Toward an Intelligent Blockchain IoT-Enabled Fish Supply Chain: A Review and Conceptual Framework.

The fish industry experiences substantial illegal, unreported, and unregulated (IUU) activities within traditional supply chain systems. Blockchain technology and the Internet of Things (IoT) are expected to transform the fish supply chain (SC) by incorporating distributed ledger technology (DLT) to build trustworthy, transparent, decentralized traceability systems that promote secure data sharing and employ IUU prevention and detection methods. We have reviewed current research efforts directed toward incorporating Blockchain in fish SC systems. We have discussed traceability in both traditional and smart SC systems that make use of Blockchain and IoT technologies. We demonstrated the key design considerations in terms of traceability in addition to a quality model to consider when designing smart Blockchain-based SC systems. In addition, we proposed an Intelligent Blockchain IoT-enabled fish SC framework that uses DLT for the trackability and traceability of fish products throughout harvesting, processing, packaging, shipping, and distribution to final delivery. More precisely, the proposed framework should be able to provide valuable and timely information that can be used to track and trace the fish product and verify its authenticity throughout the chain. Unlike other work, we have investigated the benefits of integrating machine learning (ML) into Blockchain IoT-enabled SC systems, focusing the discussion on the role of ML in fish quality, freshness assessment and fraud detection.

A Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy.

Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.

Rapid Assessment of Fish Freshness for Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy and Fusion-Based Artificial Intelligence.

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.

Handheld Multispectral Fluorescence Imaging System to Detect and Disinfect Surface Contamination.

Contamination inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle food. Food contamination must be prevented, and zero tolerance legal requirements and damage to the reputation of institutions or restaurants can be very costly. This paper introduces a new handheld fluorescence-based imaging system that can rapidly detect, disinfect, and document invisible organic residues and biofilms which may host pathogens. The contamination, sanitization inspection, and disinfection (CSI-D) system uses light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm, for the detection of organic residues, including saliva and respiratory droplets. The 275 nm light is also utilized to disinfect pathogens commonly found within the contaminated residues. Efficacy testing of the neutralizing effects of the ultraviolet light was conducted for Aspergillus fumigatus, Streptococcus pneumoniae, and the influenza A virus (a fungus, a bacterium, and a virus, respectively, each commonly found in saliva and respiratory droplets). After the exposure to UVC light from the CSI-D, all three pathogens experienced deactivation (> 99.99%) in under ten seconds. Up to five-log reductions have also been shown within 10 s of UVC irradiation from the CSI-D system.

Inactivation of Escherichia coli, Salmonella enterica, and Listeria monocytogenes using the Contamination Sanitization Inspection and Disinfection (CSI-D) device.

The Contamination Sanitization Inspection and Disinfection (CSI-D) device is a handheld fluorescence-based imaging system designed to disinfect food contact surfaces using ultraviolet-C (UVC) illumination. This study aimed to determine the optimal CSI-D parameters (i.e., UVC exposure time and intensity) for the inactivation of the following foodborne bacteria plated on non-selective media: generic Escherichia coli (indicator organism) and the pathogens enterohemorrhagic E. coli, enterotoxigenic E. coli, Salmonella enterica, and Listeria monocytogenes. Each bacterial strain was spread-plated on non-selective agar and exposed to high-intensity (10 mW/cm2) or low-intensity (5 mW/cm2) UVC for 1-5 s. Control plates were not exposed to UVC. The plates were incubated overnight at 37 °C and then enumerated. Three trials for each bacterial strain were conducted. Statistical analysis was carried out to determine if there were significant differences in bacterial growth between UVC intensities and exposure times. Overall, exposure to low or high intensity for 3-5 s resulted in consistent inhibition of bacterial growth, with reductions of 99.9-100 % for E. coli, 96.8-100 % for S. enterica, and 99.2-100 % for L. monocytogenes. The 1 s exposure time showed inconsistent results, with a 66.0-100 % reduction in growth depending on the intensity and bacterial strain. When the results for all strains within each species were combined, the 3-5 s exposure times showed significantly greater (p < 0.05) growth inhibition than the 1 s exposure time. However, there were no significant differences (p > 0.05) in growth inhibition between the high and low UVC intensities. The results of this study show that, in pure culture conditions, exposure to UVC with the CSI-D device for ≥3 s is required to achieve consistent reduction of E. coli, S. enterica, and L. monocytogenes.

Radial angular filter arrays for angle-resolved scattering spectroscopy.

The radial angular filter array (RAFA) consists of a series of radially-distributed micro-machined channels, where the long axes of the channels converge at a focal point. The high aspect ratio of each channel provides a means to reject photons with trajectories outside the acceptance angle of the channel. The output of the RAFA represents the angular distribution of photons emitted from the focal point. A series of RAFAs were designed, fabricated, and tested to evaluate the impact of device geometry, inter-channel cross talk, achromaticity, and channel leakage on device performance. As an application example, an RAFA was used together with an imaging spectrometer to capture angle-resolved spectra of turbid samples.

Application of image processing and transfer learning for the detection of rust disease.

Plant diseases introduce significant yield and quality losses to the food production industry, worldwide. Early identification of an epidemic could lead to more effective management of the disease and potentially reduce yield loss and limit excessive input costs. Image processing and deep learning techniques have shown promising results in distinguishing healthy and infected plants at early stages. In this paper, the potential of four convolutional neural network models, including Xception, Residual Networks (ResNet)50, EfficientNetB4, and MobileNet, in the detection of rust disease on three commercially important field crops was evaluated. A dataset of 857 positive and 907 negative samples captured in the field and greenhouse environments were used. Training and testing of the algorithms were conducted using 70% and 30% of the data, respectively where the performance of different optimizers and learning rates were tested. Results indicated that EfficientNetB4 model was the most accurate model (average accuracy = 94.29%) in the disease detection followed by ResNet50 (average accuracy = 93.52%). Adaptive moment estimation (Adam) optimizer and learning rate of 0.001 outperformed all other corresponding hyperparameters. The findings from this study provide insights into the development of tools and gadgets useful in the automated detection of rust disease required for precision spraying.

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses.

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

Effect of surface plasmon cross-talk on optical properties of closely packed nano-hole arrays.

The integration and miniaturization of nanostructure-based optical devices based on interaction with surface plasmons requires the fabrication of patterns of multiple nanostructures with tight spacing. The effect of surface plasmon energy interchange (cross-talk) across large grids of nanostructures and its effect on the optical characteristics of individual nanostructures have not been investigated. In this paper, we experimentally fabricated a large grid of individual nano-hole arrays of various hole diameter, hole spacing, and inter-array spacing. The spectral optical transmission of each nano-hole array was measured and the effect of inter-array spacing on the transmission spectra and resonance wavelength was determined.

Optical resonance transmission properties of nano-hole arrays in a gold film: effect of adhesion layer.

In this paper, we present a systematic study on the influence of composition of the adhesion layer between gold and a Pyrex substrate on the optical resonance transmission properties of nano-hole arrays in an optically thick gold film. Large nano-hole arrays with different hole periodicities in a square lattice arrangement were fabricated using Electron Beam Lithography using different adhesion layers (chromium, titanium, or etched adhesion layer). The fabricated nano-hole arrays were optically characterized using transmission spectroscopy. The optical performance of each nano-hole array was numerically simulated using a Finite Difference Time Domain (FDTD) method. The experiments and simulations revealed that the optical resonance transmission properties (i.e. the resonance wavelength, the spectral transmission modulation ratio, and the resonance bandwidth) of the nano-hole arrays depended highly on the composition and the thickness of the adhesion layer. The optical resonance bandwidths were larger for the nano-hole arrays with chromium or titanium adhesion layers. Also, a red-shift of the optical resonance peak was observed for nano-hole arrays with a metal adhesion layer compared to the corresponding nano-hole arrays with an etched adhesion layer, but the red-shift was greatest for the nano-hole array with the titanium adhesion layer. For adhesion layers of greater thickness, the optical resonance peaks were reduced in magnitude. Finally, nano-hole arrays with an etched adhesion layer had a significant blue-shift in the optical resonance peak and a narrower optical resonance bandwidth compared to nano-hole arrays with a titanium or a chromium adhesion layer. Consequently, a narrow optical resonance bandwidth characteristic of a nano-hole array with an etched adhesion layer can potentially enhance the spectral selectivity and offer improved optical performance.

FootAssure: A multimodal, in-home wound detection device for diabetic peripheral neuropathy.

Currently, there is no single technology capable of assessing all the multitude of factors associated with peripheral complications of diabetic neuropathy. In this work, a multimodal wound detection system is proposed to help facilitate in-home examinations, utilizing a combination of thermal, multi-spectral 3D imaging modalities. The proposed system is capable of the 3D surface rendering of the foot and would overlay thermal, blood oxygenation, besides other skin health information to aid with foot health monitoring. Examples of biomarkers include pre-ulcer formation, blood circulation, temperature change, oxygenation, swelling, blisters/ulcer formation and healing, and toe health.

Experimental and numerical analysis on the optical resonance transmission properties of nano-hole arrays.

In this paper, we present experimental and numerical analysis on Extraordinary Optical Transmission (EOT) or optical resonance transmission through various nano-hole arrays constructed from an optically thick metal film within the visible and near infra-red spectrum. Nano-hole arrays with different geometrical parameters (hole size, hole shape, and hole periodicity) having their EOT properties in the visible and near-infrared regime were simulated based on Finite Difference Time Domain (FDTD). Large nano-hole arrays with geometric properties similar to the simulated arrays were fabricated using Electron Beam Lithography (EBL). The optical resonance transmission properties (resonance position, transmission efficiency, and spectral bandwidth of resonance peak) of the fabricated nano-hole arrays were characterized. Finally, the experimental and numerical results were analyzed to determine the dependencies and discrepancies between optical resonance transmission properties for various nano-hole arrays.

Contrast and resolution analysis of iterative angular domain optical projection tomography.

In Angular Domain Imaging, image contrast and resolution are position dependent. The objective of this work was to characterize the contrast and resolution of an ADI system at a multitude of locations within the imaging plane, then compare the reconstructions of different targets using filtered back projection and iterative reconstruction algorithms. Contrast varied significantly with depth and minimally with lateral position, while resolution varied significantly with lateral position and minimally with depth. The iterative reconstruction algorithm was robust against ring and streak artifacts. The back projection reconstructions suffered from artifacts related to a lack of projection data.

Angular domain fluorescence lifetime imaging: a tissue-like phantom study.

We describe a fluorescence lifetime imaging technique employing the collimation detection capabilities of an angular filter array (AFA). The AFA accepts minimally scattered photons emitted from fluorophores up to 2 mm deep within turbid media. The technique, referred to as Angular Domain Fluorescence Lifetime Imaging (ADFLI), is described and its performance evaluated in comparison to a conventional (lens and pinhole) system. Results from a tissue-mimicking phantom demonstrated that ADFLI provides better spatial resolution and image contrast for fluorescent probes at greater depths compared to a lens and pinhole system.

Transmission and fluorescence angular domain optical projection tomography of turbid media.

When imaging through turbid media, objects are often blurred by scattered light. An optical collimator (i.e., an angular filter array) improves images by accepting only photons propagating within a narrow solid angle about the direction of the incident light. These photons are expected to participate in a limited number of small-angle scattering events, maintaining their original propagation direction and, finally, contributing to the development of a faithful image of an object within a turbid medium. The collimation method, also referred to as angular domain imaging (ADI), applies to a see-through configuration where the incident collimated light beam can be aligned with the collimator in a transillumination mode of operation. In this paper, we present angular domain optical projection tomography (ADOPT), a method that can extract depth information of optical contrast in turbid media with high longitudinal resolution based on ADI technology. The resolution of the ADI system has been tested over various depths in a 5 cm optical cuvette using a resolution target suspended in a homogeneous turbid medium. The ADOPT system reconstructed images from a series of angular domain projections collected at angular intervals. The system was used to measure the attenuation of an absorbing target in transmission mode (t-ADOPT) and to measure the light emitting from a fluorescent target (f-ADOPT). Tissue-mimicking phantoms were used to validate the performance of the method. In the t-ADOPT configuration, a background scattered light estimation and subtraction methodology was introduced to improve the imaging contrast. A target consisting of two graphite rods (0.9 mm diameter) was suspended in the cuvette by a rotation stage. An Indocyanine Green-filled glass rod was used as an imaging target in the f-ADOPT arrangement. The target was placed in a manner such that the line of laser light was perpendicular to the longitudinal axis of the rods. Several projections were collected at increments of 1.8 degrees and compiled into a sinogram. A transverse image was reconstructed from the sinogram by using filtered backprojection and image contrast was improved by experimental scatter measurements using a wedge prism and an image processing algorithm. The submillimeter target embedded in a 2 cm thick scattering medium (reduced scattering coefficient < or = 2.4 cm(-1)) was discernable in both the sinograms and the reconstructed images. In the f-ADOPT system, fluorescent line targets <1 cm in diameter embedded in a 2 cm thick scattering medium (reduced scattering coefficient < or = 0.8 cm(-1)) were discernable in both the sinograms and the reconstructed images. The proposed method could be used as the basis to construct an optical tomographic scanner for simultaneous absorption and fluorescence-based imaging of biological specimens (i.e., up to 7 mm across).

Classification and Assessment of Hand Arthritis Stage using Support Vector Machine.

Arthritis is one of the most common health problems affecting people around the world. The goal of the work presented work is to classify and categorizing hand arthritis stages for patients, who may be developing or have developed hand arthritis, using machine learning. Stage classification was done using finger border detection, developed curvature analysis, principal components analysis, support vector machine and K-nearest neighbor algorithms. The outcome of this work showed that the proposed method can classify subject finger proximal interphalangeal joints (PIP) and distal interphalangeal joints (DIP) into stage classes with promising accuracy, especially for binary classification.

Image contrast enhancement in angular domain optical imaging of turbid media.

Imaging structures within a turbid medium using Angular Domain Imaging (ADI) employs an angular filter array to separate weakly scattered photons from those that are highly scattered. At high scattering coefficients, ADI contrast declines due to the large fraction of non-uniform background scattered light still within the acceptance angle. This paper demonstrates various methods to enhance the image contrast in ADI. Experiments where a wedge prism was used to deviate the laser source so that scattered photons could be imaged and subtracted from the image obtained by standard ADI provided the greatest improvement in image contrast.

Multi-spectral angular domain optical imaging in biological tissues using diode laser sources.

Angular Domain Imaging (ADI) employs micromachined angular filter to detect non-scattered photons that pass through the micro-scale tunnels unattenuated while scattered photons are rejected. This paper describes the construction of an ADI system utilizing diode lasers at three different wavelengths in the range of the red and near infrared spectrum. Experiments are performed to verify the feasibility of ADI at multi-wavelengths. ADI results of chicken breast as a biological scattering medium are presented for different thicknesses. A spatial resolution of <0.5 mm is achieved with 5 mm thick chicken breast using a 975 nm diode laser source.

Review of the potential of optical technologies for cancer diagnosis in neurosurgery: a step toward intraoperative neurophotonics.

Advances in image-guided therapy enable physicians to obtain real-time information on neurological disorders such as brain tumors to improve resection accuracy. Image guidance data include the location, size, shape, type, and extent of tumors. Recent technological advances in neurophotonic engineering have enabled the development of techniques for minimally invasive neurosurgery. Incorporation of these methods in intraoperative imaging decreases surgical procedure time and allows neurosurgeons to find remaining or hidden tumor or epileptic lesions. This facilitates more complete resection and improved topology information for postsurgical therapy (i.e., radiation). We review the clinical application of recent advances in neurophotonic technologies including Raman spectroscopy, thermal imaging, optical coherence tomography, and fluorescence spectroscopy, highlighting the importance of these technologies in live intraoperative tissue mapping during neurosurgery. While these technologies need further validation in larger clinical trials, they show remarkable promise in their ability to help surgeons to better visualize the areas of abnormality and enable safe and successful removal of malignancies.

Real time optical Biopsy: Time-resolved Fluorescence Spectroscopy instrumentation and validation.

The Time-resolved fluorescence spectroscopy (TR-FS) has the potential to differentiate tumor and normal tissue in real time during surgical excision. In this manuscript, we describe the design of a novel TR-FS device, along with preliminary data on detection accuracy for fluorophores in a mixture. The instrument is capable of near real-time fluorescence lifetime acquisition in multiple spectral bands and analysis. It is also able to recover fluorescence lifetime with sub-20ps accuracy as validated with individual organic fluorescence dyes and dye mixtures yielding lifetime values for standard fluorescence dyes that closely match with published data. We also show that TR-FS is able to quantify the relative concentration of fluorescence dyes in a mixture by the unmixing of lifetime decays. We show that the TR-FS prototype is able to identify in near-real time the concentrations of dyes in a complex mixture based on previously trained data. As a result, we demonstrate that in complex mixtures of fluorophores, the relative concentration information is encoded in the fluorescence lifetime across multiple spectral bands. We show for the first time the temporal and spectral measurements of a mixture of fluorochromes and the ability to differentiate relative concentrations of each fluorochrome mixture in real time.