An Ensemble 3D Convolutional Neural Network for Spatiotemporal Soil Temperature Forecasting

Disease prediction based on modeling the correlations between compounded indicator factors is a widely used technique in high incidence chronic disease prevention diagnosis. Predictive models based on personal health information have been developed historically by using simple regression fitting over relatively few factors. Regression approaches have been favored in previous prediction modeling approaches because they are simplest and do not assume any non-linearity in the model for contributions of the chosen factors. In practice, many factors are correlated and have underlying non-linear relationships to the predicted outcome. Deep learning offers a means to construct a more complex modeling approach, along with automation and adaptation. The aim of this paper is to assess the ability of a deep learning model to predict the heart disease incidence using a common benchmark dataset (University of California, Irvine (UCI) dataset). The performance of deep learning model has been compared with four popular machine learning models (two linear and two nonlinear) in predicting the incidence of heart disease using data from 567 participants from two cohorts taken from UCI database. The deep learning model was able to achieve the best accuracy of 94% and an AUC score of 0.964 when compared to other models. The performance of deep learning and nonlinear machine learning models was significantly better compared to the linear machine learning models with increase in the dataset size.

Emotion recognition (ER) is crucial for understanding human behaviours, social interactions, and psychological well-being. Electroencephalography (EEG) has emerged as a promising tool for capturing the neural correlates of emotions. This work is a systematic review of articles in ER using EEG signals. A total of 120 articles from 1041 articles were selected based on PRISMA guidelines using defined inclusion and exclusion criteria, published between 2018 and 2024. This article aims to provide an in-depth understanding of the current landscape of ER from EEG signals utilizing deep learning (DL). This review offers valuable guidance for researchers and practitioners seeking more refined and reliable emotion classification systems. To explore the effectiveness of DL models in EEG-based ER, several potential DL models, such as convolutional neural network, long short-term memory (LSTM), gated recurrent unit (GRU), hybrid bidirectional LSTM (BiLSTM), bidirectional GRU, and advanced DL models such as convolutional recurrent neural network and EEG-Conformer models are applied to two popular datasets, SEED and GAMEEMO, respectively, to depict the full process of ER. Additionally, the performance of DL models is also compared with the performance of basic machine learning (ML) models such as SVM, k-nearest neighbors, logistic regression, and boosting algorithms such as AdaBoost, XGBoost and LightGBM. Through extensive experiments and performance evaluations, the performance of different models when applied to the datasets mentioned above is compared. The accuracy, precision, recall, and F1-scores are analysed to determine the most effective model for EEG-based ER. The findings of this study demonstrate that the performance of hybrid DL models is more efficacious than that of ML models. The best-performing model (BiLSTM) classified the emotions, with an accuracy of 90.54% when applied to the GAMEEMO dataset. This research contributes to the growing body of literature on ER and provides insights into the feasibility of using EEG signals to understand emotional states, and presents a structured roadmap for future exploration. The findings can aid in the development of more accurate and reliable ER systems, which can have wide-ranging applications in psychology, social sciences, and human-computer interactions.

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%.

Area under the curve may hide poor generalisation to external datasets

ObjectiveThis study aims to tackle the critical challenge of adapting deep learning (DL) models for deployment in real-world healthcare settings, specifically focusing on catastrophic forgetting due to distribution shifts between hospital and non-hospital environments. Metabolic syndrome (MetS) is susceptible to misdiagnosis by DL models due to distribution shifts. This work demonstrates the potential of continual learning (CL) to enhance model performance in MetS identification across diverse settings.Materials and MethodsWe utilized 3 healthcare datasets from 2 distinct settings: Medical Information Mart for Intensive Care (MIMIC; from a hospital setting), National Health and Nutrition Examination Survey (NHANES), and a proprietary dataset (both from non-hospital settings). We proposed a robust MetS identification pipeline with CL strategies and evaluated its effectiveness in mitigating catastrophic forgetting while maintaining high predictive performance under distribution shift.ResultsThe CL method outperformed the control (sequential training without any strategies) method. The CL method reached a cumulative area under the ROC curve (AUROC) of 0.85 and area under the precision-recall curve of 0.65 on the combined test set. Moreover, training order proved critical: models trained from hospital to non-hospital settings achieved a 7.6% improvement in AUROC, increasing from 0.79 to 0.85, compared to the reverse order.DiscussionOur results demonstrate the potential of CL for applications across healthcare settings, particularly between hospital and non-hospital settings. We also discuss the impact of training order on the results.ConclusionThe proposed CL model effectively mitigates catastrophic forgetting, enhancing the overall performance of DL models. Our results underscore the prospect of CL methods in developing medical DL models and maintaining scalability across diverse healthcare settings.

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision. In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by the Active Shape Model (ASM), is ASM Loss, designed to improve the detection of facial landmarks and head pose accuracy in facial images. Additionally, influenced by Knowledge Distillation (KD), I introduce KD-Loss, a loss designed specifically for regression tasks, focusing on detecting facial landmarks. Proceeding to the second phase of my research, I focus on regression problems. Building upon my prior work, I introduce Adaptive Coordinate-based Regression (ACR)-Loss, a context-aware loss function with face alignment implication. I provide a mechanism to dynamically measure how hard the localization of each landmark point is, and accordingly, ACR-Loss provides unique feedback to the model. Furthermore, I introduce Intensity-aware Categorical (IC)-Loss for detecting sagittal cervical spine landmark points in medical images. It effectively deploys characteristics from classification problems to enhance regression optimization. Both ACR-Loss and IC-Loss comprise contextual information, leading to a significant enhancement in localization precision. In the third phase, I turned my attention toward classification problems within the domain of deep machine learning. I introduce Adaptive Correlation-based (Ad-corre) Loss, designed to enhance the discriminative capabilities of deep learning models, with a specific focus on improving classification accuracy in automatic facial expression recognition. Furthermore, I introduce Informative (Info) Loss, a specialized loss function developed for medical applications, specifically aimed at distinguishing between Mild Cognitive Impairment and Normal Cognition groups based on transcriptions of interviews conducted as part of the I-CONECT study. Overall, I have proposed custom loss functions to improve the predictive performance in both regression and classification problems. Furthermore, I have introduced assistive loss functions, designed to enhance the performance of the main loss functions. The collective outcomes of this extensive exploration highlight the critical role of loss functions, adapting and optimizing them for various domains in deep machine learning. This research suggests and proposes a variety of methodologies for designing adaptive and context-aware loss functions within deep machine learning.

To develop a deep learning model for pressure injury stages classification based on real-world photographs and compare its performance with that of clinical nurses to seek the opportunity of its application in clinical settings. This was a retrospective observational study using a deep learning model. A plastic surgeon and two wound care nurses labelled a set of pressure injury images. We applied several modern Convolutional Neural Networks architectures and compared the performances with those of clinical nurses. We retrospectively analysed the electronic medical records of hospitalized patients between January 2019 and April 2021. A set of 2464 pressure injury images were compiled and analysed. Using EfficientNet, in classifying pressure injury images, the macro F1-score was calculated to be 0.8941, and the average performance of two experienced nurses was reported as 0.8781. A deep learning model for classifying pressure injury images by stages was successfully developed, and the performance of the model was compared with that of experienced nurses. The classification model developed in this study is expected to help less-experienced nurses or those working in under-resourced healthcare settings determine the stages of pressure injury. Our deep learning model can minimize discrepancies in nurses' assessment of classifying pressure injury stages. Follow-up studies on improving the performance of deep learning models using modern techniques and clinical usability will lead to improved quality of care among patients with pressure injury. Patients or the public were not involved in our research's design, conduct, reporting or dissemination plans because this was a retrospective study that used electronic medical records.

This paper presents a supervised learning scheme that employs key-frame extraction to enhance the performance of pre-trained deep learning models for object detection in surveillance videos. Developing supervised deep learning models requires a significant amount of annotated video frames as training data, which demands substantial human effort for preparation. Key frames, which encompass frames containing false negative or false positive objects, can introduce diversity into the training data and contribute to model improvements. Our proposed approach focuses on detecting false negatives by leveraging the motion information within video frames that contain the detected object region. Key-frame extraction significantly reduces the human effort involved in video frame extraction. We employ interactive labeling to annotate false negative video frames with accurate bounding boxes and labels. These annotated frames are then integrated with the existing training data to create a comprehensive training dataset for subsequent training cycles. Repeating the training cycles gradually improves the object detection performance of deep learning models to monitor a new environment. Experiment results demonstrate that the proposed learning approach improves the performance of the object detection model in a new operating environment, increasing the mean average precision (mAP@0.5) from 54% to 98%. Manual annotation of key frames is reduced by 81% through the proposed key-frame extraction method.

Improving soybean (Glycine max L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model's performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7's pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model's performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7.

Deep learning (DL) is appearing as a powerful tool for spectral data modelling. In many cases, the DL models have been shown to outperform the classical chemometric spectral data modelling approaches. However, a main challenge with the DL models is the limited model interpretability as there are no scores and loadings generated in DL models. Scores and loadings are key parts of chemometric modelling as they facilitate the interpretation of the models. Furthermore, most of the time in the reported literature, the performance of DL models is compared with basic chemometric approaches with less attention being paid to optimizing these chemometric models. This study aims to test the hypothesis that proper chemometric modelling of spectral data can lead to performance equivalent to that of DL models while having all the useful information such as scores, loadings, and regression coefficients to support model interpretation. To test this, a case study is presented for the prediction of nitrogen content in rapeseed (Brassica napus L.) by Vis-NIR spectroscopy. On the classical chemometric side, two recently developed pre-processing fusion approaches, i.e. sequential pre-processing through orthogonalization (SPORT) and parallel pre-processing through orthogonalization (PORTO) were used. On the DL side, the previously published with DL modelling results for the same data set were used as the benchmark. Such a comparison was valid as the chemometric analysis was performed on the same calibration and test sets as used previously for the DL modelling. Results showed that the sequential and parallel learning approaches attained the same accuracy as that of the previously reported DL procedure on the same data set. The information related to scores, loading and regression coefficients could be used for model interpretation.

The past few years have seen a surge of applying Deep Learning (DL) models for a wide array of tasks such as image classification, object detection, machine translation, etc. While DL models provide an opportunity to solve otherwise intractable tasks, their adoption relies on them being optimized to meet latency and resource requirements. Benchmarking is a key step in this process but has been hampered in part due to the lack of representative and up-to-date benchmarking suites. This is exacerbated by the fast-evolving pace of DL models. This paper proposes DLBricks, a composable benchmark generation design that reduces the effort of developing, maintaining, and running DL benchmarks on CPUs. DLBricks decomposes DL models into a set of unique runnable networks and constructs the original model's performance using the performance of the generated benchmarks. DLBricks leverages two key observations: DL layers are the performance building blocks of DL models and layers are extensively repeated within and across DL models. Since benchmarks are generated automatically and the benchmarking time is minimized, DLBricks can keep up-to-date with the latest proposed models, relieving the pressure of selecting representative DL models. Moreover, DLBricks allows users to represent proprietary models within benchmark suites. We evaluate DLBricks using $50$ MXNet models spanning $5$ DL tasks on $4$ representative CPU systems. We show that DLBricks provides an accurate performance estimate for the DL models and reduces the benchmarking time across systems (e.g. within $95\%$ accuracy and up to $4.4\times$ benchmarking time speedup on Amazon EC2 c5.xlarge).

Application of the EEMD method for distinction and suppression of motion-induced noise in grounded electrical source airborne TEM system

Objective.Functional brain network (FBN) methods are commonly integrated with deep learning (DL) models for EEG analysis. Typically, an FBN is constructed to extract features from EEG data, which are then fed into a DL model for further analysis. Beyond this two-step approach, there is potential to embed FBN construction directly within DL models as a feature extraction module, enabling the models to learn EEG representations end-to-end while incorporating insights from FBNs. However, a critical prerequisite is whether DL models can effectively learn the FBN construction process.Approach.To address this, we propose using DL models to learn FBN matrices derived from EEG data. The ability of DL models to accurately reproduce these matrices would validate their capacity to learn the FBN construction process. This approach is tested on two publicly available EEG datasets, utilizing seven DL models to learn four representative FBN matrices. Model performance is assessed through mean squared error (MSE), Pearson correlation coefficient (Corr), and concordance correlation coefficient (CCC) between predicted and actual matrices.Main results.The results show that DL models achieve low MSE and relatively high Corr and CCC values when learning the Coherence network. Visualizations of predicted and error matrices reveal that while DL models capture the general structure of all four FBNs, certain regions remain difficult to model accurately. Additionally, a pairedt-test comparing global efficiency and nodal degree between predicted and actual networks indicates that most predicted networks significantly differ from the actual networks (p<0.05).Significance.These findings suggest that while DL models can learn the connectivity relationships of certain FBNs, they struggle to capture the intrinsic topological structures. This highlights the irreplaceability of traditional FBN methods in EEG analysis and underscores the need for hybrid strategies that combine FBN methods with DL models for a more comprehensive analysis.

Pathological is crucial to cancer diagnosis. Usually, Pathologists draw their conclusion based on observed cell and tissue structure on histology slides. Rapid development in machine learning, especially deep learning have established robust and accurate classifiers. They are being used to analyze histopathological slides and assist pathologists in diagnosis. Most machine learning systems rely heavily on annotated data sets to gain experiences and knowledge to correctly and accurately perform various tasks such as classification and segmentation. This work investigates different granularity of annotations in histopathological data set including image-wise, bounding box, ellipse-wise, and pixel-wise to verify the influence of annotation in pathological slide on deep learning models. We design corresponding experiments to test classification and segmentation performance of deep learning models based on annotations with different annotation granularity. In classification, state-of-the-art deep learning-based classifiers perform better when trained by pixel-wise annotation dataset. On average, precision, recall and F1-score improves by 7.87%, 8.83% and 7.85% respectively. Thus, it is suggested that finer granularity annotations are better utilized by deep learning algorithms in classification tasks. Similarly, semantic segmentation algorithms can achieve 8.33% better segmentation accuracy when trained by pixel-wise annotations. Our study shows not only that finer-grained annotation can improve the performance of deep learning models, but also help extracts more accurate phenotypic information from histopathological slides. Intelligence systems trained on granular annotations may help pathologists inspecting certain regions for better diagnosis. The compartmentalized prediction approach similar to this work may contribute to phenotype and genotype association studies.

While deep learning (DL) models have shown promise in breast cancer diagnosis using digital breast tomosynthesis (DBT) images, the impact of varying matrix sizes and image interpolation methods on diagnostic accuracy remains unclear. Understanding these effects is essential to optimize preprocessing steps for DL models, which can lead to more efficient training processes, improved diagnostic accuracy, and better utilization of computational resources. Our institutional review board approved this retrospective study and waived the requirement for informed consent from the patients. In this study, 499 patients (29-90 years old, mean age 50.5 years) who underwent breast tomosynthesis were included. We performed downsampling to 256 × 256, 128 × 128, 64 × 64, and 32 × 32 using five image interpolation methods: Nearest (NN), Bilinear (BL), Bicubic (BC), Hamming (HM), and Lanczos (LC). The diagnostic accuracy of the DL model was assessed by mean AUC with its 95% confidence interval (CI). DL models with downsampled images to 256 × 256 pixels using the LC interpolation method showed a significantly lower AUC than the original 512 × 512 pixels model. This decrease was also observed with the 128 × 128 pixels DL models using HM and LC methods. All interpolation methods showed a significant decrease in AUC for the 64 × 64 and 32 × 32 pixels DL models. Our results highlight the significant impact of downsampling size and interpolation methods on the diagnostic performance of DL models. Understanding these effects is essential for optimizing preprocessing steps, which can enhance the accuracy and reliability of breast cancer diagnosis using DBT images.