Boost Classification Accuracy Research Articles

Towards AI-Generated Essay Classification Using Numerical Text Representation

The detection of essays written by AI compared to those authored by students is increasingly becoming a significant issue in educational settings. This research examines various numerical text representation techniques to improve the classification of these essays. Utilizing a diverse dataset, we undertook several preprocessing steps, including data cleaning, tokenization, and lemmatization. Our system analyzes different text representation methods such as Bag of Words, TF-IDF, and fastText embeddings in conjunction with multiple classifiers. Our experiments showed that TF-IDF weights paired with logistic regression reached the highest accuracy of 99.82%. Methods like Bag of Words, TF-IDF, and fastText embeddings achieved accuracies exceeding 96.50% across all tested classifiers. Sentence embeddings, including MiniLM and distilBERT, yielded accuracies from 93.78% to 96.63%, indicating room for further refinement. Conversely, pre-trained fastText embeddings showed reduced performance, with a lowest accuracy of 89.88% in logistic regression. Remarkably, the XGBoost classifier delivered the highest minimum accuracy of 96.24%. Specificity and precision were above 99% for most methods, showcasing high capability in differentiating between student-created and AI-generated texts. This study underscores the vital role of choosing dataset-specific text representations to boost classification accuracy.

Augmented histopathology: Enhancing colon cancer detection through deep learning and ensemble techniques.

Colon cancer poses a significant threat to human life with a high global mortality rate. Early and accurate detection is crucial for improving treatment quality and the survival rate. This paper presents a comprehensive approach to enhance colon cancer detection and classification. The histopathological images are gathered from the CRC-VAL-HE-7K dataset. The images undergo preprocessing to improve quality, followed by augmentation to increase dataset size and enhance model generalization. A deep learning based transformer model is designed for efficient feature extraction and enhancing classification by incorporating a convolutional neural network (CNN). A cross-transformation model captures long-range dependencies between regions, and an attention mechanism assigns weights to highlight crucial features. To boost classification accuracy, a Siamese network distinguishes colon cancer tissue classes based on probabilities. Optimization algorithms fine-tune model parameters, categorizing colon cancer tissues into different classes. The multi-class classification performance is evaluated in the experimental evaluation, which demonstrates that the proposed model provided highest accuracy rate of 98.84%. In this research article, the proposed method achieved better performance in all analyses by comparing with other existing methods. RESEARCH HIGHLIGHTS: Deep learning-based techniques are proposed. DL methods are used to enhance colon cancer detection and classification. CRC-VAL-HE-7K dataset is utilized to enhance image quality. Hybrid particle swarm optimization (PSO) and dwarf mongoose optimization (DMO) are used. The deep learning models are tuned by implementing the PSO-DMO algorithm.

BRAVE: A cascaded generative model with sample attention for robust few shot image classification

Few-shot learning (FSL) confronts notable challenges due to the disparity between training and testing categories, leading to channel bias in neural networks and hindering accurate feature discernment. To address this, we introduce Biased-Reduction Attentive Network (BRAVE), an innovative model that incorporates a refined Vector Quantized Variational Autoencoder (VQ-VAE) backbone, enhanced with our Diverse Quantization (DQ) Module, for unbiased, fine-grained feature creation. Alongside, our Sample Attention (SA) Module is utilized for extracting discriminative features from these unbiased, fine-grained features. The DQ Module in BRAVE strategically integrates prior distribution regularization and stochastic masking with Gumbel sampling for balanced and diverse codebook engagement, while the SA Module leverages inter-sample dynamics for identifying critical features. This synergy effectively counters channel bias and boosts classification accuracy in FSL setups, surpassing current leading methods. Our approach represents a practical balance between preserving detailed features through the decoder and ensuring classification effectiveness, marking a significant advance in FSL. BRAVE’s implementation is accessible for community use and further exploration. Code and models available at https://github.com/ApocalypsezZ/BRAVE.

A Novel Classification Approach for Retinal Disease Using Improved Gannet Optimization‐Based Capsule DenseNet

ABSTRACTAn unusual condition of the eye called diabetic retinopathy affects the human retina and is brought on by the blood's constant rise in insulin levels. Loss of vision is the result. Diabetic retinopathy can be improved by receiving an early diagnosis to prevent further damage. A cost‐effective method of accumulating medical treatments is through appropriate DR screening. In this work, deep learning framework is introduced for the accurate classification of retinal diseases. The proposed method processes retinal fundus images obtained from databases, addressing noise and artifacts through an improved median filter (ImMF). It leverages the UNet++ model for precise segmentation of the disease‐affected regions. UNet++ enhances feature extraction through cross‐stage connections, improving segmentation results. The segmented images are then fed as input to the improved gannet optimization‐based capsule DenseNet (IG‐CDNet) for retinal disease classification. The hybrid capsule DenseNet (CDNet) classifies disease and is optimized using the improved gannet optimization algorithm to boost classification accuracy. Finally, the accuracy and dice score values achieved are 0.9917 and 0.9652 on the APTOS‐2019 dataset.

Enhanced Classification of Human Fall and Sit Motions Using Ultra-Wideband Radar and Hidden Markov Models

In this study, we address the challenge of accurately classifying human movements in complex environments using sensor data. We analyze both video and radar data to tackle this problem. From video sequences, we extract temporal characteristics using techniques such as motion history images (MHI) and Hu moments, which capture the dynamic aspects of movement. Radar data are processed through principal component analysis (PCA) to identify unique detection signatures. We refine these features using k-means clustering and employ them to train hidden Markov models (HMMs). These models are tailored to distinguish between distinct movements, specifically focusing on differentiating sitting from falling motions. Our experimental findings reveal that integrating video-derived and radar-derived features significantly improves the accuracy of motion classification. Specifically, the combined approach enhanced the precision of detecting sitting motions by over 10% compared to using single-modality data. This integrated method not only boosts classification accuracy but also extends the practical applicability of motion detection systems in diverse real-world scenarios, such as healthcare monitoring and emergency response systems.

Logo recognition of vehicles based on deep convolutional generative adversarial networks

Vehicle logo recognition plays a critical role in enhancing the efficiency of intelligent transportation systems by enabling accurate vehicle identification and tracking. Despite advancements in image recognition technologies, accurately detecting and classifying vehicle logos in diverse and dynamically changing environments remains a significant challenge. This research introduces an innovative approach utilizing a Deep Convolutional Generative Adversarial Network (DCGAN) framework, tailored specifically for the complex task of vehicle logo recognition. Unlike traditional methods, which heavily rely on manual feature extraction and pre-defined image processing techniques, our method employs a novel DCGAN architecture. This architecture automatically learns the distinctive features of vehicle logos directly from data, enabling more robust and accurate recognition across various conditions. Furthermore, we propose a refined training strategy for both the generator and discriminator components of our DCGAN, optimized through extensive experimentation, to enhance the model’s ability to generate high-fidelity vehicle logo images for improved training efficacy. The technical core of our approach lies in the strategic integration of transfer learning techniques. These techniques significantly boost classification accuracy by leveraging pre-learned features from vast image datasets, thereby addressing the challenge of limited labeled data in the vehicle logo domain. Our experimental results demonstrate a substantial improvement in logo detection and classification accuracy, achieving an Intersection over Union (IoU) ratio of 42.67 % and a classification accuracy of 99.78 %, which markedly surpasses the performance of existing methods. This research not only advances the field of vehicle logo recognition but also contributes to the broader domain of measurement science and technology, offering a technically sound and logically coherent solution to a complex problem.

A fast interpretable adaptive meta-learning enhanced deep learning framework for diagnosis of diabetic retinopathy

Gradient-based meta-learning algorithms offer promising solutions to the challenge of swift adaptation to new tasks, especially when faced with limited sample data. One pivotal concern in few-shot classification tasks is striking the right balance between interpretability and accuracy within the meta-learning framework. This study introduces a novel methodology titled Fast, Interpretable, and Adaptive meta-Learning based on Logistic Regression (FIAML-LR). Distinctively, FIAML-LR employs logistic regression to craft a meta-network in the inner loop. This design facilitates faster generation of the learning rate and weight attenuation coefficient, enhancing the interpretability of meta-learning for new task adaptation. An adaptable parameter update strategy is also embedded, initializing with a broader hyperparameter adjustment scope and fine-tuning progressively throughout the experiment. Experimental evidence reveals that, when implemented on a 4-CONV architecture, FIAML-LR not only bolsters the model's interpretability but also amplifies its accuracy for few-shot classification tasks. A focused investigation on the diabetic retinopathy dataset demonstrated that FIAML-LR, even with limited data, could boost classification accuracy by a significant 14.28% against the benchmark model. This heightened accuracy could aid medical professionals in more precisely diagnosing diabetic retinopathy.

Classification Certainty Maximization for Unsupervised Domain Adaptation

The bi-classifier paradigm is a common practice in unsupervised domain adaptation (UDA), where two classifiers are leveraged to guide the model to learn domain invariant features. Previous approaches only focused on the consistency of the outputs between classifiers, but ignored the classification certainty of each classifier. Therefore, existing methods in some cases may mislead the classifiers into the wrong direction of ambiguous outputs and subsequently undermine the discriminability. To challenge this problem, in this paper we propose Classification Certainty Maximization (CCM) which considers both the joint certainty between classifiers and the individual certainty of each classifier via a novel formulation, and derived their optimal weight ratios by theoretical derivation from the perspective of gradient. In addition, we also propose a dynamic centroid update strategy to mitigate the domain gaps at the feature level. Extensive experiments on four widely used UDA datasets show that CCM performs better than the existing state-of-the-art domain adaptation methods. Notably, our dynamic centroid update strategy can be used as a plug-and-play module for existing bi-classifier domain adaptation methods to boost classification accuracy.

THFN: Emotional health recognition of elderly people using a Two-Step Hybrid feature fusion network along with Monte-Carlo dropout

The influence of technology’s progress on the ability to read people's emotions has received increased attention in recent years. It is essential to identify the elderly's feelings because it indicates mental wellness. This study proposes a unique approach to micro-information extraction using a cross-model attention mechanism and a two-step hybrid feature fusion Network (THFN). To predict feelings across many channels, the study suggests using a cross-model attention network. The model improves the accuracy of emotion prediction in the elderly by employing a fusion mechanism at both the feature level and the decision level. In addition, Monte-Carlo dropout (MCD) in the deep neural model is employed for improved classification and uncertainty prediction. As an activation function, the first-order derivative of Mish (Fmish) helps to boost classification accuracy. ElderReact is a brand-new multimodal dataset which is employed for senior citizens' responses to stimuli designed to evoke emotions. This research contributes to the emotional lives of the elderly, which helps to design better involvements to improve their mental health. The experimental results show that the proposed approach achieves a precision of 0.99, Recall of 0.99, F1-score of 1.00 and 99.8% accuracy, the sensitivity of 99.7% and specificity of 98.9% in emotion classification, and 100% accuracy in emotional health prediction. From the experimental results, it is proved that the proposed model performs better than the previously suggested models.

Pneumonia detection with QCSA network on chest X-ray

Worldwide, pneumonia is the leading cause of infant mortality. Experienced radiologists use chest X-rays to diagnose pneumonia and other respiratory diseases. The diagnostic procedure's complexity causes radiologists to disagree with the decision. Early diagnosis is the only feasible strategy for mitigating the disease's impact on the patent. Computer-aided diagnostics improve the accuracy of diagnosis. Recent studies established that Quaternion neural networks classify and predict better than real-valued neural networks, especially when dealing with multi-dimensional or multi-channel input. The attention mechanism has been derived from the human brain's visual and cognitive ability in which it focuses on some portion of the image and ignores the rest portion of the image. The attention mechanism maximizes the usage of the image's relevant aspects, hence boosting classification accuracy. In the current work, we propose a QCSA network (Quaternion Channel-Spatial Attention Network) by combining the spatial and channel attention mechanism with Quaternion residual network to classify chest X-Ray images for Pneumonia detection. We used a Kaggle X-ray dataset. The suggested architecture achieved 94.53% accuracy and 0.89 AUC. We have also shown that performance improves by integrating the attention mechanism in QCNN. Our results indicate that our approach to detecting pneumonia is promising.

A New Proposed Hybrid Learning Approach with Features for Extraction of Image Classification

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven classifiers. A hybrid supervised learning system that takes advantage of rich intermediate features extracted from deep learning compared to traditional feature extraction to boost classification accuracy and parameters is suggested. They provide the same set of characteristics to discover and verify which classifier yields the best classification with our new proposed approach of “hybrid learning.” To achieve this, the performance of classifiers was assessed depending on a genuine dataset that was taken by our camera system. The simulation results show that the support vector machine (SVM) has a mean square error of 0.011, a total accuracy ratio of 98.80%, and an F1 score of 0.99. Moreover, the results show that the LR classifier has a mean square error of 0.035 and a total ratio of 96.42%, and an F1 score of 0.96 comes in the second place. The ANN classifier has a mean square error of 0.047 and a total ratio of 95.23%, and an F1 score of 0.94 comes in the third place. Furthermore, RF, WKNN, DT, and NB with a mean square error and an F1 score advance to the next stage with accuracy ratios of 91.66%, 90.47%, 79.76%, and 75%, respectively. As a result, the main contribution is the enhancement of the classification performance parameters with images of varying brightness and clarity using the proposed hybrid learning approach.

Deep feature fusion and optimized feature selection based ensemble classification of liver lesions

ABSTRACT Classification of liver abnormalities is crucial for the early identification of liver cancer. In clinical settings, radiological professionals typically make diagnoses manually which is subjective, time-consuming and vulnerable to error. Therefore, there is still a demand for precise classification of liver diseases. We propose an Ensemble learning-based classification model to classify liver lesions on CT images. To excerpt all the essential facts from the image, deep feature fusion is incorporated by concatenating the features from pre-trained deep CNN models densenet201 and InceptionResnetV2. To minimize the feature space and boost classification accuracy, hybrid optimization methodologies, Genetic Algorithms and Ant Colony Optimization are applied. Finally, a Heterogeneous Ensemble classifier divides the retrieved features into four groups (liver abscess, liver cirrhosis, hepatocellular carcinoma, and metastasis). It is clearly seen and observed that 98.3% accuracy is contributed by ensemble classifier with the support of concatenated deep features and this classifier excels in all other ways and means.

Effective stabilized self-training on few-labeled graph data

Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer from severe performance degradation. Specifically, we observe that existing GNNs suffer from unstable training process on few-labeled graphs, resulting to inferior performance on node classification. Therefore, we propose an effective framework, Stabilized Self-Training (SST), which is applicable to existing GNNs to handle the scarcity of labeled data, and consequently, boost classification accuracy. We conduct thorough empirical and theoretical analysis to support our findings and motivate the algorithmic designs in SST. We apply SST to two popular GNN models GCN and DAGNN, to get SSTGCN and SSTDA methods respectively, and evaluate the two methods against 10 competitors over 5 benchmarking datasets. Extensive experiments show that the proposed SST framework is highly effective, especially when few labeled data are available. Our methods achieve superior performance under almost all settings over all datasets. For instance, on a Cora dataset with only 1 labeled node per class, the accuracy of SSTGCN is 62.5%, 17.9% higher than GCN, and the accuracy of SSTDA is 66.4%, which outperforms DAGNN by 6.6%.

An investigation of fusion strategies for boosting pig cough sound recognition

The recognition of pig cough sounds is an effective way to monitor pig respiratory diseases which seriously affect healthy pig breeding. Due to the complexity of the pig-housing environment, achieving high precision cough recognition by relying only on a single feature or classifier is challenging. Therefore, in this study we investigated two fusion strategies, namely feature fusion and classifier fusion, to boost classification accuracy. For feature fusion, we improved the previously proposed feature fusion algorithm and selected better acoustic and image features for fusion. We also proposed a novel classifier fusion algorithm. In the algorithm, the support vector machine (SVM) classifiers trained by the acoustic features and deep features were fused by soft voting for pig cough prediction. The sound data collected in the pig barn were used to validate the proposed methods. Our methods achieved a substantial classification rate of 97.47% and 99.20% for feature fusion and classifier fusion, respectively. The results demonstrate that our proposed fusion strategies can significantly improve the recognition accuracy of pig cough sounds.

Hybrid Attention-Based Encoder–Decoder Fully Convolutional Network for PolSAR Image Classification

Recently, methods based on convolutional neural networks (CNNs) achieve superior performance in polarimetric synthetic aperture radar (PolSAR) image classification. However, the current CNN-based classifiers follow patch-based frameworks, which need input images to be divided into overlapping patches. Consequently, these classification approaches have the drawback of requiring repeated calculations and only relying on local information. In addition, the receptive field size in conventional CNN-based methods is fixed, which limits the potential to extract features. In this paper, a hybrid attention-based encoder–decoder fully convolutional network (HA-EDNet) is presented for PolSAR classification. Unlike traditional CNN-based approaches, the encoder–decoder fully convolutional network (EDNet) can use an arbitrary-size image as input without dividing. Then, the output is the whole image classification result. Meanwhile, the self-attention module is used to establish global spatial dependence and extract context characteristics, which can improve the performance of classification. Moreover, an attention-based selective kernel module (SK module) is included in the network. In the module, softmax attention is employed to fuse several branches with different receptive field sizes. Consequently, the module can capture features with different scales and further boost classification accuracy. The experiment results demonstrate that the HA-EDNet achieves superior performance compared to CNN-based and traditional fully convolutional network methods.

Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets.

Cervical cancer is a significant disease affecting women worldwide. Regular cervical examination with gynecologists is important for early detection and treatment planning for women with precancers. Precancer is the direct precursor to cervical cancer. However, there is a scarcity of experts and the experts' assessments are subject to variations in interpretation. In this scenario, the development of a robust automated cervical image classification system is important to augment the experts' limitations. Ideally, for such a system the class label prediction will vary according to the cervical inspection objectives. Hence, the labeling criteria may not be the same in the cervical image datasets. Moreover, due to the lack of confirmatory test results and inter-rater labeling variation, many images are left unlabeled. Motivated by these challenges, we propose to develop a pretrained cervix model from heterogeneous and partially labeled cervical image datasets. Self-supervised Learning (SSL) is employed to build the cervical model. Further, considering data-sharing restrictions, we show how federated self-supervised learning (FSSL) can be employed to develop a cervix model without sharing the cervical images. The task-specific classification models are developed by fine-tuning the cervix model. Two partially labeled cervical image datasets labeled with different classification criteria are used in this study. According to our experimental study, the cervix model prepared with dataset-specific SSL boosts classification accuracy by 2.5%↑ than ImageNet pretrained model. The classification accuracy is further boosted by 1.5%↑ when images from both datasets are combined for SSL. We see that in comparison with the dataset-specific cervix model developed with SSL, the FSSL is performing better.

Speech Attribute Detection to Recognize Arabic Broadcast Speech in Industrial Networks

In this work, we present an alternative model to Arabic speech recognitions to boost classification accuracy of basic speech units in Industrial Internet of Things. This approach integrates both top-down and bottom-up knowledge into the automatic speech attribute transcription (ASAT) framework. ASAT is a new family of lattice-based speech recognition systems grounded on accurate detection of speech attributes. Two state-of-the-art deep neural networks were used for attribute speech feature detection, convolutional neural networks (CNNs) and feed-forward neural network, with pretraining using a stack of restricted Boltzmann machines (DBN-DNN). These attribute detectors are trained using a data-driven approach for Arabic speech data using the Buckwalter code for Arabic transcription. The detectors work by detecting phonologically distinctive articulatory features of Arabic based on manner and place of articulation, which extract characteristics of the human speech production process from the speech dataset. The results of the work are shown in terms of average equal error rate inferring that the attribute model based on the CNN consistently outperforms the DBN-DNN model. Attribute detectors with CNN, versus DBN-DNN model, reduce the AEER producing 10.42% relative improvements for manner of articulation and producing 13.11% relative improvements for place of articulation.

The Applications of Metaheuristics for Human Activity Recognition and Fall Detection Using Wearable Sensors: A Comprehensive Analysis.

In this paper, we study the applications of metaheuristics (MH) optimization algorithms in human activity recognition (HAR) and fall detection based on sensor data. It is known that MH algorithms have been utilized in complex engineering and optimization problems, including feature selection (FS). Thus, in this regard, this paper used nine MH algorithms as FS methods to boost the classification accuracy of the HAR and fall detection applications. The applied MH were the Aquila optimizer (AO), arithmetic optimization algorithm (AOA), marine predators algorithm (MPA), artificial bee colony (ABC) algorithm, genetic algorithm (GA), slime mold algorithm (SMA), grey wolf optimizer (GWO), whale optimization algorithm (WOA), and particle swarm optimization algorithm (PSO). First, we applied efficient prepossessing and segmentation methods to reveal the motion patterns and reduce the time complexities. Second, we developed a light feature extraction technique using advanced deep learning approaches. The developed model was ResRNN and was composed of several building blocks from deep learning networks including convolution neural networks (CNN), residual networks, and bidirectional recurrent neural networks (BiRNN). Third, we applied the mentioned MH algorithms to select the optimal features and boost classification accuracy. Finally, the support vector machine and random forest classifiers were employed to classify each activity in the case of multi-classification and to detect fall and non-fall actions in the case of binary classification. We used seven different and complex datasets for the multi-classification case: the PAMMP2, Sis-Fall, UniMiB SHAR, OPPORTUNITY, WISDM, UCI-HAR, and KU-HAR datasets. In addition, we used the Sis-Fall dataset for the binary classification (fall detection). We compared the results of the nine MH optimization methods using different performance indicators. We concluded that MH optimization algorithms had promising performance in HAR and fall detection applications.

Target Classification of Similar Spatial Characteristics in Complex Urban Areas by Using Multispectral LiDAR

With the rapid modernization, many remote-sensing sensors were developed for classifying urban land and environmental monitoring. Multispectral LiDAR, which serves as a new technology, has exhibited potential in remote-sensing monitoring due to the synchronous acquisition of three-dimension point cloud and spectral information. This study confirmed the potential of multispectral LiDAR for complex urban land cover classification through three comparative methods. Firstly, the Optech Titan LiDAR point cloud was pre-processed and ground filtered. Then, three methods were analyzed: (1) Channel 1, based on Titan data to simulate the classification of a single-band LiDAR; (2) three-channel information and the digital surface model (DSM); and (3) three-channel information and DSM combined with the calculated three normalized difference vegetation indices (NDVIs) for urban land classification. A decision tree was subsequently used in classification based on the combination of intensity information, elevation information, and spectral information. The overall classification accuracies of the point cloud using the single-channel classification and the multispectral LiDAR were 64.66% and 93.82%, respectively. The results show that multispectral LiDAR has excellent potential for classifying land use in complex urban areas due to the availability of spectral information and that the addition of elevation information to the classification process could boost classification accuracy.

WetNet: A Spatial–Temporal Ensemble Deep Learning Model for Wetland Classification Using Sentinel-1 and Sentinel-2

While deep learning models have been extensively applied to land-use land-cover (LULC) problems, it is still a relatively new and emerging topic for separating and classifying wetland types. On the other hand, ensemble learning has demonstrated promising results in improving and boosting classification accuracy. Accordingly, this study aims to develop a classification system for mapping complex wetland areas by incorporating deep ensemble learning and satellite datasets. To this end, time series of Sentinel-1 dual-polarized Synthetic Aperture Radar (SAR) dataset, alongside Sentinel-2 multispectral imagery (MSI), are used as input data to the model. In order to increase the diversity of the extracted features, the proposed model, herein called WetNet, consists of three different submodels, comprising several recurrent and convolutional layers. Furthermore, multiple ensembling sections are added to different stages of the model to increase the transferability of the model (to other areas) and the reliability of the final results. WetNet is evaluated in a complex wetland area located in Newfoundland, Canada. Experimental results indicate that WetNet outperforms the state-of-the-art deep models (e.g., InceptionResnetV2, InceptionV3, and DenseNet121) in terms of both the classification accuracy and processing time. This makes WetNet an efficient model for large-scale wetland mapping application. The python code of the proposed WetNet model is available at the following link for the sake of reproducibility: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://colab.research.google.com/drive/1pvMOd3_tFYaMYGyHNfxqDxOiwF78lKgN?usp=sharing</uri>