Convolutional Neural Network for Measurement of Suspended Solids and Turbidity

Lopez-Betancur, Daniela; Moreno, Iván; Guerrero-Mendez, Carlos; Saucedo-Anaya, Tonatiuh; González, Efrén; Bautista-Capetillo, Carlos; Gonzalez-Trinidad, Julián

doi:10.3390/app12126079

Cited by 14 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in Table 10, we have also included solutions based on remote sensing. In some cases, classification is used to quantify the turbidity [52][53][54][55], which is an imperfect solution compared with regression models. Of these papers, two of them use satellite images [52,53], and two of them use proximal sensing images gathered in the laboratory [54,55].…”

Section: Comparison With Existing Proposalsmentioning

confidence: 99%

“…In some cases, classification is used to quantify the turbidity [52][53][54][55], which is an imperfect solution compared with regression models. Of these papers, two of them use satellite images [52,53], and two of them use proximal sensing images gathered in the laboratory [54,55]. Among the papers that used the classification of turbidity to identify its source, the number of papers that used optical sensors is extremely limited.…”

Section: Comparison With Existing Proposalsmentioning

confidence: 99%

See 1 more Smart Citation

Combination of Machine Learning and RGB Sensors to Quantify and Classify Water Turbidity

Parra,

Ahmad,

Sendra

et al. 2024

Chemosensors

View full text Add to dashboard Cite

Turbidity is one of the crucial parameters of water quality. Even though many commercial devices, low-cost sensors, and remote sensing data can efficiently quantify turbidity, they are not valid tools for the classification it. In this paper, we design, calibrate, and test a novel optical low-cost sensor for turbidity quantification and classification. The sensor is based on an RGB light source and a light detector. The analyzed samples are characterized by turbidity values from 0.02 to 60 NTUs, and have four different sources. These samples were generated to represent natural turbidity sources and leaves in the marine areas close to agricultural lands. The data are gathered using 64 different combinations of light, generating complex matrix data. Machine learning models are compared to analyze this data, including training, validation, and test datasets. Moreover, different alternatives for data preprocessing and feature selection are assessed. Concerning the quantification of turbidity, the best results were obtained using averaged data and principal components analyses in conjunction with exponential gaussian process regression, achieving an R2 of 0.979. Regarding the classification of the turbidity, an accuracy of 91.23% is obtained with the fine K-Nearest-Neighbor classifier. The cases in which data were misclassified are characterized by turbidity values lower than 5 NTUs. The obtained results represent an improvement over the current solutions in terms of turbidity quantification and a completely novel approach to turbidity classification.

show abstract

Section: Comparison With Existing Proposalsmentioning

confidence: 99%

Section: Comparison With Existing Proposalsmentioning

confidence: 99%

Combination of Machine Learning and RGB Sensors to Quantify and Classify Water Turbidity

Parra,

Ahmad,

Sendra

et al. 2024

Chemosensors

View full text Add to dashboard Cite

show abstract

“…A high F-Score value indicates that the model performs better in positive cases. The sample size is denoted by N. A comprehensive description of the relationship between these parameters and a confusion matrix can be found in [36].…”

Section: Performance Evaluation Of Cnnmentioning

confidence: 99%

Pose Determination System for a Serial Robot Manipulator Based on Artificial Neural Networks

Rodriguez-Miranda

Yanez-Mendiola²,

Calzada-Ledesma

et al. 2023

Machines

View full text Add to dashboard Cite

Achieving the highest levels of repeatability and precision, especially in robot manipulators applied in automation manufacturing, is a practical pose-recognition problem in robotics. Deviations from nominal robot geometry could produce substantial errors at the end effector, which can be more than 0.5 inches for a 6 ft robot arm. In this research, a pose-recognition system is developed for estimating the position of each robot joint and end-effector pose using image processing. To generate the joint angle, the system is developed via the modeling of a pose obtained by combining a convolutional neural network (CNN) and a multi-layer perceptron network (MLP). The CNN categorizes the input image generated by a remote monocular camera and generates a classification probability vector. The MLP generates a multiple linear regression model based on the probability vector generated by a CNN and describes the values of each joint angle. The proposed model is compared with the P-n-Perspective problem-solving method, which is based on marker tracking using ArUco markers and the encoder values. The system was verified using a robot manipulator with four degrees of freedom. Additionally, the proposed method exhibits superior performance in terms of joint-by-joint error, with an absolute error that is three units less than that of the computer vision method. Furthermore, when evaluating the end-effector pose, the proposed method showed a lower average standard deviation of 9mm compared with the computer vision method, which had a standard deviation of 13 mm.

show abstract

“…Additionally, an SGD algorithm has also been implemented in turbidity and TSS tasks. Wan et al reached an R-squared of 0.931 [26], and Lopez-Betancur et al achieved 98.24% accuracy for turbidity, and a 97.20% for TSS estimation [27].…”

Section: Introductionmentioning

confidence: 99%

“…This methodology was adopted to maintain a controlled environment and eliminate variables that could introduce noise and optical aberrations. In this way, we ensure that the optimization algorithms focus on the nature of the database, which consists of black points (suspended solids) on a white background, analogous to liquid samples with suspended solids as referred as referred in articles [15][16][17]27]. The aim of this research is to identify the most suitable optimizer based on the nature of the database and to provide additional information about the performance of each optimizer.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Optimization Algorithms for Measurement of Suspended Solids

Lopez-Betancur,

González-Ramírez,

Guerrero-Mendez

et al. 2024

Water

Self Cite

View full text Add to dashboard Cite

Advances in convolutional neural networks (CNNs) provide novel and alternative solutions for water quality management. This paper evaluates state-of-the-art optimization strategies available in PyTorch to date using AlexNet, a simple yet powerful CNN model. We assessed twelve optimization algorithms: Adadelta, Adagrad, Adam, AdamW, Adamax, ASGD, LBFGS, NAdam, RAdam, RMSprop, Rprop, and SGD under default conditions. The AlexNet model, pre-trained and coupled with a Multiple Linear Regression (MLR) model, was used to estimate the quantity black pixels (suspended solids) randomly distributed on a white background image, representing total suspended solids in liquid samples. Simulated images were used instead of real samples to maintain a controlled environment and eliminate variables that could introduce noise and optical aberrations, ensuring a more precise evaluation of the optimization algorithms. The performance of the CNN was evaluated using the accuracy, precision, recall, specificity, and F_Score metrics. Meanwhile, MLR was evaluated with the coefficient of determination (R2), mean absolute and mean square errors. The results indicate that the top five optimizers are Adagrad, Rprop, Adamax, SGD, and ASGD, with accuracy rates of 100% for each optimizer, and R2 values of 0.996, 0.959, 0.971, 0.966, and 0.966, respectively. Instead, the three worst performing optimizers were Adam, AdamW, and NAdam with accuracy rates of 22.2%, 11.1% and 11.1%, and R2 values of 0.000, 0.148, and 0.000, respectively. These findings demonstrate the significant impact of optimization algorithms on CNN performance and provide valuable insights for selecting suitable optimizers to water quality assessment, filling existing gaps in the literature. This motivates further research to test the best optimizer models using real data to validate the findings and enhance their practical applicability, explaining how the optimizers can be used with real data.

show abstract

Convolutional Neural Network for Measurement of Suspended Solids and Turbidity

Cited by 14 publications

References 39 publications

Combination of Machine Learning and RGB Sensors to Quantify and Classify Water Turbidity

Combination of Machine Learning and RGB Sensors to Quantify and Classify Water Turbidity

Pose Determination System for a Serial Robot Manipulator Based on Artificial Neural Networks

Evaluation of Optimization Algorithms for Measurement of Suspended Solids

Contact Info

Product

Resources

About