Dropout Layer Research Articles

Abstract PR019: Transfer learning for accurate tissue of origin classification from cfDNA methylation

Abstract Accurately predicting the tissue of origin (TOO) is required for blood-based multi-cancer screening to guide follow-up imaging and care when cancer is detected. However, precisely determining the TOO using cell-free DNA (cfDNA) methylation remains challenging due to low and variable concentrations of circulating tumor DNA and cfDNA and the complex, poorly characterized nature of tissue-specific methylation patterns. To address these challenges, we developed a transfer learning approach that leverages methylation profiles learned from tissue biopsy samples to predict the TOO of cfDNA cancer samples. Our model achieved 89% balanced accuracy (BA) in classifying the TOO across 10 cancer groups and outperformed models trained solely on plasma cfDNA data. Unmatched tissue biopsy (N=517) and blood (N=1,155, NCT05435066) samples were collected from treatment-naïve cancer patients across 21 tumor types consolidated into 17 cancer groups. All samples were analyzed using a custom targeted bisulfite sequencing hybrid capture assay. Five unique metrics were used to quantify informative methylation signal at each TOO region of interest. A feed-forward neural network was first trained on biopsy methylation features, where the cancer signal is strongest. Subsequently, the model was fine-tuned using plasma cfDNA methylation features, which have significantly lower signal-to-noise ratio, allowing the model to adapt its predictions to the noisier data. The Adam optimizer was employed for both training and fine-tuning, with early stopping implemented to prevent overfitting. Dropout layers were incorporated to enhance model generalization and performance was evaluated using 10-fold cross validation on plasma cfDNA samples across 10 cancer groups for which at least 25 plasma samples were available (N=1,041). The same architecture was trained exclusively on plasma cfDNA samples for comparison. Results are reported for samples with tumor content greater than 0.1% (N=415). Our TOO prediction achieved 73% BA in top-one predictions, where the true label matched the highest probability prediction, and 89% BA in top-two predictions, where the true label matched the highest or the second-highest probability prediction. Multi-class classification revealed our method significantly outperforms a model trained only on plasma cfDNA data. The plasma only model achieved 69% and 82% BA in top-one and top-two predictions, respectively. Accuracy per indication revealed that training on biopsy data significantly improves the detection of tumor types that shed DNA at low rates compared to training on plasma data alone (breast cancer +14%, prostate cancer +12%, and uterine cancer +20% points). In conclusion, our transfer learning approach, utilizing tissue biopsy methylation data, significantly improves cfDNA-based TOO detection accuracy. This approach highlights the capability of transfer learning to enable automated feature extraction from signal-rich data to enhance the analysis of more challenging, heterogeneous cfDNA samples, advancing non-invasive cancer diagnostics. Citation Format: Shiva Farashahi, Amirali Kia, Dorna Kashef, Esther Brown, Feras Hantash, Kieran I Chacko. Transfer learning for accurate tissue of origin classification from cfDNA methylation [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr PR019.

SSFAN: A Compact and Efficient Spectral-Spatial Feature Extraction and Attention-Based Neural Network for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is a crucial technique that assigns each pixel in an image to a specific land cover category by leveraging both spectral and spatial information. In recent years, HSI classification methods based on convolutional neural networks (CNNs) and Transformers have significantly improved performance due to their strong feature extraction capabilities. However, these improvements often come with increased model complexity, leading to higher computational costs. To address this, we propose a compact and efficient spectral-spatial feature extraction and attention-based neural network (SSFAN) for HSI classification. The SSFAN model consists of three core modules: the Parallel Spectral-Spatial Feature Extraction Block (PSSB), the Scan Block, and the Squeeze-and-Excitation MLP Block (SEMB). After preprocessing the HSI data, it is fed into the PSSB module, which contains two parallel streams, each comprising a 3D convolutional layer and a 2D convolutional layer. The 3D convolutional layer extracts spectral and spatial features from the input hyperspectral data, while the 2D convolutional layer further enhances the spatial feature representation. Next, the Scan Block module employs a layered scanning strategy to extract spatial information at different scales from the central pixel outward, enabling the model to capture both local and global spatial relationships. The SEMB module combines the Spectral-Spatial Recurrent Block (SSRB) and the MLP Block. The SSRB, with its adaptive weight assignment mechanism in the SToken Module, flexibly handles time steps and feature dimensions, performing deep spectral and spatial feature extraction through multiple state updates. Finally, the MLP Block processes the input features through a series of linear transformations, GELU activation functions, and Dropout layers, capturing complex patterns and relationships within the data, and concludes with an argmax layer for classification. Experimental results show that the proposed SSFAN model delivers superior classification performance, outperforming the second-best method by 1.72%, 5.19%, and 1.94% in OA, AA, and Kappa coefficient, respectively, on the Indian Pines dataset. Additionally, it requires less training and testing time compared to other state-of-the-art deep learning methods.

Comparative analysis of vision transformers and fine-tuned transfer learning models for brain tumor classification

Brain tumors are a primary factor causing cancer-related deaths globally, and their classification remains a significant research challenge due to the variability in tumor intensity, size, and shape, as well as the similar appearances of different tumor types. Accurate differentiation is further complicated by these factors, making diagnosis difficult even with advanced imaging techniques such as magnetic resonance imaging (MRI). Recent techniques in artificial intelligence (AI), in particular deep learning (DL), have improved the speed and accuracy of medical image analysis, but they still face challenges like overfitting and the need for large annotated datasets. This study addresses these challenges by presenting two approaches for brain tumor classification using MRI images. The first approach involves fine-tuning transfer learning cutting-edge models, including SEResNet, ConvNeXtBase, and ResNet101V2, with global average pooling 2D and dropout layers to minimize overfitting and reduce the need for extensive preprocessing. The second approach leverages the Vision Transformer (ViT), optimized with the AdamW optimizer and extensive data augmentation. Experiments on the BT-Large-4C dataset demonstrate that SEResNet achieves the highest accuracy of 97.96%, surpassing ViT’s 95.4%. These results suggest that fine-tuning and transfer learning models are more effective at addressing the challenges of overfitting and dataset limitations, ultimately outperforming the Vision Transformer and existing state-of-the-art techniques in brain tumor classification.

Employing Xception convolutional neural network through high-precision MRI analysis for brain tumor diagnosis

The classification of brain tumors from medical imaging is pivotal for accurate medical diagnosis but remains challenging due to the intricate morphologies of tumors and the precision required. Existing methodologies, including manual MRI evaluations and computer-assisted systems, primarily utilize conventional machine learning and pre-trained deep learning models. These systems often suffer from overfitting due to modest medical imaging datasets and exhibit limited generalizability on unseen data, alongside substantial computational demands that hinder real-time application. To enhance diagnostic accuracy and reliability, this research introduces an advanced model utilizing the Xception architecture, enriched with additional batch normalization and dropout layers to mitigate overfitting. This model is further refined by leveraging large-scale data through transfer learning and employing a customized dense layer setup tailored to effectively distinguish between meningioma, glioma, and pituitary tumor categories. This hybrid method not only capitalizes on the strengths of pre-trained network features but also adapts specific training to a targeted dataset, thereby improving the generalization capacity of the model across different imaging conditions. Demonstrating an important improvement in diagnostic performance, the proposed model achieves a classification accuracy of 98.039% on the test dataset, with precision and recall rates above 96% for all categories. These results underscore the possibility of the model as a reliable diagnostic tool in clinical settings, significantly surpassing existing diagnostic protocols for brain tumors.

CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis

Psoriasis, being a chronic, inflammatory, lifelong skin disorder, has become a major threat to the human population. The precise and effective diagnosis of psoriasis continues to be difficult for clinicians due to its varied nature. In northern India, the prevalence of psoriasis among adult population ranges from 0.44 to 2.8%. Chronic plaque psoriasis accounts for over 90% of cases. This study utilized a dataset of 325 raw images collected from a reputable local hospital using a digital camera under uniform lighting conditions. These images were processed to generate 496 image patches (both diseased and normal), which were then normalized and resized for model training. An automated psoriasis image recognition framework was developed using four state-of-the-art deep transfer learning models: VGG16, VGG19, MobileNetV1, and ResNet-50. The convolutional layers adopted various edge, shape, and color filters to generate the feature map for psoriasis detection. Each pre-trained model was adapted with two dense layers, one dropout layer, and one output layer to classify input images. Among these models, MobileNetV1 achieved the best performance, with 94.84% sensitivity, 89.37% specificity, and 97.24% overall accuracy. Hyper-parameter tuning was performed using grid search to optimize learning rates, batch sizes, and dropout rates. The AdaGrad (Adaptive gradient)) optimizer was chosen for its adaptive learning rate capabilities, facilitating quicker convergence in model performance. Consequently, the methodology’s performance improved to 94.25% sensitivity, 96.42% specificity, and 99.13% overall accuracy. The model’s performance was also compared with non-machine learning-based diagnostic methods, yielding a Dice coefficient of 0.98. However, the model’s effectiveness is dependent upon high-quality input images, as poor image conditions may affect accuracy, and it may not generalize well across diverse demographics or psoriasis variations, highlighting the need for varied training datasets for robustness.

Financial Time Series Forecasting Based on Long-Short Term Memory, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Batch Normalization

Long-short term memory (LSTM) is a state-of-art and widely used model to forecast financial time series. However, primitive LSTM networks do not perform well due to over-fitting problems of the deep learning model and nonlinear and non-stationary characteristics of financial time series data. In addition, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is an outstanding data frequency decomposition technique that can decompose original time series into several intrinsic mode functions and a residue. Thus, this paper proposed a novel hybrid network CEEMDAN-LSTM-BN based on LSTM. Specifically, to avoid over-fitting, the modified LSTM-BN network consists of two LSTM layers, two Batch Normalization (BN) layers following each LSTM layer, and a dropout layer. Each of the intrinsic mode functions and the residue would be processed by CEEMDAN-LSTM-BN and the final prediction results are obtained by reconstructing each predictive series. The advantages of the proposed CEEMDANLSTM-BN networks are verified by comparing them to primitive LSTM, other hybrid models, and some famous machine learning models. Moreover, the robustness of the networks is assessed by numerical experiments on different stock indices datasets.

A seed-epidermis-feature-recognition-based lightweight peanut seed selection method for embedded systems

High-quality seeds improve the germination rate. Therefore, seed selection before sowing peanuts is crucial. Current peanut seed selection methods include color sorters and sieving machines, which are efficient but lack accuracy due to their reliance on a single indicator. Manual selection is inefficient and subject to subjective influences. Although machine vision and deep learning have performed well in crops such as corn and pepper, most existing research is based on PC or MATLAB platforms, which are not portable and are prone to interference, making them unsuitable for field applications. This study developed a lightweight model for recognizing peanut seed epidermal features. The model was based on deep learning and model quantization techniques. The transfer learning method was used to use four pre-trained models, EfficientNet_b0, EfficientNetv2-b0, MobileNet_v2_35_224, and NasNet_Mobile, as feature extraction layers, the input layer was added before the feature extraction layer, and the dropout and dense layers were added after the feature extraction layer to construct a classifier. The peanut seed selection network(PSSNet) models were constructed and named PSSNet-E, PSSNet-E2, PSSNet-M, and PSSNet-N, respectively, and trained on the Huayu 22 peanut seed dataset constructed in this study. The constructed models were compressed using model quantization technology, and four quantized models were obtained, namely PSSNet-Ef, PSSNet-E2f, PSSNet-Mf, and PSSNet-Nf. Finally, PSSNet-Mf, which had the best model evaluation, was selected as the peanut selection model for this study and deployed on a prototype for testing. Compared with the unquantized model, the size of the quantized model was reduced by two-thirds and the running speed was increased by 37%. A total of 400 Huayu 22 peanut seeds were selected as test samples, and 5 selection tests were conducted.The results showed that the average accuracy was 95.3%, which met the requirements of peanut selection at the production site.

Prediction of cancer therapy related cardiac dysfunction by using a machine learning approach with cardiac magnetic resonance images

Abstract Background There is inconsistent data on the value of baseline and early cardiac function assessment on identifying patients at risk of cancer therapy related cardiac dysfunction (CTRCD). Whether machine learning (ML) approaches applied to cardiac MRI (CMR) images may help risk stratify patients is unclear. Purpose In women with HER2+ breast cancer receiving sequential anthracyclines and trastuzumab we sought to (i) assess if a ML approach applied to pre-cancer therapy and early post anthracycline CMR short axis (SAX) cines can help identify patients at risk for future CTRCD and (ii) whether this approach is superior to using clinical and manual quantitative CMR data. Methods Women with HER2+ breast cancer from the EMBRACE-MRI study underwent 5 CMR studies (pre-cancer therapy, post anthracyclines, 3, 6 and 12 months during trastuzumab). CTRCD was defined using the CREC criteria by end of treatment. Three models were created: 1) clinical data (demographics, cardiovascular risk factors and medications); 2) clinical and manual quantitative CMR data (right and left ventricular volumes and LVEF); and 3) ML model based on SAX cine CMR images only. We focused on the pre-cancer therapy CMR and 1st visit post-anthracycline CMR. All images underwent standardised formatting. A 3D convolutional neural networks model architecture was used. The model consisted of multiple convolutional layers followed by max pooling and global average pooling layers. The output of the convolutional layers were then fed into a dense layer of 128 nodes incorporating an L2 activity regularizer and a subsequent dropout layer. To train and tune the model, the process was iterated 50 times. In each iteration, the patient participant dataset was shuffled, and a random 80% of patients were selected for training and tuning. The tuned model was then applied to the remaining 20% of patients in each iteration, and this entire cycle of shuffling, training, and testing was repeated 50 times with replacement. Area Under the Curve (AUC), accuracy, sensitivity, and specificity were calculated on the test set and averaged across folds to determine each model’s performance. Results 135 women were included (mean age 51.1±9.2 years) mean doxorubicin equivalent was dose 204.9±12.5mg/m2. Cardiovascular risk factors were prevalent: 33 (24%) had a smoking history; 21 (15%) had hypertension. 37 (27%) developed CTRCD. The ML model using baseline CMR cine data only had a higher AUC (0.84 95% CI [0.83-0.86]) for the detection of CTRCD compared to clinical data (0.62 95% CI [0.59-0.65]) and clinical and CMR data (0.62 95% CI [0.60-0.65]). This further improved with the addition of post-anthracycline CMR data (Table 1). Conclusion A ML model examining early cardiac MRI data with short axis cine CMR images performed better than those using clinical or manual quantitative CMR data for the prediction of CTRCD. Further studies including external validation are needed.Table 1 Mean and 95% CIs

Utilizing Attention-Enhanced Deep Neural Networks for Large-Scale Preliminary Diabetes Screening in Population Health Data

Early screening for diabetes can promptly identify potential early stage patients, possibly delaying complications and reducing mortality rates. This paper presents a novel technique for early diabetes screening and prediction, called the Attention-Enhanced Deep Neural Network (AEDNN). The proposed AEDNN model incorporates an Attention-based Feature Weighting Layer combined with deep neural network layers to achieve precise diabetes prediction. In this study, we utilized the Diabetes-NHANES dataset and the Pima Indians Diabetes dataset. To handle significant missing values and outliers, group median imputation was applied. Oversampling techniques were used to balance the diabetes and non-diabetes groups. The data were processed through an Attention-based Feature Weighting Layer for feature extraction, producing a feature matrix. This matrix was subjected to Hadamard product operations with the raw data to obtain weighted data, which were subsequently input into deep neural network layers for training. The parameters were fine-tuned and the L2 regularization and dropout layers were added to enhance the generalization performance of the model. The model’s reliability was thoroughly assessed through various metrics, including the accuracy, precision, recall, F1 score, mean squared error (MSE), and R2 score, as well as the ROC and AUC curves. The proposed model achieved a prediction accuracy of 98.4% in the Pima Indians Diabetes dataset. When the test dataset was expanded to the large-scale Diabetes-NHANES dataset, which contains 52,390 samples, the test precision of the model improved further to 99.82%, with an AUC of 0.9995. A comparative analysis was conducted using multiple models, including logistic regression with L1 regularization, support vector machine (SVM), random forest, K-nearest neighbors (KNNs), AdaBoost, XGBoost, and the latest semi-supervised XGBoost. The feature extraction method using attention mechanisms was compared with the classical feature selection methods, Lasso and Ridge. The experiments were performed on the same dataset, and the conclusion was that the Attention-based Ensemble Deep Neural Network (AEDNN) outperformed all the aforementioned methods. These results indicate that the model not only performs well on smaller datasets but also fully leverages its advantages on larger datasets, demonstrating strong generalization ability and robustness. The proposed model can effectively assist clinicians in the early screening of diabetes patients. This is particularly beneficial for the preliminary screening of high-risk individuals in large-scale, extensive healthcare datasets, followed by detailed examination and diagnosis. Compared to the existing methods, our AEDNN model showed an overall performance improvement of 1.75%.

AI driven interpretable deep learning based fetal health classification

In this study, a deep learning model is proposed for the classification of fetal health into 3 categories: Normal, suspect, and pathological. The primary objective is to utilize the power of deep learning to improve the efficiency and effectiveness of diagnostic processes. A deep neural network (DNN) model is proposed for fetal health analysis using data obtained from Cardiotocography (CTG). A dataset containing 21 attributes is used to carry out this work. The model incorporates multiple hidden layers, augmented with batch normalization and dropout layers for improved generalization. This study assesses the model's interpretation ability in fetal health classification using explainable deep learning. This enhances transparency in decision-making of the classifier model by leveraging feature importance and feature saliency analysis, fostering trust and facilitating the clinical adoption of fetal health assessments. Our proposed model demonstrates a remarkable performance with 0.99 accuracy, 0.93 sensitivity, 0.93 specificity, 0.96 AUC, 0.93 precision, and 0.93 F1 scores in classifying fetal health. We also performed comparative analysis with six other models including Logistic Regression, KNN, SVM, Naive Bayes, Random Forest, and Gradient Boosting to assess and compare the effectiveness of our model and the accuracies of 0.89, 0.88, 0.90, 081, 0.93, and 0.93 were achieved respectively by these baseline models. The results revealed that our proposed model outperformed all the baseline models in terms of accuracy. This indicates the potential of deep learning in improving fetal health assessment and contributing to the field of obstetrics by providing a robust tool for early risk detection.

A comparative study of early stage Alzheimer’s disease classification using various transfer learning CNN frameworks

ABSTRACT The current research explores the improvements in predictive performance and computational efficiency that machine learning and deep learning methods have made over time. Specifically, the application of transfer learning concepts within Convolutional Neural Networks (CNNs) has proved useful for diagnosing and classifying the various stages of Alzheimer’s disease. Using base architectures such as Xception, InceptionResNetV2, DenseNet201, InceptionV3, ResNet50, and MobileNetV2, this study extends these models by adding batch normalization (BN), dropout, and dense layers. These enhancements improve the model’s effectiveness and precision in addressing the specified medical issue. The proposed model is rigorously validated and evaluated using publicly available Kaggle MRI Alzheimer’s data consisting of 1280 testing images and 5120 patient training images. For comprehensive performance evaluation, precision, recall, F1-score, and accuracy metrics are utilized. The findings indicate that the Xception method is the most promising of those considered. Without employing five K-fold techniques, this model obtains a 99% accuracy and 0.135 loss score. In addition, integrating five K-fold methods enhances the accuracy to 99.68% while decreasing the loss score to 0.120. The research further included the evaluation of the Receiver Operating Characteristic Area Under the Curve (ROC-AUC) for various classes and models. As a result, our model may detect and diagnose Alzheimer’s disease quickly and accurately.

A New Subject-Sensitive Hashing Algorithm Based on Multi-PatchDrop and Swin-Unet for the Integrity Authentication of HRRS Image

Transformer-based subject-sensitive hashing algorithms exhibit good integrity authentication performance and have the potential to ensure the authenticity and convenience of high-resolution remote sensing (HRRS) images. However, the robustness of Transformer-based subject-sensitive hashing is still not ideal. In this paper, we propose a Multi-PatchDrop mechanism to improve the performance of Transformer-based subject-sensitive hashing. The Multi-PatchDrop mechanism determines different patch dropout values for different Transformer blocks in ViT models. On the basis of a Multi-PatchDrop, we propose an improved Swin-Unet for implementing subject-sensitive hashing. In this improved Swin-Unet, Multi-PatchDrop has been integrated, and each Swin Transformer block (except the first one) is preceded by a patch dropout layer. Experimental results demonstrate that the robustness of our proposed subject-sensitive hashing algorithm is not only stronger than that of the CNN-based algorithms but also stronger than that of Transformer-based algorithms. The tampering sensitivity is of the same intensity as the AGIM-net and M-net-based algorithms, stronger than other Transformer-based algorithms.

Activated biochar production from young coconut waste (Cocos nucifera) as bioadsorbent: a pathway through Artificial Neural Network (ANN) optimization.

This pioneering work explores the immense potential of young coconut waste, a continuously marginalized residue of the food and beverage industry, to serve as an indispensable feedstock in the production of biochar. Through an examination of the key carbonization factors that include time, temperature, and concentrations of the activating agent, KOH, the outcomes offer relevant insights that could be leveraged to maximize biochar production for tailored applications. This study stands out for its innovative use of Artificial Neural Network (ANN) approaches for predictive modeling. Fifty datasets, supplemented with secondary data obtained from the literature and experiments, were utilized for the purposes of training, testing, and validating the neural network model. Here, the datasets were processed utilizing the Deep Neural Network (DNN) framework, which was designed and implemented with the minimal loss function framework feasible. The architectural configuration comprises the following; an input layer, four hidden layers (128-neuron dense layer, batch normalization, and 64-neuron dense layer, batch normalization), a dropout layer, and an output layer. With an R2 of 0.8238 for biochar yield and 0.7324 for iodine number, the trained DNN model showed a relatively high degree of accuracy in making predictions.

Deep learning Methods for ECG-Based Heart Disease Detection

Cardiovascular disease (CVD) continues to be a primary cause of death globally, and early detection plays a critical role in improving patient outcomes. This research introduces the development of a deep learning model designed to automatically categorize heart diseases using Electrocardiogram (ECG) data. The model utilizes a 1D Convolutional Neural Network (CNN) structure and makes use of the MIT-BIH Arrhythmia dataset from Physionet. The dataset was split into training, validation, and testing subsets. Our proposed design incorporates convolutional layers, max-pooling, ReLU activation functions, and dropout layers to prevent overfitting. Comparative assessment against conventional methods such as logistic regression and Support Vector Machines (SVM) shows superior performance, achieving an accuracy of 98.29%, recall of 87.60%, precision of 93.75%, and F1 score of 90.37%. The potential of deep learning to enhance the accuracy and efficiency of diagnosing CVD from ECG data is highlighted in this study, introducing a reliable tool for clinical application.

A Research of Fine-Tuning CNN-LSTM Model for Gold Price Prediction

Gold price and foreign exchange price prediction are usually regarded as serialized data with strong time correlation. It is precisely because of this feature that the performance of traditional convolutional neural networks is often not as good as that of recurrent neural networks. This paper fine-tunes the CNN-LSTM model in two ways. The first is to simplify the input data, convert the time series into binary data, and change the model task from predicting prices to predicting price fluctuations. The second is to add a dropout layer and use the dropout layer to improve the model's overfitting problem. The results demonstrate that the improved model outperforms the first model, with prediction accuracy rising from 54% to 57%. Furthermore, the refined model is not limited to processing the gold price series; it can also be applied to other time series, and when paired with other models, it could yield even better outcomes.

The analysis of art design under improved convolutional neural network based on the Internet of Things technology

This work aims to explore the application of an improved convolutional neural network (CNN) combined with Internet of Things (IoT) technology in art design education and teaching. The development of IoT technology has created new opportunities for art design education, while deep learning and improved CNN models can provide more accurate and effective tools for image processing and analysis. In order to enhance the effectiveness of art design teaching and students’ creative expression, this work proposes an improved CNN model. In model construction, it increases the number of convolutional layers and neurons, and incorporates the batch normalization layer and dropout layer to enhance feature extraction capabilities and reduce overfitting. Besides, this work creates an experimental environment using IoT technology, capturing art image samples and environmental data using cameras, sensors, and other devices. In the model application phase, image samples undergo preprocessing and are input into the CNN for feature extraction. Sensor data are concatenated with image feature vectors and input into the fully connected layers to comprehensively understand the artwork. Finally, this work trains the model using techniques such as cross-entropy loss functions and L2 regularization and adjusts hyperparameters to optimize model performance. The results indicate that the improved CNN model can effectively acquire art sample data and student creative expression data, providing accurate and timely feedback and guidance for art design education and teaching, with promising applications. This work offers new insights and methods for the development of art design education.

Crowd Counting Using Meta-Test-Time Adaptation.

Machine learning algorithms are commonly used for quickly and efficiently counting people from a crowd. Test-time adaptation methods for crowd counting adjust model parameters and employ additional data augmentation to better adapt the model to the specific conditions encountered during testing. The majority of current studies concentrate on unsupervised domain adaptation. These approaches commonly perform hundreds of epochs of training iterations, requiring a sizable number of unannotated data of every new target domain apart from annotated data of the source domain. Unlike these methods, we propose a meta-test-time adaptive crowd counting approach called CrowdTTA, which integrates the concept of test-time adaptation into the meta-learning framework and makes it easier for the counting model to adapt to the unknown test distributions. To facilitate the reliable supervision signal at the pixel level, we introduce uncertainty by inserting the dropout layer into the counting model. The uncertainty is then used to generate valuable pseudo labels, serving as effective supervisory signals for adapting the model. In the context of meta-learning, one image can be regarded as one task for crowd counting. In each iteration, our approach is a dual-level optimization process. In the inner update, we employ a self-supervised consistency loss function to optimize the model so as to simulate the parameters update process that occurs during the test phase. In the outer update, we authentically update the parameters based on the image with ground truth, improving the model's performance and making the pseudo labels more accurate in the next iteration. At test time, the input image is used for adapting the model before testing the image. In comparison to various supervised learning and domain adaptation methods, our results via extensive experiments on diverse datasets showcase the general adaptive capability of our approach across datasets with varying crowd densities and scales.

Integrated study of prediction and optimization performance of PBI-HTPEM fuel cell using deep learning, machine learning and statistical correlation

This paper uses 3D modeling and artificial intelligence methods to predict, and find optimal point in high-temperature proton exchange membrane (HTPEM) fuel cells. The main objective is to obtain maximum power and current density at the optimum node of the HTPEM fuel cell. The response surface method (RSM) is used to prevent excessive duplication and ensure adequate data coverage for determining input parameters. Also, for the first time, the correlation presented was compared with AI-based metaheuristic optimization methods i.e., including support vector regression (SVR), Gaussian process regression (GPR), and deep neural networks (DNN) with a dropout layer, alongside metaheuristic algorithms such as whale optimization algorithm (WOA), Grasshopper optimization algorithm (GOA), firefly algorithm (FF), and the genetic algorithm (GA). The results show that SVR, GPR, and DNN methods have excellent performance, with mean absolute percentage error (MAPE) of 0.81 % for DNN, 0.83 % for SVR, and 2.24 % for GPR. Most optimization algorithms exhibit errors below 8 %. The DNN-GOA, SVR-WOA, SVR-GA, and GPR-GOA algorithms have the lowest errors among them. Correlations have a lower computational cost for obtaining maximum power and current density at the optimum node compared to optimization algorithms, with a relative error of less than 6 % in most cases.

Advanced interpretable diagnosis of Alzheimer's disease using SECNN-RF framework with explainable AI.

Early detection of Alzheimer's disease (AD) is vital for effective treatment, as interventions are most successful in the disease's early stages. Combining Magnetic Resonance Imaging (MRI) with artificial intelligence (AI) offers significant potential for enhancing AD diagnosis. However, traditional AI models often lack transparency in their decision-making processes. Explainable Artificial Intelligence (XAI) is an evolving field that aims to make AI decisions understandable to humans, providing transparency and insight into AI systems. This research introduces the Squeeze-and-Excitation Convolutional Neural Network with Random Forest (SECNN-RF) framework for early AD detection using MRI scans. The SECNN-RF integrates Squeeze-and-Excitation (SE) blocks into a Convolutional Neural Network (CNN) to focus on crucial features and uses Dropout layers to prevent overfitting. It then employs a Random Forest classifier to accurately categorize the extracted features. The SECNN-RF demonstrates high accuracy (99.89%) and offers an explainable analysis, enhancing the model's interpretability. Further exploration of the SECNN framework involved substituting the Random Forest classifier with other machine learning algorithms like Decision Tree, XGBoost, Support Vector Machine, and Gradient Boosting. While all these classifiers improved model performance, Random Forest achieved the highest accuracy, followed closely by XGBoost, Gradient Boosting, Support Vector Machine, and Decision Tree which achieved lower accuracy.

An Optimized Semi-Supervised Generative Adversarial Network Rice Extraction Method Based on Time-Series Sentinel Images

In response to the limitations of meteorological conditions in global rice growing areas and the high cost of annotating samples, this paper combines the Vertical-Vertical (VV) polarization and Vertical-Horizontal (VH) polarization backscatter features extracted from Sentinel-1 synthetic aperture radar (SAR) images and the NDVI, NDWI, and NDSI spectral index features extracted from Sentinel-2 multispectral images. By leveraging the advantages of an optimized Semi-Supervised Generative Adversarial Network (optimized SSGAN) in combining supervised learning and semi-supervised learning, rice extraction can be achieved with fewer annotated image samples. Within the optimized SSGAN framework, we introduce a focal-adversarial loss function to enhance the learning process for challenging samples; the generator module employs the Deeplabv3+ architecture, utilizing a Wide-ResNet network as its backbone while incorporating dropout layers and dilated convolutions to improve the receptive field and operational efficiency. Experimental results indicate that the optimized SSGAN, particularly when utilizing a 3/4 labeled sample ratio, significantly improves rice extraction accuracy, leading to a 5.39% increase in Mean Intersection over Union (MIoU) and a 2.05% increase in Overall Accuracy (OA) compared to the highest accuracy achieved before optimization. Moreover, the integration of SAR and multispectral data results in an OA of 93.29% and an MIoU of 82.10%, surpassing the performance of single-source data. These findings provide valuable insights for the extraction of rice information in global rice-growing regions.