Convolutional Network Research Articles

Artificial Intelligence in Audiology: A Scoping Review of Current Applications and Future Directions

The integration of artificial intelligence (AI) into medical disciplines is rapidly transforming healthcare delivery, with audiology being no exception. By synthesizing the existing literature, this review seeks to inform clinicians, researchers, and policymakers about the potential and challenges of integrating AI into audiological practice. The PubMed, Cochrane, and Google Scholar databases were searched for articles published in English from 1990 to 2024 with the following query: “(audiology) AND (“artificial intelligence” OR “machine learning” OR “deep learning”)”. The PRISMA extension for scoping reviews (PRISMA-ScR) was followed. The database research yielded 1359 results, and the selection process led to the inclusion of 104 manuscripts. The integration of AI in audiology has evolved significantly over the succeeding decades, with 87.5% of manuscripts published in the last 4 years. Most types of AI were consistently used for specific purposes, such as logistic regression and other statistical machine learning tools (e.g., support vector machine, multilayer perceptron, random forest, deep belief network, decision tree, k-nearest neighbor, or LASSO) for automated audiometry and clinical predictions; convolutional neural networks for radiological image analysis; and large language models for automatic generation of diagnostic reports. Despite the advances in AI technologies, different ethical and professional challenges are still present, underscoring the need for larger, more diverse data collection and bioethics studies in the field of audiology.

Highly Elastic, Fatigue-Resistant, and Antifreezing MXene Functionalized Organohydrogels as Flexible Pressure Sensors for Human Motion Monitoring.

Conductive organohydrogels-based flexible pressure sensors have gained considerable attention in health monitoring, artificial skin, and human-computer interaction due to their excellent biocompatibility, wearability, and versatility. However, hydrogels' unsatisfactory mechanical and unstable electrical properties hinder their comprehensive application. Herein, an elastic, fatigue-resistant, and antifreezing poly(vinyl alcohol) (PVA)/lipoic acid (LA) organohydrogel with a double-network structure and reversible cross-linking interactions has been designed, and MXene as a conductive filler is functionalized into organohydrogel to further enhance the diverse sensing performance of flexible pressure sensors. The as-fabricated MXene-based PVA/LA organohydrogels (PLBM) exhibit stable fatigue resistance for over 450 cycles under 40% compressive strain, excellent elasticity, antifreezing properties (<-20 °C), and degradability. Furthermore, the pressure sensors based on the PLBM organohydrogels show a fast response time (62 ms), high sensitivity (S = 0.0402 kPa-1), and excellent stability (over 1000 cycles). The exceptional performance enables the sensors to monitor human movements, such as joint flexion and throat swallowing. Moreover, the sensors integrating with the one-dimensional convolutional neural networks and the long-short-term memory networks deep learning algorithms have been developed to recognize letters with a 93.75% accuracy, representing enormous potential in monitoring human motion and human-computer interaction.

Design and implementation of VGD6-NET framework for waste segregation using 3-tier convolutional neural networks

Design and implementation of VGD6-NET framework for waste segregation using 3-tier convolutional neural networks

Research on a Joint Extraction Method of Track Circuit Entities and Relations Integrating Global Pointer and Tensor Learning

To address the issue of efficiently reusing the massive amount of unstructured knowledge generated during the handling of track circuit equipment faults and to automate the construction of knowledge graphs in the railway maintenance domain, it is crucial to leverage knowledge extraction techniques to efficiently extract relational triplets from fault maintenance text data. Given the current lag in joint extraction technology within the railway domain and the inefficiency in resource utilization, this paper proposes a joint extraction model for track circuit entities and relations, integrating Global Pointer and tensor learning. Taking into account the associative characteristics of semantic relations, the nesting of domain-specific terms in the railway sector, and semantic diversity, this research views the relation extraction task as a tensor learning process and the entity recognition task as a span-based Global Pointer search process. First, a multi-layer dilate gated convolutional neural network with residual connections is used to extract key features and fuse the weighted information from the 12 different semantic layers of the RoBERTa-wwm-ext model, fully exploiting the performance of each encoding layer. Next, the Tucker decomposition method is utilized to capture the semantic correlations between relations, and an Efficient Global Pointer is employed to globally predict the start and end positions of subject and object entities, incorporating relative position information through rotary position embedding (RoPE). Finally, comparative experiments with existing mainstream joint extraction models were conducted, and the proposed model’s excellent performance was validated on the English public datasets NYT and WebNLG, the Chinese public dataset DuIE, and a private track circuit dataset. The F1 scores on the NYT, WebNLG, and DuIE public datasets reached 92.1%, 92.7%, and 78.2%, respectively.

RlaNet: A Residual Convolution Nested Long-Short-Term Memory Model with an Attention Mechanism for Wind Turbine Fault Diagnosis

This paper proposes a new fault diagnosis model for wind power systems called residual convolution nested long short-term memory network with an attention mechanism (rlaNet). The method first preprocesses the SCADA data through feature engineering, uses the Hermite interpolation method to handle missing data, and uses the mutual information-based dimensionality reduction technique to improve data quality and eliminate redundant information. rlaNet combines residual networks and nested long short-term memory networks to replace traditional convolutional neural networks and standard long short-term memory architectures, thereby improving feature extraction and ensuring the abstractness and depth of the extracted features. In addition, the model emphasizes the weighted learning of spatiotemporal features in the input data, enhances the focus on key features, and improves training efficiency. Experimental results show that rlaNet achieves an accuracy of more than 90% in wind turbine fault diagnosis, showing good robustness. Furthermore, noise simulation experiments verify the model’s resistance to interference, providing a reliable solution for wind turbine fault diagnosis under complex operating conditions.

Injury prevention and rehabilitation strategies in physical education: A machine learning-based approach using biomechanical characteristics

The field of sports biomechanics employs concepts from physics, biology, and engineering to investigate the mechanical characteristics of human motion and how they affect the body’s anatomy and functions. With the development of technology, sports biomechanics has emerged as a crucial component of sports medicine, training, and rehabilitation. To reduce the risk of injury and enhance athletic performance, sports biomechanics examines motions in sports in great length. The purpose of the study is to establish injury prevention and rehabilitation strategies for physical education (PE) teaching based on biomechanical characteristics. The early warning mode of sports injuries is recognized using advanced deep learning (DL) techniques, specifically resilient convolutional neural networks (RCNN). Biomechanical data from wearable sensors is used in this study to find trends related to sports-related injuries. A questionnaire survey of 228 students from various colleges was conducted. Individualized rehabilitation strategies will be provided to injured participants, taking into account their unique biomechanical deficiencies. These programs will be created in conjunction with physical therapists, and they will be updated in response to the patient’s progress toward recovery. The study found that their sports injuries were acute and chronic. This research demonstrated the treatment, prevention, and rehabilitation strategies of injuries in sports. The study emphasizes that biomechanical analysis is crucial for improving PE programs, which will eventually enhance students’ performance and overall health.

Earthquake magnitude estimation using a two-step convolutional neural network

Earthquake magnitude estimation using a two-step convolutional neural network

A Lightweight and Efficient Multimodal Feature Fusion Network for Bearing Fault Diagnosis in Industrial Applications

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared with existing models, LEMFN captures rich fault features at multiple scales by combining time-domain and frequency-domain signals, thereby enhancing the model’s robustness to noise and improving data adaptability under varying operating conditions. Additionally, the convolutional block attention module (CBAM) and random overlapping sampling technology (ROST) are introduced, and through a feature fusion strategy, the accurate diagnosis of mechanical equipment faults is achieved. Experimental results demonstrate that the proposed method not only possesses high diagnostic accuracy and rapid convergence but also exhibits strong robustness in noisy environments. Finally, a graphical user interface (GUI)-based mechanical equipment fault detection system was developed to promote the practical application of intelligent fault diagnosis in mechanical equipment.

Wearable device data-driven athlete injury detection and rehabilitation monitoring algorithm

In recent years, sports wearable technology has completely changed the way athletes prepare, compete, and recover. Wearable technology has a lot to offer in the rehabilitation process, which is essential to an athlete’s return to their best performance. Wearable devices for athlete injury detection pose potential challenges like data quality, security, and privacy, impacting accuracy, reliability, and effectiveness. To solve these problems, an innovative injury detection and rehabilitation monitoring (IDRM) system was proposed for athletes. By employing an adjustable recurrent neural network (ARNN) to detect anomalies in injury risks such as abnormal joint movements in athletes. In this study, biomechanics data was collected from sports athletes through wearable devices, and the wearable system provided feedback to the user. A redefined convolutional neural network (RCNN) was utilized to monitor the rehabilitation process. This system tracks athlete’s rehabilitation progress and ensures that progress monitors were performed correctly, and the system, feasibility was evaluated on 10 healthy subjects performing 4 different rehabilitation exercises. Each exercise was performed four times monitoring and validation. The data was preprocessed using a Gaussian filter to remove noise from the obtained data. Then the features are extracted using independent component analysis (ICA) for dimensionality reduction from preprocessed data. The proposed method is implemented using Python software. In comparative analysis, the performance of ARNN showed high performance, with an F1-measure of 91.6%, accuracy of 93.5%, recall of 92.8%, and precision of 91.4%. With a 95% accuracy rate, 98% F1 measure, 94% precision, and 93% recall, the RCNN model functioned effectively. The result showed the proposed method achieved better performance in athlete injury detection and accurately recognizing all rehabilitation monitoring. This study provides a complete approach to athlete health management by highlighting the integration of rehabilitation monitoring and injury detection into an overall structure.

Classification of Hyperspectral Images of Explosive Fragments Based on Spatial–Spectral Combination

The identification and recovery of explosive fragments can provide a reference for the evaluation of explosive power and the design of explosion-proof measures. At present, fragment detection usually uses a few bands in the visible light or infrared bands for imaging, without fully utilizing multi-band spectral information. Hyperspectral imaging has high spectral resolution and can provide multidimensional reference information for the fragments to be classified. Therefore, this article proposed a spatial–spectral joint method for explosive fragment classification by combining hyperspectral imaging technology. In a laboratory environment, this article collected hyperspectral images of explosion fragments scattered in simulated scenes. In order to extract effective features from redundant spectral information and improve classification accuracy, this paper adopted a classification framework based on deep learning. This framework used a convolutional neural network–bidirectional long short-term memory network (CNN-BiLSTM) as the spectral information classification model and a U-shaped network (U-Net) as the spatial segmentation model. The experimental results showed that the overall accuracy exceeds 95.2%. The analysis results indicated that the method of spatial–spectral combination can accurately identify explosive fragment targets. It validated the feasibility of using hyperspectral imaging for explosive fragment classification in laboratory environments. Due to the complex environment of the actual explosion site, this study still needs to be validated in outdoor environments. Our next step is to use airborne hyperspectral imaging to identify explosive fragments in outdoor environments.

Spoken language understanding via graph contrastive learning on the context-aware graph convolutional network

Spoken language understanding via graph contrastive learning on the context-aware graph convolutional network

Machine learning models in evaluating the malignancy risk of ovarian tumors: a comparative study.

The study aimed to compare the diagnostic efficacy of the machine learning models with expert subjective assessment (SA) in assessing the malignancy risk of ovarian tumors using transvaginal ultrasound (TVUS). The retrospective single-center diagnostic study included 1555 consecutive patients from January 2019 to May 2021. Using this dataset, Residual Network(ResNet), Densely Connected Convolutional Network(DenseNet), Vision Transformer(ViT), and Swin Transformer models were established and evaluated separately or combined with Cancer antigen 125 (CA 125). The diagnostic performance was then compared with SA. Of the 1555 patients, 76.9% were benign, while 23.1% were malignant (including borderline). When differentiating the malignant from ovarian tumors, the SA had an AUC of 0.97 (95% CI, 0.93-0.99), sensitivity of 87.2%, and specificity of 98.4%. Except for Vision Transformer, other machine learning models had diagnostic performance comparable to that of the expert. The DenseNet model had an AUC of 0.91 (95% CI, 0.86-0.95), sensitivity of 84.6%, and specificity of 95.1%. The ResNet50 model had an AUC of 0.91 (0.85-0.95). The Swin Transformer model had an AUC of 0.92 (0.87-0.96), sensitivity of 87.2%, and specificity of 94.3%. There was a statistically significant difference between the Vision Transformer and SA, and between the Vision Transformer and Swin Transformer models (AUC: 0.87 vs. 0.97, P = 0.01; AUC: 0.87 vs. 0.92, P = 0.04). Adding CA125 did not improve the diagnostic performance of the models in distinguishing benign and malignant ovarian tumors. The deep learning model of TVUS can be used in ovarian cancer evaluation, and its diagnostic performance is comparable to that of expert assessment.

UPGCN: User Perception-Guided Graph Convolutional Network for Multimodal Recommendation

To tackle the challenges of cold start and data sparsity in recommendation systems, an increasing number of researchers are integrating item features, resulting in the emergence of multimodal recommendation systems. Although graph convolutional network-based approaches have achieved significant success, they still face two limitations: (1) Users have different preferences for various types of features, but existing methods often treat these preferences equally or fail to specifically address this issue. (2) They do not effectively distinguish the similarity between different modality item features, overlook the unique characteristics of each type, and fail to fully exploit their complementarity. To solve these issues, we propose the user perception-guided graph convolutional network for multimodal recommendation (UPGCN). This model consists of two main parts: the user perception-guided representation enhancement module (UPEM) and the multimodal two-step enhanced fusion method, which are designed to capture user preferences for different modalities to enhance user representation. At the same time, by distinguishing the similarity between different modalities, the model filters out noise and fully leverages their complementarity to achieve more accurate item representations. We performed comprehensive experiments on the proposed model, and the results indicate that it outperforms other baseline models in recommendation performance, strongly demonstrating its effectiveness.

An Integrated TCN-CrossMHA Model for Predicting circRNA-RBP Binding Sites.

Circular RNA (circRNA) has the capacity to bind with RNA binding protein (RBP), thereby exerting a substantial impact on diseases. Predicting binding sites aids in comprehending the interaction mechanism, thereby offering insights for disease treatment strategies. Here, we propose a novel approach based on temporal convolutional network (TCN) and cross multi-head attention mechanism to predict circRNA-RBP binding sites (circTCA). First, we employ two distinct encoding methodologies to obtain two raw matrices of circRNA sequences. Then, two parallel TCN blocks extract shallow and abstract features of the two matrices separately. The fusion of the two is achieved through cross multi-head attention mechanism and after this, global expectation pooling assigns weights to the concatenated feature. Finally, the task of classifying the input sequence is entrusted to a fully connected (FC) layer. We compare circTCA with other five methods and conduct ablation experiments to demonstrate its effectiveness. We also conduct feature visualization and assess the motifs extracted by circTCA with existing motifs. All in all, circTCA is effective for binding sites prediction of circRNA and RBP.

Prediction of antibody-antigen interaction based on backbone aware with invariant point attention.

Antibodies play a crucial role in disease treatment, leveraging their ability to selectively interact with the specific antigen. However, screening antibody gene sequences for target antigens via biological experiments is extremely time-consuming and labor-intensive. Several computational methods have been developed to predict antibody-antigen interaction while suffering from the lack of characterizing the underlying structure of the antibody. Beneficial from the recent breakthroughs in deep learning for antibody structure prediction, we propose a novel neural network architecture to predict antibody-antigen interaction. We first introduce AbAgIPA: an antibody structure prediction network to obtain the antibody backbone structure, where the structural features of antibodies and antigens are encoded into representation vectors according to the amino acid physicochemical features and Invariant Point Attention (IPA) computation methods. Finally, the antibody-antigen interaction is predicted by global max pooling, feature concatenation, and a fully connected layer. We evaluated our method on antigen diversity and antigen-specific antibody-antigen interaction datasets. Additionally, our model exhibits a commendable level of interpretability, essential for understanding underlying interaction mechanisms. Quantitative experimental results demonstrate that the new neural network architecture significantly outperforms the best sequence-based methods as well as the methods based on residue contact maps and graph convolution networks (GCNs). The source code is freely available on GitHub at https://github.com/gmthu66/AbAgIPA .

Deep convolutional neural networks are sensitive to face configuration.

Deep convolutional neural networks (DCNNs) are remarkably accurate models of human face recognition. However, less is known about whether these models generate face representations similar to those used by humans. Sensitivity to facial configuration has long been considered a marker of human perceptual expertise for faces. We tested whether DCNNs trained for face identification "perceive" alterations to facial features and their configuration. We also compared the extent to which representations changed as a function of the alteration type. Facial configuration was altered by changing the distance between the eyes or the distance between the nose and mouth. Facial features were altered by replacing the eyes or mouth with those of another face. Altered faces were processed by DCNNs (Ranjan etal., 2018; Szegedy etal., 2017) and the similarity of the generated representations was compared. Both DCNNs were sensitive to configural and feature changes-with changes to configuration altering the DCNN representations more than changes to face features. To determine whether the DCNNs' greater sensitivity to configuration was due to a priori differences in the images or characteristics of the DCNN processing, we compared the representation of features and configuration between the low-level, pixel-based representations and the DCNN-generated representations. Sensitivity to face configuration increased from the pixel-level image to the DCNN encoding, whereas the sensitivity to features did not change. The enhancement of configural information may be due to the utility of configuration for discriminating among similar faces combined with the within-category nature of face identification training.

Improving CNN Fish Detection and Classification with Tracking

The regular and consistent monitoring of marine ecosystems and fish communities is becoming more and more crucial due to increasing human pressures. To this end, underwater camera technology has become a major tool to collect an important amount of marine data. As the size of the data collected outgrew the ability to process it, new means of automatic processing have been explored. Convolutional neural networks (CNNs) have been the most popular method for automatic underwater video analysis for the last few years. However, such algorithms are rather image-based and do not exploit the potential of video data. In this paper, we propose a method of coupling video tracking and CNN image analysis to perform a robust and accurate fish classification on deep sea videos and improve automatic classification accuracy. Our method fused CNNs and tracking methods, allowing us to detect 12% more individuals compared to CNN alone.

Pesticide Residue Coverage Estimation on Citrus Leaf Using Image Analysis Assisted by Machine Learning

Globally, the agricultural industry has benefited from using pesticides to minimize crop losses. Nevertheless, the indiscriminate overuse of pesticides has led to significant risks associated with a detrimental impact on the environment and human health. Therefore, emerging concerns of pesticide residue found in crops, food, and livestock are a pressing issue. To address the above challenges, there have been many efforts made towards implementing machine learning to enable precision agricultural practices to reduce pesticide overuse. As of today, there are no guiding digital tools available for citrus growers to provide pesticide residue leaf coverage analysis after foliar applications. Herein, we are the first to report software assisted by lightweight machine learning (ML) to determine the Kocide 3000 and Oxytetracycline (OTC) residue coverage on citrus leaves based on image data analysis. This tool integrates a foundational Segment Anything Model (SAM) for image preprocessing to isolate the area of interest. In addition, Kocide 3000 and Oxytetracycline (OTC) residue coverage analysis was carried out using a specialized Mask Region-Based Convolutional Neural Network (CNN). This CNN was pre-trained on the MS COCO dataset and fine-tuned by training with acquired datasets in laboratory and field conditions. The developed software demonstrated excellent performance on both pesticides’ accuracy, precision, and recall, and F1 score metrics. In summary, this tool has the potential to assist growers with the decision-making process for controlling pesticide use rate and frequency, minimizing pesticide overuse.

ECG signal reconstruction from PPG using a hybrid attention-based deep learning network

Electrocardiography (ECG) and photoplethysmography (PPG) are non-invasive methods used to quantify signals originating from the cardiovascular system. Although there is a strong correlation between the cycles of the two measures, the correlation between the waveforms has received little attention in research. Measuring the PPG is significantly simpler and more convenient compared to the ECG measure. Recent research has demonstrated that PPG signals can be utilized to rebuild the ECG signals, suggesting that healthcare professionals might acquire a comprehensive comprehension of patients' cardiovascular well-being by only measuring PPG. With the advancement of artificial intelligence, the deep learning model has made significant progress in reconstructing ECG signals from PPG signals. However, the quality of the reconstructed ECG signal is still in need of more enhancement. In order to enhance the quality of the reconstructed ECG signal, we propose an innovative hybrid attention-based bidirectional recurrent neural network (Bi-RNN) that incorporates a dilated convolutional neural network technique for the purpose of reconstructing ECG signals from PPG signals. This addresses issues that occur when standard dilated CNN (DCNN) models neglect the link between circumstances and dispersion of gradients. The suggested approach maximizes the utilization of the DCNN and Bi-RNN unit design to provide fusion features. In order to ensure the model's resilience to deformation, it is imperative to initially extract spatial properties utilizing convolutional neural networks (CNNs). Once we have obtained geographic data, we employ BiLSTM to extract temporal features. The proposed model is so-called hybrid attention-based CNN and BiLSTM (HA-CNN-BiLSTM). BiLSTM mitigates the issues of gradient vanishing and exploding while maintaining accuracy. To showcase the advantages of the suggested model, we conduct a comparison between HA-CNN-BiLSTM and each separate state-of-the-art method. The simulation results indicated that the proposed method yielded superior root mean square error (RMSE) when reconstructing the ECG signal across different optimizers. The results also demonstrated that the proposed method results in the lowest RMSE with SGDM optimizer which is 0.031.

Reliable Augmentation and Precise Identification of EPG Waveforms Based on Multi-Criteria DCGAN

The electrical penetration graph (EPG) technique is of great significance in elucidating the mechanisms of virus transmission by piercing-sucking insects and crop resistance to these insects. The traditional method of manually processing EPG signals encounters the drawbacks of inefficiency and subjectivity. This study investigated the data augmentation and automatic identification of various EPG signals, including A, B, C, PD, E1, E2, and G, which correspond to distinct behaviors exhibited by the Asian citrus psyllid. Specifically, a data augmentation method based on an improved deep convolutional generative adversarial network (DCGAN) was proposed to address the challenge of insufficient E1 waveforms. A multi-criteria evaluation framework was constructed, leveraging maximum mean discrepancy (MMD) to evaluate the similarity between the generated and real data, and singular value decomposition (SVD) was incorporated to optimize the training iterations of DCGAN and ensure data diversity. Four models, convolutional neural network (CNN), K-nearest neighbors (KNN), decision tree (DT), and support vector machine (SVM), were established based on DCGAN to classify the EPG waveforms. The results showed that the parameter-optimized DCGAN strategy significantly improved the model accuracies by 5.8%, 6.9%, 7.1%, and 7.9% for DT, SVM, KNN, and CNN, respectively. Notably, DCGAN-CNN effectively addressed the skewed distribution of EPG waveforms, achieving an optimal classification accuracy of 94.13%. The multi-criteria optimized DCGAN-CNN model proposed in this study enables reliable augmentation and precise automatic identification of EPG waveforms, holding significant practical implications for understanding psyllid behavior and controlling citrus huanglongbing.