CentraleSupélec

About: CentraleSupélec is a based out in . It is known for research contribution in the topics: MIMO & Wireless network. The organization has 1330 authors who have published 2344 publications receiving 30533 citations. The organization is also known as: CentraleSupelec & CentraleSupelec of the Paris-Saclay University.

Dosimetry-Driven Quality Measure of Brain Pseudo Computed Tomography Generated From Deep Learning for MRI-Only Radiation Therapy Treatment Planning.

Abstract: Purpose This study aims to evaluate the impact of key parameters on the pseudo computed tomography (pCT) quality generated from magnetic resonance imaging (MRI) with a 3-dimensional (3D) convolutional neural network. Methods and Materials Four hundred two brain tumor cases were retrieved, yielding associations between 182 computed tomography (CT) and T1-weighted MRI (T1) scans, 180 CT and contrast-enhanced T1-weighted MRI (T1-Gd) scans, and 40 CT, T1, and T1-Gd scans. A 3D CNN was used to map T1 or T1-Gd onto CT scans and evaluate the importance of different components. First, the training set size’s influence on testing set accuracy was assessed. Moreover, we evaluated the MRI sequence impact, using T1-only and T1-Gd–only cohorts. We then investigated 4 MRI standardization approaches (histogram-based, zero-mean/unit-variance, white stripe, and no standardization) based on training, validation, and testing cohorts composed of 242, 81, and 79 patients cases, respectively, as well as a bias field correction influence. Finally, 2 networks, namely HighResNet and 3D UNet, were compared to evaluate the architecture’s impact on the pCT quality. The mean absolute error, gamma indices, and dose-volume histograms were used as evaluation metrics. Results Generating models using all the available cases for training led to higher pCT quality. The T1 and T1-Gd models had a maximum difference in gamma index means of 0.07 percentage point. The mean absolute error obtained with white stripe was 78 ± 22 Hounsfield units, which slightly outperformed histogram-based, zero-mean/unit-variance, and no standardization (P Conclusions Our best pCTs were generated using more than 200 samples in the training data set. Training with T1 only and T1-Gd only did not significantly affect performance. Regardless of the preprocessing applied, the dosimetry quality remained equivalent and relevant for potential use in clinical practice.

Dialogue Systems for Intelligent Human Computer Interactions.

Abstract: The most fundamental communication mechanism for interaction is dialogues involving speech, gesture, semantic and pragmatic knowledge. Various researches on dialogue management have been conducted focusing on standardized model for goal oriented applications using machine learning and deep learning models. The paper presents the overview on existing methods for dialogue manager training; their advantages and limitations. Furthermore, a new image-based method is used in Facebook bAbI Task 1 dataset in Out Of Vocabulary setting. The results show that using dialogue as an image performs well and helps dialogue manager in expanding out of vocabulary dialogue tasks in comparison to Memory Networks.

Age of Information With Prioritized Streams: When to Buffer Preempted Packets?

Abstract: In this paper, we consider N information streams sharing a common service facility. The streams are supposed to have different priorities based on their sensitivity. A higher priority stream will always preempt the service of a lower priority packet. By leveraging the notion of Stochastic Hybrid Systems (SHS), we investigate the Age of Information (AoI) in the case where each stream has its own waiting room; when preempted by a higher priority stream, the packet is stored in the waiting room for future resume. Interestingly, it will be shown that a "no waiting room" scenario, and consequently discarding preempted packets, is better in terms of average AoI in some cases. The exact cases where this happen are discussed and numerical results that corroborate the theoretical findings and highlight this trade-off are provided.

Linear Precoding Based on Truncated Polynomial Expansion—Part I: Large-Scale Single-Cell Systems

Abstract: Large-scale MIMO systems can yield a substantial improvement in spectral efficiency for future communication systems. Due to the finer spatial resolution achieved by a huge number of antennas at the base stations, these systems have shown to be robust to inter-user interference and the use of linear precoding is asymptotically optimal. However, from a practical point of view, most precoding schemes exhibit prohibitively high computational complexity as the system dimensions increase. For example, the near-optimal regularized zero forcing (RZF) precoding requires the inversion of a large matrix. This motivated our companion paper, where we proposed to solve the issue in singlecell multi-user systems by approximating the matrix inverse by a truncated polynomial expansion (TPE), where the polynomial coefficients are optimized to maximize the system performance. We have shown that the proposed TPE precoding with a small number of coefficients reaches almost the performance of RZF but never exceeds it. In a realistic multi-cell scenario involving large-scale multiuser MIMO systems, the optimization of RZF precoding has thus far not been feasible. This is mainly attributed to the high complexity of the scenario and the non-linear impact of the necessary regularizing parameters. On the other hand, the scalar weights in TPE precoding give hope for possible throughput optimization. Following the same methodology as in the companion paper, we exploit random matrix theory to derive a deterministic expression for the asymptotic signal-to-interference-and-noise ratio (SINR) for each user based on channel statistics. We also provide an optimization algorithm to approximate the weights that maximize the network-wide weighted max-min fairness. The optimization weights can be used to mimic the user throughput distribution of RZF precoding. Using simulations, we compare the network throughput of the proposed TPE precoding with that of the suboptimal RZF scheme and show that our scheme can achieve higher throughput using a TPE order of only 3.

Lower Bounds on the Capacity Regions of the Relay Channel and the Cooperative Relay-Broadcast Channel with Non-Causal Side Information.

Abstract: In this work, coding for the relay channel (RC) and the cooperative relay broadcast channel (RBC) controlled by random parameters are studied. In the first channel, the RC, information is transferred from the transmitter to the receiver through a multiplicity of nodes which all "simply" act as relays. In the second channel, the cooperative RBC, each intermediate node also acts as a receiver, i.e., it decodes a "private message". For each of these two channels, we consider the situation when side information (SI) Sn on the random parameters is non- causally provided to the transmitter and all the intermediate nodes but not the final receiver, and derive an achievable rate region based on the relays using the decode-and-forward scheme. In the special case when the channels are degraded Gaussian and the side information (SI) is additive i.i.d. Gaussian, we show that 1) the rate regions are tight and provide the corresponding capacity regions and 2) the state Sn does not affect these capacity regions, even though the final receiver has no knowledge of the state. For the degraded Gaussian RC, the results in this paper can be seen as an extension of those by Kim et al. to the case of more than one relay.