Ensemble of Multimodal Deep Learning Models for Violin Bowing Techniques Classification

The accuracy of shear wave elastography for non-invasive assessment of renal fibrosis (RF) in chronic kidney disease (CKD) needs further improvement. We developed a tool using an ensemble deep learning model (EDLM) that can accurately assess RF in CKD patients based solely on two-dimensional shear wave elastography (2D-SWE) images. Retrospective data were collected from CKD patients between April 2019 and October 2024, along with renal 2D-SWE images obtained before biopsy. Pathological evaluation was the reference standard of RF. All patients were randomly divided into training, validation, and test sets in a 7:1:2 ratio. An EDLM integrating three convolutional neural networks (ResNet18, DenseNet121, and EfficientNet-b7) through a voting strategy at the output level was developed and validated using 2D-SWE images. The diagnostic performance of the EDLM was compared with that of radiologists. A total of 286 CKD patients (mean age ± standard deviation: 41.86 ± 14.94, males: 162) and 858 2D-SWE images (mild RF: 405, moderate-severe RF: 453) were included. In the test set, EDLM achieved an accuracy of 93.0% (95% CI: 88.1, 95.9), negative predictive value of 89.6% (95% CI: 81.5, 94.5), positive predictive value of 96.4% (95% CI: 90.0, 98.8), specificity of 96.3% (95% CI: 89.7, 98.7), and sensitivity of 90.0% (95% CI: 82.1, 94.7). The area under the receiver operating characteristic curves of the EDLM was 0.989, surpassing experienced radiologist by 0.186 (P < 0.001) and less experienced radiologist by 0.279 (P < 0.001). EDLM based on 2D-SWE images significantly improved the diagnostic performance of RF in CKD. The EDLM was expected to be a potential tool for accurately non-invasive assessment of RF in CKD.

Radiologists often face challenges in differentiating benign from malignant sacral bone lesions due to their similar imaging characteristics. This study aimed to develop an ensemble deep learning (DL) model that can preoperatively distinguish between benign and malignant sacral tumors using noncontrast computed tomography images. Preoperative sacral CT scans from 569 patients with confirmed sacral lesions were analyzed. Data from Center 1 were utilized in model development and internal test via fivefold cross-validation, and those from Centers 2 and 3 were employed in external test. Various ensemble models combining human-readable interpretation and DL were developed. The diagnostic performance of the models and radiologists was assessed using metrics such as precision, recall, accuracy, area under the curve (AUC), F1 score, and confusion matrix. Furthermore, the clinical benefits derived from radiologists' interpretations and supported by the DL model were evaluated. The ensemble model, which integrates 3D-DenseNet121 with human interpretation, exhibited the most robust performance. The ensemble model demonstrated high performance on the internal and external test sets and achieved AUCs of 0.9139 and 0.8713, F1 scores of 0.9054 and 0.8571, precision of 0.9041 and 0.8824, recall of 0.9136 and 0.8333, and accuracy of 0.8630 and 0.8182, respectively. Across the external test cohort, all radiologists experienced improvements in AUC, accuracy, sensitivity, and specificity. Notably, junior radiologists demonstrated significant improvements compared with senior radiologists. The potential clinical application of the DL model lies in its capacity to considerably enhance the diagnostic efficiency of radiologists. This study presents the first ensemble deep learning model integrating 3D-DenseNet121 with radiologists' interpretation for preoperative differentiation of sacral tumors on noncontrast CT that improved diagnostic performance across all experience levels, particularly for junior radiologists. First artificial intelligence-radiologist ensemble for noncontrast computed tomography (NCCT)-based sacral tumor classification. Boosts all radiologists' performance, with the greatest gains for juniors, potentially reducing referrals. Enables reliable NCCT diagnosis, overcoming contrast/magnetic resonance imaging dependency in musculoskeletal oncology.

Churn prediction has become one of the core concepts in customer relationship management within the insurances, telecom, and internet service provider industries, which is essential in customer retention. Therefore, this study attempts to analyze the effectiveness of the advanced machine learning and deep learning models for churn prediction in the evaluation of the models’ performance across different sectors. This would help conclude whether the varied patterns of the churn throughout different sectors to the level that affects the model performance and to what extent. The work includes three datasets: namely, insurance churn, internet service provider customer churn, and Telecom churn datasets. The implementation and comparison conducted in this study of models include XGBoost, Convolutional Neural Networks (CNNs), and Ensemble Deep Learning with the pre-trained hybrid approach. The results show that the ensemble deep learning model outperforms other models in terms of accuracy and F1-score, achieving accuracies of up to 95.96% in the insurance churn dataset and of 98.42% in the telecom churn dataset. Moreover, traditional machine learning models like XGBoost also produced competitive results for selected datasets. The proposed deep learning ensembles reveal the strength and possibility for churn prediction and provide a benchmark for future research relevant to customer retention strategies. Also, the proposed ensemble deep learning model shows stable performance across different sectors, which reflects its ability to capture the varied churn patterns of different sectors.

Analyzing the condition and function of the heart is very important because cardiovascular diseases (CVDs) are responsible for high mortality rates worldwide and can lead to strokes and heart attacks; thus, early diagnosis and treatment are important. Phonocardiogram (PCG) signals can be used to analyze heart rate characteristics to detect heart health and detect heart-related diseases. In this paper, we propose a method for designing using wavelet analysis techniques and an ensemble of deep learning models from phonocardiogram (PCG) for heart sound classification. For this purpose, we use wavelet scattering transform (WST) and continuous wavelet transform (CWT) as the wavelet analysis approaches for 1D-convolutional neural network (CNN) and 2D-CNN modeling, respectively. These features are insensitive to translations of the input on an invariance scale and are continuous with respect to deformations. Furthermore, the ensemble model is combined with 1D-CNN and 2D-CNN. The proposed method consists of four stages: a preprocessing stage for dividing signals at regular intervals, a feature extraction stage through wavelet scattering transform (WST) and continuous wavelet transform (CWT), a design stage of individual 1D-CNN and 2D-CNN, and a classification stage of heart sound by the ensemble model. The datasets used for the experiment were the PhysioNet/CinC 2016 challenge dataset and the PASCAL classifying heart sounds challenge dataset. The performance evaluation is performed by precision, recall, F1-score, sensitivity, and specificity. The experimental results revealed that the proposed method showed good performance on two datasets in comparison to the previous methods. The ensemble method of the proposed deep learning model surpasses the performance of recent studies and is suitable for predicting and diagnosing heart-related diseases by classifying heart sounds through phonocardiogram (PCG) signals.

Intention recognition in Human–Robot Interaction (HRI) is critical for enabling robots to anticipate and respond to human actions effectively. This study explores the application of deep learning techniques for the classification of human intentions in HRI, utilizing data collected from Virtual Reality (VR) environments. By leveraging VR, a controlled and immersive space is created, where human behaviors can be closely monitored and recorded. Ensemble deep learning models, particularly Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformers, are trained on this rich dataset to recognize and predict human intentions with high accuracy. While CNN and CNN-LSTM models yielded high accuracy rates, they encountered difficulties in accurately identifying certain intentions (e.g., standing and walking). In contrast, the CNN-Transformer model outshone its counterparts, achieving near-perfect precision, recall, and F1-scores. The proposed approach demonstrates the potential for enhancing HRI by providing robots with the ability to anticipate and act on human intentions in real time, leading to more intuitive and effective collaboration between humans and robots. Experimental results highlight the effectiveness of VR as a data collection tool and the promise of deep learning in advancing intention recognition in HRI.

Document classification is a prevalent task in Natural Language Processing (NLP), which has an extensive range of applications in the biomedical domains such as biomedical literature indexing, automatic diagnosis codes assignment, tweets classification for public health topics, and patient safety reports classification. Nevertheless, manual classification of biomedical articles published every year into specific predefined categories becomes a cumbersome task. Hence, building an automatic document classification for biomedical databases emerges as a significant task among the scientific community. In recent years, Deep Learning (DL) models like Deep Neural Networks (DNN), Convolution Neural Networks (CNN), Recurrent Neural Networks (RNN), and Ensemble Deep Learning models are widely used in the area of text document classification for better classification performance compared to Machine Learning (ML) algorithms. The major advantage of using DL models in document classification is that it provides rich semantic and grammatical information for document representation through pre-trained word embedding. Hence, this paper investigates the deployment of the various state-of-the-art DL based classification models in automatic classification of benchmark biomedical datasets. Finally, the performance of all the aforementioned constitutional classifiers is compared and evaluated through the well-defined performance evaluation metrics such as accuracy, precision, recall, and f1-measure.

Background: Breast cancer is one of the leading causes of death in women, making early detection through mammography crucial for improving survival rates. However, human interpretation of mammograms is often prone to diagnostic errors. This study addresses the challenge of improving the accuracy of breast cancer detection by leveraging advanced machine learning techniques. Methods: We propose an extended ensemble deep learning model that integrates three state-of-the-art convolutional neural network (CNN) architectures: VGG16, DenseNet121, and InceptionV3. The model utilizes multi-scale feature extraction to enhance the detection of both benign and malignant masses in mammograms. This ensemble approach is evaluated on two benchmark datasets: INbreast and CBIS-DDSM. Results: The proposed ensemble model achieved significant performance improvements. On the INbreast dataset, the ensemble model attained an accuracy of 90.1%, recall of 88.3%, and an F1-score of 89.1%. For the CBIS-DDSM dataset, the model reached 89.5% accuracy and 90.2% specificity. The ensemble method outperformed each individual CNN model, reducing both false positives and false negatives, thereby providing more reliable diagnostic results. Conclusions: The ensemble deep learning model demonstrated strong potential as a decision support tool for radiologists, offering more accurate and earlier detection of breast cancer. By leveraging the complementary strengths of multiple CNN architectures, this approach can improve clinical decision making and enhance the accessibility of high-quality breast cancer screening.

Chronic kidney disease (CKD) involves numerous variables, but only a few significantly impact the classification task. The statistically equivalent signature (SES) method, inspired by constraint-based learning of Bayesian networks, is employed to identify essential features in CKD. Unlike conventional feature selection methods, which typically focus on a single set of features with the highest predictive potential, the SES method can identify multiple predictive feature subsets with similar performance. However, most feature selection (FS) classifiers perform suboptimally with strongly correlated data. The FS approach faces challenges in identifying crucial features and selecting the most effective classifier, particularly in high-dimensional data. This study proposes using the Least Absolute Shrinkage and Selection Operator (LASSO) in conjunction with the SES method for feature selection in CKD identification. Following this, an ensemble deep-learning model combining long short-term memory (LSTM) and gated recurrent unit (GRU) networks is proposed for CKD classification. The features selected by the hybrid feature selection method are fed into the ensemble deep-learning model. The model’s performance is evaluated using accuracy, precision, recall, and F1 score metrics. The experimental results are compared with individual classifiers, including decision tree (DT), Random Forest (RF), logistic regression (LR), and support vector machine (SVM). The findings indicate a 2% improvement in classification accuracy when using the proposed hybrid feature selection method combined with the LSTM and GRU ensemble deep-learning model. Further analysis reveals that certain features, such as HEMO, POT, bacteria, and coronary artery disease, contribute minimally to the classification task. Future research could explore additional feature selection methods, including dynamic feature selection that adapts to evolving datasets and incorporates clinical knowledge to enhance CKD classification accuracy further.

This paper introduces ensemble deep learning (EDL) models for accurate demodulation of Fiber Bragg Grating (FBG) sensor spectra, with input training data enhanced through the numerical square method (NSM) technique. The technique combines numerical squaring with an EDL to improve prediction accuracy in noisy and overlapping spectral conditions. The proposed system uses an FBG interrogator with sensors embedded in transparent liquid containers to detect liquid level changes via Bragg wavelength shifts. However, changes in the liquid level shift the float position, causing overlap or cross-talk between adjacent sensors. To address this, the NSM enhances signal clarity by boosting authentic FBG responses and minimizing noise. Single, double, and triple NSM operations are applied to the experimental data to sharpen the reflection peaks and enhance overall signal quality, ensuring the data are well-prepared for training the EDL model. The EDL model combines CNNs for spectral feature extraction and LSTMs and GRUs for sequential pattern recognition and efficient learning, effectively capturing both spectral and sequential features. The EDL model is trained on the dataset enhanced by the NSM technique and validated using unseen experimental data to evaluate its performance. The results confirm that NSM efficiently sharpens reflection peaks, improves signal clarity, and reduces noise in FBG spectra, while the EDL model effectively demodulates the overlapping spectra. Experimental results demonstrate that the integrated NSM-EDL approach outperforms traditional machine learning and standalone deep learning models in terms of prediction accuracy, minimal errors, and computational time. The proposed method is cost-effective, hardware-efficient, and ideal for real-time multiplexed FBG sensing applications, such as liquid level monitoring.

Identification of difficult to intubate patients from frontal face images using an ensemble of deep learning models.

An ensemble deep learning model for exhaust emissions prediction of heavy oil-fired boiler combustion

Sign language (SL) is the linguistics of speech and hearing-impaired individuals. The hand gesture is the primary model employed in SL by speech and hearing-challenged people to talk with themselves and ordinary persons. At present, hand gesture detection plays a vital part, and it is commonly employed in numerous applications worldwide. Hand gesture detection systems can aid in transmission between machines and humans by aiding these sets of people. Machine learning (ML) is a subdivision of artificial intelligence (AI), which concentrates on the growth of a method. The main challenge in hand gesture detection is that machines do not directly understand human language. A standard medium is required to facilitate communication between humans and machines. Hand gesture recognition (GR) serves as this medium, enabling commands for computer interaction that specifically benefit hearing-impaired and elderly individuals. This study proposes a Gesture Recognition for Hearing Impaired People Using an Ensemble of Deep Learning Models with Improving Beluga Whale Optimization (GRHIP-EDLIBWO) model. The main intention of the GRHIP-EDLIBWO model framework for GR is to assist as a valuable tool for developing accessible communication systems for hearing-impaired individuals. To accomplish that, the GRHIP-EDLIBWO method initially performs image preprocessing using a Sobel filter (SF) to enhance edge detection and extract critical gesture features. For the feature extraction process, the squeeze-and-excitation capsule network (SE-CapsNet) effectively captures spatial hierarchies and complex relationships within gesture patterns. In addition, an ensemble of classification processes, such as bidirectional gated recurrent unit (BiGRU), Variational Autoencoder (VAE), and bidirectional long short-term memory (BiLSTM) technique, is employed. Finally, the improved beluga whale optimization (IBWO) method is implemented for the hyperparameter tuning of the three ensemble models. To achieve a robust classification result with the GRHIP-EDLIBWO approach, extensive simulations are conducted on an Indian SL (ISL) dataset. The performance validation of the GRHIP-EDLIBWO approach portrayed a superior accuracy value of 98.72% over existing models.

The potential of generalized deep learning models developed for crop water estimation was examined in the current study. This study was conducted in a semiarid region of India, i.e., Karnataka, with daily climatic data (maximum and minimum air temperatures, maximum and minimum relative humidity, wind speed, sunshine hours, and rainfall) of 44 years (1976–2020) for twelve locations. The Extreme Gradient Boosting (XGBoost), Gradient Boosting (GB), and Random Forest (RF) are three ensemble deep learning models that were developed using all of the climatic data from a single location (Bengaluru) from January 1976 to December 2017 and then immediately applied at eleven different locations (Ballari, Chikmaglur, Chitradurga, Devnagiri, Dharwad, Gadag, Haveri, Koppal, Mandya, Shivmoga, and Tumkuru) without the need for any local calibration. For the test period of January 2018–June 2020, the model’s capacity to estimate the numerical values of crop water requirement (Penman-Monteith (P-M) ETo values) was assessed. The developed ensemble deep learning models were evaluated using the performance criteria of mean absolute error (MAE), average absolute relative error (AARE), coefficient of correlation (r), noise to signal ratio (NS), Nash–Sutcliffe efficiency (ɳ), and weighted standard error of estimate (WSEE). The results indicated that the WSEE values of RF, GB, and XGBoost models for each location were smaller than 1 mm per day, and the model’s effectiveness varied from 96% to 99% across various locations. While all of the deep learning models performed better with respect to the P-M ETo approach, the XGBoost model was able to estimate ETo with greater accuracy than the GB and RF models. The XGBoost model’s strong performance was also indicated by the decreased noise-to-signal ratio. Thus, in this study, a generalized mathematical model for short-term ETo estimates is developed using ensemble deep learning techniques. Because of this type of model’s accuracy in calculating crop water requirements and its ability for generalization, it can be effortlessly integrated with a real-time water management system or an autonomous weather station at the regional level.

Deep learning (DL) has become a powerful tool for the recognition and classification of biological sequences. However, conventional single-architecture models often struggle with suboptimal predictive performance and high computational costs. To address these challenges, we present EnsembleDL-Lipo, an innovative ensemble deep learning framework that combines Convolutional Neural Networks (CNNs) and Deep Neural Networks (DNNs) to enhance the identification of lipocalin sequences. Lipocalins are multifunctional extracellular proteins involved in various diseases and stress responses, and their low sequence similarity and occurrence in the 'twilight zone' of sequence alignment present significant hurdles for accurate classification. These challenges necessitate efficient computational methods to complement traditional, labor-intensive experimental approaches. EnsembleDL-Lipo overcomes these issues by leveraging a set of PSSM-based features to train a large ensemble of deep learning models. The framework integrates multiple feature representations derived from position-specific scoring matrices (PSSMs), optimizing classification performance across diverse sequence patterns. The model achieved superior results on the training dataset, with an accuracy (ACC) of 97.65%, recall of 97.10%, Matthews correlation coefficient (MCC) of 0.95, and area under the curve (AUC) of 0.99. Validation on an independent test set further confirmed the robustness of the model, yielding an ACC of 95.79%, recall of 90.48%, MCC of 0.92, and AUC of 0.97. These results demonstrate that EnsembleDL-Lipo is a highly effective and computationally efficient tool for lipocalin sequence identification, significantly outperforming existing methods and offering strong potential for applications in biomarker discovery.

BackgroundCytomegalovirus (CMV) reactivation in patients with severe ulcerative colitis (UC) leads to worse outcomes; yet, early detection remains challenging due to the reliance on time-intensive biopsy procedures.ObjectiveThis study explores the use of deep learning to differentiate CMV from severe UC through endoscopic imaging, offering a potential noninvasive diagnostic tool.MethodsWe analyzed 86 endoscopic images using an ensemble of deep learning models, including DenseNet (Densely Connected Convolutional Network) 121 pretrained on ImageNet. Advanced preprocessing and test-time augmentation (TTA) were applied to optimize model performance. The models were evaluated using metrics such as accuracy, precision, recall, F1-score, and area under the curve.ResultsThe ensemble approach, enhanced by TTA, achieved high performance, with an accuracy of 0.836, precision of 0.850, recall of 0.904, and an F1-score of 0.875. Models without TTA showed a significant drop in these metrics, emphasizing TTA’s importance in improving classification performance.ConclusionsThis study demonstrates that deep learning models can effectively distinguish CMV from severe UC in endoscopic images, paving the way for early, noninvasive diagnosis and improved patient care.