ITC/USA 2009 Conference Proceedings / The Forty-Fifth Annual International Telemetering Conference and Technical Exhibition / October 26-29, 2009 / Riviera Hotel & Convention Center, Las Vegas, Nevada / The vision of the semantic web is to unleash the next generation of information sharing and interoperability by encoding meaning into the symbols that are used to describe various computational capabilities within the World Wide Web or other networks. This paper describes the application of semantic web technologies to Test and Evaluation (T&E) metadata verification and validation. Verification is a quality process that is used to evaluate whether or not a product, service, or system complies with a regulation, specification, or conditions imposed at the start of a development phase or which exists in the organization. Validation is the process of establishing documented evidence that provides a high degree of assurance that a product, service, or system accomplishes its intended requirements. While this often involves acceptance and suitability with external customers, automation provides significant assistance to the customers.

ITC/USA 2011 Conference Proceedings / The Forty-Seventh Annual International Telemetering Conference and Technical Exhibition / October 24-27, 2011 / Bally's Las Vegas, Las Vegas, Nevada / XidML is an open, vendor neutral, XML based standard for the FTI community used to capture the metadata associated with flight test instrumentation and data acquisition networks. This paper discusses the difference between metadata and meta-metadata, how these concepts apply to XidML and an optional schema, XdefML. The paper also describes how Settings and their validation may be applied to a Generic package definition. Some examples are given of how the current version XdefML can be leveraged to auto-generate graphical user interfaces that are both feature rich and incorporate sophisticated error checking and data validation.

In the e-commerce industry, importing data from third party clothing brands require validation of this data. If the validation step of this data is done manually, it is a tedious and time-consuming task. Part of this task can be replaced or assisted by using computer vision to automatically find clothing types, such as T-shirts and pants, within imported images. After a detection of clothing type is computed, it is possible to recommend the likelihood of clothing products correlating to data imported with a certain accuracy. This was done alongside a prototype interface that can be used to start training, finding clothing types in an image and to mask annotations of products. Annotations are areas describing different clothing types and are used to train an object detector model. A model for finding clothing types is trained on Mask R-CNN object detector and achieves 0.49 mAP accuracy. A detection take just above one second on an Nvidia GTX 1070 8 GB graphics card. Recommending one or several products based on a detection take 0.5 seconds and the algorithm used is k-nearest neighbors. If prediction is done on products of which is used to build the model of the prediction algorithm almost perfect accuracy is achieved while products in images for another products does not achieve nearly as good results.

ITC/USA 2014 Conference Proceedings / The Fiftieth Annual International Telemetering Conference and Technical Exhibition / October 20-23, 2014 / Town and Country Resort & Convention Center, San Diego, CA / The paper discusses the history and background of metadata standards for the FTI community over the last 20 years and speculates on how they may develop in the future. It starts by highlighting the deficiencies of proprietary formats and the resulting problems. It then discusses the characteristics and features of specific industry standard metadata descriptions such as TMATS, iHAL, MDL and XidML in addition to their levels of maturity. The attributes of what constitutes a fully mature FTI metadata standard is then discussed. It is suggested that any standard must serve at least two functions, Configuration and Validation, and outlines what exactly each means. Finally, it is argued that there is now a significant level of convergence and consensus in both the scope and application of metadata, and in the associated concept of operations (ConOps). The details of this Concept of Operations are then discussed along with suggestions as to how this may evolve in the coming years.