Towards Tracking: Investigation of Genetic Algorithm and LSTM as Fish Trajectory Predictors in Turbid Water

Palconit, Maria Gemel B.; Almero, Vincent Jan D.; Rosales, Marife A.; Sybingco, Edwin; Bandala, Argel A.; Vicerra, Ryan Rhay P.; Dadios, Elmer P.

doi:10.1109/tencon50793.2020.9293730

Cited by 21 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Chl-a regression model was generated using multigene symbolic regression genetic programming. MSRGP is an evolutionary algorithm (EA) in the GPTIPS2 application of Matlab that evolves on a genetic search approach for mathematical topology and genetic parameters [35]. It was configured with 500 population size, 100 maximum generations, tournament size of 100, 0.1 elite fraction with lexicographic selection pressure that prefers simpler tree depth when individual fitness values are equal, 0.2 probability pareto tournament, maximum of 10 genes, maximum tree depth of 5, crossover rate of 0.84, mutation rate of 0.14, and functional set of {'times', 'minus', 'plus', 'sqrt', 'square', 'sin', 'cos', 'add3', 'mult3', 'log', 'cube', 'neg', 'abs'} (Fig.…”

Section: F Development Of Bioinspired Pre-harvest Growth Factors Optimization Modelmentioning

confidence: 99%

Hybrid Genetic Programming and Multiverse-based Optimization of Pre-Harvest Growth Factors of Aquaponic Lettuce Based on Chlorophyll Concentration

Concepcion¹,

Dadios²,

Cuello³

et al. 2021

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Optimizing photosynthesis is vital in maintaining quality farm produce in the agricultural food production sector. The nonlinear behavior of the interaction of crop pre-harvest growth factors can promote or retard its growth. This study employed multigene symbolic regression genetic programming (MSRGP) in developing the chlorophyll-a fitness function allied with bioinspired algorithms, namely genetic algorithm (GA), particle swarm optimization (PSO), and multiverse optimization (MVO), in determining the ideal combination of carbon dioxide, light intensity, air temperature, and humidity that will induce photosynthesis based on aquaponic lettuce (Lactuca sativa var. Altima) leaf chlorophyll-a concentration. Light spectra were characterized through the floating leaf disk technique, which resulted in white spectra as the most photosynthetic conducive based on the light reaction and dark respiration. Leaf spectro-textural-morphological signatures were extracted for non-destructive MSRGP chlorophyll-a concentration measurement. Carbon dioxide and humidity have a strong positive impact on chlorophyll-a concentration. Photosynthesis is impeded by Vis/IR above 7.817. The hybrid MSRGP-MVO generated the ideal global solution of 880.744 ppm of CO2, 543.147 μmol m -2 s -1 of the visible white light spectrum, 22.238 °C air temperature, and 67.742% humidity which resulted in 651.144 mg g -1 of Chl-a, 0.934 leaf weight ratio, 0.066 roots to shoot ratio, 141 xylem vessels mm -2 127.389 stomata mm -2 , and more prominent intracellular chloroplast concentration for the harvest stage lettuce. The established standard for fresh weight, chlorophylls a and b, and vitamin C concentrations are essential for developing an adaptive nutrient management system to maintain the expected growth signatures of lettuce at the end of the 6-week cultivation cycle.

show abstract

Section: F Development Of Bioinspired Pre-harvest Growth Factors Optimization Modelmentioning

confidence: 99%

Hybrid Genetic Programming and Multiverse-based Optimization of Pre-Harvest Growth Factors of Aquaponic Lettuce Based on Chlorophyll Concentration

Concepcion¹,

Dadios²,

Cuello³

et al. 2021

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

show abstract

“…However, in a recent study, the concept of the dynamic traveler problem based on the genetic algorithm and Newton equation of motion was used to obtain excellent results in predicting the minimum distance traveled by a moving fishing boat in the future. Since use of the genetic algorithm (GA) in this field has not been fully realized, Palconit et al [26] further discussed its application potential in fish tracking based on GA. On the other hand, the deep learning algorithms recurrent neural network (RNN) and long short-term memory (LSTM) have been used in several visual track prediction methods to predict targets, including pedestrians, vehicles, mobile robots, fish, etc. The results from these methods were shown to be better than most tracking methods, and thereby underwater video fish tracking research has been carried out based on RNN-LSTM.…”

Section: Accuracy Accuracy Evaluationmentioning

confidence: 99%

A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas

et al. 2022

View full text Add to dashboard Cite

Based on analysis of state-of-the-art research investigating target detection and recognition in turbid waters, and aiming to solve the problems encountered during target detection and the unique influences of turbidity areas, in this review, the main problem is divided into two areas: image degradation caused by the unique conditions of turbid water, and target recognition. Existing target recognition methods are divided into three modules: target detection based on deep learning methods, underwater image restoration and enhancement approaches, and underwater image processing methods based on polarization imaging technology and scattering. The relevant research results are analyzed in detail, and methods regarding image processing, target detection, and recognition in turbid water, and relevant datasets are summarized. The main scenarios in which underwater target detection and recognition technology are applied are listed, and the key problems that exist in the current technology are identified. Solutions and development directions are discussed. This work provides a reference for engineering tasks in underwater turbid areas and an outlook on the development of underwater intelligent sensing technology in the future.

show abstract

“…Several tracking methods have been applied to underwater fish-school tracking in the past decade [30][31][32][33][34][35][36]. Chung et al [32] proposed an automatic fish segmentation algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…However, this algorithm is time-consuming, and the mismatching phenomenon is serious when an occlusion exists. Palconit et al [33] used a time-series prediction algorithm to predict the trajectory. They first used the subtraction of two images to obtain the binary image, and then the long short-erm memory (LSTM) or genetic algorithm to predict the fish's position in the next frame.…”

Section: Related Workmentioning

confidence: 99%

A Robust Underwater Multiclass Fish-School Tracking Algorithm

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

State-of-the-art multiple-object tracking methods are frequently applied to people or vehicle tracking, but rarely involve underwater-object tracking. Compared with the processing in non-underwater photos or videos, underwater fish tracking is challenging due to variations in light conditions, water turbidity levels, shape deformations, and the similar appearances of fish. This article proposes a robust underwater fish-school tracking algorithm (FSTA). The FSTA is based on the tracking-by-detection paradigm. To solve the problem of low recognition accuracy in an underwater environment, we add an amendment detection module that uses prior knowledge to modify the detection result. Second, we introduce an underwater data association algorithm for aquatic non-rigid organisms that recombines representation and location information to refine the data matching process and improve the tracking results. The Resnet50-IBN network is used as a re-identification network to track fish. We introduce a triplet loss function based on a centroid to train the feature extraction network. The multiple-object tracking accuracy (MOTA) of the FSTA is 79.1% on the underwater dataset, which shows that it can achieve state-of-the-art performance in a complex real-world marine environment.

show abstract

Towards Tracking: Investigation of Genetic Algorithm and LSTM as Fish Trajectory Predictors in Turbid Water

Cited by 21 publications

References 17 publications

Hybrid Genetic Programming and Multiverse-based Optimization of Pre-Harvest Growth Factors of Aquaponic Lettuce Based on Chlorophyll Concentration

Hybrid Genetic Programming and Multiverse-based Optimization of Pre-Harvest Growth Factors of Aquaponic Lettuce Based on Chlorophyll Concentration

A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas

A Robust Underwater Multiclass Fish-School Tracking Algorithm

Contact Info

Product

Resources

About