Results 271 to 280 of about 21,772 (300)

Efficient handling of high-dimensional feature spaces by randomized classifier ensembles

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02, 2002
Handling massive datasets is a difficult problem not only due to prohibitively large numbers of entries but in some cases also due to the very high dimensionality of the data. Often, severe feature selection is performed to limit the number of attributes to a manageable size, which unfortunately can lead to a loss of useful information.
Aleksander Kolcz, Xiaomei Sun, Jugal K. Kalita   +2 more
openaire   +1 more source

METHODS OF HANDLING AND CLASSIFYING TRADE CATALOGUES

Aslib Proceedings, 1953
On appointment as librarian, the author took over 1,500 trade catalogues in addition to the usual library stock. The catalogues had been stored on shelves, loosely inserted in Manila folders, a system which proved hopelessly inefficient. It was necessary to continue to use the shelving but, because of the varying size of the catalogues, box files would
openaire   +1 more source

Boosting Lite – Handling Larger Datasets and Slower Base Classifiers

2007
In this paper, we examine ensemble algorithms (Boosting Lite and Ivoting) that provide accuracy approximating a single classifier, but which require significantly fewer training examples. Such algorithms allow ensemble methods to operate on very large data sets or use very slow learning algorithms.
Lawrence O. Hall, Robert E. Banfield, Kevin W. Bowyer, W. Philip Kegelmeyer   +3 more
openaire   +1 more source

Non-monotonic inference system handling knowledge allowing classified exceptions

SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218), 2002
We propose a nonmonotonic formalism for knowledge handling allowing exceptions, the Exc-Representation (ER), and its goal-directed proof procedure, the SLD-EXC resolution, for the nonmonotonic inference system, NISE. ER always provides a unique extension, which is a set of conclusions, and makes tractable the membership problem in nonmonotonic ...
Kouzou Ohara, Noboru Babaguchi, Tadahiro Kitahashi   +2 more
openaire   +1 more source

A probabilistic multi-label classifier with missing and noisy labels handling capability

Pattern Recognition Letters, 2017
Our multi-label classifier has the capability of handling missing and noisy labels.The proposed probabilistic framework uses auxiliary random variables called experts.An expert ensemble with an overriding expert is used to specify the label.The proposed method outperforms state-of-the-art methods by a large margin.
Amirhossein Akbarnejad, Mahdieh Soleymani Baghshah   +1 more
openaire   +1 more source

Handling Different Levels of Granularity within Naive Bayes Classifiers

2013
Data mining techniques usually require a flat data table as input. For categorical attributes, there is often no canonical flat data table, since they can often be considered in different levels of granularity like continent, country or local region. The choice of the best level of granularity for a data mining task can be very tedious, especially when
Kemal Ince, Frank Klawonn
openaire   +1 more source

Weak Classifiers Performance Measure in Handling Noisy Clinical Trial Data

2016
Most research concluded that machine learning performance is better when dealing with cleaned dataset compared to dirty dataset. In this paper, we experimented three weak or base machine learning classifiers: Decision Table, Naive Bayes and k-Nearest Neighbor to see their performance on real-world, noisy and messy clinical trial dataset rather than ...
Ezzatul Akmal Kamaru-Zaman, Andrew Brass, James Weatherall, Shuzlina Abdul Rahman   +3 more
openaire   +1 more source

Process Controls in Classifying, Handling, Storing and Baking Devices and PWBs

On-Demand Webinars, 2009
ABSTRACT The handling, transportation, storage and packaging of Devices and PWBs has become critical as the industry has migrated to higher temperature lead free assembly processes. Devices have expanded beyond the traditional SMD ICs and now includes any non-IC device that will likely be subjected to the higher temperature lead free (
Steven Martell, Mumtaz Bora
openaire   +1 more source

Handling Label Noise in Microarray Classification with One-Class Classifier Ensemble

2015
The advance of high-throughput techniques, such as gene microarrays and protein chips have a major impact on contemporary biology and medicine. Due to the high-dimensionality and complexity of the data, it is impossible to analyze it manually. Therefore machine learning techniques play an important role in dealing with such data.
Bartosz Krawczyk, Michal Wozniak 0001
openaire   +1 more source

A Responsible AI approach for designing resilient classifier to handle incomplete data

Intelligent Data Analysis: An International Journal
Missing values can greatly affect analyses and decision-making in many fields. In the context of Responsible Artificial Intelligence (AI), ensuring the robustness of machine learning models is essential because Responsible AI emphasizes reliability and interpretability in decision-making processes.
Sairam Utukuru, P. Radha Krishna 0001
openaire   +1 more source