A5100320062- Advanced Computational Techniques and Applications
- Machine Learning and Data Classification
- Neural Networks and Applications
- Topic Modeling
- Recommender Systems and Techniques
- Generative Adversarial Networks and Image Synthesis
- Seismology and Earthquake Studies
- Spectroscopy and Chemometric Analyses
- Advanced Algorithms and Applications
- Data Management and Algorithms
- Anomaly Detection Techniques and Applications
- Expert finding and Q&A systems
- Advanced Clustering Algorithms Research
- Domain Adaptation and Few-Shot Learning
- Explainable Artificial Intelligence (XAI)
- Computational Drug Discovery Methods
- Adversarial Robustness in Machine Learning
- Advanced Chemical Sensor Technologies
- Fuzzy Logic and Control Systems
- Time Series Analysis and Forecasting
- Earthquake Detection and Analysis
- Caching and Content Delivery
- Remote Sensing and Land Use
- Human Pose and Action Recognition
- Water Quality Monitoring and Analysis
National Institute of Metrology
2024
Shanghai University of Engineering Science
2007-2024
Shanghai Institute of Computing Technology
2021-2024
The University of Texas at Austin
2024
Shanghai University
2005-2022
Hebei University
2020
KTH Royal Institute of Technology
2020
Science for Life Laboratory
2020
University of Science and Technology of China
2015
Demand forecasting plays a crucial role for supply chain management of retail industry. The future demand certain product constructs the basis its relevant replenishment system. In this research, technique support vector machine (SVM) is employed forecasting. Various factors that affect such as seasonal and promotional have been taken into consideration in model. Meanwhile, different other approaches statistical model, Winter model radius function neural network (RBFNN) are also used...
Clustering algorithm is the foundation and important technology in data mining. In fact, real world, itself often has a hierarchical structure. Hierarchical clustering aims at constructing cluster tree, which reveals underlying modal structure of complex density. Due to its inherent complexity, most existing algorithms are usually designed heuristically without an explicit objective function, limits utilization analysis. K-means clustering, well-known simple yet effective can be expressed...
With the rapid increasing of number undergraduates in China, employment has become one greatest social concerns. In order to help improve their abilities, it is necessary analyze relationship between undergraduates' situation and performances such as academic records, reading status, so on. However, difficult identify these influence employment. Therefore, a novel method named IGWDT(Information Gain with Weight based Decision Tree) proposed, which feature selection employed get most relative...
Demand forecasting is the basis of business operation in a company and accuracy has great effect on safety inventory, profit competitive power company. In this paper, novel genetic algorithm (GA) back propagation (BP) based fuzzy neural network (GABPFNN) model proposed for demand forecasting, which new kinds rule generating matching algorithms are advanced to deal with difficulty modeling, then GA BP employed optimize network. Finally, applied beer retail industry. The final experiment...
The different effects of input attributes on category results in supervised ART (adaptive resonance theory) network is quite important during the predictive stage application that was ignored by traditional researches. In fact, some have larger effect than others results, but, even for experts field, it difficult to evaluate effect. this paper we present a novel namely impulse force based (IFART) network. It enhances prediction accuracy using genetic algorithm optimized impulsive forces...
Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning enriched features. This raises question whether this remains true when data is scarce - there an advantage to with additional labels in low-data regimes? In work, we consider a task requires difficult-to-obtain expert annotations: tumor segmentation mammography images. We show that, settings, performance can be...
Personalized recommendation technology has been developed rapidly and used more widely. LehuBT is one of the most popular Ipv6 website by Shanghai University. With rapid development users torrents, an order to help select their favors in numerous personalized should be added into current LehuBT. The influence time factor important as times go on LehuBT, a torrent was downloaded user nearer now, it's indicate interesting user. However, not taken account traditional Collaborative Filtering. In...