Machine Learning

With the goal of improving machine learning approaches in inverse scattering, we provide an experimental data set collected with a 2D near-field microwave imaging system. Machine learning approaches often train solely on synthetic data, and one of the reasons for this is that no experimentally-derived public data set exists. The imaging system consists of 24 antennas surrounding the imaging region, connected via a switch to a vector network analyzer. The data set contains over 1000 full Scattering parameter scans of five targets at numerous positions from 3-5 GHz.

This dataset presents real-world IoT device traffic captured under a scenario termed "Active," reflecting typical usage patterns encountered by everyday users. Our methodology emphasizes the collection of authentic data, employing rigorous testing and system evaluations to ensure fidelity to real-world conditions while minimizing noise and irrelevant capture.

An AI-based Ancient Hebrew Language Translator aims to revive Ancient Hebrew by constructing a comprehensive dataset with contemporary and ancient Hebrew samples. Seamless integration of the Google Vision API facilitates Optical Character Recognition (OCR) for image processing. The translation process initiates in English through the model, leading to a multilingual interface. This initiative represents a crucial step in preserving ancient languages in the digital age.

Standard dataset of the Tennessee–Eastman (TE) process.

The overall process consists of five operating units: reactor, condenser, vapor-liquid separator, recycle compressor and product stripper.

It has standard training and test data sets for soft sensor, fault detection and diagnosis, fault  classification, etc. Each data set is under different operating conditions.