A Multidisciplinary Approach for Evaluating Spatial and Temporal Variations in Water Quality

Le, Viet Thang; Quan, Nguyen Hong; Loc, Ho Huu; Duyên, Nguyễn Thị Thanh; Dung, Tran Duc; Nguyen, Hiep Dinh; Hung, Quang

doi:10.3390/w11040853

Cited by 11 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, MLP can predict and analyze the complex problem because it has some hidden layers that are able to learn the problem [31]. As opposed to these advantages, MLP necessitates long calculation times and a long training period since a hidden layer is necessary for computational purposes, increasing the necessary processing time [32]. In addition, one main difficult task in using MLP is to determine the suitable and correct network architecture that associate with input or hyperparameters in solving the problem [33].…”

Section: Comparative Analysis Of Existing Methodsmentioning

confidence: 99%

Classification of COVID-19 Symptoms Using Multilayer Perceptron

Azam,

Ismail,

Mohamad

et al. 2023

ijcsm

View full text Add to dashboard Cite

The COVID-19 virus had easily affected people worldwide through direct contact. Individuals diagnosed with positive COVID-19 virus may be affected with many symptoms, such as fever, tiredness, dry cough, difficulty in breathing, sore throat, chest pain, nasal congestion, runny nose, and diarrhea. An individual can also be diagnosed with COVID-19 even when he does not have any symptoms or be in contact with an infected person. Data classification was required due to the size of COVID-19 data that will be analyzed for future countermeasures determination. Some problems in data classification occurred due to unorganized data, such as time consumption, human error in complexity of symptom features and the diagnosis process data needed expert knowledge. This study aimed to use the artificial neural network (ANN) approach, which was multilayer perceptron (MLP) to classify the COVID-19 data by using patient symptom data. The MLP process involved data collection, data normalization, MLP design, MLP training, testing, and MLP verification. From the experiments, the MLP method was able to obtain an accuracy rate of 77.10%. In conclusion, the MLP method could classify the COVID-19 data and achieve a high accuracy rate

show abstract

Section: Comparative Analysis Of Existing Methodsmentioning

confidence: 99%

Classification of COVID-19 Symptoms Using Multilayer Perceptron

Azam,

Ismail,

Mohamad

et al. 2023

ijcsm

View full text Add to dashboard Cite

show abstract

“…However, it presents challenges in selecting the appropriate basis functions and determining the optimal number of functions. Additionally, the training phase of RBF networks tends to be computationally intensive, and they are sensitive to noisy data and high-dimensional datasets 58 . ELM offers key benefits, such as a reduced number of hyper-parameters, rapid training speed, and the ability to perform reasonably well with large datasets.…”

Section: Model Developmentmentioning

confidence: 99%

Artificial intelligence-based framework for precise prediction of asphaltene particle aggregation kinetics in petroleum recovery

Sharifzadegan,

Behnamnia,

Dehghan Monfared

2023

Sci Rep

View full text Add to dashboard Cite

The precipitation and deposition of asphaltene on solid surfaces present a significant challenge throughout all stages of petroleum recovery, from hydrocarbon reservoirs in porous media to wellbore and transfer pipelines. A comprehensive understanding of asphaltene aggregation phenomena is crucial for controlling deposition issues. In addition to experimental studies, accurate prediction of asphaltene aggregation kinetics, which has received less attention in previous research, is essential. This study proposes an artificial intelligence-based framework for precisely predicting asphaltene particle aggregation kinetics. Different techniques were utilized to predict the asphaltene aggregate diameter as a function of pressure, temperature, oil specific gravity, and oil asphaltene content. These methods included the adaptive neuro-fuzzy interference system (ANFIS), radial basis function (RBF) neural network optimized with the Grey Wolf Optimizer (GWO) algorithm, extreme learning machine (ELM), and multi-layer perceptron (MLP) coupled with Bayesian Regularization (BR), Levenberg–Marquardt (LM), and Scaled Conjugate Gradient (SCG) algorithms. The models were constructed using a series of published data. The results indicate the excellent correlation between predicted and experimental values using various models. However, the GWO-RBF modeling strategy demonstrated the highest accuracy among the developed models, with a determination coefficient, average absolute relative deviation percent, and root mean square error (RMSE) of 0.9993, 1.1326%, and 0.0537, respectively, for the total data.

show abstract

“…Hình 3 thể hiện cấu trúc của mạng RBF. Mô hình RBF có cấu trúc đơn giản và tốc độ học nhanh hơn so với mô hình MLP [11].…”

Section: Mô Hình Radial Basic Function (Rbf)unclassified

Xây dựng mô hình dự báo BOD5 cho hạ lưu sông Sài Gòn – Đồng Nai dựa trên các mạng nơ–ron nhân tạo MLP và RBF

Thúy¹,

Nhi²,

Măn³

et al. 2021

VNJHM

View full text Add to dashboard Cite

Tóm tắt: Nhu cầu oxy sinh hóa (BOD) là thông số chất lượng nước quan trọng để đánh giá mức độ ô nhiễm của nước trên các sông, hồ. Tuy nhiên, việc xác định nồng độ BOD 5 trong nước theo các phương pháp phân tích trong phòng thí nghiệm thường mất nhiều thời gian (5 ngày). Mục tiêu của nghiên cứu là xây dựng mô hình dự báo thông số BOD 5 dựa trên hai mô hình nơ-ron nhân tạo là MLP và RBF tại hạ lưu sông Sài Gòn-Đồng Nai và đánh giá hiệu quả dự báo giữa hai mô hình. Bảy kịch bản được xây dựng dựa trên tương quan riêng phần giữa thông số BOD 5 với các thông số chất lượng nước khác bao gồm COD, DO, TSS, Coliform, P-PO 4 3-, T và N-NH 4 + . Bộ dữ liệu bao gồm 08 thông số chất lượng nước theo tháng từ 2013-2018 và được chia thành hai phần theo tỷ lệ 75:25 phục vụ huấn luyện và kiểm tra các mô hình. Kết quả nghiên cứu cho thấy, cả hai mô hình MLP và RBF đều có khả năng dự báo tốt BOD 5 tại khu vực, tuy nhiên mô hình RBF với 05 thông số đầu vào (COD, DO, TSS, Coliform, P-PO 4 3-) cho kết quả dự báo tốt nhất với NSE = 0,855, R 2 = 0,9, RMSE = 0,529 cho quá trình huấn luyện và NSE = 0,848, R 2 = 0,865, RMSE = 0,454 cho quá trình kiểm tra. Kết quả nghiên cứu này cũng là nền tảng phục vụ cho việc dự báo các thông số chất lượng nước khác, cũng như dự báo ngắn hạn BOD 5 trong khu vực nghiên cứu.

show abstract

A Multidisciplinary Approach for Evaluating Spatial and Temporal Variations in Water Quality

Cited by 11 publications

References 24 publications

Classification of COVID-19 Symptoms Using Multilayer Perceptron

Classification of COVID-19 Symptoms Using Multilayer Perceptron

Artificial intelligence-based framework for precise prediction of asphaltene particle aggregation kinetics in petroleum recovery

Xây dựng mô hình dự báo BOD5 cho hạ lưu sông Sài Gòn – Đồng Nai dựa trên các mạng nơ–ron nhân tạo MLP và RBF

Contact Info

Product

Resources

About