Source Localization Tasks Research Articles

Locating the Source of Information in Social Networks using Critical Nodes

Locating the information source within social networks is crucial to understand information propagation. The source can be detected based on specific nodes known as observation nodes, and identifying them is a critical challenge that can significantly affect the accuracy of identification. To address this issue, this study proposes a novel source detection approach based on the Susceptible-Infected (SI) model and the Critical Node Problem (CNP). CNP involves identifying a subset of nodes within a graph whose removal results in the maximum reduction of a given connectivity metric, thereby isolating significant areas within the graph. A heuristic algorithm was developed, grounded in the maximal independent set for general graphs to solve the CNP, allowing the identification of the most crucial observation nodes that enhance the accuracy and using the data recorded from them to estimate the localization of the source. Experimental evaluations on various real-world networks showed that the proposed approach achieved a source detection accuracy of up to 89%, outperforming existing methods. These results demonstrate the robustness of the proposed approach, highlighting its potential to significantly improve accuracy in network-based source localization tasks across multiple applications.

Assessing Ambisonics Sound Source Localization by Means of Virtual Reality and Gamification Tools

Sound localization is a key area of interest in auditory research, especially in complex acoustic environments. This study evaluates the impact of incorporating higher-order Ambisonics (HOA) with virtual reality (VR) and gamification tools on sound source localization. The research addresses the current limitations in VR audio systems, particularly the lack of native support for HOA in game engines like Unreal Engine (UE). A novel framework was developed, combining UE for VR graphics rendering and Max for HOA audio processing. Participants performed sound source localization tasks in two VR environments using a head-mounted display (HMD). The assessment included both horizontal and vertical plane localization. Gamification elements were introduced to improve engagement and task comprehension. Results showed significant improvements in horizontal localization accuracy, although challenges remained in back localization. The findings underscore the potential of VR and gamification to enhance auditory tests, reducing test duration and participant fatigue. This research contributes to the development of immersive and interactive audio experiences, highlighting the broader applications of VR beyond entertainment.

GLFER-Net: a polyphonic sound source localization and detection network based on global-local feature extraction and recalibration

Polyphonic sound source localization and detection (SSLD) task aims to recognize the categories of sound events, identify their onset and offset times, and detect their corresponding direction-of-arrival (DOA), where polyphonic refers to the occurrence of multiple overlapping sound sources in a segment. However, vanilla SSLD methods based on convolutional recurrent neural network (CRNN) suffer from insufficient feature extraction. The convolutions with kernel of single scale in CRNN fail to adequately extract multi-scale features of sound events, which have diverse time-frequency characteristics. It results in that the extracted features lack fine-grained information helpful for the localization of sound sources. In response to these challenges, we propose a polyphonic SSLD network based on global-local feature extraction and recalibration (GLFER-Net), where the global-local feature (GLF) extractor is designed to extract the multi-scale global features through an omni-directional dynamic convolution (ODConv) layer and multi-scale feature extraction (MSFE) module. The local feature extraction (LFE) unit is designed for capturing detailed information. Besides, we design a feature recalibration (FR) module to emphasize the crucial features along multiple dimensions. On the open datasets of Task3 in DCASE 2021 and 2022 Challenges, we compared our proposed GLFER-Net with six and four SSLD methods, respectively. The results show that the GLFER-Net achieves competitive performance. The modules we designed are verified to be effective through a series of ablation experiments and visualization analyses.

MIRACLE—a microphone array impulse response dataset for acoustic learning

This work introduces a large dataset comprising impulse responses of spatially distributed sources within a plane parallel to a planar microphone array. The dataset, named MIRACLE, encompasses 856,128 single-channel impulse responses and includes four different measurement scenarios. Three measurement scenarios were conducted under anechoic conditions. The fourth scenario includes an additional specular reflection from a reflective panel. The source positions were obtained by uniformly discretizing a rectangular source plane parallel to the microphone for each scenario. The dataset contains three scenarios with a spatial resolution of 23mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$23\\,\ extrm{mm}$$\\end{document} at two different source-plane-to-array distances, as well as a scenario with a resolution of 5mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$5\\,\ extrm{mm}$$\\end{document} for the shorter distance. In contrast to existing room impulse response datasets, the accuracy of the provided source location labels is assessed and additional metadata, such as the directivity of the loudspeaker used for excitation, is provided. The MIRACLE dataset can be used as a benchmark for data-driven modelling and interpolation methods as well as for various acoustic machine learning tasks, such as source separation, localization, and characterization. Two timely applications of the dataset are presented in this work: the generation of microphone array data for data-driven source localization and characterization tasks and data-driven model order reduction.

Graph contrastive learning for source localization in social networks

In real-world scenarios, rapidly and accurately identifying sources of fake news or disease outbreaks is crucial for public safety. Existing deep learning methods for source localization tasks entirely rely on supervised learning, which requires a large amount of labeled data. Recently, the emerging self-supervised learning (SSL) methods have significantly reduced the reliance on labeled data. Nevertheless, the investigation of SSL for source localization tasks remains unexplored. In this work, we are the first to adapt SSL for source localization tasks, specifically employing graph contrastive learning (GCL). Yet, directly applying GCL to source localization tasks faces two challenges: 1) existing data augmentation strategies are not well-suited for source localization tasks; 2) extremely low-dimensional node features potentially compromise the quality of learned node representations. To address these challenges, we introduce a Source Localization with Graph Contrastive Learning (SL-GCL) framework. Firstly, we propose a data augmentation strategy which exploits the inherent stochasticity of propagation. Secondly, we design a feature enrichment module to expand the feature dimensions. Finally, our experiments on six real-world networks demonstrate that SL-GCL outperforms state-of-the-art methods and exhibits remarkable transferability across different networks and propagation patterns.

Gas source localization using Dueling Deep Q-Network with an olfactory quadruped robot

Gas source localization is one of the most common applications of a gas-sensitive mobile robot. However, most of the existing work focuses on rule-based algorithms for wheeled robots, which are difficult to apply in complex terrain with obstacles. In this article, we propose an olfactory quadruped robot to perform the gas source localization task using the Dueling Deep Q-Network (Dueling DQN) algorithm. For training, we designed a set of environments and imported gas dispersion data from computational fluid dynamics (CFD) software to construct a simulator. The olfactory quadruped robot was trained in this simulator using the Dueling DQN algorithm to learn how to find the gas source. The trained neural network was then deployed on the olfactory quadruped robot. Our method has been tested in both simulation and real environments. The olfactory quadruped robot can traverse rugged terrain in real experiments and efficiently find gas sources, demonstrating that our method is highly robust and has important practical value.

Collaborative robotics and adaptive machines laboratory – research advances in autonomous systems, advanced manufacturing, and healthcare

This report summarizes the recent research projects carried out at the Collaborative Robotics and Adaptive Machines Laboratory, Old Dominion University. The topics include collaborative robotics strategies for non-repetitive micro-drilling tasks, hand-held robots for spillage-free specimen retrieval tasks, development of a three-dimensional simulator for autonomous underwater vehicles, and enhancing search efficiency of glowworm-inspired robotic swarms for multiple source localization tasks. Research in these areas has applications in autonomous systems, advanced manufacturing, and health care.

PGSL: A probabilistic graph diffusion model for source localization

Source localization, as a reverse problem of the graph diffusion, bears paramount significance for a multitude of applications, such as tracking social rumors, detecting computer viruses, and finding epidemic spreaders. However, the innate uncertainty of the diffusion process complicates this task — different source nodes can result in similar or identical diffusions over time, making the source localization task a complex, ill-posed problem. Most existing solutions utilize deterministic techniques and therefore cannot model the diffusion uncertainty of source nodes. Moreover, current probabilistic approaches are inefficient to conduct smooth transformations with variational inference. To overcome these limitations, we propose a probabilistic framework using normalizing flows with invertible transformations and novel objective optimization methods to explicitly model the uncertainty of the diffusion sources. Moreover, graph neural networks are leveraged to encapsulate propagation patterns between the observed diffusion and sources of high uncertainty. Extensive experiments conducted on six distinct networks demonstrate the effectiveness of our model over strong baselines, up to 11.8% and 8.2% improvements in terms of F1 and AUC, respectively, on Twitter dataset under real-world diffusion.

Spatial-temporal graph convolutional networks (STGCN) based method for localizing acoustic emission sources in composite panels

A novel spatial–temporal graph convolutional networks (STGCN) based method for the regression task of localizing acoustic emission (AE) sources in composite panels is proposed. This is the first time that graph convolutional networks are introduced into the AE source localization task. Data generated by AE sensor networks is represented by a graph structure, in which the temporal features extracted from AE waveforms using one-dimensional convolutional neural networks (1D-CNN) and the spatial information of sensors constitute the node features. An adaptive distance-based adjacency matrix calculation method according to the geographical locations of AE sensors is further developed to represent the connectivity of the graph. Finally, the proposed method is experimentally validated on a glass fiber-reinforced plastic (GFRP) panel, and 5-fold cross-validation was carried out to evaluate the performance of the method effectively. The results show that the proposed STGCN method has a high performance in damage source localization and it significantly outperforms other methods.

Integrating modeled environmental variability into neural network training for underwater source localization.

Supervised machine learning (ML) is a powerful tool that has been applied to many fields of underwater acoustics, including acoustic inversion. ML algorithms depend on the existence of extensive labeled datasets, which are difficult to obtain for the task of underwater source localization. A feed-forward neural network (FNN) trained on imbalanced or biased data may end up suffering from a problem analogous to model mismatch in matched field processing (MFP), that is, producing incorrect results due to a difference between the environment sampled by the training data and the actual environment. To overcome this issue, physical and numerical propagation models can act as data augmentation tools to compensate for the lack of comprehensive acoustic data. This paper examines how modeled data can be effectively used for training FNNs. Mismatch tests compare the output from a FNN and MFP and show that the network becomes more robust to various kinds of mismatches when trained on diverse environments. A systematic analysis of how the training dataset's variability impacts a FNN's localization performance on experimental data is carried out. Results show that networks trained with synthetic data achieve better and more robust performance than regular MFP when environment variability is taken into account.

Listen to the Brain-Auditory Sound Source Localization in Neuromorphic Computing Architectures.

Conventional processing of sensory input often relies on uniform sampling leading to redundant information and unnecessary resource consumption throughout the entire processing pipeline. Neuromorphic computing challenges these conventions by mimicking biology and employing distributed event-based hardware. Based on the task of lateral auditory sound source localization (SSL), we propose a generic approach to map biologically inspired neural networks to neuromorphic hardware. First, we model the neural mechanisms of SSL based on the interaural level difference (ILD). Afterward, we identify generic computational motifs within the model and transform them into spike-based components. A hardware-specific step then implements them on neuromorphic hardware. We exemplify our approach by mapping the neural SSL model onto two platforms, namely the IBM TrueNorth Neurosynaptic System and SpiNNaker. Both implementations have been tested on synthetic and real-world data in terms of neural tunings and readout characteristics. For synthetic stimuli, both implementations provide a perfect readout (100% accuracy). Preliminary real-world experiments yield accuracies of 78% (TrueNorth) and 13% (SpiNNaker), RMSEs of 41∘ and 39∘, and MAEs of 18∘ and 29∘, respectively. Overall, the proposed mapping approach allows for the successful implementation of the same SSL model on two different neuromorphic architectures paving the way toward more hardware-independent neural SSL.

Visual Sound Localization in the Wild by Cross-Modal Interference Erasing

The task of audiovisual sound source localization has been well studied under constrained scenes, where the audio recordings are clean. However, in real world scenarios, audios are usually contaminated by off screen sound and background noise. They will interfere with the procedure of identifying desired sources and building visual sound connections, making previous studies nonapplicable. In this work, we propose the Interference Eraser (IEr) framework, which tackles the problem of audiovisual sound source localization in the wild. The key idea is to eliminate the interference by redefining and carving discriminative audio representations. Specifically, we observe that the previous practice of learning only a single audio representation is insufficient due to the additive nature of audio signals. We thus extend the audio representation with our Audio Instance Identifier module, which clearly distinguishes sounding instances when audio signals of different volumes are unevenly mixed. Then we erase the influence of the audible but off screen sounds and the silent but visible objects by a Cross modal Referrer module with cross modality distillation. Quantitative and qualitative evaluations demonstrate that our framework achieves superior results on sound localization tasks, especially under real world scenarios.

Coarray MUSIC-Group Delay: High-Resolution Source Localization Using Non-Uniform Arrays

Non-uniform linear arrays (NULA) operate in the difference coarray domain to localize more sources than the number of physical sensors. Usually, the spectral magnitude of the subspace-based coarray MUSIC algorithm is used for this task of underdetermined source localization. However, the phase spectrum of coarray MUSIC, which has not yet been utilized, exhibits sharp transitions at the direction of arrival (DOA) of the respective sources. As a result, the negative differential of this phase called the coarray group delay shows peaks at the DOAs. In this correspondence, a new source localization technique called the coarray MUSIC-Group delay (coarray MGD) described as the product of the coarray-MUSIC magnitude and the coarray group delay function is introduced. It is shown that as long as the difference coarray of the NULA is a uniform linear array (ULA), the group delay function displays an additive property in the coarray spatial domain. Owing to this property, the proposed coarray MGD technique is able to localize and resolve more closely-spaced sources than the coarray MUSIC magnitude method. Numerical simulations are performed to validate the high resolution property of the proposed method.

A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study

Robotic odor/gas source localization is a widely studied field, but most of the existing works are about rule-based algorithms. In this paper, the Deep Q-Network algorithm is applied to solve the odor source localization problem. An odor hits distribution model is proposed to model the odor concentration distribution in indoor environments, taking the dispersion by airflow, the odor molecular random walk, and the obstacles into account. The Deep Q-Network takes the stacked historic measurement data as the input and outputs the expected cumulative future reward of actions of the robots. The network is trained through 35,000 repeated episodes of random odor source localization tasks. The Deep Q-Network method is evaluated under four different environment settings in a simplified simulator and compared with two widely used odor source localization algorithms. The evaluation results demonstrate the advantages of the proposed algorithm. The algorithm is also validated in more complex indoor environments.

Audio-Visual Localization by Synthetic Acoustic Image Generation

Acoustic images constitute an emergent data modality for multimodal scene understanding. Such images have the peculiarity to distinguish the spectral signature of sounds coming from different directions in space, thus providing richer information than the one derived from mono and binaural microphones. However, acoustic images are typically generated by cumbersome microphone arrays, which are not as widespread as ordinary microphones mounted on optical cameras. To exploit this empowered modality while using standard microphones and cameras we propose to leverage the generation of synthetic acoustic images from common audio-video data for the task of audio-visual localization. The generation of synthetic acoustic images is obtained by a novel deep architecture, based on Variational Autoencoder and U-Net models, which is trained to reconstruct the ground truth spatialized audio data collected by a microphone array, from the associated video and its corresponding monaural audio signal. Namely, the model learns how to mimic what an array of microphones can produce in the same conditions. We assess the quality of the generated synthetic acoustic images on the task of unsupervised sound source localization in a qualitative and quantitative manner, while also considering standard generation metrics. Our model is evaluated by considering both multimodal datasets containing acoustic images, used for the training, and unseen datasets containing just monaural audio signals and RGB frames, showing to reach more accurate localization results as compared to the state of the art.

A novel plume tracking method in partial 3D diffusive environments using multi-sensor fusion

In recent years, dangerous gas leakage has led to serious consequences in social security. Pervious strategies for locating the odor sources were carried out in 2D environments or the gas sensors were installed at a fixed height, ignoring the characteristics of plume distribution in 3D environments. In some cases, strategies developed in 2D environments may be completely ineffective when be applied to 3D environments. To enhance the success rate and rapidity, a novel method of odor source location in partial 3D diffusive environments based on multi-sensor fusion is proposed. Considering the suspected source existed and weak wind environments, machine olfactory and vision information are both employed to track the plumes and identify its source. To enhance the speed of plume searching and the reliability of plume tracking in the early stages, an autonomous mobile robot (AMR) simulates the social mechanism and hunting behaviors of the gray wolf population and tracks the plumes. A technical strategy is also designed to enable the AMR to complete the task of gas source location successfully and the subsumption architecture is adopted to define and arbitrate behavior priorities to coordinate different behaviors in this paper. The on-site test results show that the average positioning error is 0.13 m, the average running time is 147.7 s and the average distance traveled is 21.35 m. The results show that the proposed method is competent to accomplish the task of leakage gas source localization in partial 3D diffusive environments.

Head‐related transfer function–reserved time‐frequency masking for robust binaural sound source localization

Various time-frequency (T-F) masks are being applied to sound source localization tasks. Moreover, deep learning has dramatically advanced T-F mask estimation. However, existing masks are usually designed for speech separation tasks and are suitable only for single-channel signals. A novel complex-valued T-F mask is proposed that reserves the head-related transfer function (HRTF), customized for binaural sound source localization. In addition, because the convolutional neural network that is exploited to estimate the proposed mask takes binaural spectral information as the input and output, accurate binaural cues can be preserved. Compared with conventional T-F masks that emphasize single speech source–dominated T-F units, HRTF-reserved masks eliminate the speech component while keeping the direct propagation path. Thus, the estimated HRTF is capable of extracting more reliable localization features for the final direction of arrival estimation. Hence, binaural sound source localization guided by the proposed T-F mask is robust under noisy and reverberant acoustic environments. The experimental results demonstrate that the new T-F mask is superior to conventional T-F masks and lead to the better performance of sound source localization in adverse environments.

Multimodal fusion for indoor sound source localization

To identify the localization of indoor sound source, especially when attempted using only a single microphone, it is a challenging problem to machine learning. To address these issues, this paper presents a distinct novel solution based on fusing visual and acoustic models. Therefore, we propose two novel approaches. First, to estimate orientation of vocal object in a stable manner, we employ the visual approach as estimation model, where we develop a robust image feature representation method that adopts Fourier analysis to efficiently extract polar descriptors. Second the distance information is estimated by calculating the signal difference between transmit receive ends. To implement these, we use phoneme-level hidden Markov models (HMMs) extracted from clean speech sound, to estimate the acoustic transfer function (ATF), which can capture the speech signal as a network of phoneme HMMs. And using the separated frame sequences of the ATF, we can indicate the signal difference between two positions, which can be used to estimate the distance of sound source. Experimental results show that the proposed method can simultaneously extract the sound source parameters of direction and distance, and thus improves the verification task of sound source localization.

A Crowd-Based Efficient Fault-Proof Localization System for IoT and MCS

In this paper, an efficient and fault-proof active node selection approach for localization tasks in Internet of Things (IoT) and Mobile Crowd Sensing (MCS) systems is proposed. The proposed approach is resilient to the presence of anomalous nodes. Localization is the process of fusing data readings from multiple sensing nodes with the aim of finding the location of a specific target, such as radiation source, forest fires and noisy areas. Current active node selection systems for localization tasks perform algorithms like greedy and genetic methods over the whole Area of Interest (AoI). As such, a system that considers anomalous data is required to detect anomalies and perform localization over a large number of active nodes, which usually takes multiple iterations and is computationally costly. To overcome this, we propose a resilient localization approach which a) uses the median filter based image filtering technique to level out anomalous readings, b) uses the filtered readings to reduce the AoI to be around the target location without being influenced by anomalous nodes, c) detects and eliminates anomalies in the new AoI based on the deviation between filtered readings and original readings, and d) selects remaining nodes in new AoI for localization. As a result, there is a huge reduction in the complexity of active node selection and thus reduction in time taken by the system to perform the task of source localization. The efficacy of the proposed system is evaluated for radiation source localization tasks using simulated radiation dataset, by performing experiments for several test scenarios. The results demonstrate that the system is able to perform localization tasks in significantly reduced time and therefore generate near real-time results while also maintaining low localization error.

DMMAN: A two-stage audio–visual fusion framework for sound separation and event localization

Videos are used widely as the media platforms for human beings to touch the physical change of the world. However, we always receive the mixed sound from the multiple sound objects, and cannot distinguish and localize the sounds as the separate entities in videos. In order to solve this problem, a model named the Deep Multi-Modal Attention Network (DMMAN), is established to model the unconstrained video datasets for further finishing the sound source separation and event localization tasks in this paper. Based on the multi-modal separator and multi-modal matching classifier module, our model focuses on the sound separation and modal synchronization problems using two stage fusion of the sound and visual features. To link the multi-modal separator and multi-modal matching classifier modules, the regression and classification losses are employed to build the loss function of the DMMAN. The estimated spectrum masks and attention synchronization scores calculated by the DMMAN can be easily generalized to the sound source and event localization tasks. The quantitative experimental results show the DMMAN not only separates the high quality of the sound sources evaluated by Signal-to-Distortion Ratio and Signal-to-Interference Ratio metrics, but also is suitable for the mixed sound scenes that are never heard jointly. Meanwhile, DMMAN achieves better classification accuracy than other contrast baselines for the event localization tasks.