Journal of Water Process Engineering
·
2024
·
IF 6.3
Zhineng Dai,Wenqi Zhang,Jiazhong Li,Yicheng Wu,Haiyan Fu
The prediction of Tetracycline hydrochloride (TCH) degradation using artificial intelligence (AI) has garnered increasing interest due to its potential to significantly reduce experimental costs. Despite this interest, the methods and techniques in this area remain underdeveloped and require further research. As AI technology advances, an expanding array of techniques becomes available for application in degradation prediction. In this study, polyaniline (PANI) was selected as a three-dimensional particle electrode for the degradation of TCH. We utilized five input variables: initial concentration, voltage, electrolyte concentration, particle concentration, and time, with the absorbance after degradation serving as the output. By integrating extreme gradient boosting (XGB) and a multilayer perceptron (MLP), we successfully developed the XGB_MLP model. This model achieved a predictive accuracy (R 2 ) of 98.52 % and a root mean square error (RMSE) of 0.052. Furthermore, a degradation rate of 83.48 % was observed for 10 ppm of TCH after 120 min. The findings of this study underscore the capability of the XGB_MLP model to accurately predict the degradation rate of TCH through electrochemical degradation.
研究领域:
环境科学
·
人工智能
·
化学工程
✓ 已验证
产品关联
DOI
高影响因子
MICROCHEMICAL JOURNAL
·
2025
·
IF 5.1
Chengpan Lei,Xiaobin Zhang,Zhikang Rao,Shenghui Chen,Siqi Dong,Hanyang Bao,Ying Xu
An electrochemical impedance detection method based on 3-aminophenylboronic acid-modified magnetic nanoparticles (M-APBA) is proposed, with machine learning models employed to facilitate high-sensitivity and high-accuracy glucose detection in complex biological samples. By leveraging the specific binding affinity between synthesized M-APBA nanoparticles and glucose, detection sensitivity and anti-interference capability were significantly enhanced. Experimental results demonstrated a well-defined linear response for glucose concentrations ranging from 1 to 50 μmol L −1 , with a detection limit as low as 0.71 μmol L −1 . Multidimensional impedance spectral features were extracted using the Randles equivalent circuit model, and the prediction accuracy of glucose concentration in real sample was significantly improved by incorporating an XGBoost model optimized via grid search method. The model achieved an R 2 value of 0.9997, with mean absolute error (MAE) and root mean square error (RMSE) reduced to 0.1068 and 0.2321, respectively. Compared with traditional single-feature fitting methods (the Rct value), the proposed multi-feature fusion approach demonstrated superior detection accuracy and stability in complex biological samples. Furthermore, measurements conducted on real samples revealed that M-APBA nanoparticle-modified electrodes maintained excellent detection performance in complex environments, exhibiting high repeatability and strong anti-interference capability. This study proposes a non-enzymatic glucose detection strategy by integrating M-APBA-modified magnetic nanoparticles with a machine learning-based impedance analysis framework, offering a novel solution for non-invasive, real-time glucose monitoring and demonstrating great potential for application in portable, low-cost wearable detection devices.
研究领域:
电化学传感器
·
纳米技术
·
生物医学工程
·
机器学习
·
分析化学
·
可穿戴设备
✓ 已验证
产品关联
DOI
高影响因子
FUEL
·
2025
·
IF 7.5
Songtao Wu,Modi Guan,Xiaohan Wang,Jing Zhang,Yuhang Zhou,Xiu Huang,Bin Pan
Wettability is a pivotal parameter to determine hydrocarbon reserves and production in shale reservoirs, typically characterized quantitatively by shale-oil-brine contact angles. This parameter is a complex function of shale composition, fluid properties, temperature etc. and is therefore very difficult for conventional theoretical methods to predict accurately and efficiently. Therefore, herein machine learning methods [eXtreme gradient boosting (XGBoost) and the Shapley additive explanations (SHAP)] were integrated to predict this parameter and analyze its sensitivity. To make up the shortage of available data in literature (only 162 data points), another 100 data points about shale/mineral-alkane-water contact angles were measured under in-situ reservoir conditions using the sessile droplet method, thus totally 262 data points were used for machine learning. Experimental results showed that shale, quartz, mica and albite became more hydrophilic with increasing temperature from 25 ℃ to 70 ℃, while K-feldspar and dolomite demonstrated the opposite trend; shale-alkane-water contact angle increased from 60° to 149° (thus wettability shifted from water-wet to oil-wet) with increasing TOC content from 1.9 wt% to 10 wt%. The XGBoost model demonstrated superior predictive accuracy than the gradient boosting regressor and support vector machine models (e.g. R 2 is 0.913, 0.876 and 0.623, respectively). The SHAP sensitivity analysis revealed that brine ionic strength, TOC content, calcite content and quartz content were the four most influential factors affecting wettability. This work presents an efficient artificial intelligence method for shale wettability prediction, which is beneficial for hydrocarbon reserves estimation and production in shale reservoirs.
研究领域:
石油工程
·
地质学
·
人工智能
✓ 已验证
产品关联
DOI
高影响因子
CHEMISTRY OF MATERIALS
·
2022
·
IF 10.508
Qin Hong,Xiao-Yuan Wang,Ya-Ting Gao,Jian Lv,Bin-Bin Chen,Da-Wei Li,Ruo-Can Qian
Fluorescent carbon dots (CDs) have been increasingly used in fluorescence detection and imaging based on their tunable fluorescence (FL) and resistance to photobleaching. However, the fast and reliable design of fluorescent CDs with specific optical properties involves a number of factors, such as the concentration of precursors, reaction time, and solvents. Therefore, it is usually considered difficult to design CDs with favorable optical properties. Herein, we report an extreme gradient boosting (XGBoost) model for guiding the fabrication of CDs with high FL intensity and tunable emission from p-benzoquinone (PBQ) and ethylenediamine (EDA) in different solvents at room temperature. Among a variety of studied machine learning models, XGBoost shows the best performance in the field of material synthesis, with a prediction coefficient of determination (R2) higher than 0.96. The XGBoost model can effectively predict the optical properties of CDs, including the maximum FL intensity and emission centers. Guided by the XGBoost model, various green or blue fluorescent CDs with adjustable emission centers and solubility properties are designed and fabricated accurately. These CDs are successfully applied for Fe3+ detection, sustained drug release, whole-cell imaging, and poly(vinyl alcohol) (PVA) film preparation. These results suggest the great potential of the combination of machine learning and CD synthesis as an effective strategy to help researchers realize accurate selection of reasonable CDs with individual customized properties to achieve different goals.
研究领域:
材料科学
·
生物医学工程
✓ 已验证
产品关联
DOI
高影响因子
Journal of the Mechanical Behavior of Biomedical Materials
·
2025
·
IF 3.5
Jun Li,Chuang Zhang,Weiwei Lan,Weiyi Chen,Di Huang
Polyvinyl alcohol (PVA) hydrogels have garnered increasing interest in the field of biomedical materials due to their excellent biocompatibility and controllable mechanical properties. Although various preparation strategies such as freeze-thaw cycles, solvent-exchange, salting-out and annealing treatments have been extensively employed in the preparation of PVA hydrogels, the current literature lacks systematic comparisons under the same PVA molecular weight and mass fraction conditions. It limited the in-depth understanding of the mechanism of optimizing the properties of PVA hydrogels and could not provide guidance for the construction of high strength pure PVA hydrogels. In this study, PVA with a molecular weight of 145,000 was utilized to prepare hydrogels with mass fraction of 10 wt%, 15 wt%, and 20 wt% using the aforementioned four preparation strategies. We thoroughly investigated the effects of preparation strategies and mass fraction on the mechanical properties of PVA hydrogels by employing the eXtreme Gradient Boosting (XGboost) machine learning model for precise data analysis and predictions. Additionally, we also investigated the effects of different preparation strategies and mass fraction on the microstructure and surface properties of PVA hydrogels. The results indicated that the choice of preparation strategies significantly influenced the mechanical properties of PVA hydrogels, surpassing the effects of PVA mass fraction. Notably, under the same preparation conditions, the 20 wt% annealing-PVA hydrogels exhibited the best tensile strength (3.96 ± 0.511 MPa), tensile modulus (4.36 ± 0.160 MPa), and compressive modulus (3.17 ± 0.644 MPa), representing increases of 10 times, 62 times, and 26 times, respectively, compared to freeze-thaw cycles-PVA, while also demonstrating the lowest friction coefficient (0.05). According to the XGboost machine learning model, it showed that the PVA mass fraction had 26.21 % of the effect on the variation of mechanical properties, while the preparation strategy accounted for the remaining 73.79 %. In summary, we successfully established the correlation between the mechanical properties of PVA hydrogels and preparation parameters, providing a solid technical foundation for the development of high strength pure PVA hydrogels.
研究领域:
材料科学
·
生物医学工程
·
人工智能
✓ 已验证
产品关联
DOI
PubMed
高影响因子
CERAMICS INTERNATIONAL
·
2024
·
IF 5.1
Xiao Zong,Shuangshuang Wu,Kunji Lin,Jintao Zhang,Yehua Li,Donglin Lu,Xin Deng,Shengguo Lu,Jihua Qiu,Yuanzhi Shao,Shanghua Wu
Improving the thermal conductivities and bending strengths of ceramic substrates is crucial for their applicability as key components of integrated chips. Herein, we report the latest study in which the thermal conductivity and bending strength of aluminum nitride (AlN) ceramics were systematically predicted using high-precision prediction model approached with a machine learning (ML) method based on extreme gradient enhancement method (XGBoost). The ML model was used to rank the effects of the process parameters, and SHapley Additive exPlanations (SHAP) was employed to quantify the contributions of different factors. Sintering additives were found to have the predominant influence on the thermal conductivity and bending strength; particularly, those with cationic radii within 0.085–0.105 nm enhance both properties. By using Pr 2 O 3 as the sintering additive and adopting the preparation conditions recommended by the ML model, we prepared AlN ceramics with thermal conductivity as high as 195.63 W m −1 K −1 and bending strength of 371.60 ± 9.31 MPa, thus satisfying the application requirement of high thermal conductivity . The proposed model is also applicable to alumina and silicon nitride ceramics. This study provides a practicable and once-for-all strategy to realize the entire process from the ML prediction design to the preparation of ceramic materials exhibiting superior thermal conductivity and high strength.
研究领域:
材料科学
·
人工智能
✓ 已验证
产品关联
DOI
高影响因子
International Journal of Electrochemical Science
·
2024
·
IF 1.3
Bo Zhang,Yao Zhang,Jianing Shen,Zhehai Zhou,Guixian Zhu
In the electrochemical detection process, determining the optimal experimental conditions for the standard curve often requires multiple iterations. A low-concentration glucose detection method that combines electrochemical principles with machine learning was introduced to address the challenge of determining the optimal reactant addition in electrochemical detection. We developed a model that incorporates electrochemical curve features and various experimental conditions as variables. Concentration regression analysis was conducted using five machine learning models: Multiple Linear Regression (MLR), Decision Trees (DT),Artificial Neural Networks (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The results show that the performance of the XGBoost model surpasses that of the other models. Compared to the second place—Random Forest model, it reduces the Mean Absolute Error (MAE) by 21.6 % and the Root Mean Square Error (RMSE) by 25.3 %. This method can be used for low-concentration glucose detection, addressing the challenge of determining the optimal experimental conditions. It mitigates the impact of experimental conditions on detection results, enhances concentration determination accuracy, and provides new methods for determining the optimal experimental conditions and improving detection accuracy in the field of detection and analysis.
研究领域:
生物医学工程
·
分析化学
✓ 已验证
产品关联
DOI
高影响因子
MICROCHEMICAL JOURNAL
·
2026
·
IF 5.2
Shenghui Chen,Luming Xu,Wei Yu,Xiaobin Zhang,Shijuan Cao,Bo Liang,Ying Xu
A MIP/AuNPs/GCE electrode was constructed for simultaneous detection of CAP and MNZ. • The sensor shows a wide linear range (50–1500 μM) and low LODs of 1.70 and 2.09 μM. • Wavelet transform expands the feature dimensions of the DPV signals to enhance model prediction accuracy. • TPE-optimized XGBoost realizes accurate and robust dual-analyte concentration prediction. • The method achieves satisfactory recoveries in milk, fish, and egg real samples. Food safety concerns have increased the demand for reliable simultaneous detection of chloramphenicol (CAP) and metronidazole (MNZ), as these antibiotics are strictly regulated due to their potential health risks. However, the presence of aromatic nitro groups in both compounds poses a challenge for their simultaneous detection. In this study, an electrochemical sensor integrating electrodeposited gold nanoparticles (AuNPs) with a dual-template molecularly imprinted polymer (MIP) film was developed to achieve selective recognition and signal enhancement for both analytes. However, competitive adsorption at active sites in multi-component systems leads to nonlinear signal responses, rendering traditional linear calibration ineffective. To overcome this limitation, differential pulse voltammetry (DPV) signals were transformed into two-dimensional wavelet spectrograms, from which quantitative image features were extracted, and the necessity and robustness of these features were verified using SHAP analysis. An XGBoost regression model optimized via a Tree-structured Parzen Estimator (TPE) was subsequently constructed, yielding significantly improved predictive performance. The sensor exhibited a wide linear range for both CAP and MNZ (50–1500 μM) and low detection limits (1.70 μM and 2.09 μM, respectively). Satisfactory recoveries (89.37–107.31%) were obtained in spiked milk and fish samples. The proposed TPE-XGBoost-assisted dual-template molecular sensor provides a robust and generalizable strategy for rapid and accurate multi-residue detection in complex food matrices. Download: Download high-res image (218KB) Download: Download full-size image
✓ 已验证
产品关联
DOI
高影响因子
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS
·
2025
·
IF 3.1
Abulimiti Yasen,Yuxia Zhou,Wenhan Gao,Zhongxin Zhang,Reyihan Tudi,Mei Xiang,Bumaliya Abulimiti
Laser-Induced Breakdown Spectroscopy (LIBS) holds significant value for rapid elemental detection; however, strong spectral interference, matrix effects, and high-dimensional data characteristics pose considerable challenges to accurate quantitative analysis. To enhance the performance of LIBS quantitative analysis, this study proposes a novel machine learning framework that integrates XGBoost and Multilayer Perceptron (MLP), optimized by a Multi-dimensional Adaptive Sparrow Search Algorithm (MA-SSA). The framework employs XGBoost for automated feature selection, eliminating redundant spectral variables while retaining critical information, and utilizes MA-SSA to optimize the hyperparameters of the MLP in regression tasks, significantly improving model stability and prediction accuracy. Experimental results demonstrate that the proposed method achieves 100% accuracy in multi-class classification, outperforming traditional classifiers such as Random Forest, XGBoost, and standalone MLP. In terms of quantitative detection, the MA-SSA-optimized model achieves an RMSE of 4.43 µg/g, surpassing other hybrid optimization models including XGBoost-SSA-MLP (RMSE=4.62 µg/g), XGBoost-PSO-MLP (RMSE=5.225 µg/g), and XGBoost-GA-MLP (RMSE=5.584 µg/g). XGBoost-based feature selection effectively reduces spectral dimensionality while maintaining predictive performance. The proposed MA-SSA algorithm further enhances convergence efficiency and generalization capability. This study provides a robust, efficient, and scalable solution for LIBS analysis, with broad application potential in the field of real-time quantitative detection.
研究领域:
分析化学
·
机器学习
·
光谱学
·
环境监测
·
药物分析
·
食品安全
✓ 已验证
DOI
PubMed
高影响因子
Journal of Environmental Chemical Engineering
·
2025
·
IF 7.2
Nian Liu,Tianlin Ren,Ziyan Cai,Wenjie Liu,Li He,Xichu Qiao,Xuhui Mao
Advanced Oxidation Processes (AOPs) are widely employed for the degradation of polycyclic aromatic hydrocarbons (PAHs). Determining the optimal oxidation method and corresponding process parameters is crucial for achieving the maximum degradation efficiency. Due to the complexity of AOPs, conventional kinetic models and machine learning approaches show limited accuracy in predicting the degradation kinetics of PAHs, making them inadequate in optimizing process parameters for engineering practices. This study pioneers the use of convolutional neural networks (CNN) for deep feature extraction from the gas chromatography-mass spectrometry (GC-MS) data of pyrene degradation. Meanwhile, the Fourier-based temporal embedding (FTE) method was adopted to map the discrete time into continuous frequency-domain features, preserving a temporal continuity across reaction trajectories. The fusion of CNN-extracted MS features, FTE, and reaction conditions within an eXtreme Gradient Boosting (XGBoost) framework yielded a novel CNN-FTE-XGBoost hybrid model, enabling a cross-scale modeling of degradation kinetics. The CNN-FTE-XGBoost architecture demonstrated exceptional prediction accuracy on pyrene degradation efficiency ( R ²=0.951, RMSE=0.046, MAE=0.039). SHapley Additive exPlanations (SHAP) analysis further identified the key factors influencing pyrene degradation efficiency, verifying the interpretability of model. This work establishes an interpretable multimodal fusion-driven modeling framework for a high-precision prediction of pollutant degradation in AOPs, providing a reliable tool for AI-guided optimization of AOPs in remedial applications.
研究领域:
环境工程
·
环境科学中的机器学习
·
化学降解动力学
·
分析化学
·
可持续性人工智能
✓ 已验证
产品关联
DOI
高影响因子
CHEMICAL ENGINEERING JOURNAL
·
2025
·
IF 13.2
Tao Chen,Peng Liu,Yu Ge,Xiaoting Lei,Zhenzong Fan,Xiaoyu Zhu,Yangping Wen,Hassan Karimi-Maleh,Xiaoqiang Wang
Sesamol is a momentous marker for evaluating the quality of sesame or sesame products. In this study, a new strategy for fabricating portable smartphone sensor based on violet phosphorene (VP)/two-dimensional transition metal borides (MBene) nanozyme modified with Au − Ag bimetallic nanoparticles (Au − AgNPs) on the surface of the screen-printed electrode, which is synthesized under the guidance of machine learning (ML) with eXtreme Gradient Boosting (XGBoost) algorithms, is described for intelligent sensing of sesamol in farmland and agricultural fields. A fluorine-free hydrothermal-assisted alkane etching strategy is used to prepare the fence-like MoAlB-MBene. Highly environmentally stable VP/MoAlB-MBene nanozyme decorated by Au − Ag bimetallic nanoparticles is obtained by ultrasonic-assisted liquid-phase exfoliation with XGBoost assistance. The ML models including artificial neural network, support vector machine and XGBoost for the synthesis of nanozyme are contrasted and discussed, and the XGBoost algorithm is found as the most accurate model for synthesizing nanozyme due to the highest value of correlation coefficient. The nanozyme-modified screen-printed carbon electrode coupled with the palm-sized smartphone-controlled wireless electrochemical device as a portable wireless intelligent sensing platform for the determination of sesamol in a wider linear range of 0.1 ∼ 1000 μmol/L with a lower limit of detection of 21 nmol/L, which enable the on-site determination of 10 varieties of sesame seeds. This work will provide a new reference for the one-step preparation of bimetallic nanoparticles decorated graphene-like nanozyme guided by ML for cost-effective, simple, fast detection of phytochemicals in agricultural products using a portable smartphone sensor.
研究领域:
食品科学
·
材料科学
·
人工智能
·
分析化学
✓ 已验证
产品关联
DOI
高影响因子
CURRENT MEDICINAL CHEMISTRY
·
2024
·
IF 3.5
Gan Xin,Xie Jingwen,Dong Zhaojun,Wu Yuna,Zeng Xiaoqing,Yang Zhenzhen,Liu Bo,Zhu Min,Wang Bozhen,Li Wulan,Wang Ledan,Zhang Huajie,Wu Jianzhang,Hu Yue
Background: Pyroptosis, a cell death process triggered by chemotherapy drugs, has
emerged as a highly promising mechanism for combating tumors in recent years. As the lead of
new drugs, natural products play an important role in the discovery of anticancer drugs. Compared
to other natural products, the medicine food homologous natural products (MFHNP) exhibit a superior
safety profile. Among a series of MFHNP molecular skeletons, this study found that only
benzylideneacetophenone (1) could induce cancer cell pyroptosis. However, the anti-cancer activity
of 1 remains to be improved.
Aims: This study aimed to find a pyroptosis inducer with highly effective antitumor activity by
modifying the chalcone structure.
Methods: To examine the effect of the Michael receptor in compound 1 on the induction of pyroptosis,
several analogs were synthesized by modifying the Michael acceptor. Subsequently, the anticancer
activity was tested by MTT assay, and morphological indications of pyroptosis were observed
in human lung carcinoma NCI-H460 and human ovarian cancer CP-70 cell lines. Furthermore,
to improve the activity of the chalcone skeleton, the anticancer group 3,4,5-
trimethoxyphenyl was incorporated into the phenyl ring. Subsequently, compounds 2-22 were designed,
synthesized, and screened in human lung cancer cells (NCI-H460, H1975, and A549). Additionally,
a quantitative structure-activity relationship (QSAR) model was established using the
eXtreme Gradient Boosting (XGBoost) machine learning library to identify the pharmacophore.
Furthermore, both in vitro and in vivo experiments were conducted to investigate the molecular
mechanisms of pyroptosis induced by the active compound.
Results: α, β-unsaturated ketone was the functional group of the chalcone skeleton and played a
pivotal role in inducing cancer cell pyroptosis. QSAR models showed that the regression coefficients
(R2) were 0.992 (A549 cells), 0.990 (NCI-H460 cells), and 0.998 (H1975 cells). Among these
compounds, compound 7 was selected to be the active compound. Moreover, compound 7 was
found to induce pyroptosis in lung cancer cells by upregulating the expression of CHOP by increasing
the ROS level. Furthermore, it effectively suppressed the growth of lung cancer xenograft
tumors.
Conclusion: Compound 7 exhibits antineoplastic activity by regulating the ROS/ER stress/pyroptosis
axis and is a kind of promising pyroptosis inducer.
研究领域:
肿瘤学
·
药理学
·
药物化学
·
分子生物学
✓ 已验证
DOI
PubMed
高影响因子
危险品化学品经营许可证（带存储）