Masks - Science topic

This article examines smart cities as a locus for international power struggles, emerged at the gap between their discursive and materialised realities. While the body of research on smart cities is growing, most studies focus on their development within individual nation-states. However, the rapidly growing smart city-related market in Emerging As...

This study explores the effects of natural and musical sounds on students’ sound perception and wellbeing within school environments. The methodology encompassed quantitative and qualitative methods, including pre- and post-intervention questionnaires, structured observations during the interventions, interviews and measurements. A total of 242 stu...

Unsupervised learning objectives like auto-regressive and masked language modeling constitute a significant part in producing pre-trained representations that perform various downstream applications from natural language understanding to conversational tasks. However, despite impressive generative capabilities of recent large language models, their...

Coronary artery disease (CAD) persists as a predominant contributor to global morbidity and mortality, necessitating the development of robust, automated diagnostic tools for timely and accurate detection. This study presents a novel deep learning-based framework for the automatic grading, detection and segmentation of coronary artery stenosis from...

The project is focused on designing and evaluating an image segmentation model specifically meant to segment bird sound data in an image form. The model was trained using a dataset of images paired with seg-mentation masks. Its primary goal was set to achieve an Intersection over Union (IoU) score of over 60% to demonstrate the feasibility of apply...

Quality inspection inspection systems are critical for maintaining product integrity. Being a repetitive task, when performed by operators only, it can be slow and error-prone. This paper introduces an automated inspection system for quality assessment in casting aluminum parts resorting to a robotic system. The method comprises two processes: fili...

Conceptual engineering is the practice of revising concepts to improve how people talk and think. Its ability to improve talk and thought ultimately hinges on the successful dissemination of desired conceptual changes. Unfortunately, the field has been slow to develop methods to directly test what barriers stand in the way of propagation and what m...

The regional lockdowns, implemented around the world over 2020–2022 to contain the rapid spread of the novel coronavirus disease 2019 (COVID-19), inadvertently created a natural laboratory for investigating the effect of reducing anthropogenic emissions on urban air quality in unprecedentedly large temporal and spatial scales. In this study, we ana...

Resistance to targeted therapies is a significant clinical problem, but eliminating resistant cancer cells has proven difficult. One potential reason for this difficulty is heterogeneity in the resistant population: even genetically homogeneous cancer cell populations can give rise to a variety of resistant subtypes, each potentially with their own...

Background/Objectives: This study evaluates whether convolutional neural networks (CNNs) can be trained to determine the primary tumor origin from MRI images alone in patients with metastatic brain lesions. Methods: This retrospective, monocentric study involved the segmentation of 1175 brain lesions from MRI scans of 436 patients with histologic...

In the last decade, a lot of segmentation techniques had been proposed. Most of them include using an encoder-decoder network, such as the UNet model, to predict the mask for a certain image. The issue with UNet models and fully convolutional networks, in general, is that they require a substantial amount of data. In this study, we propose a novel...

Background: Optimal head and neck positioning is key to rapid, successful tracheal intubation enabling circumvention of peri-intubation sequelae; thus, scientific search for definite anatomical landmarks to serve as reference points for favorable head and neck alignment during laryngoscopy is warranted. Methods: Ethical approval obtained, 78 adults...

Purpose Hyperspectral imaging (HSI) is a promising intraoperative imaging modality, with potential applications ranging from tissue classification and discrimination to perfusion monitoring and cancer detection. However, surgical HSI datasets are scarce, hindering the development of robust data-driven algorithms. The purpose of this work was to add...

Background In CT‐based medical image segmentation, the choice of loss function profoundly impacts the training efficacy of deep neural networks. Traditional loss functions like cross entropy (CE), Dice, Boundary, and TopK each have unique strengths and limitations, often introducing biases when used individually. Purpose This study aims to enhance...

Regularization is an important tool for the generalization of ANN models. Due to the lack of constraints, it cannot guarantee that the model will work in a real environment with input data distribution changes. Inspired by neuroplasticity, this paper introduces a bounded regularization method that can be safely applied during the deployment phase....

Diese Festschrift ist eine Hommage an Theo Hug für seine vielen Verdienste innerhalb und weit über die Universität Innsbruck hinaus. Neben den theoretischen Fragestellungen im Spannungsfeld von Bildung, Medien, Kultur, Gesellschaft und Technologie geht es Theo Hug auch immer um die praktische Auseinandersetzung mit all diesen Fragen, insbesondere u...

To jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a distributed strong lottery ticket hypothesis (DSLTH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represented as the Hadamard product of global real-valued par...

This article explores the narrative construction of interspecies relationships through the lens of equine taming practices, focusing on the work of well-known horse trainers. By analyzing the biographies of Shy Boy and Myrnah, the wild horses subjected to taming, the study critically examines how these trainers present their methods within a narrat...

The aim of this study was to train a Vision Transformer (ViT) model for semantic segmentation to differentiate between ripe and unripe strawberries using synthetic data to avoid challenges with conventional data collection methods. The solution used Blender to generate synthetic strawberry images along with their corresponding masks for precise seg...

Historical impacts of hydro-climate extremes collected in existing global disaster databases are typically recorded at the country or subnational administrative level. Such coarse spatial resolution strongly masks the spatial variability of phenomena and limits the assessment of the potential underlying environmental and human drivers. Here, we dev...

Traditional channel acquisition faces significant limitations due to ideal model assumptions and scalability challenges. A novel environment-aware paradigm, known as channel twinning, tackles these issues by constructing radio propagation environment semantics using a data-driven approach. In the spotlight of channel twinning technology, a radio ma...

Wastewater-based environmental surveillance (ES) has been demonstrated to provide an early warning signal to predict variant-driven waves of pathogens such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Our study evaluated the potential cost-effectiveness of ES for SARS-CoV-2 compared with clinical testing alone. We used the Covas...

The integration of deep learning into critical vision application areas has given rise to a necessity for techniques that can explain the rationale behind predictions. In this paper, we address this need by introducing Salvage, a novel removal-based explainability method for image classification. Our approach involves training an explainer model th...

As technology nodes continue to shrink, the demand for higher lithographic accuracy in integrated circuit fabrication intensifies. To address the limitations of traditional compensation methods, this study proposes a mask-induced thermal and mechanical optimization approach to mitigate overlay errors, thereby enhancing lithographic precision in eme...

Purpose: In this study, we investigate the training of foundation models using federated learning to address data-sharing limitations and enable collaborative model training without data transfer for minimally invasive surgery. Methods: Inspired by the EndoViT study, we adapt the Masked Autoencoder for federated learning, enhancing it with adaptive...

This paper presents a novel scheme to efficiently compress Light Detection and Ranging~(LiDAR) point clouds, enabling high-precision 3D scene archives, and such archives pave the way for a detailed understanding of the corresponding 3D scenes. We focus on 2D range images~(RIs) as a lightweight format for representing 3D LiDAR observations. Although...

Background Tumor segmentation is crucial for lung disease diagnosis and treatment. Most existing deep learning‐based automatic segmentation methods rely on manually annotated data for network training. Purpose This study aims to develop an unsupervised tumor segmentation network smic‐GAN by using a similarity‐driven generative adversarial network...

We provide an open-source dataset of RGB and NIR-HSI (near-infrared hyperspectral imaging) images with associated segmentation masks and NIR spectra of 2242 individual malting barley kernels. We imaged every kernel pre-exposure to moisture and every 24 hours after exposure to moisture for five consecutive days. Every barley kernel was labeled as ge...

Modeling the joint distribution of the data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic capabilities reaching beyond purely generative or predictive models. However, training joint models presents daunting architectural and optimization challenges. Here, we propo...

The inference of gene regulatory networks (GRNs) is a foundational stride towards deciphering the fundamentals of complex biological systems. Inferring a possible regulatory link between two genes can be formulated as a link prediction problem. Inference of GRNs via gene coexpression profiling data may not always reflect true biological interaction...

Background: Scoliosis is a disorder characterized by an abnormal spinal curvature, which can lead to negative effects on patients, affecting their quality of life. Given its progressive nature, the classification of the scoliosis severity requires an accurate diagnosis and effective monitoring. The Cobb angle measurement method has been widely cons...

The goal of the feature reconstruction network based on an autoencoder in the training phase is to force the network to reconstruct the input features well. The network tends to learn shortcuts of “identity mapping,” which leads to the network outputting abnormal features as they are in the inference phase. As such, the abnormal features based on r...

Text data are often encoded as dense vectors, known as embeddings, which capture semantic, syntactic, contextual, and domain-specific information. These embeddings, widely adopted in various applications, inherently contain rich information that may be susceptible to leakage under certain attacks. The GEIA framework highlights vulnerabilities in se...

We present a ``cyclic zoom'' method to capture the dynamics of accretion flows onto black holes across a vast range of spatial and temporal scales in general relativistic magnetohydrodynamic (GRMHD) simulations. In this method, we cyclically zoom out (derefine) and zoom in (refine) the simulation domain while using a central mask region containing...

Wavelet analysis is a prominent time–frequency analysis method in investigating various signals such as speech, vibration, acoustic signals, ultrasound, and underwater acoustic signals. Throughout the coronavirus pandemic, people have adopted diverse face shields and face masks, which have caused difficulties in understanding speech. To address thi...

Different components were manufactured to assemble respirator-type masks as an alternative (sustainable, durable and with minimal environmental impact) to commonly used face masks, for the manufacture of the component’s injection-type 3D printers were used, where the thickness, height of the injected, printing time, clamping method and infill densi...

Autonomous Vehicles (AVs) rely on artificial intelligence (AI) to accurately detect objects and interpret their surroundings. However, even when trained using millions of miles of real-world data, AVs are often unable to detect rare failure modes (RFMs). The problem of RFMs is commonly referred to as the "long-tail challenge", due to the distributi...

Rockfalls on mountainous roads pose significant safety risks to pedestrians and vehicles, particularly in remote areas with underdeveloped communication infrastructure. To enable efficient detection, this study proposes a rockfall detection system based on embedded technology and an improved Yolov8 algorithm, termed Yolov8-GCB. The algorithm enhanc...

We introduce an approach for performing spectrally resolved electron microscopy without the need for an electron spectrometer. The method involves an electron beam prepared as a coherent superposition of multiple paths, one of which passes near a laser-irradiated specimen. These paths are subsequently recombined, and their interference is measured...

italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective : Aiming to quantify and analyze disease-induced alterations in human movement, we explored the co-joint synergy patterns in locomotion through a vision-based co-joint synergistic attention algorithm. Methods : We recruited 30 participants (in...

Language models have emerged as powerful predictors of the viability of biological sequences. During training these models learn the rules of the grammar obeyed by sequences of amino acids or nucleotides. Once trained, these models can take a sequence as input and produce a likelihood score as an output; a higher likelihood implies adherence to the...

Scramblases play important roles in physiology by translocating phospholipids bidirectionally across cell membranes. For example, scrambling facilitated by VDAC1 dimers is the primary mechanism by which endoplasmic reticulum-derived phospholipids cross the outer membrane to enter mitochondria. Precise quantification of lipid scrambling, while criti...

Graphical User Interface (GUI) datasets are crucial for various downstream tasks. However, GUI datasets often generate annotation information through automatic labeling, which commonly results in inaccurate GUI element BBox annotations, including missing, duplicate, or meaningless BBoxes. These issues can degrade the performance of models trained o...

Atherosclerosis is the leading cause of death in Western industrial nations. To study the etiology of plaque progression, atherosclerotic mouse models are widely used. Traditionally, analyzing the obtained histological whole slide images of Oil Red O-stained aortic roots required manual segmentation. To accelerate this process, an artificial intell...

Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging offers broader spatial and temporal coverage but often lacks the spectral detail...

Designing free-form photonic devices is fundamentally challenging due to the vast number of possible geometries and the complex requirements of fabrication constraints. Traditional inverse-design approaches--whether driven by human intuition, global optimization, or adjoint-based gradient methods--often involve intricate binarization and filtering...

Facial masks are often used to treat skin problems, and the introduction of microcurrent ion penetration technology can improve drug penetration and help facial tissue repair. However, most microcurrent stimulation masks contain a direct current power supply and require external power sources, resulting in inconvenient portability and use. Herein,...

The COVID-19 pandemic presented significant challenges in educational settings. Schools implemented a variety of COVID-19 mitigation strategies, some of which were controversial due to potential disruptions to in-person learning. We developed an agent-based model of COVID-19 in a US high school setting to evaluate potential trade-offs between preve...

Background: In vaccine studies it is important to analyze not only vaccine effectiveness (VE) against a target disease but against all-cause mortality (ACM) as well. We analyze the Dutch observational Covid-19 vaccination data with a special focus on ACM eects and identifying potential biases and artifacts. We compare with earlier work based on the...

This study addresses the critical challenge of detecting and classifying tomato leaf diseases using advanced deep learning technologies, a pivotal step in enhancing productivity within precision agriculture. We developed a novel diagnostic system capable of categorizing tomato leaves into ten distinct classes—nine corresponding to specific diseases...

Graphene and its composites have attracted much attention for applications in energy storage systems. However, the toxic solvents required for the exfoliation process have hampered the exploitation of its properties. In this work, graphene dispersions are obtained via liquid phase exfoliation (LPE) of graphite in cyrene, an environmentally friendly...

Many existing video inpainting algorithms utilize optical flows to construct the corresponding maps and then propagate pixels from adjacent frames to missing areas by mapping. Despite the effectiveness of the propagation mechanism, they might encounter blurry and inconsistencies when dealing with inaccurate optical flows or large masks. Recently, D...

With the increase in dental patient numbers and the ongoing digital transformation of dental hospitals, tooth segmentation has become increasingly crucial for the digital diagnosis, design, treatment, and customized appliance manufacturing of orthodontics, oral implant surgery, and prosthodontics. This study aims to adapt the Segment Anything Model...

White matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric seg...

Chemical stochastics effects cover the stochastic variability occurring in the resist film immediately following the absorption of the incident exposure species, i.e. electrons in the case of e-beam mask writing or EUV photons in EUVL. Generalization of earlier developed compact stochastic models to cover this chemical variability are presented. Th...

In this paper, a double reconstructive DNA encryption transmission scheme based on ciphertext-key coordination is proposed for a fiber wireless seamless integrated communication system. The scheme uses a 5D memristor ring chaotic system and 1D chaotic system to realize the double collaborative reconstruction encryption transmission of ciphertext-ke...

This study proposes an improved optical flow algorithm based on semantic segmentation for real-time vehicle detection and tracking. The method combines the semantic segmentation capability of the SegmentAnything model with optical flow estimation technology. By generating precise vehicle region masks, it effectively narrows the search range for mat...

As the serial section community transitions to volume electron microscopy, tools are needed to balance rapid segmentation efforts with documenting the fine detail of structures that support cell function. New annotation applications should be accessible to users and meet the needs of the neuroscience and connectomics communities while also being us...

High-numerical-aperture (NA) anamorphic extreme ultraviolet lithography (EUVL) is the next-generation technology under advanced technology nodes. The design of the illumination system requires achieving better illumination uniformity while ensuring energy efficiency. However, the traditional four-mirror structure illumination system ignores the imp...

The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth annotations. However, when applying the model to unseen data, such as in clinical settings, it is often impractical to annotate all the data, making the model's performance...

The accurate recognition of geological structures in field outcrop images is critical for applications such as geological hazard analysis, seismic risk assessment, and urban geological planning. However, traditional manual interpretation of geological images is time‐consuming, labor‐intensive, and subjective, limiting its scalability and precision....

Humans, inherently social creatures, instinctively employ facial behaviors for interpersonal communication. Interestingly, when individuals find themselves alone, their facial behaviors tend to become more spontaneous than when in the presence of others, unintentionally revealing their affective states. In particular, when individuals are immersed...

Accurate detection and timely management of high-voltage transmission accessories are crucial for ensuring the safe operation of power transmission. Existing network models suffer from issues like low precision in accessory detection, elevated model complexity, and a narrow range of category detection, especially in UAV-based inspection scenarios....

Phase wraparound due to large inter-sensor spacings in multi-channel demixing renders the DUET and AdRess source separation algorithms—known for their low computational complexity and effective speech demixing performance—unsuitable for hearing-assisted living applications, where such configurations are needed. DUET is limited to relative delays of...

The exponential growth of cross-border data flows and fragmented national and regional data protection standards have intensified regulatory challenges in global trade. The effects of regulatory divergence are amplified by a lack of transparency, potentially masking discriminatory practices. Article VII of the General Agreement on Trade in Services...

Importance Masks reduce transmission of SARS-CoV2 and other respiratory pathogens. Comparative studies of the fitted filtration efficiency of different types of masks are scarce. Objective To describe the fitted filtration efficiency against small aerosols (0.02–1 µm) of medical and non-medical masks and respirators when worn, and how this is affe...

Plug-in distributed energy resources (DERs), such as balcony solar, backfeed power to the home through a standard plug. These systems may represent the future of residential solar and storage, particularly as recent net metering policies have reduced the economic appeal of rooftop solar. While plug-in DERs have seen widespread success in Europe, th...

In this study, the Electron Spin Resonance (ESR) dosimetric potential of surgical face masks was investigated within the intermediate gamma dose range of 0.05–10 kGy. White, blue, and green mask samples were used for this analysis. FTIR and XRD analyses confirmed that all masks were made of polypropylene. No ESR signals were detected in the unirrad...

We show how to construct local units for each semantic cluster in an embedding space and how these units act as domain-specific masks (gates) in Retrieval-Augmented Generation (RAG). The construction is formulated purely algebraically, dispensing with implementation and revealing the direct connection to multineutral structures .

We report two experiments demonstrating that visual word recognition is impeded by the presence of nearby stimuli, especially adjacent words. Reading research has converged on a consensus that skilled readers control their attention to make use of information from adjacent (primarily upcoming) words, increasing reading efficiency. Other lines of re...

Surface plasmon resonance (SPR) technology has been widely applied in various fields, such as biosensing, environmental monitoring, food safety, and drug screening. However, the signal-to-noise ratio (SNR) of SPR sensors varies with wavelength and greatly affects their performance due to the fact that optics and sensors work differently for varying...

Dynamic race detection is a highly effective runtime verification technique for identifying data races by instrumenting and monitoring concurrent program runs. However, standard dynamic race detection is incompatible with practical weak memory models; the added instrumentation introduces extra synchronization, which masks weakly consistent behavior...

In single-pixel imaging, reconstructing high-quality images at a low measurement rate is a key goal. Currently, deep learning methods achieve this goal by optimizing the loss between the target image and the original image, which limits the potential of low measurements. Therefore, this study proposes a single-pixel reconstruction algorithm based o...

Characterizing a material's thermo-optic coefficient lays the foundation for optimizing thermal tuning of photonic integrated devices, a key feature for applications in optical communication, sensing, and signal processing. Unlike traditional bulk measurements, determining the thermo-optic coefficient (TOC) in microscale photonic devices offers sig...

This study evaluated the filtration efficiency, and continuity of the antibacterial activity of reusable antibacterial silver, copper, and graphene antibacterial masks before and after washing. The masks were washed at three different temperatures (40 °C, 60 °C, 90 °C) and up to 10 washing cycles. The filtration efficiencies of the three reusable a...

Given a data set and one single object known to be anomalous beforehand, the outlier explanation problem consists in explaining the abnormality of the input object with respect to the data set population. The approach pursued in this paper to solve the above task consists in finding an explanation, namely, a piece of information encoding the charac...

Reading words in alphabetic scripts requires encoding the relative order of the letters. This process of letter position coding is known to be flexible. For instance, the masked transposed-letter prime jugde activates the word JUDGE to a greater degree than a replacement-letter prime like jupte, a phenomenon known as the transposed-letter effect. I...

The iterative Fourier transform algorithm (IFTA) is the most widely used algorithm for the generation of phase masks for laser beam shaping in the field of laser material processing. But its simplicity and efficiency also come with heavy limitations. We here present an overview of our research into application adapted laser beam shaping beyond the...

Assessments of listening effort are increasingly relevant to understanding the speech-comprehension difficulties experienced by older adults. Pupillometry is the most common tool to assess listening effort but has limitations. Recent research has shown that eye movements decrease when listening is effortful and proposed indicators of eye movements...

We propose a combinatorial and graph-theoretic theory of dropout by modeling training as a random walk over a high-dimensional graph of binary subnetworks. Each node represents a masked version of the network, and dropout induces stochastic traversal across this space. We define a subnetwork contribution score that quantifies generalization and sho...

Large language models (LLMs) cannot be trusted for economic forecasts during periods covered by their training data. We provide the first systematic evaluation of LLMs' memorization of economic and financial data, including major economic indicators, news headlines, stock returns, and conference calls. Our findings show that LLMs can perfectly reca...