enhancing the security and usability of virtual environments.

Research and Design of an Automated Security Event Analysis and Handling Framework Based on Threat Intelligence

In order to deeply explore and utilize the value of threat intelligence, strengthen research on attack organizations, and grasp the correlation between attack organizations, the author proposes the research and design of an automated security event analysis and handling framework based on threat intelligence. The author extracts the behavioral characteristics of the attack organization based on known APT attacks, and uses the machine learning framework Light GBM to establish a multi classification model to complete the analysis of unknown APT attack organizations. Through the study of multi-dimensional analysis of multi-source threat intelligence, attack organization correlation and judgment, an attack organization correlation and judgment system has been designed and implemented. The system includes six modules: threat intelligence collection module, threat intelligence multi-dimensional analysis module, attack organization fingerprint library module, attack organization correlation module, attack organization analysis module, and user module, providing attack organization correlation and judgment services for network security. The test results show that the intelligence reading and search query function can achieve the reading of various information of attack organizations, and achieve visual display of threat intelligence. The intelligence management function can achieve operations such as adding, deleting, and updating intelligence. The user management function of the system can achieve the management of administrator users and ordinary users. After testing, all functions of the system have been implemented and meet expectations.

Network Traffic Classification Model Based on Spatio-Temporal Feature Extraction

The demand for encrypted communication is increasing with the continuous development of secure and trustworthy networks. In edge computing scenarios, the requirement for data processing security is becoming increasingly high. Therefore, the accurate identification of encrypted traffic has become a prerequisite to ensure edge intelligent device security. Currently, encrypted network traffic classification relies on single-feature extraction methods. These methods have simple feature extraction, making distinguishing encrypted network data flows and designing compelling manual features challenging. This leads to low accuracy in multi-classification tasks involving encrypted network traffic. This paper proposes a hybrid deep learning model for multi-classification tasks to address this issue based on the synergy of dilated convolution and gating unit mechanisms. The model comprises a Gated Dilated Convolution (GDC) module and a CA-LSTM module. The GDC module completes the spatial feature extraction of encrypted network traffic through dilated convolution and gating unit mechanisms. In contrast, the CA-LSTM module focuses on extracting temporal network traffic features. By employing a collaborative approach to extract spatio-temporal features, the model ensures feature extraction diversity, guarantees robustness, and effectively enhances the feature extraction rate. We evaluate our multi-classification model using the ISCX VPN-nonVPN public dataset. Experimental results show that the proposed method achieves an accuracy rate of over 95% and a recall rate of over 90%, significantly outperforming existing methods.

Identification of breast cancer subtypes based on graph convolutional network

Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients' genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.

A Dendritic Architecture‐Based Deep Learning for Tumor Detection

Brain tumor detection typically involves classifying various tumor types. Traditional classifiers, based on the McCulloch‐Pitts model, have faced criticism due to their oversimplified structure and limited capabilities in detecting brain tumor images with complex features. In this study, we propose a multiclassification model inspired by dendritic architectures in neurons, which leverages synaptic and dendritic nonlinear information processing capabilities. Experimental results using brain tumor detection datasets demonstrate that our proposed model outperforms other state‐of‐the‐art models across all evaluation metrics. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

A multi-classification detection model for imbalanced data in NIDS based on reconstruction and feature matching

With the exponential growth of various data interactions on network systems, network intrusions are also increasing. The emergence of edge computing technology brings a new solution to network security. However, due to the difficulty of processing massive and unbalanced data at the edge, higher accuracy requirements are necessary for deployed detection models. This paper proposes a multi-classification model for network intrusion detection based on reconstruction and feature matching. This model can be deployed on small-scale edge nodes, effectively identifying various attack behaviors through the utilization of reconstruction errors and adaptive scaling. Furthermore, we proposed a model transfer method based on feature matching to enhance the training and detection efficiency of multi-classification models under different data distribution conditions. The proposed model has been evaluated on the CICIDS2017 dataset in terms of accuracy, recall, precision and F1 score. The model demonstrates high accuracy for normal flows in the network, majority class attacks, and minority class attacks, achieving an overall multi-class accuracy of 99.81%, outperforming similar models. Furthermore, this model demonstrates faster convergence and training speed after feature matching, exhibiting better robustness and outstanding performance at the edge.

A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity

In the context of autonomous driving, sensing systems play a crucial role, and their accuracy and reliability can significantly impact the overall safety of autonomous vehicles. Despite this, fault diagnosis for sensing systems has not received widespread attention, and existing research has limitations. This paper focuses on the unique characteristics of autonomous driving sensing systems and proposes a fault diagnosis method that combines hardware redundancy and analytical redundancy. Firstly, to ensure the authenticity of the study, we define 12 common real-world faults and inject them into the nuScenes dataset, creating an extended dataset. Then, employing heterogeneous hardware redundancy, we fuse MMW radar, LiDAR, and camera data, projecting them into pixel space. We utilize the “ground truth” obtained from the MMW radar to detect faults on the LiDAR and camera data. Finally, we use multidimensional temporal entropy to assess the information complexity fluctuations of LiDAR and the camera during faults. Simultaneously, we construct a CNN-based time-series data multi-classification model to identify fault types. Through experiments, our proposed method achieves 95.33% accuracy in detecting faults and 82.89% accuracy in fault diagnosis on real vehicles. The average response times for fault detection and diagnosis are 0.87 s and 1.36 s, respectively. The results demonstrate that the proposed method can effectively detect and diagnose faults in sensing systems and respond rapidly, providing enhanced reliability for autonomous driving systems.

Discernment of transformer oil stray gassing anomalies using machine learning classification techniques

This work examines the application of machine learning (ML) algorithms to evaluate dissolved gas analysis (DGA) data to quickly identify incipient faults in oil-immersed transformers (OITs). Transformers are pivotal equipment in the transmission and distribution of electrical power. The failure of a particular unit during service may interrupt a massive number of consumers and disrupt commercial activities in that area. Therefore, several monitoring techniques are proposed to ensure that the unit maintains an adequate level of functionality in addition to an extended useful lifespan. DGA is a technique commonly employed for monitoring the state of OITs. The understanding of DGA samples is conversely unsatisfactory from the perspective of evaluating incipient faults and relies mainly on the proficiency of test engineers. In the current work, a multi-classification model that is centered on ML algorithms is demonstrated to have a logical, precise, and perfect understanding of DGA. The proposed model is used to analyze 138 transformer oil (TO) samples that exhibited different stray gassing characteristics in various South African substations. The proposed model combines the design of four ML classifiers and enhances diagnosis accuracy and trust between the transformer manufacturer and power utility. Furthermore, case reports on transformer failure analysis using the proposed model, IEC 60599:2022, and Eskom (Specification—Ref: 240-75661431) standards are presented. In addition, a comparison analysis is conducted in this work against the conventional DGA approaches to validate the proposed model. The proposed model demonstrates the highest degree of accuracy of 87.7%, which was produced by Bagged Trees, followed by Fine KNN with 86.2%, and the third in rank is Quadratic SVM with 84.1%.