ANS is committed to advancing, fostering, and promoting the development and application of nuclear sciences and technologies to benefit society.
Explore the many uses for nuclear science and its impact on energy, the environment, healthcare, food, and more.
Division Spotlight
Materials Science & Technology
The objectives of MSTD are: promote the advancement of materials science in Nuclear Science Technology; support the multidisciplines which constitute it; encourage research by providing a forum for the presentation, exchange, and documentation of relevant information; promote the interaction and communication among its members; and recognize and reward its members for significant contributions to the field of materials science in nuclear technology.
Meeting Spotlight
2024 ANS Annual Conference
June 16–19, 2024
Las Vegas, NV|Mandalay Bay Resort and Casino
Standards Program
The Standards Committee is responsible for the development and maintenance of voluntary consensus standards that address the design, analysis, and operation of components, systems, and facilities related to the application of nuclear science and technology. Find out What’s New, check out the Standards Store, or Get Involved today!
Latest Magazine Issues
Apr 2024
Jan 2024
Latest Journal Issues
Nuclear Science and Engineering
May 2024
Nuclear Technology
Fusion Science and Technology
Latest News
BWXT announces nuclear manufacturing plant expansion
BWX Technologies announced today plans to expand and add advanced manufacturing equipment to its manufacturing plant in Cambridge, Ontario, Canada.
A $36.3 million USD ($50M CAD) expansion will increase the plant’s size by 25 percent–to 280,000 square feet; and another $21.7 million USD ($30M CAD) will be spent on new equipment to increase and accelerate its output of large nuclear components. The investment will increase capacity and create more than 200 long-term jobs for skilled workers, engineers, and support staff, according to the company.
Lázaro Emílio Makili, Jesús A. Vega Sánchez, Sebastián Dormido-Canto
Fusion Science and Technology | Volume 62 | Number 2 | October 2012 | Pages 347-355
Selected Paper from the Seventh Fusion Data Validation Workshop 2012 (Part 1) | doi.org/10.13182/FST12-A14626
Articles are hosted by Taylor and Francis Online.
This paper addresses the problem of finding a minimal and good enough training data set for classification purposes by using active learning and conformal predictors. Active learning means to have control in the selection process of training samples instead of choosing them in a random way. To this end, active learning methodologies look for establishing selection criteria in order to find out the samples that show better discrimination capabilities. In the present case, conformal predictors have been used for these purposes. Results will be presented in a five-class classification problem with images. The features are the vertical detail coefficients of the Haar wavelet transform at level four to diminish the sample dimensionality by reducing the spatial redundancy of the images. The active selection of training sets (through the reliability measures of a conformal predictor) allows the improvement of the classifiers. Here, the word "improvement" refers to obtaining higher generalization properties thereby avoiding overfitting. Support vector machines classifiers, in the one-versus-the-rest approach, have been used as the underlying classifiers.