Augmented Dataset Research Articles

Generative adversarial networks (GANs) to produce synthetic 12-lead electrocardiogram signals for specific and rare diseases: a novel, powerful tool towards clinical advancements

Abstract Background Remarkable technological advancements in electrocardiogram (ECG) analysis face challenges due to insufficiently diverse and extensive real-world datasets. This limitation hampers both the development of sophisticated deep learning (DL) models for ECG analysis and the exposure of new physicians to substantial training examples. Purpose To leverage Generative Adversarial Networks (GANs), a novel AI algorithm type, to generate synthetic yet realistic ECG signals resembling specific diseases. Methods We initially employed a general-purpose GAN on more than 21,000 ECG samples from the PTB-XL database, encompassing normal and abnormal ECGs across various diseases. The GAN outputs served as inputs for training "DeceptionECG", a novel GAN model inspired by the InceptionTime architecture (code available online). DeceptionECG focused on generating disease-specific ECG signals, trained on annotated ECGs validated by two electrophysiologists. Post-training, we generated synthetic ECGs for common diseases like atrial fibrillation (AF) and anterior ST-segment elevation myocardial infarction (STEMI), as well as rarer conditions like Wolf-Parkinson White (WPW) syndrome. Authentication involved an independent discriminator DL model and two cardiologists who were asked to distinguish real from synthetic ECGs. Additionally, a DL model, a variant of the InceptionTime architecture, discerned specific diseases in the ECG signals to assess their realism. Finally, we trained a DL model for detecting abnormalities in ECGs with the augmented dataset to evaluate potential performance improvement. Results We generated sets of 5,000 synthetic ECGs for various abnormalities, at a rate of 2,500 12-lead ECG signals per minute. The generated ECGs were indistinguishable from real ones, evidenced by low accuracy (Accuracy, ACC: 48.9%) of the discriminator model and two clinicians (ACC: 56% and 51%), on test sets with anterior STEMI. A DL model trained on real ECGs accurately differentiated between synthetic normal ECGs and those hosting the target disease in nearly 9 out of 10 cases (ACC: 88.7%). Furthermore, the employed DL model detector trained on the augmented dataset, encompassing both real (n=1,589) and synthetic (n=5,000) ECGs, outperformed its counterpart trained solely on real ECGs, when tested on a 1,000-sample set of real signals (ACC: 94.6% vs. 89.3%). Conclusion Our GAN-based approach showcases the potential of generating high-quality synthetic ECGs tailored for specific diseases, overcoming data scarcity challenges, and enhancing the training and performance of machine learning models. Additionally, it holds promise in advancing medical professional training by providing diverse signals with distinct "disease stamps" at massive amounts, addressing privacy concerns associated with extensive data exposure. Further testing is warranted for the applicability of the approach, especially in exceedingly rare conditions with limited available training data.Project workflow and outcomesGAN-generated ECGs: Which is fake?

Personalized Super Resolution with Face Prior

Face Super-Resolution (FSR) is a critical technology in computer vision that aims to reconstruct high-resolution facial images from low-resolution inputs. Despite recent advancements, current FSR methods struggle to accurately reconstruct personalized and detailed features. This paper proposes a novel FSR approach that addresses these challenges through a personalized feature extraction and fusion framework. Our method integrates a U-Net based downsampling mechanism to extract individual- specific features from high-resolution reference images, which are then fused with a pre-trained Generative Adversarial Network (GAN) for enhanced reconstruction. We introduce a comprehensive loss function that combines reconstruction, adversarial, facial component, and identity preservation losses to guide the learning process. Extensive experiments on the augmented FFHQ dataset demonstrate that our approach significantly improves the reconstruction of rich facial features, particularly for older individuals, outperforming existing state-of-the-art methods in both quantitative metrics and qualitative visual assessments.

An improved AlexNet deep learning method for limb tumor cancer prediction and detection.

Synovial sarcoma (SS) is a rare cancer that forms in the soft tissues around joints, where early detection is crucial for improving patient survival rates. This study introduces a convolutional neural network (CNN) using an improved AlexNet deep learning classifier to enhance the diagnosis of SS from digital pathological images. Key preprocessing steps such as dataset augmentation and noise reduction techniques like adaptive median filtering (AMF) and histogram equalization were employed to improve image quality. Feature extraction was conducted using the Gray-Level Co-occurrence Matrix (GLCM) and Improved Linear Discriminant Analysis (ILDA), while image segmentation targeted spindle-shaped cells using repetitive phase-level set segmentation (RPLSS). The improved AlexNet architecture features additional convolutional layers and resized input images, leading to superior performance. The model demonstrated significant improvements in accuracy, sensitivity, specificity, and AUC, outperforming existing methods by 3%, 1.70%, 6.08%, and 8.86%, respectively, in predicting SS.

Music-induced emotion flow modeling by ENMI Network.

The relation between emotions and music is substantial because music as an art can evoke emotions. Music emotion recognition (MER) studies the emotions that music brings in the effort to map musical features to the affective dimensions. This study conceptualizes the mapping of music and emotion as a multivariate time series regression problem, with the aim of capturing the emotion flow in the Arousal-Valence emotional space. The Efficient Net-Music Informer (ENMI) Network was introduced to address this phenomenon. The ENMI was used to extract Mel-spectrogram features, complementing the time series data. Moreover, the Music Informer model was adopted to train on both time series music features and Mel-spectrogram features to predict emotional sequences. In our regression task, the model achieved a root mean square error (RMSE) of 0.0440 and 0.0352 in the arousal and valence dimensions, respectively, in the DEAM dataset. A comprehensive analysis of the effects of different hyperparameters tuning was conducted. Furthermore, different sequence lengths were predicted for the regression accuracy of the ENMI Network on three different datasets, namely the DEAM dataset, the Emomusic dataset, and the augmented Emomusic dataset. Additionally, a feature ablation on the Mel-spectrogram features and an analysis of the importance of the various musical features in the regression results were performed, establishing the effectiveness of the model presented herein.

Prediction of lumpy skin disease virus using customized CBAM-DenseNet-attention model

Lumpy skin disease virus (LSDV) is an extremely infectious, viral, and chronic skin disease that is caused by the Capripox virus. This viral disease is predominantly found in cows. Mosquitoes and ticks are the primary transmitters for the spread of this virus. Recently, LSDV has been rapidly spreading all over the world, especially in several areas of Pakistan, India, and Iran. Thousands of cows have died due to this infectious virus in Pakistan and early detection of LSDV is needed to avoid further loss. The prediction and classification of LSDV are hindered by the lack of publicly available datasets. Despite a few studies using LSDV datasets, such datasets are often small, which may lead to model overfitting. In this regard, we collect the dataset from several online sources, as well as, collecting images from veterinary farms in different areas of Pakistan. Deep learning has been widely used in the medical field for disease detection and classification. Therefore, this study leverages DenseNet deep learning models for LSDV detection and classification. Experiments are performed using VGG-16, ResNet-50, MobileNet-V2, custom-designed convolutional neural network, and Inception-V3. The DenseNet architecture presents a Convolutional Block Attention Module (CBAM) and Spatial Attention (SA) for the prediction and classification of LSD. Results demonstrate that a 99.11% accuracy can be obtained on the augmented dataset while a 94.23% accuracy can be achieved with the original dataset for chicken pox, monkey pox, and LSDV. Comparison with state-of-the-art studies corroborates the superior performance of the proposed model.

Depression Detection on Mandarin Text through Bert Model

Depression is currently one of the most prevalent mental disorders and its incidence has been rising significantly in Malaysia amid the Covid-19 pandemic. While previous studies have demonstrated the potential of artificial intelligence technology in analysing social media texts to detect signs of depression, most of these studies have focused on English textual content. Considering that Mandarin is the second most widely spoken language worldwide, it is worthwhile to explore depression detection techniques specifically tailored for Mandarin textual content. This research aims to examine the effectiveness of the BERT model in text classification, particularly for detecting depression in Mandarin. The study proposes the utilization of the BERT model to analyse social media posts related to depression. The model is trained using the WU3D dataset, which comprises a collection of over 2 million text data sourced from Sina Weibo, a prominent Chinese social media platform. Given the dataset's inherent imbalance, text augmentation techniques were employed to assess whether they contribute to improved model performance. The findings suggest that the BERT model trained on the original dataset outperformed the model trained on the augmented dataset. This implies that the BERT model is well-equipped to handle imbalanced datasets effectively. Furthermore, it is speculated that the augmented dataset did not introduce novel information or knowledge during the model training process. Notably, the highest-performing model achieved an impressive accuracy rate of 88% on the testing dataset.

COMPARATIVE ANALYSIS OF TIME SERIES FORECASTING MODELS USING ARIMA AND NEURAL NETWORK AUTOREGRESSION METHODS

Gold price fluctuations have a significant impact because gold is a haven asset. When financial markets are volatile, investors tend to turn to safer instruments such as gold, so gold price forecasting becomes important in economic uncertainty. The novelty of this research is the comparative analysis of time series forecasting models using ARIMA and the NNAR methods to predict gold price movements specifically applied to gold price data with non-stationary and non-linear characteristics. The aim is to identify the strengths and limitations of ARIMA and NNAR on such data. ARIMA can only be applied to time series data that are already stationary or have been converted to stationary form through differentiation. However, ARIMA may struggle to capture complex non-linear patterns in non-stationary data. Instead, NNAR can handle non-stationary data more effectively by modeling the complex non-linear relationships between input and output variables. In the NNAR model, the lag values of the time series are used as input variables for the neural network. The dataset used is the closing price of gold with 1449 periods from January 2, 2018, to October 5, 2023. The augmented Dickey-Fuller test dataset obtained a p-value = 0.6746, meaning the data is not stationary. The ARIMA(1, 1, 1) model was selected as the gold price forecasting model and outperformed other candidate ARIMA models based on parameter identification and model diagnosis tests. Model performance is evaluated based on the RMSE and MAE values. In this study, the ARIMA(1, 1, 1) model obtained RMSE = 16.20431 and MAE = 11.13958. The NNAR(1, 10) model produces RMSE = 16.10002 and MAE = 11.09360. Based on the RMSE and MAE values, the NNAR(1, 10) model produces better accuracy than the ARIMA(1, 1, 1) model.

Enhanced Input-Doubling Method Leveraging Response Surface Linearization to Improve Classification Accuracy in Small Medical Data Processing

Currently, the tasks of intelligent data analysis in medicine are becoming increasingly common. Existing artificial intelligence tools provide high effectiveness in solving these tasks when analyzing sufficiently large datasets. However, when there is very little training data available, current machine learning methods do not ensure adequate classification accuracy or may even produce inadequate results. This paper presents an enhanced input-doubling method for classification tasks in the case of limited data analysis, achieved via expanding the number of independent attributes in the augmented dataset with probabilities of belonging to each class of the task. The authors have developed an algorithmic implementation of the improved method using two Naïve Bayes classifiers. The method was modeled on a small dataset for cardiovascular risk assessment. The authors explored two options for the combined use of Naïve Bayes classifiers at both stages of the method. It was found that using different methods at both stages potentially enhances the accuracy of the classification task. The results of the improved method were compared with a range of existing methods used for solving the task. It was demonstrated that the improved input-doubling method achieved the highest classification accuracy based on various performance indicators.

Dataset Augmentation and Fractional Frequency Offset Compensation Based Radio Frequency Fingerprint Identification in Drone Communications

Dataset Augmentation and Fractional Frequency Offset Compensation Based Radio Frequency Fingerprint Identification in Drone Communications

Military Equipment Entity Extraction Based on Large Language Model

The technology of military equipment entity extraction, a crucial component in constructing military knowledge bases, holds significant research value and theoretical importance for guiding the development and improvement of equipment support forces. In the military domain, equipment entities exhibit a phenomenon of nesting, where one entity is contained within another, and abbreviations or codes are frequently used to represent these entities. To address this complexity, this paper proposes a method named CoTNER for extracting entities. Initially, a large-scale language model is used to perform data augmentation with chain-of-thought on the original dataset, providing additional semantic and contextual information. Subsequently, the augmented dataset is fine-tuned on a small-scale language model to adapt it to the task of military equipment entity extraction and to enhance its ability to learn complex rules specific to the domain of military equipment. Additionally, a high-quality data filtering strategy based on instruction-following difficulty scoring is proposed to address the catastrophic forgetting issue that may occur during the fine-tuning of large language models. The experimental results demonstrate that the proposed military equipment entity extraction method outperforms mainstream traditional deep learning methods, validating the effectiveness of CoTNER.

CCTV image‐based classification of blocked trash screens

AbstractThis study introduces image‐based classification techniques to identify whether trash screens in urban rivers are blocked. The study obtained 755 images from a CCTV camera surveying a trash screen located on an urban river at Tongwynlais in Cardiff. Manual quality control reduced the dataset to 577 images, labelled as either blocked (80%) or unblocked (20%). The performance of a logistic regression for classification of images was investigated using three different subsets of the labelled images: (1) the original dataset, (2) a balanced but under‐sampled dataset with equal number of blocked and unblocked images, and (3) an augmented dataset with an equal number of blocked and unblocked images using Gaussian noise augmentation to increase the number of unblocked images. Results show that our data‐augmentation method enhanced model accuracy by 8%, successfully classifying images as blocked or unblocked with an accuracy of 88%; by overcoming the bias in the dataset these results also highlight potential solutions to overcome the challenges of operating this methodology across a network of cameras. This enables authorities in both data rich and data scarce regions the ability to take advantage of machine learning to open up the next generation of a distributed, data‐driven flood warning systems, protecting people, infrastructure and the environment.

Automated Neural Architecture Search for Cardiac Amyloidosis Classification from [18F]-Florbetaben PET Images.

Medical image classification using convolutional neural networks (CNNs) is promising but often requires extensive manual tuning for optimal model definition. Neural architecture search (NAS) automates this process, reducing human intervention significantly. This study applies NAS to [18F]-Florbetaben PET cardiac images for classifying cardiac amyloidosis (CA) sub-types (amyloid light chain (AL) and transthyretin amyloid (ATTR)) and controls. Following data preprocessing and augmentation, an evolutionary cell-based NAS approach with a fixed network macro-structure is employed, automatically deriving cells' micro-structure. The algorithm is executed five times, evaluating 100 mutating architectures per run on an augmented dataset of 4048 images (originally 597), totaling 5000 architectures evaluated. The best network (NAS-Net) achieves 76.95% overall accuracy. K-fold analysis yields mean ± SD percentages of sensitivity, specificity, and accuracy on the test dataset: AL subjects (98.7 ± 2.9, 99.3 ± 1.1, 99.7 ± 0.7), ATTR-CA subjects (93.3 ± 7.8, 78.0 ± 2.9, 70.9 ± 3.7), and controls (35.8 ± 14.6, 77.1 ± 2.0, 96.7 ± 4.4). NAS-derived network performance rivals manually determined networks in the literature while using fewer parameters, validating its automatic approach's efficacy.

Towards explainable evaluation: Explaining predicted performance using local performance regions

Identifying which instances in a learning problem are difficult to be predicted by a model is important to avoid critical errors at deployment time as well as to plan how to learn an improved model (e.g., by training data cleaning or augmentation). Previous works have been mainly devoted on measuring instance hardness or developing meta-learners (e.g., assessors) to predict a base model performance based on the instances’ features while neglecting interpretability. In this paper, we propose a method to explain the performance of learned models in a problem based on the induction of meta-rules. Each meta-rule identifies a local region of instances, called Local Performance Region (LPR), where the base model has a predictable performance. The meta-rules are induced using a reduced number of attributes, in such a way that each LPR can be more easily inspected (e.g., by an attribute plot). The proposed method combines assessors, data augmentation and rule induction procedures. Initially, given a dataset of interest and a base model, we build an assessor model, which will be able to predict the base model’s performance for new instances. The assessor is trained based on the test results obtained when the base model is evaluated, thus generalizing the observed errors across instances in the dataset. In our work, we built an assessor in a case study to predict the probability of incorrect classifications of a Random Forest (RF) base model, achieving a mean absolute error of 0.05 in a hold out experiment. Once learned, the assessor is used to predict the model’s errors for new instances in an augmented dataset, covering a variety of features. Finally, meta-rules are learned to approximate the assessor’s predictions in local regions of instances. Experiments show the usefulness of the proposal by finding 18 local regions of bad RF performance, demonstrating a special case of LPRs, called Local Hard Regions (LHRs). By explaining the (in)correctness of model predictions, LPRs constitute a novel application in explainable AI, but focusing on explaining model performance, which can be adopted to different ML contexts.

Leveraging social media and community science data for environmental niche models: A case study with native Australian bees

Museum occurrence records are popular sources of information for creating Environmental Niche Models (ENMs), which allow the mapping of the potential niche ranges of species. Occurrence data is often downloaded en masse from established databases. However, the use of non-traditional data sources, such as occurrence records from community/citizen science outreach and social media, is increasing in use and abundance. Data from non-traditional data sources are potentially valuable records of information, particularly for species where museum occurrence records may be comparatively scarce. In the current study, we aimed to determine the impact of adding occurrence data from non-traditional databases to ENMs that were originally created using traditional databases with a group of comparatively understudied species, native Australian bees. We used the Maxent algorithm to model the potential environmental niches of eight species. We created three models for each species: 1) one consisting of only location data from museum specimen collection records from the Atlas of Living Australia (ALA) (a traditional database), 2) one combining ALA and geo-tagged social media (Flickr) data, and 3) a model combining ALA and geo-tagged community science data from iNaturalist. This resulted in 24 different models. By comparing the models produced from each of the augmented data sets with the traditional species data set (ALA vs. ALA & Flickr; ALA vs. ALA & iNaturalist) we showed that there were significant differences, not only in predicted ranges, but also in the weighting of environmental variables used by the models to predict the environmental niche. Differences were more greatly influenced by the geographic location of the extra occurrences rather than the number of additional occurrence points. We demonstrate the potential value and risks of including social media and community science geo-tagged image data in supplementing knowledge of species distributions, particularly for relatively under-sampled species such as native bees.

Class activation map-based slicing-concatenation and contrastive learning: A novel strategy for record-level atrial fibrillation detection

BackgroundDeep learning-based models for atrial fibrillation (AF) detection require extensive training data, which often necessitates labor-intensive professional annotation. While data augmentation techniques have been employed to mitigate the scarcity of annotated electrocardiogram (ECG) data, specific augmentation methods tailored for recording-level ECG annotations are lacking. This gap hampers the development of robust deep learning models for AF detection. MethodsWe propose a novel strategy, a combination of Class Activation Map-based Slicing-Concatenation (CAM-SC) data augmentation and contrastive learning, to address the current challenges. Initially, a baseline model incorporating a global average pooling layer is trained for classification and to generate class activation maps (CAMs), which highlight indicative ECG segments. After that, in each recording, indicative and non-indicative segments are sliced. These segments are subsequently concatenated randomly based on starting and ending Q points of QRS complexes, with indicative segments preserved to maintain label correctness. Finally, the augmented dataset undergoes contrastive learning to learn general representations, thereby enhancing AF detection performance. ResultsUsing ResNet-101 as the baseline model, training with the augmented data yielded the highest F1-score of 0.861 on the Computing in Cardiology (CinC) Challenge 2017 dataset, a typical AF dataset with recording-level annotations. The metrics outperform most previous studies. ConclusionsThis study introduces an innovative data augmentation method specifically designed for recording-level ECG annotations, significantly enhancing AF detection using deep learning models. This approach has substantial implications for future AF detection research.

An Artificial Intelligence-Based Tool for Enhancing Pectoral Muscle Segmentation in Mammograms: Addressing Class Imbalance and Validation Challenges in Automated Breast Cancer Diagnosis.

Breast cancer remains a major health concern worldwide, requiring the advancement of early detection methods to improve prognosis and treatment outcomes. In this sense, mammography is regarded as the gold standard in breast cancer screening and early detection. However, in a scenario where extensive analysis is required, a large set of mammograms conducted by radiologists may carry out false negative or false positive diagnoses. Therefore, artificial intelligence has emerged in recent years as a method for enhancing timing in breast cancer diagnosis. Nonetheless, preprocessing stages are required to prepare the mammography dataset to enhance learning models to correctly identify breast anomalies. In this paper, we introduce a novel method employing convolutional neural networks (CNNs) to segment the pectoral muscle in 1288 mediolateral oblique mammograms (MLOs), thereby addressing class imbalance and overfitting between classes, and dataset augmentation based on translation, rotation, and scale transformation. The effectiveness of the model was assessed through a confusion matrix and performance metrics, highlighting an average Dice coefficient of 0.98 and a Jaccard index of 0.96. The outcomes demonstrate the model capability to accurately identify three classes: pectoral muscle, breast, and background. This study emphasizes the importance of tackling class imbalance problems and augmenting data for the training of models for reliable early breast cancer detection.

Generation of micrograph-annotation pairs for steel microstructure recognition using the hybrid deep generative model in the case of an extremely small and imbalanced dataset

Insufficient annotated samples coupled with class imbalance problem largely restrict the wide application of deep learning (DL)-based approach in microstructure recognition and quantification. In this work, we present a micrograph augmentation approach using the hybrid deep generative model to generate SEM image-annotation pairs for the establishment of a large-scale and well-balanced augmentation dataset. In this method, a generator is established to produce the desired annotations and then a translator is trained to translate these synthetic annotations into high-quality SEM images. The proposed method is successfully applied to an extremely small and imbalanced additively manufactured (AM) steel dataset containing only one SEM image-annotation pair with a very low martensite/austenite (MA) fraction, to significantly augment the initial dataset and achieve a more balanced distribution of phase fraction. The effectiveness of the present method is well demonstrated by the fact that the extensibility of microstructure recognition model to unseen micrographs is improved through the utilization of synthetic data. Furthermore, the impact of synthetic data proportion on the model's performance and the underlying reasons for synthetic data to improve the extensibility of trained models are also discussed in detail.

Enhancing composite cathode manufacturing with machine learning for polymer electrolyte solid-state batteries

Solid-state batteries (SSBs) represent a pivotal advancement in battery technology, poised to surpass lithium-ion batteries and drive the electrification of mobility. However, achieving cost-effective, scalable, and sustainable fabrication processes for SSB components remains a challenge. This study integrates machine learning (ML) techniques to optimize manufacturing processes of cathodes for polymer electrolyte based SSBs. The findings reveal strong predictive performance of regression models for active material loading, with support vector machine emerging as the top performer. Multiclassification models exhibit satisfactory precision, particularly in categorizing ideal electrode samples. Analysis of principal component and correlation circles highlight viscosity and wet thickness as critical variables for mixing and coating, respectively. Despite promising metrics, dataset imbalance and size limit model robustness. Further dataset augmentation is recommended before deployment in production. ML techniques offer promise in advancing battery manufacturing, paving the way for enhanced SSB performance and broader application across battery components.

TTPXHunter: Actionable Threat Intelligence Extraction as TTPs from Finished Cyber Threat Reports

Understanding the modus operandi of adversaries aids organizations to employ efficient defensive strategies and share intelligence in the community. This knowledge is often present in unstructured natural language text within threat analysis reports. A translation tool is needed to interpret the modus operandi explained in the sentences of the threat report and convert it into a structured format. This research introduces a methodology named TTPXHunter for automated extraction of threat intelligence in terms of Tactics, Techniques, and Procedures (TTPs) from finished cyber threat reports. It leverages cyber domain-specific state-of-the-art natural language model to augment sentences for minority class TTPs and refine pinpointing the TTPs in threat analysis reports significantly. We create two datasets: an augmented sentence-TTP dataset of \(39,296\) sentence samples and a \(149\) real-world cyber threat intelligence report-to-TTP dataset. Further, we evaluate TTPXHunter on the augmented sentence and report datasets. The TTPXHunter achieves the highest performance of \(92.42\%\) f1-score on the augmented dataset, and it also outperforms existing state-of-the-art TTP extraction method by achieving an f1-score of \(97.09\%\) when evaluated over the report dataset. TTPXHunter significantly improves cybersecurity threat intelligence by offering quick, actionable insights into attacker behaviors. This advancement automates threat intelligence analysis and provides a crucial tool for cybersecurity professionals to combat cyber threats.

YOLOv8-Based Drone Detection: Performance Analysis and Optimization

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, this study aimed to reduce the dangerous effects of drone use through early detection of drones. The purpose of this study is the evaluation of deep learning approaches such as pre-trained YOLOv8 drone detection for security issues. This study focuses on the YOLOv8 model to achieve optimal performance in object detection tasks using a publicly available dataset collected by Mehdi Özel for a UAV competition that is sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. YOLOv8, known for its advanced architecture, was selected due to its suitability for real-time detection applications and its ability to process complex visual data. Hyperparameter tuning and data augmentation techniques were applied to maximize the performance of the model. Basic hyperparameters such as learning rate, batch size, and optimization settings were optimized through iterative experiments to provide the best performance. In addition to hyperparameter tuning, various data augmentation strategies were used to increase the robustness and generalization ability of the model. Techniques such as rotation, scaling, flipping, and color adjustments were applied to the dataset to simulate different conditions and variations. Among the augmentation techniques applied to the specific dataset in this study, rotation was found to deliver the highest performance. Blurring and cropping methods were observed to follow closely behind. The combination of optimized hyperparameters and strategic data augmentation allowed YOLOv8 to achieve high detection accuracy and reliable performance on the publicly available dataset. This method demonstrates the effectiveness of YOLOv8 in real-world scenarios, while also highlighting the importance of hyperparameter tuning and data augmentation in increasing model capabilities. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605, and a considerable precision–recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.