Visual Output Research Articles

Gym-flp: A Python Package for Training Reinforcement Learning Algorithms on Facility Layout Problems

Reinforcement learning (RL) algorithms have proven to be useful tools for combinatorial optimisation. However, they are still underutilised in facility layout problems (FLPs). At the same time, RL research relies on standardised benchmarks such as the Arcade Learning Environment. To address these issues, we present an open-source Python package (gym-flp) that utilises the OpenAI Gym toolkit, specifically designed for developing and comparing RL algorithms. The package offers one discrete and three continuous problem representation environments with customisable state and action spaces. In addition, the package provides 138 discrete and 61 continuous problems commonly used in FLP literature and supports submitting custom problem sets. The user can choose between numerical and visual output of observations, depending on the RL approach being used. The package aims to facilitate experimentation with different algorithms in a reproducible manner and advance RL use in factory planning.

RadiantVisions: Illuminating Low-Light Imagery with a Multi-Scale Branch Network

In the realms of the Internet of Things (IoT) and artificial intelligence (AI) security, ensuring the integrity and quality of visual data becomes paramount, especially under low-light conditions, where low-light image enhancement emerges as a crucial technology. However, the current methods for enhancing images under low-light conditions still face some challenging issues, including the inability to effectively handle uneven illumination distribution, suboptimal denoising performance, and insufficient correlation among a branch network. Addressing these issues, the Multi-Scale Branch Network is proposed. It utilizes multi-scale feature extraction to handle uneven illumination distribution, introduces denoising functions to mitigate noise issues arising from image enhancement, and establishes correlations between network branches to enhance information exchange. Additionally, our approach incorporates a vision transformer to enhance feature extraction and context understanding. The process begins with capturing raw RGB data, which are then optimized through sophisticated image signal processor (ISP) techniques, resulting in a refined visual output. This method significantly improves image brightness and reduces noise, achieving remarkable improvements in low-light image enhancement compared to similar methods. Using the LOL-V2-real dataset, we achieved improvements of 0.255 in PSNR and 0.23 in SSIM, with decreases of 0.003 in MAE and 0.009 in LPIPS, compared to the state-of-the-art methods. Rigorous experimentation confirmed the reliability of this approach in enhancing image quality under low-light conditions.

Structural strength analysis of a rotary drum mower during harvesting

A Rotary Drum Mower (RDM) is a tractor-mounted mechanism used for harvesting green fodder crops. It faces dynamic forces from rough field surfaces and cutting resistance, posing design challenges and potential failures. This study aims to present a well-designed procedure for analysing the structural strength of an RDM during harvesting, employing both experimental and engineering simulation methods. A specific harvesting scenario was created to simulate realistic load conditions. Experimental testing and advanced computer-aided engineering (CAE) simulations were conducted. Tractor Power Take-off (PTO) torque measurements during harvesting revealed values of 231.07 Nm, 264.44 Nm, and 269.39 Nm at speeds of 8.56 km h-1, 12.6 km h-1, and 16.23 km h-1, respectively. Finite element analysis (FEA) was conducted to determine stress levels in the RDM components (RDM165-A-004, RDM165-B-003, and RDM165-B-004). The FEA stress results ranged from 5.070 MPa to 20.600 MPa, 13.800 MPa to 28.600 MPa, and 5.400 MPa to 27.550 MPa, respectively. Experimental testing yielded stress results ranging from 2.127 MPa to 18.600 MPa, 14.618 MPa to 33.229 MPa, and 8.838 MPa to 31.248 MPa, respectively. The comparison between experimental and FEA results showed reasonable correlation. FEA visual outputs provided insights into the maximum equivalent stress and deformation distributions on the RDM, with no indications of failure in the machine's structure observed in either the experimental or numerical analyses. In conclusion, this study demonstrates that the machine analysed operates safely under harvesting conditions. Moreover, the combination of experimental and advanced CAE methodologies presented in this research offers a valuable approach for future investigations into the complex stress and deformation evaluations of rotary drum mowers.

Diving into the virtual realm: Exploring the mechanics of virtual reality

Virtual reality (VR) is a burgeoning technology that aspires to create an immersive digital experience for its users. This essay aims to explore how VR works by inspecting its hardware and software components, as well as the integration of both. The hardware components include the head-mounted display (HMD) with display screens, lenses, and motion tracking sensors for generating visual output and detecting head movements; Input devices, such as hand controllers, enable user interaction. The software components involve 3D computer graphics and rendering techniques, which allow the creation of virtual objects and environments. Real-time rendering ensures smooth and responsive visuals, while audio processing and sound simulation promote a realistic auditory experience. Integrating hardware and software components concerns real-time tracking and synchronization, recognizing and matching user movements with the virtual environment, and ensuring accurate interactions. Feedback mechanisms, especially haptic feedback like vibrations, enhance immersion. Understanding the workings of VR provides insights into its potential applications and its ability to transport users to virtual worlds.

PoMeLo: a systematic computational approach to predicting metabolic loss in pathogen genomes

BackgroundGenome streamlining, the process by which genomes become smaller and encode fewer genes over time, is a common phenomenon among pathogenic bacteria. This reduction is driven by selection for minimized energy expenditure in a nutrient-rich environment. As pathogens evolve to become more reliant on the host, metabolic genes and resulting capabilities are lost in favor of siphoning metabolites from the host. Characterizing genome streamlining, gene loss, and metabolic pathway degradation can be useful in assessing pathogen dependency on host metabolism and identifying potential targets for host-directed therapeutics.ResultsPoMeLo (Predictor of Metabolic Loss) is a novel evolutionary genomics-guided computational approach for identifying metabolic gaps in the genomes of pathogenic bacteria. PoMeLo leverages a centralized public database of high-quality genomes and annotations and allows the user to compare an unlimited number of genomes across individual genes and pathways. PoMeLo runs locally using user-friendly prompts in a matter of minutes and generates tabular and visual outputs for users to compare predicted metabolic capacity between groups of bacteria and individual species. Each pathway is assigned a Predicted Metabolic Loss (PML) score to assess the magnitude of genome streamlining. Optionally, PoMeLo places the results in an evolutionary context by including phylogenetic relationships in visual outputs. It can also initially compute phylogenetically-weighted mean genome sizes to identify genome streamlining events. Here, we describe PoMeLo and demonstrate its use in identifying metabolic gaps in genomes of pathogenic Treponema species.ConclusionsPoMeLo represents an advance over existing methods for identifying metabolic gaps in genomic data, allowing comparison across large numbers of genomes and placing the resulting data in a phylogenetic context. PoMeLo is freely available for academic and non-academic use at https://github.com/czbiohub-sf/pomelo.

3D Optical Coherence Tomography image processing in BISCAP: characterization of biofilm structure and properties.

BISCAP is a state-of-the-art tool for automatically characterizing biofilm images obtained from Optical Coherence Tomography. Limited availability of other software tools is reported in the field. BISCAP's first version processes 2D images only. Processing 3D images is a problem of greater scientific relevance since it deals with the entire structure of biofilms instead of their 2D slices. Building on the image-processing principles and algorithms proposed earlier for 2D images, these were adapted to the 3D case, and a more general implementation of BISCAP was developed. The primary goal concerns the extension of the initial methodology to incorporate the depth axis in 3D images; multiple improvements were also made to boost computational performance. The calculation of structural properties and visual outputs was extended to offer new insights into the 3D structure of biofilms. BISCAP was tested using 3D images of biofilms with different morphologies, consistently delivering accurate characterizations of 3D structures in a few minutes using standard laptop machines. Low user dependency is required for image analysis. BISCAP is available from https://github.com/diogonarciso/BISCAP. All images used in the tutorials and the validation examples are available from https://web.fe.up.pt/∼fgm/biscap3d.

Fiber colorimetric sensors with ambient humidity tolerance for NH3 sensing

Colorimetric sensors with visual color changes toward toxic gas have been investigated to prevent potential hazardous accidents caused by leakage. The sensitivity of most colorimetric sensors in practical applications is interfered with ambient humidity. This work introduced a hygroscopic substance lithium chloride (LiCl) to be used as humidity compensation to alleviate humidity interference to colorimetric sensor. Cellulose-based colorimetric fibers were prepared from waste cotton using chlorophenol red as an indicator dye in a LiCl/DMAc solvation system. The obtained colorimetric fibers responded quickly to NH3 within 30 s at 50% RH. At the same time, this colorimetric fiber has excellent selectivity and excellent reusability, which could maintain 82% of the original colorimetric response over several cycles. Because of the flexibility, this NH3 sensing colorimetric fiber can be sewn into patterned textiles for manufacturing wearable toxic gas sensors with visual output.

Instrument-free and rapid Vibrio parahaemolyticus biosensing based on coupled dual-signal of paper-needle and LnMOF

At present, most reported studies on paper-based sensing devices for food-borne pathogens usually rely on a single signal as the basis for judging the results, accompanied with inaccurate detection results. In this study, we used the lanthanide MOFs being covalently modified with aptamers (Apt-LnMOFs) as the sensing and recognition element of Vibrio parahaemolyticus (VP), and the paper-based needle shape device (paper-needle) as the visual signal output carrier. Finally, an accurate detection strategy for VP was successfully constructed. In terms of signal output, the two signal styles of Apt-LnMOFs diffusion distance on the paper-needle and R value (measured by the RGB analysis software of smartphone) are coupled to jointly improve the accuracy of detection results. The method is simple and fast, and the detection accuracy in real samples is 91%. This strategy is very suitable for on-site rapid detection of pathogens, and does not require large professional instruments.

Rapid Visual Detection of Spiroplasma eriocheiris by Loop-Mediated Isothermal Amplification with Hydroxynaphthol Blue Dye.

In recent years, a new type of Spiroplasma has been found that can cause "tremor disease" of the Chinese mitten crab Eriocheir sinensis. The outbreak of epidemic tremor disease has caused a serious setback in the Chinese mitten crab farming industry, with an incidence rate of more than 30% and mortality rates of 80-100%. Therefore, finding a sensitive method to detect tremor disease in E. sinensis has become a current research focus. In this research, a loop-mediated isothermal amplification detection method coupled with hydroxynaphthol blue dye (LAMP-HNB) was developed and used to rapidly detect Spiroplasma eriocheiris. First, we designed and synthesized specific outer primers, inner primers and loop primers based on the 16S ribosomal RNA gene of S. eriocheiris. Second, the LAMP-HNB detection method for S. eriocheiris was successfully established by screening the primers, adjusting the temperature and time of the reaction, and optimizing the concentrations of Mg2+ and dNTPs. In the specific tests, only samples infected with S. eriocheiris showed positive results, and other infections caused by bacteria and parasites tested negative, proving that the test has high specificity. Moreover, the detection limit was 2.5 × 10-6ng/µL, indicating high sensitivity. This method for detecting S. eriocheiris provides rapid visual output based on LAMP-HNB detection and is a simple, fast, sensitive, and inexpensive method that can be applied to a wide range of field investigations.

Biomimetic photonic crystal double-network hydrogel for visual and electrical dual signal bluetooth-enabled wearable sensor

The photonic crystal wearable sensor which has visual and electrical dual signal outputs is successfully developed.

Tumor location and neurocognitive function-Unravelling the association and identifying relevant anatomical substrates in intra-axial brain tumors.

Neurocognitive function is a key outcome indicator of therapy in brain tumors. Understanding the underlying anatomical substrates involved in domain function and the pathophysiological basis of dysfunction can help ameliorate the effects of therapy and tailor directed rehabilitative strategies. Hundred adult diffuse gliomas were co-registered onto a common demographic-specific brain template to create tumor localization maps. Voxel-based lesion symptom (VLSM) technique was used to assign an association between individual voxels and neuropsychological dysfunction in various domains (attention and executive function (A & EF), language, memory, visuospatial/constructive abilities, and visuomotor speed). The probability maps thus generated were further co-registered to cortical and subcortical atlases. A permutation-based statistical testing method was used to evaluate the statistically and clinically significant anatomical parcels associated with domain dysfunction and to create heat maps. Neurocognition was affected in a high proportion of subjects (93%), with A & EF and memory being the most affected domains. Left-sided networks were implicated in patients with A & EF, memory, and language deficits with the perisylvian white matter tracts being the most common across domains. Visuospatial dysfunction was associated with lesions involving the right perisylvian cortical regions, whereas deficits in visuomotor speed were associated with lesions involving primary visual and motor output pathways. Significant baseline neurocognitive deficits are prevalent in gliomas. These are multidomain and the perisylvian network especially on the left side seems to be very important, being implicated in dysfunction of many domains.

Research on the Theory and Innovation Strategy of Digital Media Art Development Based on Artificial Intelligence Technology

Abstract Artificial intelligence (AI) technology significantly enhances the creative capabilities and expressions of artists, playing a pivotal role in the innovation of digital media art. This paper delves into the technical aspects of digital media art expression, introducing a human-computer interaction (HCI) media art model. This model is designed to cater to the visual sensitivities of the human eye by optimizing text readability and interface color during interaction. We further enhance the interactive interface by converting the color space, applying de-blurring techniques, and mitigating the noise associated with image binarization to refine the HCI interface. The efficacy of these interventions is evaluated through practical implementations in digital media art, focusing on the application effectiveness of HCI and user satisfaction. Our experimental outcomes indicate that the noise level of the employed techniques is maintained within a narrow range of −1.5 to 1.5 dB, demonstrating minimal and consistent fluctuations that substantially improve image processing and influence the final visual output. Furthermore, in assessing user interaction satisfaction, the average user satisfaction scores for the four interactive modalities ranged between 3.316 and 3.684, indicating that most users are satisfied with the digital media art designs integrated with AI.

Pro-Peace vs. Pro-War Conceptualizations in the Language of Hungarian Propaganda

The language of propaganda can be treated as a specialist language with its own specialized terminology. It is produced by groups of variously configured propaganda experts responsible for the creation of propaganda messages, placed at one end of the communication channel, together with its specific target audience that consumes these messages, situated at the other end of the communication channel. As a result of this specialized communication process, the language of propaganda is function-oriented and its focus is always put on the objectives that are to be achieved. These include shaping and manipulating public opinions. For these goals to be successful, the language of propaganda must be equipped with efficient and well-designed conceptualizations able to change and modify the way people think. Defined as such, the language of propaganda is not a purely linguistic construct, but a multimodal tool able to make use of the visual and audiovisual output as well. The interest in mental processes such as conceptualization lies at the very center of cognitive linguistics and the study of cognitive mechanisms responsible for various types of conceptualizations is of high priority in cognitively driven approaches to language. Another issue which makes cognitive linguistics suitable for this type of research in specialist languages is its long standing preference for multidisciplinary and multimodal phenomena. Applying the methodology of cognitive linguistics, the present paper aims at identifying and discussing the PRO-PEACE vs. PRO-WAR network of conceptualizations in the language of Hungarian propaganda, often compared in its mastery with Orwell’s newspeak or the Soviet propaganda machinery because of its power and influence. Hungary’s leading right-wing party, Fidesz-KDNP, has retained political control in Hungary ever since its landslide victory in the 2010 national elections and developed a powerful propaganda tool that is ideally customized to the culture-specific preferences of Hungarian voters. Through quantitative and qualitative analysis, this research studies linguistic expressions shaping PRO-PEACE vs. PRO-WAR conceptualizations with their rich social, historical and cultural contexts.

Combined use of drones and geophysics in enhancing cemetery studies: Two case studies in Northern Ireland, UK

AbstractThe real‐time use of drone‐derived orthoimagery and ground‐penetrating radar (GPR) facilitate conjunctive ground surveying and aerial visual reference of subterranean features within cemeteries. Geospatially referenced visual outputs allow sympathetic restoration and assist in understanding historical use. Two contrasting case studies demonstrate this: The first is a subterranean wall, built to separate Catholic and Protestant burials in a civic cemetery. The second example is the accurate positioning of unmarked inhumations in an Irish Famine burial ground, which facilitated preservation as a memorial garden in a hospital complex.

High-Order Moment-Encoded Kinetic Simulation of Turbulent Flows

Kinetic solvers for incompressible fluid simulation were designed to run efficiently on massively parallel architectures such as GPUs. While these lattice Boltzmann solvers have recently proven much faster and more accurate than the macroscopic Navier-Stokes-based solvers traditionally used in graphics, it systematically comes at the price of a very large memory requirement: a mesoscopic discretization of statistical mechanics requires over an order of magnitude more variables per grid node than most fluid solvers in graphics. In order to open up kinetic simulation to gaming and simulation software packages on commodity hardware, we propose a HighOrder Moment-Encoded Lattice-Boltzmann-Method solver which we coined HOME-LBM, requiring only the storage of a few moments per grid node, with little to no loss of accuracy in the typical simulation scenarios encountered in graphics. We show that our lightweight and lightspeed fluid solver requires three times less memory and runs ten times faster than state-of-the-art kinetic solvers, for a nearly-identical visual output.

Posterior Predictive Checking for Partially Observed Stochastic Epidemic Models

We address the problem of assessing the fit of stochastic epidemic models to data. Two novel model assessment methods are developed, based on disease progression curves, namely the distance method and the position-time method. The methods are illustrated using SIR (susceptible-infective-removed) models. We assume a typical data observation setting in which case-detection times are observed while infection times are not. Both methods involve Bayesian posterior predictive checking, in which the observed data are compared to data generated from the posterior predictive distribution. The distance method does this by calculating distances between disease progression curves, while the position-time method does this pointwise at suitably selected time points. Both methods provide visual and quantitative outputs with meaningful interpretations. The performance of the methods benefits from the development and application of a time-shifting method that accounts for the random time delay until an epidemic takes off. Extensive simulation studies show that both methods can successfully be used to assess the choice of infectious period distribution and the choice of infection rate function.

OP46 The Decision Uncertainty Toolkit: Risk Measures And Visual Outputs To Support Health Technology Decision-making During Public Health Crises

IntroductionDuring public health crises such as the COVID-19 pandemic, decision-makers have relied on infectious disease models to predict and estimate the impact of various health technologies. The difficulties associated with capturing and representing uncertainty using infectious disease models leads to a high risk of making decisions that are misaligned to policy objectives. Even when uncertainty is adequately captured in the analysis, the tools for communicating the risks and harms of making wrong decisions have proved inadequate, which can lead to the suboptimal adoption of critical health technologies including vaccines and antivirals. We aim to adapt and extend health economic methods for the characterization, estimation, and communication of uncertainty to infectious disease modeling.MethodsEconomic and infectious disease models share many features, including the comparison of policy alternatives on outcomes important to decision-makers (such as hospital census, total infections), but each takes a different approach to analysis of uncertainty. We extend best practices from health economics to infectious disease modeling and develop a suite of tools and visualization techniques which represent parameter uncertainty and the risk these unknowns present to decision-makers.ResultsIn consultation with decision-makers and infectious disease modeling experts we developed the ‘Decision Uncertainty Toolkit’ of model outputs and visuals. Visual tools for uncertainty are developed to: (i) accurately capture uncertainty in key infectious disease model outputs, and (ii) support intuitive and direct interpretation by infectious disease modelers and decision-makers. We also developed quantitative measures for the downside risk of policy alternatives, specified to capture both the probability and magnitude of losses relative to policy targets for a range of infectious disease model outputs. Together, these outputs can support decision-making by quantifying outcome uncertainty and the risks associated with policy alternatives.ConclusionsWe developed the toolkit visuals and risk measures alongside infectious disease modelers and decision makers. The toolkit is designed to improve decision-maker understanding of decision risk in order to improve outcomes during future public health crises.

“Growing up we’re taught about physical activity, but very little mention of brain health, but it’s all brain health”: Exploring the Conceptualisation of Brain Health in 18–39‐year‐olds in Europe and North America

AbstractBackgroundIt is widely theorised that the accumulation of risk factors for neurodegenerative diseases like Alzheimer’s and other dementias likely begins during young adulthood, yet there is limited understanding about how young adults conceptualise their own brain health. The NextGen research programs aims to explore brain health and exposure to risk factors in adults before mid‐life. In this study, we explored young adults’ (18‐39 years) understanding and attitudes towards their brain health.MethodsThis qualitative study recruited community‐based adults aged 18‐39 years from the NextGen Programme of research, a large‐scale, international, multi‐centre research programme. Participants (N = 39; 18 female) had a mean age of 26 years (SD = 3.68) and were equally represented from North America (n = 20) and Europe (n = 19). Most participants identified as Black (76%), followed by White (15%), Asian (6%) and mixed race (3%). Data collection took place over focus groups using video conference technology and a semi‐structured discussion guide. A live Illustrator was present for each focus group to provide an immediate visual output of the group discussion. Data were analysed using thematic analyses by the research team.ResultsPreliminary themes highlight discrepancies between individuals’ awareness and understanding of their brain health, in relation to their general health, family history of dementia and personal experience of brain health issues (e.g., traumatic brain injury). Regarding factors that can positively affect brain health, participants highlighted the importance of rest, good nutrition and physical exercise. Regarding factors that can negatively affect brain health, participants highlighted exposure to racism and discrimination, poor quality sleep, stress, and excessive alcohol consumption. Participants also reported being unsure about many factors, such as screen‐time, cannabis use, engagement with social media and video games.ConclusionFindings from this study are among the first to explore young adults’ perceptions around brain health. We found that young adults had a moderate level of awareness of brain health risk factors, but they often did not connect these factors to risk of Alzheimer’s disease or other dementias. Outputs from this study will be used to inform a large‐scale, international survey to explore brain health awareness, understanding and exposure to risk factors among 18‐39‐year‐olds.

Using Methyl Bromide for Interspecies Cell-Cell Signaling and As a Reporter in a Model Soil Consortium.

Soil microbial communities with reduced complexity are emerging as model systems for studying consortia-scale phenotypes. To establish synthetic biology tools for studying these communities in hard-to-image environmental materials, we evaluated whether a single member of a model soil consortium (MSC) can be programmed to report on gene expression without requiring matrix disruption. For these studies, we targeted a five-membered MSC that includes Dyadobacter fermentans, Ensifer adhaerens, Rhodococcus sp003130705, Streptomyces sp001905665, and Variovorax beijingensis. By coupling the expression of a methyl halide transferase to a constitutive promoter, we show that V. beijingensis can be programmed to synthesize methyl halides that accumulate in the soil headspace at levels that are ≥24-fold higher than all other MSC members across a range of environmentally relevant hydration conditions. We find that methyl halide production can report on an MSC promoter that is activated by changes in water potential, and we demonstrate that a synthetic gas signal can be read out directly using gas chromatography and indirectly using a soil-derived Methylorubrum that is programmed to produce a visual output in response to methyl halides. These tools will be useful for future studies that investigate how MSC responds to dynamic hydration conditions, such as drought and flood events induced by climate change, which can alter soil water potential and induce the release of stored carbon.

Screen or No Screen? Lessons Learnt from a Real-World Deployment Study of Using Voice Assistants With and Without Touchscreen for Older Adults.

While voice user interfaces offer increased accessibility due to hands-free and eyes-free interactions, older adults often have challenges such as constructing structured requests and perceiving how such devices operate. Voice-first user interfaces have the potential to address these challenges by enabling multimodal interactions. Standalone voice + touchscreen Voice Assistants (VAs), such as Echo Show, are specific types of devices that adopt such interfaces and are gaining popularity. However, the affordances of the additional touchscreen for older adults are unknown. Through a 40-day real-world deployment with older adults living independently, we present a within-subjects study (N = 16; age M = 82.5, SD = 7.77, min. = 70, max. = 97) to understand how a built-in touchscreen might benefit older adults during device setup, conducting self-report diary survey, and general uses. We found that while participants appreciated the visual outputs, they still preferred to respond via speech instead of touch. We identified six design implications that can inform future innovations of senior-friendly VAs for managing healthcare and improving quality of life.