scholarly journals Prediction by Soft Computing, Planning, and Strategy Building of Aquatic Catch: Chilika Lagoon, Odisha, India

2021 ◽  
pp. 47-62
Author(s):  
Siba Prasad Mishra ◽  
Ananta Charan Ojha
Keyword(s):  
Random Forest ◽  
Soft Computing ◽  
Tidal Inlet ◽  
Chilika Lagoon ◽  
Catch Data ◽  
Soft Computing Method ◽  
Hydraulic Regime ◽  
Fish Catch ◽  
And Migration ◽  
Strategy Building

Introduction: The Chilika lagoon in south Odisha, India was ecologically degraded from 1985 onwards by reduction of its aquatic (fish + prawn + shrimp) catches along with reduction in salinity, hydraulic regime, water exchange, aquatic weeds invasion, and sediment influx. The aquatic catch was 8669MT in year 1985-1986 gradually reduced to 1274MT during 1995-1996 from Odisha Fisheries Dept. records which resulted in poor economic condition of ≈0,2million fishermen and they migrated to adopt other livelihood. One direct tidal inlet dredged (Sipakuda) and Naraj barrage in the apex of South Mahanadi Delta were the major hydraulic interventions made to regain hydraulic regime. After the hydraulic interventions, the eco system restored, and the aquatic catch surged but it was insufficient to livelihood sustenance for the fishermen community of the Chilika,     so   that  they are forced for alternate occupation and migration. Methodologies: Fish catch data collected for 30 years and soft computing models linear regression, Multi Linear Perception (ANN), SMOorg (SVM) and the Random Forest algorithms (Weka Software) are used to predict the fish catch data of the lagoon for coming decade from 2020 to 2030. The effects of major hydraulic interventions are analyzed and the soft computing method of the fish and shrimp catch prediction of the Chilika has been attempted for the first time except some statistical approaches. Results: The Random Forest is found to be the preferred algorithm followed by the MLP model. The amount of catch remained around 12-13TMT if the variables and the present status of the lagoon is maintained. The combined effect of the Sipakuda Tidal inlet and the effective operation of the Naraj barrage have maintained the sustainable aqua catch. The present study shall be an immense help for the lake users and policy makers to augment aquatic catch, and alternate livelihood fishers community of the Chilika lagoon.

Comparative study for deriving stagedischarge– sediment concentration relationships using soft computing techniques

2021 ◽  
Vol 2 (104) ◽  
pp. 57-76
Author(s):  
P. Sihag ◽  
M.R. Sadikhani ◽  
V. Vambol ◽  
S. Vambol ◽  
A.K. Prabhakar ◽  
...  
Keyword(s):  
Random Forest ◽  
Soft Computing ◽  
Sediment Load ◽  
Prediction Models ◽  
Absolute Error ◽  
Load Prediction ◽  
Statistical Parameters ◽  
Hydro Power ◽  
Input Combination ◽  
Soft Computing Techniques

Purpose: Knowledge of sediment load carried by any river is essential for designing and planning of hydro power and irrigation projects. So the aim of this study is to develop and evaluating the best soft-computing-based model with M5P and Random Forest regressionbased techniques for computation of sediment using datasets of daily discharge, daily gauge and sediment load at the Champua gauging site of the Upper Baitarani river basin of India. Design/methodology/approach: Last few decades, the soft computing techniques based models have been successfully used in water resources modelling and estimation. In this study, the potential of tree based models are examined by developing and comparing sediment load prediction models, based on M5P tree and Random forest regression (RF). Several M5P and RF based models have been applied to a gauging site of the Baitarani River at Odisha, India. To evaluate the performance of the selected M5P and RF-based models, three most popular statistical parameters are selected such as coefficient of correlation, root mean square error and mean absolute error. Findings: A comparison of the results suggested that RF-based model could be applied successfully for the prediction of sediment load concentration with a relatively higher magnitude of prediction accuracy. In RF-based models Qt, Q(t-1), Q(t-2), S(t-1), S(t-2), Ht and H(t-1) combination based M10 model work superior than other combination based models. Another major outcome of this investigation is Qt, Q(t-1) and S(t-1) based model M4 works better than other input combination based models using M5P technique. The optimum input combination is Qt, Q(t-1) and S(t-1) for the prediction of sediment load concentration of the Baitarani River at Odisha, India. Research limitations/implications: The developed models were tested for Baitarani River at Odisha, India.

scholarly journals On the effects of pseudorandom and quantum-random number generators in soft computing

2019 ◽  
Vol 24 (12) ◽  
pp. 9243-9256
Author(s):  
Jordan J. Bird ◽  
Anikó Ekárt ◽  
Diego R. Faria
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Random Forest ◽  
Soft Computing ◽  
Convolutional Neural Networks ◽  
Random Number ◽  
Random Tree ◽  
Random Numbers ◽  
Random Number Generators ◽  
Eeg Classification

Abstract In this work, we argue that the implications of pseudorandom and quantum-random number generators (PRNG and QRNG) inexplicably affect the performances and behaviours of various machine learning models that require a random input. These implications are yet to be explored in soft computing until this work. We use a CPU and a QPU to generate random numbers for multiple machine learning techniques. Random numbers are employed in the random initial weight distributions of dense and convolutional neural networks, in which results show a profound difference in learning patterns for the two. In 50 dense neural networks (25 PRNG/25 QRNG), QRNG increases over PRNG for accent classification at + 0.1%, and QRNG exceeded PRNG for mental state EEG classification by + 2.82%. In 50 convolutional neural networks (25 PRNG/25 QRNG), the MNIST and CIFAR-10 problems are benchmarked, and in MNIST the QRNG experiences a higher starting accuracy than the PRNG but ultimately only exceeds it by 0.02%. In CIFAR-10, the QRNG outperforms PRNG by + 0.92%. The n-random split of a Random Tree is enhanced towards and new Quantum Random Tree (QRT) model, which has differing classification abilities to its classical counterpart, 200 trees are trained and compared (100 PRNG/100 QRNG). Using the accent and EEG classification data sets, a QRT seemed inferior to a RT as it performed on average worse by − 0.12%. This pattern is also seen in the EEG classification problem, where a QRT performs worse than a RT by − 0.28%. Finally, the QRT is ensembled into a Quantum Random Forest (QRF), which also has a noticeable effect when compared to the standard Random Forest (RF). Ten to 100 ensembles of trees are benchmarked for the accent and EEG classification problems. In accent classification, the best RF (100 RT) outperforms the best QRF (100 QRF) by 0.14% accuracy. In EEG classification, the best RF (100 RT) outperforms the best QRF (100 QRT) by 0.08% but is extremely more complex, requiring twice the amount of trees in committee. All differences are observed to be situationally positive or negative and thus are likely data dependent in their observed functional behaviour.

scholarly journals Article Commentary: Rough Set Soft Computing Cancer Classification and Network: One Stone, Two Birds

2010 ◽  
Vol 9 ◽  
pp. CIN.S4874 ◽  
Author(s):  
Yue Zhang
Keyword(s):  
Soft Computing ◽  
Gene Regulatory Networks ◽  
Regulatory Networks ◽  
Cancer Classification ◽  
Soft Computing Method ◽  
Direct Gene ◽  
Gene Regulatory ◽  
Variable Precision Rough Sets ◽  
Computing Method ◽  
Selection Of

Gene expression profiling provides tremendous information to help unravel the complexity of cancer. The selection of the most informative genes from huge noise for cancer classification has taken centre stage, along with predicting the function of such identified genes and the construction of direct gene regulatory networks at different system levels with a tuneable parameter. A new study by Wang and Gotoh described a novel Variable Precision Rough Sets-rooted robust soft computing method to successfully address these problems and has yielded some new insights. The significance of this progress and its perspectives will be discussed in this article.

scholarly journals A soft computing method for detecting lifetime building thermal insulation failures

2010 ◽  
Vol 17 (2) ◽  
pp. 103-115 ◽  
Author(s):  
Javier Sedano ◽  
Leticia Curiel ◽  
Emilio Corchado ◽  
Enrique de la Cal ◽  
José R. Villar
Keyword(s):  
Soft Computing ◽  
Thermal Insulation ◽  
Soft Computing Method ◽  
Computing Method
Sign in / Sign up

Export Citation Format

Share Document