Additive Color Research Articles

Extreme learning machine for identifying soil-dwelling microorganisms cultivated on agar media

The aim of this research is to create an automated system for identifying soil microorganisms at the genera level based on raw microscopic images of monocultural colonies grown in laboratory environment. The examined genera are: Fusarium, Trichoderma, Verticillium, Purpureolicillium and Phytophthora. The proposed pipeline deals with unprocessed microscopic images, avoiding additional sample marking or coloration. The methodology includes several stages: image preprocessing, segmenting images to isolate microorganisms from the background, calculating features related to image color and texture for classification. Using an extensive dataset of 2866 images from the National Institute of Horticultural Research in Skierniewice the Extreme Learning Machine model was trained and validated. The model showcases high accuracy and computational efficiency compared to other Machine Learning state-of-the art methods e.g. CatBoost, Random Forest or Convolutional Neural Networks. Statistical techniques, including Multivariate Analysis of Variance were employed to confirm significant differences among the datasets, enhancing the model’s robustness. Nevertheless, Shapley Additive Explanations values provided transparency into the model’s decision-making process. This approach has the potential to improve early detection and management of soil pathogens, promoting sustainable agriculture and demonstrating machine learning’s potential in environmental monitoring, microbial ecology or industrial microbiology.

A complete workflow from embalmed specimens to life-like 3D virtual models for veterinary anatomy teaching.

Understanding normal structural and functional anatomy is critical for health professionals across various fields such as medicine, veterinary, and dental courses. The landscape of anatomical education has evolved tremendously due to several challenges and advancements in blended learning approaches, which have led to the adoption of the use of high-fidelity 3D digital models in anatomical education. Cost-effective methods such as photogrammetry, which creates digital 3D models from aligning 2D photographs, provide a viable alternative to expensive imaging techniques (i.e. computed tomography and magnetic resonance imaging) whilst maintaining photorealism and serving multiple purposes, including surgical planning and research. This study outlines a comprehensive workflow for producing realistic 3D digital models from embalmed veterinary specimens. The process begins with the preservation of specimens using the modified-WhitWell (WhitWell-Liverpool) embalming protocol, which ensures optimal tissue rigidity and improved colour enhancement, facilitating easier manipulation and better photogrammetry outcomes. Once embalmed, specimens are photographed to create digital 3D models using photogrammetry. Briefly, all images are processed to generate a sparse point cloud, which is then rendered into a 3D mesh. The mesh undergoes decimation and smoothing to reduce computational load, and a texture is applied to create a lifelike model. Additional colour enhancements and adjustments are made using digital tools to restore the natural appearance of the specimens. The 3D models are stored on a cloud repository and integrated into the University of Liverpool's Virtual Learning Environment, providing continuous, remote access to high-quality anatomical resources. The switch to embalmed specimens during the COVID-19 pandemic allowed for longer-term use and detailed dissections, enhancing the quality of digital models. Fresh specimens, though naturally coloured, are less stable for photogrammetry, making embalmed specimens preferable for accurate 3D modelling. Our method ensures embalmed specimens are rigid enough for precise modelling while allowing texture adjustments to enhance digital representation. This approach has improved logistical efficiency, educational delivery, and specimen quality. Innovative embalming techniques and advanced photogrammetry have the power to revolutionise anatomical education with the creation of a vast digital library accessible online to students at any time. This approach paves the way for integrating digital 3D models into immersive environments and assessing their impact on learning outcomes.

TLC densitometric approach for concurrent determination of quinary mixture for treatment of migraine with appraisal to method greenness and whiteness

A new accurate, precise thin layer chromatographic (TLC densitometric) approach was developed for the simultaneous analysis of ergotamine tartrate (ERG), phenobarbital sodium (PHEN), caffeine anhydrous (CAF), dipyrone sodium (DIP) and meprobamate (MEP) in their pure form and in their combined formulation; (MIGRANIL tablets). TLC separation depended on using a stationary phase of TLC plates F254 (20 × 10 cm) and using a developing system of ethyl acetate: methanol: n- hexane (8:2:3, by volume) with UV scanning at 254 nm for ERG, PHEN, CAF and DIP. For MEP, detection was done at 560 nm after spraying with 0.3% ethanolic solution of para -dimethylaminobenzaldehyde (PDAB) and heating at 110 ºC for 30 min. Analysis was performed in the concentration intervals of 0.06-2, 0.15–5 µg/band for ERG and PHEN, respectively; while for CAF, DIP and MEP it was done in the ranges of 0.3-9, 0.5–10, 1–100 µg/band, respectively. Moreover, the method was used for the quantitation of the five studied drugs in their unique formulation and the recovery% was calculated and found to be 102.04, 100.73, 100.65, 99.91, 1nd 101.77% for ERG, PHEN, CAF, DIP, and MEP, in order and all these outcomes proved excellent selectivity of the method. Other validation parameters were tested following ICH guidelines. Accuracy ranged from 98.02 to 100.53% while the obtained %RSD of interday day precision ranged from 1.215 to 1.940%. The environmental impact and performance of the method was tested with several tools; Analytical eco-scale, green analytical procedure index (GAPI), Analytical GREEnness Metric Approach (AGREE), Blue applicability grade index (BAGI), and RGB additive color model. Results ensured minimum hazardous effect on health and environment. This is the first analytical approach developed for simultaneous analysis of the quinary mixture which can be easily applied in any analytical laboratory.

Bio‐Inspired Bright Non‐Iridescent Structurally Colored Nanopigments Featuring Additive Color Mixing Performance

AbstractOwing to the unique features of high chemical and photostability, structurally colored materials can potentially replace organic dyes and pigments in many applications. The most common fabrication method of structural color materials is the “bottom‐up” self‐assembly approach. However, the assembled structures are easily damaged by external forces, leading to color fading or even disappearance. Therefore, it is still a challenge to fabricate structural colors that mimic the appearance of absorbing pigments without assembly processes. Inspired by the Steller's jay, non‐iridescent structurally colored nanopigments are created, which are composed of hollow SiO2 (H‐SiO2) microspheres with amorphous carbon on the inner wall of the shell and disordered metasurfaces on the shell layer. It is shown that the color originates from the synergistic effect of the disordered metasurfaces and the amorphous carbon layer, which can produce strong coherent scattered light and effectively absorb incoherently scattered light, respectively. Amazingly, the H‐SiO2 microspheres can maintain their structural colors even after grinding or being dispersed in water. What's more, through the additive color mixing of two base colors and precise tuning of their ratios, gradient structural colors that spanning the visible spectrum can be achieved. These features indicate promising prospects for the designed nanopigments.

Retrospective evaluation of the induction of anaesthesia with alfaxalone or propofol in cats undergoing caesarean section.

Several anaesthetic protocols for caesarean section (c-section) have been described in dogs; however, anaesthesiological studies in cats undergoing c-section are lacking. The aim of this study was to assess the viability and outcome of kittens born from queens undergoing emergency c-section and receiving propofol or alfaxalone for anaesthetic induction and isoflurane for maintenance of general anaesthesia. All cats admitted to the Veterinary Teaching Hospital of the University of Bologna between January 2014 and December 2022 for dystocia that had undergone an emergency c-section were analysed in this retrospective study. The queens received propofol 2-6 mg/kg IV (group P) or alfaxalone 1-3 mg/kg IV (group A) administered slowly; general anaesthesia was maintained with isoflurane. Survival of all the kittens was evaluated at birth and after 24 h; in addition, heart rate, respiratory rate and mucous membrane colour were evaluated in the kittens at birth. Of the 14 cats included in the study, eight received alfaxalone (group A) and six received propofol (group P) for induction of the general anaesthesia. A total of 50 kittens were born by c-section: 30 kittens in group A and 20 in group P. The overall survival of the kittens was 90% at birth: 96.7% (29/30) for group A and 80% (16/20) for group P. The 24 h survival rate was 93.1% for group A and 87.5% for group P. The results of the present study demonstrated that in cats undergoing c-section, both alfaxalone and propofol are feasible for the induction of general anaesthesia.

Ultrafast, Fano resonant colorimetric sensor with high chromaticity beyond standard RGB

Fast-responsive colorimetric sensors with a wide color gamut have garnered significant attention for real-time atmospheric monitoring observable to the naked eye. Although swelling medium-based Fabry–Perot cavities, which enable linear resonance shifts with high Q-factors, have been widely suggested, they face limitations such as a restricted color gamut within standard RGB due to subtractive colors and slow response times caused by the top layer blocking, delaying the swelling medium’s equilibrium time. Here, we present two-dimensionally nanostructured Fano resonant colorimetric sensors using a swelling medium with significantly improved responsiveness and color representation beyond standard RGB. The nanostructured Fano resonator is elaborately designed to transform the spectral line shape into a Lorentz state in terms of reflectance, resulting in additive color through controlled coupling parameters of the resonator systems. In addition, the nanostructuring of the surface provides direct channels to water vapors, ensuring fast and strong interaction with the swelling medium. Consequently, the fabricated sensor exhibits a wide color gamut, covering 141% of standard RGB and 105% of Adobe RGB, and demonstrates rapid responsiveness with response and recovery times of 287 ms and 87 ms, respectively.

Empirical BRDF model for goniochromatic materials and soft proofing with reflective inks.

The commonly used analytic bidirectional reflectance distribution functions (BRDFs) do not model goniochromatism, that is, angle-dependent material color. The material color is usually defined by a diffuse reflectance spectrum or RGB vector and a specular part based on a spectral complex index of refraction. Extension of the commonly used BRDFs based on wave theory can help model goniochromatism, but this comes at the cost of significant added model complexity. We measured the goniochromatism of structual color pigments used for additive color printing and found that we can fit the observed spectral angular dependence of the bidirectional reflectance using a simple modification of the standard microfacet BRDF model. All we need to describe the goniochromatism is an empirically-based spectral parameter, which we use in our model together with a specular reflectance spectrum instead of the spectral complex index of refraction. We demonstrate the ability of our model to fit the measured reflectance of red, green, and blue commercial structural color pigments. Our BRDF model enables straightforward implementation of a shader for interactive preview of 3D objects with printed spatially and angularly varying texture.

QRGB+: Advanced QR Code Generator with RGB Color Method in Python to Expand Data Capacity

The present work entitled QRGB, consists of the development of an application in Python for the generation of QR codes using the additive color generation (RGB) method. This innovative method allows increasing the density of information stored in QR codes by using three color layers (red, green and blue), each representing a different set of data. QRGB offers an efficient and secure solution for storing and transmitting large amounts of information in limited spaces, significantly improving the capabilities of traditional black and white QR codes. By using three layers of colors, QRGB codes can store up to three times more information in the same space. This technique not only increases storage capacity but also improves information security, making it difficult to forge or manipulate the code. The overlay of multiple data layers allows redundancy to be implemented, increasing the robustness of the code against damage or reading errors. QRGBs are especially useful in applications that require the transmission of large amounts of data in limited spaces, such as in the packaging industry, digital business cards, and interactive advertising. Additionally, they have great potential in areas such as document and banknote security, where the authenticity and integrity of information are crucial. These points provide a solid foundation for understanding the innovation and advantages of colored QR codes (QRGB) compared to traditional QR codes, highlighting their applicability and potential in various sectors. This article presents a novel method for encoding and decoding information using a QRGB code, which involves the generation of three independent QR codes and their superimposition according to the additive color system (RGB). The research highlights the challenges encountered during the encoding and decoding processes due to the lack of specific libraries in Python, which required the creation of a custom solution using open source tools. The implementation takes advantage of Python and its libraries: qrcode[pil] to generate QR codes with the Pillow dependency for image manipulation, Pillow to open, manipulate and save different image formats, and opencv-python to perform tasks such as image processing and object detection. Despite facing issues with color mixing and accurate information retrieval, the proposed method demonstrates a significant increase in data density within a single QR code. Future work will focus on optimizing the algorithm and exploring potential applications in data security and high-density information storage. This Python script is designed to generate and decode QR codes with a logo overlay using a graphical user interface (GUI) built with Tkinter. The script combines several functionalities, such as creating QR codes, overlaying a logo, combining QR images of different colors, and manually decoding combined QR codes.

Robust blind color deconvolution and blood detection on histological images using Bayesian K-SVD

Hematoxylin and Eosin (H&E) color variation among histological images from different laboratories can significantly degrade the performance of Computer-Aided Diagnosis systems. The staining procedure is the primary factor responsible for color variation, and consequently, the methods designed to reduce such variations are designed in concordance with this procedure.In particular, Blind Color Deconvolution (BCD) methods aim to identify the true underlying colors in the image and to separate the tissue structure from the color information. Unfortunately, BCD methods often assume that images are stained solely with pure staining colors (e.g., blue and pink for H&E). This assumption does not hold true when common artifacts such as blood are present, requiring an additional color component to represent them. This is a challenge for color standardization algorithms, which are unable to correctly identify the stains in the image, leading to unexpected results.In this work, we propose a Blood-Robust Bayesian K-Singular Value Decomposition model designed to simultaneously detect blood and extract color from histological images while preserving structural details. We evaluate our method using both synthetic and real images, which contain varying amounts of blood pixels.

Development of a capillary electrophoresis method with laser-induced fluorescence detection for the characterization of oligosaccharides in human milk

Breast milk is the most appropriate food for an infant in the first months of life - it provides the essential nutrients required for proper growth, with breast milk oligosaccharides (HMOs) being the third most abundant component. HMO concentrations vary based on factors like lactation stage and maternal health. They play crucial roles in infant health, acting as prebiotics, antimicrobials, and immune modulators. Analytical methods like capillary electrophoresis and liquid chromatography are the most often used in HMOs qualitative and quantitative analysis. Continuing research aims to enhance analytical techniques for comprehensive HMOs analysis, this work presents the development of a capillary electrophoresis method with laser-induced fluorescence detection along with derivatization and solid-phase extraction steps for the characterisation of major oligosaccharides in colostrum samples. Validation parameters, such as linearity (0.9949–0.9989), limits of detection (5.49–16.40 ng cm−3) and quantification (18.30–54.67 ng cm−3), intra- and inter-day precision (2.41–9.78% and 1.27—14.5%, respectively), trueness (− 8.4 to − 2.0%), and recovery (70.02–113.5%) and repeatability (2.22–10.58%) for solid-phase extraction stage were assessed. The method was evaluated using RGB additive colour model regarding the analytical and practical effectiveness and greenness of the method (achieving a brilliance score of 67.1%). Moreover, the developed method was successfully applied to determine three oligosaccharides (DSLNT, 3’SL, and 6’SL) in colostrum samples. Considering its effectiveness, the method has promise for this type of application.Graphical abstract

Buddhism’s Knotted Thread (結縷法): Indian Origins and Chinese Adaptations

The Buddhist “Knotted Thread” originates from the ancient Indian practice of venerating sacred threads. In Indian culture, sacred threads symbolize identity and status and possess functions such as exorcism, healing, disaster prevention, blessing, protection, and divination. Initially, Buddhism opposed the use of sacred threads by its followers. However, as Buddhism evolved, it began to adopt this and other practices. Buddhist threads could be monochromatic or multicolored, with five-colored threads (五色縷) having significant cultural connections to China. In Buddhism, the five colors typically consist of four primary colors (四本色; blue, yellow, red, and white) plus an additional color. The difference between the Buddhist and traditional Chinese five colors lies in the selection of the fifth color. The five-colored threads in Buddhism have various combinations, such as blue, yellow, red, white, and black; blue, yellow, red, white, and purple; and blue, yellow, red, white and green. With Buddhism’s spread into China, to align with traditional Chinese notions of five colors, the Buddhist five-colored threads gradually standardized to blue, yellow, red, white, and black. The evolution of the Buddhist five-colored threads reflects the cultural exchange between India and China.

Graphical modeling of additive color mixing. Analyses of electromagnetic effects as colors of the vision analyzer

The human visual analyzer is a high form of evolution. Some jellyfish can distinguish light and dark objects with sensitive cells. Squids, octopuses, and nautiluses from Cephalopods family have eyes with which they can see objects. Visual information is processed in the brain. In fishes, the visual analyzer evolved. Fishes living below 100 m depth inhabit a world with blue light. The authors consider the evolution of vision in these fishes due to the lowest absorption of blue and violet colors of electromagnetic waves from the optical spectrum. Subsequently, on land, in humans vision evolved towards the green color. Green is the most prevalent color on the land. In humans, three light-sensitive cones evolved – S, M, and L. S cones are most sensitive to blue, M – to green, and L – to red color in the spectrum. Some humans retain sensitivity of S to genetic changes and disorders. Additive color mi­xing is a high form of color perception in humans. The additive mixing of different colors achieves a new color in the human visual analyzer. Remarkably, different individuals perceive observed images in varying manners. Mixing neighboring colors on the spectrum gives one, two, or three colors. This process is estimated using graphical modeling. The graphical modeling with two colors allows for the creation of additive colors. One, two, or three additive colors can be obtained. The production of colors results from the light sensitivity of S, M, and L cones. An analysis that phy­sically demonstrates the mixing of green and red colors, resulting in the colors yellow or orange. When blue and red are mixed, the resulting colors are green, yellow, and orange is proposed. The additive mixing of blue and yellow gives green. The subjective nature of visual perception, influenced by the viewer’s heightened sensitivity to one of the colors, beco­mes evident in the presence of two colors. Notably, when the background is violet, the sensitivity of the blue cones diminishes.

Resonant-mode engineering for additive reflective structural colors with high brightness and high color purity

We present quad-layered reflective structural color filters generating vivid additive primary colors by controlling a mode number in a Fabry–Perot (FP) cavity and an anti-reflective (AR) coating layer, thus accomplishing high spectral contrast which is highly demanded in creating sharp colors. The reflection brightness of fabricated structural color filters is over 78% and a color gamut is comparable to the standard color gamut (sRGB). Higher-order resonant modes are exploited yielding a narrow passband with strong suppression of the reflection at shorter and longer wavelength ranges for a green color, while red and blue colors are produced by employing fundamental resonant modes. Besides, the structural color filters maintain both high brightness and high color purity at oblique incidence angles up to 40° due to a small angle of refraction by a cavity medium with high refractive index. Moreover, a large-scale fabrication is enabled owing to the simplicity of a device structure, where thin film deposition is used. The scheme presented in this work may open the door to a number of applications, such as reflective displays, imaging devices, colored photovoltaics, and decorations.

Modeling and optimization of the ratio of fluorophores: a step towards enhancing the sensitivity of ratiometric probes.

In the ratiometric fluorescent (RF) strategy, the selection of fluorophores and their respective ratios helps to create visual quantitative detection of target analytes. This study presents a framework for optimizing ratiometric probes, employing both two-component and three-component RF designs. For this purpose, in a two-component ratiometric nanoprobe designed for detecting methyl parathion (MP), an organophosphate pesticide, yellow-emissive thioglycolic acid-capped CdTe quantum dots (Y-QDs) (analyte-responsive), and blue-emissive carbon dots (CDs) (internal reference) were utilized. Mathematical polynomial equations modeled the emission profiles of CDs and Y-QDs in the absence of MP, as well as the emission colors of Y-QDs in the presence of MP separately. In other two-/three-component examples, the detection of dopamine hydrochloride (DA) was investigated using an RF design based on blue-emissive carbon dots (B-CDs) (internal reference) and N-acetyl L-cysteine functionalized CdTe quantum dots with red/green emission colors (R-QDs/G-QDs) (analyte-responsive). The colors of binary/ternary mixtures in the absence and presence of MP/DA were predicted using fitted equations and additive color theory. Finally, the Euclidean distance method in the normalized CIE XYZ color space calculated the distance between predicted colors, with the maximum distance defining the real-optimal concentration of fluorophores. This strategy offers a more efficient and precise method for determining optimal probe concentrations compared to a trial-and-error approach. The model's effectiveness was confirmed through experimental validation, affirming its efficacy.

Viologen‐based host–guest supramolecule with tunable intramolecular/intermolecular electron transfer chromism and dynamic fluorescence

AbstractViologen, as a type of strong electron acceptor, is prone to undergo electron transfer (ET) and change color under external stimuli. However, due to the easy aggregation of viologen molecules, they usually suffer from poor fluorescence emission in the condensed phase. Herein, a new viologen derivative of VioCl2·2Cl (12+·2Cl) was designed and synthesized, in which the fluorescence was enhanced by introducing Me‐β‐CD to weaken the interactions between viologen molecules. Then a viologen‐based host–guest supramolecule of 12+@Me‐β‐CD was obtained by electrostatic interactions. Photo‐/chemo‐responded guest 12+ supplies 12+@Me‐β‐CD, a green and dark purple caused by intramolecular and intermolecular ET. Furthermore, 12+@Me‐β‐CD displays an additional thermal responsive purple color. The triple chromic behaviors all exhibit excellent reversibility and cycling stability. As expected, 12+@Me‐β‐CD exhibits strong photoluminescence (PL) in solid–liquid dual states, presenting an improved quantum yield (Φ) from 12+ (Φs = 0.37%, Φl = 16.74%) to 12+@Me‐β‐CD (Φs = 10.45%, Φl = 25.86%), and the fluorescence intensity can be dynamically modulated by light, heat, and acid/base vapors. The multi‐responsive chromism and tunable fluorescence of 12+@Me‐β‐CD allow for potential applications in information security and smart windows.

Dynamic range issues and image information content when visualizing seismic data

The purpose of this review is to discuss the problem of seismic data visualization in relation to human vision capabilities based on the seismic signal dynamic range assessment. The ways of increasing the information content and efficiency of visualization methods in terms of increasing their resolution are considered. The conducted analysis has shown that the dynamic range of seismic recordings exceeds the capabilities of the human eye by 2–3 orders of magnitude and the capabilities of technical visualization means by 4–5 orders of magnitude. Color vision models are considered on example of the most versatile hardware additive RGB color model. The model was chosen based on the idea of the human vision system as a set of photosensitive cones that register red, green and blue colors and the human brain, which processes and forms a color image in one’s consciousness. The relationships between monochrome and color images perceived by the human eye based on several types of sensitive receptors have been established. It is concluded that the use of a color image significantly expands information capabilities. Thus, 8 grey steps are enough for the monochrome method of information output, whereas the use of color devices allows to increase the number of steps up to 14. The methodology for solving this problem consists in the application of new technologies based on the use of large-scale and three-dimensional images providing a significant increase in the values of luminous flux, resolution and contrast based on the expansion of the dynamic range taking into consideration the limits of human vision.

The Descartes Code (Spin Orbital Rotation of Photons)–IV. The Harress-Sagnac Color Excess in the Rotation Curves of Galaxies

In 1933, Zwicky formulated the significant bifurcation point in the history of astrophysics. Zwicky postulated an unknown dark matter in order to explain the color excess in the observed Doppler effect in the rotation curves of galaxies. However, until now we have not detected these dark matter particles. In this contribution, we propose to come back to this bifurcation point and to interpret the observed color excess as the Harress-Sagnac effect known in the rotating interferometers. We have described photon properties in those rotating interferometers based on the old color theory of Descartes—rotating light globules (spin-orbital rotation of photons). Therefore, the color excess observed in the rotation curves of galaxies can be interpreted as the additional color excess of photons emitting from distant rotating stars. Formulae for these color excesses are given for different locations of the rotating galaxy inspired by Zwicky’s core-shell model of galaxies. A part of Zwicky’s enigma is an unknown influence of the Solar gravitational field at 1 AU on the distant photon properties. From the forgotten Gerber’s retarded potential formula we have derived an expression for the acceleration of distant photons towards the Sun at 1 AU as ax = 1.171 × 10⁻¹⁰ ms⁻². This is a very surprising coincidence with the Milgrom empirical value a0 = (1.2 ± 0.1) × 10⁻¹⁰ ms⁻². Therefore, we propose to test this new formula at the surface of Mercury and Mars in order to reveal if our gravitational models are universal or “geocentric”, valid for the surroundings of the Earth only.

Mining co-location patterns of manufacturing firms using Q statistic and additive color mixing.

The agglomeration effect significantly influences firms' site selection. Manufacturing firms often exhibit intricate spatial co-location patterns that are indicative of agglomerations due to their reliance on material input and product output across various subdivisions of manufacture. In this study, we present an analytical approach employing the Q statistic and additive color mixing visualization to assess co-location patterns of manufacturing firms. We identified frequent pairs and triplets of manufacturing divisions, mapping them to reveal distinct categories: labor-intensive clusters, upstream/downstream industrial chains, and technology-spillover clusters. These agglomeration categories concentrate in different regions of the city. Policy implications are proposed to promote the upgrade of labor-intensive divisions, enhance the operational efficiency of upstream/downstream industrial chains, and reinforce the spillover effects of technology-intensive divisions.

Development of craft drinks with oat milk and fruit and berry powders

Consumption of plant-based milk is growing every year, especially among allergy sufferers and lactose intolerant people. The development of beverages based on it with the addition of nutrients and improved taste properties is a trend among soft drink manufacturers. The purpose of the article is to develop recipes for craft drinks with oat milk and powders from freeze-dried fruits and berries, as well as to determine their sensory and physicochemical characteristics. The research was conducted using the method of expert evaluation of the sensory characteristics of drink compositions, the calculation method for calculating the nutritional and energy value of drinks, qualimetry methods for calculating a comprehensive indicator of drink quality, methods for determining the physicochemical characteristics of drinks, the Color Detector & Catcher mobile application for determining the colour of drinks using the RGB additive colour model, and methods of statistical data processing using Mathcad 14 software. For drinks based on plant-based milk, it is proposed to use powders from freeze-dried fruits and berries as a recipe components. Freeze-dried plant powders preserve the colour, smell and taste of natural raw materials, as well as their nutrients. Model compositions of drinks with oat milk and powders made from freeze-dried mango, blueberries, strawberries, bilberries and raspberries were developed. The best drink compositions with high sensory properties (taste and smell, colour, appearance and consistency) were identified by an expert evaluation method. The density and active acidity of the developed drink compositions were investigated and their nutritional and energy values were calculated. It was found that the density of drinks increases with the increase in the content of fruit and berry powders, and the pH of drinks decreases. It has also been found that an increase in the content of freeze-dried fruit and berry powders in a drink leads to an increase in the content of protein and carbohydrates. Fruit and berry powders fortify drinks with nutrients and diversify their taste and aroma. The proposed drinks can be recommended for implementation in food industry enterprises, craft food production facilities and restaurants

Marine Object Detection using YOLOv4 Adapted Convolutional Neural Network

This research presents an innovative application of the YOLOv4 object detection model for the identification and classification of marine objects within a dataset encompassing seven distinct classes. The study focuses on enhancing the robustness and accuracy of object detection in challenging marine environments, leveraging the unique capabilities of YOLOv4. Pre-processing steps involve resizing raw images, applying data augmentations, and normalizing pixel values to ensure optimal model training. Specifically tailored for underwater scenarios, additional color space transformations address variations in lighting conditions. The model is trained to detect marine objects such as fish, corals, and underwater structures, contributing to advancements in underwater exploration, environmental monitoring, and marine resource management. Experimental results demonstrate the effectiveness of the proposed approach, showcasing YOLOv4's ability to accurately identify and classify marine objects across the specified seven classes. This research not only expands the applicability of YOLOv4 in the marine domain but also provides valuable insights for the development of intelligent systems for underwater object detection.