Search

Predicting program behavior without execution is a crucial and challenging task in software engineering. Traditional models often struggle to capture the dynamic dependencies and interactions within code. This paper introduces a novel machine learning-based framework called CodeFlow, designed to predict code coverage and detect runtime errors through Dynamic Dependencies Learning. By utilizing control flow graphs (CFGs), CodeFlow represents all possible execution paths and the relationships between different statements, providing a comprehensive understanding of program behavior. CodeFlow constructs CFGs to depict execution paths and learns vector representations for CFG nodes, capturing static control-flow dependencies. Additionally, it learns dynamic dependencies through execution traces, which reflect the impacts among statements during execution. This approach enables accurate prediction of code coverage and effective identification of runtime errors. Empirical evaluations demonstrate significant improvements in code coverage prediction accuracy and effective localization of runtime errors, outperforming existing models.

Reinforcement learning from human feedback plays a crucial role in aligning language models towards human preferences, traditionally represented through comparisons between pairs or sets of responses within a given context. While many studies have enhanced algorithmic techniques to optimize learning from such data, this work shifts focus to improving preference learning through a data-centric approach. Specifically, we propose enriching existing preference datasets with machine-generated rationales that explain the reasons behind choices. We develop a simple and principled framework to augment current preference learning methods with rationale information. Our comprehensive analysis highlights how rationales enhance learning efficiency. Extensive experiments reveal that rationale-enriched preference learning offers multiple advantages: it improves data efficiency, accelerates convergence to higher-performing models, and reduces verbosity bias and hallucination. Furthermore, this framework is versatile enough to integrate with various preference optimization algorithms. Overall, our findings highlight the potential of re-imagining data design for preference learning, demonstrating that even freely available machine-generated rationales can significantly boost performance across multiple dimensions. The code repository is available at https: //github.com/reds-lab/preference-learning-with-rationales, Comment: Data-Centric Human Preference Learning with Rationales

Speech emotion recognition is a challenging classification task with natural emotional speech, especially when the distribution of emotion types is imbalanced in the training and test data. In this case, it is more difficult for a model to learn to separate minority classes, resulting in those sometimes being ignored or frequently misclassified. Previous work has utilised class weighted loss for training, but problems remain as it sometimes causes over-fitting for minor classes or under-fitting for major classes. This paper presents the system developed by a multi-site team for the participation in the Odyssey 2024 Emotion Recognition Challenge Track-1. The challenge data has the aforementioned properties and therefore the presented systems aimed to tackle these issues, by introducing focal loss in optimisation when applying class weighted loss. Specifically, the focal loss is further weighted by prior-based class weights. Experimental results show that combining these two approaches brings better overall performance, by sacrificing performance on major classes. The system further employs a majority voting strategy to combine the outputs of an ensemble of 7 models. The models are trained independently, using different acoustic features and loss functions - with the aim to have different properties for different data. Hence these models show different performance preferences on major classes and minor classes. The ensemble system output obtained the best performance in the challenge, ranking top-1 among 68 submissions. It also outperformed all single models in our set. On the Odyssey 2024 Emotion Recognition Challenge Task-1 data the system obtained a Macro-F1 score of 35.69% and an accuracy of 37.32%.

Novice researchers often face difficulties in understanding a multitude of academic papers and grasping the fundamentals of a new research field. To solve such problems, the knowledge graph supporting research survey is gradually being developed. Existing keyword-based knowledge graphs make it difficult for researchers to deeply understand abstract concepts. Meanwhile, novice researchers may find it difficult to use ChatGPT effectively for research surveys due to their limited understanding of the research field. Without the ability to ask proficient questions that align with key concepts, obtaining desired and accurate answers from this large language model (LLM) could be inefficient. This study aims to help novice researchers by providing a fish-bone diagram that includes causal relationships, offering an overview of the research topic. The diagram is constructed using the issue ontology from academic papers, and it offers a broad, highly generalized perspective of the research field, based on relevance and logical factors. Furthermore, we evaluate the strengths and improvable points of the fish-bone diagram derived from this study's development pattern, emphasizing its potential as a viable tool for supporting research survey., Comment: This paper has been accepted by IEEE SMC 2024

Detecting the presence of animal vocalisations in nature is essential to study animal populations and their behaviors. A recent development in the field is the introduction of the task known as few-shot bioacoustic sound event detection, which aims to train a versatile animal sound detector using only a small set of audio samples. Previous efforts in this area have utilized different architectures and data augmentation techniques to enhance model performance. However, these approaches have not fully bridged the domain gap between source and target distributions, limiting their applicability in real-world scenarios. In this work, we introduce an new dataset designed to augment the diversity and breadth of classes available for few-shot bioacoustic event detection, building on the foundations of our previous datasets. To establish a robust baseline system tailored for the DCASE 2024 Task 5 challenge, we delve into an array of acoustic features and adopt negative hard sampling as our primary domain adaptation strategy. This approach, chosen in alignment with the challenge's guidelines that necessitate the independent treatment of each audio file, sidesteps the use of transductive learning to ensure compliance while aiming to enhance the system's adaptability to domain shifts. Our experiments show that the proposed baseline system achieves a better performance compared with the vanilla prototypical network. The findings also confirm the effectiveness of each domain adaptation method by ablating different components within the networks. This highlights the potential to improve few-shot bioacoustic sound event detection by further reducing the impact of domain shift.

We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically, WavCraft describes the content of raw audio materials in natural language and prompts the LLM conditioned on audio descriptions and user requests. WavCraft leverages the in-context learning ability of the LLM to decomposes users' instructions into several tasks and tackle each task collaboratively with the particular module. Through task decomposition along with a set of task-specific models, WavCraft follows the input instruction to create or edit audio content with more details and rationales, facilitating user control. In addition, WavCraft is able to cooperate with users via dialogue interaction and even produce the audio content without explicit user commands. Experiments demonstrate that WavCraft yields a better performance than existing methods, especially when adjusting the local regions of audio clips. Moreover, WavCraft can follow complex instructions to edit and create audio content on the top of input recordings, facilitating audio producers in a broader range of applications. Our implementation and demos are available at this https://github.com/JinhuaLiang/WavCraft.

Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the {\em Repo-level Semantic Graph} (RSG), a novel semantic graph structure that encapsulates the vast context of code repositories. Furthermore, RepoHyper leverages Expand and Refine retrieval method, including a graph expansion and a link prediction algorithm applied to the RSG, enabling the effective retrieval and prioritization of relevant code snippets. Our evaluations show that \tool markedly outperforms existing techniques in repository-level code completion, showcasing enhanced accuracy across various datasets when compared to several strong baselines. Our implementation of RepoHYPER can be found at https://github.com/FSoft-AI4Code/RepoHyper.

In this paper, we present a new ultra-low power method of indoor localization of smartphones (SM) based on zero-energy-devices (ZEDs) beacons instead of active wireless beacons. Each ZED is equipped with a unique identification number coded into a bit-sequence, and its precise position on the map is recorded. An SM inside the building is assumed to have access to the map of ZEDs. The ZED backscatters ambient waves from base stations (BSs) of the cellular network. The SM detects the ZED message in the variations of the received ambient signal from the BS. We accurately simulate the ambient waves from a BS of Orange 4G commercial network, inside an existing large building covered with ZED beacons, thanks to a ray-tracing-based propagation simulation tool. Our first performance evaluation study shows that the proposed localization system enables us to determine in which room a SM is located, in a realistic and challenging propagation scenario., Comment: Submitted to EUCAP 2024

The 3GPP has recently conducted a study on the Ambient Internet of Things (AIoT), with a particular emphasis on examining backscatter communications as one of the primary techniques under consideration. Previous investigations into Ambient Backscatter Communications (AmBC) within the long term evolution (LTE) downlink have shown that it is feasible to utilize the user equipment channel estimator as a receiver for demodulating frequency shift keyed (FSK) messages transmitted by the backscatter devices. In practical deployment scenarios, the backscattered link often experiences a low signal-to-noise ratio, leading to subpar bit error rate (BER) performance in the case of uncoded transmissions. In this paper, we propose the adoption of the same convolutional coding methodology for backscatter links that is already employed for LTE downlink control signals. This approach facilitates the reuse of identical demodulation functions at the modem for both control signals and backscattered AIoT messages. To assess the performance of the proposed scheme, we conducted experiments utilizing real LTE downlink signals generated by a mobile operator within an office environment. When compared to uncoded FSK, convolutional channel coding delivers a notable gain of approximately 6 dB at a BER of $10^{-3}$. Consequently, the AmBC system demonstrates a high level of reliability, achieving a BER of $10^{-3}$ at a Signal-to-Noise Ratio (SNR) of 5 dB.

Low-cost, resource-constrained, maintenance-free, and energy-harvesting (EH) Internet of Things (IoT) devices, referred to as zero-energy devices (ZEDs), are rapidly attracting attention from industry and academia due to their myriad of applications. To date, such devices remain primarily unsupported by modern IoT connectivity solutions due to their intrinsic fabrication, hardware, deployment, and operation limitations, while lacking clarity on their key technical enablers and prospects. Herein, we address this by discussing the main characteristics and enabling technologies of ZEDs within the next generation of mobile networks, specifically focusing on unconventional EH sources, multi-source EH, power management, energy storage solutions, manufacturing material and practices, backscattering, and low-complexity receivers. Moreover, we highlight the need for lightweight and energy-aware computing, communication, and scheduling protocols, while discussing potential approaches related to TinyML, duty cycling, and infrastructure enablers like radio frequency wireless power transfer and wake-up protocols. Challenging aspects and open research directions are identified and discussed in all the cases. Finally, we showcase an experimental ZED proof-of-concept related to ambient cellular backscattering., Comment: 8 pages, 4 Figures

Research surveys have always posed a challenge for beginner researchers who lack of research training. These researchers struggle to understand the directions within their research topic, and the discovery of new research findings within a short time. One way to provide intuitive assistance to beginner researchers is by offering relevant knowledge graphs(KG) and recommending related academic papers. However, existing navigation knowledge graphs primarily rely on keywords in the research field and often fail to present the logical hierarchy among multiple related papers clearly. Moreover, most recommendation systems for academic papers simply rely on high text similarity, which can leave researchers confused as to why a particular article is being recommended. They may lack of grasp important information about the insight connection between "Issue resolved" and "Issue finding" that they hope to obtain. To address these issues, this study aims to support research insight surveys for beginner researchers by establishing a hierarchical tree-structured knowledge graph that reflects the inheritance insight of research topics and the relevance insight among the academic papers., Comment: This paper has been accepted by 'The 18TH International Conference on INnovations in Intelligent SysTems and Applications (INISTA 2024)'

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and critical. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges of this popular and fundamental AI technique. In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the properties of the trigger pattern in the existing diffusion backdoor attacks, discovering the important role of distribution discrepancy in Trojan detection. Based on this finding, we propose a low-cost trigger detection mechanism that can effectively identify the poisoned input noise. We then take a further step to study the same problem from the attack side, proposing a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100\% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100\% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

Low-rank compression, a popular model compression technique that produces compact convolutional neural networks (CNNs) with low rankness, has been well-studied in the literature. On the other hand, low-rank training, as an alternative way to train low-rank CNNs from scratch, has been exploited little yet. Unlike low-rank compression, low-rank training does not need pre-trained full-rank models, and the entire training phase is always performed on the low-rank structure, bringing attractive benefits for practical applications. However, the existing low-rank training solutions still face several challenges, such as a considerable accuracy drop and/or still needing to update full-size models during the training. In this paper, we perform a systematic investigation on low-rank CNN training. By identifying the proper low-rank format and performance-improving strategy, we propose ELRT, an efficient low-rank training solution for high-accuracy, high-compactness, low-rank CNN models. Our extensive evaluation results for training various CNNs on different datasets demonstrate the effectiveness of ELRT.

Despite the promising performance of current 3D human pose estimation techniques, understanding and enhancing their generalization on challenging in-the-wild videos remain an open problem. In this work, we focus on the robustness of 2D-to-3D pose lifters. To this end, we develop two benchmark datasets, namely Human3.6M-C and HumanEva-I-C, to examine the robustness of video-based 3D pose lifters to a wide range of common video corruptions including temporary occlusion, motion blur, and pixel-level noise. We observe the poor generalization of state-of-the-art 3D pose lifters in the presence of corruption and establish two techniques to tackle this issue. First, we introduce Temporal Additive Gaussian Noise (TAGN) as a simple yet effective 2D input pose data augmentation. Additionally, to incorporate the confidence scores output by the 2D pose detectors, we design a confidence-aware convolution (CA-Conv) block. Extensively tested on corrupted videos, the proposed strategies consistently boost the robustness of 3D pose lifters and serve as new baselines for future research.

The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) have shown their promise in solving a wide variety of vision and language understanding tasks, only a few of them can be generalised to the audio domain without compromising their domain-specific capacity. In this work, we introduce Acoustic Prompt Turning (APT), a new adapter extending LLMs and VLMs to the audio domain by soft prompting only. Specifically, APT applies an instruction-aware audio aligner to generate soft prompts, conditioned on both input text and sounds, as language model inputs. To mitigate the data scarcity in the audio domain, a multi-task learning strategy is proposed by formulating diverse audio tasks in a sequence-to-sequence manner. Moreover, we improve the framework of audio language model by using interleaved audio-text embeddings as the input sequence. This improved framework imposes zero constraints on the input format and thus is capable of tackling more understanding tasks, such as few-shot audio classification and audio reasoning. To further evaluate the reasoning ability of audio networks, we propose natural language audio reasoning (NLAR), a new task that analyses across two audio clips by comparison and summarization. Experiments show that APT-enhanced LLMs (namely APT-LLMs) achieve competitive results compared to the expert models (i.e., the networks trained on the targeted datasets) across various tasks. We finally demonstrate the APT's ability in extending frozen VLMs to the audio domain without finetuning, achieving promising results in the audio-visual question and answering task. Our code and model weights are released at https://github.com/JinhuaLiang/APT.

Fractals are ubiquitous natural emergences that have gained increased attention in engineering applications, thanks to recent technological advancements enabling the fabrication of structures spanning across many spatial scales. We show how the geometries of fractals can be exploited to determine their important mechanical properties, such as the first and second moments, which physically correspond to the center of mass and the moment of inertia, using a family of complex fractals known as the dragons.

Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited. Transformers on the other hand are able to map global context through self-attention, but treat the spectrogram as a sequence of patches which is not flexible enough to capture irregular audio objects. In this work, we treat the spectrogram in a more flexible way by considering it as graph structure and process it with a novel graph neural architecture called ATGNN. ATGNN not only combines the capability of CNNs with the global information sharing ability of Graph Neural Networks, but also maps semantic relationships between learnable class embeddings and corresponding spectrogram regions. We evaluate ATGNN on two audio tagging tasks, where it achieves 0.585 mAP on the FSD50K dataset and 0.335 mAP on the AudioSet-balanced dataset, achieving comparable results to Transformer based models with significantly lower number of learnable parameters.

Ambient backscatter communication technology (AmBC) and a novel device category called zero-energy devices (ZED) have recently emerged as potential components for the forthcoming 6th generation (6G) networks. A ZED communicates with a smartphone without emitting additional radio waves, by backscattering ambient waves from base stations. Thanks to its very low consumption, a ZED powers itself by harvesting ambient light energy. However, the time variations of data traffic in cellular networks prevents AmBC to work properly. Recent works have demonstrated experimentally that a backscatter device could be detected by listening only ambient pilot signals (which are steady) instead of the whole ambient signal (which is bursty) of 4G. However, these experiments were run with a 4G base station emulator and a bulky energy greedy backscatter device. In this paper, for the first time, we demonstrate real-time AmBC on the field, with Orange commercial 4G network as ambient source and Orange Zero-Energy Device., Comment: 3 pages, 7 figures , 6Get2023

Reconfigurable intelligent surface (RIS) is a promising solution to boost coverage sustainably by reflecting waves from a transmitter to a receiver and acting as a low-power and passive relay. In this paper, for the first time, we demonstrate experimentally that a reconfigurable intelligent surface designed for sub6GHz, and using varactor technology, can perform three-dimensional reflective beamforming. This result is achieved with a RIS prototype of 984 unit-cells, thanks to a compact control circuit individually addressing and configuring the voltage of each unit-cell, with a distinct voltage. To our knowledge, this prototype configures 17 to 70 times more distinct voltages than in the state-of-the-art. The experimental results in an indoor environment show a 10 dB gain. They also show, for the first time, that producing such a new prototype is feasible with minimal energy footprint and environmental impact, thanks to refurbishing. Indeed, a reflectarray antenna originally designed for three-dimensional beamforming has been turned into a RIS.

This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Our system initially performs audio feature extraction using Continuous Wavelet transformation. This transformation converts the respiratory sound input into a two-dimensional spectrogram where both spectral and temporal features are presented. Then, our proposed deep learning architecture inspired by the Inception-residual-based backbone performs the spatial-temporal focusing and multi-head attention mechanism to classify respiratory anomalies. In this work, we evaluate our proposed models on the benchmark SPRSound (The Open-Source SJTU Paediatric Respiratory Sound) database proposed by the IEEE BioCAS 2023 challenge. As regards the Score computed by an average between the average score and harmonic score, our robust system has achieved Top-1 performance with Scores of 0.810, 0.667, 0.744, and 0.608 in Tasks 1-1, 1-2, 2-1, and 2-2, respectively., Comment: arXiv admin note: text overlap with arXiv:2303.04104

We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we designed CALM to retrieve the probability distribution of text-audio clips over classes using a set of audio-label pairs and combined it with CLAP's zero-shot classification results. Furthermore, we designed a training-free version of the Treff adapter by using CALM as a cosine similarity measure. Experiments showed that the proposed Treff adapter is comparable and even better than fully-supervised methods and adaptation methods in low-shot and data-abundant scenarios. While the Treff adapter shows that combining large-scale pretraining and rapid learning of domain-specific knowledge is non-trivial for obtaining generic representations for few-shot learning, it is still limited to audio classification tasks. In the future, we will explore how to use audio-language models in diverse audio domains.

Sleep abnormalities can have severe health consequences. Automated sleep staging, i.e. labelling the sequence of sleep stages from the patient's physiological recordings, could simplify the diagnostic process. Previous work on automated sleep staging has achieved great results, mainly relying on the EEG signal. However, often multiple sources of information are available beyond EEG. This can be particularly beneficial when the EEG recordings are noisy or even missing completely. In this paper, we propose CoRe-Sleep, a Coordinated Representation multimodal fusion network that is particularly focused on improving the robustness of signal analysis on imperfect data. We demonstrate how appropriately handling multimodal information can be the key to achieving such robustness. CoRe-Sleep tolerates noisy or missing modalities segments, allowing training on incomplete data. Additionally, it shows state-of-the-art performance when testing on both multimodal and unimodal data using a single model on SHHS-1, the largest publicly available study that includes sleep stage labels. The results indicate that training the model on multimodal data does positively influence performance when tested on unimodal data. This work aims at bridging the gap between automated analysis tools and their clinical utility., Comment: 10 pages, 4 figures, 2 tables, journal

Reconfigurable Intelligent Surfaces (RISs) constitute the key enabler for programmable electromagnetic propagation environments, and are lately being considered as a candidate physical-layer technology for the demanding connectivity, reliability, localization, and sustainability requirements of next generation wireless networks. In this paper, we first present the deployment scenarios for RIS-enabled smart wireless environments that have been recently designed within the ongoing European Union Horizon 2020 RISE-6G project, as well as a network architecture integrating RISs with existing standardized interfaces. We identify various RIS deployment strategies and sketch the core architectural requirements in terms of RIS control and signaling, depending on the RIS hardware architectures and respective capabilities. Furthermore, we introduce and discuss, with the aid of simulations and reflectarray measurements, two novel metrics that emerge in the context of RIS-empowered wireless systems: the RIS bandwidth and area of influence. Their extensive investigation corroborates the need for careful deployment and planning of the RIS technology in future networks., Comment: 43 pages, 21 figures, sumbitted for a journal publication. arXiv admin note: text overlap with arXiv:2203.13478

This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Initially, our system begins with audio feature extraction using Gammatone and Continuous Wavelet transformation. This step aims to transform the respiratory sound input into a two-dimensional spectrogram where both spectral and temporal features are presented. Then, our proposed system integrates Inception-residual-based backbone models combined with multi-head attention and multi-objective loss to classify respiratory anomalies. Instead of applying a simple concatenation approach by combining results from various spectrograms, we propose a Linear combination, which has the ability to regulate equally the contribution of each individual spectrogram throughout the training process. To evaluate the performance, we conducted experiments over the benchmark dataset of SPRSound (The Open-Source SJTU Paediatric Respiratory Sound) proposed by the IEEE BioCAS 2022 challenge. As regards the Score computed by an average between the average score and harmonic score, our proposed system gained significant improvements of 9.7%, 15.8%, 17.8%, and 16.1% in Task 1-1, Task 1-2, Task 2-1, and Task 2-2, respectively, compared to the challenge baseline system. Notably, we achieved the Top-1 performance in Task 2-1 and Task 2-2 with the highest Score of 74.5% and 53.9%, respectively.

Multimodal emotion recognition (MER) is a fundamental complex research problem due to the uncertainty of human emotional expression and the heterogeneity gap between different modalities. Audio and text modalities are particularly important for a human participant in understanding emotions. Although many successful attempts have been designed multimodal representations for MER, there still exist multiple challenges to be addressed: 1) bridging the heterogeneity gap between multimodal features and model inter- and intra-modal interactions of multiple modalities; 2) effectively and efficiently modelling the contextual dynamics in the conversation sequence. In this paper, we propose Cross-Modal RoBERTa (CM-RoBERTa) model for emotion detection from spoken audio and corresponding transcripts. As the core unit of the CM-RoBERTa, parallel self- and cross- attention is designed to dynamically capture inter- and intra-modal interactions of audio and text. Specially, the mid-level fusion and residual module are employed to model long-term contextual dependencies and learn modality-specific patterns. We evaluate the approach on the MELD dataset and the experimental results show the proposed approach achieves the state-of-art performance on the dataset., Comment: 6 pages, 2 figures

Accurately detecting emotions in conversation is a necessary yet challenging task due to the complexity of emotions and dynamics in dialogues. The emotional state of a speaker can be influenced by many different factors, such as interlocutor stimulus, dialogue scene, and topic. In this work, we propose a conversational speech emotion recognition method to deal with capturing attentive contextual dependency and speaker-sensitive interactions. First, we use a pretrained VGGish model to extract segment-based audio representation in individual utterances. Second, an attentive bi-directional gated recurrent unit (GRU) models contextual-sensitive information and explores intra- and inter-speaker dependencies jointly in a dynamic manner. The experiments conducted on the standard conversational dataset MELD demonstrate the effectiveness of the proposed method when compared against state-of the-art methods., Comment: 6 pages, 4 figures

Long Term Evolution (LTE) signal is ubiquitously present in electromagnetic (EM) background environment, which make it an attractive signal source for the ambient backscatter communications (AmBC). In this paper, we propose a system, in which a backscatter device (BD) introduces artificial Doppler shift to the channel which is larger than the natural Doppler but still small enough such that it can be tracked by the channel estimator at the User Equipment (UE). Channel estimation is done using the downlink cell specific reference signals (CRS) that are present regardless the UE being attached to the network or not. FSK was selected due to its robust operation in a fading channel. We describe the whole AmBC system, use two receivers. Finally, numerical simulations and measurements are provided to validate the proposed FSK AmBC performance.

Human sleep is cyclical with a period of approximately 90 minutes, implying long temporal dependency in the sleep data. Yet, exploring this long-term dependency when developing sleep staging models has remained untouched. In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose. We thus introduce a method for efficient long sequence modelling and propose a new deep learning model, L-SeqSleepNet, which takes into account whole-cycle sleep information for sleep staging. Evaluating L-SeqSleepNet on four distinct databases of various sizes, we demonstrate state-of-the-art performance obtained by the model over three different EEG setups, including scalp EEG in conventional Polysomnography (PSG), in-ear EEG, and around-the-ear EEG (cEEGrid), even with a single EEG channel input. Our analyses also show that L-SeqSleepNet is able to alleviate the predominance of N2 sleep (the major class in terms of classification) to bring down errors in other sleep stages. Moreover the network becomes much more robust, meaning that for all subjects where the baseline method had exceptionally poor performance, their performance are improved significantly. Finally, the computation time only grows at a sub-linear rate when the sequence length increases., Comment: This article has been published in IEEE Journal of Biomedical and Health Informatics (JBHI). Source code is available at http://github.com/pquochuy/l-seqsleepnet

Everyday sound recognition aims to infer types of sound events in audio streams. While many works succeeded in training models with high performance in a fully-supervised manner, they are still restricted to the demand of large quantities of labelled data and the range of predefined classes. To overcome these drawbacks, this work firstly curates a new database named FSD-FS for multi-label few-shot audio classification. It then explores how to incorporate audio taxonomy in few-shot learning. Specifically, this work proposes label-dependent prototypical networks (LaD-protonet) to exploit parent-children relationships between labels. Plus, it applies taxonomy-aware label smoothing techniques to boost model performance. Experiments demonstrate that LaD-protonet outperforms original prototypical networks as well as other state-of-the-art methods. Moreover, its performance can be further boosted when combined with taxonomy-aware label smoothing., Comment: submitted to ICASSP2023

Sound source localization is crucial in acoustic sensing and monitoring-related applications. In this paper, we do a comprehensive analysis of improvement in sound source localization by combining the direction of arrivals (DOAs) with their derivatives which quantify the changes in the positions of sources over time. This study uses the SALSA-Lite feature with a convolutional recurrent neural network (CRNN) model for predicting DOAs and their first-order derivatives. An update rule is introduced to combine the predicted DOAs with the estimated derivatives to obtain the final DOAs. The experimental validation is done using TAU-NIGENS Spatial Sound Events (TNSSE) 2021 dataset. We compare the performance of the networks predicting DOAs with derivative vs. the one predicting only the DOAs at low SNR levels. The results show that combining the derivatives with the DOAs improves the localization accuracy of moving sources.

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks. However, the structured sparse models obtained by the exiting works suffer severe performance degradation for both benign and robust accuracy, thereby causing a challenging dilemma between robustness and structuredness of the compact DNNs. To address this problem, in this paper, we propose CSTAR, an efficient solution that can simultaneously impose the low-rankness-based Compactness, high STructuredness and high Adversarial Robustness on the target DNN models. By formulating the low-rankness and robustness requirement within the same framework and globally determining the ranks, the compressed DNNs can simultaneously achieve high compression performance and strong adversarial robustness. Evaluations for various DNN models on different datasets demonstrate the effectiveness of CSTAR. Compared with the state-of-the-art robust structured pruning methods, CSTAR shows consistently better performance. For instance, when compressing ResNet-18 on CIFAR-10, CSTAR can achieve up to 20.07% and 11.91% improvement for benign accuracy and robust accuracy, respectively. For compressing ResNet-18 with 16x compression ratio on Imagenet, CSTAR can obtain 8.58% benign accuracy gain and 4.27% robust accuracy gain compared to the existing robust structured pruning method., Comment: AAAI-23

Deep learning approaches for black-box modelling of audio effects have shown promise, however, the majority of existing work focuses on nonlinear effects with behaviour on relatively short time-scales, such as guitar amplifiers and distortion. While recurrent and convolutional architectures can theoretically be extended to capture behaviour at longer time scales, we show that simply scaling the width, depth, or dilation factor of existing architectures does not result in satisfactory performance when modelling audio effects such as fuzz and dynamic range compression. To address this, we propose the integration of time-varying feature-wise linear modulation into existing temporal convolutional backbones, an approach that enables learnable adaptation of the intermediate activations. We demonstrate that our approach more accurately captures long-range dependencies for a range of fuzz and compressor implementations across both time and frequency domain metrics. We provide sound examples, source code, and pretrained models to faciliate reproducibility.

Reconfigurable Intelligent Surface (RIS) is one of the key technologies for the upcoming 6th Generation (6G) communications, which can improve the signal strength at the receivers by adding artificial propagation paths. In the context of Downlink (DL) Multi-User Multiple-Input Multiple-Output (MU-MIMO) communications, designing an appropriate Beamforming (BF) scheme to take full advantage of this reconfigured propagation environment and improve the network capacity is a major challenge. Due to the spatial dimension provided by MIMO systems, independent data streams can be transmitted to multiple users simultaneously on the same radio resources. It is important to note that serving the same subset of users over a period of time may lead to undesired areas where the average Electromagnetic Field Exposure (EMFE) exceeds regulatory limits. To address this challenge, in this paper, we propose a Dual Gradient Descent (Dual-GD)-based Electromagnetic Field (EMF)-aware MU-MIMO BF scheme that aims to optimize the overall capacity under EMFE constraints in RIS-aided 6G cellular networks., Comment: 8 pages, 5 figures, published in the SWirNet workshop at the conference WiOpt 2022. arXiv admin note: substantial text overlap with arXiv:2209.14785

Reconfigurable Intelligent Surfaces (RISs) are one of the key emerging 6th Generation (6G) technologies that are expected to improve the link budgets between transmitters and receivers by adding artificial propagation paths. In such re-configured propagation environment, Downlink (DL) Multi-User Multi-Input Multi-Output (MU-MIMO) brings capacity improvement to cellular networks. It benefits from the spatial dimension offered by MIMO systems to enable simultaneous transmission of independent data streams to multiple users on the same radio resources by applying appropriate Beamforming (BF) schemes. However, in some cases, serving the same subset of users for a long period of time may cause some undesired regions where the average Electromagnetic Field Exposure (EMFE) exceeds the regulatory limits. To address this challenge, we propose in this paper a novel Electromagnetic Field (EMF) aware MU-MIMO BF scheme that aims to optimize the overall capacity under EMF constraints in RIS-aided cellular networks., Comment: 6 pages, 6 figures, to be published in IEEE GLOBECOM 2022

On the one hand, there is a growing demand for high throughput which can be satisfied thanks to the deployment of new networks using massive multiple-input multiple-output (MIMO) and beamforming. On the other hand, in some countries or cities, there is a demand for arbitrarily low electromagnetic field exposure (EMFE) of people not concerned by the ongoing communication, which slows down the deployment of new networks. Recently, it has been proposed to take the opportunity, when designing the future 6th generation (6G), to offer, in addition to higher throughput, a new type of service: arbitrarily low EMFE. Recent works have shown that a reconfigurable intelligent surface (RIS), jointly optimized with the base station (BS) beamforming can improve the received throughput at the desired location whilst reducing EMFE everywhere. In this paper, we introduce a new concept of a non-intended user (NIU). An NIU is a user of the network who requests low EMFE when he/she is not downloading/uploading data. An NIU lets his/her device, called NIU equipment (NIUE), exchange some control signaling and pilots with the network, to help the network avoid exposing NIU to waves that are transporting data for another user of the network: the intended user (IU), whose device is called IU equipment (IUE). Specifically, we propose several new schemes to maximize the IU throughput under an EMFE constraint at the NIU (in practice, an interference constraint at the NIUE). Several propagation scenarios are investigated. Analytical and numerical results show that proper power allocation and beam optimization can remarkably boost the EMFE-constrained system's performance with limited complexity and channel information., Comment: 6 pages, 6 figures. Accepted in Globecom 2022 Workshop

Personalized longitudinal disease assessment is central to quickly diagnosing, appropriately managing, and optimally adapting the therapeutic strategy of multiple sclerosis (MS). It is also important for identifying the idiosyncratic subject-specific disease profiles. Here, we design a novel longitudinal model to map individual disease trajectories in an automated way using sensor data that may contain missing values. First, we collect digital measurements related to gait and balance, and upper extremity functions using sensor-based assessments administered on a smartphone. Next, we treat missing data via imputation. We then discover potential markers of MS by employing a generalized estimation equation. Subsequently, parameters learned from multiple training datasets are ensembled to form a simple, unified longitudinal predictive model to forecast MS over time in previously unseen people with MS. To mitigate potential underestimation for individuals with severe disease scores, the final model incorporates additional subject-specific fine-tuning using data from the first day. The results show that the proposed model is promising to achieve personalized longitudinal MS assessment; they also suggest that features related to gait and balance as well as upper extremity function, remotely collected from sensor-based assessments, may be useful digital markers for predicting MS over time.

Long Term Evolution (LTE) systems provide ubiquitous coverage for mobile communications, which makes it a promising candidate to be used as a signal source in the ambient backscatter communications. In this paper, we propose a system in which a backscatter device modulates the ambient LTE signal by changing its reflection coefficient and the receiver uses the LTE Cell Specific Reference Signals (CRS) to estimate the channel and demodulates the backscattered signal from the obtained channel impulse response estimates. We first outline the overall system, discuss the receiver operation, and then provide experimental evidence on the practicality of the proposed system., Comment: 4 pages, 5 figures, IEEE RFID-TA 2022