Abstract ：

Retinal diseases such as age-related macular degeneration and diabetic macular edema will lead to irreversible blindness without timely diagnosis and treatment. Optical coherence tomography (OCT) has been widely utilized to detect retinal diseases because of its non-contact and non-invasive imaging peculiarities. Due to the lack of ophthalmic medical resources, automatic analyzing and diagnosing retinal OCT images is necessary with computer-aided diagnosis algorithms. In this study, we propose a lightweight retinal OCT image classification model integrating convolutional neural network (CNN) and Transformer to classify various retinal diseases with few parameters of the model. Local lesion features extracted by CNN can be encoded with the whole OCT image through the Transformer, which improves the classification ability. A convolutional block attention module is also integrated into our model to enhance the representational power. Compared with several classical models, our model achieves the best accuracy of 0.9800 and recall of 0.9799 with the least number of parameters and prediction time for an image on the OCT-C8 dataset. Moreover, on the OCT2017 dataset, our model outperforms the four state-of-the-art models except almost equal to another, achieving an average accuracy, precision, recall, specificity and F1-score of 0.9985, 0.9970, 0.9970, 0.9990, and 0.9970. Simultaneously, the number of parameters of our model has been reduced to just 1.28 M, and the average prediction time for an image is only 2.5 ms. © 2024 Elsevier Ltd

Keyword ：

Ophthalmology Optical coherence tomography Convolutional neural networks

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The bolted joint is an important link that affects the accuracy maintenance of the heavy-duty machine tool. Due to bolts of the crossbeam are under a preload of several hundred kN for an extended period, the bolt gradually creeps and elongates as the machine tool's service time increases. This relaxation of the preload results in a degradation of the bolted stiffness, weakening the dynamic response of the bolted joint system. To reveal that the degradation law of crossbeam bolting performance of the heavy-duty machine tool induced by bolt creep, based on the NortonBailey(NB) model, a method for analyzing the creep of bolts with precision threads is proposed, and the influence of thread geometry and friction coefficient on the creep stress relaxation of bolts is studied. Considering the interface contact, an interface contact stiffness model is derived based on fractal theory. The dynamic equation of the bolted beam system is established using the Matrix27 stiffness matrix. The dynamic response of the bolted system, resulting from the degradation of interface stiffness due to bolt creep, is analyzed. The results show that the stress relaxation of bolt creep is not only related to creep parameters, but also related to the mate-thread interaction. The dynamic model with Matrix27 stiffness matrix is comparable to experiment in calculation accuracy and efficiency, which provides technical guidance for machine tool dynamics analysis and effectively solves the scientific problem of beam bolting performance degradation during the service of heavy-duty machine tools.

Keyword ：

Dynamic response of the crossbeam Pre-tightening force relaxation Bolted joint system Heavy-duty machine tools Creep

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Lung cancer stands as the leading cause of cancer related mortality worldwide. Precise and automated identification of lung nodules through 3D Computed Tomography (CT) scans is an essential part of screening for lung cancer effectively. Due to the small size of pulmonary nodules and the close correlation between neighboring slices of 3D CT images, most of the existing methods only consider the characteristics of a single slice, thus easily lead to insufficient detection accuracy of pulmonary nodules. To solve this problem, this paper proposes a Channel Shuffle Slice-Aware Network (CSSANet), which aims to fully exploit the spatial correlation between slices and effectively utilize the intra-slice features and inter-slice contextual information to achieve accurate detection of lung nodules. Specifically, we design a Group Shuffle Attention module (GSA module) to fuse the inter-slice feature in order to enhance the discrimination and extraction of corresponding shape information of distinct nodules in the same group of slices. Experiments and ablation study on a publicly available LUNA16 dataset demonstrate that the proposed method can enhance the detection sensitivity effectively. The Competition Performance Metric (CPM) score of 89.8 % is superior over other representative detection models. © 2024

Keyword ：

Pulmonary diseases Lung cancer Image correlation Diagnosis Computerized tomography

Cite：

Copy from the list or Export to your reference management。

Abstract ：

A Sybil attack involves a Malicious vehicle node stealing fake identities to continuously generate fake vehicles on the road, creating an illusion of congestion and interfering with the normal traffic flow of legitimate vehicles. In the current traffic environment, vehicles cannot perform real-time authentication, allowing highly stealthy Malicious vehicle nodes to continue attacking and significantly impact traffic. Given the rapidly changing network topology in vehicular networks, high precision and speed are required for attack detection methods. This paper proposes a three-class classification method for Sybil vehicles, Malicious vehicles, and Normal vehicles based on BSM packets. This method utilizes multiple features and employs a sliding window with the Random Forest algorithm for classification. Compared with deep learning methods, this method has the advantages of strong interpretability and fast detection speed. Experiments demonstrate that this method achieves fast detection speeds and high accuracy. With a window size of 2, the method achieves precision and recall both greater than 94%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Keyword ：

Decision trees Traffic congestion Deep learning Vehicular ad hoc networks

Cite：

Copy from the list or Export to your reference management。

Abstract ：

This paper presents a deep learning-based topology optimization method for the joint design of material layout and fiber orientation in continuous fiber-reinforced composite structure (CFRCS). The proposed method mainly includes three steps: (1) a ResUNet-involved generative and adversarial network (ResUNet-GAN) is developed to establish the end-to-end mapping from structural design parameters to fiber-reinforced composite optimized structure, and a fiber orientation chromatogram is presented to represent continuous fiber angles; (2) to avoid the local optimum problem, the independent continuous mapping method (ICM method) considering the improved principal stress orientation interpolated continuous fiber angle optimization (PSO-CFAO) strategy is utilized to construct CFRCS topology optimization dataset; (3) the well-trained ResUNet-GAN is deployed to design the optimal structural material distribution together with the corresponding continuous fiber orientations. Numerical simulations for benchmark structure verify that the proposed method greatly improves the design efficiency of CFRCS along with high design accuracy. Furthermore, the CFRCS topology configuration designed by ResUNet-GAN is fabricated by additive manufacturing. Compression experiments of the specimens show that both the stiffness structure and peak load of the CFRCS topology configuration designed by the proposed method have significantly enhanced. The proposed deep learning-based topology optimization method will provide great flexibility in CFRCS for engineering applications. © The Chinese Society of Theoretical and Applied Mechanics and Springer-Verlag GmbH Germany, part of Springer Nature 2024.

Keyword ：

High modulus textile fibers Shape optimization Structural optimization Benchmarking Topology Structural dynamics Composite structures

Cite：

Copy from the list or Export to your reference management。

Abstract ：

This research aims to explore the complex dynamics governing the correlation between oil futures prices and Chinese agricultural futures prices, with a specific emphasis on unveiling the crucial role played by oil futures prices in predicting the trajectory of agricultural futures prices. The study utilizes the Vector Error Correction-Dynamic Conditional Correlation-Multivariate Generalized Autoregressive Conditional Heteroskedasticity (VEC-DCC-MGARCH) model to dissect the interplay among oil, soybean, and corn price series. Additionally, this study integrates the innovative Spatio-temporal Information Recombination Hypergraph Neural Network (STIR-HGNN) model to analyze how oil futures prices contribute to improving the accuracy of forecasting agricultural product prices. Findings indicate numerous connections between oil prices and agricultural futures prices, highlighting the significant role of oil prices in forecasting agricultural futures price movements. The empirical insights derived from this study serve as a valuable compass for futures market participants, urging them to leverage these findings to refine and optimize their market strategies, enhancing their capacity to navigate and capitalize on the intricate complexities inherent in these interconnected markets.

Keyword ：

Oil futures markets Agricultural futures prices forecast STIR-HGNN model VEC-DCC-MGARCH model

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Intelligent controllers based on the broad learning system can simplify the process of model parameter adjustment, finding wide applications in the motion control of multi-joint robotic arms. However, motion controllers for multi-joint robotic arms based on broad learning system exhibit insufficient precision and overlook the impact of joint motion commonalities on controller design. Therefore, this paper proposes a novel motion control strategy for a multi-joint robotic arm based on a deep cascade feature-enhancement gated Bayesian broad learning system. Firstly, the motion controller of the deep cascade feature-enhancement Bayesian broad learning system is constructed to enhance the robotic arm motion control precision. Secondly, an incremental node generation module with an attention-gated mechanism is constructed to capture the unique motion characteristics of the target joints, which is further combined with model generalization to simplify the motion control process of the multi-joint robotic arm. Finally, controller convergence is enhanced by combining it with the Lyapunov theory to constrain the learning parameters. Simulations and physical experiments are designed to verify the feasibility and superiority of the proposed motion control strategy. The results demonstrated that the strategy improved the accuracy of robotic arm motion control, with the root mean square error in position tracking reduced to 0.0019 rad. This represents a 93.39% reduction in error compared to existing techniques.

Keyword ：

Attention-gated mechanism Intelligent manufacturing Broad learning system Multi-joint robotic arm control Motion controller

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Personalized federated learning (PFL) addresses the significant challenge of non-independent and identically distributed (non-IID) data across clients in federated learning (FL). Our proposed framework, "FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with Strategic Client Selection", marks a notable advancement in this domain. By integrating dynamic learning rate adjustments and a strategic client selection mechanism, our approach effectively mitigates the challenges posed by non-IID data while enhancing model personalization, fairness, and efficiency. We evaluated FairDPFL-SCS using standard datasets, including MNIST, FashionMNIST, and SVHN, employing architectures like VGG and CNN. Our model achieved impressive results, attaining 99.04% accuracy on MNIST, 89.19% on FashionMNIST, and 90.9% on SVHN. These results represent a substantial improvement over existing methods, including a highest increase of 16.74% inaccuracy on SVHN when compared to the best-performing benchmark methods. In particular, our method also demonstrated lower fairness variance, presenting the importance of fairness in model personalization, a frequently overlooked aspect in FL research. Through extensive experiments, we validate the superior performance of FairDPFL-SCS compared to benchmark PFL approaches, highlighting significant improvements over state-of-the-art methods. This work represents a promising step forward in the field of federated learning, offering a comprehensive solution to the challenges presented by non-IID data while prioritizing fairness and efficiency in model personalization.

Keyword ：

Client selection Personalized federated learning Dynamic learning Model optimization Fairness

Cite：

Copy from the list or Export to your reference management。

Abstract ：

For software evolution, user feedback has become a meaningful way to improve applications. Recent studies show a significant increase in analyzing end-user feedback from various social media platforms for software evolution. However, less attention has been given to the end-user feedback for low-rating software applications. Also, such approaches are developed mainly on the understanding of human annotators who might have subconsciously tried for a second guess, questioning the validity of the methods. For this purpose, we proposed an approach that analyzes end-user feedback for low-rating applications to identify the end-user opinion types associated with negative reviews (an issue or bug). Also, we utilized Generative Artificial Intelligence (AI), i.e., ChatGPT, as an annotator and negotiator when preparing a truth set for the deep learning (DL) classifiers to identify end-user emotion. For the proposed approach, we first used the ChatGPT Application Programming Interface (API) to identify negative end-user feedback by processing 71853 reviews collected from 45 apps in the Amazon store. Next, a novel grounded theory is developed by manually processing end-user negative feedback to identify frequently associated emotion types, including anger, confusion, disgust, distrust, disappointment, fear, frustration, and sadness. Next, two datasets were developed, one with human annotators using a content analysis approach and the other using ChatGPT API with the identified emotion types. Next, another round is conducted with ChatGPT to negotiate over the conflicts with the human-annotated dataset, resulting in a conflict-free emotion detection dataset. Finally, various DL classifiers, including LSTM, BILSTM, CNN, RNN, GRU, BiGRU and BiRNN, are employed to identify their efficacy in detecting end-users emotions by preprocessing the input data, applying feature engineering, balancing the data set, and then training and testing them using a cross-validation approach. We obtained an average accuracy of 94%, 94%, 93%, 92%, 91%, 91%, and 85%, with LSTM, BILSTM, RNN, CNN, GRU, BiGRU and BiRNN, respectively, showing improved results with the truth set curated with human and ChatGPT. Using ChatGPT as an annotator and negotiator can help automate and validate the annotation process, resulting in better DL performances. © 2024 Elsevier Ltd

Keyword ：

Input output programs Application programs Emotion Recognition Software testing Requirements engineering Deep learning

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The fatigue crack growth simulation and life prediction of structures are implemented in this paper based on the physics-informed neural networks (PINNs). Firstly, the enhanced PINNs are proposed by introducing the crack tip asymptotic displacement fields, so that the crack tip stress intensity factors can be calculated accurately even when the number of collocation points is small and the distribution grid is regular. The enhanced PINNs essentially transform the solution of elastic body containing crack into the optimization of minimizing the constructed loss functions, and can invert the fracture parameters. Then, an automatic crack propagation simulation method is developed based on the enhanced PINNs. The network architecture and the overall node distribution can be unchanged during the crack propagation process, and only new crack surfaces need to be processed and corresponding loss functions need to be modified. Because the nodal refinement around crack-tip is not required, this simulation method is convenient and can accurately predict the mixed -mode crack propagation path. Finally, the fatigue crack growth life algorithm considering overload is developed, where the effect of each overload can be captured by the cycle -by -cycle method. Based on this algorithm, the retardation behavior can be characterized and the fatigue life of structure under the load spectrum with periodic overloads can be accurately predicted. The sufficient examples are given to verify the feasibility and accuracy of the method proposed in this paper.

Keyword ：

Fatigue crack growth life Overload effect Stress intensity factors Crack propagation simulation Physics-informed neural networks

Cite：

Copy from the list or Export to your reference management。