KSKakade Sandeep

Kakade Sandeep

*This is an algorithmically generated author record based on publicly available information.

Kakade Sandeep has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Emerging materials and technologies for next-generation sensors in smart IoT systems: a comprehensive review

    by Choon Kit Chan, Kakade Sandeep, Shivale Nitin, Deshpande Asmita, Patil Shrishail, Sonawane Vijay, Dushyant Patil, Chandrakant Sonawane, Saurav Dixit, Deekshant Varshney

  • Reimagining Spectrum Management

    by Kakade Sandeep, Nitin Shivale, Shrishail Patil, Gayatri M. Bhandari, Vijay Sonawane, Tushar Phadtare

    Due to fast-paced growth in wireless communication technologies and introduction of 6G, the efficient allocation and use of spectrum has become extremely challenging. The traditional method for allocating spectrum based on a pre-defined set of static rules no longer works as effectively in today’s rapidly changing, intensive, data-based, and heterogeneous networks. This chapter provides an overview of the conceptual framework for artificial intelligence (AI)-based (and related) spectrum management systems, which will allow for the development of a completely self-directing and intelligent (or “self-organizing”) ecosystem for spectrum management. The chapter discusses how to identify challenges in current allocation models, provides a conceptual design for developing an AI-based decision-making and machine learning (ML)-based ecosystem for spectrum management, and discusses future directions for research on AI models that include enhanced interpretability, increased energy efficiency, and the development of a globally harmonized regulatory framework for spectrum management. Finally, the chapter provides a discussion of the regulatory and ethical considerations associated with AI-based spectrum management, including algorithmic transparency and data privacy, and presents the proposed direction for future research regarding interpretability and sustainability (including energy use). Recent studies indicate that AI-driven dynamic spectrum allocation can improve overall spectrum utilization to approximately 85–90% under heterogeneous 6G network conditions.