• Diese Seite als PDF öffnen.

Learning Aided SC Flip Decoding for Polar Codes

Description

Polar codes achieve the capacity of binary-input discrete memoryless channels asymptotically in the block length under successive cancellation (SC) decoding. Polar codes have been adopted for the control channel in 5G enhanced mobile broadband (eMBB).

Due to the serial nature of SC decoding, an erroneous bit decision can be caused by the channel noise or previous erroneous bit estimates. The main idea of SC flip decoding is trying to correct the first erroneous bit decision by sequentially flipping the unreliable decisions. 

The optimal flipping strategy is considered difficult due to lack of an analytical solution. Alternatively, (deep) learning aided SC flip algorithm are investigated in this thesis.

[1] O. Afisiadis, A. Balatsoukas-Stimming, and A. Burg, “A low-complexity improved successive cancellation decoder for polar codes,” in Proc. 48th Asilomar Conf. Signals, Systems and Computers, pp. 2116-2120, 2014.

[2] L. Chandesris, V. Savin, and D. Declercq, “Dynamic-SCFlip Decoding of Polar Codes,” IEEE Trans. Commun., vol. 66, no. 6, pp. 2333-2345, Jun., 2018.

[3] X. Wang, et al. "Learning to Flip Successive Cancellation Decoding of Polar Codes with LSTM Networks." arXiv preprint arXiv:1902.08394 (2019).

[4] N. Doan, et al. "Neural Dynamic Successive Cancellation Flip Decoding of Polar Codes." arXiv preprint arXiv:1907.11563 (2019).

Supervisor:

• Diese Seite als PDF öffnen.

Polar Coding with Non-Binary Kernels

Description

This thesis will focus on polar codes with non-binary kernels on GF(q). Some of the following tasks might be covered: 

• Kernel selection
• Decoder implementation
• Efficient construction
• Comparison of binary and non-binary polar codes

Prerequisites

Supervisor:

• Diese Seite als PDF öffnen.

Adaptive List Decoding for Polar Codes

Description

The finite-length performance of polar codes can be improved by using successive cancellation list decoding. In this thesis, decoder design/implementation and performance prediction are investigated.

Reference:

[1] I. Tal and A. Vardy. "List decoding of polar codes." IEEE Transactions on Information Theory 61.5 (2015): 2213-2226.

[2] P. Yuan and F. Steiner. "Efficient Decoding Algorithms for Polar Codes based on 2×2 Non-Binary Kernels." International Symposium on Turbo Codes & Iterative Information Processing. 2018.

Prerequisites

Supervisor:

• Diese Seite als PDF öffnen.

Polar Codes in Block Fading Channel

Description

-

Supervisor:

Student

• Diese Seite als PDF öffnen.

Machine learning-aided coordination for the autonomous car-pedestrian crossing problem

Description

The project considers the problem of decentralized decision making under input uncertainties. The problem is applied to a transportation scenario where an autonomous car runs on a road with the existence of pedestrians that are on the side walk and possibly about to cross the road. Both the car and pedestrian are modeled as rational decision makers that take (noisy) visual observation inputs as basis for their decision variables (speed adjustment for the car, and decision to cross or not cross for the pedestrian).

The decision makers will be modeled from machine learning algorithms that are trained to maximize the transport efficiency while keeping the probability of a crash as low as possible.

The use of DNN is envisioned. Several heuristic policies will be tested out for comparison.

Prerequisites

Supervisor:

Student

• Diese Seite als PDF öffnen.

Investigation of Receiver Strategies for Ultra Wideband Communication with Time-of-Flight Distance Measurement

Description

In particular, receiving algorithms for the IEEE 802.15.4 transmission protocol (designed for ultra wideband, low-power transmission) will be developed, in conjunction with time-of-flight positioning schemes from higher OSI layers (such as ZigBee). Possible aspects to be investigated could include, e.g., the overall transmission quality with regards to channel impairments (noise/doppler/multipath fading), robustness against deviations in the transmitter/receiver LO frequency, problems in coexistence with other standards such as Bluetooth or WLAN and security measures against interferers (imposed by the localization of the TOF protocol).

Supervisor:

Student

• Diese Seite als PDF öffnen.

Implementation of SCFlip Decoders for Polar Codes

Description

-

Supervisor:

Student

• Diese Seite als PDF öffnen.

Complexity-adaptive Decoders for Polar Codes

Description

-

Supervisor:

Student