Muscle biochemical constituents of cultured amberjack <Emphasis Type="Italic">Seriola dumerili</Emphasis> and their influence on raw meat texture

The study was conducted to evaluate the meat texture, muscle proximate composition, lipid class composition, and collagen content of cultured amberjack and to compare these parameters with those of the yellowtail. Our results showed that the meat texture of cultured amberjack was tougher and had a lower degree of seasonality than that of cultured yellowtail. Muscle lipid and collagen content also varied in the two fish species over the study period. Meat breaking strength was not correlated with any of the muscle constituents, indicating that variations in the meat texture of cultured amberjack was not directly influenced by the changes in the muscle biochemical constituents.     

Deep learning-based appearance features extraction for automated carp species identification

Fish species identification is vital for aquaculture and fishery industries, stock management of water bodies and environmental monitoring of aquatics. Traditional fish species identification approaches are costly, time consuming, expert-based and unsuitable for large-scale applications. Hence, in this study, a deep learning neural network as a smart, real-time and non-destructive method was developed and applied to automate the identification of four economically important carp species namely common carp (Cyprinus carpio), grass carp (Ctenopharingodon idella), bighead carp (Hypophtalmichthys nobilis) and silver carp (Hypophthalmichthys molitrix). The obtained results proved that our approach, evaluated through 5-fold cross-validation, achieved the highest possible accuracy of 100 %. The achieved high level of classification accuracy was due to the ability of the suggested deep model to build a hierarchy of self-learned features, which was in accordance with the hierarchy of these fish’s identification keys. In conclusion, the proposed convolutional neural network (CNN)-based method has a single and generic trained architecture with promising performance for fish species identification.     

Formulated Food Products from Previously Frozen Skipjack Tuna Meat

Previously frozen skipjack tuna (Katsuwonus pelamis) obtained from Hawaiian waters provides a potential raw material for new value-added fish products. Fish patties (plain and teriyaki flavored) were successfully developed utilizing tuna meat, cellulose, soy protein isolates and other ingredients to form patties with texture characteristics similar to that of ground beef. The product contained 24% protein, 67% water, and less than 1% fat. Sensory evaluation responses by intermediate and high school students to these products were favorable. This study showed that an attractive and acceptable nutritional alternative could be produced and used as a low oil substitute for higher fat content ground beef patties.     

养殖日本真鲈和大口黑鲈原料特性比较

为了解养殖海水鲈鱼日本真鲈(Lateolabrax iaponcas)和淡水大口黑鲈(Micropterus salmoides)原料特性及加工可适性,测定了养殖日本真鲈和大口黑鲈的形态参数、基本成分、蛋白质组成、p H值、采肉率、熟肉率、系水力、滴水损失、鱼肉色泽和质构参数,并对养殖日本真鲈和大口黑鲈原料特性进行比较分析。结果表明:日本真鲈和大口黑鲈的形体参数和色泽差异显著(P0.05),两者的鱼头、鱼骨和内脏所占比例均较高;粗脂肪含量差异较大(P0.05),大口黑鲈粗脂肪含量是日本真鲈的2.70倍;粗蛋白总含量差异不大,但各种蛋白的含量有显著性差异(P0.05),日本真鲈的总基质蛋白含量高于大口黑鲈;大口黑鲈鱼肉较日本真鲈p H略低,熟肉率低,滴水损失率和失水率分别为日本真鲈的2.20倍和2.06倍;大口黑鲈和日本真鲈的质构参数均存在显著性差异(P0.05),大口黑鲈质构特性优于日本真鲈,口感较好。综合分析表明日本真鲈适合加工鱼糜等产品,而大口黑鲈适合生鱼片、鱼片等加工。两种鱼在加工过程中产生的下脚料较多,应合理利用下脚料提高其附加值。     

Biological,chemical and organoleptic changes during maturation of farmed Atlantic salmon,Salmo salar

Changes occurring during sexual maturation of farmed Atlantic salmon were investigated. Fifteen immature and maturing fish were sampled every fourth week from April to December. The skin colour and other external changes were registered, and the chemical composition of the fillets was analysed and the meat quality evaluated.The maturing females lost weight beginning in July, and the maturing males had a reduced weight gain during maturation. The external sexual characteristics appeared as early as May. Changes in the skin colour of maturing fish took place in July/August. From June to December, the fat content of the fillets decreased from about 12% to 5%; the protein content decreased from about 22% to 19%; and the water content increased from about 66% to 74%. In the same period, the weight of the viscera decreased from about 6% to 2–3% of the ungutted body weight. The red colour of the fillets decreased from August onwards. In October, significant differences in the chemical composition of the fillets of maturing and immature fish coincided with marked sensory differences. These differences increased later on. The odour and flavour became much less pronounced, and the texture became watery and tough. It is concluded that in the later stages of maturation, the quality of the meat deteriorates.     

肉松粉、羽毛粉和肉骨粉替代鱼粉养殖奥尼罗非鱼的效果研究

试验研究了肉松粉、羽毛粉和肉骨粉替代鱼粉池塘养殖奥尼罗非鱼的效果研究。24 000尾(349±28.3)g奥尼罗非鱼分为4组,每组设计3个平行试验区域,每2 000尾饲养于2×667 m2左右的实验区域中。对照组和1、2、3试验组日粮分别以鱼粉、肉松粉、羽毛粉和肉骨粉设计蛋白质水平为28%左右,消化能为2 670～2 810 Kcal/kg。在水温(28.2±2.8)℃饲养60 d。试验结果:①奥尼罗非鱼的相对生长率,食物转化率肉松粉组鱼粉组肉骨粉组羽毛粉组,差异显著(P0.05)。由于单位鱼成本不同,肉松粉组养殖效益为对照组的132.46%,肉骨粉组为对照组的96.60%,羽毛粉组为对照组的80.51%。②奥尼罗非鱼体水分,灰分含量差异不显著(P0.05);蛋白质含量鱼粉组肉松粉组肉骨粉组羽毛粉组,鱼粉组显著性高于肉骨粉和羽毛粉组(P0.05);脂肪含量肉骨粉组羽毛粉组肉松粉组鱼粉组,前3组显著性高于鱼粉组(P0.05)。③奥尼罗非鱼肥满度,脏体比,肝体比无显著性差异(P0.05),仅肉骨粉组肠脂比及肝脂肪含量最高,羽毛粉组最低,显著性差异(P0.05)。在池塘养殖中,饲料中使用肉松粉替代鱼粉可明显降低成本,提高经济效益。在罗非鱼饲料中使用部分肉骨粉和羽毛粉是安全的。     

Evaluating fish feeding intensity in aquaculture with convolutional neural networks

This paper presents a novel method to evaluate fish feeding intensity for aquaculture fish farming. Determining the level of fish appetite helps optimize fish production and design more efficient aquaculture smart feeding systems. Given an aquaculture surveillance video, our goal is to improve fish feeding intensity evaluation by proposing a two-stage approach: an optical flow neural network is first applied to generate optical flow frames, which are then inputted to a 3D convolution neural network (3D CNN) for fish feeding intensity evaluation. Using an aerial drone, we capture RGB water surface images with significant optical flows from an aquaculture site during the fish feeding activity. The captured images are inputs to our deep optical flow neural network, consisting of the leading neural network layers for video interpolation and the last layer for optical flow regression. Our optical flow detection model calculates the displacement vector of each pixel across two consecutive frames. To construct the training dataset of our CNNs and verify the effectiveness of our proposed approach, we manually annotated the level of fish feeding intensity for each training image frame. In this paper, the fish feeding intensity is categorized into four, i.e., ‘none,’ ‘weak,’ ‘medium’ and ‘strong.’ We compared our method with other state-of-the-art fish feeding intensity evaluations. Our proposed method reached up to 95 % accuracy, which outperforms the existing systems that use CNNs to evaluate the fish feeding intensity.     

基于卷积神经网络的养殖鱼类品种识别模型

随着机器学习、计算机视觉等技术的发展,卷积神经网络(CNN)越来越多地应用于图像识别领域,但现有的鱼类图像公共数据集资源较匮乏,难以满足深度CNN模型优化及性能提升的需要。实验以大黄鱼、鲤、鲢、秋刀鱼和鳙为对象,采用网络爬虫以及实验室人工拍照采集相结合的方式,构建了供鱼种分类的基础图片数据集,针对网络爬虫手段获取到的鱼类图像存在尺度不一、格式不定等问题,采用图像批处理的方式对所有获取到的图像进行了统一的数据预处理,并通过内容变换以及尺度变换对基础数据集做了数据增强处理,完成了7 993个样本的图像采集与归纳;在权值共享和局部连接的基础上,构建了一个用于鱼类识别的CNN模型,采用ReLU函数作为激活函数,通过dropout和正则化等方法避免过度拟合。结果显示,所构建的CNN鱼种识别模型具有良好的识别精度和泛化能力。随着迭代次数的增加,CNN模型的性能也逐步提高,迭代1 000次达到最佳,模型的准确率为96.56%。该模型采用监督学习的机器学习方式,基于CNN模型,实现了5种常见鱼类的鱼种分类,具有较高的识别精度和良好的稳定性,为养殖鱼类的品种识别提供了一种新的理论计算模型。     

基于LightGBM模型的鱼类异常行为检测

针对传统理化方法分析水质污染情况耗时耗力等问题,提出一种基于鱼类异常行为识别的水质监测方法。以红色斑马鱼(red zebrafish)为研究对象,利用计算机视觉技术,首先对斑马鱼图像进行预处理,利用灰度共生矩阵获取鱼群纹理特征;然后通过Lucas-Kanade光流法计算鱼群的运动信息熵,并对获取的纹理特征和信息熵进行归一化处理;最后采用轻量化梯度促进机(LightGBM)对鱼类异常行为进行检测,与深度神经网络(DNN)和支持向量机(SVM)检测效果对比。结果显示:利用LightGBM对鱼类异常行为进行检测,准确率为98.5%,与其他模型对比分别提高0.5%和25.3%。研究表明,基于LightGBM模型的鱼类异常行为检测方法相比其他模型能更准确地识别鱼类非正常游动。该模型适用于自动水质监测。     

A modified YOLOv3 model for fish detection based on MobileNetv1 as backbone

This paper proposes a new approach combining YOLOv3 with MobileNetv1 for fish detection in real breeding farm. The feature maps of MobileNet are reselected as per their receptive fields for better fish detection instead of fixed chosen strategy in the original YOLOv3 framework. A set of fish image data acquired in breeding farm is used to evaluate the proposed method. The high accuracy of detection results is achieved to confirm the effectiveness of the proposed method. Furthermore, taking the place of “ImageNet”, a slighter dataset including fish images with 16 species for backbone network pretraining is picked out from “ImageNet” to extract fish features. On this basis, the effect of detection of the model is further improved due to that the extracted features are more closed to fish objects. Therefore, the proposed method is proved to have the capability of providing necessary and accurate number of fish, which will then be used to determine the breeding actions accordingly.     

Comparison of Collagen Distribution and Muscle Structure Between Cultured Amberjack (Seriola dumerili) and Cultured Yellowtail (Seriola quinqueradiata)

ABSTRACT

The collagen distribution in cultured specimens of amberjack and yellowtail were assessed by histochemical observation in relation to the meat texture of the fish. Major structural alteration was observed in the level of pericellular connective tissue of yellowtail that had higher muscle lipid content; these changes are likely to be associated with the large-scale changes in muscle firmness resulting from the weakening of the cellular binding force. However, lipid deposition was limited to the myocommata in amberjack muscle; lipid deposition was not observed in the pericellular connective tissue, which is the likely reason why amberjack maintained firmer meat texture.     

Determination of fat, protein and dry matter content of fish by mid-infrared transmission spectroscopy

A simple, fast and accurate method for making multicomponent analyses of fish meat using mid-infrared (IR) absorption technique is presented. Basically, the method involves dissolving fish meat in an alkaline detergent with a blender, forming a suspension that can be analysed with commercial milk infrared analysers. Various types and concentrations of detergents and two blending times were evaluated. The relative repeatabilities, expressed as the residual standard deviation in relation to the corresponding means, of the method were less than 0-5%, and relative accuracies were less than 2% for fat and total solids and less than 1% for protein. Possible ways to improve the method further are discussed.     

Seasonal variation in flesh quality, comparison between large and small Atlantic salmon (Salmo salar) transferred into seawater as 0+ or 1+ smolts

The aim of this study was to identify the effect of growth, size and season on the flesh quality of Atlantic salmon (Salmo salar). Following smoltification, two groups of size sorted 0+ and 1+ smolts (four treatment groups in all) were measured for body weight and length in January, June and October 2002. The fish were stored on ice for 4 days before filleted and samples taken for flesh colour, fat/dry content, end pH, gaping score and texture shear force. Large fish upon smoltification grew faster during the first year at sea, while smaller fish grew faster during the second year at sea, resulting in similar weight at slaughter. Season showed the main influence on quality, where fish slaughtered in October had harder texture, higher fat content and redder colour compared to previous samples (P < 0.05). There were only minor differences between the fish slaughtered in January and June (P > 0.15). No significant differences (P > 0.05) were detected as an effect of size or smoltification age when effects of season were accounted for in the statistical model. We conclude that the observed variation in quality was an effect of changes in growth with season. We recommend that actions aimed to halter growth prior to slaughter could be an effective control measure to reduce seasonal quality variations.     

不同乳酸菌对发酵草鱼品质的影响

为探明不同乳酸菌对发酵草鱼微生物数量和理化性质的影响,进一步提高发酵鱼制品的品质,实验对草鱼背部肌肉经不同乳酸菌(植物乳杆菌、戊糖片球菌和副干酪乳杆菌)发酵后制品的微生物数量、pH、总酸、水分含量、白度、氨基酸态氮、硫代巴比妥酸和挥发性盐基氮等进行分析,探究不同乳酸菌在草鱼发酵过程中(0～15d)对其品质的影响.结果显...     

Online fat detection and evaluation in modelling digital physiological fish

The accumulation of excess fat in fish might impair the health of fish in aquaculture. This paper introduces an online sequential extreme learning machine (OS‐ELM) into region‐of‐interest (ROI) detection of adipose tissues in fish digitalized by means of magnetic resonance imaging (MRI). Three typical economic fish species, turbot (Scophthalmus maximus L.), large yellow croaker (Pseudosciaena crocea R.) and Japanese seabass (Lateolabrax japonicus), were selected to compose into digital physiological atlas. We manually labelled with ITK‐SNAP discriminating adipose tissue regions as standard references. Then, single‐hidden‐layer feedforward neural networks (SLFNs) were established to deduce the potential mathematical criterion for fat detection via OS‐ELM for each fish species. We further carried out classical adaptive segmentation to extract details in fat location and distribution of adipose tissues. The quantitative correspondence regarding adipose tissues regions, between 3D voxel representation in MRI and chemical measurement in real fish, have been statistically investigated across each species. The experimental results showed that our online fat detection automatically through MRI is consistent with the standard references, and the recognition rate for three fish species could be up to 89.13% ± 5.32%, 91.43% ± 6.68% and 93.08% ± 6.57% on average, with FAR rate 5.35%, 4.05%, 3.39% and FRRs of 5.52%, 4.52% and 3.53% respectively. Those 3D volumes involved in fat region counting keep pace with the real weights of adipose tissues across species, which implies we might utilize 3D voxel counting to quantify fat accumulation in adipose tissues in a species‐dependent manner. The proposed mechanism brings comparative performances for fat detection and evaluation at a much faster speed, which could help high‐throughput insights into fat metabolism process in fish.     

Effects of different heating conditions on the texture and extracts of the meat from each part of the yellowtail Seriola quinqueradiata

Fisheries Science - We investigated the effects of different heating conditions on the texture and extractive compounds of meat derived from each part of the yellowtail Seriola quinqueradiata fish....     

Lipid composition and deposition of cultured yellowtail Seriola quinqueradiata muscle at different anatomical locations in relation to meat texture

ABSTRACT:   The present study was undertaken to assess the lipid composition and deposition in muscle at three anatomical locations in cultured yellowtail and to investigate the effect of lipid composition and deposition on meat texture. Lipid deposition in muscle was studied by histochemical staining of lipid with Sudan dye. Lipid class composition analysis showed that neutral lipids were the main constituents of lipid in cultured yellowtail and accounted primarily for the variation in muscle lipid content with the anatomical location of meat, as well as with season, whereas the polar lipid content remained almost constant. Furthermore, muscle neutral lipid content was correlated negatively with meat breaking strength; however, no correlation was observed between muscle polar lipid content and meat breaking strength. The histochemical study revealed that, in yellowtail muscle, lipid is preferentially deposited in the myosepta and, with increases in muscle lipid content, additional fat is deposited along sparsely distributed thin connective tissue. It was also observed that the greater the lipid deposition in collageneous connective tissue, the lower the meat breaking strength; presumably, higher lipid deposition in the connective tissue resulted in weakening of the muscle structure.     

Performance of Different Types of Commercial Feeds on the Growth of Juvenile Silver Pomfret, Pampus argenteus, under Tank Culture Conditions

The present study was carried out using juveniles of silver pomfret, Pampus argenteus, produced in the hatchery by stripping eggs from spawners collected from the wild during 2004 and 2005 culture period. The experiments carried out during 2004 investigated the efficiency of using salmon feed mixed with cyclopeeze, salmon feed mixed with shrimp meat, salmon feed alone, and shrimp meat alone in the diet using 1 m³ capacity round fiberglass tanks in three replicates for each treatment with flow‐through seawater. The results showed that inclusion of shrimp meat in the diet either with salmon feed or alone give significantly high (P < 0.01) weight gain of up to 1.10 ± 0.06 g/fish/d and significantly lower (P < 0.001) feed conversion ratio compared to that of feeds without shrimp meat. The experiments carried out during 2005 investigated the use of commercially available feeds with feed additives. The results showed that feeding with “Gemma” feed with 54.0% crude protein and 19.0% crude fat or salmon feed with 41.4% crude protein and 23.9% crude fat give significantly high (P < 0.01) growth rates compared to that of pompano feed with 43.0% crude protein and 6.0% crude fat. The results of these investigations although show high growth rate of the fish compared to that of previous observations; there is yet an urgent need to formulate a suitable feed for this fish species for commercial ventures.     

水库网箱和池塘养殖斑点叉尾（鱼回）肌肉营养成分和品质的比较分析

为了了解池塘和水库网箱两种养殖模式下斑点叉尾鮰（Ictalurus punctatus）肌肉营养成分和品质特性,利用生化分析、物性分析方法和电感耦合等离子体原子发射光谱法分别对斑点叉尾鮰肌肉的常规营养成分、系水力、质构特性及肌肉矿物元素含量进行了测定。结果显示,池塘和水库网箱养殖的斑点叉尾鮰含肉率都在65%以上;池塘组的贮存损失和失水率显著低于水库网箱养殖组,而冷冻渗出率显著高于水库网箱养殖组;水库网箱养殖组的粗蛋白、粗灰分含量均显著高于池塘组,而粗脂肪含量显著低于池塘组;两组中矿物元素含量都比较丰富,水库网箱养殖组肌肉中钾、磷、钙、镁、锌、铁六种元素的含量均显著高于池塘组;池塘组肌肉的凝聚性和回复性显著高于水库网箱养殖组,而肌肉硬度、胶黏性和咀嚼性显著低于水库网箱养殖组。研究表明,池塘养殖的斑点叉尾鮰肌肉具有较好的系水力,而水库网箱养殖的斑点叉尾鮰肌肉具有高蛋白低脂肪、矿物元素更丰富、肉质硬度大的特点。     

Strategies and technologies in offshore farming

A more restrictive attitude to inshore farming, in addition to positive biological findings among offshore farmed fish, have increased the demand for suitable offshore fish farming cages/systems.

To develop such a cage/system, the requirements of the fish, the fish farmer, the insurance companies, the authorities and the moorings must be considered. The existing offshore concepts can be classified into: (1) simple flexible one-net bag cages; (2) integrated stiff semi-submersible one-net bag constructions; (3) simple stiff poly-net bag cages; (4) integrated stiff poly-net bag constructions; (5) submersible and submerged cages. An example from each group is described.

The Bridgestone cage and the Farmocean system, the only offshore concepts that have been in commercial use for some years, are compared with respect to strength and management. The other concepts are evaluated in various parts.

A suitable offshore concept should, in general, consist of a stable, strong and safe platform that should be easy and safe to tow, moor and board. It should allow a proper attachment of the net bag (preferably round, 15 m deep and 5000 m³ in volume), and guarantee its strength and shape during all weather conditions. The fish should be fed by means of a computer-controlled automatic feeder.

Faster growth, lowered mortality and reduced visceral fat content are reported among offshore farmed fish compared with those farmed inshore. A lower degree of self-pollution will also be a consequence of moving larger and deeper cages/systems offshore.

The tentative rules for the type approval of floating fish farming units that have been presented by “Det norske Veritas” (DnV) in Norway will be positive for the fish farming business if it starts to be valid and cover the rest of the fish farming countries.

Despite the higher investment required for the offshore cages/systems, it has been indicated that there is a better economic result and that the cost of producing 1 kg of fish is lower than in conventional fish farms.

As the single-net bag concept represents a lower risk for the fish farmer, insurance company and veterinary authority, it will probably be the preferred concept.