A5101555782- Neural Networks and Reservoir Computing
- Spectroscopy and Chemometric Analyses
- Optical Network Technologies
- Genomics and Phylogenetic Studies
- Wood and Agarwood Research
- Photonic and Optical Devices
- Advanced Optical Sensing Technologies
- CRISPR and Genetic Engineering
- Anomaly Detection Techniques and Applications
- Nematode management and characterization studies
- Smart Agriculture and AI
- Remote Sensing in Agriculture
- Viral Infections and Outbreaks Research
- Advanced Memory and Neural Computing
- Plant tissue culture and regeneration
- Herpesvirus Infections and Treatments
- Remote Sensing and LiDAR Applications
- Photonic Crystals and Applications
- Photosynthetic Processes and Mechanisms
- Advances in Cucurbitaceae Research
- Air Quality Monitoring and Forecasting
- Network Security and Intrusion Detection
- Plant Diversity and Evolution
- Advanced Chemical Sensor Technologies
- Spectroscopy Techniques in Biomedical and Chemical Research
Tianjin Normal University
2023-2024
Zhejiang University
2021-2024
Huzhou University
2022
Xuzhou Medical College
2019
Abstract Background Pumpkin seeds are major oil crops with high nutritional value and content. The collection identification of different pumpkin germplasm resources play a significant role in the realization precision breeding variety improvement. In this research, we collected 75 species from Zhejiang Province China. 35,927 near-infrared hyperspectral images types were used as research object. Results To realize rapid classification seed varieties, position attention embedded...
The Question Generation System (QGS) for Information Technology (IT) education, designed to create, evaluate, and improve Multiple-Choice Questions (MCQs) using Knowledge graphs (KGs) Large Language Models (LLMs), encounters three major needs: ensuring the generation of contextually relevant accurate distractors, enhancing diversity generated questions, balancing higher-order thinking questions match various learning levels. To address these needs, we proposed a multi-agent system named...
In the field of pipeline weld defect detection, common object detection algorithms have high complexity and huge computational load, making it difficult to meet real-time monitoring requirements defects on production lines. To address this issue, paper proposes a lightweight model YOLOv8-BVS based YOLOv8 framework. The introduces BRA module improve recognition ability small defects. further accuracy recognition, upsampling algorithm CARAFE is used in feature fusion network quality richness...
Remote sensing information acquisition technology based on UAV has been widely used in the agricultural field. remote platform to obtain crop characteristics of high timeliness, resolution, low cost, rapidity and accuracy, is one important means obtaining farmland precision agriculture. Using multispectral images, taking wheat, barley Chinese cabbage as research objects, selecting different vegetation indices for image threshold segmentation, combining results machine learning classification...
Photonic neural networks (PNNs), as emerging analog computing paradigms, have the potential to break both power consumption wall and processing speed boundary of digital architectures. However, most reported PNNs were mainly focused on real-valued regions, where phases optical fields only utilized indirect information affect amplitudes. Moreover, quantization phase at each node multi-layer is disregarded. In this work, we propose demonstrate a Clements-enhanced complex-valued mesh (CCM) with...
Abstract Background Transgenic glyphosate-resistant maize has emerged as a way to expand the use of glyphosate for weed control. Studying microbiome in transgenic plant and rhizosphere soil is vital understanding mechanism optimizing design crops. Results In our study, modification did not affect initial bacterial community leaf, stem, root maize, but promoted healthier soil. After stimulation, recruited more beneficial bacteria regulate biocontrol, N fixation P solubilization both tissues...
Abstract Accurate delineation of plant cell organelles from electron microscope images is essential to understand subcellular behaviors and functions. Here, we develop a deep learning pipeline, organelle segmentation network (OrgSegNet) for pixel-wise identify chloroplasts, mitochondria, nuclei, vacuoles. OrgSegNet was evaluated on large manually-annotated dataset 6371 collected 13 species, achieved state-of-the-art performance these organelles. To generalize the morphological...
We propose a two-dimensional beam scanner based on hitless microring switch array. By changing the resonance state of interference between different wavelength selection switches is avoided. The operation complexity steering FPA chip array reduced.
Objective To analyze the correlation between herpes zoster neuralgia and methylation status of whole genome GCH1 gene. Methods From June to October in 2017, patients with confirmed obvious were selected Department Dermatology, The Affiliated Hospital Xuzhou Medical University, who achieved complete remission (no effect was observed on normal sleep) after antiviral neurotrophic treatment. Finally, 36 healthy controls enrolled into this study. Peripheral blood samples obtained from...
Silicon-based waveguides and all-pass microring resonators used as the all-optical nonlinear activators for photonic neural networks are demonstrated. For three-layer, full-connected network MNIST dataset, recognition accuracies based on proposed silicon-based devices all can reach more than 90%.