Gray Component Research Articles

The sum of the parts: Green, gray, and green-gray infrastructure to mitigate wave overtopping

Hybrid approaches to shoreline protection, where natural (“green”) features are combined with hardened (“gray”) infrastructure, are increasingly used to protect coastlines from erosion and flood-based hazards. Our understanding of hybrid systems is limited, and it is unknown whether the components of these systems interact in any meaningful sense to provide flood reduction benefits that are greater or less than “the sum of the parts.” In this study, a large-scale physical model was used to investigate the overtopping of a vertical wall protected by a hybrid system where an idealized Rhizophora mangrove forest of moderate cross-shore width fronted a rubble-mound revetment. Configurations included the wall alone, the wall with a low- or intermediate-density mangrove forest without the revetment, the wall with the revetment, and the wall with an intermediate- or high-density mangrove forest and the revetment. The study isolated the reduction in overtopping of the wall by the revetment component, the mangrove forest component, and the interaction between the components of the hybrid system. The total reduction by the hybrid system was estimated within 5% accuracy as the sum of the reduction by each component minus the product of the component reductions. Comparison of the proportional reduction in overtopping by the mangrove forest on the wall alone and the wall with the revetment indicated that the mangrove forest reduced the overtopping of the revetment by approximately the same proportion that the forest reduced the overtopping of the wall. Therefore, (1) total overtopping reduction by the hybrid system was modeled as the reduction expected from the green and gray components in series. Additional analysis showed that (2) for the same wave conditions, a mangrove forest of moderate cross-shore width can have equal or greater protective benefits than a coastal revetment, (3) there is an exponential relationship between the discharge rate and the forest density, and (4) the mangrove forest, the revetment, and the hybrid system all provided greater reduction in overtopping as wave steepness increased. The tests in this study were conducted without wave breaking, with constant freeboard and water depth, with a specific revetment geometry, and without a mangrove canopy. Therefore, these results should be interpreted with caution if used for engineering design.

The use of artificial intelligence for predicting postinfarction myocardial viability in echocardiographic images.

Evaluation of standard echocardiographic examination with artificial intelligence may help in the diagnosis of myocardial viability and function recovery after acute coronary syndrome. Sixty-one consecutive patients with acute coronary syndrome were enrolled in the present study (43 men, mean age 61 ± 9 years). All patients underwent percutaneous coronary intervention (PCI). 533 segments of the heart echo images were used. After 12 ± 1 months of follow-up, patients had an echocardiographic evaluation. After PCI each patient underwent cardiac magnetic resonance (CMR) with late enhancement and low-dose dobutamine echocardiographic examination. For texture analysis, custom software was used (MaZda 5.20, Institute of Electronics).Linear and non-linear (neural network) discriminative analyses were performed to identify the optimal analytic method correlating with CMR regarding the necrosis extent and viability prediction after follow-up. Texture parameters were analyzed using machine learning techniques: Artificial Neural Networks, Namely Multilayer Perceptron, Nonlinear Discriminant Analysis, Support Vector Machine, and Adaboost algorithm. The mean concordance between the CMR definition of viability and three classification models in Artificial Neural Networks varied from 42% to 76%. Echo-based detection of non-viable tissue was more sensitive in the segments with the highest relative transmural scar thickness: 51-75% and 76-99%. The best results have been obtained for images with contrast for red and grey components (74% of proper classification). In dobutamine echocardiography, the results of appropriate prediction were 67% for monochromatic images. Detection and semi-quantification of scar transmurality are feasible in echocardiographic images analyzed with artificial intelligence. Selected analytic methods yielded similar accuracy, and contrast enhancement contributed to the prediction accuracy of myocardial viability after myocardial infarction in 12 months of follow-up.

Towards healthy cities: Modeling restorative potential of urban environments by coupling LiDAR-derived 3D metrics with panorama-based online survey

With the growing concern for the psychological well-being of urban dwellers, there has been a recognized need to explore the role of green environments in facilitating mental restorative benefits from the demands of city life. However, a significant gap exists in quantitatively modeling the restorative potential of urban environments, especially in terms of comprehensive 3D characteristics beyond mere greenery. This research gap has hindered our understanding of how to plan and design urban spaces that promote mental health. To bridge this gap, we conducted a study using Singapore as a case study to model the restorative potential for landscape planning and design by integrating LiDAR-derived 3D metrics, outcomes of an online survey, and a machine learning-based regularized regression model. We first collected data from 100 scenes, including both residential neighborhoods and urban parks, by extracting point cloud information from LiDAR scans for calculating a diverse set of 41 3D spatial metrics. Alongside these objective measurements, we conducted an online survey (N = 1500) using the Perceived Restorativeness Scale (PRS) where respondents evaluated the restorative potential of these scenes presented as interactive panoramic images. We subsequently utilized a regularized regression technique based on machine learning by conducting K-fold cross-validation (K = 10) with 1251 tests to identify the feature metrics significantly contributing to restorative potential. Our findings highlighted the importance of the green volumetric ratio as the most significant positive factor for restorative potential. Additionally, the results on the metrics of grey horizontal diversity and grey cluster number indicated a positive impact of unregulated and unaggregated grey components on restorative potential. The results on green horizontal diversity suggested that a uniform and concentrated spatial arrangement of greenery is a positive predictor, while other factors like front-background ratio, colorfulness, and slope variation also positively influenced restorative potential. In essence, our study not only provides novel insights but also introduces innovative methods for quantitatively assessing and characterizing the quality of urban environments that enhance psychological well-being. These findings inform the practical planning and design strategies aimed at fostering healthy and sustainable urban spaces.

Applying machine learning to a nonlinear spectral mixing model for mapping lunar soils composition using CHANDRAYAAN-1 M3 data

We present a newly developed method which combines the nonlinear spectral mixing model of Shkuratov et al. (1999) with a machine learning algorithm to map the lunar regolith composition using spectral data. The new method performs orders of magnitude faster than the traditionally used numerical optimization approaches, allowing the mapping of regolith properties (including mineralogical composition, average grain size and optical maturity) over large areas of the lunar surface. A new set of basic mineral spectra of the lunar soil for using with spectral mixing models is proposed. Used together with the nonlinear mixing model (Shkuratov et al., 1999), the set is able to describes Chandrayaan-1 M3 instrument spectra collected from test areas which includes the Shapley crater with its surroundings containing mare and highland terrains well. The new set includes a virtual “gray component” with a “flat” (constant) spectrum, accounting for the factors that change general surface albedo, such as spectrally neutral components (e.g., agglutinate glasses), errors in the photometric reduction, uncertainties in estimations of lunar regolith porosity q and the mean grain size S of the basic minerals. The proposed new method takes into account the influence of space weathering and nonlinear correlation between the compositional and spectral parameters of the lunar soils delivering values for the optical properties and mineralogical abundance determination of the lunar regolith which are compatible with the results found from lunar samples measurements in the laboratory. The proposed approach can be used for analyzing spectral observations not only of the lunar surface but also for other surfaces with are covered by regolith.

VSDHS-CIEA: Color image encryption algorithm based on novel variable-structure discrete hyperchaotic system and cross-plane confusion strategy

Recently, the color image encryption algorithm based on chaos theory has become the focus of current research. When encrypting color images, the common practice is to treat color images as different gray components and process them severally, which results in more redundancy and low efficiency. The security of chaotic cryptosystems also depends on the performance of the chaotic systems adopted. The structures of many current chaotic systems are fixed, making their behaviors highly predictable. Additionally, the range of chaotic region parameters is limited and discontinuous. To solve the above-mentioned problems, a new color image encryption algorithm (CIEA) using fractal and chaos theory is presented, which fully considers the inherent connection among the RGB components of color images. First, we propose a variable-structure discrete hyperchaotic system (VSDHS) to solve the dilemma encountered by existing chaotic systems. The excellent dynamic properties of VSDHS are verified by rigorous mathematical proof and simulation performance analyses. Then, VSDHS-CIEA is designed using fractal theory and VSDHS. The algorithm makes full use of the inherent connection among the different components of color images and performs cross-plane confusion. Simulations and performance analyses prove that VSDHS-CIEA has higher security and better performance than some representative image encryption algorithms.

Understanding Consumer Choices: Towards Sustainable Water Use in India

This study addresses the pressing issue of water scarcity in India, focusing on sustainable water management and the crucial role of consumer behavior. It establishes a clear correlation between safe water access, economic development, and public health, emphasizing the interconnectedness of these factors. The concept of a water footprint, comprising green, blue, and gray components, provides a framework for analyzing global water usage. The socio-economic context highlights the significance of recognizing water as an economic good for efficient resource allocation. Global water availability is discussed, revealing the inadequacies in freshwater distribution and the widening gap between demand and supply. India's precarious position, given its large population, is underscored. Issues related to water consumption, including reckless groundwater exploitation, emphasize the need for stakeholder involvement and a paradigm shift in water management. The study stresses the urgency of an action plan for sustainable water management, advocating strategies such as storage, conservation, and recycling. Disproportionate water usage in agriculture and urban inefficiencies are addressed, urging modernization and technological advancements. Public engagement emerges as pivotal, with consumer behavior significantly impacting water usage patterns. The study discusses the role of public feedback "report cards" in promoting accountability among service providers, whether private or government-owned. Highlighting growing awareness in India, referencing NITI Aayog's Composite Water Management Index, the study emphasizes the disparity between population and freshwater resources. Groundwater depletion and per capita water use statistics underscore the need for immediate action. The study explores untapped water supply sources, advocating for the reduction of system leakage and promoting rainwater harvesting. The potential of stormwater and wastewater management is discussed, emphasizing the importance of incorporating green infrastructure solutions. In conclusion, the study underscores the significance of studying consumer behavior to enhance water conservation strategies. Recommendations include assessing consumer awareness, understanding utilization patterns, and perceptions affecting economic impact. The research advocates for a paradigm shift in water use and recycling, emphasizing the critical role of consumers in shaping a sustainable water future for India.

Co-building trust in urban nature: Learning from participatory design and construction of Nature-Based Solutions in informal settlements in East Africa

While the amount of research on NBS is growing rapidly, there is a lack of evidence on community experiences of NBS design and implementation, particularly from low-income and informal settlements of African cities. This article adds new empirical evidence in this space through grounded analysis of NBS “niche” projects co-developed by intermediary organizations and communities in five sites across three settlements in Nairobi and Dar es Salaam. Findings are organized around four established NBS knowledge gaps: (1) NBS-society relations; (2) Design; (3) Implementation; (4) Effectiveness. We find that across the five studied sites, residents' perceptions and valuation of urban nature has changed through processes of co-design and co-implementation, enabling community ownership of projects, and hence playing a crucial role in NBS effectiveness over time. The integration of gray components into green infrastructure to create hybrid systems has proven necessary to meet physical constraints and communities' urgent needs such as flood mitigation. However, maintenance responsibilities and cost burdens are persisting issues that highlight the complex reality of NBS development in informal settlements. The cases highlight key considerations for actors involved in NBS development to support the replication, scaling up and institutionalization of NBS. These include the need to: (i) develop forms of engagement that align with co-production values; (ii) capture communities' own valuation of and motivations with NBS development for integration into design; (iii) elaborate technical guidance for hybrid green-gray infrastructure systems that can be constructed with communities; and (iv) help define and establish structures for maintenance responsibilities (especially governmental vs. civil society) that will enhance the environmental stewardship of public spaces.

Low-Frequency Data Embedding for DFT-Based Image Steganography

As sharing digital media is getting more prominent, there has been a rise in the development of techniques for protecting digital media against misuse. However, the amount of such techniques has been less prominent for printed goods. The data hiding method presented in this paper is suited for the print domain. The method uses the Discrete Fourier Transform to embed data into images and Gray Component Replacement to maintain high image quality by masking embedding artifacts. This research examines whether the method's performance can be optimized using low-frequency ranges for embedding. The aim is to evaluate the usage of low-frequency ranges in order to achieve higher robustness. Different frequency ranges are tested to determine how they affect image quality and detection rates. Tests are conducted in the digital domain. The results show that the method can maintain image quality regardless of the frequency range, and that low-frequency ranges lead to more consistent detection rates. Future research will be done on images in the print domain.

Robust Image Hashing Combining 3D Space Contour and Vector Angle Features

AbstractIn this paper, an image hashing scheme combining 3D space contour (TDSC) features with vector angle (VA) features is proposed. The proposed algorithm extracts the 3D contours of the local component variation features of the image and the expression changes of the local component of the image in the form of a 3D VA to improve the performance. First, the gray component of the color image is used to construct a 3D space and the contour change features of the local component of the gray image are extracted using multi-perspectives. Then, the opposite color component and the brightness component Y of the YCbCr color space are extracted from the input image. The angular features of several image components are, respectively, extracted in the 3D space. Finally, the TDSC features are combined with the VA features to obtain image hashing. The simulations demonstrate and validate that the proposed image hashing scheme not only has better classification performance compared with the other image hashing techniques but is also equipped with the performance of tamper localization.

Water footprint assessment of surface and subsurface drip fertigated cotton-wheat cropping system – A case study under semi-arid environments of Indian Punjab

The advanced methods of irrigation and nutrient supply may save huge quantity of costly inputs over the prevalent practice of surface flood (SF) irrigation and fertilizer broadcasting in Indian Punjab. Surface drip fertigation (SDF) and subsurface drip fertigation (SSDF) enables the combined application of fertilizer and irrigation for improving the input use efficiency in Cotton-Wheat cropping system (CWCS) over the SF. Though, both SDF and SSDF perform better than SF, but their suitability in reducing the water footprint (WF) of CWCS has been least assessed. Therefore, a 2 yr field study at two distinct agro-climatic zones has been conducted to quantify and compare the WF of SDF and SSDF in comparison to SF for CWCS under semi-arid environments. Results revealed that under SSDF, cotton and wheat crops consumed 32 and 37% lower water than respective SF, indicative of huge water saving over the prevalent practice. Contribution of green, blue and grey components towards total WF under SF was 42, 48 and 10% respectively for cotton, and 24, 59 and 18% for wheat. SSDF application at 80% crop evapotranspiration (ETc) along with 100% recommended dose of nitrogen remarkably reduced the WF without any yield loss for CWCS. Higher total WF for CWCS under SF (5.30 m³ kg⁻1) revealed it to be inferior as compared to SDF (3.71 m³ kg⁻1) and SSDF (3.52 m³ kg⁻1). Cotton alone consumed 65–78% of WFtotal of the CWCS, while the remaining 22–35% was attributed to wheat. A lowered WFtotal for CWCS under SDF and SSDF over that of SF elucidated them to be immensely helpful to conserve limited water resources under semi arid climates. A cropping system based assessment was much reliable option to obtain a clear indicator about the annual WF as compared to single crop based estimation. These results could be utilized to access the performance of alternative irrigation and cultivation systems for developing the WF reduction approach over extended geographical scale.

Evaluation of water footprint in sugar industries and bioethanol distilleries in two different water basins toward water sustainability.

Sugarcane farming and bioethanol production are water-intensive activities that result in high water competition. The competition, in turn, can exacerbate water scarcity. Therefore, this study aims to evaluate the water footprint (WF) of the sugar and bioethanol production at the Finchaa and Metehara sugarcane farms, which are located in different river basins in Ethiopia. The climatic data (minimal and maximum temperature, relative humidity, wind speed, and sunshine duration), meteorological data (rainfall), CROPWAT 8.0 model, nitrogen fertilizer application rates, sugarcane yield, and sugar and bioethanol production over 12 years (2008–2019) were used. Penman–Monteith method-based sugarcane water requirements of Finchaa and Metehara were found to be 2021.1 and 3605.4 mm/growing period, respectively. The sugarcane WF of Finchaa was 188.01 m3/t, which was composed of green (67.45 m3/t), blue (113.42 m3/t), and grey (7.14 m3/t) components, whereas the WF of Metehara was 239.11 m3/t consisting of green (29.42 m3/t), blue (204.13 m3/t), and grey (5.56 m3/t). The low sugarcane WF recorded was attributed to the high yield of sugarcane that was harvested in the study areas. Hence, the irrigation (blue WF) requirement is the major concern of water management in the basins. Similarly, the WF of bioethanol at the Finchaa distillery (2067.62 L/L) was much higher than that of the Metehara distillery (1441.54 L/L). However, both WFs were within the global range. Significant differences were observed between the two water basins. The sugarcane estate farm and bioethanol production processes require water management intervention to reduce the impact of WF in the basins.

Robust DFT watermarking method with gray component replacement masking

Robust DFT watermarking method with gray component replacement masking

Variational Single Nighttime Image Haze Removal With a Gray Haze-Line Prior.

Influenced by glowing effects, nighttime haze removal is a challenging ill-posed task. Existing nighttime dehazing methods usually result in glowing artifacts, color shifts, overexposure, and noise amplification. Thus, through statistical and theoretical analyses, we propose a simple and effective gray haze-line prior (GHLP) to identify accurate hazy feature areas. This prior demonstrates that haze is concentrated on the haze line in the RGB color space and can be accurately projected into the gray component in the Y channel of the YUV color space. Based on this prior, we establish a new unified nighttime haze removal framework and then decompose a nighttime hazy image into color and gray components in the YUV color space. Glowing color correction and haze removal are two important consecutive steps in the nighttime dehazing process. The glowing color correction method is designed to separately remove glow in the color component and enhance illumination in the gray component. After obtaining a refined nighttime hazy image, we propose a new structure-aware variational framework to simultaneously estimate the inverted scene radiance and the transmission in the gray component. This approach can not only recover the high-quality nighttime scene radiance but also preserve the significant structural information and intrinsic color of the scene. Quantitative and qualitative comparisons validate the excellent effectiveness of the proposed nighttime dehazing method against previous state-of-the-art methods. In addition, the proposed approach can be extended to achieve image enhancement for inclement weather scenes, such as sandstorm scenes and extreme daytime hazy scenes.

Evaluating the Neuroimaging-Genetic Prediction of Symptom Changes in Individuals with ADHD.

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder that could persist into adulthood with known abnormalities in brain structure. Genetics also play an important role in the etiology of the disorder and could affect the disorder trajectory. In this study, we investigated the prediction power of brain image and genomic features for symptom change in 77 individuals with ADHD as part of NeuroIMAGE cohort. Gray matter components and working memory assessments at baseline, as well as gene scores of interest, were used to predict the changes in the two symptom domains: inattentive and hyperactive/impulsive, an average of 4 years. A linear regression model coupled with various feature selection approaches, including leave-one-out-cross-validation (LOOCV), stability selection with resampling, and permutation tests, was implemented to mitigate the overtraining potential caused by small sample sizes. Results showed that traditional LOOCV overestimated the prediction power. We proposed a novel stability selection with the threshold set by permutation tests, which provided more objective assessment. Using our proposed procedure, we identified a statistical promising prediction model for inattention symptom change; the consistent correlation between predicted values and measured values during model training, validating and hold out testing (r=0.64, 0.53, 0.46, respectively), but the p value is not significant in the holdout test. The selected features include age, gray matter in the insula, genes OSBPL1A, CTNNB1, PRPSAP2, ACADM, and polygenic risk score of education attainment, which have been previously reported to be associated with ADHD. We speculate that significant associations may be observed with a large sample size.

An entropy minimization based multilevel colour thresholding technique for analysis of breast thermograms using equilibrium slime mould algorithm

Breast cancer is one of the leading causes of death in women due to the abnormal growth of cells known as a tumour. Thermography is an imaging technique used to capture infrared radiation and generate a thermogram. The major advantages of thermography are contactless, radiation-free, painless, and real-time screening. The thermogram is used further in a pathological investigation. However, in the modern-day, machine intelligence technologies are used for the analysis of breast thermograms, which assist the expert in decision making. The machine intelligence technique requires a thresholding image during the preprocessing stage, which warrants an efficient thresholding method. Here, we investigate the multilevel thresholding objective function to minimize the information regarding the entropic dependence on various classes. A new Equilibrium Slime Mould Algorithm (ESMA) is proposed for colour image thresholding, an improvement of the Slime Mould Algorithm (SMA), by integrating the equilibrium practice in updating the slime mould positions from an equilibrium pool concept of Equilibrium Optimizer (EO). The ESMA performance is compared with well know optimization algorithms and ranked one based on Friedman’s mean rank, when evaluated using 53 test problems. Further, the ESMA is used for the development of an entropy minimization based multilevel colour thresholding method for the analysis of breast thermograms. It is applied in two sets of experiments using grey components and the RGB components of breast thermograms. The encouraging results on the thermogram image analysis are presented. Even more interesting results are seen while evaluating our proposal in terms of different metrics—the peak signal to noise ratio (PSNR), the feature similarity (FSIM), and the structure similarity (SSIM). Statistical a nalysis provided reveals the suitability of the technique for the analysis of breast thermograms. The method may assist the medical practitioners, as an additional tool. The ESMA may be useful for solving different optimization problems in the world of engineering.

Yield, technological quality and water footprints of wheat under Mediterranean climate conditions: A field experiment to evaluate the effects of irrigation and nitrogen fertilization strategies

The evaluation of the role of different agronomic strategies in achieving sustainable wheat yields under variable Mediterranean climate conditions may involve the use of resource-use indicators that combine productivity and environmental impact. A two-seasons field experiment was conducted in South Portugal to study the effect of water regimes and nitrogen fertilization on wheat yield, grain quality and water use evaluated with water productivity and water footprint indicators. The water regime treatments were full irrigation, supplemental irrigation, and rainfed. Nitrogen fertilizer treatments, including conventional and enhanced efficiency fertilizers (EEF) were distinguished by N splitting and timing over the crop cycle. Contrasting meteorological variables in the two years caused distinct wheat productive responses. Although leading to lower grain yields, supplemental irrigation guaranteed a water productivity similar to full irrigation. The use of EEFs in which 50% of the total nitrogen was applied at the booting phase had a positive significant effect on grain protein content and on dough rheologic properties, indicating that late nitrogen applications benefit the technological quality of wheat. The average total water footprints estimated for the two seasons showed no relevant differences but the partition of the green, blue and grey components in irrigated wheat varied, with an increased importance of blue water consumptive use in the second year of the experiment. In fact, the ratio blue water footprint/green water footprint increased from 0.40 to 2.00 due to higher irrigation requirements. High grey water footprint in rainfed wheat was mostly influenced by lower yields in 2018–2019, and by an advantageous rainfall distribution during the 2017–2018 season. No significant reduction in grey water footprint was observed when using EEFs. A multivariate statistical approach through factor analysis (FA) and multivariate linear regression (MLR) was used to examine the data structure and correlation. FA resulted in three-factor models of yield and water use, yield components and wheat quality, in the first season. In the second, drier, season, variables most related with irrigation water use were clustered in one detached factor. The stepwise MLR pointed to a good prediction capability of water footprints from NDVI measured with proximal sensors at booting, anthesis, maturation and/or tillering.

Water Footprint of soybean, cotton, and corn crops in the western region of Bahia State

ABSTRACT Water catchment to subsidize agricultural activities is estimated at 70% of world consumption. In the western region of Bahia, the main agricultural center of the state, there is intensive use of water for the production of agricultural commodities. In regions with high water demand, quantification of the use of this resource can be performed using anthropic pressure indicators, such as the Water Footprint. Thus, this work determined the Water Footprint of the soybean, cotton, and corn crops produced in the western region of Bahia State. In order to determine the Water Footprint, data of the environmental characteristics and crop production in the region were used, were obtained from different Brazilian public and private institutions. The calculation of Water Footprint of the crops was performed by the sum of the green, blue, and gray components. The average Water Footprint between 2012 and 2017 for soybean corresponded to 1,972.3 m3 t-1, with cotton at 1,825.2 m3 t-1, and corn 512.4 m3 t-1. The analyses of the results and the comparison with the values of the Water Footprint of other regions demonstrate that the edaphoclimatic conditions of the western region of Bahia are propitious to the development of these crops.

Setting boundaries within a bottled water plant aid to better visualize the water use: An approach through the water footprint indicator

In this work, the total water involved in a bottled water model plant was estimated. Total water footprint (WF), including blue, grey, and indirect components were calculated for three setting boundaries: inner (process), middle (product) and outer (industry). Total WF was obtained as the sum of the direct (operational) and the indirect (supply chain) WF. Then, five hypothetical scenarios (with regard to the base-case) were examined to find alternatives for WF reduction. In WF terms, total water use involved in the entire plant was 600% higher than the amount directly consumed (blue). The indirect WF component contributed the most to the total in all boundaries (64–78%), due to energy consumption and raw materials. Blue and grey components were the highest in the inner due to bottles filling and detergent use. Hypothetical scenarios showed us that WF values can change among established boundaries, which would directly impact on decision-making, based upon the priorities set by the stakeholders. For example, if business wants to increase production while minimizing water use, it should aim to reduce the WF of the middle boundary. Conversely, if the goal is to reach an environmental and social commitment, the plant should consider reducing the WF of the outer boundary, to reduce the electrical energy usage or to replace tap with groundwater. Defining boundaries for WF calculation is a smart tool to distinguish critical sectors so that business could decide where and how to apply (or not) actions towards more efficient production.

Color reproduction on varnished cardboard packaging by using lower ink coverages due to the gray component replacement image processing

AbstractEven in these challenging times, cardboard packaging industry is increasing its revenue with stable annual increase prediction, but customers are increasing demands on the packaging with respect to environmental protection, attractiveness, and branding. This article aims to determine the influence of image processing in terms of gray component replacement and overprint varnishing on the color reproduction on a cardboard packaging material. A test chart with tertiary colors was defined and modified by different gray component replacement levels. It was printed in accordance with ISO norm on coated and uncoated cardboard and finished by overprinting water based, offset, and UV varnish. The prepared samples were evaluated by measuring surface coverage, tone value increase (dot gain) of primary colors and calculating ΔE00 of defined tertiary colors. The results showed that gray component replacement application reduces ink consumption. Higher gray component replacement applied results in lower ink surface coverage, but the decrease is also dependent on the image content. The TVI (dot gain) is significantly influenced only by applying UV varnish, resulting with higher TVI. The color differences of the tertiary colors showed that increased level of the gray component replacement applied did not cause significant color differences, even decreased color difference in some cases. Additionally, applying gray component replacement decreased color differences in “reddish” part of the gamut. This research proved that lowering the ink consumption due to the gray component replacement will not cause significant differences in the color reproduction. Furthermore, varnishing with commercial offset or water‐based varnish will not cause higher deviations in color reproduction, but use of the UV varnish would.

Determination of Pneumonia in X-ray Chest Images by Using Convolutional Neural Network

Pneumonia is one of the major diseases that cause a lot of deaths all over the world. Determining pneumonia from chest X-ray (CXR) images is an extremely difficult and important image processing problem. The discrimination of whether pneumonia is of bacterium or virus origin has also become more important during the pandemic. Automatic determination of the presence and origin of pneumonia is crucial for speeding up the treatment process and increasing the patient's survival rate. In this study, a convolutional neural network (CNN) framework is proposed for detection of pneumonia from CXR images. Two different binary CNNs and a triple CNN are used for determining: (\textit {i}) normal or pneumonia, (\textit{ii}) pneumonia of bacterium or virus origin, and (\textit{iii}) normal or bacterial pneumonia or viral pneumonia. In this approach, CNNs are trained with Walsh functions to extract the features from CXR images, and minimum distance classifier instead of a fully connected neural network is employed for classification purpose. Training with Walsh functions maintains the within-class scattering to be low, and between-class scattering to be high. Preferring the minimum distance classifier reduces the number of nodes used and also allows the network to be controlled with fewer hyperparameters. These approaches bring some advantages to the system designed for the classification process: (\textit{i}) easy determination of hyperparameters, (\textit{ii}) achieving higher classification performance, and (\textit{iii}) use of fewer neurons. The proposed small-size CNN model was applied to CXR images from 1- to 5-year-old children provided by the Guangzhou Women's and Children's Medical Center (GWCMC). Three experiments have been conducted to improve the classification performance: (\textit{i}) the effect of different sizes of input images on the performance of the network was investigated, (\textit{ii}) training set was augmented by randomly flipping left to right or down to up, by adding Gaussian noise to the images, by creating negative images randomly, and by changing image brightness randomly (\textit{iii}) instead of RGB CXR images, gray component of the original image and four 2D wavelet images were given as input to the network. In these experiments, no major changes were observed in the classification results obtained by using the proposed CNNs. The proposed method has achieved 100\% accuracy for normal or pneumonia, 92\% for pneumonia of bacterium or virus origin, and 90\% for normal or bacterial pneumonia or viral pneumonia. It is observed that higher classification performances were obtained with approximately five times less parameters compared to the networks that gave the best results in the literature. Thus, the applied CNN model is promising in medicine and can help experts make quick and accurate decisions.