One-Dimensional Deep Learning Architecture for Fast Fluorescence Lifetime Imaging

Deep learning models, particularly one‐dimensional convolutional neural networks (1D CNNs), have shown great potential in the fault diagnosis of rotating machines. However, standard 1D CNNs face challenges in capturing long‐term dependencies in time series data. To overcome this, various studies have proposed hybrid models that combine 1D CNN with long short‐term memory (LSTM) networks. Despite these improvements, current 1D CNN‐LSTM methods still encounter issues such as low diagnostic accuracy, limited adaptability to changing conditions, poor generalization, and difficulty detecting compound faults. In response to these issues, this paper presents an improved hybrid fault diagnosis method based on a combination of 1D CNN and LSTM for rotating machines. In this approach, the 1D CNN extracts meaningful features from raw vibration data, which are then processed by the LSTM to model long‐term dependencies within the feature set. The experimental results show diagnosis accuracies of 99.57% for bearing data and 99.15% for the gearbox data, outperforming existing methods. These findings support the practical applicability of the proposed 1D CNN‐LSTM in real‐world industrial applications.

RUL prediction of lithium ion battery based on CEEMDAN-CNN BiLSTM model

Classification of non-small cell lung cancer using one-dimensional convolutional neural network

Anemia is one of the most prevalent nutritional and hematological disorders worldwide, characterized by low hemoglobin levels caused by iron deficiency, genetic factors, or chronic diseases. Diagnosis commonly relies on Complete Blood Count (CBC) interpretation, a manual process that is time-consuming and susceptible to human error. This study proposes a novel hybrid framework that integrates Extreme Gradient Boosting (XGBoost) and a One-Dimensional Convolutional Neural Network (1D-CNN) to enhance anemia classification. The methodological novelty lies in employing XGBoost as a feature-augmentation mechanism, where its class-probability outputs are fused with the original CBC features before being processed by the 1D-CNN, enabling richer representation learning compared to conventional single-model approaches. The model was trained and evaluated using a CBC dataset consisting of 364 samples covering four anemia classes (normocytic, microcytic, macrocytic, and normal), with performance assessed through an 80:20 stratified train–test split. Experimental results demonstrate that the proposed XGB–1DCNN model achieves a testing accuracy of 97.26%, precision of 98.68%, recall of 96.46%, and F1-score of 97.48%, outperforming the baseline 1D-CNN model (83.56%). These findings demonstrate that combining ensemble learning and deep learning significantly improves the model’s ability to capture complex nonlinear patterns in CBC data, offering a more reliable solution for AI-based early anemia diagnosis and clinical decision support.

As an important indicator of vehicle systems, tire load is a key factor in the structural design and safety assessment of vehicles. Direct measurement methods for tire loads are expensive and complicated, while conventional load identification methods are limited by low accuracy and poor robustness. This study aimed to propose a radial load identification method for rubber-tired vehicles based on a one-dimensional convolutional neural network (1D CNN) and bidirectional gated recurrent unit (BiGRU). Considering a priori information of the radial load data of tires and based on the observability of the vehicle vibration system, the proposed method selected feature sets and then retained the effective feature subsets through feature selection to construct samples with multiple time steps as input and with a single time step as output for network training. In doing so, the load prediction results were obtained, and the theoretical model was modified by integrating prediction accuracy, generalization performance, and robustness. Compared with traditional algorithms, the proposed method could effectively reduce the error of load identification, improve adaptability under different operating conditions, and handle the measurement error of different noise levels, which are of practical application value in the engineering field.

Identification of olive oil in vegetable blend oil by one-dimensional convolutional neural network combined with Raman spectroscopy

Identification of faulty feeder in resonant grounding distribution networks remains a significant challenge due to the weak fault current and complicated working conditions. In this paper, we present a deep learning-based multi-label classification framework to reliably distinguish the faulty feeder. Three different neural networks (NNs) including the multilayer perceptron, one-dimensional convolutional neural network (1D CNN), and 2D CNN are built. However, the labeled data may be difficult to obtain in the actual environment. We use the simplified simulation model based on a full-scale test field (FSTF) to obtain sufficient labeled source data. Different from most learning-based methods assuming that the distribution of source domain and target domain is identical, we propose a samples-based transfer learning method to improve the domain adaptation by using samples in the source domain with appreciate weights. The TrAdaBoost algorithm is adopted to update the weights of each sample. The recorded data obtained in the FSTF are utilized to test the domain adaptability. According to our validation and testing, the validation accuracies are high when there is sufficient labeled data for training the proposed NNs. The proposed 2D CNN has the best domain adaptability. The TrAdaBoost algorithm can help the NNs to train an efficient classifier that has better domain adaptation. It has been therefore concluded that the proposed method especially the 2D CNN is suitable for actual distribution networks.

Functional magnetic resonance imaging (fMRI) is one of the best techniques for precise localization of abnormal brain activity non-invasively. Machine-learning approaches have been widely used in neuroimaging studies; however, few studies have investigated the single-voxel modeling of fMRI data under cognitive tasks. We proposed a hybrid one-dimensional (1D) convolutional neural network (1D-CNN) based on the temporal dynamics of single-voxel fMRI time-series and successfully differentiated two continuous task states, namely, self-initiated (SI) and visually guided (VG) motor tasks. First, 25 activation peaks were identified from the contrast maps of SI and VG tasks in a blocked design. Then, the fMRI time-series of each peak voxel was transformed into a temporal-frequency domain by using continuous wavelet transform across a broader frequency range (0.003–0.313 Hz, with a step of 0.01 Hz). The transformed time-series was inputted into a 1D-CNN model for the binary classification of SI and VG continuous tasks. Compared with the univariate analysis, e.g., amplitude of low-frequency fluctuation (ALFF) at each frequency band, including, wavelet-ALFF, the 1D-CNN model highly outperformed wavelet-ALFF, with more efficient decoding models [46% of 800 models showing area under the curve (AUC) > 0.61] and higher decoding accuracies (94% of the efficient models), especially on the high-frequency bands (>0.1 Hz). Moreover, our results also demonstrated the advantages of wavelet decompositions over the original fMRI series by showing higher decoding performance on all peak voxels. Overall, this study suggests a great potential of single-voxel analysis using 1D-CNN and wavelet transformation of fMRI series with continuous, naturalistic, steady-state task design or resting-state design. It opens new avenues to precise localization of abnormal brain activity and fMRI-guided precision brain stimulation therapy.

Human Activity Recognition (HAR) is a complex problem in deep learning, and One-Dimensional Convolutional Neural Networks (1D CNNs) have emerged as a popular approach for addressing it. These networks efficiently learn features from data that can be utilized to classify human activities with high performance. However, understanding and explaining the features learned by these networks remains a challenge. This paper presents a novel eXplainable Artificial Intelligence (XAI) method for generating visual explanations of features learned by one-dimensional CNNs in its training process, utilizing t-Distributed Stochastic Neighbor Embedding (t-SNE). By applying this method, we provide insights into the decision-making process through visualizing the information obtained from the model's deepest layer before classification. Our results demonstrate that the learned features from one dataset can be applied to differentiate human activities in other datasets. Our trained networks achieved high performance on two public databases, with 0.98 accuracy on the SHO dataset and 0.93 accuracy on the HAPT dataset. The visualization method proposed in this work offers a powerful means to detect bias issues or explain incorrect predictions. This work introduces a new type of XAI application, enhancing the reliability and practicality of CNN models in real-world scenarios.

Tool wear condition monitoring during the machining process is one of the most important considerations in precision manufacturing. Cutting force is one of the signals that has been widely used for tool wear condition monitoring, which contains the dynamical information of tool wear conditions. This paper proposes a novel multivariate cutting force-based tool wear monitoring method using one-dimensional convolutional neural network (1D CNN). Firstly, multivariate variational mode decomposition (MVMD) is used to process the multivariate cutting force signals. The multivariate band-limited intrinsic mode functions (BLIMFs) are obtained, which contain a large number of nonlinear and nonstationary tool wear characteristics. Afterwards, the proposed modified multiscale permutation entropy (MMPE) is used to measure the complexity of multivariate BLIMFs. The entropy values on multiple scales are calculated as condition indicators in tool wear condition monitoring. Finally, the one-dimensional feature vectors are constructed and employed as the input of 1D CNN to achieve accurate and stable tool wear condition monitoring. The results of the research in this paper demonstrate that the proposed approach has broad prospects in tool wear condition monitoring.

Fluorescence lifetime imaging of the co-enzyme reduced nicotinamide adenine dinucleotide (NADH) offers a label-free approach for detecting cellular metabolic perturbations. However, the relationships between variations in NADH lifetime and metabolic pathway changes are complex, preventing robust interpretation of NADH lifetime data relative to metabolic phenotypes. Here, a three-dimensional convolutional neural network (3D CNN) trained at the cell level with 3D NAD(P)H lifetime decay images (two spatial dimensions and one time dimension) was developed to identify metabolic pathway usage by cancer cells. NADH fluorescence lifetime images of MCF7 breast cancer cells with three isolated metabolic pathways, glycolysis, oxidative phosphorylation, and glutaminolysis were obtained by a multiphoton fluorescence lifetime microscope and then segmented into individual cells as the input data for the classification models. The 3D CNN models achieved over 90% accuracy in identifying cancer cells reliant on glycolysis, oxidative phosphorylation, or glutaminolysis. Furthermore, the model trained with human breast cancer cell data successfully predicted the differences in metabolic phenotypes of macrophages from control and POLG-mutated mice. These results suggest that the integration of autofluorescence lifetime imaging with 3D CNNs enables intracellular spatial patterns of NADH intensity and temporal dynamics of the lifetime decay to discriminate multiple metabolic phenotypes. Furthermore, the use of 3D CNNs to identify metabolic phenotypes from NADH fluorescence lifetime decay images eliminates the need for time- and expertise-demanding exponential decay fitting procedures. In summary, metabolic-prediction CNNs will enable live-cell and in vivo metabolic measurements with single-cell resolution, filling a current gap in metabolic measurement technologies.

Summary Miscible carbon dioxide (CO2) injection has proven to be an effective method of recovering oil from unconventional reservoirs. An accurate and efficient procedure to calculate the oil-CO2 minimum miscibility pressure (MMP) is a crucial subroutine in the successful design of a miscible CO2 injection. However, current numerical methods for the unconventional MMP prediction are very demanding in terms of time and computational costs which result in long runtime with a reservoir simulator. This work proposes to employ a one-dimensional convolutional neural network (1D CNN) to accelerate the unconventional MMP determination process. Over 1,200 unconventional MMP data points are generated using the multiple-mixing-cell (MMC) method coupled with capillarity and confinement effects for training purposes. The data set is first standardized and then processed with principal component analysis (PCA) to avoid overfitting. The performance of the proposed model is evaluated with testing data. By applying the trained model, the unconventional MMP results are almost instantly produced and a coefficient of determination of 0.9862 is achieved with the testing data. Notably, 98.58% of predicting data points lie within 5% absolute relative error. This work demonstrates that the prediction of unconventional MMP can be significantly accelerated, compared with the numerical simulations, by the proposed well-trained deep learning model with a slight impact on the accuracy.

Pneumatic systems are widely utilized in industrial manufacturing plants. Leakage is the most common fault and the dominating way of energy waste in pneumatic systems. Due to the low investment cost and high reliability of pneumatic systems, it is significant to detect leakage faults with a minimal number of cheap sensors. In this study, the feasibility of locating the leakages in 11 positions of a typical pneumatic system is verified with machine learning methods and the measured signal at a single point upstream. Both external and internal leakages of different pneumatic components are considered. Feature extraction is conducted using a one-dimensional convolutional neural network (1D CNN). Various machine learning classifiers, including GPC (Gaussian Process Classification), SVM (Support Vector Machine), KNN (k-Nearest Neighbour), CART (Classification and Regression Tree), MLP (Multi-Layer Perceptron), and RF (Random Forest) are used for fault classification and comparison. Class Activation Mapping (CAM) is calculated for the visualization of decision-making processes. The results show that it is feasible and convenient to detect and locate the multipoint leakages in a pneumatic system by analysing signal measured at a sole upstream point with the help of machine learning methods. The methodology can be extrapolated to and applied in more complex pneumatic systems.

The analysis of body motion is a valuable tool in the assessment and diagnosis of gait impairments, particularly those related to neurological disorders. In this study, we propose a novel automated system leveraging artificial intelligence for efficiently analyzing gait impairment from video-recorded images. The proposed methodology encompasses three key aspects. First, we generate a novel one-dimensional representation of each silhouette image, termed a silhouette sinogram, by computing the distance and angle between the centroid and each detected boundary points. This process enables us to effectively utilize relative variations in motion at different angles to detect gait patterns. Second, a one-dimensional convolutional neural network (1D CNN) model is developed and trained by incorporating the consecutive silhouette sinogram signals of silhouette frames to capture spatiotemporal information via assisted knowledge learning. This process allows the network to capture a broader context and temporal dependencies within the gait cycle, enabling a more accurate diagnosis of gait abnormalities. This study conducts training and an evaluation utilizing the publicly accessible INIT GAIT database. Finally, two evaluation schemes are employed: one leveraging individual silhouette frames and the other operating at the subject level, utilizing a majority voting technique. The outcomes of the proposed method showed superior enhancements in gait impairment recognition, with overall F1-scores of 100%, 90.62%, and 77.32% when evaluated based on sinogram signals, and 100%, 100%, and 83.33% when evaluated based on the subject level, for cases involving two, four, and six gait abnormalities, respectively. In conclusion, by comparing the observed locomotor function to a conventional gait pattern often seen in healthy individuals, the recommended approach allows for a quantitative and non-invasive evaluation of locomotion.

This study introduces the EMR Score, a novel approach that integrates seismocardiography (SCG) features with clinical risk factors to estimate the pre-test probability of coronary artery disease (CAD) while focusing solely on chest pain presence. Data were collected from a multicenter randomized trial enrolling 1,640 participants, including 740 patients diagnosed with obstructive CAD and 900 healthy controls. CAD diagnosis was confirmed using coronary computed tomography angiography (CCTA) or invasive coronary angiography (ICA). SCG and electrocardiography (ECG) signals were recorded using the HeartForce CardioClin device. The EMR Score was developed using a one-dimensional convolutional neural network (1D CNN) trained on SCG-derived features and clinical variables, including age, sex, smoking status, hypertension, hyperlipidemia, diabetes, family history, and chest pain presence. The final model produced probabilities for CAD and non-CAD outcomes, optimized using categorical cross-entropy and the Adam optimizer, with performance evaluated via cross-validation. Unlike traditional models that rely on chest pain subtyping, the EMR Score follows the American Heart Association's (AHA) recommendation to prioritize chest pain as a key screening factor, reducing interobserver variability and improving applicability across diverse populations. The EMR Score outperformed the AHA model, achieving a higher AUC (0.85 vs. 0.74) and improved specificity (42% vs. 35%) while maintaining high sensitivity (96% vs. 90%). It also reclassified many intermediate-risk patients (69% in the AHA model vs. 19%), shifting them to low- (25%) or high-risk (55%) categories, where CAD prevalence was 8% and 70%, respectively. By eliminating subjective symptom classification and leveraging SCG-derived features, the EMR Score provides a scalable, cost-effective screening tool that enhances CAD risk stratification and optimizes clinical decision-making.