A5026752161- Cell Image Analysis Techniques
- Software Engineering Research
- Gene expression and cancer classification
- Single-cell and spatial transcriptomics
- Biosensors and Analytical Detection
- SARS-CoV-2 detection and testing
- SARS-CoV-2 and COVID-19 Research
- Recommender Systems and Techniques
- Fault Detection and Control Systems
- Integrated Energy Systems Optimization
- Peer-to-Peer Network Technologies
- Advanced Neural Network Applications
- Software System Performance and Reliability
- Spacecraft and Cryogenic Technologies
- Energy Load and Power Forecasting
- Advanced Image and Video Retrieval Techniques
- Software Reliability and Analysis Research
- Medical Image Segmentation Techniques
- Hybrid Renewable Energy Systems
- Image Processing Techniques and Applications
- Molecular Biology Techniques and Applications
- Topological and Geometric Data Analysis
- Anomaly Detection Techniques and Applications
- Multimedia Communication and Technology
- Computational Physics and Python Applications
Columbia University
2021-2024
University of California, Berkeley
2021
Shanghai University
2021
Guilin University of Electronic Technology
2019
North China Electric Power University
2019
Dalian University of Technology
2017
Shanghai University of Engineering Science
2009
A bstract Probabilistic models have provided the underpinnings for state-of-the-art performance in many single-cell omics data analysis tasks, including dimensionality reduction, clustering, differential expression, annotation, removal of unwanted variation, and integration across modalities. Many being deployed are amenable to scalable stochastic inference techniques, accordingly they able process datasets realistic growing sizes. However, community-wide adoption probabilistic approaches is...
Users’ preferences, and consequently their ratings reviews to items, change over time. Likewise, characteristics of items are also time-varying. By dividing data into time periods, temporal Recommender Systems (RSs) improve recommendation accuracy by exploring the dynamics in user rating data. However, RSs have cope with sparsity each period. Meanwhile, generated users contain rich information about which can be exploited address further performance RSs. In this article, we develop a model...
Spatial mapping of transcriptional states provides valuable biological insights into cellular functions and interactions in the context tissue. Accurate 3D cell segmentation is a critical step analysis this data towards understanding diseases normal development situ. Current approaches designed to automate include stitching masks along one dimension, training neural network architecture from scratch, reconstructing volume 2D segmentations on all dimensions. However, applicability existing...
Abstract Background Spatial mapping of transcriptional states provides valuable biological insights into cellular functions and interactions in the context tissue. Accurate 3D cell segmentation is a critical step analysis this data towards understanding diseases normal development situ . Current approaches designed to automate include stitching masks along one dimension, training neural network architecture from scratch, reconstructing volume 2D segmentations on all dimensions. However,...
RNA sequencing (scRNA-seq) technologies have revolutionized our understanding of cellular heterogeneity. However, the characterization scRNA-seq datasets remains challenging. We introduce a novel computational method that significantly enhances annotation scRNA clusters query dataset using established as references. RefCM leverages optimal transport to measure similarity in gene expression distributions between and solves an integer program optimally link reference based on this metric. Our...
Wind energy is a typical representative of environmentally friendly new energy. However, its huge randomness and suddenness have caused many harms losses to the actual applied wind power. Therefore, predicting in advance improving prediction accuracy become top priority. Since data kind time series, LSTM model has excellent performance. Most researches are focused on one-dimensional data. This paper uses multivariate model. In addition weather conditions, at previous moment included as one...
Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may that they do not have part-based inductive bias like human process. Motivated this, several models been proposed to improve of recognition. However, due lack part annotations, effectiveness these methods is only validated on small-scale nonstandard datasets. In this work, we propose PIN++, short PartImageNet++, a dataset providing high-quality...
Software Deformity Prone datasets models are interesting research direction in the era of software world. In this study, interest class deformity prone is defective model datasets. There different techniques to predict model. Our proposed solution technique AttributeSelectedClassifier with selected evaluators and searching method for reducing dimensionality training testing data provided by defected NASA attribute selection before being passed on classifiers. We have used three search...
Abstract Group testing saves time and resources by each pre-assigned group instead of individual, one-stage emerged as essential for cost-effectively controlling the current COVID-19 pandemic. Yet, practical challenge adjusting pooling designs based on infection rate has not been systematically addressed. In particular, there are both theoretical interests motivation to analyze at finite, problem sizes, rather than asymptotic ones, under noisy, perfect tests, when number positives is...
Under the dual pressure of growing crisis in energy and severe pollution environment, research on utilization has attracted people's attention. Energy hub (EH) is a port network node which can represent complex coupling among different types energy. In this paper, new model applied with Monte Carlo method order to reduce impact uncertainties wind power. Considering constraints storage demand response, an optimal scheduling minimum daily payment established. Simulation results scenarios...