A hybrid linear–nonlinear model with two-stage feature selection for TiO2 content prediction in ilmenite based on XRF spectroscopy

X-ray fluorescence (XRF) spectroscopy provides an efficient and non-destructive means for determining the Titanium Dioxide (TiO2) content in ilmenite. However, the accuracy of this technique can be compromised by matrix effects, and its industrial application is often bottlenecked by the limited ava...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Minerals engineering Jg. 236; S. 109929
Hauptverfasser: Dai, Wei, Duan, Mingzi, Nan, Jing, Wang, Lanhao
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.02.2026
Schlagworte:
ISSN:0892-6875
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract X-ray fluorescence (XRF) spectroscopy provides an efficient and non-destructive means for determining the Titanium Dioxide (TiO2) content in ilmenite. However, the accuracy of this technique can be compromised by matrix effects, and its industrial application is often bottlenecked by the limited availability of labeled samples. To address this issue, this paper proposes an efficient method (L(FeTi)-CMI-SICA) for predicting the TiO2 content in ilmenite. The paper initially proposes a two-stage feature selection method based on physical mechanism analysis and mutual information statistics, aimed at addressing the issue of inaccurate feature selection due to matrix effects. Subsequently, this paper introduces a Stacked Interpretable Constructive Algorithm (SICA) for resource-constrained industrial scenarios, which achieves precise modeling of the complex nonlinear relationships in XRF data through a multi-layer feature abstraction mechanism. Finally, this paper employs SICA as the nonlinear component of the model, combining it with linear least squares regression to construct a linear–nonlinear hybrid model. Extensive experiments on the ilmenite XRF dataset demonstrate that our method not only achieves superior performance across key metrics but also exhibits remarkable robustness under the constraint of small-sample conditions. •A two-stage feature selection method is proposed to accurately identify key features for TiO2 content prediction in ilmenite.•A hybrid model is developed to effectively correct matrix effects and enhance prediction accuracy.•Stacked Interpretable Constructive Algorithm (SICA) employs a multi-layer feature abstraction mechanism to precisely model complex nonlinear relationships in XRF data.•Extensive experiments on industrial dataset show that our method outperforms existing approaches in prediction accuracy.
AbstractList X-ray fluorescence (XRF) spectroscopy provides an efficient and non-destructive means for determining the Titanium Dioxide (TiO2) content in ilmenite. However, the accuracy of this technique can be compromised by matrix effects, and its industrial application is often bottlenecked by the limited availability of labeled samples. To address this issue, this paper proposes an efficient method (L(FeTi)-CMI-SICA) for predicting the TiO2 content in ilmenite. The paper initially proposes a two-stage feature selection method based on physical mechanism analysis and mutual information statistics, aimed at addressing the issue of inaccurate feature selection due to matrix effects. Subsequently, this paper introduces a Stacked Interpretable Constructive Algorithm (SICA) for resource-constrained industrial scenarios, which achieves precise modeling of the complex nonlinear relationships in XRF data through a multi-layer feature abstraction mechanism. Finally, this paper employs SICA as the nonlinear component of the model, combining it with linear least squares regression to construct a linear–nonlinear hybrid model. Extensive experiments on the ilmenite XRF dataset demonstrate that our method not only achieves superior performance across key metrics but also exhibits remarkable robustness under the constraint of small-sample conditions. •A two-stage feature selection method is proposed to accurately identify key features for TiO2 content prediction in ilmenite.•A hybrid model is developed to effectively correct matrix effects and enhance prediction accuracy.•Stacked Interpretable Constructive Algorithm (SICA) employs a multi-layer feature abstraction mechanism to precisely model complex nonlinear relationships in XRF data.•Extensive experiments on industrial dataset show that our method outperforms existing approaches in prediction accuracy.
ArticleNumber 109929
Author Wang, Lanhao
Duan, Mingzi
Nan, Jing
Dai, Wei
Author_xml – sequence: 1
  givenname: Wei
  surname: Dai
  fullname: Dai, Wei
  organization: School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, Jiangsu Province, China
– sequence: 2
  givenname: Mingzi
  surname: Duan
  fullname: Duan, Mingzi
  organization: School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, Jiangsu Province, China
– sequence: 3
  givenname: Jing
  surname: Nan
  fullname: Nan, Jing
  email: jingn@cumt.edu.cn
  organization: School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, Jiangsu Province, China
– sequence: 4
  givenname: Lanhao
  surname: Wang
  fullname: Wang, Lanhao
  organization: State Key Laboratory of Coking Coal Resources Green Exploitation, China University of Mining and Technology, Xuzhou 221116, China
BookMark eNp9UMFKAzEQzaGCrfoHHvIDW5Nss7u5CKVYFQoFqeAtZDezbcpuUpJo6c2Df-Af-iWmrGdhYIY3vDfz3gSNrLOA0C0lU0pocbef9saC3U4ZYTxBQjAxQmNSCZYVVckv0SSEPSGEl5UYo6853p1qbzTuEk35n8_vJDjMuHcaOnw0cYfj0WUhqi3gFlR894ADdNBE4yxunccbs2a4cTaCjfjgQZthZ1J1PVgTAdcqgMYJfHtZ4nBIbO9C4w6na3TRqi7AzV-_Qq_Lh83iKVutH58X81XW0JLFjCrgShMQVZuagLrmjKiaEw1KVAJErgsCuS6rusjZTGhGWbLJCq7ymtMqv0KzQbdJh4OHVh686ZU_SUrkOT25l0N68pyeHNJLtPuBBum3DwNehsaAbZJJn0xI7cz_Ar83u4IH
Cites_doi 10.1016/j.ijmst.2022.05.001
10.1039/D2AY00593J
10.1016/j.apradiso.2022.110191
10.1016/j.mineng.2019.106117
10.3390/agronomy10060787
10.1016/j.fuel.2022.125991
10.1007/s10661-022-09750-x
10.1016/j.mineng.2024.109002
10.1016/j.microc.2019.03.077
10.1002/1099-128X(200009/12)14:5/6<751::AID-CEM622>3.0.CO;2-D
10.1016/j.mineng.2022.107458
10.1088/1361-6501/abf61a
10.1039/D3JA00392B
10.1016/j.chemolab.2023.104842
10.1109/TII.2024.3423487
10.1109/72.623214
10.1039/D3JA00120B
10.1016/j.molliq.2020.113726
10.1016/j.engappai.2023.107052
10.1109/TIM.2023.3328080
10.1038/s41598-024-53988-z
10.46770/AS.2020.01.003
10.1016/j.sab.2006.06.014
10.1016/j.sab.2024.107001
10.1016/j.aca.2024.343073
10.1016/j.mineng.2023.108003
10.1016/j.sab.2021.106310
ContentType Journal Article
Copyright 2025 Elsevier Ltd
Copyright_xml – notice: 2025 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.mineng.2025.109929
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_mineng_2025_109929
S0892687525007575
GroupedDBID --K
--M
.~1
0R~
123
1B1
1RT
1~.
1~5
29M
4.4
457
4G.
5VS
7-5
71M
8P~
9DU
9JN
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYWO
ABFNM
ABJNI
ABMAC
ABNUV
ABQEM
ABQYD
ABWVN
ABXDB
ACDAQ
ACGFS
ACLOT
ACLVX
ACRLP
ACRPL
ACSBN
ACVFH
ADBBV
ADCNI
ADEWK
ADEZE
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHPOS
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKURH
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
ASPBG
ATOGT
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
ENUVR
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HMA
HVGLF
HZ~
IHE
IMUCA
J1W
KOM
LY3
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SDF
SDG
SEP
SES
SET
SEW
SPC
SPCBC
SSE
SSG
SSZ
T5K
WUQ
XPP
ZMT
~02
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c172t-1ae5ad0e98fad09ebb520ab50dea989e93d60e3d78b63249d212057265a3b5183
ISSN 0892-6875
IngestDate Thu Nov 27 01:03:10 EST 2025
Wed Dec 10 14:25:50 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Hybrid model
X-ray fluorescence
Geometric control strategy
Stacked structure
Ilmenite
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c172t-1ae5ad0e98fad09ebb520ab50dea989e93d60e3d78b63249d212057265a3b5183
ParticipantIDs crossref_primary_10_1016_j_mineng_2025_109929
elsevier_sciencedirect_doi_10_1016_j_mineng_2025_109929
PublicationCentury 2000
PublicationDate February 2026
2026-02-00
PublicationDateYYYYMMDD 2026-02-01
PublicationDate_xml – month: 02
  year: 2026
  text: February 2026
PublicationDecade 2020
PublicationTitle Minerals engineering
PublicationYear 2026
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Li, Zhang, Lu, Xu, Ren, You (b12) 2022; 194
Yang, Li, Lyu, Zhang, Zhao (b24) 2023; 38
Lemberge, De Raedt, Janssens, Wei, Van Espen (b6) 2000; 14
Wen, Liu, Zhou, Liu, Zhou (b21) 2023; 332
Li, Tu, Zhang, Cheng, Yang (b10) 2022; 184
Tavares, Mouazen, Alves, dos Santos, Melquiades, Pereira de Carvalho, Molin (b18) 2020; 10
Xu, Klein, Li, Gopaluni (b23) 2023; 192
Xie, Xiao, Mao (b22) 2023; 72
Yuan, Zhao, Meng, Zhang, Xu, Li (b27) 2021; 171
Zhang, Li, Yang (b28) 2024; 39
Lai, Xi, Sun, He, Wang, Zheng, Mao (b5) 2020; 41
Li, Hao, Yuan, Liu, Li (b7) 2020; 315
Rousseau (b17) 2006; 61
Wang, Zhong, Wang, Dai (b20) 2024; 218
Li, Klein, Sun, Kou (b8) 2020; 146
Andric, Kvascev, Cvetanovic, Stojanovic, Bacanin, Gajic-Kvascev (b2) 2024; 14
Lu, Li, Yang, Zhu, Lv (b13) 2023; 238
Zhang, Zhang, Zhou, Lu (b29) 2022; 32
Meng, Du, Yuan, Xu, Zhao, Li (b14) 2022; 179
Aidene, Khaydukova, Pashkova, Chubarov, Savinov, Semenov, Kirsanov, Panchuk (b1) 2021; 185
Li, Tang, Ge, Wu, Cheng, Sun (b9) 2019; vol. 1423
Kwok, Yeung (b4) 1997; 8
Yang, Li, Zhang, Lyu (b25) 2024; 1323
Panlin, Jiqing, Anquan, Jieqing (b16) 1999; 22
Yang, Li, Zhao, Lu, Yang, Zhu (b26) 2022; 14
Li, Yang, Ma, Cheng, Lu, Zhao (b11) 2021; 32
Nan, Dai, Yuan, Zhou (b15) 2024
Babos, Costa, Pereira-Filho (b3) 2019; 147
Zhang, Zhou, Karimi, Fujita, Hu, Wen, Wang (b30) 2023; 126
Wang, Gan, Zhao, Yin, Ye, Sheng, Li, Liang, Jia, Fang (b19) 2024; 219
Yang (10.1016/j.mineng.2025.109929_b24) 2023; 38
Wang (10.1016/j.mineng.2025.109929_b19) 2024; 219
Li (10.1016/j.mineng.2025.109929_b10) 2022; 184
Li (10.1016/j.mineng.2025.109929_b12) 2022; 194
Yang (10.1016/j.mineng.2025.109929_b26) 2022; 14
Andric (10.1016/j.mineng.2025.109929_b2) 2024; 14
Lu (10.1016/j.mineng.2025.109929_b13) 2023; 238
Nan (10.1016/j.mineng.2025.109929_b15) 2024
Xu (10.1016/j.mineng.2025.109929_b23) 2023; 192
Aidene (10.1016/j.mineng.2025.109929_b1) 2021; 185
Zhang (10.1016/j.mineng.2025.109929_b29) 2022; 32
Lemberge (10.1016/j.mineng.2025.109929_b6) 2000; 14
Meng (10.1016/j.mineng.2025.109929_b14) 2022; 179
Babos (10.1016/j.mineng.2025.109929_b3) 2019; 147
Wang (10.1016/j.mineng.2025.109929_b20) 2024; 218
Yang (10.1016/j.mineng.2025.109929_b25) 2024; 1323
Zhang (10.1016/j.mineng.2025.109929_b30) 2023; 126
Wen (10.1016/j.mineng.2025.109929_b21) 2023; 332
Rousseau (10.1016/j.mineng.2025.109929_b17) 2006; 61
Xie (10.1016/j.mineng.2025.109929_b22) 2023; 72
Li (10.1016/j.mineng.2025.109929_b8) 2020; 146
Yuan (10.1016/j.mineng.2025.109929_b27) 2021; 171
Li (10.1016/j.mineng.2025.109929_b7) 2020; 315
Zhang (10.1016/j.mineng.2025.109929_b28) 2024; 39
Panlin (10.1016/j.mineng.2025.109929_b16) 1999; 22
Lai (10.1016/j.mineng.2025.109929_b5) 2020; 41
Tavares (10.1016/j.mineng.2025.109929_b18) 2020; 10
Li (10.1016/j.mineng.2025.109929_b9) 2019; vol. 1423
Li (10.1016/j.mineng.2025.109929_b11) 2021; 32
Kwok (10.1016/j.mineng.2025.109929_b4) 1997; 8
References_xml – volume: 185
  year: 2021
  ident: b1
  article-title: Does chemometrics work for matrix effects correction in X-ray fluorescence analysis?
  publication-title: Spectrochim. Acta B
– volume: 38
  start-page: 1830
  year: 2023
  end-page: 1840
  ident: b24
  article-title: Quantitative analysis of heavy metals in soil via hierarchical deep neural networks with X-ray fluorescence spectroscopy
  publication-title: J. Anal. At. Spectrom.
– volume: 61
  start-page: 759
  year: 2006
  end-page: 777
  ident: b17
  article-title: Corrections for matrix effects in X-ray fluorescence analysis—A tutorial
  publication-title: Spectrochim. Acta B
– volume: 10
  start-page: 787
  year: 2020
  ident: b18
  article-title: Assessing soil key fertility attributes using a portable X-ray fluorescence: A simple method to overcome matrix effect
  publication-title: Agronomy
– volume: vol. 1423
  year: 2019
  ident: b9
  article-title: Application of small sample BP neural network in quantitative analysis of EDXRF
  publication-title: Journal of Physics: Conference Series
– volume: 219
  year: 2024
  ident: b19
  article-title: Identification study of soil types based on feature factors of XRF spectrum combining with machine learning
  publication-title: Spectrochim. Acta B
– volume: 332
  year: 2023
  ident: b21
  article-title: Explainable machine learning rapid approach to evaluate coal ash content based on X-ray fluorescence
  publication-title: Fuel
– year: 2024
  ident: b15
  article-title: An interpretable constructive algorithm for incremental random weight neural networks and its application
  publication-title: IEEE Trans. Ind. Inform.
– volume: 14
  start-page: 3944
  year: 2022
  end-page: 3952
  ident: b26
  article-title: Quantitative analysis of heavy metals in soil by X-ray fluorescence with PCA–ANOVA and support vector regression
  publication-title: Anal. Methods
– volume: 147
  start-page: 628
  year: 2019
  end-page: 634
  ident: b3
  article-title: Wavelength dispersive X-ray fluorescence (WD-XRF) applied to speciation of sulphur in mineral supplement for cattle: Evaluation of the chemical and matrix effects
  publication-title: Microchem. J.
– volume: 41
  start-page: 20
  year: 2020
  end-page: 28
  ident: b5
  article-title: Multi-elemental analysis by energy dispersion X-ray fluorescence spectrometry and its application on the traceability of soybean origin
  publication-title: At. Spectrosc.
– volume: 14
  start-page: 3666
  year: 2024
  ident: b2
  article-title: Deep learning assisted XRF spectra classification
  publication-title: Sci. Rep.
– volume: 146
  year: 2020
  ident: b8
  article-title: Applying receiver-operating-characteristic (ROC) to bulk ore sorting using XRF
  publication-title: Miner. Eng.
– volume: 171
  year: 2021
  ident: b27
  article-title: Adsorption mode of sodium citrate for achieving effective flotation separation of ilmenite from titanaugite
  publication-title: Miner. Eng.
– volume: 32
  start-page: 865
  year: 2022
  end-page: 876
  ident: b29
  article-title: Application of multi-stage dynamic magnetizing roasting technology on the utilization of cryptocrystalline oolitic hematite: A review
  publication-title: Int. J. Min. Sci. Technol.
– volume: 14
  start-page: 751
  year: 2000
  end-page: 763
  ident: b6
  article-title: Quantitative analysis of 16–17th century archaeological glass vessels using PLS regression of EPXMA and
  publication-title: J. Chemom.: A J. Chemom. Soc.
– volume: 194
  start-page: 95
  year: 2022
  ident: b12
  article-title: Estimation of metal elements content in soil using x-ray fluorescence based on multilayer perceptron
  publication-title: Environ. Monit. Assess.
– volume: 184
  year: 2022
  ident: b10
  article-title: Application of a back propagation neural network model based on genetic algorithm to in situ analysis of marine sediment cores by X-ray fluorescence core scanner
  publication-title: Appl. Radiat. Isot.
– volume: 39
  start-page: 478
  year: 2024
  end-page: 490
  ident: b28
  article-title: A deep spectral prediction network to quantitatively determine heavy metal elements in soil by X-ray fluorescence
  publication-title: J. Anal. At. Spectrom.
– volume: 126
  year: 2023
  ident: b30
  article-title: Attention gate guided multiscale recursive fusion strategy for deep neural network-based fault diagnosis
  publication-title: Eng. Appl. Artif. Intell.
– volume: 22
  year: 1999
  ident: b16
  article-title: Comparison of artificial neural network with least-square regression in quantitative analysis of XRF
  publication-title: Nucl. Tech.
– volume: 179
  year: 2022
  ident: b14
  article-title: Study on the mineral characteristics and separation performances of a low-TiO2 ilmenite
  publication-title: Miner. Eng.
– volume: 8
  start-page: 1131
  year: 1997
  end-page: 1148
  ident: b4
  article-title: Objective functions for training new hidden units in constructive neural networks
  publication-title: IEEE Trans. Neural Netw.
– volume: 238
  year: 2023
  ident: b13
  article-title: Quantitative analysis of heavy metals in soil by X-ray fluorescence with improved variable selection strategy and bayesian optimized support vector regression
  publication-title: Chemometr. Intell. Lab. Syst.
– volume: 72
  start-page: 1
  year: 2023
  end-page: 10
  ident: b22
  article-title: Rapid detection of iron ore grades based on fractional-order derivative spectroscopy and machine learning
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 315
  year: 2020
  ident: b7
  article-title: Regulating effects of citric acid and pregelatinized starch on selective flocculation flotation of micro-fine siderite
  publication-title: J. Mol. Liq.
– volume: 218
  year: 2024
  ident: b20
  article-title: A mechanistic and data-driven approach for real-time online determination of ilmenite grade in pulp by X-ray fluorescence
  publication-title: Miner. Eng.
– volume: 1323
  year: 2024
  ident: b25
  article-title: An integrated CBLA-net with fractional discrete wavelet transform and frequency-based CARS to predict heavy metal elements by XRF
  publication-title: Anal. Chim. Acta
– volume: 192
  year: 2023
  ident: b23
  article-title: Evaluation of logistic regression and support vector machine approaches for XRF based particle sorting for a copper ore
  publication-title: Miner. Eng.
– volume: 32
  year: 2021
  ident: b11
  article-title: X-ray fluorescence spectroscopic analysis of trace elements in soil with an adaboost back propagation neural network and multivariate-partial least squares regression
  publication-title: Meas. Sci. Technol.
– volume: 32
  start-page: 865
  issue: 4
  year: 2022
  ident: 10.1016/j.mineng.2025.109929_b29
  article-title: Application of multi-stage dynamic magnetizing roasting technology on the utilization of cryptocrystalline oolitic hematite: A review
  publication-title: Int. J. Min. Sci. Technol.
  doi: 10.1016/j.ijmst.2022.05.001
– volume: 14
  start-page: 3944
  issue: 40
  year: 2022
  ident: 10.1016/j.mineng.2025.109929_b26
  article-title: Quantitative analysis of heavy metals in soil by X-ray fluorescence with PCA–ANOVA and support vector regression
  publication-title: Anal. Methods
  doi: 10.1039/D2AY00593J
– volume: 184
  year: 2022
  ident: 10.1016/j.mineng.2025.109929_b10
  article-title: Application of a back propagation neural network model based on genetic algorithm to in situ analysis of marine sediment cores by X-ray fluorescence core scanner
  publication-title: Appl. Radiat. Isot.
  doi: 10.1016/j.apradiso.2022.110191
– volume: 146
  year: 2020
  ident: 10.1016/j.mineng.2025.109929_b8
  article-title: Applying receiver-operating-characteristic (ROC) to bulk ore sorting using XRF
  publication-title: Miner. Eng.
  doi: 10.1016/j.mineng.2019.106117
– volume: 10
  start-page: 787
  issue: 6
  year: 2020
  ident: 10.1016/j.mineng.2025.109929_b18
  article-title: Assessing soil key fertility attributes using a portable X-ray fluorescence: A simple method to overcome matrix effect
  publication-title: Agronomy
  doi: 10.3390/agronomy10060787
– volume: 332
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b21
  article-title: Explainable machine learning rapid approach to evaluate coal ash content based on X-ray fluorescence
  publication-title: Fuel
  doi: 10.1016/j.fuel.2022.125991
– volume: 194
  start-page: 95
  issue: 2
  year: 2022
  ident: 10.1016/j.mineng.2025.109929_b12
  article-title: Estimation of metal elements content in soil using x-ray fluorescence based on multilayer perceptron
  publication-title: Environ. Monit. Assess.
  doi: 10.1007/s10661-022-09750-x
– volume: 218
  year: 2024
  ident: 10.1016/j.mineng.2025.109929_b20
  article-title: A mechanistic and data-driven approach for real-time online determination of ilmenite grade in pulp by X-ray fluorescence
  publication-title: Miner. Eng.
  doi: 10.1016/j.mineng.2024.109002
– volume: 147
  start-page: 628
  year: 2019
  ident: 10.1016/j.mineng.2025.109929_b3
  article-title: Wavelength dispersive X-ray fluorescence (WD-XRF) applied to speciation of sulphur in mineral supplement for cattle: Evaluation of the chemical and matrix effects
  publication-title: Microchem. J.
  doi: 10.1016/j.microc.2019.03.077
– volume: 14
  start-page: 751
  issue: 5–6
  year: 2000
  ident: 10.1016/j.mineng.2025.109929_b6
  article-title: Quantitative analysis of 16–17th century archaeological glass vessels using PLS regression of EPXMA and μ-XRF data
  publication-title: J. Chemom.: A J. Chemom. Soc.
  doi: 10.1002/1099-128X(200009/12)14:5/6<751::AID-CEM622>3.0.CO;2-D
– volume: 179
  year: 2022
  ident: 10.1016/j.mineng.2025.109929_b14
  article-title: Study on the mineral characteristics and separation performances of a low-TiO2 ilmenite
  publication-title: Miner. Eng.
  doi: 10.1016/j.mineng.2022.107458
– volume: 32
  issue: 10
  year: 2021
  ident: 10.1016/j.mineng.2025.109929_b11
  article-title: X-ray fluorescence spectroscopic analysis of trace elements in soil with an adaboost back propagation neural network and multivariate-partial least squares regression
  publication-title: Meas. Sci. Technol.
  doi: 10.1088/1361-6501/abf61a
– volume: 171
  year: 2021
  ident: 10.1016/j.mineng.2025.109929_b27
  article-title: Adsorption mode of sodium citrate for achieving effective flotation separation of ilmenite from titanaugite
  publication-title: Miner. Eng.
– volume: 39
  start-page: 478
  issue: 2
  year: 2024
  ident: 10.1016/j.mineng.2025.109929_b28
  article-title: A deep spectral prediction network to quantitatively determine heavy metal elements in soil by X-ray fluorescence
  publication-title: J. Anal. At. Spectrom.
  doi: 10.1039/D3JA00392B
– volume: 238
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b13
  article-title: Quantitative analysis of heavy metals in soil by X-ray fluorescence with improved variable selection strategy and bayesian optimized support vector regression
  publication-title: Chemometr. Intell. Lab. Syst.
  doi: 10.1016/j.chemolab.2023.104842
– year: 2024
  ident: 10.1016/j.mineng.2025.109929_b15
  article-title: An interpretable constructive algorithm for incremental random weight neural networks and its application
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2024.3423487
– volume: 8
  start-page: 1131
  issue: 5
  year: 1997
  ident: 10.1016/j.mineng.2025.109929_b4
  article-title: Objective functions for training new hidden units in constructive neural networks
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/72.623214
– volume: 38
  start-page: 1830
  issue: 9
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b24
  article-title: Quantitative analysis of heavy metals in soil via hierarchical deep neural networks with X-ray fluorescence spectroscopy
  publication-title: J. Anal. At. Spectrom.
  doi: 10.1039/D3JA00120B
– volume: 315
  year: 2020
  ident: 10.1016/j.mineng.2025.109929_b7
  article-title: Regulating effects of citric acid and pregelatinized starch on selective flocculation flotation of micro-fine siderite
  publication-title: J. Mol. Liq.
  doi: 10.1016/j.molliq.2020.113726
– volume: 126
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b30
  article-title: Attention gate guided multiscale recursive fusion strategy for deep neural network-based fault diagnosis
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.107052
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b22
  article-title: Rapid detection of iron ore grades based on fractional-order derivative spectroscopy and machine learning
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2023.3328080
– volume: 22
  year: 1999
  ident: 10.1016/j.mineng.2025.109929_b16
  article-title: Comparison of artificial neural network with least-square regression in quantitative analysis of XRF
  publication-title: Nucl. Tech.
– volume: 14
  start-page: 3666
  issue: 1
  year: 2024
  ident: 10.1016/j.mineng.2025.109929_b2
  article-title: Deep learning assisted XRF spectra classification
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-024-53988-z
– volume: 41
  start-page: 20
  issue: 1
  year: 2020
  ident: 10.1016/j.mineng.2025.109929_b5
  article-title: Multi-elemental analysis by energy dispersion X-ray fluorescence spectrometry and its application on the traceability of soybean origin
  publication-title: At. Spectrosc.
  doi: 10.46770/AS.2020.01.003
– volume: 61
  start-page: 759
  issue: 7
  year: 2006
  ident: 10.1016/j.mineng.2025.109929_b17
  article-title: Corrections for matrix effects in X-ray fluorescence analysis—A tutorial
  publication-title: Spectrochim. Acta B
  doi: 10.1016/j.sab.2006.06.014
– volume: vol. 1423
  year: 2019
  ident: 10.1016/j.mineng.2025.109929_b9
  article-title: Application of small sample BP neural network in quantitative analysis of EDXRF
– volume: 219
  year: 2024
  ident: 10.1016/j.mineng.2025.109929_b19
  article-title: Identification study of soil types based on feature factors of XRF spectrum combining with machine learning
  publication-title: Spectrochim. Acta B
  doi: 10.1016/j.sab.2024.107001
– volume: 1323
  year: 2024
  ident: 10.1016/j.mineng.2025.109929_b25
  article-title: An integrated CBLA-net with fractional discrete wavelet transform and frequency-based CARS to predict heavy metal elements by XRF
  publication-title: Anal. Chim. Acta
  doi: 10.1016/j.aca.2024.343073
– volume: 192
  year: 2023
  ident: 10.1016/j.mineng.2025.109929_b23
  article-title: Evaluation of logistic regression and support vector machine approaches for XRF based particle sorting for a copper ore
  publication-title: Miner. Eng.
  doi: 10.1016/j.mineng.2023.108003
– volume: 185
  year: 2021
  ident: 10.1016/j.mineng.2025.109929_b1
  article-title: Does chemometrics work for matrix effects correction in X-ray fluorescence analysis?
  publication-title: Spectrochim. Acta B
  doi: 10.1016/j.sab.2021.106310
SSID ssj0005789
Score 2.446411
Snippet X-ray fluorescence (XRF) spectroscopy provides an efficient and non-destructive means for determining the Titanium Dioxide (TiO2) content in ilmenite. However,...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 109929
SubjectTerms Geometric control strategy
Hybrid model
Ilmenite
Stacked structure
X-ray fluorescence
Title A hybrid linear–nonlinear model with two-stage feature selection for TiO2 content prediction in ilmenite based on XRF spectroscopy
URI https://dx.doi.org/10.1016/j.mineng.2025.109929
Volume 236
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0892-6875
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0005789
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbKxgM8IK7auMkPvEVBrRPH8WOFNsEEBUHR-hbZsdtl2tIqLWMgIfHAP-Af8ks4viWZhhAgIVVpZcluc85X5_Px53MQepJRUkqt4I-UjEiczhMZ54lI41ylI1bqMtWZtMUm2GSSz2b8zWDwJZyFOTthdZ2fn_PVf3U1tIGzzdHZv3B3Oyg0wGdwOlzB7XD9I8ePo6NP5hhWZAikaIKaIaldUgzRuOo3PgL7cRkDP1zoaK5tis9obQvjBAHitHpNrJzdSAZWjdnVCerI6uRUG8IamQehMpsOs7f7kT25aTJkLlcXNoxfVTa99TrSXQLELkpuJQWHuupotfCi_nrxuW2duMaDXtdDH-5-KeojseyHMEireg5xtXC2phMy2emPkzjLXV2VMFcTly3l0rzvQhDHT0_hDuoFLPsJNYmyuI-mXMyo_c4MbUYG-geMidEraJswymFe3x6_2JsddBohZmsotj8lnL20AsHL3_VrbtPjK9Ob6IZfaOCxA8gtNND1bXS9l37yDvo2xg4q2AHjx9fvLUiwBQk2IMEtSLAHCW5BggEk2IAEe5DgDiS4gpcHCbYgwdAIIMF9kNxF7_f3ps-ex74qR1wC2d3EI6GpUEPN8zm8cS0lJUMh6VBpwXOueaKyoU4Uy6UpBcAVkCMwJMmoSCSFJ8g9tAU3o3cQVpKxLM0zAWvclPKSE5UB403kKIFVbCl2URzsWaxc8pUiqBKPC2f_wti_cPbfRSwYvfAE0hHDAnDy2573_7nnA3Stg_RDtLVpPuhH6Gp5tqnWzWMPqJ99jZt4
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+hybrid+linear%E2%80%93nonlinear+model+with+two-stage+feature+selection+for+TiO2+content+prediction+in+ilmenite+based+on+XRF+spectroscopy&rft.jtitle=Minerals+engineering&rft.au=Dai%2C+Wei&rft.au=Duan%2C+Mingzi&rft.au=Nan%2C+Jing&rft.au=Wang%2C+Lanhao&rft.date=2026-02-01&rft.pub=Elsevier+Ltd&rft.issn=0892-6875&rft.volume=236&rft_id=info:doi/10.1016%2Fj.mineng.2025.109929&rft.externalDocID=S0892687525007575
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0892-6875&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0892-6875&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0892-6875&client=summon