Table Tennis Track Detection Based on Temporal Feature Multiplexing Network.

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent's attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the "feature store & return" module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models.

Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting.

Advancements in deep learning and computer vision have led to the discovery of numerous effective solutions to challenging problems in the field of agricultural automation. With the aim to improve the detection precision in the autonomous harvesting process of green asparagus, in this article, we proposed the DA-Mask RCNN model, which utilizes the depth information in the region proposal network. Firstly, the deep residual network and feature pyramid network were combined to form the backbone network. Secondly, the DA-Mask RCNN model added a depth filter to aid the softmax function in anchor classification. Afterwards, the region proposals were further processed by the detection head unit. The training and test images were mainly acquired from different regions in the basin of the Yangtze River. During the capturing process, various weather and illumination conditions were taken into account, including sunny weather, sunny but overshadowed conditions, cloudy weather, and daytime greenhouse conditions as well as nighttime greenhouse conditions. Performance experiments, comparison experiments, and ablation experiments were carried out using the five constructed datasets to verify the effectiveness of the proposed model. Precision, recall, and F1-score values were applied to evaluate the performances of different approaches. The overall experimental results demonstrate that the balance of the precision and speed of the proposed DA-Mask RCNN model outperform those of existing algorithms.

Multiple high-regional-incidence cardiac disease diagnosis with deep learning and its potential to elevate cardiologist performance.

Currently, due to lack of large-scale datasets containing multiple arrhythmias and acute coronary syndrome-related diseases, AI-aided diagnosis for cardiac diseases is limited in clinical scenarios. Whether AI-based ECG diagnosis can assist cardiologists to improve performance has not been reported. We constructed a large-scale dataset containing multiple high-regional-incidence arrhythmias and ACS-related diseases, including 162,622 12-lead ECGs collected between January 2018 and March 2021. We presented a deep learning model for clinical ECG diagnosis of multiple cardiac diseases. Results show that our model for diagnosing 15 cardiac abnormalities achieved 88.216% accuracy, and its average AUC ROC score reached 0.961. On the board-certified re-annotated dataset, its performance surpasses that of cardiologists in non-reference group. Moreover, with aid of labels given by our model, accuracy and efficiency for cardiologist increased by 13.5% and 69.9% than non-reference group. Our approach provides solutions for AI-aided diagnosis systems of cardiac diseases in applications.

A novel P-QRS-T wave localization method in ECG signals based on hybrid neural networks.

As the number of people suffering from cardiovascular diseases increases every year, it becomes essential to have an accurate automatic electrocardiogram (ECG) diagnosis system. Researchers have adopted different methods, such as deep learning, to investigate arrhythmias classification. However, the importance of ECG waveform features is generally ignored when deep learning approaches are applied to classification tasks. P-wave, QRS-wave, and T-wave, containing plenty of physiological information, are three critical waves in the ECG heartbeat. The accurate localization of these critical ECG wave components is a prerequisite for ECG classification and diagnosis. In this study, a novel P-QRS-T wave localization method based on hybrid neural networks is proposed. The raw ECG signal is preprocessed sequentially by filtering, heartbeat extraction, and data standardization. The hybrid neural network is constructed by combining the residual neural network (ResNet) and the Long Short-Term Memory (LSTM). It predicts the relative positions of the P-peak, QRS-peak, and T-peak for each heartbeat. The proposed algorithm was validated on four ECG databases with input noise of different signal-to-noise ratio (SNR) levels. The results show that the proposed method can accurately predict the positions of the three key waves. The proposed P-QRS-T localization approach can improve the efficiency of ECG delineation. Integrated with cardiac disease classification methods, it can contribute to the development of advanced automatic ECG diagnosis systems.

An incremental learning system for atrial fibrillation detection based on transfer learning and active learning.

BACKGROUND AND OBJECTIVE: Atrial fibrillation (AF) is a type of arrhythmia with high incidence. Automatic AF detection methods have been studied in previous works. However, a model cannot be used all the time without any improvement. And updating model requires adequate data and cost. Therefore, this study aims at finding a low-cost way to choose learning samples and developing an incremental learning system for AF detection. METHODS: Based on transfer learning and active learning, this paper proposed a loop-locked framework integrating AF diagnose, label query, and model fine-tuning. In the pre-training stage, a novel multiple-input deep neural network (MIDNN) is pre-trained using labeled samples from an original training set. In practical application, the model can be used for AF detection. Meanwhile, continuous data is collected to form the candidate set. In the incremental learning stage, the model was fine-tuned continuously by the most informative samples in the candidate set. These samples are selected from the candidate set based on the pre-trained model and a new active learning strategy. The strategy combines the features and the uncertainty of the predicted results. RESULTS: In order to evaluate the method, the MIT-BIH atrial fibrillation database was used for pre-training and samples of the MIT-BIH arrhythmia database were taken as candidate set. The initial values of Acc, Sen, and PPV were 87.40%, 97.46%, and 81.11%. These indexes reached to the top values of 97.53%, 100.00%, and 95.29% after 14 iterations. Hence, the number of queries was saved by 90.67%. CONCLUSIONS: The proposed system is able to update the model continuously and reduce the labeling cost over 90%. The comparisons demonstrated the effectiveness of MIDNN model and the suitability of novel learning strategy for AF. Moreover, this framework can be extended to other biomedical applications.

Intelligent Fault Diagnosis of Diesel Engines via Extreme Gradient Boosting and High-Accuracy Time-Frequency Information of Vibration Signals.

Accurate and timely misfire fault diagnosis is of vital significance for diesel engines. However, existing algorithms are prone to fall into model over-fitting and adopt low energy-concentrated features. This paper presents a novel extreme gradient boosting-based misfire fault diagnosis approach utilizing the high-accuracy time-frequency information of vibration signals. First, diesel engine misfire tests were conducted under different spindle speeds, and the corresponding vibration signals were acquired via a triaxial accelerometer. The time-domain features of signals were extracted by using a time-domain statistics method, while the high-accuracy time-frequency domain features were obtained via the high-resolution multisynchrosqueezing transform. Thereafter, considering the nonlinearity and high dimensionality of the original characteristic data sets, the locally linear embedding method was employed for feature dimensionality reduction. Eventually, to avoid model overfitting, the extreme gradient boosting algorithm was utilized for diesel engine misfire fault diagnosis. Experiments under different spindle speeds and comprehensive comparisons with other evaluation methods were conducted to demonstrate the effectiveness of the proposed extreme gradient boosting-based misfire diagnosis method. The results verify that the highest classification accuracy of the proposed extreme gradient boosting-based algorithm is up to 99.93%. Simultaneously, the classification accuracy of the presented approach is approximately 24.63% higher on average than those of algorithms that use wavelet packet-based features. Moreover, it is shown that it obtains the minimum root mean squared error and can effectively prevent the model from falling into overfitting.

A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification.

BACKGROUND AND OBJECTIVE: Electrocardiogram (ECG) is a useful tool for detecting heart disease. Automated ECG diagnosis allows for heart monitoring on small devices, especially on wearable devices. In order to recognize arrhythmias automatically, accurate classification method for electrocardiogram (ECG) heartbeats was studied in this paper. METHODS: Based on weighted extreme gradient boosting (XGBoost), a hierarchical classification method is proposed. A large number of features from 6 categories are extracted from the preprocessed heartbeats. Then recursive feature elimination is used for selecting features. Afterwards, a hierarchical classifier is constructed in classification stage. The hierarchical classifier is composed of threshold and XGBoost classifiers. And the XGBoost classifiers are improved with weights. RESULTS: The method was applied to an inter-patient experiment conforming AAMI standard. The obtained sensitivities for normal (N), supraventricular (S), ventricular (V), fusion (F), and Unknown beats (Q) were 92.1%, 91.7%, 95.1%, and 61.6%. Positive predictive values of 99.5%, 46.2%, 88.1%, and 15.2% were also provided for the four classes. CONCLUSIONS: XGBoost was improved and firstly introduced in single heartbeat classification. A comparison showed the effectiveness of the novel method. The method was more suitable for clinical application as both high positive predictive value for N class and high sensitivities for abnormal classes were provided.