A5066651833- Text and Document Classification Technologies
- Engineering and Information Technology
- Machine Learning and Data Classification
- Neural Networks and Applications
- Imbalanced Data Classification Techniques
- Time Series Analysis and Forecasting
- Data Mining Algorithms and Applications
- Algorithms and Data Compression
- Anomaly Detection Techniques and Applications
- Face and Expression Recognition
- Machine Learning in Bioinformatics
- Forecasting Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Technology in Education and Healthcare
- Knowledge Societies in the 21st Century
- Image Retrieval and Classification Techniques
- Business, Education, Mathematics Research
- Stock Market Forecasting Methods
- Web Data Mining and Analysis
- Spam and Phishing Detection
- Evolutionary Algorithms and Applications
- Educational Innovations and Technology
- Natural Language Processing Techniques
- Fuzzy Logic and Control Systems
- Parallel Computing and Optimization Techniques
Universidad de Jaén
2011-2024
Universidad de Granada
1998-2017
Informatica (South Korea)
2017
Oak Ridge National Laboratory
1998
This paper discusses how to forecast time series using generalized regression neural networks. The main goal is take advantage of their inherent properties generate fast, highly accurate forecasts. To this end, the key modeling decisions involved in forecasting with networks are described. deal every decision, several strategies proposed. Each strategy analyzed terms accuracy and computational time. Apart from decisions, any successful methodology has be able capture seasonal trend patterns...
Most classification algorithms deal with datasets which have a set of input features, the variables to be used as predictors, and only one output class, variable predicted.However, in late years many scenarios classifier has work several outputs come life.Automatic labeling text documents, image annotation or protein are among them.Multilabel product these new needs, they specific traits.The mldr package allows user load this kind, obtain their characteristics, produce specialized plots,...
In this paper the tsfknn package for time series forecasting using k-nearest neighbor regression is described.This allows users to specify a KNN model and generate its forecasts.The user can choose among different multi-step ahead strategies functions aggregate targets of nearest neighbors.It also possible assess forecast accuracy model.
Predictive models trained on imbalanced data tend to produce biased results. This problem is exacerbated when there not just one output label, but a set of them. the case for multilabel learning (MLL) algorithms used classify patterns, rank labels, or learn distribution outputs. Many solutions have been proposed in literature. The that can be applied universally, independent algorithm build model, resampling. generation new instances associated with minority so empty areas feature space are...
Multilabel classification (MLC) has generated considerable research interest in recent years, as a technique that can be applied to many real-world scenarios. To process them with binary or multiclass classifiers, methods for transforming multilabel data sets (MLDs) have been proposed, well adapted algorithms able work this type of sets. However, until now, few studies addressed the problem how deal MLDs having large number labels. This characteristic defined high dimensionality label space...
The Web is broadly used nowadays to obtain information about almost any topic, from scientific procedures cooking recipes. Electronic forums are very popular, with thousands of questions asked and answered every day. Correctly tagging the posted by users usually produces quicker better answers other experts. In this paper a prototype system aimed assist while their proposed. To accomplish task, firstly text each post processed produce multilabel dataset, then lazy nearest neighbor...