Spatial–Temporal Distribution of the Euphausiid Euphausia pacifica and Fish Schools in the Coastal Southwestern East Sea

The spatial and temporal distribution of euphausiid Euphausia pacifica and fish schools were observed along acoustic transects in the coastal southwestern East Sea. Two-frequency (38- and 120-kHz) acoustic backscatter data were examined from April to July 2010. A dB identification window (SV120–38) and school detection algorithm identified E. pacifica and fish schools in the acoustic backscatter, respectively. The E. pacifica was regularly observed in middle of southern waters, where phytoplankton was abundant during spring, and irregularly during summer, when phytoplankton was homogeneously distributed. Using the distorted-wave Born approximation model, the acoustic density of E. pacifica calculated was higher in spring (April: 75.9 mg m−2, May: 85.3 mg m−2) than in summer (June: 71.4 mg m−2, July: 54.1 mg m−2). The fish schools in the acoustic data tended to significantly increase from spring to summer. Although major fish species, such as anchovies and herring, fed on copepods and euphausiids in the survey area, the temporal and spatial distribution of E. pacifica was weakly correlated with the distribution of the fish schools. These findings aid in our understanding of the temporal and spatial distribution dynamics of euphausiids and fish schools in the food web of the coastal southwestern East Sea.

Seasonal variation in fish school spatial distribution and abundance under the Kuroshio regular pattern and the large meander in Suzu coastal waters

The Kuroshio Current can take two paths; usually it follows the regular pattern but occasionally it follows a pattern known as the large meander. In this study, we investigated the abundance of fish that migrate to coastal waters and the spatial distribution of fish schools under both Kuroshio patterns in Suzu district, Kochi prefecture, where the set net is the main fishery industry. We clarified the seasonal variation in the density and distribution of fish schools using a quantitative echo sounder. The effects of the Kuroshio large meander (LM) depended on the season. There was no effect of current pattern in summer or autumn, but in winter and spring the LM altered the marine environment and fish distributions. Cold water masses were formed in the survey area during winter and spring during the LM, and the water temperature dropped significantly compared with during the Kuroshio non-large meander (NLM). This altered the fish species and the distribution of fish schools in the survey area. The catches of Japanese horse mackerels (Trachurus japonicus) and Yellowtails (Seriola quinqueradiata) were much higher during the LM compared with those during the NLM. Unlike these two species, the small-sized pelagic fishes in spring has decreased significantly during the LM.

Using Predicted Patterns of 3D Prey Distribution to Map King Penguin Foraging Habitat

King penguins (Aptenodytes patagonicus) are an iconic Southern Ocean species, but the prey distributions that underpin their at-sea foraging tracks and diving behaviour remain unclear. We conducted simultaneous acoustic surveys off South Georgia and tracking of king penguins breeding ashore there in Austral summer 2017 to gain insight into habitat use and foraging behaviour. Acoustic surveys revealed ubiquitous deep scattering layers (DSLs; acoustically detected layers of fish and other micronekton that inhabit the mesopelagic zone) at c. 500 m and shallower ephemeral fish schools. Based on DNA extracted from penguin faecal samples, these schools were likely comprised of lanternfish (an important component of king penguin diets), icefish (Channichthyidae spp.) and painted noties (Lepidonotothen larseni). Penguins did not dive as deep as DSLs, but their prey-encounter depth-distributions, as revealed by biologging, overlapped at fine scale (10s of m) with depths of acoustically detected fish schools. We used neural networks to predict local scale (10 km) fish echo intensity and depth distribution at penguin dive locations based on environmental correlates, and developed models of habitat use. Habitat modelling revealed that king penguins preferentially foraged at locations predicted to have shallow and dense (high acoustic energy) fish schools associated with shallow and dense DSLs. These associations could be used to predict the distribution of king penguins from other colonies at South Georgia for which no tracking data are available, and to identify areas of potential ecological significance within the South Georgia and the South Sandwich Islands marine protected area.

Discrimination between schools and submerged trees in reservoirs: A preliminary approach using narrowband and broadband acoustics

With a growing demand for hydroelectric energy, the number of reservoirs is dramatically increasing worldwide. These new water bodies also present an opportunity for the development of fishing activities. However, these reservoirs are commonly impounded on uncut forests, resulting in many immersed trees. These trees hinder fish assessments by disrupting both gill netting and acoustic sampling. Immersed trees can easily be confused with fish schools on echograms. To overcome this issue, we developed a method to discriminate fish schools from immersed trees. A random forest algorithm was used to classify echo-traces at 120 and 200 kHz, recorded by an EK80 (SIMRAD) in narrowband (Continuous Wave) and in broadband mode (Frequency Modulated). We obtained a good discrimination rate between trees and schools, especially in broadband (90 % ratio of good classification). We demonstrate that it is possible to discriminate fish schools from immersed trees and thus facilitate the use of fisheries acoustics in reservoirs.

A comparative Evaluation of Swarm Intelligence Algorithm Optimization: A Review

Swarm intelligence (SI), an important aspect of artificial intelligence, is increasingly gaining popularity as more and more high-complexity challenges necessitate solutions that are sub-optimal but still feasible in a fair amount of time. Artificial intelligence that mimics the collective behavior of a group of animals is known as swarm intelligence. Attempting to survive. It is primarily influenced by biological systems. The main aim of our article is to find out more about the guiding principle, classify possible implementation areas, and include a thorough analysis of several SI algorithms. Swarms can be observed in ant colonies, fish schools, bird flocks, among other fields. During this article, we will look at some Swarm instances and their behavior. We see many Swarm Intelligence systems, like Ant colony Optimization, which explains ant activity, nature, and how they conquer challenges; in birds, we see Particle Swarm Optimization is a swarm intelligence-based optimization technique, and how the locations must be positioned based on the three concepts. The Bee Colony Optimization follows, and explores the behavior of bees, their relationships, as well as movement and how they work in a swarm. This paper explores some of the methods and algorithms.

Automatic Recognition of Fish Behavior with a Fusion of RGB and Optical Flow Data Based on Deep Learning

The rapid and precise recognition of fish behavior is critical in perceiving health and welfare by allowing farmers to make informed management decisions on recirculating aquaculture systems while reducing labor. The conventional recognition methods are to obtain movement information by implanting sensors on the skin or in the body of the fish, which can affect the normal behavior and welfare of the fish. We present a novel nondestructive method with spatiotemporal and motion information based on deep learning for real-time recognition of fish schools’ behavior. In this work, a dual-stream 3D convolutional neural network (DSC3D) was proposed for the recognition of five behavior states of fish schools, including feeding, hypoxia, hypothermia, frightening and normal behavior. This DSC3D combines spatiotemporal features and motion features by using FlowNet2 and 3D convolutional neural networks and shows significant results suitable for industrial applications in automatic monitoring of fish behavior, with an average accuracy rate of 95.79%. The model evaluation results on the test dataset further demonstrated that our proposed method could be used as an effective tool for the intelligent perception of fish health status.

The visual coupling between neighbors explains 'flocking' in human crowds

Patterns of collective motion or 'flocking' in birds, fish schools, and human crowds are believed to emerge from local interactions between individuals. Most models of collective motion attribute these interactions to hypothetical rules or forces, often inspired by physical systems, and described from an overhead view. We develop a visual model of human flocking from an embedded view, based on optical variables that actually govern pedestrian interactions. Specifically, people control their walking speed and direction by canceling the average optical expansion and angular velocity of their neighbors, weighted by visual occlusion. We test the model by simulating data from experiments with virtual crowds and real human 'swarms'. The visual model outperforms our previous overhead model and explains basic properties of physics-inspired models: 'repulsion' forces reduce to canceling optical expansion, 'attraction' forces to canceling optical contraction, and 'alignment' to canceling the combination of expansion/contraction and angular velocity. Critically, the neighborhood of interaction follows from Euclid's Law of perspective and the geometry of occlusion. We conclude that the local interactions underlying human flocking are a natural consequence of the laws of optics. Similar principles may apply to collective motion in other species.

Flow Field Inside and Around a Square Fish Cage Considering Fish School Swimming Pattern

The interaction between fluid and fish cage with stocked fish is extremely complex, including fluid and structure, as well as fluid and fish swimming behavior. The on-current swimming pattern of fish schools was found toward the incoming flow in the previous laboratory studies, which is different from the circular swimming pattern commonly observed in the farming site. In this study, a pseudo fish school structure model (PFS) was proposed to reproduce the five circular swimming patterns of farmed yellowtail, and to investigate the influence of fish school behaviors on the flow field inside and around a model square fish cage in laboratory experiments. The results showed that the drag force acting on the square fish cage increased with the increase of the current speed for all fish school swimming patterns, but no clear difference was observed between the fish school swimming behavior patterns. Overall, the drag force of the square fish cage considering the farmed fish behavior decreased by 11.8%, compared to the drag force of the fish cage without PFS. The current speeds inside and downstream of the fish cage increased almost linearly with increasing current velocities. Compared with the case of the fish cage without PFS, the current speed inside the cage under motionless closely PFS (C0), revolving closely PFS (CR), motionless loosely PFS (L0) and revolving loosely PFS (LR) conditions changed by 10.8%, 9.4%, 65.8% and 39.7%, respectively. In addition, compared to the case of the fish cage without PFS, the current speeds under C0, CR, L0 and LR conditions decreased by 89.8%, 16.3%, 58.2%, and 31.9%, respectively, at 16.0cm downstream from the fish cage, and decreased by 69.2%, 19.4%, 62.7% and 26.3%, respectively, at 63.6cm downstream from the fish cage. Furthermore, the current speed distribution and relative horizontal turbulence intensity distribution inside and around the fish cage under different fish school swimming pattern was discussed. In the future, we will use live fish to conduct experiments to evaluate fish school models.

Pose Estimation of Swimming Fish Using NACA Airfoil Model for Collective Behavior Analysis

We propose a pose estimation method using a National Advisory Committee for Aeronautics (NACA) airfoil model for fish schools. This method allows one to understand the state in which fish are swimming based on their posture and dynamic variations. Moreover, their collective behavior can be understood based on their posture changes. Therefore, fish pose is a crucial indicator for collective behavior analysis. We use the NACA model to represent the fish posture; this enables more accurate tracking and movement prediction owing to the capability of the model in describing posture dynamics. To fit the model to video data, we first adopt the DeepLabCut toolbox to detect body parts (i.e., head, center, and tail fin) in an image sequence. Subsequently, we apply a particle filter to fit a set of parameters from the NACA model. The results from DeepLabCut, i.e., three points on a fish body, are used to adjust the components of the state vector. This enables more reliable estimation results to be obtained when the speed and direction of the fish change abruptly. Experimental results using both simulation data and real video data demonstrate that the proposed method provides good results, including when rapid changes occur in the swimming direction.