Decoding Cardio-Respiratory Acoustic Patterns via Multi-Dimensional Deep Representation Learning for Clinical Insight

Commonly observed challenges in water quality anomaly detection using Machine Learning (ML) classifiers include unbalanced class distribution and missing data. Classifiers trained on such imbalanced datasets often exhibit biased accuracy, favoring the majority class and neglecting the minority class, while incomplete datasets limit the applicability of more complex models and hinder thorough analysis. This research addresses the handling of incomplete data and class imbalance by proposing a robust framework for an ML-based water quality anomaly detection system using several resampling techniques. A comparative study was conducted on six imputation methods for missing data, including Expectation Maximization (EM) and Multiple Imputation by Chained Equations (MICE), alongside three resampling techniques: Random Under Sampling (RUS), Rapidly Converging Gibbs (RACOG) sampler, and RACOG combined with RUS (RACOG-RUS). These methods were evaluated across three classifiers: Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Naïve Bayes (NB). The models were assessed using stratified 5-fold cross-validation and evaluated based on accuracy, Receiver Operating Characteristic Area Under Curve (ROC-AUC), and F1-score. Further experiments incorporated feature selection methods such as Boruta and Mean Decrease Accuracy (MDA) to optimize performance. Results demonstrate that RF combined with RACOG-RUS and EM achieved the highest F1-score of 0.9954, effectively addressing both class imbalance and missing data. Additionally, computational analysis highlights the efficiency of RF when optimized with appropriate hyperparameters.

This study was aimed to assess if combining the evaluation of blood glucose level (BGL) and the Triage Revised Trauma Score (T-RTS) may result in a more accurate prediction of the actual clinical outcome, both in general adult population and in elderly patients with trauma. This is a retrospective cohort study, conducted in the emergency department (ED) of an urban teaching hospital, with an average ED admission rate of 75,000 patients per year. Those excluded: known diagnosis of diabetes, age <18 years old, pregnancy, and mild trauma (classified as isolate trauma of upper or lower limb, in absence of exposed fractures). A combined Revised Trauma Score Glucose (RTS-G) score was obtained adding to T-RTS: two for BGL <160mg/dL (8.9mmol/L); one for BGL ≥160mg/dL and < 200mg/dL (11.1mmol/L); and zero for BGL ≥ 200mg/dL. The primary outcome was a composite of patient's death in ED or admission to intensive care unit (ICU). Receiver Operating Characteristic (ROC) curve analysis was used to evaluate the overall performance of T-RTS and of the combined RTS-G score. Among a total of 68,933 traumas, 9,436 patients (4,407 females) were enrolled, aged from 18 to 103 years; 4,288 were aged ≥65 years. A total of 577 (6.1%) met the primary endpoint: 38 patients died in ED (0.4%) and 539 patients were admitted to ICU. The T-RTS and BGL were independently associated to primary endpoint at multivariate analysis. The cumulative RTS-G score was significantly more accurate than T-RTS and reached the best accuracy in elderly patients. In general population, ROC area under curve (AUC) for T-RTS was 0.671 (95% CI, 0.661 - 0.680) compared to RTS-G ROC AUC 0.743 (95% CI, 0.734 - 0.752); P <.001. In patients ≥65 years, T-RTS ROC AUC was 0.671 (95% CI, 0.657 - 0.685) compared to RTS-G ROC AUC 0.780 (95% CI, 0.768 - 0.793); P <.001. Results showed RTS-G could be used effectively at ED triage for the risk stratification for death in ED and ICU admission of trauma patients, and it could reduce under-triage of approximately 20% compared to T-RTS. Comparing ROC AUCs, the combined RTS-G score performs significantly better than T-RTS and gives best results in patients ≥65 years.

We have previously developed a model-based method to compensate for the crosstalk in simultaneous acquisition of Tc-99m stress and Tl-201 rest myocardial perfusion SPECT. The purpose of this study is to evaluate the performance of this method in terms of a defect detection task using a mathematical Channelized Hoteling Observer (CHO) study. In this study we also optimized the iteration number in reconstruction of Tl distributions. A population of male and female NCAT phantoms were used to realistically model variation in patients. Both defect-free and defect-present data of Tc and Tl were simulated using the SimSET/PHG codes and our newly developed and validated angular response function (ARF) method to mimic simultaneous acquisition and separate acquisition. Poisson noise was modeled at clinically realistic levels. The Tl data were reconstructed using filtered backprojection (FBP) and ordered subset expectation maximization (OSEM) algorithms for up to 20 iterations with and without the model-based crosstalk compensation (MBC). CHO methodology and receiver operating characteristic (ROC) analysis were applied to short axis Tl images to obtain ROC curves and area under ROC curves (AUC). The AUC values were compared with those from separately acquired data reconstructed using FBP and OSEM algorithms. The results show that a relatively small number of iteration (/spl sim/3) is optimal for the postreconstruction filtering cutoff frequency of 0.16 pixel/sup -1/ used in this study. Also, the AUC values obtained with the MBC were significantly better than those without crosstalk compensation and those with the FBP reconstruction method applied to the separately acquired data.

The performance of seven classification methods, binary logistic (BLR), probit (PR) and cumulative probit (CPR) regression, linear (LDA) and quadratic (QDA) discriminant analysis, artificial neural networks (ANN), and naïve Bayes classification (NBC), is examined in skeletal sex estimation. These methods were tested using cranial and pelvic sexually dimorphic traits recorded on a modern documented collection, the Athens Collection. For their implementation, an R package has been written to perform cross-validated (CV) sex classification and give the discriminant function of each of the methods studied. A simple algorithm that combines two discriminant functions is also proposed. It was found that the differences in the classification performance between BLR, PR, CPR, LDA, QDA, ANN, and NBC are overall small. However, LDA is simpler and more flexible than CPR, QDA, and ANN and has a small but clear advantage over BLR, NBC, and PR. Consequently, LDA may be preferred in skeletal sex estimation. Finally, it is striking that the combination of pelvic and cranial traits via their discriminant functions, determined either by BLR or LDA, removes practically any population-specificity and yields much better predictions than the individual functions; in fact, the prediction accuracy increases above 97%.

Multimodal fusion: A study on speech-text emotion recognition with the integration of deep learning

Development without any defect is unsubstantial. Timely detection of software defects favors the proper resource utilization saving time, effort and money. With the increasing size and complexity of software, demand for accurate and efficient prediction models is increasing. Recently, search-based techniques (SBTs) have fascinated many researchers for Software Defect Prediction (SDP). The goal of this study is to conduct an empirical evaluation to assess the applicability of SBTs for predicting software defects in object-oriented (OO) softwares. In this study, 16 SBTs are exploited to build defect prediction models for 13 OO software projects. Stable performance measures — GMean, Balance and Receiver Operating Characteristic-Area Under Curve (ROC-AUC) are employed to probe into the predictive capability of developed models, taking into consideration the imbalanced nature of software datasets. Proper measures are taken to handle the stochastic behavior of SBTs. The significance of results is statistically validated using the Friedman test complied with Wilcoxon post hoc analysis. The results confirm that software defects can be detected in the early phases of software development with help of SBTs. This paper identifies the effective subset of SBTs that will aid software practitioners to timely detect the probable software defects, therefore, saving resources and bringing up good quality softwares. Eight SBTs — sUpervised Classification System (UCS), Bioinformatics-oriented hierarchical evolutionary learning (BIOHEL), CHC, Genetic Algorithm-based Classifier System with Adaptive Discretization Intervals (GA_ADI), Genetic Algorithm-based Classifier System with Intervalar Rule (GA_INT), Memetic Pittsburgh Learning Classifier System (MPLCS), Population-Based Incremental Learning (PBIL) and Steady-State Genetic Algorithm for Instance Selection (SGA) are found to be statistically good defect predictors.

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

Sentiment Analysis of Self Driving Car Dataset: A comparative study of Deep Learning approaches

In this paper the permutation entropy (PE) obtained from heart rate variability (HRV) is analyzed in a statistical model. In this model we also integrate other feature extraction techniques, the cepstrum coefficients derived from the same HRV and a set of band powers obtained from the electrocardiogram derived respiratory (EDR) signal. The aim of the model is detecting obstructive sleep apnea (OSA) events. For this purpose, we apply two statistical classification methods: Logistic Regression (LR) and Quadratic Discriminant Analysis (QDA). For testing the models we use seventy ECG recordings from the Physionet database which are divided into equal-size learning and testing sets. Both sets consist of 35 recordings, each containing a single ECG signal. In our experiments we have found that the features extracted from the EDR signal present a sensitivity of 65.6% and specificity of 87.7% (auc = 85) in the LR classifier, and sensitivity of 59.4% and specificity of 90.3% (auc = 83.9) in the QDA classifier. The HRV-based cepstrum coefficients present a sensitivity of 63.8% and specificity of 89.2% (auc = 86) in the LR classifier, and sensitivity of 67.2% and specificity of 86.8% (auc = 86.9) in the QDA. Subsequent tests show that the contribution of the permutation entropy increases the performance of the classifiers, implying that the complexity of RR interval time series play an important role in the breathing pauses detection. Particularly, when all features are jointly used, the quantification task reaches a sensitivity of 71.9% and specificity of 92.1% (auc = 90.3) for LR. Similarly, for QDA the sensitivity is 75.1% and the specificity is 90.5% (auc = 91.7).

The most common type of pancreatic cancer is pancreatic ductal adenocarcinoma (PDAC), which accounts for the vast majority of pancreatic cancers. The five-year survival rate for PDAC due to late diagnosis is 9%. Early diagnosed PDAC patients survive longer than patients diagnosed at a more advanced stage. Biomarkers can play an essential role in the early detection of PDAC to assist the health professional. Machine learning and deep learning methods are used with biomarkers obtained in recent studies for diagnostic purposes. In order to increase the survival rates of PDAC patients, early diagnosis of the disease with a noninvasive test is a critical need. Our study offers a promising approach for the early detection of PDAC with noninvasive urinary biomarkers and carbohydrate antigen 19-9 (CA19-9). The Kaggle Urinary Biomarkers for Pancreatic Cancer (2020) open-access dataset consisting of 590 participants was used in this study. Seven machine learning classifiers (support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (kNN), random forest (RF), light gradient boosting machine (LightGBM), AdaBoost, and gradient boosting classifier (GBC)) to detect PDAC disease classifier were used. Binary and multiple classification processes were carried out. Data was validated in our study using 5-10-fold crossvalidation. This study aimed to determine the best machine learning model by analyzing the performance of machine learning models in determining the classes of healthy controls, pancreatic disorders, and patients with PDAC. It is a remarkable finding that ensemble learning models were more successful in all our groups. The most successful classification method in classifying healthy controls and patients with PDAC was CV-10, while the GBC (92.99%) model was (AUC = 0.9761). The most successful classification method in classifying patients with pancreatic disorders and PDAC was CV-10, while the LightGBM (86.37%) model was (AUC = 0.9348). In the classification of healthy controls, pancreatic disorders, and patients with PDAC, the most successful classification method was CV-5, while the GBC (72.91%) model was (AUC = 0.8733).

Multi-label bird species classification from audio recordings using attention framework

The aim of this paper is to classify both (left and right) hand motor imagery (MI) tasks using event-related (de) synchronization (ERD/ERS) patterns based on the inter trial variance (IV). In this work, publicly available online BCI-2003 competition data set was used which contains MI based Electroencephalography (EEG) data of a single subject. The raw MI based EEG signals were extracted from C3 and C4 channels and band pass filtered to mu (8–12 Hz) frequency band. The mean, inter trial variance and ERD/ERS patterns were calculated in both the channels for both MI tasks of the subject. The patterns were used as feature vector and input to the different machine learning classifiers. The logistic regression and Naive Bayesian classifiers were used for the classification of both MI tasks of the subject. For logistic regression classifier, the accuracy, precision and sensitivity were found to be 92.40%, 92.00% and 92.00%, respectively. Meanwhile, 92.19% accuracy, 92.00% precision and 92.00% sensitivity were obtained for the Naive Bayesian classifier. The logistic regression classifier provides maximum classification accuracy (92.40%) in comparison with the existing methods (87.90–90.20%). Result shows that, the proposed method can quantify ERD/ERS patterns effectively in both the channels and also classifies both MI tasks of the subject successfully.