Noisy Settings Research Articles

Unraveling a Histopathological Needle-in-Haystack Problem: Exploring the Challenges of Detecting Tumor Budding in Colorectal Carcinoma Histology

Background: In this study focusing on colorectal carcinoma (CRC), we address the imperative task of predicting post-surgery treatment needs by identifying crucial tumor features within whole slide images of solid tumors, analogous to locating a needle in a histological haystack. We evaluate two approaches to address this challenge using a small CRC dataset. Methods: First, we explore a conventional tile-level training approach, testing various data augmentation methods to mitigate the memorization effect in a noisy label setting. Second, we examine a multi-instance learning (MIL) approach at the case level, adapting data augmentation techniques to prevent over-fitting in the limited data set context. Results: The tile-level approach proves ineffective due to the limited number of informative image tiles per case. Conversely, the MIL approach demonstrates success for the small dataset when coupled with post-feature vector creation data augmentation techniques. In this setting, the MIL model accurately predicts nodal status corresponding to expert-based budding scores for these cases. Conclusions: This study incorporates data augmentation techniques into a MIL approach, highlighting the effectiveness of the MIL method in detecting predictive factors such as tumor budding, despite the constraints of a limited dataset size.

Hybrid Adaptive Beamforming Approach for Antenna Array fed Parabolic Reflector for C-band Applications

This paper presents the design of a parabolic reflector fed through a patch antenna array feed to enhance the directivity and radiation properties. Adaptive beam formers steer and alter an array's beam pattern to increase signal reception and minimize interference. Weight selection is a critical difficulty in achieving low SLL and beam width. Low SLL and narrow beam reduce antenna radiation and reception. Adjusting the weights reduces SLL and tilts the nulls. Adaptive beam formers are successful signal processors if their array output converges to the required signal. Smart antenna weights can be determined using any window function. HPBW and SLL could be used to explore different algorithms. Both must be low for excellent smart antenna performance. In noisy settings, ACLMS and CLMS create narrow beams and side lobes. AANGD offers more control than CLMS and ACLMS. The blend of CLMS and ACLMS is more effective at signal convergence than CLMS and AANGD. It presents an alternative to the conventionally used horn-based feed network for C-band applications such as satellite communication. Broadside radiation patterns and 4x4 circular patch antenna arrays are used in the proposed design. 1400 aperture illumination is provided by the array's feed parabolic reflector, whose F/D ratio is 0.36. The proposed design's efficacy is assessed using simulation analysis.

Vectorized Evidential Learning for Weakly-supervised Temporal Action Localization.

With the explosive growth of videos, weakly-supervised temporal action localization (WS-TAL) task has become a promising research direction in pattern analysis and machine learning. WS-TAL aims to detect and localize action instances with only video-level labels during training. Modern approaches have achieved impressive progress via powerful deep neural networks. However, robust and reliable WS-TAL remains challenging and underexplored due to considerable uncertainty caused by weak supervision, noisy evaluation environment, and unknown categories in the open world. To this end, we propose a new paradigm, named vectorized evidential learning (VEL), to explore local-to-global evidence collection for facilitating model performance. Specifically, a series of learnable meta-action units (MAUs) are automatically constructed, which serve as fundamental elements constituting diverse action categories. Since the same meta-action unit can manifest as distinct action components within different action categories, we leverage MAUs and category representations to dynamically and adaptively learn action components and action-component relations. After performing uncertainty estimation at both category-level and unit-level, the local evidence from action components is accumulated and optimized under the Subject Logic theory. Extensive experiments on the regular, noisy, and open-set settings of three popular benchmarks show that VEL consistently obtains more robust and reliable action localization performance than state-of-the-arts.

From Pulses to Sleep Stages: Towards Optimized Sleep Classification Using Heart-Rate Variability.

More and more people quantify their sleep using wearables and are becoming obsessed in their pursuit of optimal sleep ("orthosomnia"). However, it is criticized that many of these wearables are giving inaccurate feedback and can even lead to negative daytime consequences. Acknowledging these facts, we here optimize our previously suggested sleep classification procedure in a new sample of 136 self-reported poor sleepers to minimize erroneous classification during ambulatory sleep sensing. Firstly, we introduce an advanced interbeat-interval (IBI) quality control using a random forest method to account for wearable recordings in naturalistic and more noisy settings. We further aim to improve sleep classification by opting for a loss function model instead of the overall epoch-by-epoch accuracy to avoid model biases towards the majority class (i.e., "light sleep"). Using these implementations, we compare the classification performance between the optimized (loss function model) and the accuracy model. We use signals derived from PSG, one-channel ECG, and two consumer wearables: the ECG breast belt Polar® H10 (H10) and the Polar® Verity Sense (VS), an optical Photoplethysmography (PPG) heart-rate sensor. The results reveal a high overall accuracy for the loss function in ECG (86.3 %, κ = 0.79), as well as the H10 (84.4%, κ = 0.76), and VS (84.2%, κ = 0.75) sensors, with improvements in deep sleep and wake. In addition, the new optimized model displays moderate to high correlations and agreement with PSG on primary sleep parameters, while measures of reliability, expressed in intra-class correlations, suggest excellent reliability for most sleep parameters. Finally, it is demonstrated that the new model is still classifying sleep accurately in 4-classes in users taking heart-affecting and/or psychoactive medication, which can be considered a prerequisite in older individuals with or without common disorders. Further improving and validating automatic sleep stage classification algorithms based on signals from affordable wearables may resolve existing scepticism and open the door for such approaches in clinical practice.

A Comparison of Listening Skills of Autistic and Non-Autistic Youth While Using and Not Using Remote Microphone Systems.

The purposes of this study were to compare (a) listening-in-noise (accuracy and effort) and (b) remote microphone (RM) system benefits between autistic and non-autistic youth. Groups of autistic and non-autistic youth that were matched on chronological age and biological sex completed listening-in-noise testing when wearing and not wearing an RM system. Listening-in-noise accuracy and listening effort were evaluated simultaneously using a dual-task paradigm for stimuli varying in type (syllables, words, sentences, and passages). Several putative moderators of RM system effects on outcomes of interest were also evaluated. Autistic youth outperformed non-autistic youth in some conditions on listening-in-noise accuracy; listening effort between the two groups was not significantly different. RM system use resulted in listening-in-noise accuracy improvements that were nonsignificantly different across groups. Benefits of listening-in-noise accuracy were all large in magnitude. RM system use did not have an effect on listening effort for either group. None of the putative moderators yielded effects of the RM system on listening-in-noise accuracy or effort for non-autistic youth that were significant and interpretable, indicating that RM system benefits did not vary according to any of the participant characteristics assessed. Contrary to expectations, autistic youth did not demonstrate listening-in-noise deficits compared to non-autistic youth. Both autistic and non-autistic youth appear to experience RM system benefits marked by large gains in listening-in-noise performance. Thus, the use of this technology in educational and other noisy settings where speech perception needs enhancement might be beneficial for both groups of children.

Harmonic retrieval using weighted lifted-structure low-rank matrix completion

In this paper, we investigate the problem of recovering the frequency components of a mixture of K complex sinusoids from a random subset of N equally-spaced time-domain samples. Because of the random subset, the samples are effectively non-uniform. Besides, the frequency values of each of the K complex sinusoids are assumed to vary continuously within a given range. For this problem, we propose a two-step strategy: (i) we first lift the incomplete set of uniform samples (unavailable samples are treated as missing data) into a structured matrix with missing entries, which is potentially low-rank; then (ii) we complete the matrix using a weighted nuclear minimization problem. We call the method a weighted lifted-structured (WLi) low-rank matrix recovery. Our approach can be applied to a range of matrix structures such as Hankel and double-Hankel, among others, and provides improvement over the unweighted existing schemes such as EMaC and DEMaC. We provide theoretical guarantees for the proposed method, as well as numerical simulations in both noiseless and noisy settings. Both the theoretical and the numerical results confirm the superiority of the proposed approach.

Hearing loss, depression, and cognition in younger and older adult CI candidates.

Hearing loss in old age is associated with cognitive decline and with depression. Our study aimed to investigate the relationship between hearing loss, cognitive decline, and secondary depressive symptoms in a sample of younger and older cochlear implant candidates with profound to severe hearing loss. This study is part of a larger cohort study designated to provide information on baseline data before CI. Sixty-one cochlear implant candidates with hearing loss from adulthood onwards (>18 years) were enrolled in this study. All had symmetrical sensorineural hearing loss in both ears (four-frequency hearing threshold difference of no more than 20 dB, PTA). Individuals with primary affective disorders, psychosis, below-average intelligence, poor German language skills, visual impairment, and a medical diagnosis with potential impact on cognition (e.g., neurodegenerative diseases,) were excluded. Four-frequency hearing thresholds (dB, PTA, better ear) were collected. Using the Abbreviated Profile of Hearing Aid Benefit, we assessed subjective hearing in noise. Clinical and subclinical depressive symptoms were assessed with the Beck Depression Inventory (BDI II). Cognitive status was assessed with a neurocognitive test battery. Our findings revealed a significant negative association between subjective hearing in noise (APHAB subscale "Background Noise") and BDII. However, we did not observe any link between hearing thresholds, depression, and cognition. Additionally, no differences emerged between younger (25-54 years) and older subjects (55-75 years). Unexpectedly, further unplanned analyses unveiled correlations between subjective hearing in quiet environments (APHAB) and cognitive performance [phonemic fluency (Regensburg Word Fluency), cognitive flexibility (TMTB), and nonverbal episodic memory (Nonverbal Learning Test), as well as subjective hearing of aversive/loud sounds (APHAB)], cognitive performance [semantic word fluency (RWT), and inhibition (Go/Nogo) and depression]. Duration of hearing loss and speech recognition at quiet (Freiburg Monosyllables) were not related to depression and cognitive performance. Impact of hearing loss on mood and cognition appears to be independent, suggesting a relationship with distinct aspects of hearing loss. These results underscore the importance of considering not only conventional audiometric measures like hearing thresholds but also variables related to hearing abilities during verbal communication in everyday life, both in quiet and noisy settings.

Medical federated learning with joint graph purification for noisy label learning

In terms of increasing privacy issues, Federated Learning (FL) has received extensive attention in medical imaging. Through collaborative training, FL can produce superior diagnostic models with global knowledge, while preserving private data locally. In practice, medical diagnosis suffers from intra-/inter-observer variability, thus label noise is inevitable in dataset preparation. Different from existing studies on centralized datasets, the label noise problem in FL scenarios confronts more challenges, due to data inaccessibility and even noise heterogeneity. In this work, we propose a federated framework with joint Graph Purification (FedGP) to address the label noise in FL through server and clients collaboration. Specifically, to overcome the impact of label noise on local training, we first devise a noisy graph purification on the client side to generate reliable pseudo labels by progressively expanding the purified graph with topological knowledge. Then, we further propose a graph-guided negative ensemble loss to exploit the topology of the client-side purified graph with robust complementary supervision against label noise. Moreover, to address the FL label noise with data silos, we propose a global centroid aggregation on the server side to produce a robust classifier with global knowledge, which can be optimized collaboratively in the FL framework. Extensive experiments are conducted on endoscopic and pathological images with the comparison under the homogeneous, heterogeneous, and real-world label noise for medical FL. Among these diverse noisy FL settings, our FedGP framework significantly outperforms denoising and noisy FL state-of-the-arts by a large margin. The source code is available at https://github.com/CUHK-AIM-Group/FedGP.

CNN‐SCNet: A CNN net‐based deep learning framework for infant cry detection in household setting

AbstractInfants are vulnerable to several health problems and cannot express their needs clearly. Whenever they are in a state of urgency and require immediate attention, they cry, which is a form of communication for them. Therefore, the parents of the infants always need to be alert and keep continuous supervision of their infants. However, parents cannot monitor their infants all the time. An infant monitoring system could be a possible solution to monitor the infants, determine when the infants are crying, and notify the parents immediately. Although many such systems are available, most cannot detect infant cries. Some systems have infant cry detection mechanisms, but those mechanisms are not very accurate in detecting infant cries because the mechanisms either include obsolete approaches or machine learning (ML) models that cannot identify infant cries from noisy household settings. To address this limitation, in this research, different conventional and hybrid ML models were developed and analyzed in detail to find out the best model for detecting infant cries in a household setting. A stacked classifier is proposed using different state‐of‐the‐art technologies, outperforming all other developed models. The proposed CNN‐SCNet's (CNN‐Stacked Classifier Network) precision, recall, and f1‐score were found to be 98.72%, 98.05%, and 98.39%, respectively. Infant monitoring systems can use this classifier to detect infant cries in noisy household settings.

Simultaneous estimation and clustering with finite mixture of nonparanormal graphical models

Graphical mixture models provide a powerful tool to visually depict conditional independencies or dependencies between heterogeneous high-dimensional data. When the random variables corresponding to the vertices are continuous, mixture component densities are assumed to be multivariate normal with different covariance matrices, leading to introduction of the Gaussian graphical mixture model (GGMM). The nonparanormal graphical mixture model (NGMM) replaces the restrictive normal assumption with a semiparametric Gaussian copula, which extends the nonparanormal graphical model and mixture models. Such an extension allows us to simultaneously estimate cluster assignments and cluster-specific graphical model structure. To enable such analyses, we propose a regularized estimation scheme with two forms of penalty function (conventional and unconventional) via the expectation-maximization algorithm to learn a finite mixture of nonparanormal graphical models. We illustrate the performance of our method through a simulation study under both ideal and noisy settings. We also apply the proposed methodology to a breast cancer data set to diagnose malignant or benign tumors in patients. The results showed that the combination of NGMM together with unconventional penalty, which was named as NGMM1 during this study, provides the most efficient approach in clustering and estimating the graphical model structure.

A robust and compact population code for competing sounds in auditory cortex.

Cortical circuits encoding sensory information consist of populations of neurons, yet how information aggregates via pooling individual cells remains poorly understood. Such pooling may be particularly important in noisy settings where single-neuron encoding is degraded. One example is the cocktail party problem, with competing sounds from multiple spatial locations. How populations of neurons in auditory cortex code competing sounds have not been previously investigated. Here, we apply a novel information-theoretic approach to estimate information in populations of neurons in mouse auditory cortex about competing sounds from multiple spatial locations, including both summed population (SP) and labeled line (LL) codes. We find that a small subset of neurons is sufficient to nearly maximize mutual information over different spatial configurations, with the labeled line code outperforming the summed population code and approaching information levels attained in the absence of competing stimuli. Finally, information in the labeled line code increases with spatial separation between target and masker, in correspondence with behavioral results on spatial release from masking in humans and animals. Taken together, our results reveal that a compact population of neurons in auditory cortex provides a robust code for competing sounds from different spatial locations.NEW & NOTEWORTHY Little is known about how populations of neurons within cortical circuits encode sensory stimuli in the presence of competing stimuli at other spatial locations. Here, we investigate this problem in auditory cortex using a recently proposed information-theoretic approach. We find a small subset of neurons nearly maximizes information about target sounds in the presence of competing maskers, approaching information levels for isolated stimuli, and provides a noise-robust code for sounds in a complex auditory scene.

Benchmarking of different optimizers in the variational quantum algorithms for applications in quantum chemistry.

Classical optimizers play a crucial role in determining the accuracy and convergence of variational quantum algorithms; leading algorithms use a near-term quantum computer to solve the ground state properties of molecules, simulate dynamics of different quantum systems, and so on. In the literature, many optimizers, each having its own architecture, have been employed expediently for different applications. In this work, we consider a few popular and efficacious optimizers and assess their performance in variational quantum algorithms for applications in quantum chemistry in a realistic noisy setting. We benchmark the optimizers with critical analysis based on quantum simulations of simple molecules, such as hydrogen, lithium hydride, beryllium hydride, water, and hydrogen fluoride. The errors in the ground state energy, dissociation energy, and dipole moment are the parameters used as yardsticks. All the simulations were carried out with an ideal quantum circuit simulator, a noisy quantum circuit simulator, and finally a noisy simulator with noise embedded from the IBM Cairo quantum device to understand the performance of the classical optimizers in ideal and realistic quantum environments. We used the standard unitary coupled cluster ansatz for simulations, and the number of qubits varied from two starting from the hydrogen molecule to ten qubits in hydrogen fluoride. Based on the performance of these optimizers in the ideal quantum circuits, the conjugate gradient, limited-memory Broyden-Fletcher-Goldfarb-Shanno bound, and sequential least squares programming optimizers are found to be the best-performing gradient-based optimizers. While constrained optimization by linear approximation (COBYLA) and Powell's conjugate direction algorithm for unconstrained optimization (POWELL) perform most efficiently among the gradient-free methods, in noisy quantum circuit conditions, simultaneous perturbation stochastic approximation, POWELL, and COBYLA are among the best-performing optimizers.

FPGA implementation of a sub-400ns 6G free-space optical wireless communications transmitter.

Future wireless networks are planned to service many applications with an Ultra Low-Latency (ULL) requirement. Numerous 6G systems have been proposed including more traditional electro-magnetic (EM) antenna transmissions and optical wireless communications (OWC). For extremely wide-band operation, the traditional approaches require digital pre-distortion and other processing techniques which, in turn, require more computational resources and processing times thus increasing latency. Alternatively, OWC has the potential for extremely wide bandwidths in 6G without the need for as much digital signal processing. In order to realise ULL performance, a minimum number of digital signal processing (DSP) blocks is required, as well as an optimal design of each of these. In this letter, we propose a DSP solution for ULL and peak to average power ratio (PAPR) reduction for OWC systems. Unitary checkerboard precoding - orthogonal frequency division multiplexing (UCP-OFDM) is chosen as the modulation scheme and has been implemented within a single digital block avoiding the use of standard OFDM which would otherwise require multiple digital blocks. Experimentally validated results successfully demonstrate a 2.21184 GSps wireless link at distances of up to 2m in noisy daylight settings. Bit error rates (BER) of 0 at root mean square (RMS) error vector magnitude (EVM) of 4.09% are achieved. A complete digital line-up of an OWC transmitter chain for this work contains only three core blocks and ULL of less than 400 ns.

A wearable group-synchronized EEG system for multi-subject brain-computer interfaces.

The multi-subject brain-computer interface (mBCI) is becoming a key tool for the analysis of group behaviors. It is necessary to adopt a neural recording system for collaborative brain signal acquisition, which is usually in the form of a fixed wire. In this study, we designed a wireless group-synchronized neural recording system that supports real-time mBCI and event-related potential (ERP) analysis. This system uses a wireless synchronizer to broadcast events to multiple wearable EEG amplifiers. The simultaneously received broadcast signals are marked in data packets to achieve real-time event correlation analysis of multiple targets in a group. To evaluate the performance of the proposed real-time group-synchronized neural recording system, we conducted collaborative signal sampling on 10 wireless mBCI devices. The average signal correlation reached 99.8%, the amplitude of average noise was 0.87 μV, and the average common mode rejection ratio (CMRR) reached 109.02 dB. The minimum synchronization error is 237 μs. We also tested the system in real-time processing of the steady-state visual-evoked potential (SSVEP) ranging from 8 to 15.8 Hz. Under 40 target stimulators, with 2 s data length, the average information transfer rate (ITR) reached 150 ± 20 bits/min, and the highest reached 260 bits/min, which was comparable to the marketing leading EEG system (the average: 150 ± 15 bits/min; the highest: 280 bits/min). The accuracy of target recognition in 2 s was 98%, similar to that of the Synamps2 (99%), but a higher signal-to-noise ratio (SNR) of 5.08 dB was achieved. We designed a group EEG cognitive experiment; to verify, this system can be used in noisy settings. The evaluation results revealed that the proposed real-time group-synchronized neural recording system is a high-performance tool for real-time mBCI research. It is an enabler for a wide range of future applications in collaborative intelligence, cognitive neurology, and rehabilitation.

Evaluating feasibility of functional near-infrared spectroscopy in dolphins.

Using functional near-infrared spectroscopy (fNIRS) in bottlenose dolphins (Tursiops truncatus) could help to understand how echolocating animals perceive their environment and how they focus on specific auditory objects, such as fish, in noisy marine settings. To test the feasibility of near-infrared spectroscopy (NIRS) in medium-sized marine mammals, such as dolphins, we modeled the light propagation with computational tools to determine the wavelengths, optode locations, and separation distances that maximize sensitivity to brain tissue. Using frequency-domain NIRS, we measured the absorption and reduced scattering coefficient of dolphin sculp. We assigned muscle, bone, and brain optical properties from the literature and modeled light propagation in a spatially accurate and biologically relevant model of a dolphin head, using finite-element modeling. We assessed tissue sensitivities for a range of wavelengths (600 to 1700nm), source-detector distances (50 to 120mm), and animal sizes (juvenile model 25% smaller than adult). We found that the wavelengths most suitable for imaging the brain fell into two ranges: 700 to 900nm and 1100 to 1150nm. The optimal location for brain sensing positioned the center point between source and detector 30 to 50mm caudal of the blowhole and at an angle 45deg to 90deg lateral off the midsagittal plane. Brain tissue sensitivity comparable to human measurements appears achievable only for smaller animals, such as juvenile bottlenose dolphins or smaller species of cetaceans, such as porpoises, or with source-detector separations in adult dolphins. Brain measurements in juvenile or subadult dolphins, or smaller dolphin species, may be possible using specialized fNIRS devices that support optode separations of . We speculate that many measurement repetitions will be required to overcome hemodynamic signals originating predominantly from the muscle layer above the skull. NIRS measurements of muscle tissue are feasible today with source-detector separations of 50mm, or even less.

Rank-Aware Negative Training for Semi-Supervised Text Classification

Abstract Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. The key idea is to train a deep classifier on limited labeled texts and then iteratively predict the unlabeled texts as their pseudo-labels for further training. However, the performance is largely affected by the accuracy of pseudo-labels, which may not be significant in real-world scenarios. This paper presents a Rank-aware Negative Training (RNT) framework to address SSTC in learning with noisy label settings. To alleviate the noisy information, we adapt a reasoning with uncertainty-based approach to rank the unlabeled texts based on the evidential support received from the labeled texts. Moreover, we propose the use of negative training to train RNT based on the concept that “the input instance does not belong to the complementary label”. A complementary label is randomly selected from all labels except the label on-target. Intuitively, the probability of a true label serving as a complementary label is low and thus provides less noisy information during the training, resulting in better performance on the test data. Finally, we evaluate the proposed solution on various text classification benchmark datasets. Our extensive experiments show that it consistently overcomes the state-of-the-art alternatives in most scenarios and achieves competitive performance in the others. The code of RNT is publicly available on GitHub.

Adaptive Group Testing on Networks With Community Structure: The Stochastic Block Model

Group testing was conceived during World War II to identify soldiers infected with syphilis using as few tests as possible, and it has attracted renewed interest during the COVID-19 pandemic. A long-standing assumption in the probabilistic variant of the group testing problem is that individuals are infected by the disease <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">independently</i> . However, this assumption rarely holds in practice, as diseases often spread through interactions between individuals and therefore cause infections to be correlated. Inspired by characteristics of COVID-19 and other infectious diseases, we introduce an infection model over networks which generalizes the traditional i.i.d. model from probabilistic group testing. Under this model, we ask whether knowledge of the network structure can be leveraged to perform group testing more efficiently, focusing specifically on community-structured graphs drawn from the stochastic block model. We prove that a simple community-aware algorithm outperforms the baseline binary splitting algorithm when the model parameters are conducive to “strong community structure.” Moreover, our novel lower bounds imply that the community-aware algorithm is order-optimal in certain parameter regimes. We extend our bounds to the noisy setting and support our results with numerical experiments.

Learning and Planning under Uncertainty for Conservation Decisions

My research focuses on new techniques in machine learning and game theory to optimally allocate our scarce resources in multi-agent settings to maximize environmental sustainability. Drawing scientific questions from my close partnership with conservation organizations, I have advanced new lines of research in learning and planning under uncertainty, inspired by the low-data, noisy, and dynamic settings faced by rangers on the frontlines of protected areas.

Semantic relatedness and the cocktail party problem in aphasia: A hybrid remote/in-lab study

ABSTRACT Background Previous work has found that individuals with aphasia demonstrate impaired performance, relative to controls, on listening tasks where target speech is masked by other intelligible speech (Villard & Kidd, 2019). While this deficit may be due in part to impaired cognitive skills (e.g., attention, memory), the current study examined whether impaired linguistic-semantic processing could be a contributing factor as well. Aims This study compared the effect of semantic relatedness between target and masker words on performance on a speech-on-speech masking task, in listeners with aphasia vs. age-matched controls. Additionally, the study compared performance on a remote vs. an in-lab version of the experiment, with the goal of establishing the validity of remote listening experiments in these populations. Methods & Procedures Eight persons with aphasia (PWA) and eight age-matched controls (AMC) participated in the remote version of the experiment; similarly, eight PWA and eight AMC participated in the in-lab version of the experiment. In both versions, participants listened to short target sentences while ignoring maskers. Maskers consisted of either intelligible speech from the same semantic category as the target (e.g., target and maskers were all fruits), intelligible speech from a distant semantic category from the target (e.g., target was a fruit; maskers were articles of clothing), or speech-shaped, speech envelope-modulated noise. Procedures and stimuli were kept as similar as possible between the remote and in-lab versions of the experiment. Outcomes & Results In-lab results revealed a significant effect of group, such that PWA performed more poorly than AMC, as well as a significant effect of masking condition, such that participants performed more poorly on speech masking vs. noise masking conditions. No significant differences between same-category and different-category maskers were observed. A comparison of remote vs. in-lab results revealed similar patterns of performance between the two settings but suggested that remote testing resulted in overall noisier data. Conclusions These findings add to the existing body of knowledge about auditory masking in aphasia. Furthermore, they help lead to a clearer understanding of barriers to social engagement and community participation in PWA by characterizing challenges associated with communicating in noisy settings. The study also provided qualified support for the use of remote testing paradigms for listening experiments.

Intelligent Bearing Fault Diagnosis Based on Feature Fusion of One-Dimensional Dilated CNN and Multi-Domain Signal Processing

Finding relevant features that can represent different types of faults under a noisy environment is the key to practical applications of intelligent fault diagnosis. However, high classification accuracy cannot be achieved with only a few simple empirical features, and advanced feature engineering and modelling necessitate extensive specialised knowledge, resulting in restricted widespread use. This paper has proposed a novel and efficient fusion method, named MD-1d-DCNN, that combines statistical features from multiple domains and adaptive features retrieved using a one-dimensional dilated convolutional neural network. Moreover, signal processing techniques are utilised to uncover statistical features and realise the general fault information. To offset the negative influence of noise in signals and achieve high accuracy of fault diagnosis in noisy settings, 1d-DCNN is adopted to extract more dispersed and intrinsic fault-associated features, while also preventing the model from overfitting. In the end, fault classification based on fusion features is accomplished by the usage of fully connected layers. Two bearing datasets containing varying amounts of noise are used to verify the effectiveness and robustness of the suggested approach. The experimental results demonstrate MD-1d-DCNN’s superior anti-noise capability. When compared to other benchmark models, the proposed method performs better at all noise levels.