Spectral Sensors Research Articles

Spectral data driven machine learning classification models for real time leaf spot disease detection in brinjal crops

This study presents the development and evaluation of machine learning models for detecting leaf spot disease in brinjal crops using spectral sensor data. The spectral reflectance of diseased and healthy tissues was recorded across nine wavelength bands (F1: 415 nm, F2: 445 nm, F3: 480 nm, F4: 515 nm, F5: 555 nm, F6: 590 nm, F7: 630 nm, F8: 680 nm, and F9: NIR-750 nm). The data revealed distinct spectral signatures, particularly between F5 (555 nm) and F9 (NIR), where diseased tissues consistently showed lower reflectance compared to healthy tissues. Two machine learning algorithms, Decision Tree (DT) and Support Vector Machine (SVM), were employed to classify the spectral data. The DT model achieved a maximum testing accuracy of 88.2 %, with a Gini index and a depth of 4 as optimal hyperparameters. The confusion matrix indicated that the DT model correctly identified 883 diseased instances and 667 healthy cases, while misclassifying 213 healthy tissues as diseased and 25 diseased tissues as healthy. The SVM model, configured with a cost parameter of 10.0 and a tolerance of 0.01, outperformed the DT model, achieving a testing accuracy of 92.4 %. The SVM model correctly classified 99.3 % of diseased instances and 94.1 % of healthy cases. The results demonstrate the potential of spectral sensor data combined with ML algorithms for precise disease detection, facilitating targeted pesticide application, and reducing input costs. The high accuracy of the SVM model underscores its utility in agricultural disease management, enabling early intervention and enhancing crop health monitoring. Future research may explore integrating multiple sensors and advanced feature extraction methods to further improve the efficiency and accuracy of these systems.

Nondestructive intelligent detection of total viable count in pork based on miniaturized spectral sensor

Changes in the freshness of pork due to microbial action during complex transportation and storage indicate an urgent need for in-situ, real-time monitoring techniques for chemical spoilage of meat. This study reported the use of a portable detection device based on a miniaturized visible/near-infrared spectrometer, combined with data noise reduction and machine learning methods, to predict the total viable count (TVC) in pork samples. A rapid detection device for pork TVC was designed based on the miniaturized spectrometer; a spectral preprocessing method based on the resolution of the spectrometer was proposed; the effects of different preprocessing methods on the full-wavelength modeling effect were compared; and four different feature wavelength extraction algorithms were utilized for the feature wavelengths of pork TVC. The modeling effects of different simplified models were compared. The results showed that resolution interval correction combined with standard normal variation was the most effective in full-wavelength modeling, with correlation coefficients of prediction set (RP), root mean square errors in prediction set (RMSEP), and relative percent deviation (RPD) of 0.918, 0.464 (lg CFU/g), and 2.508, respectively; interval random frog − partial least squares regression (iRF-PLSR) had the best predictive ability among all simplified models, the number of wavelengths used in the simplified model was reduced by 85.45% compared with the full-wavelength model. In contrast, the model performance was improved with RP, RMSEP, and RPD of 0.948, 0.392 (lg CFU/g) and 2.970, respectively. The combination of a rational spectral acquisition setup and a data processing methodology, the miniaturized spectrometer showed competitive results with the complex detection system in predicting meat TVC.

A Child-Friendly Wearable Device for Quantifying Environmental Risk Factors for Myopia.

In the past few decades, the prevalence of myopia, where the eye grows too long, has increased dramatically. The visual environment appears to be critical to regulating the eye growth. Thus, it is very important to determine the properties of the environment that put children at risk for myopia. Researchers have suggested that the intensity of illumination and range of distances to which a child's eyes are exposed are important, but this has not been confirmed. We designed, built, and tested an inexpensive, child-friendly, head-mounted device that can measure the intensity and spectral content of illumination approaching the eyes and can also measure the distances to which the central visual field of the eyes are exposed. The device is mounted on a child's bicycle helmet. It includes a camera that measures distances over a substantial range and a six-channel spectral sensor. The sensors are hosted by a light-weight, battery-powered microcomputer. We acquired pilot data from children while they were engaged in various indoor and outdoor activities. The device proved to be comfortable, easy, and safe to wear, and able to collect very useful data on the statistics of illumination and distances. The designed device is an ideal tool to be used in a population of young children, some of whom will later develop myopia and some of whom will not. Such data would be critical for determining the properties of the visual environment that put children at risk for becoming myopic.

A Versatile, Machine-Learning-Enhanced RF Spectral Sensor for Developing a Trunk Hydration Monitoring System in Smart Agriculture

This paper comprehensively explores the development of a standalone and compact microwave sensing system tailored for automated radio frequency (RF) scattered parameter acquisitions. Coupled with an emitting RF device (antenna, resonator, open waveguide), the system could be used for non-invasive monitoring of external matter or latent environmental variables. Central to this design is the integration of a NanoVNA and a Raspberry Pi Zero W platform, allowing easy recording of S-parameters (scattering parameters) in the range of the 50 kHz–4.4 GHz frequency band. Noteworthy features include dual recording modes, manual for on-demand acquisitions and automatic for scheduled data collection, powered seamlessly by a single battery source. Thanks to the flexibility of the system’s architecture, which embeds a Linux operating system, we can easily embed machine learning (ML) algorithms and predictive models for information detection. As a case study, the potential application of the integrated sensor system with an RF patch antenna is explored in the context of greenwood hydration detection within the field of smart agriculture. This innovative system enables non-invasive monitoring of wood hydration levels by analyzing scattering parameters (S-parameters). These S-parameters are then processed using ML techniques to automate the monitoring process, enabling real-time and predictive analysis of moisture levels.

Retraction Note: Application of system virtual simulation platform based on spectral sensors in home physical education curriculum

Retraction Note: Application of system virtual simulation platform based on spectral sensors in home physical education curriculum

Development of low-cost portable spectrometer equipped with 18-band spectral sensors using deep learning model for evaluating moisture content of rubber sheets

While the choice of spectrometer can vary depending on its intended use, the increased cost of high-performance spectrometers may not be justified in certain applications. Therefore, this research developed an affordable and portable device using 18-band spectral sensors incorporating a deep learning model for accurately determining the moisture content in rubber sheets. A set of 286 rubber sheets was randomly separated into two categories: 200 for model calibration and 86 for model validation. In the calibration process, the spectral data were calibrated using a one-dimensional convolutional neural network (1D-CNN) and then were compared with a recognized linear model using partial least squares regression (PLSR). The experiments revealed the exceptional performance of the 1D-CNN model in predicting the moisture content of rubber sheets, outperforming the PLSR model. The 1D-CNN model had a better prediction accuracy, with a coefficient of determination (R2) of 0.962, a root mean squared error of prediction (RMSEP) of 0.410 %, a prediction-to-deviation ratio (RPD) of 5.2, and an error range ratio (RER) of 18.0. A portable device was constructed by incorporating the 1D-CNN model into a 32-bit microcontroller, which was embedded within the measurement device. During testing of the instrument, the results indicated that its predictive performance did not differ significantly from that of the primary calibration model. Therefore, it could be concluded that the designed instrument was capable of accurately measuring the moisture content of rubber sheets and is suitable for field use due to its portability and cost-effectiveness.

Development and application of a low-cost and portable multi-channel spectral detection system for mutton adulteration

It is important to develop low-cost, fast and portable meat adulteration detection systems to ensure the meat authenticity and safety in complex market environments. A multi-channel spectral detection system for meat adulteration was developed in this study. The core hardware of the system mainly includes a designed spectral module and a Raspberry pi controller. The spectral module consists of three multi-channel spectral sensors and LED lamps with specific wavelengths, containing 18 channels covering a range of 410–940 nm. The software was developed based on PyQt5. After completing the construction of the system, the detection distance was discussed and determined to be 4 mm. Based on the spectral data collected by the developed system, the models for classifying pure mutton, pure pork, mutton flavour essence adulteration, colourant adulteration and adulterated mutton with pork were established and compared. Four intelligent optimisation algorithms were further used to improve the model performance. The results of the test set showed that the support vector classification (SVC) model optimised by a sparrow search algorithm (SSA) obtained the best classification performance, with an accuracy of 97.59% and a Kappa coefficient of 0.9696. After the SSA-SVC was incorporated into the sensor software, the system performance was evaluated using external validation samples. The overall accuracy of the system was 94.29%. The system took about 5.31 s to detect a sample, and the total weight of the system was 1.55 kg. Overall, the developed portable spectral system has considerable potential to rapidly and accurately discriminate adulterated mutton in the field.

Synchronising an IMX219 image sensor and AS7265x spectral sensor to make a novel low-cost spectral camera

A low-cost novel spectral camera able to be used for near infrared spectroscopy was made by using a Jetson Nano to synchronize a Sony IMX219 NOIR autofocus image sensor, an AMS AS7265x 18-channel spectral sensor and Osram SFH 4737 broadband infrared LED’s. Synchronizing an image sensor and spectral sensor augments a standard RGB image with light spectrum information; capturing the light distribution information normally lost in RGB image capture. Sutherland et al. [1] used this novel spectral camera to examine the dorsal surface of juvenile lobsters as a possible pre-moult detector. Having the image and spectrum in combination allowed the incomplete and unmineralized post-moult dorsal surface to be characterized with 86.7% accuracy for the first time. A proposed application for the spectral camera is to omit the local SFH 4737 light source and use the camera in daylight, effectively making a low-cost substitute hyperspectral snapshot camera. In this configuration the camera may have application for low-cost drone deployment for small scale agriculture.

The response of a sorghum sudangrass cover crop to residual nitrogen and its relationship with spectral sensors

AbstractA sorghum sudangrass (SSG) cover crop grown after a cash crop could take up residual nitrogen (N) before it is lost. As in‐field monitoring of SSG properties is laborious, predicting biomass and N concentrations with spectral sensors could be useful. At two sites in Live Oak, Florida, we evaluated the response of SSG to residual N from previous N fertilization and the performance of handheld and satellite sensors in estimating SSG properties. We quantified aboveground biomass, plant N, leaf greenness (NDVI), net potential N mineralization (PNM), and soil permanganate oxidizable carbon (POXC). Residual N did not affect SSG properties, PNM was highest at the highest N input rate in one site, and soil POXC was correlated with SSG properties (biomass and plant N). NDVI measured from a handheld sensor better predicted SSG properties than satellite imagery in these small plots, suggesting a greater potential to be a useful management tool.

Crude oil-water separation with the aid of carbon based materials

Carbon-based materials are commonly utilized in water filtration and purification due to their affordability and environmental friendliness. This study investigates the effectiveness of four different carbon-based materials: activated carbon (AC), graphene oxide (GO), reduced graphene oxide (rGO), and polyethylene (PE) in crude oil–water separation. To test the effectiveness of the separation, light transmission measurements were carried out with the aid of Arduino UNO using a red, green, and blue (RGB) light spectral sensor. The results revealed that the emulsions with AC was the most effective material in the separation, followed by rGO, and GO was the least effective. To explain the mechanism behind the separation performance, the carbon materials have been characterized by x-ray photoelectron spectroscopy (XPS) and Fourier Transform Infrared Spectroscopy (FTIR). The effectiveness of AC and rGO in the separation process was directly related to the quantity of surface oxides. The experimental results are perfectly agreed with published Density functional theory (DFT) calculations of HOMO–LUMO gap energies. AC shows the best performance and the smallest gap, which indicates that it requires less energy for electrons transition between the HOMO and LUMO. This phenomenon can be attributed to the affinity towards hydrogen in the hydrocarbon chains in crude oil.

Characterization and detailed mapping of C by spectral sensor for soils of the Western Plateau of São Paulo

Soil mineralogy and texture are directly related to soil carbon due to the physical properties of the clay surface. Traditional techniques for quantifying carbon in soil are time-consuming and expensive, making large-scale quantification for mapping unfeasible. The alternative is the use of soil sensors, such as diffuse reflectance spectroscopy (DRS), an economical, fast, and accurate technique for predicting carbon stocks. In this sense, this study aimed to (a) investigate the relationship of C with different soil mineralogical, chemical, and physical attributes for different geological and geomorphological compartments; (b) understand which spectral bands are most important for estimating C content; (c) estimate C content from diffuse reflectance spectroscopy using different mathematical techniques and indicate which one is the best for tropical soil conditions; and (d) map C contents in detail. The study area was the Western Plateau of São Paulo (WPSP), which covers approximately 13 million hectares (~ 48% of the State of São Paulo, Brazil). A total of 265 samples were collected in this area. The attributes clay, silt, sand, crystalline and non-crystalline iron, base saturation, soil density, total pore volume, total C, C stock, kaolinite/(kaolinite + gibbsite) and hematite/(hematite + goethite), hematite and goethite contents, and spectral curves were evaluated. The spectra were recorded at 0.5-nm intervals, with an integration time of 2.43 nm s−1 over the 350 to 2500-nm range (350–800 nm—visible—VIS and 801–2500 nm—near-infrared—NIR). The data were subjected to descriptive statistics, Spearman correlation, stepwise analysis, and cluster grouping for characterization purposes; partial least squares regression (PLSR) and random forest (RF) for estimation purposes; and geostatistics analysis for creation of spatial maps. Our results indicate that the highest C contents are associated with more clayey soils, oxidic mineralogy, higher total pore volume, and lower soil density in highly dissected basalt compartments. The random forest algorithm associated with the Vis–NIR spectral range is more efficient for estimating and mapping C contents. This suggests that integrating diffuse reflectance spectroscopy with machine learning techniques holds promise for shaping public policies related to land use, mitigating CO2 emissions, and facilitating the implementation of carbon credit policies in a rapid and economically efficient manner.

Tailored detection efficiency for linear variable filter-based sensors: applying simulation models of spectral characteristics in optical design

To accurately model the specific detection characteristics of spectral sensors based on linear variable filters (LVFs) within an optical design tool, it is essential to consider crucial position-variable spectral properties, such as peak transmittance, central wavelength, half width, or slope steepness. In this context, we propose a straightforward approach, integrating a dynamic link library (DLL) containing all position-dependent spectral properties of the LVF into a commercial optical design software. Exemplary investigations are conducted for an LVF with a detection range of 450–850 nm. For ease of use, the measured position-, wavelength-, and angle-dependent transmission properties of the LVF have been described through a simple yet highly accurate model system. Moreover, to highlight the essential value of this simulation for specific applications, an efficiency-enhancing spectral module is simulated, which is an LVF-mirror arrangement characterized by a multiple-reflected beam path. The introduced optical design tool demonstrates its particular strength by enabling the optimization of the highest detection efficiency for either the short- or long-wavelength range.

Spectral sensor‐based device for real‐time detection and severity estimation of groundnut bud necrosis virus in tomato

AbstractA machine learning‐based approach was utilized to develop a device for groundnut bud necrosis virus (GBNV) disease severity detection and estimation in tomato plants (Solanum lycopersicum L.). The study involved inoculating tomato plants with GBNV, monitoring changes in morphological and spectral characteristics, evaluating machine learning algorithms (decision tree [DT] classifier) for analysis and classification of disease severity, and developing and validating a device for disease detection and severity estimation. Spectral data analysis revealed distinct patterns in reflectance, with notable peaks observed in the 680 and 760 nm bands, while reflectance remained low and constant beyond 900 nm. Machine learning techniques, specifically a DT model, were employed to classify disease severity based on spectral data with high accuracy (95.01% training accuracy and 93.65% testing accuracy). The model identified the near‐infrared band as highly correlated (correlation coefficient of 0.82) with disease severity. Furthermore, a compact handheld device integrating a spectral sensor, organic light‐emitting diode display, and Raspberry Pi 3B was developed for real‐time disease severity estimation. The device demonstrated robust performance, accurately predicting disease severity at different growth stages, even in the absence of visible symptoms. Additionally, disease severity percentages obtained via reverse transcription polymerase chain reaction were used to validate the accuracy of the device's estimations. Its responsive nature, with estimated response times ranging from milliseconds to seconds, facilitates timely interventions in agricultural settings. Overall, this interdisciplinary approach, combining spectral analysis, machine learning, and device development, presents a promising solution for efficient disease monitoring and management in agriculture, contributing to enhanced crop health and food security.

Unmanned Aerial Vehicle for Pipeline Surveillance: A Review

Petroleum products being transported through pipelines can be easily targeted by economic and political saboteurs. Unmanned Aerial Vehicle (UAV) heralds a new technology on pipeline safety, surveillance, surveying mapping, assessment and safety for the oil and gas industry. With the advent of this technology, leaks, corrosion, third party interference and other faults leading to the loss of life, environmental pollution can be checked. This review highlights the state of the technology and benefits of UAV to the Nigeria oil and gas industry. The Nigeria oil and gas industry vested with over 2,300,000 barrels of crude oil daily production has over 9000km pipeline route which is prone to rupture from leaks, corrosion and vandalism. The industry will benefit from a flexible compatible and adaptable UAV platform with a multispectral and hyper spectral sensor for extensive safety, real-time imagery within a localized small to medium spatial scale, over larger expanse of space and time. The technology is adjured cheaper for inspection mission over traditional methods. Adoption of these technology would improve the environmental imprints of the oil and gas companies operating in the Niger Delta, and cases of pipeline vandalism and unrest might be lessened.

Exploring the efficacy of subwavelength gratings as short-wavelength infrared filters

Advancements in nanofabrication technology have greatly facilitated research on nanostructures and their associated properties. Among these structures, subwavelength components have emerged as promising candidates for ultra-compact optical elements, can potentially supplant conventional optical components and enable the realization of compact and efficient optical devices. Spectral analysis within the infrared spectrum offers a wealth of information for monitoring crop health, industrial processes, and target identification. However, conventional spectrometers are typically bulky and expensive, driving an increasing demand for cost-effective spectral sensors. Here we investigate three distinct subwavelength grating structures designed to function as narrowband filters within the short-wavelength infrared (SWIR) range. Through simple adjustments to the period of grating strips, these filters selectively transmit light across a wide wavelength range from 1100 to 1700 nm with transmission exceeding 70% and full width at half maximum (FWHM) down to 6 nm. Based on a simple design, the results present great potential of subwavelength grating filters for multiband integration and developing ultra-compact spectral sensors.

Sensing Pre- and Post-Ecdysis of Tropical Rock Lobsters, Panulirus ornatus, Using a Low-Cost Novel Spectral Camera

Tropical rock lobsters (Panulirus ornatus) are a highly cannibalistic species with intermoult animals predominantly attacking animals during ecdysis (moulting). Rapid, positive characterisation of pre-ecdysis lobsters may open a pathway to disrupt cannibalism. Ecdysial suture line development is considered for pre-ecdysis recognition with suture line definition compared for intermoult and pre-ecdysis lobsters emerged and immerged, using white, near ultraviolet (365 nm), near infrared (850 nm), and specialty SFH 4737 broadband IR LEDs against a reference of intermoult lobsters with no suture line development. Difficulties in acquiring suture line images prompted research into pre-ecdysis characterisation from the lobster’s dorsal carapace, due to its accessibility through a culture vessel’s surface. In this study, a novel low-cost spectral camera was developed by coordinating an IMX219 image sensor, an AS7265x spectral sensor, and four SFH 4737 broadband infrared LEDs through a single-board computer. Images and spectral data from the lobster’s dorsal carapace were acquired from intermoult, pre-ecdysis, and post-ecdysis lobsters. For the first time, suture line definition was found to be enhanced under 850 nm, 365 nm, and SFH 4737 LEDs for immerged lobsters, while the 850 nm LED achieved the best suture line definition of emerged lobsters. Although the spectral camera was unable to characterise pre-ecdysis, its development was validated when a least squares regression for binary classification decision boundary successfully separated 86.7% of post-ecdysis lobsters. Achieving post-ecdysis characterisation is the first time the dorsal carapace surface has been used to characterise a moult stage for palinurid lobsters.

Design, development and validation of a handheld colourimeter for the quantification of colourimetric assays on paper analytical devices

Colourimetric quantification of analytes on paper analytical devices (PADs) using smartphones has been gaining popularity. However, the accuracy of these devices is prone to be affected by different environmental conditions, including the intensity and colour of the ambient light. This work explains in depth the design and fabrication of a handheld colourimeter whose accuracy is unaffected by ambient light conditions using the commercially available spectral sensor AS7262. The device works on the principle of light reflection from the sample and can quantify as well as display the concentration of the analyte on an organic light-emitting-diode (OLED) display. The data acquisition, processing, and transmission of the data to a smartphone using Bluetooth in less than 7 seconds is also a salient feature. The accuracy of the device was validated by testing different concentrations of alkaline phosphatase (ALP) and total protein on PADs explicitly developed for this study. The colourimeter exhibited linearity with R² values of 0.98 for ALP and 0.97 for total protein. The LOD and LOQ obtained for ALP and total protein are 1.1, 3.89 U/L and 0.037, 0.12 g/dL, respectively. The relative standard deviation (RSD) calculated was 0.006 for ALP and 0.004 for total protein. The validation of the colourimeter was carried out with the clinical samples to obtain a relative error of less than 10 % for both the analytes.

Wireless charging flexible in-situ optical sensing for food monitoring

Food safety is an important public health issue, real-time monitoring and identification of food freshness is essential to ensure food quality and consumer health. This study presents a wireless charging flexible in-situ optical sensing system (FIOS). FIOS integrates visible (VIS)/near-infrared (NIR) spectral sensors, electronic components, and microcontrollers into flexible circuits by flexible electronic technology, and obtains energy through wireless charging to solve the problem of battery replacement and frequent charging of electronic systems. FIOS exhibits excellent flexibility and bendability which can be attached well to the surface of the food for efficient, accurate, non-destructive, and in-situ monitoring. A prediction model between food quality and spectral data was established by chemometrics to achieve accurate prediction of food quality. It can obtain the spectral information of the food in real-time and transmit the data wirelessly to a cloud platform, which enables the visualization of food quality and facilitates quality traceability. FIOS is characterized by simple craft, low cost, and real-time monitoring, and can be widely deployed as an Internet of Things (IoT) node in food transportation, storage, and sales to improve the transparency of food at all stages and ensure the quality and safety of food. The FIOS has the advantages of portable and non-destructive monitoring, which improves the accuracy of food quality monitoring and provides a new technological program in the field of food quality monitoring. It is expected to promote the development of food quality and safety monitoring in the future and provide consumers with a more reliable guarantee of food quality.

Remote Sensing-Based Water Quality Parameters Retrieval Methods: A Review

Water quality is a sensitive global environmental issue, as it is important for long-term economic development and environmental sustainability. It is a general descriptor of water properties in terms of physical, chemical, thermal, and/or biological characteristics. Laboratory analysis is used to measure and analyze water quality parameter, however, it is a conventional, time-consuming, and expensive approach often providing discrete data at a single point in space and time and making it difficult to characterize a larger waterbody, while remote sensing methods is a cost effective and accurate methods of water quality monitoring with a high spatial and temporal resolution for large area of waterbodies. To this end, this review focused on novel findings in the field of water quality estimation using remote sensing techniques, and the result revealed that remote sensing method has used to retrieve water quality parameters which are optically active (Chlorophyll-a, Secchi Disk depth, Water temperature, Turbidity, Total Suspended Matter, Electrical conductivity, Sea Surface Salinity and Colored Dissolved Organic Matter), and optically non active (Dissolved Oxygen, Chemical Oxygen Demand, Biochemical Oxygen Demand, Total Nitrogen, Ammonia Nitrogen and Total Phosphorus). Various properties (spectral, spatial and temporal, etc.) of the more commonly employed multi spectral and hyper spectral sensors of both satellite and non-satellite-born data sources are tabulated to be used as a sensor selection guide. Furthermore, this paper summarizes the commonly used different retrieval algorisms (analytical, empirical, and artificial intelligence/machine learning (AI/ML)) employed in evaluating and quantifying the water quality parameters. As a whole, remote sensing technology is a permissible method for water quality monitoring across the world in its spatio-temporal coverage, accuracy, and its cost effectiveness

RETRACTED ARTICLE: Prediction of sports fatigue degree based on spectral sensors and machine learning algorithms

RETRACTED ARTICLE: Prediction of sports fatigue degree based on spectral sensors and machine learning algorithms