Three-tier quick-response code: Applications for encoded text and counterfeit prevention system

This paper introduces a novel approach for encoding information in PDF documents or similar files. The proposed encoding involves a dual-step method: firstly, the information is encoded in base64, and subsequently, it is uploaded in a user-selected color, while the rest of the colors contain dummy information. Merging of the encoded segments results in a single QR code. The Literature Review subsection investigates the usage of similar methods for information encoding, followed by a comparison of the luminance of the generated QR code with theoretical expectations. Finally, diverse use cases are presented. The proposed methodology is presented:•Compare the results obtained from the theorical approximation with those acquired in the merged QR code.•Use cases: encoding text sample to obtain a counterfeit system.•Results, contributions, and future work.

Nanosized quantum dots-wrapped metallic particles ensembles integrated into filter disc-based analytical device for garlic evaluation. Application to monitor fake pickled garlic in balsamic vinegar

Herein, an affordable and simple analytical device is presented to portable identify of garlic in 30 min; the evaluation needs no pre-treatment of sample. The analytical device fabrication was did employing a headspace-based nanosensor array using of inexpensive materials as commercial filter discs, quantum dots (QDs), and metallic nanoparticles (MNPs). The nanoarray is fabricated by the accumulation QDs on MNPs surface, that results in the production of ensembles of QDs/MNPs. The ensembles generate diverse colorimetric profiles as "fingerprints" regarding to each garlic sample. The volatile organosulfur compounds (OSCs) of garlic can prefer binding to the MNPs comparing with QDs. The color profiles can be displayed with a smartphone camera, which can be quantitatively distinguished by chemometrics approaches. The analytical device was used to assessment of fake pickled samples in balsamic vinegar. This device proves well potential for qualitative control of garlic.

Feasibility of Using a Cheap Colour Sensor to Detect Blends of Vegetable Oils in Avocado Oil

This proof-of-concept study explored the use of an RGB colour sensor to identify different blends of vegetable oils in avocado oil. The main aim of this work was to distinguish avocado oil from its blends with canola, sunflower, corn, olive, and soybean oils. The study involved RGB measurements conducted using two different light sources: UV (395 nm) and white light. Classification methods, such as Linear Discriminant Analysis (LDA) and Least Squares Support Vector Machine (LS-SVM), were employed for detecting the blends. The LS-SVM model exhibited superior classification performance under white light, with an accuracy exceeding 90%, thus demonstrating a robust prediction capability without evidence of random adjustments. A quantitative approach was followed as well, employing Multiple Linear Regression (MLR) and LS-SVM, for the quantification of each vegetable oil in the blends. The LS-SVM model consistently achieved good performance (R2 > 0.9) in all examined cases, both for internal and external validation. Additionally, under white light, LS-SVM models yielded root mean square errors (RMSE) between 1.17-3.07%, indicating a high accuracy in blend prediction. The method proved to be rapid and cost-effective, without the necessity of any sample pretreatment. These findings highlight the feasibility of a cost-effective colour sensor in identifying avocado oil blended with other oils, such as canola, sunflower, corn, olive, and soybean oils, suggesting its potential as a low-cost and efficient alternative for on-site oil analysis.

Fraxicon for Optical Applications with Aperture ∼1 mm: Characterisation Study

Emerging applications of optical technologies are driving the development of miniaturised light sources, which in turn require the fabrication of matching micro-optical elements with sub-1 mm cross-sections and high optical quality. This is particularly challenging for spatially constrained biomedical applications where reduced dimensionality is required, such as endoscopy, optogenetics, or optical implants. Planarisation of a lens by the Fresnel lens approach was adapted for a conical lens (axicon) and was made by direct femtosecond 780 nm/100 fs laser writing in the SZ2080™ polymer with a photo-initiator. Optical characterisation of the positive and negative fraxicons is presented. Numerical modelling of fraxicon optical performance under illumination by incoherent and spatially extended light sources is compared with the ideal case of plane-wave illumination. Considering the potential for rapid replication in soft polymers and resists, this approach holds great promise for the most demanding technological applications.

Protocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning

BACKGROUND

The escalating impact of diabetes and its complications, including diabetic foot ulcers (DFUs), presents global challenges in quality of life, economics, and resources, affecting around half a billion people. DFU healing is hindered by hyperglycemia-related issues and diverse diabetes-related physiological changes, necessitating ongoing personalized care. Artificial intelligence and clinical research strive to address these challenges by facilitating early detection and efficient treatments despite resource constraints. This study establishes a standardized framework for DFU data collection, introducing a dedicated case report form, a comprehensive dataset named Zivot with patient population clinical feature breakdowns and a baseline for DFU detection using this dataset and a UNet architecture.

RESULTS

Following this protocol, we created the Zivot dataset consisting of 269 patients with active DFUs, and about 3700 RGB images and corresponding thermal and depth maps for the DFUs. The effectiveness of collecting a consistent and clean dataset was demonstrated using a bounding box prediction deep learning network that was constructed with EfficientNet as the feature extractor and UNet architecture. The network was trained on the Zivot dataset, and the evaluation metrics showed promising values of 0.79 and 0.86 for F1-score and mAP segmentation metrics.

CONCLUSIONS

This work and the Zivot database offer a foundation for further exploration of holistic and multimodal approaches to DFU research.

Machine learning constructs color features to accelerate development of long-term continuous water quality monitoring

Long-term continuous water quality monitoring (LTCM) is crucial to ensure the safety of water resources. However, lab-based pollutant detection via machine learning (ML) usually involves colorimetric materials or sensors, and it cannot be ignored that sensor limitations prevent their use for LTCM. To address this challenge, we propose a novel method that leverages image recognition to establish a relationship between pollutant concentration and color. By extracting efficient color variation features from raw pixel matrices using a combination of Kmeans clustering and RGB average features, the concentrations of pollutants that are difficult to distinguish by the naked eyes can be directly captured without the need for sensors and preprocessing. Four ML models (XGBoost, Linear, support vector regression (SVR), and Ridge) achieved up to a 95.9% increase in coefficient of determination (R2) compared to principal component analysis (PCA). In the prediction of the concentration of simulated pollutants such as Cu2+, Co2+, Rhodamine B, and the concentration of Cr(VI) in actual electroplating wastewater, natural resource water and drinking water, over 95% R2 was achieved. The method reported in our work can effectively capture subtle color changes that cannot be observed by the naked eyes without any preprocessing of water samples, providing a reliable method for LTCM.

A simple, fast, and cost-effective smartphone-based digital imaging method for quantification of lidocaine hydrochloride in pharmaceutical formulations

OBJECTIVE

A simple, highly specific, accurate and fast method by smartphone-based digital imaging was developed for estimating lidocaine hydrochloride in pharmaceutical formulations.

MATERIAL AND METHODS

To obtain the images, a Galaxy A03 Core smartphone and an image acquisition device developed in the laboratory were used to control the incident factors in reproducibility of the measurements. The processing of the images was carried out with the Color Grab application. Finally, the absorbance values were calculated using the RGB intensity values of blank, standard, and sample solutions. The proposed method was compared with spectroscopic and chromatographic methods.

RESULTS

The reaction between copper and lidocaine hydrochloride was characterized, showing better results in an equimolar ratio and maintaining the pH of the solution above 11.5. The use of the device for the capture of digital images allowed to control those sensitive parameters for reproducibility so that the analytical measurements showed adequate precision and accuracy. Validation of the main parameters of the method showed compliance with acceptance criteria. The application of the method for the analysis of injectable samples achieved reliable results, which were statistically similar to other reference instrumental methods.

CONCLUSION

The proposed method presented figures of merit in relation to linearity, precision, selectivity, accuracy, and robustness; it was carried out by designing and manufacturing a device for capturing digital images on a smartphone, which were analyzed to obtain RGB intensity values. These data are finally used to calculate absorbance values of solutions. All these elements provide this work with innovative characteristics in the field of analysis for control of pharmaceutical formulations.

Current trends in digital camera-based bioassays for point-of-care tests

Point-of-care and bedside tests are analytical devices suitable for a growing role in the current healthcare system and provide the opportunity to achieve an exact diagnosis by an untrained person and in various conditions and sites where it is necessary. Using a digital camera integrated into a well-accessible device like a smartphone brings a new way in which a colorimetric point-of-care diagnostic test can provide unbiased data. This review summarizes basic facts about the colorimetric point-of-care tests, principles of how to use a portable device with a camera in the assay, applications of digital cameras for the current tests, and new devices described in the recent papers. An overview of the recent literature and a discussion of recent developments and future trends are provided.

Multicolor emission-based nitrogen, sulfur and boron co-doped photoluminescent carbon dots for sequential sensing of Fe3+ and cysteine: RGB color sensor and live cell imaging

Herein, a simple hydrothermal synthesis is used to prepare multiple heteroatom-doped photoluminescent carbon dots (CDs) from thiourea (N and S source) and boric acid (B source) as precursors. The optical and physicochemical properties of the as-synthesized NSB-CDs were studied using UV-Vis, photoluminescence, TEM, FT-IR, XRD, Raman, and XPS analyses. The NSB-CDs exhibited excellent stability, high photostability, pH, and ionic strength tolerance; they retained their excellent stability independent of excitation. The NSB-CDs featured small sizes of approximately 3.2 ± 0.4 nm (range: 2.0-5.0 nm) as evidenced using TEM measurements. The NSB-CDs were used as a photoluminescent sensing platform to detect Fe3+ as well as cysteine (Cys) molecules. The competitive binding of Cys to Fe3+ resulted in NSB-CDs that retained their photoluminescence. For the rapid identification and quantification of Fe3+ and Cys, NSB-CDs were developed as a "switch-on" dual-function sensing platform. The linear detection range of Fe3+ was 0-20 μM (limit of detection [LOD]: 54.4 nM) and that of Cys was 0-50 μM (LOD: 4.9 nM). We also introduced a smartphone RGB analysis method for detecting low-concentration solutions based on digital images. The NSB-CDs showed no toxicity at 100 μg/mL. Photoluminescent probes for multicolor live-cell imaging can be used with NSB-CDs at this concentration, suggesting that NSB-CDs may be promising photoluminescent probes.

Biosensor-Based Multimodal Deep Human Locomotion Decoding via Internet of Healthcare Things

Multiple Internet of Healthcare Things (IoHT)-based devices have been utilized as sensing methodologies for human locomotion decoding to aid in applications related to e-healthcare. Different measurement conditions affect the daily routine monitoring, including the sensor type, wearing style, data retrieval method, and processing model. Currently, several models are present in this domain that include a variety of techniques for pre-processing, descriptor extraction, and reduction, along with the classification of data captured from multiple sensors. However, such models consisting of multiple subject-based data using different techniques may degrade the accuracy rate of locomotion decoding. Therefore, this study proposes a deep neural network model that not only applies the state-of-the-art Quaternion-based filtration technique for motion and ambient data along with background subtraction and skeleton modeling for video-based data, but also learns important descriptors from novel graph-based representations and Gaussian Markov random-field mechanisms. Due to the non-linear nature of data, these descriptors are further utilized to extract the codebook via the Gaussian mixture regression model. Furthermore, the codebook is provided to the recurrent neural network to classify the activities for the locomotion-decoding system. We show the validity of the proposed model across two publicly available data sampling strategies, namely, the HWU-USP and LARa datasets. The proposed model is significantly improved over previous systems, as it achieved 82.22% and 82.50% for the HWU-USP and LARa datasets, respectively. The proposed IoHT-based locomotion-decoding model is useful for unobtrusive human activity recognition over extended periods in e-healthcare facilities.

A deep learning model for rapid classification of tea coal disease

BACKGROUND

The common tea tree disease known as "tea coal disease" (Neocapnodium theae Hara) can have a negative impact on tea yield and quality. The majority of conventional approaches for identifying tea coal disease rely on observation with the human naked eye, which is labor- and time-intensive and frequently influenced by subjective factors. The present study developed a deep learning model based on RGB and hyperspectral images for tea coal disease rapid classification.

RESULTS

Both RGB and hyperspectral could be used for classifying tea coal disease. The accuracy of the classification models established by RGB imaging using ResNet18, VGG16, AlexNet, WT-ResNet18, WT-VGG16, and WT-AlexNet was 60%, 58%, 52%, 70%, 64%, and 57%, respectively, and the optimal classification model for RGB was the WT-ResNet18. The accuracy of the classification models established by hyperspectral imaging using UVE-LSTM, CARS-LSTM, NONE-LSTM, UVE-SVM, CARS-SVM, and NONE-SVM was 80%, 95%, 90%, 61%, 77%, and 65%, respectively, and the optimal classification model for hyperspectral was the CARS-LSTM, which was superior to the model based on RGB imaging.

CONCLUSIONS

This study revealed the classification potential of tea coal disease based on RGB and hyperspectral imaging, which can provide an accurate, non-destructive, and efficient classification method for monitoring tea coal disease.

Versatile recognition of graphene layers from optical images under controlled illumination through green channel correlation method

In this study, a simple yet versatile method is proposed for identifying the number of exfoliated graphene layers transferred on an oxide substrate from optical images, utilizing a limited number of input images for training, paired with a more traditional number of a few thousand well-published Github images for testing and predicting. Two thresholding approaches, namely the standard deviation-based approach and the linear regression-based approach, were employed in this study. The method specifically leverages the red, green, and blue color channels of image pixels and creates a correlation between the green channel of the background and the green channel of the various layers of graphene. This method proves to be a feasible alternative to deep learning-based graphene recognition and traditional microscopic analysis. The proposed methodology performs well under conditions where the effect of surrounding light on the graphene-on-oxide sample is minimum and allows rapid identification of the various graphene layers. The study additionally addresses the functionality of the proposed methodology with nonhomogeneous lighting conditions, showcasing successful prediction of graphene layers from images that are lower in quality compared to typically published in literature. In all, the proposed methodology opens up the possibility for the non-destructive identification of graphene layers from optical images by utilizing a new and versatile method that is quick, inexpensive, and works well with fewer images that are not necessarily of high quality.

A Low-Cost Microfluidic-Based Detection Device for Rapid Identification and Quantification of Biomarkers-Based on a Smartphone

The sensitive and rapid detection of microsamples is crucial for early diagnosis of diseases. The short response times and low sample volume requirements of microfluidic chips have shown great potential in early diagnosis, but there are still shortcomings such as complex preparation processes and high costs. We developed a low-cost smartphone-based fluorescence detection device (Smartphone-BFDD) without precision equipment for rapid identification and quantification of biomarkers on glass capillary. The device combines microfluidic technology with RGB image analysis, effectively reducing the sample volume to 20 μL and detection time to only 30 min. For the sensitivity of the device, we constructed a standard sandwich immunoassay (antibody-antigen-antibody) in a glass capillary using the N-protein of SARS-CoV-2 as a biological model, realizing a low limit of detection (LOD, 40 ng mL^-1). This device provides potential applications for different biomarkers and offers wide use for rapid biochemical analysis in biomedical research.

Analysis of facial redness by comparing VISIA and YLGTD

BACKGROUND

Erythema, characterized by redness of the skin, is a common symptom in various facial skin conditions. Recent advancements in image processing and analysis techniques have led to the development of methods for analyzing and assessing skin texture. This study aimed to investigate the correlation between the parameters of "You Look Good Today" (YLGTD) and VISIA in the detection and assessment of facial redness.

MATERIALS AND METHODS

Thirty female subjects participated in this experiment, undergoing assessments using both YLGTD and VISIA. The subjects were evaluated for facial redness, and the feature count results within the red zone were measured by VISIA. YLGTD analyzed the number and percentage of red zone pixels. The assessments were conducted between [specific dates] in [location].

RESULTS

The results demonstrated a significant positive correlation between the feature count results within the red zone measured by VISIA and the number of red zone pixels. Similarly, YLGTD exhibited a significant positive correlation with the number and percentage of red zone pixels.

CONCLUSION

In conclusion, our findings suggest a correlation between YLGTD and VISIA in the measurement of facial erythema. YLGTD can serve as a portable device for primary screening assessments, offering a convenient and reliable method to evaluate facial redness. This research contributes to the development of non-invasive techniques for assessing and monitoring facial skin conditions, providing valuable insights for dermatological diagnosis and cosmetic testing.

Row selection in remote sensing from four-row plots of maize and sorghum based on repeatability and predictive modeling

Remote sensing enables the rapid assessment of many traits that provide valuable information to plant breeders throughout the growing season to improve genetic gain. These traits are often extracted from remote sensing data on a row segment (rows within a plot) basis enabling the quantitative assessment of any row-wise subset of plants in a plot, rather than a few individual representative plants, as is commonly done in field-based phenotyping. Nevertheless, which rows to include in analysis is still a matter of debate. The objective of this experiment was to evaluate row selection and plot trimming in field trials conducted using four-row plots with remote sensing traits extracted from RGB (red-green-blue), LiDAR (light detection and ranging), and VNIR (visible near infrared) hyperspectral data. Uncrewed aerial vehicle flights were conducted throughout the growing seasons of 2018 to 2021 with data collected on three years of a sorghum experiment and two years of a maize experiment. Traits were extracted from each plot based on all four row segments (RS) (RS1234), inner rows (RS23), outer rows (RS14), and individual rows (RS1, RS2, RS3, and RS4). Plot end trimming of 40 cm was an additional factor tested. Repeatability and predictive modeling of end-season yield were used to evaluate performance of these methodologies. Plot trimming was never shown to result in significantly different outcomes from non-trimmed plots. Significant differences were often observed based on differences in row selection. Plots with more row segments were often favorable for increasing repeatability, and excluding outer rows improved predictive modeling. These results support long-standing principles of experimental design in agronomy and should be considered in breeding programs that incorporate remote sensing.

Soybean leaf estimation based on RGB images and machine learning methods

BACKGROUND

RGB photographs are a powerful tool for dynamically estimating crop growth. Leaves are related to crop photosynthesis, transpiration, and nutrient uptake. Traditional blade parameter measurements were labor-intensive and time-consuming. Therefore, based on the phenotypic features extracted from RGB images, it is essential to choose the best model for soybean leaf parameter estimation. This research was carried out to speed up the breeding procedure and provide a novel technique for precisely estimating soybean leaf parameters.

RESULTS

The findings demonstrate that using an Unet neural network, the IOU, PA, and Recall values for soybean image segmentation can achieve 0.98, 0.99, and 0.98, respectively. Overall, the average testing prediction accuracy (ATPA) of the three regression models is Random forest > Cat Boost > Simple nonlinear regression. The Random forest ATPAs for leaf number (LN), leaf fresh weight (LFW), and leaf area index (LAI) reached 73.45%, 74.96%, and 85.09%, respectively, which were 6.93%, 3.98%, and 8.01%, respectively, higher than those of the optimal Cat Boost model and 18.78%, 19.08%, and 10.88%, respectively, higher than those of the optimal SNR model.

CONCLUSION

The results show that the Unet neural network can separate soybeans accurately from an RGB image. The Random forest model has a strong ability for generalization and high accuracy for the estimation of leaf parameters. Combining cutting-edge machine learning methods with digital images improves the estimation of soybean leaf characteristics.

Microglia colonize the developing brain by clonal expansion of highly proliferative progenitors, following allometric scaling

Microglia arise from the yolk sac and enter the brain during early embryogenesis. Upon entry, microglia undergo in situ proliferation and eventually colonize the entire brain by the third postnatal week in mice. However, the intricacies of their developmental expansion remain unclear. Here, we characterize the proliferative dynamics of microglia during embryonic and postnatal development using complementary fate-mapping techniques. We demonstrate that the developmental colonization of the brain is facilitated by clonal expansion of highly proliferative microglial progenitors that occupy spatial niches throughout the brain. Moreover, the spatial distribution of microglia switches from a clustered to a random pattern between embryonic and late postnatal development. Interestingly, the developmental increase in microglial numbers follows the proportional growth of the brain in an allometric manner until a mosaic distribution has been established. Overall, our findings offer insight into how the competition for space may drive microglial colonization by clonal expansion during development.

Decoding of the neural representation of the visual RGB color model

RGB color is a basic visual feature. Here we use machine learning and visual evoked potential (VEP) of electroencephalogram (EEG) data to investigate the decoding features of the time courses and space location that extract it, and whether they depend on a common brain cortex channel. We show that RGB color information can be decoded from EEG data and, with the task-irrelevant paradigm, features can be decoded across fast changes in VEP stimuli. These results are consistent with the theory of both event-related potential (ERP) and P300 mechanisms. The latency on time course is shorter and more temporally precise for RGB color stimuli than P300, a result that does not depend on a task-relevant paradigm, suggesting that RGB color is an updating signal that separates visual events. Meanwhile, distribution features are evident for the brain cortex of EEG signal, providing a space correlate of RGB color in classification accuracy and channel location. Finally, space decoding of RGB color depends on the channel classification accuracy and location obtained through training and testing EEG data. The result is consistent with channel power value distribution discharged by both VEP and electrophysiological stimuli mechanisms.

Learning-Based Near-Infrared Band Simulation with Applications on Large-Scale Landcover Classification

Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges for the vegetation extraction. To this end, this paper presents a conditional generative adversarial network (cGAN) method to simulate the NIR band from RGB bands of Sentinel-2 multispectral data. We adapt a robust loss function and a structural similarity index loss (SSIM) in addition to the GAN loss to improve the model performance. With 45,529 multi-seasonal test images across the globe, the simulated NIR band had a mean absolute error of 0.02378 and an SSIM of 89.98%. A rule-based landcover classification using the simulated normalized difference vegetation index (NDVI) achieved a Jaccard score of 89.50%. The evaluation metrics demonstrated the versatility of the learning-based paradigm in remote sensing applications. Our simulation approach is flexible and can be easily adapted to other spectral bands.

Highly biologically active and pH-sensitive collagen hydrolysate-chitosan film loaded with red cabbage extracts realizing dynamic visualization and preservation of shrimp freshness

Accurate and efficient detection of food freshness is of great significance to guarantee food safety. Herein, pH sensitive colorimetric films with considerable biological activities have been prepared by combining red cabbage anthocyanin extracts (RCE) with collagen hydrolysate-chitosan (CH-CS) matrix film. The formation mechanism of CH-CS-RCE films was discussed by SEM, FT-IR and XRD, which showed that RCE was successfully fixed in CH-CS film through hydrogen bonding and electrostatic interaction. The CH-CS-RCE films exhibited good mechanical properties, high barrier ability, excellent thermal stability, significant antioxidant and antimicrobial activity, and especially sensitive response to pH and ammonia. Fickian diffusion was the main mechanism for the release of RCE from CH-CS-RCE films and such release mechanism facilitated the maintenance of functional features of films. During the storage of shrimps at 4 °C, CH-CS-RCE2% showed a remarkable preservation effect on shrimps, and their shelf life was prolonged from 2 d to 5 d. Furthermore, CH-CS-RCE2% provided a dynamic visual color switching to detect the freshness of shrimp, realizing real-time monitoring of freshness. Color information (RGB) extracted via smartphone APP was used to enhance the accuracy and universality of freshness indication. Thus, this multifunctional film has great potential in food preservation and freshness monitoring.

Chromatographic analysis of ciprofloxacin and metronidazole in real human plasma: green analytical chemistry perspective

Background: Ciprofloxacin and metronidazole are beneficial for treating mixed aerobic/anaerobic infections. Methods: Following the oral administration of ciprofloxacin and metronidazole in healthy volunteers, TLC and HPLC methods were described for their analysis in plasma samples. In the first method, a stationary phase of silica gel TLC F254 plates was used using acetone/water/triethylamine/glacial acetic acid (8:2:0.25:0.1 v/v). The second approach used a C18 column and methanol/aqueous 0.05% triethylamine (25:75 v/v), with a flow rate of 1 ml/min and detection at 325 nm. Four green metrics were used to evaluate the approaches' environmental impact. Conclusion: The study provided the sensitivity required for determination of the two drugs in the collected samples. The findings showed that results were within permitted ranges with minimal environmental impact.

A Novel Approach to Quantifying the Failure Modes of Concrete-Epoxy Interface

The failure or debonding of CEIs (Concrete-Epoxy Interfaces) in Fiber-Reinforced Polymer concrete (FRP) systems occurs in one or a combination of three modes: CC (Cohesive failure in Concrete), CE (Cohesive failure in Epoxy), and IF (Interfacial Failure). These failure modes are usually identified, and their relationships are established by human intuition, which is prone to subjectivity. This study proposes a novel method based on image processing techniques to analyze CEI fracture surfaces and evaluate their failure modes. The failure modes of CEI fracture surfaces of specimens from a 3PB (Three-Point Bending) experiment were assessed using an HVS, CIE L*a*b*, YC_bC_r, or RGB color space image segmentation-based image processing technique on the preprocessed images of the CEI failure sides. A manual approach was adopted to validate the accuracy of the proposed method. Comparing the failure mode (CE) obtained using the manual and the proposed methodology, an RMSE (Root Means Square Error) of 0.19, 0.10, 0.23, and 0.26 was obtained for HVS, CIE L*a*b*, YC_bC_r, or RGB color space, respectively. The epoxy area selected with CIE L*a*b* color space produced the most accurate evaluation of the failure modes. This study provides an accurate method of quantifying the failure modes of CEI fracture surfaces. The methodology proposed in this study is recommended for forensic investigations to understand better the possible causes of failure in externally bounded fiber-reinforced polymers.

Influence of location, season and time of day on the spectral composition of ambient light: Investigation for application in myopia

PURPOSE

Given the possible role of spectral composition of light and myopia, this study aimed at investigating the variation in the spectral composition of ambient light in different (a) outdoor/indoor locations, (b) time of a day and (c) seasons.

METHODS

The spectral power distribution (SPD), categorised into short (380-500 nm), middle (505-565 nm) and long wavelengths (625-780 nm), was recorded using a handheld spectrometer at three outdoor locations ('open playground', 'under shade of tree' and 'canopy') and three indoor locations ('room with multiple windows', 'closed room' and 'closed corridor'). Readings were taken at five different time points (3-h intervals between 6:30 and 18:00 hours) on two days, each during the summer and monsoon seasons.

RESULTS

The overall median SPD (IQR [25th-75th percentile] W/nm/m² ) across the three outdoor locations (0.11 [0.09, 0.12]) was 157 times higher than that of the indoor locations (0.0007 [0.0001, 0.001]). Considerable locational, diurnal and seasonal variation was observed in the distribution of the median SPD value, with the highest value being recorded in the 'open playground' (0.27 [0.21, 0.28]) followed by 'under shade of tree' (0.083 [0.074, 0.09]), 'canopy' (0.014 [0.012, 0.015]) and 'room with multiple windows' (0.023 [0.015, 0.028]). The relative percentage composition of short, middle and long wavelengths was similar in both the outdoor and indoor locations, with the proportion of middle wavelengths significantly higher (p < 0.01) than short and long wavelengths in all the locations, except 'canopy'.

CONCLUSION

Irrespective of variation in SPD values with location, time, day and season, outdoor locations always exhibited significantly higher spectral power than indoor locations. The relative percentage composition of short, middle and long wavelengths of light was similar across all locations. These findings establish a foundation for future research to understand the relationship between spectral power and the development of myopia.

Colorimetric Determination of Glucose in Sweat Using an Alginate-Based Biosystem

Glucose is an analyte of great importance, both in the clinical and sports fields. Since blood is the gold standard biofluid used for the analytical determination of glucose, there is high interest in finding alternative non-invasive biofluids, such as sweat, for its determination. In this research, we present an alginate-based bead-like biosystem integrated with an enzymatic assay for the determination of glucose in sweat. The system was calibrated and verified in artificial sweat, and a linear calibration range was obtained for glucose of 10-1000 µM. The colorimetric determination was investigated, and the analysis was carried out both in the black and white and in the Red:Green:Blue color code. A limit of detection and quantification of 3.8 µM and 12.7 µM, respectively, were obtained for glucose determination. The biosystem was also applied with real sweat, using a prototype of a microfluidic device platform as a proof of concept. This research demonstrated the potential of alginate hydrogels as scaffolds for the fabrication of biosystems and their possible integration in microfluidic devices. These results are intended to bring awareness of sweat as a complementary tool for standard analytical diagnosis.

Portable Smartphone Platform Based on Aggregation-Induced Enhanced Emission Carbon Dots for Ratiometric Quantitative Sensing of Fluoride Ions

The development of an instrument-free, on-site, real-time, sensitive, and visualized fluoride-ion (F^-) content rapid detection strategy is crucial to ensuring the health of the population. Smart microdevices that are portable, directly read, and easy to operate have recently attracted much attention. Herein, a ratiometric fluorescent probe (AA-CDs@[Ru(bpy)₃]²⁺)-based smartphone sensing platform was developed for the detection of F^-. The red fluorescent ruthenium bipyridine [Ru(bpy)₃]²⁺ molecule was chosen as the reference signal, and the carbon dots (AA-CDs) with Al³⁺ aggregation-induced enhanced emission (AIE) were designed as the response signal. The ratiometric probe fluorescence changed continuously from red to cyan in response to different concentrations of F^-, and the red-green-blue (RGB) channel values of the fluorescence image were extracted through the smartphone color recognition application (APP). There was a linear relationship between the blue-red (B/R) ratio and the F^- concentration, with a limit of detection (LOD) of 1.53 μM, far below the allowable content of F^- in drinking water prescribed by the World Health Organization. The F^- content was rapidly detected on-site with satisfactory repeatability and relative standard deviation using several water and toothpaste samples as the real sample. The platform features low cost, portability, easy operation, and good stability, selectivity, and repeatability, which provides a powerful tool for the visual quantitative detection of smartphone-based microsensing platforms possibly in the fields of environmental protection, diagnosis, and food safety assessment.

Improving the reliability of smartphone-based urine colorimetry using a colour card calibration method

Objective

Urine colorimetry using a digital image-based colorimetry is potentially an accessible hydration assessment method. This study evaluated the agreement between urine colorimetry values measured with different smartphone brands under various lighting conditions in patients with dengue fever.

Methods

The urine samples were photographed in a customized photo box, under five simulated lighting conditions, using five smartphones. These images were analyzed using Adobe Photoshop to obtain urine Red, Green and Blue (RGB) values with and without colour correction. A commercially available colour calibration card was used for colour correction. Using intraclass correlation coefficient (ICC), inter-phone and intra-phone agreements of urine RGB values were analyzed.

Results

Without colour correction, the various smartphones produced the highest agreement for Blue and Green values under the 'daylight' lighting condition. With colour correction, ICC values showed 'exceptional' inter-phone and intra-phone agreement for the Blue and Green values (ICC > 0.9). Red values showed 'poor' (ICC < 0.5) agreement with and without colour correction in all lighting conditions. Out of the five phones compared in this study, Phone 4 produced the lowest intra-phone agreement.

Conclusions

Colour calibration using photo colour cards improved the reliability of smartphone-based urine colorimetry, making this a promising point-of-care hydration assessment tool using the ubiquitous smartphone.

Accuracy of smartphone camera urine photo colorimetry as indicators of dehydration

Objective

Direct urine color assessment has been shown to correlate with hydration status. However, this method is subject to inter- and intra-observer variability. Digital image colorimetry provides a more objective method. This study evaluated the diagnostic accuracy of urine photo colorimetry using different smartphones under different lighting conditions, and determined the optimal cut-off value to predict clinical dehydration.

Methods

The urine samples were photographed in a customized photo box, under five simulated lighting conditions, using five smartphones. The images were analyzed using Adobe Photoshop to obtain Red, Green, and Blue (RGB) values. The correlation between RGB values and urine laboratory parameters were determined. The optimal cut-off value to predict dehydration was determined using area under the receiver operating characteristic curve.

Results

A total of 56 patients were included in the data analysis. Images captured using five different smartphones under five lighting conditions produced a dataset of 1400 images. The study found a statistically significant correlation between Blue and Green values with urine osmolality, sodium, urine specific gravity, protein, and ketones. The diagnostic accuracy of the Blue value for predicting dehydration were "good" to "excellent" across all phones under all lighting conditions with sensitivity >90% at cut-off Blue value of 170.

Conclusions

Smartphone-based urine colorimetry is a highly sensitive tool in predicting dehydration.

A Sol-gel Membrane Utilized Cellulose Paper Doped with α-furil Dioxime for Colorimetric Determination of Nickel

A simple and sensitive colorimetric sensor for nickel(II) ions has been successfully prepared by immobilizing α-furil dioxime reagent in the sol-gel matrix with a solid supporting filter paper medium. The sensor was developed using tetraethyl orthosilicate (TEOS) precursors with 4 days aging time, the mole ratio of water: precursor was 4:1, and reagent concentration at 0.10%. The sensor was quantified by utilizing the Red (R), Green (G), and Blue (B) values ​​of the colors that were successfully displayed after the detection process. The RGB value is confirmed by the Euclidean Distance (ED) equation to determine the optimum conditions. There was no observed degree of leaching in plain sight, and the result of leaching investigation by the double dyeing method did not show any significant change. The linear range was ​​0.10 to 2.8 ppm with an R² of 0.9964. The values of LOD and LOQ were 0.1 ppm and 0.4 ppm, respectively. In addition, the sensor was free from interfering species and had a percent recovery around 90 to 110%.

Easy Nitrite Analysis of Processed Meat with Colorimetric Polymer Sensors and a Smartphone App

We have developed an in situ methodology for determining nitrite concentration in processed meats that can also be used by unskilled personnel. It is based on a colorimetric film-shaped sensory polymer that changes its color upon contacting the meat and a mobile app that automatically calculates the manufacturing and residual nitrite concentration by only taking digital photographs of sensory films and analyzing digital color parameters. The film-shaped polymer sensor detects nitrite anions by an azo-coupling reaction, since they activate this reaction between two of the four monomers that the copolymer is based on. The sensory polymer is complemented with an app, which analyzes the color in two different digital color spaces (RGB and HSV) and performs a set of 32 data fittings representing the concentration of nitrite versus eight different variables, finally providing the nitrite concentration of the test samples using the best fitting curve. The calculated concentration of nitrite correlates with a validated method (ISO 2918: 1975) usually used to determine nitrite, and no statistically significant difference between these methods and our proposed one has been found in our study (26 meat samples, 8 prepared, and 18 commercial). Our method represents a great advance in terms of analysis time, simplicity, and orientation to use by average citizens.

Evaluation of important phenotypic parameters of tea plantations using multi-source remote sensing data

Tea height, leaf area index, canopy water content, leaf chlorophyll, and nitrogen concentrations are important phenotypic parameters to reflect the status of tea growth and guide the management of tea plantation. UAV multi-source remote sensing is an emerging technology, which can obtain more abundant multi-source information and enhance dynamic monitoring ability of crops. To monitor the phenotypic parameters of tea canopy more efficiently, we first deploy UAVs equipped with multispectral, thermal infrared, RGB, LiDAR, and tilt photography sensors to acquire phenotypic remote sensing data of tea canopy, and then, we utilize four machine learning algorithms to model the single-source and multi-source data, respectively. The results show that, on the one hand, using multi-source data sets to evaluate H, LAI, W, and LCC can greatly improve the accuracy and robustness of the model. LiDAR + TC data sets are suggested for assessing H, and the SVM model delivers the best estimation (Rp² = 0.82 and RMSEP = 0.078). LiDAR + TC + MS data sets are suggested for LAI assessment, and the SVM model delivers the best estimation (Rp² = 0.90 and RMSEP = 0.40). RGB + TM data sets are recommended for evaluating W, and the SVM model delivers the best estimation (Rp² = 0.62 and RMSEP = 1.80). The MS +RGB data set is suggested for studying LCC, and the RF model offers the best estimation (Rp² = 0.87 and RMSEP = 1.80). On the other hand, using single-source data sets to evaluate LNC can greatly improve the accuracy and robustness of the model. MS data set is suggested for assessing LNC, and the RF model delivers the best estimation (Rp² = 0.65 and RMSEP = 0.85). The work revealed an effective technique for obtaining high-throughput tea crown phenotypic information and the best model for the joint analysis of diverse phenotypes, and it has significant importance as a guiding principle for the future use of artificial intelligence in the management of tea plantations.

Predictive System Implementation to Improve the Accuracy of Urine Self-Diagnosis with Smartphones: Application of a Confusion Matrix-Based Learning Model through RGB Semiquantitative Analysis

Urinalysis, an elementary chemical reaction-based method for analyzing color conversion factors, facilitates examination of pathological conditions in the human body. Recently, considerable urinalysis-centered research has been conducted on the analysis of urine dipstick colors using smartphone cameras; however, such methods have a drawback: the problem of reproducibility of accuracy through quantitative analysis. In this study, to solve this problem, the function values for each concentration of a range of analysis factors were implemented in an algorithm through urine dipstick RGB semi-quantitative color analysis to enable real-time results. Herein, pH, glucose, ketones, hemoglobin, bilirubin, protein (albumin), and nitrites were selected as analysis factors, and the accuracy levels of the existing equipment and the test application were compared and evaluated using artificial urine. In the semi-quantitative analysis, the red (R), green (G), and blue (B) characteristic values were analyzed by extracting the RGB characteristic values of the analysis factors for each concentration of artificial urine and obtaining linear function values. In addition, to improve the reproducibility of detection accuracy, the measurement value of the existing test equipment was set to an absolute value; using a machine-learning technique, the confusion matrix, we attempted to stabilize test results that vary with environment.

Microplastic detection and identification by Nile red staining: Towards a semi-automated, cost- and time-effective technique

Microplastic pollution is an issue of concern due to the accumulation rates in the marine environment combined with the limited knowledge about their abundance, distribution and associated environmental impacts. However, surveying and monitoring microplastics in the environment can be time consuming and costly. The development of cost- and time-effective methods is imperative to overcome some of the current critical bottlenecks in microplastic detection and identification, and to advance microplastics research. Here, an innovative approach for microplastic analysis is presented that combines the advantages of high-throughput screening with those of automation. The proposed approach used Red Green Blue (RGB) data extracted from photos of Nile red-fluorescently stained microplastics (50-1200 μm) to train and validate a 'Plastic Detection Model' (PDM) and a 'Polymer Identification Model' (PIM). These two supervised machine learning models predicted with high accuracy the plastic or natural origin of particles (95.8%), and the polymer types of the microplastics (88.1%). The applicability of the PDM and the PIM was demonstrated by successfully using the models to detect (92.7%) and identify (80%) plastic particles in spiked environmental samples that underwent laboratorial processing. The classification models represent a semi-automated, high-throughput and reproducible method to characterize microplastics in a straightforward, cost- and time-effective yet reliable way.

Development of chipscale InGaN RGB displays using strain-relaxed nanosphere-defined nanopillars

Chip-scale red, green and blue (RGB) light emission on an InGaN/GaN multi-quantum well wafer adopting a top-down fabrication approach is demonstrated in this study, facilitated by shadow-masked nanosphere lithography for precise site-controlled nano-patterning. Exploiting the strain relaxation mechanism by fabricating arrays of nanosphere-defined nanopillars of two different dimensions utilizing a sequential shadow-masked nanosphere coating approach into the blue and green light-emitting pixel regions on a red-light emitting InGaN/GaN wafer, RGB light emission from a monolithic chip is demonstrated. The micro-sized RGB light-emitting pixels emit at 645 nm-680 nm, 510 nm-521 nm and 475 nm-498 nm respectively, achieving a maximum color gamut of 60% NTSC and 72% sRGB. Dimensional fluctuations of the nanopillars of 73% and 71% for the green and blue light-emitting pixels, respectively, are estimated from scanning electron microscope images of the fabricated device, corresponding to fluctuations in spectral blue-shifts of 5.4 nm and 21.2 nm as estimated by strain-coupledk·pSchrödinger calculations, consistent with observations from micro-photoluminescence (μ-PL) mapping which shows deviations of emission wavelengths for the RGB light-emitting pixels to be 8.9 nm, 14.9 nm and 23.7 nm, respectively. The RGB pixels are also configured in a matrix-addressable configuration to form an RGB microdisplay, demonstrating the feasibility of the approach towards chip-scale color displays.

On the Acquisition of High-Quality Digital Images and Extraction of Effective Color Information for Soil Water Content Testing

Soil water content (SWC) is a critical indicator for engineering construction, crop production, and the hydrologic cycle. The rapid and accurate assessment of SWC is of great importance. At present, digital images are becoming increasingly popular in environmental monitoring and soil property analysis owing to the advantages of non-destructiveness, cheapness, and high-efficiency. However, the capture of high-quality digital image and effective color information acquisition is challenging. For this reason, a photographic platform with an integrated experimental structure configuration was designed to yield high-quality soil images. The detrimental parameters of the platform including type and intensity of the light source and the camera shooting angle were determined after systematic exploration. A new method based on Gaussian fitting gray histogram for extracting RGB image feature parameters was proposed and validated. The correlation between 21 characteristic parameters of five color spaces (RGB, HLS, CIEXYZ, CIELAB, and CIELUV) and SWC was investigated. The model for the relationship between characteristic parameters and SWC was constructed by using least squares regression (LSR), stepwise regression (STR), and partial least squares regression (PLSR). Findings showed that the camera platform equipped with 45° illumination D65 light source, 90° shooting angle, 1900~2500 lx surface illumination, and operating at ambient temperature difference of 5 °C could produce highly reproducible and stable soil color information. The effects of image scale had a great influence on color feature extraction. The entire area of soil image, i.e., 3,000,000 pixels, was chosen in conjunction with a new method for obtaining color features, which is beneficial to eliminate the interference of uneven lightness and micro-topography of soil samples. For the five color spaces and related 21 characteristic parameters, RGB and CIEXYZ spaces and characteristic parameter of lightness both exhibited the strongest correlation with SWC. The PLSR model based on soil specimen images ID had an excellent predictive accuracy and the best stability (R² = 0.999, RMSE = 0.236). This study showed the potential of the application of color information of digital images to predict SWC in agriculture and geotechnical engineering.

Theoretical Approach for the Luminescent Properties of Ir(III) Complexes to Produce Red-Green-Blue LEC Devices

With an appropriate mixture of cyclometalating and ancillary ligands, based on simple structures (commercial or easily synthesized), it has been possible to design a family of eight new Ir(III) complexes (1A, 1B, 2B, 2C, 3B, 3C, 3D and 3E) useful as luminescent materials in LEC devices. These complexes involved the use of phenylpyridines or fluorophenylpyridines as cyclometalating ligands and bipyridine or phenanthroline-type structures as ancillary ligands. The emitting properties have been evaluated from a theoretical approach through Density Functional Theory and Time-Dependent Density Functional Theory calculations, determining geometric parameters, frontier orbital energies, absorption and emission energies, injection and transport parameters of holes and electrons, and parameters associated with the radiative and non-radiative decays. With these complexes it was possible to obtain a wide range of emission colours, from deep red to blue (701-440 nm). Considering all the calculated parameters between all the complexes, it was identified that 1B was the best red, 2B was the best green, and 3D was the best blue emitter. Thus, with the mixture of these complexes, a dual host-guest system with 3D-1B and an RGB (red-green-blue) system with 3D-2B-1B are proposed, to produce white LECs.

Smartphone-based portable fluorescence sensor with gold nanoparticle mediation for selective detection of nitrite ions

A simple, portable device for the detection of NO₂^- via a fluorescence method was developed. The proposed device consisted of a dark box containing a blue LED as a low-power excitation light source and a smartphone with a mobile application for RGB analysis as a light detector. Detection was mediated by using synthesized cetyltrimethylammonium bromide-stabilized gold nanoparticles (CTAB-AuNPs). The CTAB-AuNPs were etched with NO₂^- to yield Au³⁺, which catalyzes the oxidation of o-phenylenediamine (OPD) in the presence of H₂O₂ to generate 2,3-diaminophenazine (DAP). Triton X-100 (TX-100) micelles were introduced to improve the DAP fluorescence emission. The fluorescence intensity of DAP was recorded by the smartphone in terms of RGB intensity, which was correlated with the NO₂^- concentration. This method provided a wide linear working concentration range (0.5-100 μM), a limit of detection of 0.17 μM and excellent selectivity for NO₂^- over other anions.

High-Throughput Screening to Examine the Dynamic of Stay-Green by an Imaging System

The development of RGB (red, green, blue) sensors has opened the way for plant phenotyping. This is relevant because plant phenotyping allows us to visualize the product of the interaction between the plant ontogeny, anatomy, physiology, and biochemistry. Better yet, this can be achieved at any stage of plant development, i.e., from seedling to maturity. Here, we describe the use of phenotyping, based on the stay-green trait, of common bean (Phaseolus vulgaris L.) plant, as a model, stressed by water deficit, to elucidate the result of that interaction. Description is based on interpretation of RGB digital images acquired using a phenomic platform and a specific software. These images allow us to obtain a data group related to the color parameters that quantify the changes and alterations in each plant growth and development.

A Combined Immunofluorescence and Fluorescent Viability Cocktail Staining Procedure for Rapid Microscopic Detection and Enumeration of Live Legionella pneumophila

This report describes a combined immunofluorescence and fluorescence viability stain applied as one staining solution for rapid detection of live Legionella pneumophila in mixed bacterial populations. Instead of sequential viability staining with the Invitrogen BacLight LIVE/DEAD staining kit followed by antibody-Alexa Fluor (AF) 647 conjugate staining to identify live L. pneumophila, a combined single cocktail solution staining protocol was developed to simplify and accelerate the time to detection of viable L. pneumophila serogroup-1 (SG-1) in mixed species populations on a filter membrane. The stain cocktail will aid in accelerating fluorescence microscopic analysis of cooling tower, air conditioner and water fountain or other liquid samples for the presence of L. pneumophila and its viability status. Visibly red stained cells were identified as dead non-L. pneumophila SG-1 cells, while green fluorescing cells represented viable non-L. pneumophila SG-1 cells. Due to also staining red with antibody-AF 647, L. pneumophila SG-1 cells were pseudocolorized as blue to distinguish them from other dead cells. Fluorescence color emission mixing from the viability dyes (SYTO 9 and propidium iodide) with antibody-AF 647 stained L. pneumophila led to other fluorescent colors. For example, green plus pseudocolorized blue AF 647-antibody- labeled cells were identified as live cyan-colored L. pneumophila SG-1 cells. Magenta-colored cells resulted from dead L. pneumophila cells that combined red propidium iodide with blue pseudocolorized AF 647-antibody emissions. Analysis of measured RGB (red, green, blue) color values in microscopic images of mixed bacterial populations suggests the possibility of facile automated discrimination of subpopulations of live and dead L. pneumophila and non-L. pneumophila species by computers in 3-dimensional RGB color space after staining in the combined cocktail which will save time for more rapid microscopic detection of potential sources of Legionnaire's disease.

Editing Light Emission with Stable Crystalline Covalent Organic Frameworks via Wall Surface Perturbation

The ordered π skeletons of covalent organic frameworks make them viable light-emitting materials but their limited tunability has precluded further implementation. Here we report the synthesis of hydrazone-linked frameworks which are stable in water, acid, and base, and demonstrate their utility as a platform for light emission. The polygonal backbone is designed to be luminescent and partially π conjugated while the pore wall is docked with single atom or unit to induce resonance, hyperconjugation, and tautomerization effects. These effects can be transmitted to the backbone, so that the framework can emit three primary colors of light. The wall can be perturbated with multiple surface sites, rendering the material able to edit diverse emission colors in a predesignable and digital way. The systems show high activity, stability, tunability, and sensibility: a set of features attractive for light-emitting and sensing applications.

Direct minimally invasive enzymatic determination of tyramine in cheese using digital imaging

An enzymatic method for the direct (without pretreatment) minimally invasive tyramine determination in cheese is proposed. Colorimetric test strips containing tyramine oxidase (TAO), peroxidase and 3,3',5,5'-tetramethylbenzidine (Q-TAO), allow tyramine determination through the RGB chromatic coordinates of the observed blue colour (LOD = 2.6·10^-6 M, LOQ = 8.7·10^-6 M, RSD% (n = 5; 1.8·10^-4 M) = 3.2%). The strips are inserted in the sample for 2 min and then the RGB coordinates are measured using a smartphone. Previously, these Q-TAO strips have been also optimized for tyramine determination in cheese extract. To do that, a spectrophotometric method in solution for tyramine determination in cheese extracts has been developed, which included an in-depth study of the indicating reaction; this study has allowed to gain new information about the spectroscopic properties of different TMB species and, which it is more important, to detect cross-reactions between TAO and TMB species. A mathematical model has also been developed which relate the RGB signals obtained with the tyramine concentrations, the instrumental characteristics of the smartphone and the spectroscopic properties of the absorbing product of the enzymatic reaction.

An Evaluation of the Factors Affecting 'Poacher' Detection with Drones and the Efficacy of Machine-Learning for Detection

Drones are being increasingly used in conservation to tackle the illegal poaching of animals. An important aspect of using drones for this purpose is establishing the technological and the environmental factors that increase the chances of success when detecting poachers. Recent studies focused on investigating these factors, and this research builds upon this as well as exploring the efficacy of machine-learning for automated detection. In an experimental setting with voluntary test subjects, various factors were tested for their effect on detection probability: camera type (visible spectrum, RGB, and thermal infrared, TIR), time of day, camera angle, canopy density, and walking/stationary test subjects. The drone footage was analysed both manually by volunteers and through automated detection software. A generalised linear model with a logit link function was used to statistically analyse the data for both types of analysis. The findings concluded that using a TIR camera improved detection probability, particularly at dawn and with a 90° camera angle. An oblique angle was more effective during RGB flights, and walking/stationary test subjects did not influence detection with both cameras. Probability of detection decreased with increasing vegetation cover. Machine-learning software had a successful detection probability of 0.558, however, it produced nearly five times more false positives than manual analysis. Manual analysis, however, produced 2.5 times more false negatives than automated detection. Despite manual analysis producing more true positive detections than automated detection in this study, the automated software gives promising, successful results, and the advantages of automated methods over manual analysis make it a promising tool with the potential to be successfully incorporated into anti-poaching strategies.

Smartphone-based technique for the determination of a titration equivalence point from an RGB linear-segment curve with an example application to miniaturized titration of sodium chloride injections

A smartphone-based technique for determining the titration equivalence point from a linear-segment curve was developed for the first time. In this method, a titrant in an increasing microliter-volume was added to a set of sample aliquots containing an indicator covering both sides of the equivalence point. The solutions were subsequently photographed in one shot, in a dark box using a smartphone camera and an illuminating screen of a tablet or light emitting diode lamps arranged below a white acrylic sheet as a light source. After the colors of the solutions were delineated to Red, Green, and Blue (RGB) values, 1/log G was used to construct a plot in which the equivalence point was located at the intersection of the two lines in the region before and after the equivalence point. The technique was successfully applied to the miniaturized titration of sodium chloride injections, showing the good linear relationship of equivalence points to the sodium chloride concentration in the range of 0.4163-0.9675% w/v (R² of 0.9998). The assay was accurate (% recovery of 98.92-100.52), precise (% relative standard deviation ≤ 1.20), and unaffected by the use of different types of microplates, smartphones, and RGB analysis tools. Additionally, it required no expensive nor complicated equipment and offered the possibility of performing analysis on a single smartphone device when it was used with a mobile application developed to aid data processing and immediate production of reports of analytical results.

Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild

Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.

Fully Automated DCNN-Based Thermal Images Annotation Using Neural Network Pretrained on RGB Data

One of the biggest challenges of training deep neural network is the need for massive data annotation. To train the neural network for object detection, millions of annotated training images are required. However, currently, there are no large-scale thermal image datasets that could be used to train the state of the art neural networks, while voluminous RGB image datasets are available. This paper presents a method that allows to create hundreds of thousands of annotated thermal images using the RGB pre-trained object detector. A dataset created in this way can be used to train object detectors with improved performance. The main gain of this work is the novel method for fully automatic thermal image labeling. The proposed system uses the RGB camera, thermal camera, 3D LiDAR, and the pre-trained neural network that detects objects in the RGB domain. Using this setup, it is possible to run the fully automated process that annotates the thermal images and creates the automatically annotated thermal training dataset. As the result, we created a dataset containing hundreds of thousands of annotated objects. This approach allows to train deep learning models with similar performance as the common human-annotation-based methods do. This paper also proposes several improvements to fine-tune the results with minimal human intervention. Finally, the evaluation of the proposed solution shows that the method gives significantly better results than training the neural network with standard small-scale hand-annotated thermal image datasets.

3D-printed and fully portable fluorescent-based platform for sulfide determination in waters combining vapor generation extraction and digital images treatment

The determination of sulfide anion in a variety of waters (e.g. wastewaters and natural waters) even at low concentration (i.e. in the μM range) is essential due to its high toxicity, corrosivity and unpleasant smelling proprieties. Despite several methodologies are dedicated to aqueous sulfide determination, most of them need sampling/transport steps - which is no adequate to sulfide due to its reactivity and instability - resulting in critical analytical bias. In this study, we present a fully modular and portable 3D-printed platform for in-situ aqueous sulfide determination. The analytical device is based on H₂S vapor generation from the sulfide sample solution by addition of H₃PO₄ followed by collection in a miniaturized cuvette (μCuvette) containing few microliters of Fluorescein Mercury Acetate (FMA), a fluorescent dye. The chemical reaction results in fluorescence quenching of the dye at 530 nm when excited at 470 nm. A light-emitted diode (LED) emitting at 470 nm and powered with 9 V-battery based circuitry was employed to provide stable excitation light source at 20 mA. Digital images from the light emitted by FMA were captured by a smartphone and the Green channel intensity was used as analytical signal. Under optimized conditions, a linear relation (r² > 0.99) from 0.1 to 5 μM of sulfide was obtained using 10 mL of standard/sample solution. The portable platform was applied to the in-situ monitoring of sulfide in tap water and river water with no loss of analyte, no need for external power supplies or powered pumps. and the analysis results were obtained in 20 min. The proposed device shows advantages in terms of high degree of portability, low-power consumption, easiness to use, minimal use of reagents yet enabling on-site determination of sulfide with high sensitivity. By using the vapor generation approach combined with the modular building blocks concept presented herein for the first time, we anticipate the development of a tailored "plug-and-play" platform enabling the multiplexed determination of volatile substances using absorbance, reflectance or fluorescence measurements with smartphones.

Inner Product of RGB Unit Vectors for Simple and Versatile Detection of Color Transition

We propose a novel concept for detecting color transition by the inner product (IP) of RGB unit vectors. A digital microscope-based detector and a Visual Basic program were developed in-house. The concept is applied to indicator-based flow titration. The IP is 1 or < 1 if the vector's direction is the same or different, respectively. The IP's change can be used as a criterion for the indicator's color transition. The present IP-based approach is simple, economical, and versatile because it is applicable to any color transition without selecting an analytical wavelength.

Light Drones for Basic In-Field Phenotyping and Precision Farming Applications: RGB Tools Based on Image Analysis

Plant phenotyping has garnered major attention in recent years, leading to developing new strategies to measure and assess plant traits of interest. For data acquisition of large fields, devices and sensors are required that deliver detailed and reproducible temporal and spatial information on the cultivated crop. This work proposes the potential use of low-cost light drones for in-field phenotyping applications on cereal crops. The proposed method allows to obtain precise measurements of color and height of the plants for the individual plots. The method is based on a color calibration algorithm (TPS-3D interpolating function) and a 3D ortho image reconstruction. The method has been applied on an experimental field with durum and soft wheat parcels obtaining information on real color (with an error lower than 12/256) and height for each single plot.

Near infrared spectroscopy and smartphone-based imaging as fast alternatives for the evaluation of the bioactive potential of freeze-dried açai

The development of green analytical techniques for food industry quality control has become an important issue in the context of the fourth industrial revolution. In this sense, near infrared spectroscopy (NIR) and smartphone-based imaging (SBI) were applied to evaluate the bioactive potential of freeze-dried açai pulps. For this purpose, reference results of ninety-six samples were obtained by determining total anthocyanins (TAC), polyphenol content (TPC), and antioxidant capacity (DPPH, ORAC and TEAC) by traditional methods and correlated to NIR spectra and SBI to build predictive models based on partial square least (PLS) regression. In summary, the NIR-PLS models showed better performance for predicting the TAC, TPC and antioxidant capacity of studied samples; considering the parameters of merit, such as coefficient of determination (0.8) and residual prediction deviation (RPD) (2.2) compared to the SBI-PLS models (0.7 and lower 1.5, respectively). The better performance of NIR-PLS could be potentially justified by a higher sensitivity of the NIR equipment than the smartphone images. In conclusion, these results show that the proposed alternative methods are promising tools for the future context of the 4.0 food industry.

RAP3DF - One shoot 3D face dataset

Develop researches in the 3D biometrics field requires a large set of images, whether for training the algorithms or during the recognition test. Several datasets can be found in the literature. In an analysis of these datasets it was observed that a single dataset does not have the types of infrared images, visible and three-dimensional light, for the same sample. Given this context, the present work conceived this 3D facial dataset, with its respective visible light image and infrared spectrum, providing the entire image acquisition process from the Kinect One device. The work consists of 267 samples from 64 volunteers, where each volunteer has a frontal facial image and 3 images in arbitrary positions.

Spectral Reflectance Reconstruction Using Fuzzy Logic System Training: Color Science Application

In this work, we address the problem of spectral reflectance recovery from both CIEXYZ and RGB values by means of a machine learning approach within the fuzzy logic framework, which constitutes the first application of fuzzy logic in these tasks. We train a fuzzy logic inference system using the Macbeth ColorChecker DC and we test its performance with a 130 sample target set made out of Artist’s paints. As a result, we obtain a fuzzy logic inference system (FIS) that performs quite accurately. We have studied different parameter settings within the training to achieve a meaningful overfitting-free system. We compare the system performance against previous successful methods and we observe that both spectrally and colorimetrically our approach substantially outperforms these classical methods. In addition, from the FIS trained we extract the fuzzy rules that the system has learned, which provide insightful information about how the RGB/XYZ inputs are related to the outputs. That is to say that, once the system is trained, we extract the codified knowledge used to relate inputs and outputs. Thus, we are able to assign a physical and/or conceptual meaning to its performance that allows not only to understand the procedure applied by the system but also to acquire insight that in turn might lead to further improvements. In particular, we find that both trained systems use four reference spectral curves, with some similarities, that are combined in a non-linear way to predict spectral curves for other inputs. Notice that the possibility of being able to understand the method applied in the trained system is an interesting difference with respect to other ’black box’ machine learning approaches such as the currently fashionable convolutional neural networks in which the downside is the impossibility to understand their ways of procedure. Another contribution of this work is to serve as an example of how, through the construction of a FIS, some knowledge relating inputs and outputs in ground truth datasets can be extracted so that an analogous strategy could be followed for other problems in color and spectral science.