Search

Image anomaly detection is a trending research topic in computer vision. The objective is to build models using available normal samples to detect various abnormal images without depending on real abnormal samples. It has high research significance and value for applications in the detection of defects in product appearance, medical image analysis, hyperspectral image processing, and other fields. This paper proposes an image anomaly detection algorithm based on feature distillation and an autoencoder structure, which uses the feature distillation structure of a dual-teacher network to train the encoder, thus suppressing the reconstruction of abnormal regions. This system also introduces an attention mechanism to highlight the detection objects, achieving effective detection of different defects in product appearance. In addition, this paper proposes a method for anomaly evaluation based on patch similarity that calculates the difference between the reconstructed image and the input image according to different regions of the image, thus improving the sensitivity and accuracy of the anomaly score. This paper conducts experiments on several datasets, and the results show that the proposed algorithm has superior performance in image anomaly detection. It achieves 98.8% average AUC on the SMDC-DET dataset and 98.9% average AUC on the MVTec-AD dataset. [ABSTRACT FROM AUTHOR]

Fatigue failure is a typical failure mode of welded structures. It is of great engineering significance to predict the remaining fatigue life of structures after a certain period of service. In this paper, a two-stage hybrid deep learning approach is proposed only using the response of structures under fatigue loading to predict the remaining fatigue life. In the first stage, a combination of convolutional neural network (CNN), squeeze-and-excitation (SE) block, and long short-term memory (LSTM) network is employed to calculate health indicator values based on the current measured data sequence. In the second stage, a particle filtering-based algorithm is utilized to predict the remaining fatigue life using the previously calculated health indicators. Experimental results on different welded specimens under the same loading conditions demonstrate that the hybrid deep learning approach achieves superior prediction accuracy and generalization ability compared to CNN, LSTM, or CNN-LSTM models in the first stage. Moreover, the average relative deviation between the predicted and actual fatigue life is less than 6% during the final quarter of the crack propagation and fracture stage. [ABSTRACT FROM AUTHOR]

This study investigated the time-optimal low-thrust interplanetary transfer problem, and proposes a fast estimation method for guessing the initial costate and optimal transfer time based on a surrogate model, and applied it to the problem of the 11th Global Trajectory Optimization Competition (GTOC 11). Two core methods are proposed in this paper: (1) a fast generation method called the neighbor point iteration algorithm (NPIA) is presented for rapidly generating low-thrust databases with high efficiency and accuracy; and (2) deep neural networks (DNNs) are adopted to learn the state–costate pairs of low-thrust databases, and the surrogate network can quickly estimate the initial costate and optimal transfer time of the low-thrust interplanetary problem. Experiments verified the proposed method and investigated the influence of network structure, learning rate, and loss function on the accuracy of network estimation. The effects of database generation and network estimation were compared based on three transfer scenarios: coplanar, non-coplanar, and arbitrary orbital transfer. In addition, the application case study showed that the proposed method can quickly obtain the time-optimal low-thrust solution to GTOC 11's interplanetary transfer, which achieves high precision and meets the terminal constraints. [ABSTRACT FROM AUTHOR]

An eight-week feeding trail was carried out to investigate the impacts of different dietary arachidonic acid (ARA) supplementations on growth performance, antioxidant capacity, tissue fatty acid profiles, and lipid metabolism of mud crab (Scylla paramamosain) juvenile. Six isonitrogenous (480 g kg-1 crude protein) and isolipidic (80 g kg-1 crude lipid) diets were formulated to contain 0.40, 2.50, 4.60, 8.90, 12.50, and 15.70 g ARA kg-1 (dry matter), respectively. Each experimental treatment included 24 mud crab juveniles (initial weight 11.29 ± 0.09 g) and was assigned to triplicate groups (n = 3). Crabs fed diets with 2.50, 4.60, and 8.90 g kg-1 ARA presented significantly higher percent weight gain (PWG) and specific growth rate (SGR) than those fed the other diets. Based on two-slope broken-line and quadratic curve regression analysis of PWG against dietary ARA levels, optimal dietary ARA levels were determined to be 5.20 g kg-1 and 6.20 g kg-1, respectively. Crabs fed with 4.60 g kg-1 ARA diet showed the lowest activities of alanine aminotransferase (ALT) as well as aspartate aminotransferase (AST) in hemolymph among all treatments. In hemolymph and hepatopancreas, total antioxidant capacity (T-AOC), the activities of total superoxide dismutase (T-SOD), and glutathione peroxidase (GSH-Px) as well as the contents of reduced glutathione (GSH) rose first and then dropped with the increase of dietary ARA levels, while the concentration of malondialdehyde (MDA) showed an opposite trend. Tissue fatty acid profiles reflected diets fatty acid compositions. The ARA contents in hepatopancreas and muscle significantly increased with the increase of dietary ARA levels. Furthermore, the areas of blasenzellen (B) cells and restzellen (R) cells were significantly downregulated with the increase of dietary ARA levels. Crabs fed with 0.40 g kg-1 ARA diet showed significantly higher gene expression levels of fatty acid synthase (fas) as well as acetyl-CoA carboxylase (acc) among all treatments. Relative gene expression levels of 6-phosphogluconate dehydrogenase (6pgd) as well as glucose-6-phosphate dehydrogenase (g6pd) have been significantly upregulated in 0.40 and 2.50 g kg-1 ARA groups. Relative gene expression level of fatty acid binding protein 1 (fabp1) significantly increased in 4.60, 8.90, 12.50, and 15.70 g kg-1 ARA groups. However, the gene expression levels of fatty acid binding protein 4 (fabp4) as well as scavenger receptor class 2 (srb2) have not been influenced by dietary ARA levels. What is more, crabs fed diets with 4.60, 8.90, 12.50, and 15.70 g kg-1 ARA had a significantly higher expression level of carnitine palmitoyltransferase 1 (cpt1) than those fed diets with 0.40 and 2.50 g kg-1 ARA. In summary, optimum dietary ARA can promote growth, enhance antioxidant capacity, and improve health of mud crab juveniles. It also demonstrated that lipogenesis has been restrained with the increasing dietary ARA levels. These findings could provide theoretical guidance and reference for the lipid nutrition research as well as the development of the commercial diet in mud crab. [ABSTRACT FROM AUTHOR]

An 8-week feeding trial was carried out to assess the effect of dietary krill meal on growth performance and expression of genes related to TOR pathway and antioxidation of swimming crab (Portunus trituberculatus). Four experimental diets (45% crude protein and 9% crude lipid) were formulated to obtain different replacements of fish meal (FM) with krill meal (KM); FM was replaced with KM at 0% (KM0), 10% (KM10), 20% (KM20), and 30% (KM30); fluorine concentration in diets were analyzed to be 27.16, 94.06, 153.81, and 265.30 mg kg-1, respectively. Each diet was randomly divided into 3 replicates; ten swimming crabs were stocked in each replicate (initial weight, 5.62 ± 0.19 g). The results indicated that crabs fed with the KM10 diet had the highest final weight, percent weight gain (PWG), and specific growth rate (SGR) among all treatments (P < 0.05). Crabs fed with the KM0 diet had the lowest activities of total antioxidant capacity (T-AOC), total superoxide dismutase (SOD), glutathione (GSH), and hydroxyl radical scavenging activity and had the highest concentration of malondialdehyde (MDA) in the hemolymph and the hepatopancreas (P < 0.05). In the hepatopancreas, the highest content of 20:5n-3 (EPA) and the lowest content of 22:6n-3 (DHA) were shown in crabs fed with the KM30 diet among all treatments (P < 0.05). With the substitution level of FM with KM gradually increasing from 0% to 30%, the color of the hepatopancreas changed from pale white to red. Expression of tor, akt, s6k1, and s6 in the hepatopancreas was significantly upregulated, while 4e-bp1, eif4e1a, eif4e2, and eif4e3 were downregulated with dietary replacement of FM with KM increasing from 0% to 30% (P < 0.05). Crabs fed with the KM20 diet had notably higher expression of cat, gpx, cMnsod, and prx than those fed with the KM0 diet (P < 0.05). Results demonstrated that 10% replacement of FM with KM can promote growth performance and antioxidant capacity and notably upregulate the mRNA levels of genes related to TOR pathway and antioxidant of swimming crab. [ABSTRACT FROM AUTHOR]

Carbohydrate is the cheapest source of energy among the three major nutrient groups, an appropriate amount of carbohydrates can reduce feed cost and improve growth performance, but carnivorous aquatic animals cannot effectively utilize carbohydrates. The objectives of the present study are aimed at exploring the effects of dietary corn starch levels on glucose loading capacity, insulin-mediated glycemic responses, and glucose homeostasis for Portunus trituberculatus. After two weeks of feeding trial, swimming crabs were starved and sampled at 0, 1, 2, 3, 4, 5, 6, 12, and 24 hours, respectively. The results indicated that crabs fed diet with 0% corn starch exhibited lower glucose concentration in hemolymph than those fed with the other diets, and glucose concentration in hemolymph remained low with the extension of sampling time. The glucose concentration in hemolymph of crabs fed with 6% and 12% corn starch diets reached the peak after 2 hours of feeding; however, the glucose concentration in hemolymph of crabs fed with 24% corn starch attained the highest value after 3 hours of feeding, and the hyperglycemia lasted for 3 hours and decreased rapidly after 6 hours of feeding. Enzyme activities in hemolymph related to glucose metabolism such as pyruvate kinase (PK), glucokinase (GK), and phosphoenolpyruvate carboxykinase (PEPCK) were significantly influenced by dietary corn starch levels and sampling time. Glycogen content in hepatopancreas of crabs fed with 6% and 12% corn starch first increased and then decreased; however, the glycogen content in hepatopancreas of crabs fed with 24% corn starch significantly increased with the prolongation of feeding time. In the 24% corn starch diet, insulin-like peptide (ILP) in hemolymph reached a peak after 1 hour of feeding and then significantly decreased, whereas crustacean hyperglycemia hormone (CHH) was not significantly influenced by dietary corn starch levels and sampling time. ATP content in hepatopancreas peaked at 1 h after feeding and then decreased significantly in different corn starch feeding groups, while the opposite trend was observed in NADH. The activities of mitochondrial respiratory chain complexes I, II, III, and V of crabs fed with different corn starch diets significantly increased first and then decreased. In addition, relative expressions of genes related to glycolysis, gluconeogenesis, glucose transport, glycogen synthesis, insulin signaling pathway, and energy metabolism were significantly affected by dietary corn starch levels and sampling time. In conclusion, the results of the present study reveal glucose metabolic responses were regulated by different corn starch levels at different time points and play an important role in clearing glucose through increased activity of insulin, glycolysis, and glycogenesis, along with gluconeogenesis suppression. [ABSTRACT FROM AUTHOR]

This paper focuses on an operation optimisation problem for a class of multi-head surface mounting machines in printed circuit board assembly lines. The problem involves five interrelated sub-problems: assigning nozzle types as well as components to heads, assigning feeders to slots and determining component pickup and placement sequences. According to the depth of making decisions, the sub-problems are first classified into two layers. Based on the classification, a two-stage mixed-integer linear programming (MILP) is developed to describe it and a two-stage problem-solving frame with a hybrid evolutionary algorithm (HEA) is proposed. In the first stage, a constructive heuristic is developed to determine the set of nozzle types assigned to each head and the total number of assembly cycles; in the second stage, constructive heuristics, an evolutionary algorithm with two evolutionary operators and a tabu search (TS) with multiple neighbourhoods are combined to solve all the sub-problems simultaneously, where the results obtained in the first stage are taken as constraints. Computational experiments show that the HEA can obtain good near-optimal solutions for small size instances when compared with an optimal solver, Cplex, and can provide better results when compared with a TS and an EA for actual instances. [ABSTRACT FROM PUBLISHER]

This experiment was conducted to evaluate the effects of different carbohydrate levels on the growth performance, glycogen accumulation in tissue, enzyme activities, and expression levels of genes related to hepatopancreatic glucose and lipid metabolism and insulin signaling pathway in swimming crab, Portunus trituberculatus for 8 weeks. The results indicated that crabs fed with the 60.0 g kg-1 carbohydrate diet exhibited the highest final body weight (FBW), percent weight gain (PWG), and specific growth rate (SGR) among all treatments. FBW, PWG, and SGR significantly decreased when dietary carbohydrate levels exceeded 240.0 g kg-1. Light microscopy results showed that dietary excessive carbohydrate levels will lead to vacuole, hepatopancreatic tubule lysis, and lipid droplets in hepatopancreas. Expression levels of genes involved into glucose transport, glucose and lipid metabolism, and insulin-like metabolism in the hepatopancreas were significantly influenced by dietary carbohydrate levels. In general, the results of present study demonstrated that dietary optimal carbohydrate levels could not only improve PWG and SGR but also influence the expression of genes involved in glucose, lipid, and insulin-like metabolism. The optimal actual carbohydrate level was estimated to be 87.8-98.4 g kg-1 based on broken-line and second-order polynomial regression analysis between PWG against dietary carbohydrate levels for juvenile Portunus trituberculatus. [ABSTRACT FROM AUTHOR]

An 8‐week feeding trial was conducted to investigate the effects of DL‐methionyl‐DL‐methionine (Met‐Met) supplementation in different fishmeal levels on growth performance, antioxidant and immune response of juvenile Pacific white shrimp, Litopenaeus vannamei. Eight isonitrogenous and isolipidic experimental diets were formulated to meet the nutrient requirements of Pacific white shrimp. The supplemental amount of fishmeal in diets without essential amino acid supplementation are 200 g/kg (F20), 100 g/kg (F10), 50 g/kg (F5) and 0 g/kg (F0), and with essential amino acid supplementation are 200 g/kg (M20), 100 g/kg (M10) 50 g/kg (M5) and 0 g/kg (M0) respectively. The results indicated that shrimp fed the F5 and F0 diets had significantly lower final body weight (FBW), per cent weight gain (PWG), specific growth rate (SGR) and higher feed conversion ratio (FCR) compared with those fed the F20 diet (p <.05). Glucose (GLU), triacylglycerol (TG) and cholesterol (CHO) concentration in haemolymph significantly decreased with fishmeal supplementation decreasing from 200 g/kg to 0 g/kg (p <.05). Met‐Met supplementation in low fishmeal diets significantly reduced the content of malondialdehyde (MDA), increased the activities of acid phosphatase (ACP) and lysozyme (LZM) in hepatopancreas, as well as increasing the activity of total antioxidant capacity (T‐AOC) in haemolymph (p <.05). Meanwhile, shrimp fed M5 and M0 diets had significant upregulation of gene expression of acp, lzm (immune‐related), RagC and s6k (TOR signalling pathway‑related) in hepatopancreas (p <.05). In conclusion, the present study demonstrated that dietary Met‐Met supplementation could improve the growth performance and the abilities of antioxidant and non‐specific immunity of Pacific white shrimp by reducing MDA concentration, increasing T‐AOC, ACP and LZM activities, and upregulating gene expression level of immune (acp and lzm) and TOR signalling pathway (RagC, and s6k). Moreover, Pacific white shrimp fed low fishmeal diets had the positive response of well‐balanced amino acid, and the results will provide further insight into the possibility of reducing fishmeal content in the commercial feed of shrimp. [ABSTRACT FROM AUTHOR]

In the integrated circuit (IC) packaging, the surface defect detection of flexible printed circuit boards (FPCBs) is important to control the quality of IC. Although various computer vision (CV)-based object detection frameworks have been widely used in industrial surface defect detection scenarios, FPCB surface defect detection is still challenging due to non-salient defects and the similarities between diverse defects on FPCBs. To solve this problem, a decoupled two-stage object detection framework based on convolutional neural networks (CNNs) is proposed, wherein the localization task and the classification task are decoupled through two specific modules. Specifically, to effectively locate non-salient defects, a multi-hierarchical aggregation (MHA) block is proposed as a location feature (LF) enhancement module in the defect localization task. Meanwhile, to accurately classify similar defects, a locally non-local (LNL) block is presented as a SEF enhancement module in the defect classification task. What is more, an FPCB surface defect detection dataset (FPCB-DET) is built with corresponding defect category and defect location annotations. Evaluated on the FPCB-DET, the proposed framework achieves state-of-the-art (SOTA) accuracy to 94.15% mean average precision (mAP) compared with the existing surface defect detection networks. Soon, source code and dataset will be available at https://github.com/SCUTyzy/decoupled-two-stage-framework. [ABSTRACT FROM AUTHOR]

An 8-week feeding trial was conducted to evaluate the effects of dietary n-3 LC-PUFA levels on growth performance, tissue fatty acid profiles and relative expression of genes involved in the lipid metabolism of mud crab (Scylla paramamosain). Ten isonitrogenous diets were formulated to contain five n-3 LC-PUFA levels at 7 and 12 % dietary lipid levels. The highest weight gain and specific growth rate were observed in crabs fed the diets with 19·8 and 13·2 mg/g n-3 LC-PUFA at 7 and 12 % lipid, respectively. Moisture and lipid contents in hepatopancreas and muscle were significantly influenced by dietary n-3 LC-PUFA at the two lipid levels. The DHA, EPA, n-3 LC-PUFA contents and n-3:n-6 PUFA ratio in hepatopancreas and muscle significantly increased as dietary n-3 LC-PUFA levels increased at both lipid levels. The expression levels of -6 fatty acyl desaturase and acyl-CoA oxidase in hepatopancreas increased significantly, and expression levels of fatty acid synthase, carnitine palmitoyltransferase I and hormone-sensitive TAG lipase were down-regulated, with increased dietary n-3 LC-PUFA regardless of lipid level. Based on weight gain, n-3 LC-PUFA requirements of S. paramamosain were estimated to be 20·1 and 12·7 mg/g of diet at 7 and 12 % dietary lipid, respectively. Overall, dietary lipid level influenced lipid metabolism, and purified, high-lipid diets rich in palmitic acid reduced the n-3 LC-PUFA requirement of juvenile mud crab. [ABSTRACT FROM AUTHOR]

The sterol regulatory element-binding proteins (SREBPs) are a family of transcription factors known to activate the transcription of genes encoding key lipogenic enzymes. The present study reports on the molecular cloning, tissue expression and nutritional regulation of SREBP-1 from the swimming crab Portunus trituberculatus (Miers, 1876). The SREBP-1 full-length cDNA was 3785 bp, encoding a polypeptide of 1039 amino acids. Quantitative PCR analysis revealed that SREBP-1 expression was detected in various tissues, and the significantly higher expression levels were found in eyestalk and hepatopancreas compared with other tested tissues. Additionally, the effects of dietary iron on expression of SREBP-1 were investigated, and the results indicated that SREBP-1 expressions were down-regulated by crabs fed diets containing 218.9 and 373.9 mg/kg iron compared with that fed the basal diet (55.2 mg/kg). Suggesting that the relative expression level of SREBP-1 can be suppressed by dietary iron supplementation. These findings provide further insight into the regulatory capacity of SREBP-1 in the lipid anabolism of P. trituberculatus. Résumé: Les SREBPs (protéines de liaison à l'élément de régulation des stérols) sont une famille de facteurs de transcription connus pour activer la transcription de gènes codant des enzymes lipogéniques. Cette étude présente le clonage moléculaire, l'expression des tissus et la régulation de la nutrition de SREBP-1 du crabe Portunus trituberculatus (Miers, 1876). La longueur totale de l'ADNc de SREBP-1 est de 3785 pb, codant un polypeptide de 1039 acides aminés. Une analyse par PCR quantitative révèle que l'expression de SREBP-1 a été détectée dans différents tissus, et que l'expression significativement la plus élevée a été trouvée dans le pédoncule oculaire et l'hépatopancréas par comparaison aux autres tissus testés. De plus, les effets du fer alimentaire sur l'expression de SREBP-1 a été examiné, et les résultats indiquent que, par comparaison avec un régime de base (55,2 mg kg−1 de fer), les expressions de SREBP-1 ont été régulées à la baisse chez les crabes nourris avec un régime contenant 218,9 et 373,9 mg kg−1 de fer. Ce qui laisse supposer que le niveau d'expression relatif de SREBP-1 peut être réprimé par une supplémentation en fer alimentaire. Ces résultats fournissent plus d'information sur la capacité régulatrice de SREBP-1 dans le metabolisme lipidique de P. trituberculatus. [ABSTRACT FROM AUTHOR]

This paper deals with a scheduling optimisation problem arising in printed circuit board (PCB) assembly. In one class of PCB assembly, light-emitting diodes are to be assembled into the placement locations on PCBs by a machine with multiple pick-and-place heads. The scheduling optimisation problem is to determine the assembly sequence of placement locations and the assignment of pick-and-place heads for locations so as to minimise the assembly time. We formulate it as a mixed integer linear programming model. To solve the problem efficiently, we classify the PCBs into two types. For the first type of PCBs, on which the locations are linearly arranged, a constructive heuristic is proposed based on the analysis of the best next location after a location is assembled. For the second type of PCBs, on which the locations are circularly arranged, a heuristic based on clustering strategy and path relinking method is proposed. Computational experiments show that the solutions obtained by the two heuristics make 2.32 and 6.82% improvements averagely for the PCBs with linearly and circularly arranged locations, respectively, as compared to the solutions used in real production, and they are also better than those obtained by a hybrid genetic algorithm. [ABSTRACT FROM AUTHOR]

The aim of the present study was to investigate the effects of dietary Zn level on growth performance, Zn bioaccumulation, antioxidant capacity and innate immunity in juvenile mud crabs (Scylla paramamosain). Six semi-purified diets were formulated to contain dietary Zn levels of 44·5, 56·9, 68·5, 97·3, 155·6 or 254·7 mg/kg. Dietary Zn level significantly influenced percentage weight gain (PWG), with the highest observed in crabs fed the diet containing 97·3 mg/kg Zn. Tissue Zn concentrations significantly increased as dietary Zn levels increased from 44·5 to 254·7 mg/kg. Retention of Zn in hepatopancreas increased with dietary Zn levels up to 68·5 mg/kg and then significantly decreased. Moreover, inadequate dietary Zn (44·5 and 56·9 mg/kg) reduced antioxidation markers including total superoxide dismutase (SOD) and Cu/Zn SOD activities and total antioxidant level. Crabs fed the diet with 44·5 mg/kg Zn also showed significantly lower expression of genes involved in antioxidant status, such as Cu/Zn SOD, glutathione peroxidase, catalase and thioredoxin than those fed diets containing 68·5 and 97·3 mg/kg Zn. The highest activities of phenoloxidase and alkaline phosphatase were recorded in crabs fed the diets containing 68·5 and 97·3 mg/kg Zn. Expression levels of prophenoloxidase and toll-like receptor 2 were higher in crabs fed the 97·3 mg/kg Zn diet compared with crabs fed the other diets. Based on PWG alone, the optimal dietary Zn level was estimated to be 82·9 mg/kg, with 68·5 to 97·3 mg/kg recommended for maintaining optimal Zn bioaccumulation, oxidation resistance and innate immune response of juvenile mud crabs. [ABSTRACT FROM AUTHOR]

This paper considers a slab reallocation problem arising from operations planning in the steel industry. The problem involves reallocating steel slabs to customer orders to improve the utilisation of slabs and the level of customer satisfaction. It can be viewed as an extension of a multiple knapsack problem. We firstly formulate the problem as an integer nonlinear programming (INLP) model. With variable replacement, the INLP model is then transformed into a mixed integer linear programming (MILP) model, which can be solved to optimality by MILP optimisers for very small instances. To obtain satisfactory solutions efficiently for practical-sized instances, a heuristic algorithm based on tabu search (TS) is proposed. The algorithm employs multiple neighbourhoods including swap, insertion and ejection chain in local search, and adopts solution space decomposition to speed up computation. In the ejection chain neighbourhood, a new and more effective search method is also proposed to take advantage of the structural properties of the problem. Computational experiments on real data from an advanced iron and steel company in China show that the algorithm generates very good results within a short time. Based on the model and solution approach, a decision support system has been developed and implemented in the company. [ABSTRACT FROM PUBLISHER]

An 8‐week feeding trial was conducted to evaluate the effects of replacement of fish oil (FO) with blending vegetable oils (VOs) on growth performance, antioxidant enzyme activities and fatty acid composition in tissue of swimming crab Portunustrituberculatus. Five isonitrogenous and isolipidic diets were formulated to contain VOs (colza oil: palm oil: linseed oil = 4:2:1) to replace 0 (the control diet), 250, 500, 750 and 1000 g/kg of FO (defined D0, D25, D50, D75, D100). Three hundred juvenile swimming crabs (initial weight 2.34 ± 0.08 g) were randomly stocked and sorted into 300 individual rectangle plastic baskets in three cement pools. Each treatment has three replicates, one replicate has 20 swimming crabs, and each diet fed 60 crabs distributed in 60 baskets. The results indicated that crabs fed the control diet showed significantly higher survival, final body weight, per cent weight gain (PWG), specific growth rate and moulting frequency, crude protein and crude lipid contents in muscles than those fed the D75 and D100 VO diets (p <.05). Crabs fed the D25 VO diet showed significantly higher concentration of triglyceride, low‐density lipoprotein cholesterol and total protein, activities of superoxide dismutase, catalase and glutathione peroxidase (GSH‐Px) in haemolymph than those fed the control diet (p <.05). Fatty acid composition in hepatopancreas was positively correlated with dietary composition. In summary, based on the PWG, the optimal replacement of FO with VOs was estimated to be 250 g/kg. These findings demonstrated that swimming crabs make better use of FO than VOs. [ABSTRACT FROM AUTHOR]

Support vector machine (SVM) is a powerful technique in pattern classification, but its performance is highly dependent on its parameters. In this paper, a new SVM optimized by a novel differential evolution (DE) with a hybrid parameter setting strategy and a population size adaptation method is proposed and simplified as FDE-PS-SVM. In the hybrid parameter setting strategy, the SVM parameter offspring are generated by DE operators with evolutionary parameters that are fixed or with the ones generated by fuzzy logic inference (FLI) according to a given probability. In the population size adaptation method, the population size is shrunk gradually during the search, which tries to balance the diversity and concentration ability of the algorithm to find better SVM parameters. Some benchmark data sets are used to evaluate the proposed algorithm. Experimental results show that the two proposed strategies are effective to search for better SVM parameters while the proposed FDE-PS-SVM algorithm outperforms other algorithms published in other literature. [ABSTRACT FROM AUTHOR]

An 8-week feeding trial was conducted to evaluate the effects of dietary xylanase supplementation on growth performance, digestive enzyme activity, intestinal morphology parameter, intestinal microbiome diversity, and carbohydrate metabolism for juvenile large yellow croaker (Larimichthys crocea). Four levels of xylanase were added to basal diets (0, 600, 1200, and 1800 U kg−1). The results indicated that fish fed the 1200 U kg−1 xylanase diet had higher weight gain than those fed the 0 and 600 U kg−1 xylanase diet. The highest intestinal folds and microvillous height were observed at fish fed the 1200 U kg−1 xylanase diet. High-throughput sequencing revealed that the majority of reads derived from the large yellow croaker digesta belonged to members of Proteobacteria followed by Chloroflex, Bacteroidetes, Spirochaetae, and Firmicute. Supplementation of xylanase in diets increased the relative abundance of Bacteroides and Gemmatimonadete. The higher hepatic glucokinase (GK) and glucose-6-phosphate dehydrogenase (G6PD) activities were observed in fish fed the xylanase supplementation diet. Accordingly, dietary xylanase supplementation upgraded the relative expressions of gk and g6pd genes in liver. In conclusion, optimum dietary xylanase supplementation (600-1200 U kg−1) could improve the growth performance, optimize the intestinal morphology structure and microbiota constitution, and enhance the ability of carbohydrate utilization of juvenile large yellow croaker. [ABSTRACT FROM AUTHOR]

In advanced integrated circuit packing, a very important substrate is high-density flexible printed circuit (FPC) board, which is small and foldable. The detection of the circular holes on FPCs’ surfaces through machine vision is very useful to identify root causes in FPC manufacturing process. However, it is a challenge as FPC images always contain many high details. This paper proposes a circle detection method with a modified tri-class thresholding-based contour extraction to detect and measure the circular holes on FPCs’ surfaces. It first extracts object contours by using a modified tri-class thresholding and then uses two circle validation criterions to eliminate noncircles: one is based on geometrical features and the other is based on the Helmholtz principle. Moreover, an iterative circle parameter refinement strategy is proposed. Experiments are carried out on 120 FPC images and the results indicate that the modified tri-class thresholding-based contour extraction method is more efficient than Canny detector, and the proposed circle detection method shows a better performance in terms of false detection rate, computation cost, and robustness than three other popular algorithms for detecting the circles in FPC images. [ABSTRACT FROM AUTHOR]

An 8‐week feeding trial was conducted to evaluate the effects of dietary lipid sources on growth performance, antioxidant enzyme activities and biochemical composition of juvenile swimming crab Portunus trituberculatus of initial weight 2.34 ± 0.08 g. Four different diets were formulated to contain fish oil (FO), soybean oil (SO), linseed oil (LO) or palm oil (PO). The highest final body weight, weight gain, specific growth rate and molting frequency were observed in crabs fed the FO diet. Crabs fed the SO diet showed higher glutathione peroxidase, superoxide dismutase (SOD) and catalase (CAT) activities in both serum and hepatopancreas than those fed the FO diet. The lowest malondialdehyde concentration in hepatopancreas and serum were occurred at crabs fed the SO diet. Crabs fed the LO diet had significantly higher SOD and CAT activities in hepatopancreas compared with those fed the FO diet. Crabs fed the PO diet had the highest activities of fatty acid synthase and carnitine palmitoyltransferase 1 activities in hepatopancreas among all treatments. Fatty acid compositions both in hepatopancreas and muscle reflected those of diets. Overall, these findings demonstrated that physiological–biochemical characteristics and lipid metabolism were significantly regulated by different dietary lipid sources. Moreover, dietary SO and LO supplementation could improve antioxidant ability. [ABSTRACT FROM AUTHOR]

Squid visceral paste is a popular attractant and feeding stimulator supplement in shrimp feeds in China, but it often faces problems with fluctuating availability, cost, composition, and quality. An 8‐week experiment was performed to test a proprietary palatability enhancer as an alternative to squid paste in white shrimp feed. Seven diets were tested: a control diet with no supplementations; S1 and S3 diets supplemented with squid paste at 1 or 3%, respectively; S1+PE0.1 and S1+PE0.15 supplemented with both 1% squid paste and the palatability enhancer at either 0.1 or 0.15%, respectively; and finally PE0.1 and PE0.15 supplemented only with the palatability enhancer at 0.1 or 0.15%, respectively. The results showed a trend for increased feed intake and weight gain when squid paste was added to the diet compared to the control, but this was worsened by raising the inclusion level from 1 to 3%. The inclusion of the PE, in combination with squid paste or alone at 0.15%, led to a significantly higher growth, and a feeding stimulation effect was also indicated, with PE0.1 and PE0.15 having a higher feed intake than the control. A further beneficial effect was a significant increase in protease activity in the hepatopancreas in the S1+PE0.15, PE0.1, and PE0.15 treatments compared to the control. In addition, a significant increase in the height of the intestinal mucosal folds was observed in PE0.15, followed by PE0.1. The results demonstrated the potential to replace or reduce squid visceral paste in shrimp diets by supplementing with a PE with functional effects beyond feeding stimulation. [ABSTRACT FROM AUTHOR]

This paper is mainly devoted to a monotonically convergent iterative learning control (ILC) design for a class of uncertain discrete-time switched systems with state delay (UDTSDSs). By taking advantage of output error and state information, a hybrid ILC law for a class of UDTSDSs is proposed. After the ILC process is transformed into a 2D system, sufficient conditions in terms of linear matrix inequalities (LMIs) are derived by using a multiple Lyapunov–Krasovskii-like functional approach and a quadratic performance function. It is shown that if certain LMIs are met, the tracking error 2-norm converges monotonically to zero along the iteration direction, while the learning gains could be determined directly by solving the LMIs. The simulation results are provided to illustrate the theoretical analysis. [ABSTRACT FROM AUTHOR]