Machine Learning Techniques for Data Rate Reduction Tender, Netherlands - 101320428

Procurement Summary

Country : Netherlands

Summary : Machine Learning Techniques for Data Rate Reduction

Deadline : 02 Sep 2024

Other Information

Notice Type : Tender

TOT Ref.No.: 101320428

Document Ref. No. : 1-12223

Financier : Agency for the Cooperation of Energy Regulators (ACER)

Purchaser Ownership : Public

Tender Value : Refer Document

Purchaser's Detail

Name :Login to see tender_details

Address : Login to see tender_details

Email : Login to see tender_details

Login to see details

Tender Details

Tenders are invited for Machine Learning Techniques for Data Rate Reduction (Artes at 7b.079)

The objective of this activity is to design, implement and test Machine Learning (ML) and Artificial Intelligence (AI) based data rate reduction techniques for ground terminals. A testbed will be developed to assess performance savings in terms of throughput, complexity and power consumption.Targeted Improvements: Decrease the transmitted data rate by at least 40% for specific applicationsDescription: Many types of data transmissions and reception require a high bandwidth occupancy and they can be very demanding in terms of decoding and consumed power at the terminal. Machine Learning (ML)/Artificial Intelligence (AI) could potentially reduce capacity demands and enable less complex and less power consuming coding schemes in the receiver. For instance, data, such as video and voice, often contains replica (e.g., pixels, words) of previous data. ML and AI could identify such repetition and avoid the transmission of such information, reducing capacity demands. In addition, regarding signal decoding, very robust code rates, and complex and power consuming coding schemes are being used today to ensure correct decoding of the information at the receiver. These can be relaxed for specific data types, such as voice and IoT, as ML and AI, after extensive training can assist to predict the correct information hidden in erroneous received data. This would allow less robust coding rates to be used at the transmitter but also less complex and power consuming coding schemes to be used at the receiver.Research has shown that this application of ML and AI is viable and this activity will therefore develop and test ML and AI-based data rate reduction techniques for ground terminals of specific applications whose low levels of false predictions will not have a significant impact on the quality of service. The performance improvements will be tested in a laboratory testbed with inputs of real data, such as voice and video.Procurement Policy: C(1) = Activity restricted to non-prime contractors (incl. SMEs). For additional information please go to:http://www.esa.int/About_Us/Business_with_ESA/Small_and_Medium_Sized_Enterprises/Opportunities_for_SMEs/Procurement_policy_on_fair_access_for_SMEs_-_the_C1-C4_ClausesRead more

Documents

 Tender Notice