A5102883867- Remote-Sensing Image Classification
- Metal-Organic Frameworks: Synthesis and Applications
- Image Retrieval and Classification Techniques
- Covalent Organic Framework Applications
- Advanced Image Processing Techniques
- Industrial Technology and Control Systems
- Remote Sensing and Land Use
- Advanced Sensor and Control Systems
- Generative Adversarial Networks and Image Synthesis
- Machine Fault Diagnosis Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Computational Techniques and Applications
- Advanced Algorithms and Applications
- Advanced Battery Technologies Research
- Quantum Dots Synthesis And Properties
- Industrial Vision Systems and Defect Detection
- Advanced Image Fusion Techniques
- Mechanical Engineering and Vibrations Research
- Anomaly Detection Techniques and Applications
- Translation Studies and Practices
- Reliability and Maintenance Optimization
- Digital and Cyber Forensics
- Geoscience and Mining Technology
- Advanced Measurement and Detection Methods
- Lymphoma Diagnosis and Treatment
Sun Yat-sen University
2017-2024
China Centre for Resources Satellite Data and Application
2020-2024
Dalian Jiaotong University
2024
Tianjin University
2024
Hangzhou Dianzi University
2023
Sun Yat-sen University Cancer Center
2017-2021
Southwest University of Science and Technology
2020-2021
Institute of Electrical and Electronics Engineers
2021
Beijing Institute of Technology
2021
Ministry of Transport
2015-2020
For health prognostic task, ever-increasing efforts have been focused on machine learning based methods, which are capable of yielding accurate remaining useful life (RUL) estimation for industrial equipment or components without exploring the degradation mechanism. A prerequisite ensuring success these methods depends a wealth run-to-failure data; however, data may be insufficient in practice. That is, conducting substantial amount destructive experiments not only is high cost but also...
Separation of methanol/benzene azeotrope mixtures is very challenging not only by the conventional distillation technique but also adsorbents. In this work, we design and synthesize a flexible Ca-based metal–organic framework MAF-58 consisting cheap raw materials. shows selective methanol-induced pore-opening flexibility. Although opened pores are large enough to accommodate benzene molecules, molecular sieving with ultrahigh experimental selectivity, giving 5.1 mmol g–1 high-purity...
In recent years, the tumor-stroma ratio (TSR) has been considered to a new and independent predictive variable for prognosis of some kinds neoplasms. The objective this study was assess prognostic significance TSR in non-small cell lung cancer (NSCLC).A cohort 261 NSCLC patients who underwent radical surgery were included present study. Two observers visually estimated on hematoxylin-eosin (H&E) stained tissue pathological slices. According proportion stroma ≥50% or <50%, We separate into...
Nonlinear graph-based dimensionality reduction algorithms such as Laplacian Eigenmaps (LE) and Schroedinger (SE) have been shown to be very effective at yielding low-dimensional representations of hyperspectral image data. However, the steps graph construction eigenvector computation required by LE SE can prohibitively costly number pixels grows. In this paper, we propose pre-clustering into Simple Linear Iterative Clustering (SLIC) superpixels then performing LE- or SE-based with input. We...
Background: Malignant lymphomas are a group of distinct lymphoid neoplasms, exhibiting marked diversity in biological behaviors and clinical outcomes.Liquid biopsy, such as circulating cell-free DNA (cfDNA), has recently been attempted to be used for mutation profiling using next-generation sequencing (NGS).However, only limited data about cfDNA restricted Hodgkin's lymphoma B cell lymphoma, there is no report the T so far.Patient Methods: Medical records total 50 patients were...
High expression of fibrinogen and platelets are often observed in non-small cell lung cancer (NSCLC) patients with local regional or distant metastasis. However, the role these factors remains unclear. The aims this study were to evaluate prognostic significance plasma concentration platelet count, as well determine overall survival NSCLC brain metastases. A total 275 metastasis enrolled into study. Univariate analysis showed that high was associated age≥65 years (P = 0.011), smoking status...
Collaborative filtering is the most popular approach when building recommender systems, but large scale and sparse data of user-item matrix seriously affect recommendation results. Recent research shows user’s social relations information can improve quality recommendation. However, current algorithms only consider user's direct relations, while ignoring potential users’ interest preference group clustering information. Moreover, project attribute also important in item rating. We propose a...
The extranodal natural killer (NK)/T-cell lymphoma (NKTCL) of non-upper aerodigestive tract (NUAT) was found to have clinical heterogeneity compared with NKTCL the upper (UAT) in small scale studies. We conducted this study a much larger cohort analyze characteristics, prognostic factors, treatment modality, and outcomes patients NUAT-NKTCL.From January 2001 December 2017, total 757 were identified included study, including 92 NUAT-NKTCL (12.2%) 665 UAT-NKTCL (87.8%).NUAT-NKTCL had...
This paper proposes a segmentation method based on K-mean and SOM network. Firstly remote sensing image is decomposed by wavelet transform at multiple-scale. Secondly the directional eigenvector of constructed transform. At coarser scale, we construct 4-dimension with feature images, images are roughly segmented K-means algorithm. Then other fine scale. Based results in remote-sensing scale The experiments about done two different ways, one which network simultaneously, mere K-mean. show...
According to some reasons, such as multifarious, low efficiency status of scientific research management work by artificial way, furthermore, big workload and poor adaptability requirement change exists in traditional software development method. In this paper, a typical model project process was build based on workflow technology. The business logic specific function were designed separately, so unified orderly realized, flexibility system enhanced too. Rapid platform technology chosen the...
Abstract Antimony(III) trichloride (SbCl 3 ) is an effective catalyst (1 mol%) for the condensation of anthranilic amide with various aldehydes or ketones to quinazolin-4(3 H )-one derivatives in good excellent yields under microwave irradiation. The process carried out within several minutes solvent-free conditions. This general methodology has advantages simplicity, mild reaction conditions and high products.
A new scheme integrating segmentation into classification to analyze hyperspectral images is presented in this paper, particularly for with a very few number of labels and largely adjacent spatial structures. Using pixel-wise semi-supervised support vector machine, the image classified, segmented by modified C-V level set method. Afterwards, are combined neighborhood voting. Experiments conducted on 200-band AVIRIS Northwestern Indiana's Indian Pine site. The integration information from...
Monitoring of cutting chatter in metal process is a very important economical consideration automated manufacturing. However, the complicated process. The still an unsolved problem In this paper, new method for monitoring developed. First, it uses fast Fourier transform (FFT) to signals and extract feature vectors. Then, Hidden Markov Model (HMM) as classifiers recognize chatter. experimental results show that proposed feasible effective.
Positron emission tomography(PET) and computed tomography(CT) imaging can obtain the functional metabolic information anatomical of human body, respectively. In response to problem how merge complementary PET CT, a lung tumor image fusion method based on VGG19 GAN model is proposed in this paper. The basic idea extract content style CT separately, then these two generate image. represented using series statistical methods that capture features such as color, texture, style. deep learning...