A5029066094- Mass Spectrometry Techniques and Applications
- Metabolomics and Mass Spectrometry Studies
- Isotope Analysis in Ecology
- Privacy-Preserving Technologies in Data
- Molecular Biology Techniques and Applications
- Algorithms and Data Compression
- Data Mining Algorithms and Applications
- Advanced Proteomics Techniques and Applications
- Adversarial Robustness in Machine Learning
- Data Management and Algorithms
- Graph Theory and Algorithms
- Neural Networks and Applications
- Rough Sets and Fuzzy Logic
- Advanced Chemical Sensor Technologies
- Genetic factors in colorectal cancer
- ECG Monitoring and Analysis
- Analytical chemistry methods development
- Herpesvirus Infections and Treatments
- Machine Learning and Data Classification
- Pesticide Residue Analysis and Safety
- Ion-surface interactions and analysis
- SARS-CoV-2 and COVID-19 Research
- Internet Traffic Analysis and Secure E-voting
- Viral gastroenteritis research and epidemiology
- Machine Learning in Materials Science
South China Agricultural University
2025
Shanxi University
2024
Northeastern University
2018-2023
Universidad del Noreste
2022
Boston University
2021
Beijing Institute of Technology
2016
Beijing Haidian Hospital
2016
Harbin University of Commerce
2012
Mass spectrometry imaging (MSI) characterizes the molecular composition of tissues at spatial resolution, and has a strong potential for distinguishing tissue types, or disease states. This can be achieved by supervised classification, which takes as input MSI spectra, assigns class labels to subtissue locations. Unfortunately, developing such classifiers is hindered limited availability training sets with ground truth. Subtissue labeling prohibitively expensive, only rough annotations...
Mass spectrometry imaging (MSI) derives spatial molecular distribution maps directly from clinical tissue specimens and thus bears great potential for assisting pathologists with diagnostic decisions or personalized treatments. Unfortunately, progress in translational MSI is often hindered by insufficient quality control lack of reproducible data analysis. Raw analysis scripts are rarely publicly shared. Here, we demonstrate the application Galaxy tool set a urothelial carcinoma...
Abstract Motivation Mass spectrometry imaging (MSI) characterizes the spatial distribution of ions in complex biological samples such as tissues. Since many tissues have morphology, treatments and conditions often affect morphology-specific ways. Evaluating selectivity specificity ion localization regulation across morphology types is biologically important. However, MSI lacks algorithms for segmenting images at both single-ion resolution. Results This article contributes spatial-Dirichlet...
Machine learning models are widely used in science and engineering to predict the properties of materials solve complex problems. However, training large can take days fine-tuning hyperparameters months, making it challenging achieve optimal performance. To address this issue, we propose a Knowledge Enhancing (KE) algorithm that enhances knowledge gained from lower capacity model higher model, enhancing efficiency We focus on problem predicting bandgap an unknown material present theoretical...
Distributed learning such as federated or collaborative enables model training on decentralized data from users and only collects local gradients, where is processed close to its sources for privacy. The nature of not centralizing the addresses privacy issue privacy-sensitive data. Recent studies show that a third party can reconstruct true in distributed machine system through publicly-shared gradients. However, existing reconstruction attack frameworks lack generalizability different Deep...
Mass Spectrometry Imaging (MSI) analyzes complex biological samples such as tissues. It simultaneously characterizes the ions present in tissue form of mass spectra, and spatial distribution across ion images. Unsupervised clustering images facilitates interpretation spectral domain, by identifying groups with similar distributions. Unfortunately, many current methods for ignore features images, are therefore unable to learn these purposes. Alternative extract using deep neural networks...
Abstract Chemoresistance is a major cause of breast cancer (BC) recurrence and metastasis, chemotherapy resistance comes from tumor stemness. Our previous study showed that quinoa bran terpenoids (QBT) exhibited significant antitumor activity. In this study, we found QBT increased the sensitivity drug‐resistant BC cells to chemotherapeutic drugs adriamycin (ADR) taxol (TAX). A novel lncRNA 667012 was identified along with treatment. Moreover, overexpression promoted drug resistance,...
Cardinal v3 is an open source software for reproducible analysis of mass spectrometry imaging experiments. A major update from its previous versions, supports most workflows. Its analytical capabilities include advanced data processing such as re-calibration, statistical analyses single-ion segmentation and rough annotation-based classification, memory-efficient large-scale multi-tissue
Though the information technology outsourcing (ITO) can help many companies to reduce total costs of their (IT) projects and seek a more efficient allocation resources, ITO-based probably have insecure risks unexpected even failure whole project.After quantitative analysis with principal-agent theory towards security problem projects, new incentive reward-punishment model was proposed in this paper, order ITO risk generate optimal contract under asymmetric condition.The experimental results...
Distributed machine learning (DML) enables model training on a large corpus of decentralized data from users and only collects local models or gradients for global synchronization the cloud. Recent studies show that third party can recover in DML system through publicly shared gradients. Our investigation has revealed existing techniques (e.g., DLG) uniform weight distribution fail to other weights initialization normal distribution) during stage. In this work, we provide an analysis how...
In order to accurately obtain the identification information, in basis of various biometric technology comparative study , using a higher safety and reliability ecg signal technology.This paper studies method technology, first wavelet transform remove noise interference signal, pinpoint cycle, then contrast recognition rate two feature extraction methods harmonic fundamental wave ratio single cycle inner time-frequency joint analysis, finally proposed fusion analysis.Through small amount...
The decision tree algorithm is a kind of approximate discrete function value method with high precision, construction model classification noise data simple and has good robustness etc, it currently the most widely used in one inductive reasoning algorithms mining, extensive attention by researchers. This paper selects ID3 to realize standardization lumber level division, ensure accuracy while improving partition speed.
ABSTRACT Background Mass spectrometry imaging (MSI) derives spatial molecular distribution maps directly from clinical tissue specimens. This allows for characterization of compositions different types and tumor subtypes, which bears great potential assisting pathologists with diagnostic decisions or personalized treatments. Unfortunately, progress in translational MSI is often hindered by insufficient quality control lack reproducible data analysis. Raw analysis scripts are rarely publicly...