Search

The rapid adoption of Generative AI (GenAI) based on Large Language Models (LLMs) such as ChatGPT has recently and profoundly impacted education, offering transformative opportunities while raising significant concerns. In this study we present the results of a survey that investigates how 395 students aged 13 to 25 years old in France and Italy integrate LLMs into their educational routines. Key findings include the widespread use of these tools across all age groups and disciplines, with older students and male students demonstrating higher usage frequencies, particularly in scientific contexts. The results also show gender disparities, raising concerns about an emerging AI literacy and technological gender gap. Additionally, while most students utilise LLMs constructively, the lack of systematic proofreading and critical evaluation among younger users suggests potential risks to cognitive skills development, including critical thinking and foundational knowledge. The survey results underscore the need for educational institutions to adapt their curricula to integrate AI tools effectively, promoting ethical use, critical thinking, and awareness of AI limitations and environmental costs. This paper provides actionable recommendations for fostering equitable and effective cohabitation of LLMs and education while addressing emerging challenges., Comment: 33 pages + references

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in predictions, especially in data not seen during training. This is particularly problematic in semantic segmentation due to inherent class imbalance. Popular uncertainty quantification approaches are task-agnostic and fail to leverage spatial pixel correlations in uncertainty estimates, crucial in this task. In this work, a novel training methodology specifically designed for semantic segmentation is presented. Training samples are weighted by instance-wise uncertainty masks computed by an ensemble. This is shown to increase performance on minority classes, boost model generalization and robustness to domain-shift when compared to using the inverse of class proportions or no class weights at all. This method addresses the challenges of class imbalance and uncertainty estimation in semantic segmentation, potentially enhancing model performance and reliability across various applications.

This paper presents an iterative detection and decoding scheme along with an adaptive strategy to improve the selection of access points (APs) in a grant-free uplink cell-free scenario. With the requirement for the APs to have low-computational power in mind, we introduce a low-complexity scheme for local activity and data detection. At the central processing unit (CPU) level, we propose an adaptive technique based on local log-likelihood ratios (LLRs) to select the list of APs that should be considered for each device. Simulation results show that the proposed LLRs-based APs selection scheme outperforms the existing techniques in the literature in terms of bit error rate (BER) while requiring comparable fronthaul load., Comment: 3 figures, 8 pages

This paper proposes an iterative detection and decoding (IDD) scheme and an approach to improve the selection of access points (APs) in uplink cell-free massive multiple-antenna systems. A cost-effective scheme for selection of APs based on local log-likelihood ratios (LLRs) is developed that provides sufficient statistics to the central processing unit and selects which APs should be considered for each user. {Numerical results show that the proposed IDD scheme works very well and the proposed LLRs-based approach to select APs outperforms the existing techniques in terms of bit error rate and spectral efficiency while requiring a comparable fronthaul load., Comment: 4 figures, 7 pages

Deep Reinforcement Learning (DRL) is a quickly evolving research field rooted in operations research and behavioural psychology, with potential applications extending across various domains, including robotics. This thesis delineates the background of modern Reinforcement Learning (RL), starting with the framework constituted by the Markov decision processes, Markov properties, goals and rewards, agent-environment interactions, and policies. We explain the main types of algorithms commonly used in RL, including value-based, policy gradient, and actor-critic methods, with a special emphasis on DQN, A2C and PPO. We then give a short literature review on some widely adopted frameworks for implementing RL algorithms and environments. Subsequently, we present Bidimensional Gripper Environment (BGE), a virtual simulator based on the Pymunk physics engine we developed to analyse top-down bidimensional object manipulation. The methodology section frames our agent-environment interaction as a Markov decision process, such that we can apply our RL algorithms. We list various goal formulation strategies, including reward shaping and curriculum learning. We also employ different steps of observation preprocessing to reduce the computational workload required. In the experimental phase, we run through a series of scenarios of increasing difficulty. We start with a simple static scenario and then gradually increase the amount of stochasticity. Whenever the agents show difficulty in learning, we counteract by increasing the degree of reward shaping and curriculum learning. These experiments demonstrate the substantial limitations and pitfalls of model-free algorithms under changing dynamics. In conclusion, we present a summary of our findings and remarks. We then outline potential future work to improve our methodology and possibly expand to real-world systems.

This paper proposes an iterative detection and decoding (IDD) scheme for a cell free massive multiple input multiple output (CF-mMIMO) system. Users send coded data to the access points (APs), which is jointly detected at central processing unit (CPU). The symbols are exchanged iteratively in the form of log likelihood ratios (LLRs) between the detector and the low-density parity check codes (LPDC) decoder, increasing the coded system's performance. We propose a list-based multi-feedback diversity with successive interference cancellation (MF-SIC) to improve the performance of the CF-mMIMO. Furthermore, the proposed detector is compared with the parallel interference cancellation (PIC) and MF-PIC schemes. Finally, the bit error rate (BER) performance of CF-mMIMO is compared with the co-located mMIMO (Col-mMIMO)., Comment: 4 figures, 8 pages

Objective: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. Methods: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. Results: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. Conclusions: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. Significance: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity which may provide a enhanced classification of clinical outcomes.

In this work, we present a joint channel estimation, activity detection and data decoding scheme for massive machine-type communications. By including the channel and the a priori activity factor in the factor graph, we present the bilinear message-scheduling GAMP (BiMSGAMP), a message-passing solution that uses the channel decoder beliefs to refine the activity detection and data decoding. We include two message-scheduling strategies based on the residual belief propagation and the activity user detection in which messages are evaluated and scheduled in every new iteration. An analysis of the convergence of BiMSGAMP along with a study of its computational complexity is carried out. Numerical results show that BiMSGAMP outperforms state-of-the-art algorithms, highlighting the gains achieved by using the dynamic scheduling strategies and the effects of the channel decoding part in the system., Comment: 17 pages, 7 figures

Cardiac auscultation is one of the most cost-effective techniques used to detect and identify many heart conditions. Computer-assisted decision systems based on auscultation can support physicians in their decisions. Unfortunately, the application of such systems in clinical trials is still minimal since most of them only aim to detect the presence of extra or abnormal waves in the phonocardiogram signal, i.e., only a binary ground truth variable (normal vs abnormal) is provided. This is mainly due to the lack of large publicly available datasets, where a more detailed description of such abnormal waves (e.g., cardiac murmurs) exists. To pave the way to more effective research on healthcare recommendation systems based on auscultation, our team has prepared the currently largest pediatric heart sound dataset. A total of 5282 recordings have been collected from the four main auscultation locations of 1568 patients, in the process, 215780 heart sounds have been manually annotated. Furthermore, and for the first time, each cardiac murmur has been manually annotated by an expert annotator according to its timing, shape, pitch, grading, and quality. In addition, the auscultation locations where the murmur is present were identified as well as the auscultation location where the murmur is detected more intensively. Such detailed description for a relatively large number of heart sounds may pave the way for new machine learning algorithms with a real-world application for the detection and analysis of murmur waves for diagnostic purposes., Comment: 12 pages, 6 tables, 8 figures, in IEEE Journal of Biomedical and Health Informatics

In this work, based on the hybrid generalized approximate message passing (HyGAMP) algorithm, we propose the message-scheduling GAMP (MSGAMP) algorithm in order to address the problem of joint active device detection and channel estimation in an uplink grant-free massive MIMO system scenario. In MSGAMP, we apply three different scheduling techniques based on the Residual Belief Propagation (RBP) in which messages are generated using the latest available information. With a much lower computational cost than the state-of-the-art algorithms, MSGAMP-type schemes exhibits good performance in terms of activity error rate and normalized mean squared error, requiring a small number of iterations for convergence. %, Comment: 6 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2103.04486

In this letter, we propose a joint active device detection and channel estimation framework based on factor graphs for asynchronous uplink grant-free massive multiple-antenna systems. We then develop the message-scheduling GAMP (MSGAMP) algorithm to perform joint active device detection and channel estimation. In MSGAMP we apply scheduling techniques based on the residual belief propagation (RBP) and the activity user detection (AUD) in which messages are generated using the latest available information. MSGAMP-type schemes show a good performance in terms of activity error rate and normalized mean squared error, requiring a smaller number of iterations for convergence and lower complexity than state-of-the-art techniques., Comment: 5 figures, 2 tables, 6 pages

The main challenge of massive machine-type communications (mMTC) is the joint activity and signal detection of devices. The mMTC scenario with many devices transmitting data intermittently at low data rates and via very short packets enables its modelling as a sparse signal processing problem. In this work, we consider a grant-free system and propose a detection and decoding scheme that jointly detects activity and signals of devices. The proposed scheme consists of a list detection technique, an $l_0$-norm regularized activity-aware recursive least-squares algorithm, and an iterative detection and decoding (IDD) approach that exploits the device activity probability. In particular, the proposed list detection technique uses two candidate-list schemes to enhance the detection performance. We also incorporate the proposed list detection technique into an IDD scheme based on low-density parity-check codes. We derive uplink sum-rate expressions that take into account metadata collisions, interference and a variable activity probability for each user. A computational complexity analysis shows that the proposed list detector does not require a significant additional complexity over existing detectors, whereas a diversity analysis discusses its diversity order. Simulations show that the proposed scheme obtains a performance superior to existing suboptimal detectors and close to the oracle LMMSE detector., Comment: 11 figures, 15 pages

In this work, we propose an adaptive list-based decision feedback detector along with an $l_0$-norm regularized recursive least-squares algorithm that only requires pilot symbols (AA-CL-DF). The proposed detector employs a list strategy based on the signal constellation points to generate different candidates for detection. Simulation results show that the proposed AA-CL-DF successfully mitigates the error propagation and approaches the performance for the oracle LMMSE algorithm., Comment: 7 pages, 7 figures

This work studies the uplink of grant-free low data-rate massive machine-to-machine communications (mMTC) where devices are only active sporadically, which requires a joint activity and data detection at the receiver. We develop an adaptive decision feedback detector along with an $l_0$-norm regularized activity-aware recursive least-squares algorithm that only require pilot symbols. An iterative detection and decoding scheme based on low-density parity-check (LDPC) is also devised for signal detection in mMTC. Simulations show the performance of the proposed approaches against existing schemes., Comment: 9 pages, 3 figures, 1 table

In this work, we propose an activity-aware low-complexity multiple feedback successive interference cancellation (AA-MF-SIC) strategy for massive machine-type communications. The computational complexity of the proposed AA-MF-SIC is as low as the conventional SIC algorithm with very low additional complexity added. The simulation results show that the algorithm significantly outperforms the conventional SIC schemes and other proposals., Comment: 14 pages, 6 figures

Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a counterintuitive type of instability) more samples may yield poorer performance. Our new stability test with algorithms and easy to use software detects the instability phenomena. The test is aimed at researchers to test their networks for instabilities and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.

We introduce a framework for the reconstruction of the amplitude, phase and polarisation of an optical vector-field using calibration measurements acquired by an imaging device with an unknown linear transformation. By incorporating effective regularisation terms, this new approach is able to recover an optical vector-field with respect to an arbitrary representation system, which may be different from the one used in calibration. In particular, it enables the recovery of an optical vector-field with respect to a Fourier basis, which is shown to yield indicative features of increased scattering associated with tissue abnormalities. We demonstrate the effectiveness of our approach using synthetic holographic images as well as biological tissue samples in an experimental setting where measurements of an optical vector-field are acquired by a fibre endoscope, and observe that indeed the recovered Fourier coefficients are useful in distinguishing healthy tissues from lesions in early stages of oesophageal cancer.