Behavior Of Fish Schools Research Articles

Computer-Simulated Virtual Image Datasets to Train Machine Learning Models for Non-Invasive Fish Detection in Recirculating Aquaculture.

Artificial Intelligence (AI) and Machine Learning (ML) can assist producers to better manage recirculating aquaculture systems (RASs). ML is a data-intensive process, and model performance primarily depends on the quality of training data. Relatively higher fish density and water turbidity in intensive RAS culture produce major challenges in acquiring high-quality underwater image data. Additionally, the manual image annotation involved in model training can be subjective, time-consuming, and labor-intensive. Therefore, the presented study aimed to simulate fish schooling behavior for RAS conditions and investigate the feasibility of using computer-simulated virtual images to train a robust fish detection model. Additionally, to expedite the model training and automate the virtual image annotation, a process flow was developed. The 'virtual model' performances were compared with models trained on real-world images and combinations of real and virtual images. The results of the study indicate that the virtual model trained solely with computer-simulated images could not perform satisfactorily (mAP = 62.8%, F1 score = 0.61) to detect fish in a real RAS environment; however, replacing a small number of the virtual images with real images in the training dataset significantly improved the model's performance. The M6 mixed model trained with 630 virtual and 70 real images (virtual-to-real image ratio: 90:10) achieved mAP and F1 scores of 91.8% and 0.87, respectively. Furthermore, the training time cost for the M6 model was seven times shorter than that for the 'real model'. Overall, the virtual simulation approach exhibited great promise in rapidly training a reliable fish detection model for RAS operations.

Optimization of the concentration of ozone generated by DBD using PSO algorithm for water treatment process

The water treatment process with ozone is influenced by various operating parameters and environmental factors that can impact its efficiency. In this study, experiments were conducted using a Venturi pumping frame to investigate the effects of three controllable variables: oxygen flow height, applied voltage level, and water flow rate. The tests aimed to develop a mathematical model that accurately represents the relationship between these input variables and the resulting ozone concentration in the treated water. The experimental data was analyzed using the MODDE 5.0 software, a specialized application for statistical modeling and design of experiments. By fitting the data to appropriate model equations, a mathematical model was obtained that quantifies the influence of each variable and their interactions on the ozone concentration response. To optimize the process performance, a particle swarm optimization (PSO) algorithm was employed to extract the best-fit parameters for the mathematical model. PSO is a computational technique inspired by the social behavior of bird flocks or fish schools, utilizing a population of candidate solutions that evolve iteratively to converge on the global optimum solution. In this case, PSO searched for the model parameter values that minimized the error between predicted and experimentally measured ozone concentrations, rapidly converging to an accurate solution. The optimized mathematical model enables predicting the ozone concentration under any combination of oxygen flow height, voltage, and water flow rate within the experimental range. This predictive capability facilitates identifying the optimum operating conditions to maximize ozone concentration, thereby enhancing the efficiency of the water treatment process. The model serves as a valuable tool for process control, monitoring, and optimization, ensuring consistent treatment quality while minimizing resource consumption and operational costs.

A real-time feeding decision method based on density estimation of farmed fish

With the global population growth and increasing demand for high-quality protein, aquaculture has experienced rapid development. Fish culture management and feed supply are crucial components of aquaculture. Traditional baiting management relies on experiential judgment and regular observation, which often leads to inefficient baiting practices and wastage. To address these issues, intelligent bait casting decisions have emerged. Leveraging advanced artificial intelligence algorithms, intelligent bait casting decisions can overcome most drawbacks of traditional bait management and enhance breeding efficiency. However, most of the current intelligent baiting decisions are focused on using methods such as image processing and target detection to identify different feeding actions and patterns. These methods do not discuss based on video streams and do not consider the changes in fish behavior during the baiting process. Therefore, we proposed a real-time analysis method based on the density distribution of fish feeding behavior (FishFeed). Firstly, this method upgrades the input mechanism, not only handling static images but also capable of real-time video stream analysis. Secondly, by evaluating the fish school density distribution through a new intelligent baiting strategy, this method can monitor the feeding behavior of fish school during the baiting process in real time. Finally, we constructed a dataset for fish school density analysis (DlouFishDensity) that includes a wealth of video and image frames, providing a valuable resource for research. Experimental results indicate that our algorithm outperforms MCNN, improving MAE by 1.63 and 1.35, MSE by 1.92 and 1.58, and reducing prediction time by 2.56 seconds on the same dataset. By implementing real-time analysis of fish feeding behavior density distribution, our method offers a more efficient and effective approach to baiting management in aquaculture, contributing to improved breeding efficiency and resource utilization.

HIF signaling overactivation inhibits lateral line neuromast development through Wnt in zebrafish

The lateral line is critical for prey detection, predator avoidance, schooling, and rheotaxis behavior in fish. As similar to hair cells in the mammalian inner ear, the lateral line sensory organ called neuromasts is a popular model for hair cell regeneration. However, the mechanism of lateral line development has not been fully understood. In this study, we showed for the first time that hypoxia-inducible factor (HIF) signaling is involved in lateral line development in zebrafish. hif1ab and epas1b were highly expressed in neuromasts during lateral line development. Hypoxia response induced by a prolyl hydroxylase domain-containing proteins (PHD) inhibitor treatment or vhl gene knockout significantly reduced hair cells and support cells in neuromast during lateral line development. In addition, inhibition of Hif-1α or Epas1 could partially rescue hair cells in the larvae with increased HIF activity, respectively. Moreover, the support cell proliferation and the expression of Wnt target genes decreased in vhl mutants which suggests that Wnt signaling mediated the role of HIF signaling in lateral line development. Collectively, our results demonstrate that HIF signaling overactivation inhibits lateral line development in zebrafish and suggest that inhibition of HIF signaling might be a potential therapeutic method for hair cell death.

Problems and Prospects of Studying Schooling Behavior of Fish

Problems and Prospects of Studying Schooling Behavior of Fish

Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow

Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow

IMPROVED QoE IN 5G BASE STATION USING PSO BASED DSA

In the 5G era, base stations can offer multiple services in various scenarios, enhancing spectrum efficiency by utilizing idle frequency bands for low-demand services while ensuring high-priority services are prioritized. This creates a distributed architecture for spectrum allocation. The proposed dynamic spectrum allocation scheme for base stations, optimizes spectrum rearrangement based on service priority, energy consumption, and renting cost. We employ the Particle Swarm Optimization (PSO) algorithm, inspired by bird flocking or fish schooling behavior, to solve the problem. Moreover, provide detailed information on our approach, demonstrating the effectiveness of PSO in optimizing spectrum allocation. By using PSO, we find the optimal solution considering service priority, energy consumption, and renting cost, supported by mathematical proofs of PSO algorithm performance. MATLAB is used as the simulation tool to carry out these techniques. Simulation experiments validate the approach, showing the stability and efficacy of PSO-based algorithm, which aligns with the theoretical analysis. . Key Words: Spectrum efficiency; 5G; dynamic spectrum allocation; service priority; PSO.

Development of a feeding simulation to evaluate how feeding distribution in aquaculture affects individual differences in growth based on the fish schooling behavioral model.

In this study, we developed a feeding simulation using the fish schooling behavior model to evaluate growth differences from the feeding spatial distribution. In the proposed simulation, feeding behavior was modeled using the fish schooling model to simulate the amount of feed consumed by each individual. Next, body mass growth was calculated based on the amount of feed consumed. A 3.0-m diameter aquaculture tank was used for the simulation. We used three feeding methods to evaluate how feeding distribution affected growth: Feeding A, B, and C. The feed was distributed in a square pattern with one side length of 1.5, 1.0, or 0.5 m for Feeding A, B, and C groups, respectively. The results revealed that individual differences in body mass resulting from each feeding method differed greatly. The individual difference was largest in the Feeding C group. Here, maximum swimming speed was assumed to be proportional to total length. The feeding area of Feeding C was narrow; therefore, the first individual to arrive in the feeding area dominated the feed. Large individuals accessed the feed more easily than did small individuals. Consequently, the growth of large individuals became more rapid, and the individual differences became large in Feeding C. A rearing test can be conducted in a short time, and the optimal aquaculture operation was easily determined using the proposed simulation method. We concluded that the proposed simulation is useful as a decision-making tool for aquaculture management.

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.

Effects of shady environments on fish collective behavior

Despite significant efforts devoted to understanding the underlying complexity and emergence of collective movement in animal groups, the role of different external settings on this type of movement remains largely unexplored. Here, by combining time series analysis and complex network tools, we present an extensive investigation of the effects of shady environments on the behavior of a fish species (Silver Carp Hypophthalmichthys molitrix) within earthen ponds. We find that shade encourages fish residence during daylight hours, but the degree of preference for shade varies substantially among trials and ponds. Silver Carp are much slower and exhibit lower persistence in their speeds when under shade than out of it during daytime and nighttime, with fish displaying the highest persistence degree and speeds at night. Furthermore, our research shows that shade affects fish schooling behavior by reducing their polarization, number of interactions among individuals, and the stability among local neighbors; however, fish keep a higher local degree of order when under shade compared to nighttime positions.

Kayak Drone – a silent acoustic unmanned surface vehicle for marine research

Advancements in technologies have led to a rapid development of unmanned surface vehicles (USV) for marine ecosystem monitoring. The design, size, and scientific payload of the USVs differ as they are built for different purposes. Here, we present the design criteria and detailed technical solutions of a prototype USV which has been built to fulfill the following experimental and operational needs; the USV should be used for inshore and shallow water acoustic monitoring, offshore comparison of echo sounder recordings from the USV and research vessels, monitor natural fish schooling behavior and seabird-fish behavioral interactions. The prototype has been built over a period of 5 years with steadily quality improvements. As the hull is based on an expedition double kayak, the USV is named Kayak Drone, and we aimed at building the Kayak Drone using of-the-shelf hardware and existing open-source software. This allowed for the development of a modular and well-functioning USV at a relatively low cost. The Kayak Drone produces very little noise and in situ experiments show that the Kayak Drone can record echo sounder data of fish near the surface without disturbing their natural distribution and behavior. One in situ study shows that the Kayak Drone could navigate within a couple of meters from swimming puffin and other seabirds without triggering escape. These results demonstrate that the Kayak Drone can be utilized to produce unbiased survey estimates for fish distributed in shallow waters and near the surface, which is very important for many fish stock assessments and managements. Furthermore, it can also be used as a tool to observe the predation by seabirds on fish schools without interfering with their natural interspecific behavior, which traditionally has been very difficult. The use of the Kayak Drone is not restricted to these tasks, and we foresee that the Kayak Drone can be utilized in many different experiments where a silent platform is needed.

A MobileNetV2-SENet-based method for identifying fish school feeding behavior

Analyzing fish school feeding behavior can assist aquaculturists in making successful feeding decisions, which is critical for enhancing farming efficiency and supporting healthy fish growth. Due to the fierce gathering, jumping, chasing and other actions that occur during fish school feeding, images contain varying degrees of noise and significant overlap between fish targets. Therefore, accurately identifying fish school feeding behavior becomes challenging. To address this problem, the study proposes a MobileNetV2-SENet-based method for identifying fish school feeding behavior. To enhance sample diversity, fish school images are preprocessed with some operations, such as random cropping and brightness-contrast adjustment. Then, MobileNetV2 is used to extract fish school image features, and a feature weighting network based on SENet (Squeeze-and-Excitation Networks) is built. Weights are assigned to features with varying degrees of value. The feeding behavior of fish school is identified using the linear classifier. Finally, a method of determining feeding amount is provided based on the identification result to reduce feed consumption. The SENet is introduced in the proposed method based on the original MobileNetV2 feature extraction network, and a feature extraction and weighting network that integrates MobileNetV2 and SENet is built to improve the weights of features relevant for fish school state identification while suppressing the weights of interference elements such as noise, resulting in more accurate identification. The proposed method was tested on the real fish school images and yielded an accuracy of 97.76%. The accuracy of our model was improved by 3.81%, 9.99%, 50.35%, and 100.37% when compared to the fish school feeding behavior identification model based on EfficientNet_B0, ShuffleNetV2, AlexNet, and EfficientNetV2, respectively, indicating that our method can accurately identify the feeding behavior of fish school in real aquaculture.

Fish behavior based on the effect of variations in oceanographic condition variations in FADs Area of Bone Bay Waters, Sulawesi, Indonesia

Abstract. Rumpa A, Najamuddin, Safruddin, Hajar MAI. 2022. Fish behavior based on the effect of variations in oceanographic condition variations in FADs Area of Bone Bay Waters, Sulawesi, Indonesia. Biodiversitas 23: 1875-1883. Fish behavior is the response of fish to conditions existing in their environment. One of the causes is oceanographic factors, which can affect the schooling movement of fish. This study aimed to identify the schooling behavior of fish based on the influence of oceanographic variations in the Fish Aggregating Device (FADs) area. Study took place from March to September 2021 in Bone Bay Waters, Indonesia. The type of research was experimental fishing with an acoustic approach for 57 times. Parameters observed were current velocity, current direction, and water temperature to the distance of schooling fish from FADs vertically and horizontally in the afternoon, evening, night, and early morning. The behavioral data of fish species were namely Decapterus russelli. The results showed namely the variation in current velocity affected the horizontal distance; variation in the direction of currents affected the horizontal distribution distance, while the water temperature affected the vertical schooling of fish. In the operation of fishing gear, especially in the early morning, in terms of the concentration pattern of schooling fish under FADs. The ideal current velocity was in the range of 0.2-0.29 [m s-1], while the ideal current direction is direct current was at the angle of 0°-60°. The schooling of fish approached to the surface and was concentrated under FADs at >30°C. Understanding on the distribution of horizontal and vertical movements and the time of concentration of fish schooling at the central point of FADs due to oceanographic variations will facilitate the effectiveness of fishing gear operation.

VLC Turbulence Effects on the Performance of the Fish School Behavior Modeling Mobile Diffusion Adaptive Networks in Underwater Environments

VLC Turbulence Effects on the Performance of the Fish School Behavior Modeling Mobile Diffusion Adaptive Networks in Underwater Environments

Remote acoustic detection and characterization of fish schooling behavior.

Many fish species form social aggregations or shoals. Understanding the conditions under which these groups sometimes coordinate their behavior in space and time, or "school," is important for understanding their ecology, their effects on the ecosystem, and effective management of their stocks. An automated approach to isolate acoustic aggregations in echosounder data relative to the local background scattering is introduced. Aggregations were then identified and characterized in a large dataset acquired from an autonomous platform and a research vessel. Fish schools were statistically distinct from other aggregations of fish, with differences in their geometry, frequency response, scattering intensity, and scattering distribution. The statistical distribution of acoustic scattering from fish shoals generally followed a Rayleigh distribution as predicted for a randomly organized aggregation of homogenous scatterers. Within fish schools, however, the distribution was distinct from Rayleigh, showing a consistent pattern with most values at low relative scattering levels followed by a sharp roll-off and long right tail. These differences in distribution provide the ability to remotely observe the polarized, organized behavior that defines schooling, a difficult to observe response to environmental and internal conditions, which has large implications for our understanding and management of schooling fish.

Test case prioritization based on Artificial Fish School Algorithm

Software testing is considered as an essential and critical part of the software development process. To improve the efficiency of software testing, the test case prioritization (TCP) technique is usually used to preprocess the test case set, which is formulated as a single-objective or multiple-objective optimization problem and solved by swarm intelligence algorithms. In this paper, we adopted one of the state-of-art swarm intelligence algorithms — Artificial Fish School Algorithm to solve the TCP problem. Specifically, the coding method of artificial fish school was designed in combination with the test case set; the Average Percentage of Test-point Coverage and Effective Execution Time were selected to optimize the design of clustering behavior, foraging behavior and tail-chasing behavior of artificial fish school; the optimal solution was found by population iteration. Empirical evaluation was conducted to analyze the performance of the proposed method. Comparison experiments were also carried out, and the experimental results showed that in terms of both single-objective and multiple-objective, the Artificial Fish School Algorithm could better solve the TCP problems and improve the efficiency of software testing.

Zebrafish automatic monitoring system for conditioning and behavioral analysis

Studies using zebrafish (Danio rerio) in neuro-behavioural research are growing. Measuring fish behavior by computational methods is one of the most efficient ways to avoid human bias in experimental analyses, extending them to various approaches. Sometimes, thorough analyses are difficult to do, as fish can behave unpredictably during an experimental strategy. However, the analyses can be implemented in an automated way, using an online strategy and video processing for a complete assessment of the zebrafish behavior, based on the detection and tracking of fish during an activity. Here, a fully automatic conditioning and detailed analysis of zebrafish behavior is presented. Microcontrolled components were used to control the delivery of visual and sound stimuli, in addition to the concise amounts of food after conditioned stimuli for adult zebrafish groups in a conventional tank. The images were captured and processed for automatic detection of the fish, and the training of the fish was done in two evaluation strategies: simple and complex. In simple conditioning, the zebrafish showed significant responses from the second attempt, learning that the conditioned stimulus was a predictor of food presentation in a specific space of the tank, where the food was dumped. When the fish were subjected to two stimuli for decision-making in the food reward, the zebrafish obtained better responses to red light stimuli in relation to vibration. The behavior change was clear in stimulated fish in relation to the control group, thus, the distances traveled and the speed were greater, while the polarization was lower in stimulated fish. This automated system allows for the conditioning and assessment of zebrafish behavior online, with greater stability in experiments, and in the analysis of the behavior of individual fish or fish schools, including learning and memory studies.

Flow-mediated organization of two freely flapping swimmers

Abstract

Fisheries-induced selection against schooling behaviour in marine fishes.

Group living is a common strategy used by fishes to improve their fitness. While sociality is associated with many benefits in natural environments, including predator avoidance, this behaviour may be maladaptive in the Anthropocene. Humans have become the dominant predator in many marine systems, with modern fishing gear developed to specifically target groups of schooling species. Therefore, ironically, behavioural strategies which evolved to avoid non-human predators may now actually make certain fish more vulnerable to predation by humans. Here, we use an individual-based model to explore the evolution of fish schooling behaviour in a range of environments, including natural and human-dominated predation conditions. In our model, individual fish may leave or join groups depending on their group-size preferences, but their experienced group size is also a function of the preferences of others in the population. Our model predicts that industrial fishing selects against individual-level behaviours that produce large groups. However, the relationship between fishing pressure and sociality is nonlinear, and we observe discontinuities and hysteresis as fishing pressure is increased or decreased. Our results suggest that industrial fishing practices could be altering fishes' tendency to school, and that social behaviour should be added to the list of traits subject to fishery-induced evolution.

Simulation of the capture process in set net fishing using a fish-schooling behavior model

Generally, the catch efficiency (CE) of a set net is difficult to evaluate because it is affected by fish behavior. Therefore, to evaluate CE, we proposed a fish school behavior simulation model based on the boid model and applied it to a full-scale set net. The moving path of the fish school around the set net was simulated and visualized via the proposed method. From the moving path, three behaviors were identified: all individuals entering, all individuals escaping, and the school dividing in the entrance. A Monte Carlo simulation was conducted to evaluate the relationship between set net entrance shape and CE. The entrance net angle (θ) was considered over a range of 55°–90°. The ratio of fish entering the set net was ~ 60% at θ = 60°–90°, and significantly lower at θ = 55°. After entering the playground, over 80% of individuals entered the bag net. When θ = 60°, the ratios of fish escaping from the set net and entering the bag net were at their lowest and highest, respectively. Therefore, maximum CE was achieved at θ = 60°. We conclude that the proposed simulation method will contribute to more efficient set net design.