scholarly journals Experimental studies on scour of supercritical flow jets in upstream of screens and modelling scouring dimensions using artificial intelligence to combine multiple models (AIMM)

2019 ◽  
Vol 21 (5) ◽  
pp. 893-907 ◽  
Author(s):  
Sina Sadeghfam ◽  
Rasoul Daneshfaraz ◽  
Rahman Khatibi ◽  
Omar Minaei
Keyword(s):  
Artificial Intelligence ◽  
Froude Number ◽  
Experimental Studies ◽  
Support Vector ◽  
Densimetric Froude Number ◽  
Number Range ◽  
Artificial Intelligence Models ◽  
Level 1 ◽  
Supercritical Flows ◽  
Level 2

Abstract Performances of screens in watercourses are investigated for dissipating energy of supercritical flows, capable of inducing scour or stabilising hydraulic jumps. Subsequent scouring pits are characterised by pit depth and pit length. Inherent processes are studied through laboratory tests by producing a set of empirical data to formulate a model of the scour for explaining subsequent processes. The experimental set-up comprises: (i) Froude number of supercritical flows (range: 3.5–8.0); (ii) particle densimetric Froude number (range: 2–10) using five granular samples; and (iii) two screen porosities (40% and 50%). Trained and tested artificial intelligence models explain the data by expressing depth and length of the pit through the following levels: Level 1: use the experimental data and test the models of: Sugeno fuzzy logic (SFL) and neuro-fuzzy (NF); and Level 2: use outputs of Level 1 models as inputs to support vector machine (SVM). The results reveal that the Level 2 model improves model performances compared with the single models with respect to R2, root mean square error (RMSE), Nash–Sutcliffe coefficient (NSC) and residual errors. While Level 1 models remain fit-for-purpose, the comparative improvement from Level 1 to Level 2 can be as high as 58% in terms of NSC for the testing phase.

Experimental Studies of Sedimentation Basin Dynamics

1977 ◽  
Vol 12 (1) ◽  
pp. 77-90
Author(s):  
J.F. Cordoba-Molina ◽  
P.L. Silveston ◽  
R. R. Hudgins
Keyword(s):  
Dynamic Response ◽  
Froude Number ◽  
Flow Model ◽  
Experimental Studies ◽  
Densimetric Froude Number ◽  
Number Range ◽  
The Real ◽  
Highly Correlated ◽  
Sedimentation Basins ◽  
Simple Flow

Abstract A simple Flow Model is proposed to describe the dynamic response of sedimentation basins. The response predicted by this model is linear as opposed to the real response of the basin which is nonlinear. However, the real response of the basin is highly correlated with its densimetric Froude number, and as a consequence our linear model effectively predicts the response of the basin in a restricted densimetric Froude Number range. Our experiments show that the response of the basin becomes more sluggish and erratic as the densimetric Froude number decreases.

scholarly journals Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques

Water ◽  
2021 ◽  
Vol 13 (19) ◽  
pp. 2622
Author(s):  
Ata Allah Nadiri ◽  
Marjan Moazamnia ◽  
Sina Sadeghfam ◽  
Rahim Barzegar
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Land Subsidence ◽  
Support Vector ◽  
Groundwater Depletion ◽  
Multi Criteria Decision Making ◽  
Hazard Vulnerability ◽  
Level 1 ◽  
Modeling Strategy ◽  
Level 2

Groundwater over-abstraction may cause land subsidence (LS), and the LS mapping suffers the subjectivity associated with expert judgment. The paper seeks to reduce the subjectivity associated with the hazard, vulnerability, and risk mapping by formulating an inclusive multiple modeling (IMM), which combines two common approaches of multi-criteria decision-making (MCDM) at Level 1 and artificial intelligence (AI) at Level 2. Fuzzy catastrophe scheme (FCS) is used as MCDM, and support vector machine (SVM) is employed as AI. The developed methodology is applied in Iran’s Tasuj plain, which has experienced groundwater depletion. The result highlights hotspots within the study area in terms of hazard, vulnerability, and risk. According to the receiver operating characteristic and the area under curve (AUC), significant signals are identified at both levels; however, IMM increases the modeling performance from Level 1 to Level 2, as a result of its multiple modeling capabilities. In addition, the AUC values indicate that LS in the study area is caused by intrinsic vulnerability rather than man-made hazards. Still, the hazard plays the triggering role in the risk realization.

Deep Level Analysis of Legitimacy in Bengali News Sentences

2022 ◽  
Vol 21 (1) ◽  
pp. 1-18
Author(s):  
Soma Das ◽  
Pooja Rai ◽  
Sanjay Chatterji
Keyword(s):  
Deep Level ◽  
Research Direction ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
News Article ◽  
Support Vector ◽  
Potential Threat ◽  
Annotation Guideline ◽  
Level 1 ◽  
Level 2

The tremendous increase in the growth of misinformation in news articles has the potential threat for the adverse effects on society. Hence, the detection of misinformation in news data has become an appealing research area. The task of annotating and detecting distorted news article sentences is the immediate need in this research direction. Therefore, an attempt has been made to formulate the legitimacy annotation guideline followed by annotation and detection of the legitimacy in Bengali e-papers. The sentence-level manual annotation of Bengali news has been carried out in two levels, namely “Level-1 Shallow Level Classification” and “Level-2 Deep Level Classification” based on semantic properties of Bengali sentences. The tagging of 1,300 anonymous Bengali e-paper sentences has been done using the formulated guideline-based tags for both levels. The validation of the annotation guideline has been done by applying benchmark supervised machine learning algorithms using the lexical feature, syntactic feature, domain-specific feature, and Level-2 specific feature in both levels. Performance evaluation of these classifiers is done in terms of Accuracy, Precision, Recall, and F-Measure. In both levels, Support Vector Machine outperforms other benchmark classifiers with an accuracy of 72% and 65% in Level-1 and Level-2, respectively.

scholarly journals Hybrid Harmony Search–Artificial Intelligence Models in Credit Scoring

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 989
Author(s):  
Rui Ying Goh ◽  
Lai Soon Lee ◽  
Hsin-Vonn Seow ◽  
Kathiresan Gopal
Keyword(s):  
Artificial Intelligence ◽  
Feature Selection ◽  
Credit Scoring ◽  
Harmony Search ◽  
Model Performance ◽  
Hybrid Models ◽  
Performance Model ◽  
Computational Time ◽  
Support Vector ◽  
Artificial Intelligence Models

Credit scoring is an important tool used by financial institutions to correctly identify defaulters and non-defaulters. Support Vector Machines (SVM) and Random Forest (RF) are the Artificial Intelligence techniques that have been attracting interest due to their flexibility to account for various data patterns. Both are black-box models which are sensitive to hyperparameter settings. Feature selection can be performed on SVM to enable explanation with the reduced features, whereas feature importance computed by RF can be used for model explanation. The benefits of accuracy and interpretation allow for significant improvement in the area of credit risk and credit scoring. This paper proposes the use of Harmony Search (HS), to form a hybrid HS-SVM to perform feature selection and hyperparameter tuning simultaneously, and a hybrid HS-RF to tune the hyperparameters. A Modified HS (MHS) is also proposed with the main objective to achieve comparable results as the standard HS with a shorter computational time. MHS consists of four main modifications in the standard HS: (i) Elitism selection during memory consideration instead of random selection, (ii) dynamic exploration and exploitation operators in place of the original static operators, (iii) a self-adjusted bandwidth operator, and (iv) inclusion of additional termination criteria to reach faster convergence. Along with parallel computing, MHS effectively reduces the computational time of the proposed hybrid models. The proposed hybrid models are compared with standard statistical models across three different datasets commonly used in credit scoring studies. The computational results show that MHS-RF is most robust in terms of model performance, model explainability and computational time.

Prediction of Electrical Conductivity of Cu-15Ni-8Sn-XSi Alloys Using the Physical Model and Artificial Intelligence Model

2013 ◽  
Vol 652-654 ◽  
pp. 1138-1142 ◽  
Author(s):  
Shan Feng Fang ◽  
Yuan Shan Han ◽  
Ming Pu Wang
Keyword(s):  
Artificial Intelligence ◽  
Electrical Conductivity ◽  
Phase Transformation ◽  
Physical Model ◽  
Volume Fraction ◽  
Least Square ◽  
Support Vector ◽  
Intelligence Models ◽  
Artificial Intelligence Models ◽  
Experimental Values

The kinetics of phase transformation in Cu-15Ni-8Sn-XSi alloys alloy was studied through the measurement of the relationship between electric conductivity and volume friction of the new phase. The phase transformation kinetics equation was deduced from the Avrami empirical formula based on the linear relationship between the electrical conductivity and the volume fraction of the phase transformation. The electrical conductivity calculated by the physical model was also obtained. As comparisons, a new model based on least square support vector machines (LSSVM) and capable of forecasting electrical property of Cu-15Ni-8Sn-XSi alloys has been proposed and tested on the same data. The present calculated results of both the physical and artificial intelligence models are in very good agreement with the experimental values. Two models are feasible and efficient to forecast the electrical conductivity of Cu-15Ni-8Sn-XSi alloys.

scholarly journals Development of artificial intelligence models for well groundwater quality simulation: Different modeling scenarios

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0251510
Author(s):  
Naser Shiri ◽  
Jalal Shiri ◽  
Zaher Mundher Yaseen ◽  
Sungwon Kim ◽  
Il-Moon Chung ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Groundwater Quality ◽  
Quality Parameters ◽  
Geographical Information ◽  
Support Vector ◽  
Quality Factors ◽  
Intelligence Models ◽  
Artificial Intelligence Models ◽  
Total Dissolved Solid ◽  
Tabriz Plain

Groundwater is one of the most important freshwater resources, especially in arid and semi-arid regions where the annual amounts of precipitation are small with frequent drought durations. Information on qualitative parameters of these valuable resources is very crucial as it might affect its applicability from agricultural, drinking, and industrial aspects. Although geo-statistics methods can provide insight about spatial distribution of quality factors, applications of advanced artificial intelligence (AI) models can contribute to produce more accurate results as robust alternative for such a complex geo-science problem. The present research investigates the capacity of several types of AI models for modeling four key water quality variables namely electrical conductivity (EC), sodium adsorption ratio (SAR), total dissolved solid (TDS) and Sulfate (SO4) using dataset obtained from 90 wells in Tabriz Plain, Iran; assessed by k-fold testing. Two different modeling scenarios were established to make simulations using other quality parameters and the geographical information. The obtained results confirmed the capabilities of the AI models for modeling the well groundwater quality variables. Among all the applied AI models, the developed hybrid support vector machine-firefly algorithm (SVM-FFA) model achieved the best predictability performance for both investigated scenarios. The introduced computer aid methodology provided a reliable technology for groundwater monitoring and assessment.

scholarly journals Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels

2021 ◽  
Author(s):  
Sina Sadeghfam ◽  
Rahman Khatibi ◽  
Tara Moradian ◽  
Rasoul Daneshfaraz
Keyword(s):  
Statistical Downscaling ◽  
Large Scale ◽  
Fuzzy Model ◽  
Support Vector ◽  
Monthly Precipitation ◽  
Local Data ◽  
Neuro Fuzzy ◽  
Level 1 ◽  
Environmental Prediction ◽  
Level 2

Abstract Topical research on hydrological impacts of climate change in terms of downscaling of monthly precipitation is investigated in this paper by formulating an inclusive multiple modelling (IMM) strategy. IMM strategies manage multiple models at two levels and the paper uses statistical downscaling model, Sugeno fuzzy logic and support vector machine at Level 1 and feeds their outputs to a neuro-fuzzy model at Level 2. In the downscaling stage, large-scale NCEP (National Centres for Environmental Prediction)/NCAR (National Centre for Atmospheric Research) data for a station with local data record from 1961 to 2005 are used for training and testing Level 1 models, which are found to be ‘fit-for-purpose’, but the variations between them signify some room for improvements. The model at Level 2 combines outputs of those at Level 1 and produces Level 2 results, which are over the Level 1 models in terms of dispersion of residual errors. In this way, IMM provides a more defensible modelling strategy for application in the projection stage. The comparison between observed and projected precipitation indicates that precipitation will be likely to reduce compared with observed precipitation in cold seasons (October–February), but the projected precipitation will be likely to increase slightly in wet seasons (April and May).

scholarly journals KLASIFIKASI MULTIKSKALA UNTUK PEMETAAN ZONA GEOMORFOLOGI DAN HABITAT BENTIK MENGGUNAKAN METODE OBIA DI PULAU PARI (MULTISCALE CLASSIFICATION FOR GEOMORPHIC ZONE AND BENTHIC HABITATS MAPPING USING OBIA METHOD IN PARI ISLAND)

2018 ◽  
Vol 14 (2) ◽  
Author(s):  
Ari Anggoro ◽  
Vincentius Paulus Siregar ◽  
Syamsul B. Agus
Keyword(s):  
Support Vector Machines ◽  
Support Vector ◽  
Benthic Habitat ◽  
Benthic Habitats ◽  
Vector Machines ◽  
Optimum Scale ◽  
Level 3 ◽  
Geomorphic Zone ◽  
Level 1 ◽  
Level 2

This study used multiscale classification and applied object-based image analysis (OBIA) for geomorphic zone and benthic habitats mapping in Pari islands. An optimized segmentation was performed to get optimum classification result. Classification methods for level 1 and 2 used contextual editing classification and for level 3 used support vector machines classifier. The results showed that overall accuracy for level 1 was 97% (reef level), level 2 was 87% (geomorphic zone), and level 3 was 75% (benthic habitats). Accuracy achieved by support vector machines classification was performed only in level 3 and optimum scale value achieved was 50 in compare with other scale values, i.e. 5, 25, 50, 75, 95. OBIA methods can be used as an alternative for geomorphic zone and benthic habitats map. Abstrak Penelitian ini menggunakan klasifikasi multiskala dan penerapan analisis citra berbasis obyek (OBIA) untuk pemetaan zona geomorfologi dan habitat bentik di Pulau Pari. Analisis berbasis obyek dilakukan optimasi pada proses segmentasi untuk mendapatkan hasil klasifikasi optimal. Metode klasifikasi pada level 1 dan 2 menggunakan klasifikasi contextual editing dan pada level 3 menggunakan klasifikasi Support Vector Machines (SVM). Hasil penelitian ini menunjukkan akurasi keseluruhan pada level 1 yaitu 97% (reef level), level 2 yaitu 87% (Geomorphic level), dan level 3 yaitu 75% (benthic habitat level). Klasifikasi SVM hanya diterapkan pada level 3 dan nilai skala optimum sebesar 50 dari percobaan nilai skala yaitu 5, 25, 50, 75, 95. Metode OBIA dapat digunakan sebagai alternatif untuk pemetaan zona geomorfologi dan habitat bentik.

scholarly journals PEMETAAN HABITAT BENTIK BERBASIS OBJEK MENGGUNAKAN CITRA SENTINEL-2 DI PERAIRAN PULAU WANGI-WANGI KABUPATEN WAKATOBI

2018 ◽  
Vol 10 (2) ◽  
pp. 381-396 ◽  
Author(s):  
La Ode Khairum Mastu ◽  
Bisman Nababan ◽  
James P Panjaitan
Keyword(s):  
Support Vector Machine ◽  
Decision Tree ◽  
Support Vector ◽  
Nearest Neighbour ◽  
Level 1 ◽  
Level 2 ◽  
Sentinel 2

Penelitian pemetaan habitat bentik di Pulau Wangi-wangi masih sangat sedikit dilakukan, sehingga ketersediaan data spasial habitat bentik di daerah ini sangat terbatas. Penelitian ini bertujuan untuk memetakan habitat bentik perairan dangkal menggunakan citra Sentinel-2 dengan metode klasifikasi berbasis objek/OBIA dan menghitung tingkat akurasi hasil klasifikasi habitat bentik di perairan Pulau Wangi-wangi Kabupaten Wakatobi. Penelitian ini dilaksanakan di perairan Pulau Wangi-wangi, khususnya perairan Sombu Dive dan sekitarnya. Penelitian ini menggunakan data satelit Sentinel-2 dengan resolusi spasial 10x10 m2 yang diakuisisi pada tanggal 4 April 2017 dan pengambilan data lapangan dilakukan pada bulan Maret - April 2017. Klasifikasi citra dengan metode OBIA menggunakan metode contextual editing pada level 1. Level 2 menggunakan klasifikasi terbimbing dengan beberapa algoritma klasifikasi yaitu support vector machine (SVM), decision tree (DT), Bayesian, dan k-nearest neighbour (KNN) dengan input themathic layer dari data lapangan. Klasifikasi habitat bentik dilakukan pada 12 dan 9 kelas dengan penerapan optimasi skala segmentasi yaitu 1, 1,5, 2, dan 2,5. Berdasarkan metode OBIA, habitat bentik dapat dipetakan dengan tingkat akurasi sebesar 60,4% dan 64,1% pada citra klasifikasi 12 dan 9 kelas secara berturut-turut pada nilai optimum skala segmentasi 2 dengan algoritma SVM.

Utilizing Artificial Intelligence to Collect Pavement Surface Condition Data

2020 ◽  
Vol 38 (1A) ◽  
pp. 74-82
Author(s):  
Hasan H. Joni ◽  
Imzahim A. Alwan ◽  
Ghazwan Naji
Keyword(s):  
Artificial Intelligence ◽  
Signal To Noise Ratio ◽  
Surface Condition ◽  
Discrete Wavelet ◽  
Signal To Noise ◽  
Band Frequency ◽  
Message Length ◽  
Frequency Components ◽  
Level 1 ◽  
Level 2

Recently the Discrete-Wavelet-Transform (DWT) has been represented as signal processing powerful tool to separate the signal into its band frequency components. In this paper, improvement of the steganography techniques by hiding the required message into the suitable frequency band is presented. The results show that the increase of the message length will reduce the Peak Signal to Noise Ratio (PSNR), while the PSNR increases with the increasing the  DWT levels. It should be noted that the PSNR reduction was from -13.8278 to -17.77208 when increasing the message length from 161 to 505 characters. In this context, the PSNR is increased from -13.8278 to 7.0554 and from -17.7208 to 1.7901 when the DWT increased from level (1) to level (2).

Sign in / Sign up

Export Citation Format

Share Document