A5019597664- Advanced Text Analysis Techniques
- Semantic Web and Ontologies
- Consumer Market Behavior and Pricing
- Software System Performance and Reliability
- Cultural Industries and Urban Development
- Insect and Pesticide Research
- Manufacturing Process and Optimization
- Architecture, Design, and Social History
- Topic Modeling
- Industrial Gas Emission Control
- Advanced Data Compression Techniques
- Catalytic Processes in Materials Science
- Text and Document Classification Technologies
- High Altitude and Hypoxia
- Data Mining Algorithms and Applications
- Recommender Systems and Techniques
- Remote Sensing and Land Use
- Simulation and Modeling Applications
- Digital Platforms and Economics
- Supply Chain and Inventory Management
- Optimization and Search Problems
- Data Quality and Management
- Wireless Signal Modulation Classification
- Acne and Rosacea Treatments and Effects
- Healthcare Technology and Patient Monitoring
Xi'an Jiaotong University
2006-2024
Institute of Geographic Sciences and Natural Resources Research
2024
Chinese Academy of Sciences
2024
Massachusetts Institute of Technology
2023
Institute of Scientific and Technical Information
2022
Yunnan University
2022
Weifang University of Science and Technology
2021
University of Science and Technology of China
2018-2021
Xi’an University of Posts and Telecommunications
2021
Xi'an University of Architecture and Technology
2011-2019
This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., recovery of whole-scene hyperspectral (HS) information a 3-channel image. The was divided into 2 tracks: "Clean" track sought HS noiseless images obtained known response function (representing spectrally-calibrated camera) while "Real World" challenged participants to recover cubes JPEG-compressed generated by an unknown function. To facilitate challenge, BGU Hyperspectral Image Database [4]...
The fast development of neuromorphic hardwares promotes Spiking Neural Networks (SNNs) to a thrilling research avenue. Current SNNs, though much efficient, are less effective compared with leading Artificial (ANNs) especially in supervised learning tasks. Recent efforts further demonstrate the potential SNNs by introducing approximated backpropagation (BP) methods. To deal non-differentiable spike function these BP methods utilize information from spatio-temporal domain adjust model...
A deep neural network (DNN) based power control method that aims at solving the non-convex optimization problem of maximizing sum rate a fading multi-user interference channel is proposed. Towards this end, we first present PCNet, which multi-layer fully connected specifically designed for problem. key challenge in training DNN lack ground truth, i.e., optimal allocation unknown. To address issue, PCNet leverages unsupervised learning strategy and directly maximizes phase. Observing single...
The two most essential factors for mobile self-organizing networks applicable to drones are reliability and stability. In harsh communication environments, such as mountainous regions natural disasters, the use of satellites terrestrial stations has severe time delays due high speed UAVs, resulting in frequent interruptions with UAVs. Therefore, UAVs need establish information sharing. High-speed movement will lead rapid changes network topology, established links being an unstable...
Cloud manufacturing (CMfg) emerges as a promising paradigm, where service composition (SC) is critical process concentrating on matching tasks and services. Existing studies usually ignore the dynamic nature of CMfg environment, task information not always known before. Moreover, services are re-entrant, i.e. after being occupied for period time, these re-enter platform (i.e. be available again). Re-entrant significantly complicate revenue management. In this regard, we study SC problem...
An innovative low-nitrogen natural gas burner was developed, leveraging air-staged combustion as the primary mechanism, supplemented by swirl and flue recirculation technology. This design enables adaptation to a multitude of conditions through adjustment secondary air ratio. A prototype with power output 60 kW constructed for experimental study. The velocity field, concentration temperature NOx within zone were analyzed under different load, impact ratio on burner's performance explored....
Abstract In recent years, BIM technology has developed rapidly in the field of housing construction, and been well applied many construction projects. However, application on bridges is less. This article takes Hongjiazhong Bridge as an example to research explore bridges. Conduct accountability, program simulation, quality safety management, platform etc., explain innovative applications GIS, VR, AR, operation maintenance.
Identifying the subcellular localization of a given protein is an essential part biological and medical research, since must be localized in correct organelle to ensure physiological function. Conventional experiments for have some limitations, such as high cost low efficiency, thus massive computational methods are proposed solve these problems. However, need improved further with class imbalance problem. We propose new model, generating minority samples (Gm-PLoc), predict multi-label...
The rapid growth of information technology and Internet applications has provided users with an explosion information. Mobile e-commerce web search engines are great interest in extracting representative from the original abundant However, extracted by several existing methods, such as top- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> , often quite similar, which is difficult to meet users’ demand for diversified In order increase...
The high rate of false arrhythmia alarms in intensive care units (ICUs) can negatively impact patient and lead to slow staff response time due alarm fatigue. To reduce ICUs, previous works proposed conventional supervised learning methods which have inherent limitations dealing with high-dimensional, sparse, unbalanced, limited data. We propose a deep generative approach based on the conditional denoising diffusion model detect ICUs. Conditioning past waveform data patient, our generates...
Medical decision making often relies on accurately forecasting future patient trajectories. Conventional approaches for progression modeling do not explicitly model treatments when predicting trajectories and outcomes. In this paper, we propose Alternating Transformer (AL-Transformer) to jointly treatment clinical outcomes over time as alternating sequential models. We leverage causal convolution in the self-attention mechanism of AL-Transformer incorporate local spatial information...
Motivated by the breakthroughs of AI in both theory and applications, we are perceiving a great potential for network innovations from new dimension intelligence. However, as engine networks, switches designed "dumb" elements with sole purpose forwarding packets, thus barrier against entrance an intrinsic part is unconsciously erected. This article proposes evolved switch architecture aimed at breaking this accommodating in-network We enhance current embedding intelligence plane, which...
The current neuron reconstruction pipeline for electron microscopy (EM) data usually includes automatic image segmentation followed by extensive human expert proofreading. In this work, we aim to reduce workload predicting connectivity between over-segmented pieces, taking both and 3D morphology features into account, similar proofreading workflow. To end, first construct a dataset, named FlyTracing, that contains millions of pairwise connections segments expanding the whole fly brain, which...