Search Results

The 4D auto-labeling system, with its potential to enhance data annotation efficiency for 3D object detection, has garnered significant attention. However, its adoption has been hampered by the high costs associated with temporally annotated long-...

In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods primarily ...

Glaucoma is one of the leading causes of vision impairment. Digital imaging techniques, such as color fundus photography (CFP) and optical coherence tomography (OCT), provide quantitative and noninvasive methods for glaucoma diagnosis. Recently, ...

As traditional credit evaluation methods generally only use accepted sample modeling, the rejected data is omitted, which means the model's prediction of new customers is biased. However, reject inference can be used to solve this credit ...

Federated learning (FL) is an emerging distributed optimization paradigm that learns from data samples distributed across many clients with data privacy protection in the artificial intelligence of things (AIoT). Adaptive client selection can ...

The thickness of the coating layer of coated fuel particles plays a vital role in the reliable operation of a high-temperature gas-cooled reactor. Coating thickness remains extremely challenging to measure it efficiently, accurately, and ...

• An encoder-decoder segmentation network is proposed for coated fuel particle image segmentation.
• A designed context fusion module is proposed to capture multiscale contextual information.
• A boundary refinement module is introduced ...

Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution. In the past few decades, numerous methods have been proposed to find Pareto ...

Recently, deep multi-view clustering leveraging autoencoders has garnered significant attention due to its ability to simultaneously enhance feature learning capabilities and optimize clustering outcomes. However, existing autoencoder-based deep ...

• This work provides a new model framework for predicting grain yield.
• Combining spectral data and RGB images to develop the fusion models of grain yield.
• Multi-source remotely sensed data can improve the estimation accuracy of rice ...

Predicting rice grain yield using multi-source remotely sensed data is crucial for improving prediction accuracy, optimizing nitrogen management, and advancing precision agricultural development. However, the feasibility and reliability of using ...

• Investigated the optimization decision problem for HES under uncertainty.
• Introduced a novel two-stage MILP model for HES operations.
• Proposed a unique meta-heuristic methodology.
• Presented real-world case study insights for ...

The rapid expansion of high-speed railway (HSR) networks has elevated the HSR express system, which combines road and HSR transport, as a notable intermodal transport choice. This research delves into the optimization challenges present in the ...

• Address the decision for hydrogen refueling stations network under various scenarios.
• The location and size of hydrogen refueling stations are considered in decision.
• A two-stage mixed-integer linear programming model is ...

Hydrogen refueling stations (HRS) are essential for the growth of the hydrogen energy and fuel cell vehicle industry, making the strategic decision of their location and scale critical. This study advances the HRS location optimization problem by ...

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this ...

• We address the service assignment and transportation problem in cloud manufacturing.
• Hybrid hub-and-spoke network is considered.
• A mixed integer programming model is established.
• A column generation-based algorithm is proposed ...

Cloud-based manufacturing has gained significant attention in academia and industry, presenting opportunities for enhanced operational efficiency. This paper addresses two critical challenges in cloud manufacturing: service assignment and ...

The emergence of single-cell RNA sequencing (scRNA-seq) technology makes it possible to measure DNA, RNA, and protein in a single cell. Cellular Indexing of Transcriptomes and Epitopes by sequencing (CITE-seq) is a powerful multimodal single-cell ...

• The multimodal CITE-seq datasets were obtained and analyzed.
• A novel quantitative model of RNA and protein was built by deep neural network algorithm.
• 18 cell-type-specific genes were identified in bone marrow stem cells.

Search and rescue robots have been widely investigated to detect humans in disaster scenarios. SLAM (Simultaneous Localisation and Mapping), as a critical function of the robot, can localise the robot and create the map during the rescue tasks. In ...

This paper introduces a mixed-integer nonlinear programming (MINLP) model aimed at designing a dependable closed-loop supply chain that can function effectively despite disruptions. The model incorporates several strategies to reduce the risks ...

Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems. However, this method can be very sensitive to the continuation schedule design and might lead to a ...

The thickness of the coating layers on coated fuel particles is critical to the safe operation of a high-temperature gas-cooled reactor, while how to measure it precisely, efficiently, and automatically remains challenging. The ...

• A high precision detection method is proposed based on improved Faster-RCNN.
• A ...

Expensive multi-objective optimization problems can be found in many real-world applications, where their objective function evaluations involve expensive computations or physical experiments. It is desirable to obtain an approximate Pareto front with a ...

Neural Radiance Fields (NeRF) learn a model for the high-quality 3D-view reconstruction of a single object. Category-specific representation makes it possible to generalize to the reconstruction and even generation of multiple objects. Existing ...