Abstract 184: The utility of deep metric learning for breast cancer identification on mammographic images

The increasing popularity of social media platforms has revolutionized how news and information are shared. While these social platforms facilitate rapid dissemination, they also provide fertile ground for the proliferation of rumors and unverified information. False information spreads as quickly as accurate news, often influencing public opinion and decision-making processes. Identifying rumors early is critical to limiting their potential harm and mitigating negative consequences. This study evaluates the practical application and scalability of transformer-based models, specifically GPT-2, in detecting rumors on social media platforms alongside traditional deep learning (DL) models. We explore various deep learning models such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), ALBERT, and GPT-2. Performance was assessed using standard evaluation metrics, including accuracy, precision, recall, F1-score, and analysis of Receiver Operating Characteristic (ROC) curves. The comparative results reveal that transformer-based approaches significantly outperform traditional DL models in detecting rumors with higher accuracy and reliability. Among the evaluated models, GPT-2 achieved the highest scores across all performance metrics, demonstrating exceptional capability in identifying and predicting rumor-laden content. This study introduces key innovations, including a direct comparative analysis of transformer-based and traditional DL models, highlighting GPT-2’s advanced attention mechanisms that capture nuanced linguistic and contextual features. Additionally, it underscores GPT-2’s scalability for real-world misinformation mitigation and critically examines dataset biases and adaptability challenges. Future advancements, such as multimodal approaches integrating text, images, and videos, as well as hybrid models combining transformers with traditional DL techniques, are proposed to enhance detection accuracy and efficiency. These findings underline the transformative potential of advanced AI techniques in combating misinformation on social media platforms. The research emphasizes the potential for scalable and practical implementation of GPT-2-based tools in mitigating false information dissemination, contributing to a more reliable and resilient digital ecosystem. This work advances the understanding of AI's role in mitigating the spread of false information.

Soil temperature (ST) plays an important role in agriculture and other fields, and has a close relationship with plant growth and development. Therefore, accurate ST prediction methods are widely needed. Deep learning (DL) models have been widely applied for ST prediction. However, the traditional DL models may fail to capture the spatiotemporal relationship due to its complex dependency under different related hydrologic variables. Hence, the DL models with Ensemble Empirical Mode Decomposition (EEMD) are proposed in this study. The proposed models can capture more complex spatiotemporal relationship after decomposing the ST into different intrinsic mode functions. Therefore, the performance of models is further improved. The results show that the performance of DL models with EEMD are better than that of corresponding DL models without EEMD. Moreover, EEMD-Conv3d has the best performance among all the experimental models. It has the highest R2 ranging from 0.9826 to 0.9893, the lowest RMSE ranging from 1.3096 to 1.6497 and the lowest MAE ranging from 0.9656 to 1.2056 in predicting ST at the lead time from one to five days. In addition, the lines between predicted ST and observed ST are closer to the ideal line (y = x) than other DL models. The results show that our EEMD-Conv3D can better capture spatiotemporal correlation and is an applicable method for predicting spatiotemporal ST.

Lung cancer is one of the major cancers worldwide, and rapid, accurate diagnosis is crucial for subsequent treatment and management. Currently, pathological subtype detection requires clinical experts to invest significant time and effort, making the development of automatic, efficient detection models essential. This study developed a novel deep learning model named BreezeNet for the recognition of lung adenocarcinoma, lung squamous cell carcinoma, and benign lung tissue. BreezeNet is a lightweight deep learning framework specifically designed for precise and automated diagnosis of lung adenocarcinoma, lung squamous cell carcinoma, and benign lung tissue. Compared with current mainstream deep learning models such as VGG, GoogleNet, and MobileNet, BreezeNet demonstrated superior performance in key metrics such as precision and accuracy. In our study, we developed a lightweight deep learning model named BreezeNet for the automatic classification of lung cancer cells. The experimental results show that BreezeNet performs excellently across various metrics, particularly in terms of the number of parameters. Specifically, BreezeNet achieved a precision of 0.9749, a recall of 0.9742, an F1-score of 0.9742, and an accuracy of 0.9789, which are slightly better than traditional deep learning models such as AlexNet, VGG, GoogleNet, ResNet, and MobileNet. However, the most significant advantage of BreezeNet lies in its parameter count, which is only 1,256,679, far lower than AlexNet's 14,587,587 and ResNet's 23,514,179. This means that our model is not only competitive in terms of performance but also significantly reduces the computational resource requirements, greatly enhancing the model's lightweight nature and deployment efficiency. Compared with traditional deep learning models such as AlexNet, VGG, and ResNet, BreezeNet achieves slightly better performance across all key metrics, with up to 1.6% higher accuracy, 1.76% higher F1-score, and over 18× fewer parameters, highlighting its superior lightweight design and diagnostic effectiveness. Our developed deep learning model can efficiently perform automated subtyping of lung cancer cells, providing accurate diagnostic recommendations for doctors. This will help improve the efficiency of lung cancer diagnosis, thereby enhancing patient survival rates.

In this study, we propose an interpretable deep learning radiomics (IDLR) model based on [18F]FDG PET images to diagnose the clinical spectrum of Alzheimer's disease (AD) and predict the progression from mild cognitive impairment (MCI) to AD. This multicentre study included 1962 subjects from two ethnically diverse, independent cohorts (a Caucasian cohort from ADNI and an Asian cohort merged from two hospitals in China). The IDLR model involved feature extraction, feature selection, and classification/prediction. We evaluated the IDLR model's ability to distinguish between subjects with different cognitive statuses and MCI trajectories (sMCI and pMCI) and compared results with radiomic and deep learning (DL) models. A Cox model tested the IDLR signature's predictive capability for MCI to AD progression. Correlation analyses identified critical IDLR features and verified their clinical diagnostic value. The IDLR model achieved the best classification results for subjects with different cognitive statuses as well as in those with MCI with distinct trajectories, with an accuracy of 76.51% [72.88%, 79.60%], (95% confidence interval, CI) while those of radiomic and DL models were 69.13% [66.28%, 73.12%] and 73.89% [68.99%, 77.89%], respectively. According to the Cox model, the hazard ratio (HR) of the IDLR model was 1.465 (95% CI: 1.236-1.737, p < 0.001). Moreover, three crucial IDLR features were significantly different across cognitive stages and were significantly correlated with cognitive scale scores (p < 0.01). Preliminary results demonstrated that the IDLR model based on [18F]FDG PET images enhanced accuracy in diagnosing the clinical spectrum of AD. Question The study addresses the lack of interpretability in existing DL classification models for diagnosing the AD spectrum. Findings The proposed interpretable DL radiomics model, using radiomics-supervised DL features, enhances interpretability from traditional DL models and improves classification accuracy. Clinical relevance The IDLR model interprets DL features through radiomics supervision, potentially advancing the application of DL in clinical classification tasks.

Recently, a large near‐infrared spectroscopy data set for mango fruit quality assessment was made available online. Based on that data, a deep learning (DL) model outperformed all major chemometrics and machine learning approaches. However, in earlier studies, the model validation was limited to the test set from the same data set which was measured with the same instrument on samples from a similar origin. From a DL perspective, once a model is trained it is expected to generalise well when applied to a new batch of data. Hence, this study aims to validate the generalisability performance of the earlier developed DL model related to DM prediction in mango on a different test set measured in a local laboratory setting, with a different instrument. At first, the performance of the old DL model was presented. Later, a new DL model was crafted to cover the seasonal variability related to fruit harvest season. Finally, a DL model transfer method was performed to use the model on a new instrument. The direct application of the old DL model led to a higher error compared to the PLS model. However, the performance of the DL model was improved drastically when it was tuned to cover the seasonal variability. The updated DL model performed the best compared to the implementation of a new PLS model or updating the existing PLS model. A final root‐mean‐square error prediction (RMSEP) of 0.518% was reached. This result supports that, in the availability of large data sets, DL modelling can outperform chemometrics approaches.

Forecasting the risk factor of the financial frontier markets has always been a very challenging task. Unlike an emerging market, a frontier market has a missing parameter named “volatility”, which indicates the market’s risk and as a result of the absence of this missing parameter and the lack of proper prediction, it has almost become difficult for direct customers to invest money in frontier markets. However, the noises, seasonality, random spikes and trends of the time-series datasets make it even more complicated to predict stock prices with high accuracy. In this work, we have developed a novel stacking ensemble of the neural network model that performs best on multiple data patterns. We have compared our model’s performance with the performance results obtained by using some traditional machine learning ensemble models such as Random Forest, AdaBoost, Gradient Boosting Machine and Stacking Ensemble, along with some traditional deep learning models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term (BiLSTM). We have calculated the missing parameter named “volatility” using stock price (Close price) for 20 different companies of the frontier market and then made predictions using the aforementioned machine learning ensemble models, deep learning models and our proposed stacking ensemble of the neural network model. The statistical evaluation metrics RMSE and MAE have been used to evaluate the performance of the models. It has been found that our proposed stacking ensemble neural network model outperforms all other traditional machine learning and deep learning models which have been used for comparison in this paper. The lowest RMSE and MAE values we have received using our proposed model are 0.3626 and 0.3682 percent, respectively, and the highest RMSE and MAE values are 2.5696 and 2.444 percent, respectively. The traditional ensemble learning models give the highest RMSE and MAE error rate of 20.4852 and 20.4260 percent, while the deep learning models give 15.2332 and 15.1668 percent, respectively, which clearly states that our proposed model provides a very low error value compared with the traditional models.

The electrocardiogram (ECG) is a principal signal employed to automatically diagnose cardiovascular disease in shallow and deep learning models. However, ECG feature extraction is required and this may reduce diagnosis accuracy in traditional shallow learning models, while backward propagation (BP) algorithm used by the traditional deep learning models has the disadvantages of local minimization and slow convergence rate. To solve these problems, a new deep learning algorithm called deep kernel extreme learning machine (DKELM) is proposed by combining the extreme learning machine auto-encoder (ELM-AE) and kernel ELM (KELM). In the new DKELM architecture with [Formula: see text] hidden layers, ELM-AEs are employed by the front [Formula: see text] hidden layers for feature extraction in the unsupervised learning process, which can effectively extract abstract features from the original ECG signal. To overcome the “dimension disaster” problem, the kernel function is introduced into ELM to act as classifier by the [Formula: see text]th hidden layer in the supervised learning process. The experiments demonstrate that DKELM outperforms the BP neural network, support vector machine (SVM), extreme learning machine (ELM), deep auto-encoder (DAE), deep belief network (DBN) in classification accuracy. Though the accuracy of convolutional neural network (CNN) is almost the same as DKELM, the computing time of CNN is much longer than DKELM.

The need for intubation in methanol-poisoned patients, if not predicted in time, can lead to irreparable complications and even death. Artificial intelligence (AI) techniques like machine learning (ML) and deep learning (DL) greatly aid in accurately predicting intubation needs for methanol-poisoned patients. So, our study aims to assess Explainable Artificial Intelligence (XAI) for predicting intubation necessity in methanol-poisoned patients, comparing deep learning and machine learning models. This study analyzed a dataset of 897 patient records from Loghman Hakim Hospital in Tehran, Iran, encompassing cases of methanol poisoning, including those requiring intubation (202 cases) and those not requiring it (695 cases). Eight established ML (SVM, XGB, DT, RF) and DL (DNN, FNN, LSTM, CNN) models were used. Techniques such as tenfold cross-validation and hyperparameter tuning were applied to prevent overfitting. The study also focused on interpretability through SHAP and LIME methods. Model performance was evaluated based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior performance in accuracy (94.0%), sensitivity (99.0%), specificity (94.0%), and F1-score (97.0%). CNN led in ROC with 78.0%. For ML models, RF excelled in accuracy (97.0%) and specificity (100%), followed by XGB with sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%). Overall, RF and XGB outperformed other models, with accuracy (97.0%) and specificity (100%) for RF, and sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%) for XGB. ML models surpassed DL models across all metrics, with accuracies from 93.0% to 97.0% for DL and 93.0% to 99.0% for ML. Sensitivities ranged from 98.0% to 99.37% for DL and 93.0% to 99.0% for ML. DL models achieved specificities from 78.0% to 94.0%, while ML models ranged from 93.0% to 100%. F1-scores for DL were between 93.0% and 97.0%, and for ML between 96.0% and 98.27%. DL models scored ROC between 68.0% and 78.0%, while ML models ranged from 84.0% to 96.08%. Key features for predicting intubation necessity include GCS at admission, ICU admission, age, longer folic acid therapy duration, elevated BUN and AST levels, VBG_HCO3 at initial record, and hemodialysis presence. This study as the showcases XAI's effectiveness in predicting intubation necessity in methanol-poisoned patients. ML models, particularly RF and XGB, outperform DL counterparts, underscoring their potential for clinical decision-making.

Deep learning and machine learning in CT-based COPD diagnosis: Systematic review and meta-analysis.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

In this study, music mood classification is explored using advanced deep learning and transformer-based models to accurately predict the emotional content of music. Music plays a crucial role in human life, influencing emotions, behaviors, and mental states. Accurately classifying the mood of music is essential for applications such as music recommendation systems, emotional intelligence in AI, and mental health monitoring. With the growing impact of Artificial Intelligence (AI) in emotion recognition, sentiment analysis has become a vital research area, contributing to fields like social media monitoring, customer experience analysis, and personalized content delivery. We employ a state-of-the-art transformer-based model (HuBERT) in comparison with deep learning models (ConvFormer, LSTM) and pre-trained models (YAMNet) to evaluate their effectiveness in music mood classification. The study is conducted on a publicly available dataset containing five mood labels such as Aggressive, Happy, Dramatic, Sad, and Romantic with 500 audio files per category. To analyze and extract meaningful patterns from the dataset, advanced different five audio features such as Short-Time Fourier Transform (STFT), and Mel-Frequency Cepstral Coefficients (MFCC) are utilized. To ensure robust model evaluation, an 80-20 holdout split is applied. Our experimental results indicate that HuBERT achieves the highest classification accuracy of 95%, outperforming both traditional deep learning models and pre-trained architecture. This study provides a comprehensive evaluation of machine learning approaches for music mood classification, demonstrating the potential of transformer-based models in enhancing AI-driven sentiment analysis. The findings contribute to the development of intelligent music recommendation systems, emotional AI applications, and advancements in affective computing.

Text similarity calculation based on deep learning has always been an important research in the field of natural language processing. However, the traditional deep learning model has some disadvantages in the application of text similarity calculation, Text similarity calculation based on deep learning has always been an important research in the field of natural language processing. However, traditional deep learning models have drawbacks in the application of text similarity calculation, such as insufficient extraction of text semantics, inability to combine context, and inability to Understand polysemy and so on. In order to solve the problems of existing text similarity calculation methods based on deep learning, this paper proposes a Siamese network based on ALBERT, uses ALBERT model for word embedding, and proposed the ABSBGRU model by combining Bi-GRU of Siamese structure with attention mechanism. On the premise of minimizing the increased computational cost, we can extract the deep semantic information better. The experimental results show that ABSBGRU model has stronger deep semantic extraction ability. Compared with other traditional models, F1 Score is higher and training cost less than some other models.

Improving entity recognition using ensembles of deep learning and fine-tuned large language models: A case study on adverse event extraction from VAERS and social media.

BinDeep: A deep learning approach to binary code similarity detection

Due to the scalability of deep learning technology, researchers have applied it to the non-destructive testing of peach internal quality. In addition, the soluble solids content (SSC) is an important internal quality indicator that determines the quality of peaches. Peaches with high SSC have a sweeter taste and better texture, making them popular in the market. Therefore, SSC is an important indicator for measuring peach internal quality and making harvesting decisions. This article presents the High Order Spatial Interaction Network (HOSINet), which combines the Position Attention Module (PAM) and Channel Attention Module (CAM). Additionally, a feature wavelength selection algorithm similar to the Group-based Clustering Subspace Representation (GCSR-C) is used to establish the Position and Channel Attention Module-High Order Spatial Interaction (PC-HOSI) model for peach SSC prediction. The accuracy of this model is compared with traditional machine learning and traditional deep learning models. Finally, the permutation algorithm is combined with deep learning models to visually evaluate the importance of feature wavelengths. Increasing the order of the PC-HOSI model enhances its ability to learn spatial correlations in the dataset, thus improving its predictive performance. The optimal model, PC-HOSI model, performed well with an order of 3 (PC-HOSI-3), with a root mean square error of 0.421 °Brix and a coefficient of determination of 0.864. Compared with traditional machine learning and deep learning algorithms, the coefficient of determination for the prediction set was improved by 0.07 and 0.39, respectively. The permutation algorithm also provided interpretability analysis for the predictions of the deep learning model, offering insights into the importance of spectral bands. These results contribute to the accurate prediction of SSC in peaches and support research on interpretability of neural network models for prediction. © 2024 Society of Chemical Industry.