AI/ML-based Communication and Spectrum Sensing Applications

HİSAR Lab specializes in AI/ML methods for spectrum sensing and modulation classification. We have developed a range of machine learning and deep learning architectures to tackle various challenges in this field, including analog and digital modulation classification, cellular signal classification for technologies such as GSM, UMTS, LTE, and 5GNR, utilizing advanced object detection methods like YOLO and Detectron. Additionally, we focus on wireless interference detection and classification.

Our work is not limited to these applications. We envision that AI/ML-based solutions will be key enablers of complex physical layer solutions. Instead of merely adding new blocks to the transmitter and receiver sides, which increases computational and system complexity, AI/ML can replace or augment these blocks, reducing system complexity through learned models. Our research includes the development of AI/ML-based transceiver components such as mappers, coders, beamformers, channel estimators, demodulators, decoders and many others to improve accuracy and reduce computational overhead.