Addressing the challenges in detecting surface defects on ceramic disks, such as difficulty in detecting small defects, variations in defect sizes, and inaccurate defect localization, we propose an enhanced YOLOv5s algorithm. Firstly, we improve the anchor frame structure of the YOLOv5s model to enhance its generalization ability, enabling robust defect detection for objects of varying sizes. Secondly, we introduce the ECA attention mechanism to improve the model\'s accuracy in detecting small targets. Under identical experimental conditions, our enhanced YOLOv5s algorithm demonstrates significant improvements, with precision, F1 scores, and mAP values increasing by 3.1 %, 3 %, and 4.5 % respectively. Moreover, the accuracy in detecting crack, damage, slag, and spot defects increases by 0.2 %, 4.7 %, 5.4 %, and 1.9 % respectively. Notably, the detection speed improves from 232 frames/s to 256 frames/s. Comparative analysis with other algorithms reveals superior performance over YOLOv3 and YOLOv4 models, showcasing enhanced capability in identifying small target defects and achieving real-time detection.

Protein-peptide interactions (PPepIs) are vital to understanding cellular functions, which can facilitate the design of novel drugs. As an essential component in forming a PPepI, protein-peptide binding sites are the basis for understanding the mechanisms involved in PPepIs. Therefore, accurately identifying protein-peptide binding sites becomes a critical task. The traditional experimental methods for researching these binding sites are labor-intensive and time-consuming, and some computational tools have been invented to supplement it. However, these computational tools have limitations in generality or accuracy due to the need for ligand information, complex feature construction, or their reliance on modeling based on amino acid residues. To deal with the drawbacks of these computational algorithms, we describe a geometric attention-based network for peptide binding site identification (GAPS) in this work. The proposed model utilizes geometric feature engineering to construct atom representations and incorporates multiple attention mechanisms to update relevant biological features. In addition, the transfer learning strategy is implemented for leveraging the protein-protein binding sites information to enhance the protein-peptide binding sites recognition capability, taking into account the common structure and biological bias between proteins and peptides. Consequently, GAPS demonstrates the state-of-the-art performance and excellent robustness in this task. Moreover, our model exhibits exceptional performance across several extended experiments including predicting the apo protein-peptide, protein-cyclic peptide and the AlphaFold-predicted protein-peptide binding sites. These results confirm that the GAPS model is a powerful, versatile, stable method suitable for diverse binding site predictions.

Amid the wave of globalization, the phenomenon of cultural amalgamation has surged in frequency, bringing to the fore the heightened prominence of challenges inherent in cross-cultural communication. To address these challenges, contemporary research has shifted its focus to human-computer dialogue. Especially in the educational paradigm of human-computer dialogue, analysing emotion recognition in user dialogues is particularly important. Accurately identify and understand users\' emotional tendencies and the efficiency and experience of human-computer interaction and play. This study aims to improve the capability of language emotion recognition in human-computer dialogue. It proposes a hybrid model (BCBA) based on bidirectional encoder representations from transformers (BERT), convolutional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and the attention mechanism. This model leverages the BERT model to extract semantic and syntactic features from the text. Simultaneously, it integrates CNN and BiGRU networks to delve deeper into textual features, enhancing the model\'s proficiency in nuanced sentiment recognition. Furthermore, by introducing the attention mechanism, the model can assign different weights to words based on their emotional tendencies. This enables it to prioritize words with discernible emotional inclinations for more precise sentiment analysis. The BCBA model has achieved remarkable results in emotion recognition and classification tasks through experimental validation on two datasets. The model has significantly improved both accuracy and F1 scores, with an average accuracy of 0.84 and an average F1 score of 0.8. The confusion matrix analysis reveals a minimal classification error rate for this model. Additionally, as the number of iterations increases, the model\'s recall rate stabilizes at approximately 0.7. This accomplishment demonstrates the model\'s robust capabilities in semantic understanding and sentiment analysis and showcases its advantages in handling emotional characteristics in language expressions within a cross-cultural context. The BCBA model proposed in this study provides effective technical support for emotion recognition in human-computer dialogue, which is of great significance for building more intelligent and user-friendly human-computer interaction systems. In the future, we will continue to optimize the model\'s structure, improve its capability in handling complex emotions and cross-lingual emotion recognition, and explore applying the model to more practical scenarios to further promote the development and application of human-computer dialogue technology.

As the diversity and volume of images continue to grow, the demand for efficient fine-grained image retrieval has surged across numerous fields. However, the current deep learning-based approaches to fine-grained image retrieval often concentrate solely on the top-layer features, neglecting the relevant information carried in the middle layer, even though these information contains more fine-grained identification content. Moreover, these methods typically employ a uniform weighting strategy during hash code mapping, risking the loss of critical region mapping-an irreversible detriment to fine-grained retrieval tasks. To address the above problems, we propose a novel method for fine-grained image retrieval that leverage feature fusion and hash mapping techniques. Our approach harnesses a multi-level feature cascade, emphasizing not just top-layer but also intermediate-layer image features, and integrates a feature fusion module at each level to enhance the extraction of discriminative information. In addition, we introduce an agent self-attention architecture, marking its first application in this context, which steers the model to prioritize on long-range features, further avoiding the loss of critical regions of the mapping. Finally, our proposed model significantly outperforms existing state-of-the-art, improving the retrieval accuracy by an average of 40% for the 12-bit dataset, 22% for the 24-bit dataset, 16% for the 32-bit dataset, and 11% for the 48-bit dataset across five publicly available fine-grained datasets. We also validate the generalization ability and performance stability of our proposed method by another five datasets and statistical significance tests. Our code can be downloaded from https://github.com/BJFU-CS2012/MuiltNet.git.

Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.

Organ segmentation is a crucial task in various medical imaging applications. Many deep learning models have been developed to do this, but they are slow and require a lot of computational resources. To solve this problem, attention mechanisms are used which can locate important objects of interest within medical images, allowing the model to segment them accurately even when there is noise or artifact. By paying attention to specific anatomical regions, the model becomes better at segmentation. Medical images have unique features in the form of anatomical information, which makes them different from natural images. Unfortunately, most deep learning methods either ignore this information or do not use it effectively and explicitly. Combined natural intelligence with artificial intelligence, known as hybrid intelligence, has shown promising results in medical image segmentation, making models more robust and able to perform well in challenging situations. In this paper, we propose several methods and models to find attention regions in medical images for deep learning-based segmentation via non-deep-learning methods. We developed these models and trained them using hybrid intelligence concepts. To evaluate their performance, we tested the models on unique test data and analyzed metrics including false negatives quotient and false positives quotient. Our findings demonstrate that object shape and layout variations can be explicitly learned to create computational models that are suitable for each anatomic object. This work opens new possibilities for advancements in medical image segmentation and analysis.

Cracks in tunnel lining structures constitute a common and serious problem that jeopardizes the safety of traffic and the durability of the tunnel. The similarity between lining seams and cracks in terms of strength and morphological characteristics renders the detection of cracks in tunnel lining structures challenging. To address this issue, a new deep learning-based method for crack detection in tunnel lining structures is proposed. First, an improved attention mechanism is introduced for the morphological features of lining seams, which not only aggregates global spatial information but also features along two dimensions, height and width, to mine more long-distance feature information. Furthermore, a mixed strip convolution module leveraging four different directions of strip convolution is proposed. This module captures remote contextual information from various angles to avoid interference from background pixels. To evaluate the proposed approach, the two modules are integrated into a U-shaped network, and experiments are conducted on Tunnel200, a tunnel lining crack dataset, as well as the publicly available crack datasets Crack500 and DeepCrack. The results show that the approach outperforms existing methods and achieves superior performance on these datasets.

The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model\'s generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels.

Joint source-channel coding (JSCC) based on deep learning has shown significant advancements in image transmission tasks. However, previous channel-adaptive JSCC methods often rely on the signal-to-noise ratio (SNR) of the current channel for encoding, which overlooks the neural network\'s self-adaptive capability across varying SNRs. This paper investigates the self-adaptive capability of deep learning-based JSCC models to dynamically changing channels and introduces a novel method named Channel-Blind JSCC (CBJSCC). CBJSCC leverages the intrinsic learning capability of neural networks to self-adapt to dynamic channels and diverse SNRs without relying on external SNR information. This approach is advantageous, as it is not affected by channel estimation errors and can be applied to one-to-many wireless communication scenarios. To enhance the performance of JSCC tasks, the CBJSCC model employs a specially designed encoder-decoder. Experimental results show that CBJSCC outperforms existing channel-adaptive JSCC methods that depend on SNR estimation and feedback, both in additive white Gaussian noise environments and under slow Rayleigh fading channel conditions. Through a comprehensive analysis of the model\'s performance, we further validate the robustness and adaptability of this strategy across different application scenarios, with the experimental results providing strong evidence to support this claim.

A new algorithm, Yolov8n-FADS, has been proposed with the aim of improving the accuracy of miners\' helmet detection algorithms in complex underground environments. By replacing the head part with Attentional Sequence Fusion (ASF) and introducing the P2 detection layer, the ASF-P2 structure is able to comprehensively extract the global and local feature information of the image, and the improvement in the backbone part is able to capture the spatially sparsely distributed features more efficiently, which improves the model\'s ability to perceive complex patterns. The improved detection head, SEAMHead by the SEAM module, can handle occlusion more effectively. The Focal Loss module can improve the model\'s ability to detect rare target categories by adjusting the weights of positive and negative samples. This study shows that compared with the original model, the improved model has 29% memory compression, a 36.7% reduction in the amount of parameters, and a 4.9% improvement in the detection accuracy, which can effectively improve the detection accuracy of underground helmet wearers, reduce the workload of underground video surveillance personnel, and improve the monitoring efficiency.