Fish Schools Research Articles

Analysis of mono- and multi-cluster flocking for a nonlinear Cucker–Smale model with external force

The Cucker–Smale model describes the dynamics of groups of interacting self-propelled agents. This model is developed to study the collective behavior of groups of living things, such as bird flocks, fish schools, and herds of bacteria colonies. Since this model was introduced, it has been studied from a variety of perspectives, such as consensus, mono-cluster flocking, multi-cluster flocking, pattern formation, collision avoidance, and so on.In this study, we introduce the nonlinear Cucker–Smale model via nonlinear external force and discuss the collective motions of agents in this model from the perspective of consensus, mono-cluster flocking, and multi-cluster flocking. In particular, we present some conditions to derive consensus, mono-cluster flocking, and multi-cluster flocking. These conditions are simpler and more tractable to induce consensus, mono-cluster flocking, and multi-cluster flocking than the conditions presented for the (traditional) Cucker–Smale model. More precisely, this study shows that if p∈(1,3) or q∈(1,3), then the mono-cluster flocking is induced, and DMtCF does not occur in our model. In the case where p≥3 and q≥3, this study proves that only the consensus multi-cluster flocking is induced. Finally, the results of this paper are numerically verified.

Effects of season and diel cycle on hydroacoustic estimates of density, Target Strength, and vertical distribution of fish in Yudong Reservoir, a plateau deep water reservoir in southwest China in a plateau deep

Hydroacoustics is a non-invasive fish stock assessment sampling technique that plays an important role in fishery science and management. However, non-standard hydroacoustic surveys could lead to biased results, and the factor of the sampling period (e.g., season and diel cycle) is extremely critical as it can greatly affect hydroacoustic results. Efforts to improve the accuracy and credibility of the hydroacoustic survey results are getting more and more attention. Thus, we conducted two diel hydroacoustic surveys in situ in summer and winter to detect whether there were diel and seasonal differences in density, Target Strength (TS) and vertical distribution of fish. The results indicated that nighttime had significantly higher fish mean density than daytime in summer and winter. No significant difference between summer and winter daytime, however, significant difference between summer and winter nighttime, but this bias could be accepted from the fisheries management perspective; The mean TS of the summer daytime was significantly higher than that of summer nighttime, winter daytime and winter nighttime, but there were no significant differences among summer nighttime, winter daytime, and winter nighttime, mainly due to mean TS may be overestimated from fish schooling behavior during summer daytime; The fish vertical distribution had significant seasonal correlations and was more dispersed in different water layers during the nighttime, proving that the assessment was better at nighttime than during the daytime. Consequently, the hydroacoustic surveys in Yudong Reservoir and other similar plateau deep water reservoirs should be performed at nighttime, which will yield relatively accurate density and TS, and dispersed vertical distribution of fish.

MENENTUKAN SWIMMING LAYER DAN DISTRIBUSI IKAN PELAGIS DI LAUT FLORES BAGIAN BARAT DENGAN DETEKSI AKUSTIK

The purpose of this study determined the swimming layer and distribution of pelagic fish in the waters west of the Flores Sea through acoustic detection. Experimental fishing is a method used with two data analyses: 1) analysis of acoustic data at sampling stations with stationery techniques; and 2) analysis of acoustic data along transects between stations. The detection results at stationery 1 showed a very low abundance of pelagic fish, distributed at layer 4 (150-200 m) at night and suspected to be a large pelagic type of tuna with a small amount. The detection results on stationery 2 and stationery 3 are relatively the same, showing a relatively higher abundance compared to stationery 1. Detection results for transects between stations 1-2, 2-3, 3-4, and 4-5 starting from Dewakang waters to east of Takarawataya waters did not detect schooling fish but only single fish. On transects between stations 5-6 very low abundance, the highest mean abundance of 0.5 fish/1000 m3 was detected at layer 4 (150-200 m). On transects between stations 6-7 the abundance was not too high, the highest mean abundance was detected at layer 3 of 10.8 fish/1000 m3. The transect between stations 7-8 is the highest abundance of all transects, the highest abundance average value detected at layer 3 is 20.3 fish/1000 m3. On transects between stations 8-9 the abundance was not too high, schooling tended to be present in all layers, and the highest mean abundance was detected at layer 4 of 1.3 fish/1000 m3. The results of the study concluded that the abundance of pelagic fish in the western Flores Sea is distributed in layers 3 and 4 (100-200 m).
 Keywords: Acoustic, distribution, pelagic fish, Flores Sea, layer

Modeling three-dimensional bait ball collective motion.

Collective motion of animal groups such as fish schools and bird flocks in three-dimensional (3D) space are modeled by considering a topological (Voronoi) neighborhood. The tridimensionality of the group is quantified. Apart from the patterns of swarming, schooling, and milling, we identify a 3D bait ball around the phase transition boundary. More significantly, we find that by considering a blind angle in this topology based model, an individual interacts statistically with six to seven neighbors, consistent precisely with the previous field observations of the starling flocks. This model could be expected to enable more insightful investigation on realistic collective motion of shoals or flocks.

Numerical study of the correlation between fish school arrangement and propulsive performance

Numerical study of the correlation between fish school arrangement and propulsive performance

A spatiotemporal attention network-based analysis of golden pompano school feeding behavior in an aquaculture vessel

Behavior analysis and recognition of fish school have substantial management value and optimization implications for many aquaculture activities, such as feeding, which is currently the most expensive and polluting element of the aquaculture process. However, fish school behaviors analysis for complex marine environments is an extremely challenging task. Recent developments in artificial intelligence have demonstrated that Deep-Learning techniques can be ideally adapted for behavior analysis. Seeing such prospects, a spatiotemporal attention network (STAN) was proposed in this study to analyse the feeding states and behaviors of golden pompano school. Specifically, spatial images and optical flow images were created from videos using image processing techniques and the Lucas–Kanade algorithm. STAN was then used to extract intuitive and perceptual features from the intuitive channel and perceptual channel, respectively. Finally, the states of Feeding or Non-Feeding of the golden pompano school were established by the fusing channel with LSTM and Fully–connected networks. To evaluate the performance of the proposed method, quantitative and qualitative experiments were conducted. Results showed that STAN outperformed other models with a test accuracy of 97.97%. Further validation on a genuine golden pompano farming vessel was implemented, showing that the STAN architecture delivers state-of-the-art accuracy in the task of analysing feeding behavior for golden pompano school in aquaculture.

Influence of climate-mediated shifts in wetland vegetation on prey fish habitat use and schooling dynamics

Intertidal wetlands provide vital habitat for numerous species by serving as a basal resource and refuge for shelter-seeking fauna. These environments are particularly important for transient nekton that trophically link marine and terrestrial food webs via migration into the intertidal during the flooding tide. Changes in coastal vegetation due to a warming climate, such as the replacement of temperate saltmarshes with tropical mangroves, may alter habitat use by transient species due to differences in food provisioning and the structural attributes of mangrove and saltmarsh vegetation. In northeast Florida (USA), Fundulus heteroclitus (mummichog) and F. majalis (striped killifish) are abundant, trophically important, transient fishes that may exhibit behavioral changes with coastal habitat shifts. We experimentally manipulated predator presence in a large-scale mesocosm containing an array of 4 habitats found at the mangrove-saltmarsh ecotone: marsh vegetation (smooth cordgrass Spartina alterniflora), 2 species of mangroves (red mangrove Rhizophora mangle and black mangrove Avicennia germinans), and sand, and measured prey fish habitat use and schooling dynamics. Mummichogs utilized black mangrove habitat to the same degree as cordgrass regardless of the presence of a predator, indicating that mummichogs perceive both habitats as providing equivalent protection. Killifish exhibited little affinity for any particular habitat and exhibited schooling behavior over seeking refugia for predator avoidance, suggesting that vegetation changes may have little effect on killifish behavior. Further research on how such patterns of habitat use combined with habitat-specific dietary constituents of fundulids will help to predict how saltmarsh loss at the ecotone will influence nutrient and energy flows in coastal food webs.

Uma dúzia de peixes: algumas espécies exóticas invasoras encontradas em águas brasileiras e seus impactos

Abstract The introduction of invasive alien species (IAS) is among the leading causes of biodiversity loss in the world. The arrival of these species causes several imbalances in the natural environment. The establishment of these species depends on their transport, entry, adaptive success, and interactions in the environment. This work aims to present 12 species of exotic invasive fish that occur in natural environments in Brazil in the form of a booklet and to discuss some aspects inherent to legislation changes related to the cultivation of these species. The target audience of this study is mainly fish farmers, fishermen, riverside dwellers, assistance technicians, schools, environmental departments, and rural communities. The list had as a criterion the selection of species that are raised in fish farming stations and that already have records of occurrence in natural ecosystems in the country. These are exotic species introduced (from other countries) and with high invasive potential in Brazilian continental waters. To compose the list of these species, national and international studies that discuss the subject were sought, the following species being selected: Ctenopharyngodon idella, Hypophthalmichthys molitrix, Hypophthalmichthys nobilis, Cyprinus carpio, Oreochromis niloticus, Coptodon Rendalli, Oreochromis mossambicus, Oreochromis macrochir, Clarias gariepinus, Ictalurus punctatus, Oncorhynchus mykiss, Micropterus salmoides. In addition to presenting the impacts of invasive alien species on native ichthyofauna, this material will help disseminate technical information and may also be an aid to guide public policy decision making and awareness.

Retracted: Classification of Breast Cancer Images by Implementing Improved DCNN with Artificial Fish School Model.

[This retracts the article DOI: 10.1155/2022/6785707.].

Construction cost prediction system based on Random Forest optimized by the Bird Swarm Algorithm.

Predicting construction costs often involves disadvantages, such as low prediction accuracy, poor promotion value and unfavorable efficiency, owing to the complex composition of construction projects, a large number of personnel, long working periods and high levels of uncertainty. To address these concerns, a prediction index system and a prediction model were developed. First, the factors influencing construction cost were first identified, a prediction index system including 14 secondary indexes was constructed and the methods of obtaining data were presented elaborately. A prediction model based on the Random Forest (RF) algorithm was then constructed. Bird Swarm Algorithm (BSA) was used to optimize RF parameters and thereby avoid the effect of the random selection of RF parameters on prediction accuracy. Finally, the engineering data of a construction company in Xinyu, China were selected as a case study. The case study showed that the maximum relative error of the proposed model was only 1.24%, which met the requirements of engineering practice. For the selected cases, the minimum prediction index system that met the requirement of prediction accuracy included 11 secondary indexes. Compared with classical metaheuristic optimization algorithms (Particle Swarm Optimization, Genetic Algorithms, Tabu Search, Simulated Annealing, Ant Colony Optimization, Differential Evolution and Artificial Fish School), BSA could more quickly determine the optimal combination of calculation parameters, on average. Compared with the classical and latest forecasting methods (Back Propagation Neural Network, Support Vector Machines, Stacked Auto-Encoders and Extreme Learning Machine), the proposed model exhibited higher forecasting accuracy and efficiency. The prediction model proposed in this study could better support the prediction of construction cost, and the prediction results provided a basis for optimizing the cost management of construction projects.

Modeling Collective Behavior for Fish School With Deep Q-Networks

Modeling collective behavior is a way to better understand the mechanisms that govern collective animal behaviors. Traditional rule-based modeling methods rely heavily on human prior knowledge and may not provide a proper explanation of the phenomenon of collective behaviors. This paper proposes a Deep Q-Networks (DQN)-based modeling method for fish school. Firstly, an individual’s state (continuous value) is expressed by the angle between its direction and the average direction of its perceived neighbors. An individual’s action is represented with discretized turning angle. Then, the reward function is constructed with the change in the number of neighbors. And finally, the neural network structure is constructed to represent the Q-value function and is trained by the DQN algorithm. The proposed approach is tested in two scenarios: single-learner and multi-learner. Results show that in both scenarios the proposed method can gradually converge and finally obtain a model that can produce collective behavior. On this basis, this paper also deeply analyzes the learned model from the perspectives of average order parameter and collective behavior patterns. It verifies that the behavior pattern generated by the learned model is a highly ordered collective behavior. In addition, we make a comparison between our proposed approach and the Q-Learning algorithm. The results show that our approach not only has a stronger ability to express policy and is better at handling continuous states but also has a more stable learning performance in training.

STUDI TINGKAT KERAMAHAN LINGKUNGAN ALAT TANGKAP PURSE SEINE DI PPI PONTAP KOTA PALOPO

Purse Seine is a fishing gear used to catch fish that have a schooling fish. The purpose of this study is 1) Knowing the composition of the type of fishermen's catch using purse seine fishing gear 2) Knowing the level of environmental friendliness of fishermen's purse seine fishing gear at PPI Pontap Palopo City based on the Code of Conduct for Responsible Fisheries (CCRF). This research was conducted for 1 (one) month, namely in June-July 2022. The methods used in this study are primary and secondary methods. Based on the results of the study; 1) The composition of the type of catch on the purse seine fishing gear at PPI Pontap caught 8 types of fish including male bloating (Rastrelliger kanagurta) with a total weight of 20 trips from 22 ships was 15,111.2 kg, Tembang (Sardinella gibbosa) 10,705.82 kg, Kite deles (Decapterus macrosoma) 9,213.43 kg, Skipjack (Katsuwonus pelamis) 822.9 kg, Selar como (Atule mate) 2,008 kg, Yellow selar (Salaroides leptolepis) 4,230.9 kg, Petek (Secutor indicius) 1,823.9 kg and Gutters (Scomberoides tala) 306.5 kg. So the total overall weight for 20 fishing trips reached 44,223 kg. 2) The level of environmental friendliness of purse seine fishing gear at TPI Pontap is included in the category of very environmentally friendly with a total weight value of 29.

A fellow-following-principle based group model and its application to fish school analysis

Group models based on simple rules are viewed as a bridge to clarifying animal group movements. The more similar a model to real-world observations, the closer it is to the essence of such movements. Inspired by the fish school, this study suggests a principle called fellow-following for group movements. More specifically, a simple-rules-based model was proposed and extended into a set of concrete rules, and two- and three-dimensional group models were established. The model results are intuitively similar to the fish school, and when the group size increases, the milling phase of both the model and fish school tends from unstable to stable. Further, we proposed a novel order parameter and a similarity measurement framework for group structures. The proposed model indicates the intuition similarity, consistency of dynamic characteristics, and static structure similarity with fish schools, which suggests that the principle of fellow-following may reveal the essence of fish school movements. Our work suggests a different approach for the self-organized formation of a swarm robotic system based on local information.

Modeling collective motion for fish schooling via multi-agent reinforcement learning

Complex collective motion patterns can emerge from very simple local interactions among individual agents. However, it is still unclear how and why the interactions among individuals lead to the emergence of collective motion. Modeling is an effective way to understand the mechanisms that govern collective animal motions. In this work, to avoid imposing fixed sets of rules on collective motion models a priori as classical approaches do, we propose a new method of modeling collective motion for fish schooling via multi-agent reinforcement learning. We model each fish individual as an artificial learning agent, whose policy is acquired by using mean field Q-learning (MFQ). The observation of each fish agent is represented as a multi-channel image, where each channel describes a different feature, such as an agent's position or an agent's orientation. The policy of an agent is approximated with a neural network trained with the MFQ algorithm, during which, agents are rewarded (or penalized) according to the number of neighbors and consecutive collisions between individuals. We study the dynamics of collective motion that emerge from the learned policy. The experimental results show that the learned policy can produce collective motion in groups of various sizes. In addition, three different collective motion patterns observed in nature emerged during the training process. The learned policy can help us gain new insight into how and why individual interactions lead to collective motion. This study also demonstrates that multi-agent reinforcement learning has great potential to be a new approach for analysis and modeling of collective motion.

Clusterization of vector and matrix data arrays using the combined evolutionary method of fish schools

The problem of clustering data arrays described in both vector and matrix forms and based on the optimization of data distribution density functions in these arrays is considered. For the optimization of these functions, the algorithm that is a hybrid of Fish School Search, random search, and evolutionary optimization is proposed. This algorithm does not require calculating the optimized function’s derivatives and, in the general case, is designed to find optimums of multiextremal functions of the matrix argument (images). The proposed approach reduces the number of runs of the optimization procedure, finds extrema of complex functions with many extrema, and is simple in numerical implementation.

Spawning Phenology and Early Growth of Japanese Anchovy (Engraulis japonicus) off the Pacific Coast of Japan

The reproduction and early growth of fish are essential elements that affect recruitment and provide breakthrough points for understanding population fluctuations. In this study, larval and juvenile Japanese anchovy (Engraulis japonicus) were collected from five coastal waters off the Pacific coast of Japan in 2020 and 2021 to gain more insight into life history traits such as reproduction and early growth of this species on the basis of otolith microstructure analysis. The spawning period appeared to be related to temperature and chlorophyll-a concentrations, showing latitudinal gradient variation among fishing areas. We detected a significant positive allometric growth pattern between standard length and body weight. The Gompertz model best fits the growth of standard length, showing an initial stage of growth that was quick and accelerating. The mean daily growth rate for standard length was 0.64 ± 0.09 mm per day. A series of mixed-effect models was constructed to investigate the sources of differences in the mean growth rates among individuals. The results revealed regional variability in fish growth, with individuals in the central Pacific stock growing faster. Individuals that grew slower were heavier than those of the same length, indicating a trade-off between length growth and weight growth. The mean growth of individual fish was positively influenced by environmental factors (surface water temperature and chlorophyll-a concentration), and individuals within the same school of fish displayed a striking homogeneity of growth. Our research demonstrates the significance of including both physiological characteristics and environmental influences in early growth studies on fish.

Adaptive clustering of multiextremа data arrays using a modified fish school algorithm

The problem of clustering multiextrema data arrays is considered. To optimize the local extrema search functions, an algorithm is proposed, that is essentially an optimization function of the modified Fish School Search algorithm, random search, and evolutionary optimization.

How swimming style and schooling affect the hydrodynamics of two accelerating wavy hydrofoils

Fish schools can make frequent accelerations that are almost simultaneous. While schooling at constant speed is well studied, far less is known concerning accelerating fish school across various body caudal fin swimming styles. The present study investigates the effects of swimming styles and schooling on two accelerating wavy hydrofoils in a free stream flow at wavelengths λ=0.5−8, Strouhal number St=0.2−0.7, front–back distance D=0,0.25,0.5,0.75, phase difference ϕ/π=0,0.5,1,1.5, and lateral gap distance G=0.25,0.3,0.35 with fixed Reynolds number Re=5000 and maximum amplitude Amax=0.1. In total, 591 cases were simulated using open-source software IBAMR based on immersed boundary method. Low and high wavelengths correspond to advantageous propulsive efficiency and thrust, respectively. The highest group propulsive efficiency is obtained at low wavelength λ<1.2. At a side-by-side arrangement, the thrust upon the two foils can be equivalent across various wavelengths, indicating a synchronised acceleration. At staggered arrangement, the follower can take significant advantage of the leader in locomotion performance by tuning phase difference, especially at high wavelengths and close distances. Front–back distance is a key factor affecting the follower’s propulsive efficiency for short-wavelength swimmers, but not for long-wavelength ones. Various combinations of wavelength and relative distance can lead to distinct flow structures, indicating a tunable stealth capacity of the accelerating fish schools.

Fish school feeding behavior quantification using acoustic signal and improved Swin Transformer

In aquaculture, the real-time quantification of fish feeding behavior is an important basis for feeding decisions. The acoustics produced by fish chewing feed and activities during feeding can be used to quantify feeding behavior. This study proposes an Audio Spectrum Swin Transformer (ASST) model based on an acoustic signal and attention mechanism that can divide the feeding intensity of fish into four grades: strong, medium, weak, and none. The specific implementation methods are: (1) A sliding window was applied to clip the audio and the acoustic. Signals are transformed into spectrograms. (2) The perceptual domain of fish feeding acoustic spectrum recognition task was gradually expanded by adopting the Swin Transformer and utilizing its hierarchical structure. (3) The model's performance for small data sets was further improved by adding SPT, LSA, and enhanced residual connections. (4) A predictive optimization module was designed to correct the feeding strategy according to four feeding levels. The final experimental results demonstrate that the accuracy of the improved ASST network for fish feeding behavior quantification reached 96.16%. It can effectively identify-four fish feeding intensities, allowing on-demand feeding and providing a basis for developing intelligent feeding machines.

Experimentally Determining Optimal Conditions for Mapping Forage Fish with RPAS

RPAS (Remotely piloted aircraft systems, i.e., drones) present an efficient method for mapping schooling coastal forage fish species that have limited distribution and abundance data. However, RPAS imagery acquisition in marine environments is highly dependent on suitable environmental conditions. Additionally, the size, color and depth of forage fish schools will impact their detectability in RPAS imagery. In this study, we identified optimal and suboptimal coastal environmental conditions through a controlled experiment using a model fish school containing four forage fish-like fishing lures. The school was placed at 0.5 m, 1.0 m, 1.5 m, and 2.0 m depths in a wide range of coastal conditions and then we captured RPAS video imagery. The results from a cluster analysis, principal components, and correlation analysis of RPAS data found that the optimal conditions consisted of moderate sun altitudes (20–40°), glassy seas, low winds (&lt;5 km/h), clear skies (&lt;10% cloud cover), and low turbidity. The environmental conditions identified in this study will provide researchers using RPAS with the best criteria for detecting coastal forage fish schools.