Article
Engineering, Environmental
Justyna Kujawska, Malgorzata Pawlowska
Summary: Drill cuttings addition had a positive impact on the growth of Trifolium pretense L, but led to an increase in heavy metal concentrations with higher doses. The artificial neural network model showed over 90% correlation in predicting heavy metal content in clover grown in soils polluted with drill cuttings.
JOURNAL OF HAZARDOUS MATERIALS
(2022)
Article
Environmental Sciences
Seyed Faridedin Rafie, Hadi Abdollahi, Hani Sayahi, Faramarz Doulati Ardejani, Kioumars Aghapoor, Mohammad Hossein Karimi Darvanjooghi, Satinder Kaur Brar, Sara Magdouli
Summary: MnFe2O4 and CoFe2O4 nanoparticles were synthesized and used for the adsorption of Pb (II) and Cr (VI). The adsorbents showed high adsorption rates, reaching 90% of their capacity within 30 minutes. The adsorption capability of the Magnetic Nanoparticles (MNPs) was significantly higher at lower initial pollutant concentrations. A data-driven model of Artificial Neural Network accurately predicted the adsorption capacity. The mechanism involved electrostatic physisorption and a combination of ion exchange chemisorption and electrostatic physisorption.
Article
Environmental Sciences
Guangcai Yin, Xingling Chen, Hanghai Zhu, Zhiliang Chen, Chuanghong Su, Zechen He, Jinrong Qiu, Tieyu Wang
Summary: A novel interpolation method based on genetic algorithm and neural network model (GANN model) was proposed to improve the prediction accuracy of soil heavy metals (HMs) by spatial interpolation. The results showed that the GANN model had a good prediction performance with relatively lower root mean square error values compared to other traditional interpolation methods.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Computer Science, Information Systems
Wenbin Zou, Liang Chen, Yi Wu, Yunchen Zhang, Yuxiang Xu, Jun Shao
Summary: This article introduces a novel CNN-based super-resolution method named joint wavelet sub-bands guided network (JWSGN), which separates different frequency information of the image by the WT and recovers it through a multi-branch network. The method achieves better high-frequency detail reconstruction by using an edge extraction module and exploiting the complementary relationship between different frequencies.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Chemistry, Analytical
Antonella de las M. Biasi, Eduardo A. Takara, Maria L. Scala-Benuzzi, Agustina M. Valverde, Nidia N. Gomez, German A. Messina
Summary: Currently, there is a demand for fast and sensitive methods to monitor metals in water due to their increasing presence in the environment. This study evaluated different polymeric nanocomposites for the simultaneous electrochemical determination of Cu, Cd, and Zn in water samples. Screen-printed carbon electrodes were modified with nanocomposites containing graphene, graphite oxide, and polymers like polyethyleneimide, gelatin, and chitosan. The modified electrodes showed excellent performance for detecting metal ions in water samples using square-wave anodic stripping voltammetry.
ANALYTICA CHIMICA ACTA
(2023)
Article
Computer Science, Artificial Intelligence
Yue Yu, Kun She, Jinhua Liu, Xiao Cai, Kaibo Shi, O. M. Kwon
Summary: In recent years, deep learning super-resolution models for progressive reconstruction have achieved great success. However, these models ignore the information contained in the lower subspaces and do not explore the correlation between features in the wavelet and spatial domain, resulting in not fully utilizing the auxiliary information brought by multi-resolution analysis. Therefore, we propose a super-resolution network based on the wavelet multi-resolution framework (WMRSR) to capture the auxiliary information contained in multiple subspaces and to be aware of the interdependencies between spatial domain and wavelet domain features.
Article
Automation & Control Systems
Yuxiang Wei, Huan Wang
Summary: This paper proposes a noise-robust framework for wafer defect recognition, which utilizes discrete wavelet transform for frequency learning. It introduces a learnable discrete wavelet transform layer and a frequency-location attention module. Experimental results show that the framework achieves excellent performance in detecting wafer defect images, with an accuracy of 98.84%, and outperforms other methods under high noise ratios.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Environmental
Jyoti Singh, Sarvanshi Swaroop, Vishal Mishra
Summary: Researchers used decision tree and random forest regression algorithms to model and predict the adsorption capacity of fired and non-fired beads. The results showed that the random forest regression algorithm had better performance. This approach is an effective way to combat heavy metal contamination while reducing the number of experiments required.
JOURNAL OF ENVIRONMENTAL CHEMICAL ENGINEERING
(2022)
Article
Environmental Sciences
Kevin Lawrence M. De Jesus, Delia B. Senoro, Jennifer C. Dela Cruz, Eduardo B. Chan
Summary: This study used physicochemical parameters to assess HM concentration in SW and GW in Marinduque Island Province, Philippines. The developed NN-PSO models showed superior prediction capability compared to other models.
Article
Food Science & Technology
Oscar Lopez-Balladares, Patricio J. Espinoza-Montero, Lenys Fernandez
Summary: In this study, the concentration of Cd(II), Cu(II), and Fe(III) was determined in 13 brands of craft beer in Quito, Ecuador. The DPASV method on BDD was found to have acceptable precision and accuracy for the quantification of these metals. It was discovered that some beers did not comply with the permissible limits of food standards.
Article
Chemistry, Analytical
Wanqi Yang, Fusheng Li, Shubin Lyu, Qinglun Zhang, Yanchun Zhao
Summary: Soil is a significant source of potentially toxic metals that can enter the human body through the food chain. Accurate determination of elemental concentrations in soil is crucial for protecting human health, requiring reliable detection techniques. This study proposed a new quantitative analysis method that combines pre-processing and concentration prediction. The method achieved enhanced accuracy in identifying and removing spectral background, establishing instrument calibration curves, and accurately detecting the elemental concentration using a hierarchical deep neural network. The proposed method provides a new option for the elemental analysis of samples rich in potentially toxic metals.
JOURNAL OF ANALYTICAL ATOMIC SPECTROMETRY
(2023)
Article
Chemistry, Analytical
Mohammad Imran, Eun-Bi Kim, Dong-Heui Kwak, Sadia Ameen
Summary: A simple hydrothermal synthesis approach was used to synthesize porous MgNiO2 Chrysanthemum Flowers nanostructures, which were applied as a sensing electrode for quick detection of hazardous mercury ions. The MgNiO2 CFs based electrode showed good selectivity, sensitivity, and stability for Hg2+ ions, with a broad linear detection range.
Article
Biochemical Research Methods
Rui Wang, Zhipeng Zhang, Ruiyi Chen, Xiaohai Yu, Hongyu Zhang, Gang Hu, Qiegen Liu, Xianlin Song
Summary: A deep learning method is proposed to enhance the defocused resolution and signal-to-noise ratio in optical-resolution photoacoustic microscopy. Datasets with different noise levels were obtained using a virtual optical-resolution photoacoustic microscopy based on k-wave. A fully dense U-Net was trained with randomly distributed sources to improve the quality of photoacoustic images. The results show significant enhancements in PSNR, lateral resolution, and axial resolution of defocused regions.
JOURNAL OF BIOPHOTONICS
(2023)
Article
Agricultural Engineering
Mouna Dammak, Hajer Ben Hlima, Latifa Tounsi, Philippe Michaud, Imen Fendri, Slim Abdelkafi
Summary: Phycoremediation using oleaginous microalgae is an effective and eco-friendly method for removing heavy metals from contaminated waters.
BIORESOURCE TECHNOLOGY
(2022)
Article
Automation & Control Systems
Ziyan Zhao, Zhenfang Liu, Mingqiang Ji, Xin Zhao, Qibing Zhu, Min Huang
Summary: In this study, a novel deep learning method called ConInceDeep was proposed for component identification of mixture by Raman spectroscopy. It utilized continuous wavelet transform and multiple-size kernels to construct a 2D CNN model, improving the accuracy of identifying weak and overlapping spectral peaks in complex mixtures.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Marta Bonet-San-Emeterio, Noelia Felipe Montiel, Manel del Valle
Summary: This study successfully developed an enzymatic biosensor using reduced graphene oxide as a key nanomaterial for detecting contaminants. By modifying the graphene platform with laccase enzyme, the sensor became more selective and sensitive in detecting and inhibiting catalysts such as EDTA and benzoic acid.
Article
Chemistry, Analytical
Anna Herrera-Chacon, Andreu Gonzalez-Calabuig, Manel del Valle
Summary: This study introduces a voltammetric sensor based on a dummy molecularly imprinted polymer (MIP) for the detection of 2,4,6-trinitrotoluene (TNT) and 2,4-dinitrophenol (DNP). The sensor is cost-effective, rapid, and simple to use. Chemometric tools, particularly principal component analysis (PCA), demonstrate the sensor's potential applications in environmental settings for discriminating nitroaromatic and potential interfering species.
Article
Biophysics
Mingyue Wang, Xavier Ceto, Manel del Valle
Summary: This study explores the combination of chemometrics and electrochemical sensors modified with molecularly imprinted polymers (MIPs) for the development of MIP-based electronic tongues (ETs). The potential of this approach is demonstrated through the simultaneous determination of paracetamol, ascorbic acid, and uric acid mixtures in pharmaceutical samples. MIP-based sensors for different compounds were prepared using in situ electropolymerization and characterized by scanning electron microscopy and electrochemical methods. The developed sensors showed good performance, with good linearity and repeatability at the μM level. An artificial neural networks (ANNs) model was used for the quantification of individual substances in different pharmaceutical samples with satisfactory agreement between expected and obtained values.
BIOSENSORS & BIOELECTRONICS
(2022)
Article
Chemistry, Analytical
Dionisia Ortiz-Aguayo, Karolien De Wael, Manel del Valle
Summary: This study employed modified screen-printed carbon electrodes for the identification of drugs of abuse and cutting agents, using voltammetric sensing and chemometrics. The electrochemical fingerprints of codeine, heroin, and morphine were elucidated through Square Wave Voltammetry. Principal Component Analysis and Silhouette parameter assessment were used to select the most suitable combination of sensors for successful identification.
JOURNAL OF ELECTROANALYTICAL CHEMISTRY
(2021)
Article
Chemistry, Analytical
Dionisia Ortiz-Aguayo, Xavier Ceto, Karolien De Wael, Manel del Valle
Summary: This work evaluates the ability of an electronic tongue (ET) to resolve and quantify mixtures of different opiate compounds in the presence of common cutting agents. The study successfully resolved ternary mixtures of heroin, morphine, and codeine in the presence of caffeine and paracetamol. The developed sensors showed good linearity and low detection limits for the three drugs, and a quantitative model based on partial least squares regression (PLS) was able to accurately identify and quantify the individual substances from the voltammograms.
SENSORS AND ACTUATORS B-CHEMICAL
(2022)
Review
Multidisciplinary Sciences
Xavier Ceto, Manel Del Valle
Summary: This review provides an overview of the basic concepts and applications of electronic tongues (ETs) in environmental analysis, with a focus on monitoring, quality assessment, and pollutant detection in water and soil.
Article
Chemistry, Multidisciplinary
Mingyue Wang, Xavier Ceto, Manel del Valle
Summary: This study reports a voltammetric electronic tongue for simultaneous determination of fluoroquinolones in pharmaceutical and biological samples. The electronic tongue comprises four sensors modified with customized molecularly imprinted polymers and Au nanoparticle-decorated multiwall carbon nanotubes. The sensors showed different responses to the target fluoroquinolones and exhibited a wide detection range. The developed electronic tongue demonstrated satisfactory performance in the simultaneous determination of fluoroquinolones.
Article
Chemistry, Analytical
Guadalupe Yoselin Aguilar-Lira, Jesus Eduardo Lopez-Barriguete, Prisciliano Hernandez, Giaan Arturo Alvarez-Romero, Juan Manuel Gutierrez
Summary: This study simultaneously quantified four non-steroidal anti-inflammatory drugs (NSAIDs) - paracetamol, diclofenac, naproxen, and aspirin - in mixture solutions using a laboratory-made working electrode based on carbon paste modified with multi-wall carbon nanotubes (MWCNT-CPE) and Differential Pulse Voltammetry (DPV). The performance of the sensor was characterized using cyclic voltammetry, scanning electronic microscopy, and electrochemical impedance spectroscopy. A data compression strategy based on discrete wavelet transform was applied to handle the complexity and high dimensionality of the voltammograms. Partial Least Square Regression (PLS) and Artificial Neural Networks (ANN) were used to predict the drug concentrations in the mixtures. The results showed successful prediction of the concentration of paracetamol and diclofenac using PLS-adjusted models, achieving correlation values of R >= 0.9 (testing set). The ANN model exhibited good prediction results for all four analyzed drugs, with correlation values of R >= 0.968 (testing stage). Overall, the MWCNT-CPE electrode showed potential as a sensor for voltammetric determination and NSAID analysis.
Article
Chemistry, Analytical
Qing Wang, Xavier Ceto, Manel del Valle
Summary: Water quality monitoring is crucial in various areas and stages of modern societies. Conventional COD determination has limitations due to toxic reagents and potential interferences. Electrochemical COD determination, especially with the use of an electronic tongue, provides an alternative with satisfactory results.
Article
Chemistry, Analytical
Xavier Ceto, Munmi Sarma, Manel del Valle
Summary: Electronic tongues (ETs) are multisensor systems that can classify samples and quantify analytes. The stability and cross-sensitivity of the sensors are crucial for the success of ETs. However, the sensor selection is often overlooked in research. Therefore, this study proposes a simple methodology using principal component analysis and clustering indices to assess the suitability of sensors for a specific application.
Article
Food Science & Technology
Josep Pages-Rebull, Clara Perez-Rafols, Nuria Serrano, Manel del Valle, Jose Manuel Diaz-Cruz
Summary: Recent increase in spice and aromatic herb adulteration in the food industry necessitates comprehensive quality control. A new HPLC method with UV-vis detection was developed for the characterization, identification, and authentication of various spices and herbs. Chromatographic separation and analysis using chemometric techniques demonstrated the feasibility of classifying these products based on their characteristic biomarkers. PLS-DA showed better classification performance than SIMCA.
Article
Chemistry, Analytical
Ivet Jimenez, Clara Perez-Rafols, Nuria Serrano, Manel del Valle, Jose Manuel Diaz-Cuzc
Summary: A voltammetric sensor based on the modification of a screen-printed carbon electrode with reduced graphene oxide (rGO-SPCE) was developed for the determination of capsaicin. The sensor showed improved sensitivity and repeatability compared to other modified electrodes. It achieved a low limit of detection and provided accurate results for the determination of capsaicin in various samples.
MICROCHEMICAL JOURNAL
(2023)
Article
Chemistry, Analytical
Phanumas Yomthiangthae, Manel del Valle, Weena Siangproh
Summary: A novel sensing material was developed for the detection of L-hydroxyproline (Hyp). The material consisted of a bismuth film and poly(L-hydroxyproline) synthesized on a screen-printed graphene electrode. The sensor exhibited high response towards Hyp detection due to its large electroactive area. The sensor showed good selectivity and sensitivity, and could linearly measure Hyp concentrations in the range of 0.01-5.0 mM.
Proceedings Paper
Chemistry, Analytical
Xavier Ceto, Marta Bonet-San-Emeterio, Dionisia Ortiz-Aguayo, Elena Rodriguez-Franch, Manel del Valle
Summary: This paper explores the application of voltammetric sensors in combination with different chemometric tools for the identification and quantification of illicit drugs. By analyzing the whole voltammograms using pattern recognition methods to extract characteristic fingerprints, the drugs can be identified and quantified.
2022 IEEE INTERNATIONAL SYMPOSIUM ON OLFACTION AND ELECTRONIC NOSE (ISOEN 2022)
(2022)
Review
Multidisciplinary Sciences
Xavier Ceto, Manel del Valle
Summary: The assessment of water and soil quality is crucial for the health, economy, and sustainability of any community. Electronic tongues are emerging as a promising tool for sustainable and green monitoring of soil and water resources, given the challenge of monitoring a diverse range of compounds.