Masking Functions Research Articles

Active noise-cancelling headphones do not improve cognitive performance in office noise environment

Our purpose was to determine the influence of different use settings of on-ear ANC (active noise-cancelling) headphones on performance, experience, and physiological stress in conditions resembling an office where task irrelevant speech is present. Laboratory experiment involved 54 participants, who were exposed to five conditions: 1. No headphones, 2. Headphones without ANC operation, 3. Headphones with ANC operation, 4. Headphones with sound masking playback, 5. Headphones with ANC operation and sound masking playback. In all conditions, speech was present in the room at 52 dB LAeq. Masking was 51 dB LAeq wideband noise played from the headphones. Participants' performance was measured with visual serial recall and 3-back tasks, and physiological stress with heart rate variability. The condition did not influence performances nor physiological stress. The only effects of sound condition were observed in subjective experiences. With masking (conditions 4 and 5), the speech was less annoying than without the headphones (condition 1). Sound environment was estimated to impair performance and disturb concentration less than without the headphones only in condition 5. Therefore, using headphones together with masking and ANC function can improve experience. Using headphones with ANC function alone did not improve performance nor reduce stress level.

Evaluation of Cloud Masking Methods using Sentinel-2 Satellite Images on Google Earth Engine: A Case Study in Vietnam

The production of cloudless images from the optical satellite are critical in Earth surface monitoring. In 2015,Sentinel-2A was successfully launched into orbit by the European Space Agency. Sentinel-2 imagery is currently theprimary source of data for Earth monitoring. There are several ways to create cloudless images from multi-temporalSentinel-2 optical satellite imagery on the Google Earth Engine (GEE) platform. These include the Fmask (Function ofmask) method, the Fmask CDI (Cloud Displacement Index) method, and the Fmask CSP (Cloud Score Plus) method. Inthis paper, the authors build a program and evaluate the cloud masking methods on the GEE platform in Song Hinhdistrict, Phu Yen province, which is situated in the South-Central Coast region of Central Vietnam. The Song Hinh districtis a suitable study area for the evaluation of cloud masking methods on optical satellite images due to its diverse andcomplex terrain, which includes numerous peaks and valleys and a variety of climatic conditions. This article illustratesthe results of three cloud masking methods on Sentinel-2 images. In contrast to the Fmask method, the Fmask CDI andFmask CSP methods provide more benefits in detecting clouds and cloud shadows, resulting in more accurate outcomes

Semi-supervised segmentation of medical images focused on the pixels with unreliable predictions

Pseudo-labeling is a well-studied approach in semi-supervised learning. However, unreliable or potentially incorrect pseudo-labels can accumulate training errors during iterative self-training steps, leading to unstable performance. Addressing this challenge typically involves either discarding unreliable pseudo-labels, resulting in the loss of important data, or attempting to refine them, risking the possibility of worsening the pseudo-labels in some cases/pixels. In this paper, we propose a novel method based on pseudo-labeling for semi-supervised segmentation of medical images. Unlike existing approaches, our method neither discards any data nor worsens reliable pseudo-labels. Our approach generates uncertainty masks for the predictions, utilizing reliable pixels without any modification as ground truths and modifying the unreliable ones rather than discarding them. Furthermore, we introduce a novel loss function that incorporates both mentioned parts by multiplying each term by its corresponding uncertainty mask, encompassing reliable and unreliable pixels. The reliable pixels are addressed using a masked cross-entropy loss function, while the modification of the unreliable pixels is performed through a deep-learning-based adaptation of active contours. The entire process is solved within a single loss function without the need to solve traditional active contour equations. We evaluated our approach on three publicly available datasets, including MRI and CT images from cardiac structures and lung tissue. Our proposed method outperforms the state-of-the-art semi-supervised learning methods on all three datasets. Implementation of our work is available at https://github.com/behnam-rahmati/Semi-supervised-medical.

Dynamic Physics-Guided Deep Learning for Long-Term Production Forecasting in Unconventional Reservoirs

Summary Neural network predictive models are popular for production forecasting in unconventional reservoirs due to their ability to learn complex relationships between well properties and production responses from extensive field data. The intricate flow behavior in hydraulically fractured unconventional reservoirs, which remains poorly understood, makes these statistical models particularly useful. Various neural network variants have been developed for production prediction in these reservoirs, each offering predictive capability of varying levels of granularity, accuracy, and robustness against noisy and incomplete data. Neural network predictive models that integrate physical principles are especially useful for subsurface systems, as they provide predictions that adhere to physical laws. This work introduces a new dynamic physics-guided deep learning (DPGDL) model that incorporates physical functions into neural networks and employs residual learning to compensate for the imperfect description of the physics, under variable data support. The new formulation allows for dynamic residual correction, avoids unintended bias due to less-than-ideal input data, and provides robust long-term predictions. The DPGDL model improves upon a static formulation by utilizing a masked loss function to enable learning from wells with varying production lengths and by improving the results when partially-observed timesteps are present. In addition, a sequence-to-sequence residual model has been developed to correct additional biases in the long-term predictions from the physics-constrained neural networks. Several synthetic data sets with increasing complexity as well as a field data set from the Bakken are used to demonstrate the performance of the new DPGDL model.

Improved fusion model for generating hourly fine scale land surface temperature data under all-weather condition

Existing Land Surface Temperature (LST) fusion models encounter some challenges due to missing data, complex weather areas, and rapid land cover changes. To overcome these limitations, we proposed the Integrated SpatioTemporal Fusion Algorithm (ISFAT). ISFAT is developed based on contemporary fusion models but in addition incorporates data from partially contaminated LSTs using the masked weight function. This helps to predict fine-scale LST on prediction date while considering error resulting from landcover changes between the base and prediction date. This algorithm also factors in the calculation of model residuals, which are distributed back to the predicted fine-scale LST using the thin-plate spline function. The fine-scale LST on prediction can thereafter employed for predicting hourly fine-scale LST images by integrating a coarse resolution LST with hourly temporal resolution. Compared to contemporary LST fusion models, ISFAT demonstrates superior performance, with mean average differences of 0.1 K and 0.27 K over SADFAT and STITFM, respectively. Additionally, diurnal LST predictions from ISFAT compare well with air temperatures from automatic weather stations. Notably, on February 18, 2020, ISFAT effectively optimized fine-scale LST for Hong Kong, achieving an RMSE of 3.33 K, despite the limitation of cloud cover in the base date. The newly developed ISFAT could facilitate better LST retrieval over a large spatial coverage under different degrees of cloud contamination.

CHARACTERISTICS OF BIRD EGGSHELL COLORATION DEPENDING ON NEST LOCATION

Based on the analysis of egg collections of different ecological groups of birds and various literature sources, a summary of scientific studies on morphological adaptations related to the color of eggshells in birds is given. Eggshell color in birds is a morphological adaptation with a masking function that depends on nesting conditions. The article examines egg collections of birds with an open nesting type: Eurasian skylark (ground-nesting), Eurasian chaffinch (crown-nesting), and Red-backed shrike (bush-nesting). The study confirmed the high variability of eggshell color in birds with an open nesting type, which allows clutches to be invisible which contributes to successful nesting. The correlation between the location of the nest and the color of the eggshells of the studied bird species was analyzed, and the peculiarities of this correlation were determined.

Intramolecular Radical Amidooxygenation of Alkenes for the Construction of Pyrrolidinones.

An intramolecular 1,2-amidooxygenation of unactivated alkenes for the construction of the pyrrolidinone scaffold containing a masked 5-hydroxymethyl functionality is reported. γ,δ-Unsaturated N-aryloxyamides react with sodium 2,2,6,6-tetramethylpiperidin-1-olate (TEMPONa) to afford alkoxyaminated pyrrolidinones. The cascade proceeds through reductive amidyl radical generation with TEMPONa, 5-exo cyclization, and TEMPO trapping. No transition metal is required to perform these transformations, and complex (fused, bridged) pyrrolidinones are accessible in moderate to good yields. The product alkoxyamines are readily further converted into ketones and alcohols through either oxidation or reduction.

Design of easily swallowable xerogel pill with enough physical strength through hardening-process under heating and humidification

The xerogel pill has been developed as a novel dosage form with dose-adjusting and swallow-assisting functions by using drop freeze-drying (DFD) technique. It was double-structured small sphere composed of an inner drug core and an outer dried-gel layer, however, had problem of insufficient physical strength. In this study, it was attempted to use dextrin (DEX), one of oligosaccharides, to strengthen the xerogel pill. DEX was co-dissolved in the dropping fluid in the DFD process and co-loaded in the conventional pill, which was mainly composed of mannitol (MNT) as a filler, to prepare the rigid body. DEX-loaded pill could be successfully prepared with high recovery (>90 %) by optimizing the ratio of DEX and MNT. Further, the representative pills with and without DEX (P-DEX and P-MNT, respectively) were hardening-processed under humidification. The physical strength of P-DEX pill was significantly increased when humidified under severe condition, resulting in enough hardness (>5N) and friability (<1.0 %). Processed P-DEX was found to have dense structure covered with a thick outer shell, which would be formed by interparticle bridge of DEX. It was also found that processed P-DEX pill suppressed initial drug dissolution significantly and exhibited sustained dissolution behavior, suggesting the potential function of bitter taste masking. Processed P-DEX pill had excellent sliding behavior with low friction forces as a result of lubricant effect of xanthan gum (XG) surrounding the pills. Furthermore, the sliding test also suggested that processed P-DEX pill had hard candy-like texture, in contrast unprocessed P-DEX pill had orally disintegrating (OD) tablet-like texture. Various xerogel pills with such different swallowing texture would have a potential to accommodate the children’s preferences when taking medication.

Physics Guided Deep Learning-Based Model for Short-Term Origin–Destination Demand Prediction in Urban Rail Transit Systems Under Pandemic

Accurate origin–destination (OD) demand prediction is crucial for the efficient operation and management of urban rail transit (URT) systems, particularly during a pandemic. However, this task faces several limitations, including real-time availability, sparsity, and high-dimensionality issues, and the impact of the pandemic. Consequently, this study proposes a unified framework called the physics-guided adaptive graph spatial–temporal attention network (PAG-STAN) for metro OD demand prediction under pandemic conditions. Specifically, PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices. Subsequently, a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices. Thereafter, PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic. Finally, a masked physics-guided loss function (MPG-loss function) incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model interpretability. PAG-STAN demonstrated favorable performance on two real-world metro OD demand datasets under the pandemic and conventional scenarios, highlighting its robustness and sensitivity for metro OD demand prediction. A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.

Behavioral evidence of the modulation filterbank in an avian animal model of complex-sound perception

Behavioral detection of amplitude modulation (AM) can be adversely affected by competing AM “noise” present in the acoustic environment. Called AM masking, human studies suggest the existence of a modulation filterbank that separates sounds (signal from noise) based on differences in AM frequency. The modulation filterbank is an important theoretical advancement in hearing science because in addition to explaining AM masking, the model successfully predicts differences in speech perception across noisy listening environments with different AM statistics. Currently, there are no behavioral animal models of the modulation filterbank, presenting a serious impediment to understanding neural underpinnings. We trained budgerigars, a parakeet species, to detect AM frequencies from 64 to 400 Hz in the presence of narrowband AM maskers applied to a 2.8-kHz carrier signal. AM masker center frequencies spanned a &amp;gt;2 octave range centered on the target AM frequency. Behavioral AM sensitivity was evaluated with operant conditioning, a single-interval two-alternative discrimination task, and two-down one-up adaptive threshold tracking procedures. Budgerigar AM masking functions had a band-pass characteristic, consistent with the modulation filterbank and with human AM masking results for the same stimuli. To our knowledge, these are the first behaviorally estimated modulation filter shapes in a nonhuman species. [Funding: NIDCD R01-DC017519.]

The Signaling Function of Vaccine Status and Masking in Evaluations of Online Dating Profiles

The Signaling Function of Vaccine Status and Masking in Evaluations of Online Dating Profiles

Visible polarized reflection of target material surface based on improved Blinn masking function

Visible polarized reflection of target material surface based on improved Blinn masking function

A ChannelWise weighting technique of slice-based Temporal Convolutional Network for noisy speech enhancement

In recent years, Temporal Convolutional Networks (TCNs) have driven significant progress in single-channel noisy speech enhancement. However, TCN-based systems still face certain challenges, such as limited utilization of network channel depth for handling long-range dependencies and issues with weight sharing. To address these challenges, this paper proposes a novel channel-wise weighting scheme, specifically designed for the sliced TCN framework. The proposed scheme involves the element-wise multiplication of shifting weight techniques for each channel of the TCN slice. Utilizing a cyclically shifted approach, these weights capture information from neighboring channels, uncovering the dependencies between adjacent channels. By combining the channel-wise weighted TCN output and subsequently estimating a masking function, the proposed method effectively suppresses noise components, leading to enhanced speech quality. To train and evaluate our proposed method, we utilize speech datasets that consist of various noise types at different levels. To optimize the performance of the proposed end-to-end enhancement system, we adopt the Scale-Invariant Signal-to-Noise Ratio (SI-SNR) objective function. Experimental results demonstrate the effectiveness of our proposed TCN channel-wise weighting method, with a significant average improvement of approximately 9.8% in SI-SNR for the unseen noise dataset. This improvement was observed at an SNR of −3 dB for both non-channel-wise weighting schemes and the proposed channel-wise weighting schemes within the Multi-slicing TCNs framework. The main advantage of the proposed approach is its ability to address the challenges of uneven and biased output from TCN slices, particularly when dealing with highly non-stationary, noisy speech signals infused with speech-like noise. This leads to more robust performance in various real-world applications.

An origin–destination passenger flow prediction system based on convolutional neural network and passenger source-based attention mechanism

An accurate origin–destination (OD) passenger flow prediction system is crucially important for urban metro operation and management. However, there are still lacking targeted prediction systems focusing on the passenger travel demand causing urban metro oversaturation. In this study, we first identify the passenger sources of the oversaturated sections and pinpoint the key part of passenger travel demand causing major oversaturation. Next, we take advantage of the attention mechanism and the masked loss function to incorporate the passenger source information into the prediction model and develop a passenger source attention mechanism based convolutional neural network (PSAM-CNN) model. Finally, the developed PSAM-CNN model is validated using the actual passenger travel demand data of Shenzhen Metro. Comparing with several state-of-art benchmark models, the PSAM-CNN model can predict the OD passenger flows causing urban metro oversaturation more accurately, providing more targeted and accurate OD flow information for improving the operation and management of urban metro.

A context-based approach to predict intelligibility of meaningful and nonsense words in interrupted noise: Model evaluation.

The context-based Extended Speech Transmission Index (cESTI) by Van Schoonhoven et al. (2022) was successfully used to predict the intelligibility of meaningful, monosyllabic words in interrupted noise. However, it is not clear how the model behaves when using different degrees of context. In the current paper, intelligibility of meaningful and nonsense CVC words in stationary and interrupted noise was measured in fourteen normally hearing adults. Intelligibility of nonsense words in interrupted noise at -18 dB SNR was relatively poor, possibly because listeners did not profit from coarticulatory cues as they did in stationary noise. With 75% of the total variance explained, the cESTI model performed better than the original ESTI model (R2 = 27%), especially due to better predictions at low interruption rates. However, predictions for meaningful word scores were relatively poor (R2 = 38%), mainly due to remaining inaccuracies at interruption rates below 4 Hz and a large effect of forward masking. Adjusting parameters of the forward masking function improved the accuracy of the model to a total explained variance of 83%, while the predicted power of previously published cESTI data remained similar.

Do face masks undermine social connection?

AbstractMask mandates were commonplace around the world during the COVID‐19 pandemic and essential to slowing the spread of SARS‐CoV‐2. However, it is still unclear whether and how masks impact social bonding. Building on past research examining the effects of masking on emotion recognition and social perception, the current research examines the effect of masking on feelings of social connectedness. Three studies (total N = 177) using videotaped introductions of masked and unmasked peers and varied assessments of desire for social connectedness yielded no differences as a function of masking. Although participants reported more difficulty hearing masked (vs. unmasked) peers, masking did not significantly impact other facets of communication or perception related to social bonding. When participants filmed their own introductory videos (Study 3), results showed increased expressivity within the masked (vs. unmasked) conditions, perhaps as a compensatory measure to aid bonding. These findings speak to the resiliency of the human need to belong and belonging‐maintenance processes.

LAnoBERT: System log anomaly detection based on BERT masked language model

The system log generated in a computer system refers to large-scale data that are collected simultaneously and used as the basic data for determining errors, intrusion and abnormal behaviors. The aim of system log anomaly detection is to promptly identify anomalies while minimizing human intervention, which is a critical problem in the industry. Previous studies performed anomaly detection through algorithms after converting various forms of log data into a standardized template using a parser. Particularly, a template corresponding to a specific event should be defined in advance for all the log data using which the information within the log key may get lost. In this study, we propose LAnoBERT, a parser free system log anomaly detection method that uses the BERT model, exhibiting excellent natural language processing performance. The proposed method, LAnoBERT, learns the model through masked language modeling, which is a BERT-based pre-training method, and proceeds with unsupervised learning-based anomaly detection using the masked language modeling loss function per log key during the test process. In addition, we also propose an efficient inference process to establish a practically applicable pipeline to the actual system. Experiments on three well-known log datasets, i.e., HDFS, BGL, and Thunderbird, show that not only did LAnoBERT yield a higher anomaly detection performance compared to unsupervised learning-based benchmark models, but also it resulted in a comparable performance with supervised learning-based benchmark models.

Deep Reinforcement Learning-Based Deterministic Routing and Scheduling for Mixed-Criticality Flows

Deterministic networking (DetNet) has recently drawn much attention by investigating deterministic flow scheduling. Combined with artificial intelligent (AI) technologies, it can be leveraged as a promising network technology for facilitating automated network configuration in the Industrial Internet of Things (IIoT). However, the stricter requirements of the IIoT have posed significant challenges, that is, deterministic and bounded latency for time-critical applications. This paper incorporates deep reinforcement learning (DRL) in Cycle Specified Queuing and Forwarding (CSQF) and proposes a DRL-based Deterministic Flow Scheduler (Deep-DFS) to solve the Deterministic Flow Routing and Scheduling (DFRS) problem. Novel delay aware network representations, action masking and criticality aware reward function design are proposed to make Deep-DFS more scalable and efficient. Simulation experiments are conducted to evaluate the performances of Deep-DFS, and the results show that Deep-DFS can schedule more flows than the other benchmark methods (heuristic-based and AI-based methods).

Deep Learning for Metro Short-Term Origin-Destination Passenger Flow Forecasting Considering Section Capacity Utilization Ratio

Origin-destination (OD) short-term passenger flow forecasting (OD STPFF) in urban rail transit (URT) is essential for developing timely network measures. The capacity utilization ratios of critical sections are key factors in developing these measures. The OD pairs passing through critical sections require a higher prediction accuracy than others; however, most studies have raised equal concerns on the prediction accuracy of each OD pair, namely, prediction at the network level. To address this problem, we raise heterogeneous time-variant concerns on OD pairs and employ an operation-oriented deep-learning architecture called the spatiotemporal convolutional neural network (STCNN) for realizing short-term OD passenger flow prediction. The architecture contains OD pair importance calculation, lagged spatiotemporal relationship construction, lagged spatiotemporal learning, real-time information learning, and sequential-temporal learning blocks. To this end, critical OD pairs are ascertained first, and the topological lagged spatiotemporal relationship among critical OD pairs are constructed and then normalized into grid-shaped data. The third block utilizes a convolutional neural network (CNN) to learn the grid-shaped lagged spatiotemporal feature and real-time information in parallel. A temporal convolutional neural network (TCN) is utilized for learning the sequential-temporal feature at last. Further, we design a time-varying weighted masked loss function to jointly reinforce the concerns on critical OD pairs during model training. Finally, we test the proposed STCNN and its components on a field dataset from Chengdu Metro. Although the proposed STCNN performs only slightly better at the network level than the other models, it outperforms state-of-the-art methods with significant superiority on critical OD pairs.

Modular oxime formation by a trans-AT polyketide synthase.

Modular trans-acyltransferase polyketide synthases (trans-AT PKSs) are enzymatic assembly lines that biosynthesize complex polyketide natural products. Relative to their better studied cis-AT counterparts, the trans-AT PKSs introduce remarkable chemical diversity into their polyketide products. A notable example is the lobatamide A PKS, which incorporates a methylated oxime. Here we demonstrate biochemically that this functionality is installed on-line by an unusual oxygenase-containing bimodule. Furthermore, analysis of the oxygenase crystal structure coupled with site-directed mutagenesis allows us to propose a model for catalysis, as well as identifying key protein-protein interactions that support this chemistry. Overall, our work adds oxime-forming machinery to the biomolecular toolbox available for trans-AT PKS engineering, opening the way to introducing such masked aldehyde functionalities into diverse polyketides.