Search

[Abstract] This study reviews current artificial intelligence (AI) systems legislation, the AI techniques definition proposed by the AI Act and main applications of AI methods in the fisheries sector with special focus on applications to enhance traceability of fishery products, fishing gear selectivity, good practices, and potential to help young people finding jobs. Finally, this study offers policy recommendations relevant to EU decision-making to achieve a better use of AI systems in the fisheries sector.

Bioelectrical impedance analysis (BIA), near-infrared (NIR) spectroscopy and time domain reflectometry (TDR) were compared as non-destructive techniques, coupled with a classifier based on partial least square discriminant analysis (PLS-DA), to assess added water detection in a seafood model: tuna. Three classification models were developed for each technology in unfrozen, thawed and in a combination of both stages to distinguish between added and non-added water samples. Results were acceptable for the unfrozen stage with all the technologies, giving TDR the best performance (accuracy = 0.95; error rate = 0.06). However, results on the model for thawed stage were not satisfactory, due to the behavior of water during the freezing-thawing process in both types of samples (with and without added water). For the combined model, NIR failed in the classification (accuracy = 0.68; error rate = 0.32), BIA gave acceptable results (accuracy = 0.72; error rate = 0.28) and TDR made a good classification (accuracy = 0.87; error rate = 0.12)

The performances of three non-destructive sensors, based on different principles, bioelectrical impedance analysis (BIA), near-infrared spectroscopy (NIR) and time domain reflectometry (TDR), were studied to discriminate between unfrozen and frozen-thawed fish. Bigeye tuna (Thunnus obesus) was selected as a model to evaluate these technologies. The addition of water and additives is usual in the fish industry, thus, in order to have a wide range of possible commercial conditions, some samples were injected with different water solutions (based on different concentrations of salt, polyphosphates and a protein hydrolysate solution). Three different models, based on partial least squares discriminant analysis (PLS-DA), were developed for each technology. This is a linear classification method that combines the properties of partial least squares (PLS) regression with the classification power of a discriminant technique. The results obtained in the evaluation of the test set were satisfactory for all the sensors, giving NIR the best performance (accuracy = 0.91, error rate = 0.10). Nevertheless, the classification accomplished with BIA and TDR data resulted also satisfactory and almost equally as good, with accuracies of 0.88 and 0.86 and error rates of 0.14 and 0.15, respectively. This work opens new possibilities to discriminate between unfrozen and frozen-thawed fish samples with different non-destructive alternatives, regardless of whether or not they have added water.

A handheld near infrared (NIR) spectroscopy device, with a wavelength range from 900 nm to 1650 nm and coupled with two Partial Least-Squares Discriminant Analysis (PLS-DA) models, has been used to demonstrate its applicability as a proof of concept for quality monitoring of bigeye tuna (Thunnus obesus). First, a classification model was created to discriminate between injected and non-injected tuna samples. Then, a second classification model was developed to discriminate between non-injected and each water and additives treatment used. The results were promising, showing both models good results in the validation dataset. The first model, with 8 latent variables (LV), had an error-rate of 0.08 and an accuracy value of 0.93. It showed a good discrimination between injected and non-injected samples. The second model, with 10 LV, presented an error rate of 0.15 and an accuracy of 0.88. The discrimination between treatments was good even when protein hydrolysate solutions were used (sensitivity = 0.81; specificity = 0.99; precision = 0.87), a case which is typically hard to detect with accurate destructive analysis. This work opens new possibilities for onsite inspection in the fish industry, where NIR could be used as a complementary tool for the detection of water solutions in tuna

The microbial safety and stability of most food, are based on an application of preservative factors called hurdles. Each hurdle implies putting microorganisms in a hostile environment, which inhibits their growth or causes their death (Leistner, 2000). Some of those hurdles have been empirically used for years to stabilize meat, fish, milk and vegetables. This sometimes leads to completely different product with its own new taste characteristics. Examples of hurdles in marine products are salt (salted cod, klipfish), smoke (cold or hot smoked salmon, herring), acids (marinated products, pickles), temperature (high or low), fermentative microorganisms (traditional Asian sauces) and more recently redox potential (vacuum-packed products). Those preservative factors have been studied for years, but a large amount of potential hurdles for food have already been described including organic acids, bacteriocins, chitosan, nitrate, lactoperoxidase, essential oil, modified atmosphere packaging... , as well as novel decontamination technologies such as microwave and radio frequency, ohmic and inductive heating, high pressure, pulsed electric field, high voltage arc discharge, pulsed light, oscillation magnetic field, ultraviolet light, ultrasound, X-ray, electrolyse NaCl water, ozone... (Kim et al, 1999 ; Weber, 2000 ; Mahmoud et al, 2006). Hurdles that have a positive effect by inhibiting microorganisms may have a negative one on other parameters such as nutritional properties or sensory quality, depending on their intensity. As an example, salt content in food must be high enough to inhibit pathogens and spoilage microorganisms, but not so high to impair taste. In order to lower the preservative level, the hurdle technology concept has been developed (Leistner, 1985), consisting in using combined hurdles to establish an additive antimicrobial effect, and even sometimes a synergetic one, thus improving the safety and the sensory quality of food.

In order to understand the mechanisms behind the undesired aging of films based on vital wheat gluten plasticized with glycerol, films cast from water/ethanol solutions were investigated. The effect of pH was studied by casting from solutions at pH 4 and pH 11. The films were aged for 120 days at 50% relative humidity and 23 C, and the tensile properties and oxygen and water vapor permeabilities were measured as a function of aging time. The changes in the protein structure were determined by infrared spectroscopy and size-exclusion and reverse-phase high-performance liquid chromatography, and the film structure was revealed by optical and scanning electron microscopy. The pH 11 film was mechanically more stable with time than the pH 4 film, the latter being initially very ductile but turning brittle toward the end of the aging period. The protein solubility and infrared spectroscopy measurements indicated that the protein structure of the pH 4 film was initially significantly less polymerized/ aggregated than that of the pH 11 film. The polymerization of the pH 4 film increased during storage but it did not reach the degree of aggregation of the pH 11 film. Reverse-phase chromatography indicated that the pH 11 films were to some extent deamidated and that this increased with aging. At the same time a large fraction of the aged pH 11 film was unaffected by reducing agents, suggesting that a time-induced isopeptide cross-linking had occurred. This isopeptide formation did not, however, change the overall degree of aggregation and consequently the mechanical properties of the film. During aging, the pH 4 films lost more mass than the pH 11 films mainly due to migration of glycerol but also due to some loss of volatile mass. Scanning electron and optical microscopy showed that the pH 11 film was more uniform in thickness and that the film structure was more homogeneous than that of the pH 4 film. The oxygen permeability was also lower for the pH 11 film. The fact that, QC 20100708

The properties of new and aged glycerol-plasticized vital wheat gluten films containing ≤4.5 wt % natural or quaternary ammonium salt modified montmorillonite clay were investigated. The films were cast from pH 4 or pH 11 ethanol/water solutions. The films, aged for ≤120 days, were characterized by tensile testing, X-ray diffraction, and transmission electron microscopy. In addition, water vapor permeability (11% relative humidity) and the content of volatile components were measured. The large reduction in the water vapor permeability with respect to the pristine polymer suggests that the clay platelets were evenly distributed within the films and oriented preferably with the platelet long axis parallel to the film surface. The film prepared from pH 11 solution containing natural clay was, as revealed by transmission electron microscopy and X-ray diffraction, almost completely exfoliated. This film was consequently also the strongest, the stiffest, and the most brittle and, together with the pH 11 film containing modified clay, it also showed the greatest decrease in water vapor permeability. The large blocking effect of the clay had no effect on the aging kinetics of the films. During aging, the pH 4 and pH 11 film strength and the pH 4 film stiffness increased and the pH 4 film ductility decreased at the same rate with or without clay. This suggests that the aging was not diffusion rate limited, that is, that the loss of volatile components or the migration of glycerol or glycerol/wheat gluten phase separation was not limited by diffusion kinetics. The aging rate seemed to be determined by slow structural changes, possibly involving protein denaturation and aggregation processes., Uppdaterad från submitted till published: 20101013.QC 20101013

Chitosan, Whey Protein Isolate (WPI) and vital wheat gluten (WG) are three biomaterials that have quite promising properties for packaging purposes. They have good film forming properties and good gas barrier properties in dry conditions. Moreover, because they are produced from industrial waste of food processing, they offer an ecological advantage over polymers made from petroleum. However, their physicochemical characteristics still must be improved for them to be of commercial interest for the food packaging industry. The purpose of this work was to study different strategies aiming to improve the water resistance and aging properties of these polymers, which are some of the key disadvantages of these materials. The produced solution cast chitosan and WPI films were characterised with scanning electron microscopy (SEM), density measurements and thermogravimetry. The water vapour transmission rate was determined at a relative humidity of 11%. In the first part, mechanical properties of solid films and seals were assessed by tensile testing. WG film’s tensile properties and oxygen and water vapour permeabilities were measured as a function of aging time. The changes in the protein structure were determined by infrared spectroscopy and size-exclusion high-performance liquid chromatography and the film structure was revealed by optical and scanning electron microscopy. Gluten-clay nanocomposites were characterised by tensile testing, X-ray diffraction and transmission electron microscopy. The incorporation of a hydrophobic biodegradable polymer, poly ( ε-caprolactone), PCL, in both chitosan and whey protein, yielded a significant decrease in water vapour transmission rate. It was observed that a certain amount of the PCL particles were ellipsoidal in chitosan and fibrous in WPI. The obtained data also indicated that the particle shape had an important influence in the water vapour transmission rate. In the second part, the aging properties of WG films, plasticized w, QC 20101013

Properties important for packaging were studied on blends of 0-15 wt% poly( caprolactone) and chitosan and a whey-protein-isolate. The blends were obtained by solution mixing, and films were produced by solvent casting. Transparency was measured by UV/VIS spectroscopy and the printability was qualitatively estimted by using a red ethanol dye. Mechanical properties of solid films and seals were assessed by tensile tests. Stiffness and folding endurence were also measured. The blend morphology was characterized by scanning electron microscopy. It was found that all the blends were transparent. The whey-protein-isolate had the best printability properties and printability remained in the poly( -caprolactone)-blends. Film stiffness decreased and strain at break increased strongly when the pure chitosan and the pure whey-protein-isolate were wetted. The addition of poly( -caprolactone) to chitosan and whey-protein-isolate had only a moderate effect on the toughness properties but a strong effect on the modulus which could be predicted by the Halpin-Tsai model. The modulus of the whey-protein-isolate increased and the modulus of the chitosan decreased with the addiion of poly( -caprolactone). It was found that it was impossible to seal chitosan with a standard heat-pulse sealing technique. The whey-protein-isolate was sealable but the strength of the seals was lower than the intrinsic strength of the pure whey-protein-isolate. The folding endurance properties of chitosan and its blends were far better than those of the whey-protein-isolate and its blends., QC 20101013

NR 20140805

Blends of poly(p-caprolactone) (PCL) with chitosan and a whey-protein-isolate (WPI) were prepared by solution mixing and film casting. The purpose was to increase the water vapour resistivity of chitosan and whey by blending them with a hydrophobic biodegradable polymer. The water vapour transmission rate was determined by a standard technique and by a new technique based on microcalorimetry. The blends were characterised by scanning electron microscopy (SEM), density measurements and thermogravimetry. Oxygen permeability was measured on the pure components and on some of the blends. The incorporation of PCL yielded a pronounced decrease in water vapour transmission rate of both chitosan and the WPI measured at a relative humidity gradient of 11 to 0%. A volume content of 17-18% of PCL lowered the water vapour transmission rate by 70-90%. It was found that the majority of the PCL particles were ellipsoidal in chitosan and fibrous in the WPI and the data indicated that the particle shape had an important influence on the water vapour transmission rate. The large decrease in water vapour transmission rate was also due to a reduction in water solubility because of limited swelling of the constrained chitosan or WPI matrix in the presence of PCL. SEM revealed that the miscibility/compatibility between PCL and the matrices was good. The water vapour transmission rate of the films decreased with increasing vacuum-drying time of the chitosan and WPI solutions. Microcalorimetry provided accurate estimates of water vapour transmission rate. Furthermore. this technique proved to be very flexible and the water vapour transmission rate could be determined over a broad range of relative humidities in a single experiment., QC 20101005