RadioUNet: Fast Radio Map Estimation With Convolutional Neural Networks

Levie, Ron; Yapar, Çağkan; Kutyniok, Gitta; Caire, Giuseppe

doi:10.1109/twc.2021.3054977

Cited by 157 publications

(77 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Tx and Rx locations and the frequency band are adopted in [101] as input to train an ANN network to predict the amplitude, delay, phase, and cross polarization ratio at each location point, and thus can "playback" the MIMO channels. A similar approach was taken in [125]. Instead of using LSTM, a CNNbased pathloss and shadowing prediction is proposed in [102], where the coordinates of Rx and Tx, the physical environment information, i.e., terrain height, building height, and foliage height, and the visibility condition (LoS/NLoS) are used as input to predict the received power at each position.…”

Section: B Ml-enabled Channel Modeling and Predictionmentioning

confidence: 99%

Artificial Intelligence Enabled Radio Propagation for Communications—Part II: Scenario Identification and Channel Modeling

Huang

et al. 2022

IEEE Trans. Antennas Propagat.

105

View full text Add to dashboard Cite

This two-part paper investigates the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels. In Part I, we introduced AI and ML as well as provided a comprehensive survey on ML enabled channel characterization and antennachannel optimization, and in this part (Part II) we review state-ofthe-art literature on scenario identification and channel modeling here. In particular, the key ideas of ML for scenario identification and channel modeling/prediction are presented, and the widely used ML methods for propagation scenario identification and channel modeling and prediction are analyzed and compared. Based on the state-of-art, the future challenges of AI/ML-based channel data processing techniques are given as well.

show abstract

Section: B Ml-enabled Channel Modeling and Predictionmentioning

confidence: 99%

Artificial Intelligence Enabled Radio Propagation for Communications—Part II: Scenario Identification and Channel Modeling

Huang

et al. 2022

IEEE Trans. Antennas Propagat.

105

View full text Add to dashboard Cite

show abstract

“…The mask is optimized to produce low distortion in the model output after applying perturbations to the unselected features in the input while remaining relatively sparse. [8] also applied RDE to non-canonical input representations to explain model decisions in challenging domains such as audio classification [6] and radio-map estimation [14,13].…”

Section: Related Workmentioning

confidence: 99%

Cartoon Explanations of Image Classifiers

Kolek¹,

Nguyễn²,

Levie³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion explanation (RDE) framework. Natural images are roughly piece-wise smooth signals-also called cartoon images-and tend to be sparse in the wavelet domain. CartoonX is the first explanation method to exploit this by requiring its explanations to be sparse in the wavelet domain, thus extracting the relevant piece-wise smooth part of an image instead of relevant pixel-sparse regions. We demonstrate experimentally that CartoonX is not only highly interpretable due to its piece-wise smooth nature but also particularly apt at explaining misclassifications.

show abstract

“…These models rely on numeric data that is backed by physics as their basis for model creation. Other works aim to create models using intelligent algorithms such as machine learning and deep learning tools to learn features and estimate the link quality [8], [1], [9], [10], [11]. These works are more datadriven in the context of information and aim at detecting and learning from features of the provided data.…”

Section: Related Workmentioning

confidence: 99%

“…From attempted known works, it becomes apparent that models which rely on classification tend to underperform as they cannot predict the values but only classify them over ranges. Regression-based models are trained with numeric data from simulations (e.g., [11]), but and also tend to underperform as they fail to consider the impact of the surrounding environment of the wireless network. This raises the need for a regressive model with considerations for environmental and other numeric factors.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Indoor Wireless Coverage from 3D Floor Plans Using Deep Convolutional Neural Networks

Ansari

Tiyal

Flushing

et al. 2021

2021 IEEE 46th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

With significant advancements in Machine Learning and Deep Learning, Convolutional Neural Networks (CNNs) have shown promising results in handling classification and regression problems. We present 3DRSSNet, a model that can predict the signal strength of an Access point in a 3-D environment based on the 3-D floor map of the building. Our deep CNN approach differs from previous work in that (i) it can generalize to unseen environments, and (ii) to the best of our knowledge, it is the first work to utilize 3D maps to build a signal strength prediction model and validate its results using actual measured data. The proposed neural network model can help solve problems lie optimal access point placement and blind spot detection. Experimental results show that CNNs can predict indoor radio link quality with a performance with a Mean Absolute Error of 4.4 dBm and is able to generalize well to unseen environments.

show abstract

RadioUNet: Fast Radio Map Estimation With Convolutional Neural Networks

Cited by 157 publications

References 50 publications

Artificial Intelligence Enabled Radio Propagation for Communications—Part II: Scenario Identification and Channel Modeling

Artificial Intelligence Enabled Radio Propagation for Communications—Part II: Scenario Identification and Channel Modeling

Cartoon Explanations of Image Classifiers

Prediction of Indoor Wireless Coverage from 3D Floor Plans Using Deep Convolutional Neural Networks

Contact Info

Product

Resources

About