Stop Technique Research Articles

Transmission regulating immune genes- a potential strategy to control vector borne disease.

More than 1 million people die every year from vector-borne diseases, which constitute more than 17% of all infectious diseases. This study's primary focus is on the detailed evolutionary history and expression analysis of immune genes, one of the key gene families in the immune system of vectors that play a role in the regulation and interaction of parasites in vector bodies, particularly the mosquitoes that transmit malaria and dengue, significant vector borne disease. The vector potentiality and participation of TLR genes in vector parasite interaction in the Indian context will be explained by the differential expression study of this potential gene family in Indian populations of vector species. This knowledge is supportive undoubtedly for creating new pharmacological targets and inhibitors that can create insect-based transmission stopping techniques for many vector-borne diseases. However, the genetic diversity was found to be comparatively lower in the Toll1A gene than in the NOS immune gene in the malaria vector An. minimus population samples which supports the hypothesis of positive selection in recent evolutionary time scale in malaria vectors. This is one of the novel strategies to identify transmission regulating genetic traits that are controlling the vector-parasite interaction and co-evolution in vector borne disease.

THOUGHT STOPPING TECHNIQUE GROUP COUNSELING TO REDUCE ACADEMIC ANXIETY

The large number of students who experience academic anxiety and the challenges they face in completing their final assignments are the impetus for conducting this research. Students who feel academic anxiety or also called academic anxiety due to lack of confidence in their abilities in carrying out academic activities, are generally motivated by several factors such as the desire to graduate on time, high parental expectations, and pressure from supervisors. The aim of this research is to reduce academic anxiety in final year students by using thought stopping strategies in group counseling. Purposive sampling is used in the pre-experimental design quantitative research methodology which has a one-group pre-test-post-test design pattern. Seven students with high levels of academic anxiety will be research participants. They will receive treatment in the form of group counseling using thought stopping techniques. Four sessions were held to conduct this research. T-Test statistical samples with SPSS For Windows Version 26.0 statistical software were used in the data analysis procedure. The findings of this study show the effectiveness of thought stopping strategies in group counseling to reduce academic anxiety. The acceptance of the alternative hypothesis (Ha) is indicated by the results of the Paired Sample T-Test analysis which produces a significant probability value (2-tailed) < 0.05. It was found that after the final students underwent group counseling treatment using the thought stopping technique, there was a significant reduction in anxiety levels.

Novel Ransomware Detection Exploiting Uncertainty and Calibration Quality Measures Using Deep Learning

Ransomware poses a significant threat by encrypting files or systems demanding a ransom be paid. Early detection is essential to mitigate its impact. This paper presents an Uncertainty-Aware Dynamic Early Stopping (UA-DES) technique for optimizing Deep Belief Networks (DBNs) in ransomware detection. UA-DES leverages Bayesian methods, dropout techniques, and an active learning framework to dynamically adjust the number of epochs during the training of the detection model, preventing overfitting while enhancing model accuracy and reliability. Our solution takes a set of Application Programming Interfaces (APIs), representing ransomware behavior as input we call “UA-DES-DBN”. The method incorporates uncertainty and calibration quality measures, optimizing the training process for better more accurate ransomware detection. Experiments demonstrate the effectiveness of UA-DES-DBN compared to more conventional models. The proposed model improved accuracy from 94% to 98% across various input sizes, surpassing other models. UA-DES-DBN also decreased the false positive rate from 0.18 to 0.10, making it more useful in real-world cybersecurity applications.

VOC data-driven evaluation of vehicle cabin odor: from ANN to CNN-BiLSTM.

Emissions of volatile organic compounds (VOCs) in vehicles represent a significant problem, causing unpleasant odors. To mitigate VOCs and odors in vehicles, it is critical to choose interior parts with low odor and VOC emissions. However, prevailing odor evaluation methods are subjective, costly, and potentially harmful to the health of evaluators. In this study, we analyzed 139 automotive interior parts and 92 vehicles, establishing a cost-effective, data-driven method for odor evaluation. The contents of benzene, toluene, ethylbenzene, xylene, styrene, formaldehyde, acetaldehyde, acrolein, and total volatile organic compounds (TVOC) were detected by thermal desorption gas chromatography-mass spectrometry (TD-GC/MS) and high-performance liquid chromatography with an ultraviolet detector (HPLC-UV). Professional odor evaluators assessed the odors, identifying intensity levels from 2.0 to 4.5 in interior parts and 2.5 to 3.5 in whole vehicles. Leveraging this data, we applied four supervised learning algorithms to develop predictive models for the odor intensity of both interior parts and entire vehicles. During model training, we implemented early stopping techniques for the artificial neural network (ANN) and convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) models, while optimizing the support vector machine (SVM) and extreme gradient boosting (XGBoost) models using the GridSearch algorithm. The evaluation results reveal that the CNN-BiLSTM model performs the best, achieving an average accuracy of 89% for unknown samples within an odor intensity level of 0.5. The root mean square error (RMSE) is 0.24, and the mean absolute error (MAE) is 0.08. The model also underwent a sevenfold cross-validation, achieving an accuracy of 83.43%. Additionally, we employed SHapley Additive exPlanations (SHAP) for the interpretative analysis of the model, which confirmed the consistency of each VOC's odor contribution with human olfactory rules. By predicting odors based on VOCs through supervised learning, this study reduces the costs and enhances the efficiency and applicability of odor assessment across various vehicle interiors.

Noisecut: a python package for noise-tolerant classification of binary data using prior knowledge integration and max-cut solutions

BackgroundClassification of binary data arises naturally in many clinical applications, such as patient risk stratification through ICD codes. One of the key practical challenges in data classification using machine learning is to avoid overfitting. Overfitting in supervised learning primarily occurs when a model learns random variations from noisy labels in training data rather than the underlying patterns. While traditional methods such as regularization and early stopping have demonstrated effectiveness in interpolation tasks, addressing overfitting in the classification of binary data, in which predictions always amount to extrapolation, demands extrapolation-enhanced strategies. One such approach is hybrid mechanistic/data-driven modeling, which integrates prior knowledge on input features into the learning process, enhancing the model’s ability to extrapolate.ResultsWe present NoiseCut, a Python package for noise-tolerant classification of binary data by employing a hybrid modeling approach that leverages solutions of defined max-cut problems. In a comparative analysis conducted on synthetically generated binary datasets, NoiseCut exhibits better overfitting prevention compared to the early stopping technique employed by different supervised machine learning algorithms. The noise tolerance of NoiseCut stems from a dropout strategy that leverages prior knowledge of input features and is further enhanced by the integration of max-cut problems into the learning process.ConclusionsNoiseCut is a Python package for the implementation of hybrid modeling for the classification of binary data. It facilitates the integration of mechanistic knowledge on the input features into learning from data in a structured manner and proves to be a valuable classification tool when the available training data is noisy and/or limited in size. This advantage is especially prominent in medical and biomedical applications where data scarcity and noise are common challenges. The codebase, illustrations, and documentation for NoiseCut are accessible for download at https://pypi.org/project/noisecut/. The implementation detailed in this paper corresponds to the version 0.2.1 release of the software.

An imbalance-aware BiLSTM for control chart patterns early detection

Digital twins-based predictive models find their roots in smart manufacturing. However, their potential applications to control chart pattern recognition (CCPR) algorithms, which lie at the heart of advanced fault detection systems, remain underexplored. A key challenge in CCPR models arises from the intrinsic imbalance between classes, which can compromise the model’s performance if left untreated. Further, existing CCPR models are often trained over simulated control chart data in which abnormal patterns are generated separately from abnormal signals; the resulting classifiers, however, perform poorly in the early detection of abnormalities in real-time production environments. To address these challenges, we develop a cost-sensitive, bi-directional long short-term memory neural network for data sequences with mixed normal and abnormal signals. We further introduce a novel adaptive weighting strategy for data generation by enforcing the rates of abnormal signals within mini-batch distributions. Our model benefits from a new bi-objective early stopping technique, which optimally balances loss minimization and G-mean maximization for model training. Finally, we introduce a novel rolling window-based metric for evaluating CCPR classifier stability. We conduct a comprehensive experimental study of our model using both simulated data and two real-world datasets collected from biomanufacturing and wafer industries. The results of our study consistently demonstrate the superiority of our proposed stopping technique over traditional methods. Our experiments further show the effectiveness of our proposed model in maintaining the classifier stability and specifying optimal process monitoring window length within the datasets.

Analysis of the quality information provided by “Dr. YouTube™” on premature ejaculation

ABSTRACT Background: YouTube™ is an important online resource to access health-related online information by the public worldwide. However, the quality of information available on it has not been adequately characterized. Aim: To assess the quality and reliability of information available on the treatment of premature ejaculation (PME) on YouTube™ in the Hindi and English language videos. Materials and Methods: A total of 151 (Hindi: 109, English: 42) YouTube videos were selected for assessment. The quality was evaluated using structured tools: Patient Education Materials Assessment Tool (PEMAT); and a 5-point modified DISCERN questionnaire (Range: 1-serious shortcomings; 5-minimal shortcomings). PEMAT assesses the understandability and actionability of video as separate percentages. Results: Three most common treatments suggested for PME were Kegel exercise (22.5%), start–stop technique (21.9%), and antidepressant medications (20.5%). Antidepressant medications, stop-squeeze techniques, and psychotherapy were more frequently suggested in English videos, whereas ayurvedic or herbal medicines were more frequently suggested in Hindi videos. About two-thirds of videos presented information in an easy-to-understand and actionable manner (PEMAT scores ≥70%). Only 6% of videos had a DISCERN score of ≥4, indicating good overall quality of information presented in them. Conclusion: People likely to encounter poor-quality information when seeking information for PME treatment on YouTube. A large number of videos suggested ineffective or unproven treatment strategies for PME. Healthcare professionals need to be mindful of this while counselling patients, and guide them regarding useful and reliable sources of health information available online.

The COVID-19 Tweets Classification Based on Recurrent Neural Network

Due to its extensive use in both public and commercial contexts, sentiment analysis on Twitter has recently received much attention, particularly concerning tweets about COVID-19. Information about COVID-19 has been widely spread over social media, resulting in various views, opinions, and emotions about this pandemic, significantly impacting people's health. It is exceedingly challenging for the authorities to find these rumors on these public platforms manually. This paper proposes a framework for text classification using the RNN model and its updates, such as LSTM, BiLSTM, and GRU. This study aims to determine the best recurrent network model for handling cases of Twitter data classification. We utilized Twitter data relevant to COVID-19 and the lockdown with four classification classes (sad, joy, fear, and anger). In addition, this study aims to prove whether GloVe pre-trained word embedding can increase the accuracy of model predictions. The training and testing datasets were split into 80% and 20%, respectively. Therefore, in this experiment an early stopping technique was used with a limit of 15 epochs and a minimum delta of 0.01, meaning that training will be stopped if there is no improvement of 0.1% accuracy after 15 epochs. We used the f1-score average to measure the accuracy of the classification task results. The test results show that the BiLSTM model with GloVe word embedding yields the best f1-score compared to other models. Moreover, in all model testing, the f1-score value of the 'fear' class displays the highest accuracy compared to other classes.

Spectrally Segmented-Enhanced Neural Network for Precise Land Cover Object Classification in Hyperspectral Imagery

The paradigm shift brought by deep learning in land cover object classification in hyperspectral images (HSIs) is undeniable, particularly in addressing the intricate 3D cube structure inherent in HSI data. Leveraging convolutional neural networks (CNNs), despite their architectural constraints, offers a promising solution for precise spectral data classification. However, challenges persist in object classification in hyperspectral imagery or hyperspectral image classification, including the curse of dimensionality, data redundancy, overfitting, and computational costs. To tackle these hurdles, we introduce the spectrally segmented-enhanced neural network (SENN), a novel model integrating segmentation-based, multi-layer CNNs, SVM classification, and spectrally segmented dimensionality reduction. SENN adeptly integrates spectral–spatial data and is particularly crucial for agricultural land classification. By strategically fusing CNNs and support vector machines (SVMs), SENN enhances class differentiation while mitigating overfitting through dropout and early stopping techniques. Our contributions extend to effective dimensionality reduction, precise CNN-based classification, and enhanced performance via CNN-SVM fusion. SENN harnesses spectral information to surmount challenges in “hyperspectral image classification in hyperspectral imagery”, marking a significant advancement in accuracy and efficiency within this domain.

The Effect Of Optimizers On The Generalizability Additive Neural Attention For Customer Support Twitter Dataset In Chatbot Application

When optimizing the performance of neural network-based chatbots, determining the optimizer is one of the most important aspects. Optimizers primarily control the adjustment of model parameters such as weight and bias to minimize a loss function during training. Adaptive optimizers such as ADAM have become a standard choice and are widely used for their invariant parameter updates' magnitudes concerning gradient scale variations, but often pose generalization problems. Alternatively, Stochastic Gradient Descent (SGD) with Momentum and the extension of ADAM, the ADAMW, offers several advantages. This study aims to compare and examine the effects of these optimizers on the chatbot CST dataset. The effectiveness of each optimizer is evaluated based on its sparse-categorical loss during training and BLEU in the inference phase, utilizing a neural generative attention-based additive scoring function. Despite memory constraints that limited ADAMW to ten epochs, this optimizer showed promising results compared to configurations using early stopping techniques. SGD provided higher BLEU scores for generalization but was very time-consuming. The results highlight the importance of finding a balance between optimization performance and computational efficiency, positioning ADAMW as a promising alternative when training efficiency and generalization are primary concerns.

Evaluating Neural Radiance Fields for 3D Plant Geometry Reconstruction in Field Conditions.

We evaluate different Neural Radiance Field (NeRF) techniques for the 3D reconstruction of plants in varied environments, from indoor settings to outdoor fields. Traditional methods usually fail to capture the complex geometric details of plants, which is crucial for phenotyping and breeding studies. We evaluate the reconstruction fidelity of NeRFs in 3 scenarios with increasing complexity and compare the results with the point cloud obtained using light detection and ranging as ground truth. In the most realistic field scenario, the NeRF models achieve a 74.6% F1 score after 30 min of training on the graphics processing unit, highlighting the efficacy of NeRFs for 3D reconstruction in challenging environments. Additionally, we propose an early stopping technique for NeRF training that almost halves the training time while achieving only a reduction of 7.4% in the average F1 score. This optimization process substantially enhances the speed and efficiency of 3D reconstruction using NeRFs. Our findings demonstrate the potential of NeRFs in detailed and realistic 3D plant reconstruction and suggest practical approaches for enhancing the speed and efficiency of NeRFs in the 3D reconstruction process.

Hybrid Feature Extraction Technique-based Alzheimer’s Disease Detection Model Using MRI Images

Detecting Alzheimer’s disease (AD) using magnetic resonance imaging (MRI) is essential for early diagnosis and management. This study introduces a new method for detecting AD by combining three robust models: DenseNet201, EfficientNet B7, and extremely randomized trees (ERT). We improve the ability to extract features in DenseNet201 by including a self-attention mechanism. Additionally, we use early stopping techniques on EfficientNet B7 to address the issue of overfitting. In addition, Bayesian Optimization and Hyperband optimization techniques are used to adjust the hyperparameters of extra-trees to differentiate normal and abnormal MRI images. In addition, the authors used SHapley Additive exPlanations to understand the model’s decision. With minimal computer resources, the proposed model achieved a remarkable accuracy of 98.9% in detecting AD. The findings highlight the effectiveness of recommended feature extraction and ERT models and optimization methods to accurately identify AD using MRI images.

Corneal Clarity after Phacoemulsification: Nuclear Management by Stop and Chop Method

Introduction: Restoration of effective vision is the principal aim of all modalities of cataract surgery including phacoemulsification. In this method, nuclear part of the cataractous lens is emulsified by ultrasonic power. Energy level of ultrasonic power and turbulence of fluid in the anterior chamber play an important role in corneal endothelial cell loss which inturn influences post-operative corneal clarity. Endothelial cell loss can be minimized by modification of nuclear management method. The common nuclear division techniques of phacoemulsification are stop and chop, divide and conquer and phaco chop. Purpose: To show post-operative corneal clarity after phacoemulsification by stop and chop technique of nuclear divisions. Materials and Methods: This prospective observational study was conducted at selected outdoor patients from January, 2023 to June, 2023 over 33 patients of age related cataract selected for phacoemulsification surgery. Patients were selected based on specific selection criteria. Selected patient underwent detail, ocular and systemic examinations as well as relevant investigations which included assessment of corneal endothelial cell count and central corneal thickness. Phacoemulsification were done in all patients by a single expert surgeon where technique of nuclear management by stop and chop were chosen randomly. Patients were followed up on 1 week, 4 weak and 12 weak after surgery. Corneal endothelial cell count and central corneal thickness were assessed in each visit. All the relevant data were presented by appropriate tables. Results: The mean age of the study subjects were 60.96 with standard deviation 1.75 years out of which 14 were males and 17 were females. Pre-operative value of mean endothelial cell count was 2620+-70.20/mm2. Mean value of endothelial count was 2420+-68.90/ mm2, 2345+-66.64/ mm2, 2310+-66.04/ mm2 respectively after 1 week , 4 weeks and 12 weeks after surgery. Mean value of central corneal thickness was 545+-40.50 micrometer, 535+-40.02 micrometer, 532+-39.85 micrometer respectively after 1 week, 4 weeks and 12 weeks after surgery. Conclusion: Quantitative assessment of endothelial cell count and central corneal thickness shows that at end of the study there was no significant difference in mean endothelial cell count and mean central corneal thickness . Medicine Today 2023 Vol.35(2): 118-120

Simultaneous Multispot Temperature Prediction of Traction Transformer in Urban Rail Transit Using Long Short-Term Memory Networks

Hot-spot temperature (HST) is a typical indicator of transformer’s health status, accurate prediction of HST is critical for prognosis and health management (PHM) of traction transformer in urban rail transit (URT), where dramatically fluctuating loads and complex climates pose serious challenges. This paper proposed a novel deep-learning-enabled method to predict multi-spot temperatures of transformer simultaneous using long short-term memory (LSTM) neural networks. Real-world operation data collected from Qingdao Metro over a year-long period were used to train the prediction model and verify its validity. The most appropriate transformer-related parameters were selected as the inputs of model by Pearson correlation coefficients (PCC) to improve the accuracy and efficiency of the model. Besides, the dropout and early stopping techniques are used to prevent model from overfitting. Furthermore, the robustness and versatility of proposed method were verified by testing the data on different seasons of multiple transformers, and the superiority of the method was also proved by comparing with other methods. The results show that the proposed model can achieve accurate on-line temperature prediction of transformer, and the mean-relative-error of sixteen minutes ahead HST prediction is less than 0.26%. The proposed method can provide a reference for PHM of transformers.

A comparative study of deep learning methods for food classification with images

The monitoring of food intake plays a key role in avoiding different health problems such as diseases, but also difficulties linked with mental and physical wellbeing. Food monitoring consists firstly of, identifying food types and secondly, recommending the appropriate food for better nutrition. This study addresses the aspect of identifying and classifying food types using Artificial Intelligence (AI) through computer vision, deep learning and transfer learning techniques. We used a dataset containing over 16000 food images, classified into 11 categories: Bread, Dairy product, Dessert, Egg, Fried food, Meat, Noodles/Pasta, Rice, Seafood, Soup, and Vegetable/Fruit. On average, an additional 15884 images were computationally generated for each experiment with data augmentation techniques such as rotation, shifting, shearing, zooming and flipping. Our experiments with different Convolutional Neural Networks (CNN) demonstrate that transfer learning with the EfficientNetV2 model achieved a significant validation accuracy of 94.5 % in classifying the different types of food from images. Also, data augmentation contributes to deal with the imbalanced dataset, with the model achieving an F1-score of 94.7 %. Together with drop out and early stopping techniques, data augmentation also contributes to keep the model safe from overfitting.

VOYAGE SPEED OPTIMIZATION USING GENETIC ALGORITHM

Decreasing the fuel consumption and thus greenhouse gas emissions of vessels have emerged as a critical topic for both ship operators and policymakers in recent years. The speed of vessels has long been recognized to have the highest impact on fuel consumption. The aim of this study is to develop a speed optimization model using a time-constrained genetic algorithm (GA). Subsequent to this, this paper also presents the application of machine learning regression methods in constructing a model to predict the fuel consumption of vessels. The local outlier factor algorithm is used to eliminate outliers in prediction features. The overfitting problem is observed after hyperparameter tuning in boosting and tree-based regression prediction methods. The early stopping technique is applied for overfitted models. In this study, speed is found to be the most significant feature for fuel consumption prediction. On the other hand, GA evaluation results showed that random modifications in the default speed profile could increase GA performance and thus fuel savings more than constant speed limits during voyages.

Comparison between cryoballoon double stop and single stop in patients with paroxysmal atrial fibrillation

BackgroundCurrently, cryoballoon (CB) thawing after single stop is generally performed. Previous research had reported that long thawing time using a single stop affects pulmonary veins tissue injury. However, it is uncertain whether CB thawing after single stop affects clinical outcomes. ObjectiveThis study aimed to clarify clinical significance of CB thawing in patients with paroxysmal atrial fibrillation. MethodsTwo hundred ten patients with paroxysmal atrial fibrillation who underwent CB from January 2018 to October 2019 were analyzed. We compared the clinical outcomes of patients whose CB applications were completely stopped with only the double stop technique (DS group, n = 99) and patients with single stop (SS group, n = 111). In DS group, we performed double stop technique for all CB application regardless of phrenic nerve injury or the temperature of esophagus. ResultsThe atrial arrhythmia free-survival rate at 2 years after CB was significantly lower for the DS group than the SS group (76.8% vs 87.4%; p = 0.045). Complications occurred in 2 patients from the DS group and no complications were observed in patients from the SS group (p = 0.13). Mean procedural time was shorter in the DS group than in the SS group (53.1 vs 58.1 min; p = 0.046) ConclusionDS group had higher recurrence rate than SS group. There was no significant difference regarding safety between both the groups. We found that the thawing process after single stop is very important for CB application.

Fast Model Predictive Control System for Wave Energy Converters With Wave Tank Tests

At present, the mainstream solution for the control of wave energy converters (WECs), the model predictive control (MPC)-like method, faces a gap between simulation-based research and practical application. Two of the major difficulties are the online computation burden and the requirement of real-time wave information. In this study, a fast solving strategy is proposed at the level of quadratic programming (QP), where a tailored warm-start algorithm is designed and combined with an early stop technique. Simulations show that only one iteration of interior-point method (IPM) suffices to reach over 95% efficiency of the exact MPC, which significantly speeds up the computation. The fast strategy is then deployed on the real-time controller of a prototype WEC platform. During this implementation, the instantaneous wave force is estimated by a Kalman filter entirely based on the basic feedback signals: position, velocity, and the generator current, while future wave forces are predicted by an autoregressive model. The wave tank test confirms that the proposed fast MPC is capable of being executed at a high frequency, achieving stable operations within constraints, and reaching satisfactory energy efficiency under real wave-body interactions.

Gas stopping and reacceleration techniques at the Facility for Rare Isotope Beams (FRIB)

The Facility for Rare Isotope Beams (FRIB) at Michigan State University provides a wide range of beams and energies for science with fast, stopped and reaccelerated rare-isotope beams. FRIB was commissioned in 2022 with the science program beginning in May 2022. The combination of fast beams followed by gas stopping of rare-isotope beams together with reacceleration is unique to FRIB. Stopping techniques and beam manipulation at very-low energies are important to slow down fast beams for use in either stopped-beam experimental devices, or subsequent injection in the reaccelerator for experiments at energies ranging from 0.3 MeV/u to 12 MeV/u, depending on the Q/A of the ion. Innovative stopped-beam techniques to optimize the stopping and extraction efficiencies across a wide range of atomic numbers, as well as to reduce contamination and increase extraction speed, were developed. Reacceleration of those beams involve cooling, bunching, charge breeding and acceleration by a state-of-the-art superconducting reaccelerator, ReA. In this contribution we present the latest results of various gas stoppers and techniques to eliminate contaminants after reacceleration by the ReA.

An Adaptive Early Stopping Technique for DenseNet169-Based Knee Osteoarthritis Detection Model.

Knee osteoarthritis (OA) detection is an important area of research in health informatics that aims to improve the accuracy of diagnosing this debilitating condition. In this paper, we investigate the ability of DenseNet169, a deep convolutional neural network architecture, for knee osteoarthritis detection using X-ray images. We focus on the use of the DenseNet169 architecture and propose an adaptive early stopping technique that utilizes gradual cross-entropy loss estimation. The proposed approach allows for the efficient selection of the optimal number of training epochs, thus preventing overfitting. To achieve the goal of this study, the adaptive early stopping mechanism that observes the validation accuracy as a threshold was designed. Then, the gradual cross-entropy (GCE) loss estimation technique was developed and integrated to the epoch training mechanism. Both adaptive early stopping and GCE were incorporated into the DenseNet169 for the OA detection model. The performance of the model was measured using several metrics including accuracy, precision, and recall. The obtained results were compared with those obtained from the existing works. The comparison shows that the proposed model outperformed the existing solutions in terms of accuracy, precision, recall, and loss performance, which indicates that the adaptive early stopping coupled with GCE improved the ability of DenseNet169 to accurately detect knee OA.