Search Results

Resource reconfiguration can integrate and optimize manufacturing resources (MRs) into various resource sets, enhancing overall resource management in cloud manufacturing (CM). However, achieving efficient resource reconfiguration remains ...

Segmentation models for thyroid ultrasound images are challenged by domain gaps across multi-center data. Some methods have been proposed to address this issue by enforcing consistency across multi-domains or by simulating domain gaps using ...

Despite the significant advancements that deep learning has brought to single image super-resolution (SISR), challenges persist in the real world due to unknown degradation and the lack of ground truth priors, rendering existing fully supervised ...

• Introduced Zero-Shot Domain Translation (ZSDT) framework for real-world SISR.
• Utilized Gradient Adaptive Coordinate Attention (GACA) for better domain translation.
• Proposed Diffusion-Guided Local High-Frequency Data Augmentation (...

In the treatment of malocclusion, continuous monitoring of the three-dimensional relationship between dental roots and the surrounding alveolar bone is essential for preventing complications from orthodontic procedures. Cone-beam ...

Display Omitted

• The first deep learning based orthodontic system to continuous risk monitoring.
• Cross-temporal fusion framework for multimodal medical imaging registration.
• Novel registration method based on segmentation for internal structure ...

The DeepFake, which generates synthetic content, has sparked a revolution in the fight against deception and forgery. However, most existing DeepFake detection methods mainly focus on improving detection performance with high-quality data while ...

• We explore the difference between uncompressed and high- compressed deepfake data.
• A High-Frequency Enhancement network is proposed for deepfake detection.
• A two-stage cross-fusion strategy is designed for information ...

The harmful utilization of DeepFake technology poses a significant threat to public welfare, precipitating a crisis in public opinion. Existing detection methodologies, predominantly relying on convolutional neural networks and deep learning ...

• We build an artifact and texture inconsistency detector for deepfake detection.
• Texture coherence is analyzed via a novel mask extraction method and an autoencoder.
• The use of an ensemble training strategy improved the ability to ...

The current deep learning-based intelligent diagnosis algorithms depend on large amounts of well-labeled data, but they may not perform well in engineering practice where the fault data available from a single device is limited. The significant ...

• A cross-device fault transfer diagnosis method for rolling bearings is proposed.
• A multi-domain feature extractor is built to fully mine key fault information.
• A multi-domain feature deep fusion strategy based on BiGRU is designed.

Working remotely and collaborating with colleagues online has become a prevailing trend. The user experience with various collaboration tools, such as teleconferencing platforms, online whiteboards, and virtual reality, plays a pivotal role in ...

Document-level relation extraction (RE) aims to simultaneously predict relations (including no-relation cases denoted as NA) between all entity pairs in a document. It is typically formulated as a relation classification task with entities pre-detected in ...

Based on multimodal and low-carbon transportation both domestically and internationally, combined with carbon tax policies, this article conducts empirical research on the transportation of goods in the Yangtze River Delta region. A dual objective model ...

This paper investigates the problem of mainlobe deceptive jammer suppression via joint transmit–receive design in a multiple-input multiple-output (MIMO) radar. At the design stage, a discrete element-pulse coding (DEPC) phase is implemented in ...

• The DEPC-MIMO scheme is proposed by discretizing element pulse coding coefficients.
• The true and false targets are distinguished in the transmit–receive spatial domain.
• The false targets are suppressed by optimizing DEPC ...

Teaching incentives are important in teaching and training. However, in traditional online teaching and training due to the characteristics of non-disclosure and non-transparency of information, students cannot be encouraged to learn well. In order to ...

With ChatGPT’s release, conversational prompting has become the most popular form of human-LLM interaction. However, its effectiveness is limited for more complex tasks involving reasoning, creativity, and iteration. Through a systematic analysis of HCI ...

Large language models (LLMs) stand to reshape traditional methods of working with data. While LLMs unlock new and potentially useful ways of interfacing with data, their use in research processes requires methodological and critical evaluation. In this ...

The deliberative potential of online platforms has been widely examined. However, little is known about how various interface-based reflection nudges impact the quality of deliberation. This paper presents two user studies with 12 and 120 participants, ...

Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both complex and costly. To lower this bar, we take a theoretical ...

In recent years, emerging evidence has revealed a strong association between dysregulations of long non-coding RNAs (lncRNAs) and sophisticated human diseases. Biological experiments are adequate to identify such associations, but they are costly ...

• NFMCLDA uses miRNA information as the transition path and effectively integrates multi-source association data.
• An unbalanced random walk method on three-layer heterogeneous network is adopted in preprocessing.
• This method ...

• An isogeometric Bézier element data structure for an efficient ITO method is constructed.
• An open-source MATLAB toolbox B-ITO with a higher efficiency is developed for the ITO method.
• An updated version of the B-ITO toolbox with a ...

The Bézier extraction can decompose the NURBS-based isogeometric analysis (IGA) elements into a series of Bézier elements with C⁰ continuity, which is considered into developing a higher efficient isogeometric topology optimization (ITO) method. ...

Lysosomes serve as regulatory hubs, and play a pivotal role in human diseases. However, the precise functions and mechanisms of action of lysosome-related genes remain unclear in preeclampsia and cancers. This study aimed to identify ...

Display Omitted

• Eleven DELRGs were systematically identified, which exhibit potential value for molecular clusters of PE.
• Machine learning and WGCNA methods identify GBA, OCRL, TLR7, and HEXB as lysosome related diagnostic biomarkers in PE.
• Pan-...

The application of ultrasound (US) image has been limited by its limited resolution, inherent speckle noise, and the impact of clutter and artifacts, especially in the miniaturized devices with restricted hardware conditions. In order to solve ...

• A joint constraint deconvolution method is proposed.
• Based on Nyquist sampling, neighboring pixels of ultrasound image are continuous.
• Based on the relative sparsity, high-frequency information is extracted.
• Continuity and ...