judithcodes Goto Github PK

kmeanscluster

The realization of k-means clustering algorithm by MATLAB

knn-and-kmeans

knnand kmeans algorithms

label-consistent-autoencoder

This is a MATLAB function implementing an autoencoder which incorporates label information.

large-scale-fading-decoding

Simulation code for “Large-Scale-Fading Decoding in Cellular Massive MIMO Systems with Spatially Correlated Channels,” by Trinh Van Chien, Christopher Mollén, and Emil Björnson, IEEE Transactions on Communications, vol. 67, no. 4, pp. 2746-2762, April 2019.

ldamp_based-channel-estimation

This code is for the following paper: H. He, C. Wen, S. Jin, and G. Y. Li, “Deep learning-based channel estimation for beamspace mmwave massive MIMO systems,” IEEE Wireless Commun. Lett., vol. 7, no. 5, pp. 852–855, Oct. 2018.

learn_data_science_in_3_months

This is the Curriculum for "Learn Data Science in 3 Months" By Siraj Raval on Youtube

learning-mmse-est

Julia code for the paper "Learning the MMSE Channel Estimator"

learnopencv

Learn OpenCV : C++ and Python Examples

lecture-examples

Sample scripts used in the lectures of the CEL (Communications Engineering Lab) at KIT

limited-feedback-channel-estimation-in-massive-mimo-systems

Today, plenty of cellular systems utilize frequency-division duplexing (FDD). Downlink training for channel state information in FDD is difficult since training and feedback overhead is proportional to the number of antennas at the base station, which is large in a Massive MIMO systems. To deal with the limited feedback mechanism of downlink channel in FDD Massive MIMO system, we can adopt the double directional model. This is applicable for the 5G systems to get high capacity and data rate. We analyse and test the performance of the Limited feedback channel with DD model via the MATLAB and we had the better performance rather than other models.

localization-in-wireless-sensor-networks-evaluation-and-comparison-of-the-optimization-methods

Sensor localization is a main component in any problem related to wireless sensor networks. The knowledge of sensor locations plays a major role in energy optimiza- tion, communication protocol designs and data analysis of wireless sensor networks. In this thesis we aim at gathering many of the algorithms introduced recently in the literature for sensor localization and categorize them in several meaningful cat- egories. We also study a particularly interesting optimization framework for finding the location of the sensors using their mutual distances. We introduce the use of simulated annealing based methods for sensor localization as a minimizer of any defined cost function for this purpose. Our simulation results confirm the usefulness of these approaches in practical setups.

low-rank-mimo-channel-estimation-from-one-bit-measurements

This directory contains the code required to reproduce the results in our ICASSP 2020 submission titled "Low-rank mmWave MIMO channel estimation in one-bit receivers"

lstm-anomaly-detect

Example code for neural-network-based anomaly detection of time-series data (uses LSTM)

lstm_anomaly_detector

A try to autoencode an LSTM to do anomaly detection

lstm_anomaly_thesis

Anomaly detection for temporal data using LSTMs

m.s.-thesis

M.S. Thesis: "Channel Allocation and Power Control for Device-to-Device Communications Underlaying Cellular Cellular Networks Incorporated With Deep Learning Assistance"

mabalgs

:bust_in_silhouette: Multi-Armed Bandit Algorithms Library (MAB) :cop:

machine-learning

Programming Assignments and Lectures for Andrew Ng's "Machine Learning" Coursera course

machine-learning-coursera-1

This repo is specially created for all the work done my me as a part of Coursera's Machine Learning Course.

machine-learning-with-python

Python code for common Machine Learning Algorithms

marlspectrumsharingv2x

Spectrum sharing in vehicular networks based on multi-agent reinforcement learning, IEEE Journal on Selected Areas in Communications

massive-mimo-hardware-impairments

Simulation code for “Massive MIMO Systems with Non-Ideal Hardware: Energy Efficiency, Estimation, and Capacity Limits” by Emil Björnson, Jakob Hoydis, Marios Kountouris, Mérouane Debbah, IEEE Transactions on Information Theory, vol. 60, no. 11, pp. 7112-7139, November 2014.

massive-mimo-hybrid-beamforming-matlab-example

A simple example with how hybrid beamforming is employed at the transmit end of a massive MIMO communications system.

massive-mimo-myths

Simulation code for “Massive MIMO: Ten Myths and One Critical Question” by Emil Björnson, Erik G. Larsson, Thomas L. Marzetta, IEEE Communications Magazine, vol. 54, no. 2, pp. 114-123, February 2016

massive-mimo-rician-channels

This code computes the spectral efficiency in the downlink of a Massive MIMO systems over Uncorrelated Rician Fading Channels. In particular, it generates Figs. 4 and 5 of a manuscript that is currently under review for publication on IEEE Transactions on Communications (submitted May 2018). The manuscript will be made available soon on arxiv.

massive-mimo-small-cells

Simulation code for “Massive MIMO and Small Cells: Improving Energy Efficiency by Optimal Soft-Cell Coordination” by Emil Björnson, Marios Kountouris, Mérouane Debbah, Proceedings of International Conference on Telecommunications (ICT), Casablanca, Morocco, May 2013.

massive_mimo1

Simulation codes for "Performance"

massivemimo-simulationcode-ruralscenario

massivemimobook

Book PDF and simulation code for the monograph "Massive MIMO Networks: Spectral, Energy, and Hardware Efficiency" by Emil Björnson, Jakob Hoydis and Luca Sanguinetti, published in Foundations and Trends in Signal Processing, 2017.

master-thesis

Source Code to my master's thesis with the topic "End-to-end optimisation of MIMO systems using deep learning autoencoders"