The detection of goat milk adulteration with cow milk using a combination of voltammetric fingerprints and chemometrics analysis DOI Creative Commons

Demiati Demiati,

Wulan Tri Wahyuni, Mohamad Rafi

и другие.

Research Square (Research Square), Год журнала: 2022, Номер unknown

Опубликована: Ноя. 30, 2022

Abstract In this study, a novel analytical approach was developed for detecting and predicting adulteration of goat milk with cow using combination voltammetric fingerprints chemometrics analysis. The fresh samples were obtained from local farmers analyzed cyclic voltammetry technique glassy carbon electrode as the working KClO 4 supporting electrolyte. fingerprint both showed an anodic peak between potential range 0.40 to 0.75 V vs. Ag/AgCl. This is mainly attributed several electroactive species contained in samples. current intensities at 0 + 1 vs Ag/AgCl further selected due majority components having their oxidation range. pre-treated maximum normalization submitted chemometric tools multivariate Orthogonal partial least square-discriminant analysis provided clear discrimination milk. Meanwhile, prediction achieved squares regression These enabled satisfactory successful model predict percentage adulterants demonstrated results revealed that might offer low-cost, simple, rapid which be possible promising method detection adulterants.

Язык: Английский

MTJNet: Multi-task joint learning network for advancing medicinal plant and leaf classification DOI
Shubham Sharma, Manu Vardhan

Knowledge-Based Systems, Год журнала: 2024, Номер 299, С. 112147 - 112147

Опубликована: Июнь 17, 2024

Язык: Английский

Процитировано

11

Analysis of Electrochemical Impedance Data: Use of Deep Neural Networks DOI Creative Commons

Dulyawat Doonyapisut,

Padmanathan-Karthick Kannan,

Byeongkyu Kim

и другие.

Advanced Intelligent Systems, Год журнала: 2023, Номер 5(8)

Опубликована: Апрель 21, 2023

Technology advancements in energy storage, photocatalysis, and sensors have generated enormous impedimetric data. Electrochemical impedance spectroscopy (EIS) results play an essential role analyzing the interfacial properties of materials. Nonetheless, many situations, data is misinterpreted due to complexity electrochemical system or compromise between experimental result theoretical model, resulting partiality interpretation process, especially for results. Typically, experimenter interprets using a searching approach based on model until best‐fitting obtained, which time‐consuming errors can occur. To reduce misinterpretation by experimenter, herein, machine‐learning strategy demonstrated classification EIS circuit parameter prediction deep neural network (DNN). The DNN shows highly accurate classifier commonly used with average area under receiver operating characteristic curve more than 0.95. Additionally, demonstrates high accuracy parameters complex system, maximum R 2 0.999. These reveal that may open new room studying systems.

Язык: Английский

Процитировано

15

Authentication and identification of Lamiaceae family with cyclic voltammetry fingerprint-PCA-LDA and determination of the used phenolic contents for classification using chromatographic analyses DOI
Maryam Abbasi Tarighat, Gholamreza Abdi,

Fereshteh Abbasi Tarighat

и другие.

Talanta, Год журнала: 2023, Номер 265, С. 124894 - 124894

Опубликована: Июль 4, 2023

Язык: Английский

Процитировано

13

Where artificial intelligence stands in the development of electrochemical sensors for healthcare applications-A review DOI Creative Commons
Andreea Cernat, Adrian Groza, Mihaela Tertiş

и другие.

TrAC Trends in Analytical Chemistry, Год журнала: 2024, Номер 181, С. 117999 - 117999

Опубликована: Окт. 5, 2024

Язык: Английский

Процитировано

5

Wood species classification using prototypical networks: a few shot learning model DOI
M. Diviya,

M. Subramanian

Journal of the Indian Academy of Wood Science, Год журнала: 2025, Номер unknown

Опубликована: Янв. 17, 2025

Язык: Английский

Процитировано

0

Leaf-Face Dendrobium Classifier Based on an Integrated Electrochemical Tongue and Machine Learning DOI

Yaqi Huang,

Yueyu Wang,

Fulin Zhu

и другие.

ACS Sensors, Год журнала: 2025, Номер unknown

Опубликована: Фев. 4, 2025

Botanical sourcing seriously impacts the safety and potency of herbal medicines, restricting development traditional Chinese medicinal industry. Rapid convenient identification plant resources is important to address this problem. Herein, we innovated a portable, intelligent, integrated platform, termed Smart Electronic Tongue (SET), for right recognizing Dendrobium bonsai different subspecies origins. The device miniaturized with hollow microneedle array leaf-face extraction, press-pumping pipeline on-demand sample sap suction, plus five-electrode chip electrochemical readout. Differential pulse voltammograms on three simplexes self-assembled monolayers as well their multiplexed configurations are specialized generate high-dimensional fingerprinting subtypes. Taking advantage machine learning algorithms, platform achieves automatic authentication over eight varieties discriminatory accuracy 95%. Given this, anticipate that such bionic sensing setup would offer versatile solution toward classification diverse officinals at point need.

Язык: Английский

Процитировано

0

Rapid identification of Gastrodia elata Blume hybrids using near-infrared spectroscopy combined with lightweight depthwise separable convolutional neural networks DOI
Tuo Guo, Qin Li, Caiyun Wang

и другие.

Microchemical Journal, Год журнала: 2025, Номер unknown, С. 113273 - 113273

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

Detection of Medicinal Plants Using Machine Learning DOI

S. Ravikumar,

I. Eugene Berna,

R. Babu

и другие.

Lecture notes in networks and systems, Год журнала: 2025, Номер unknown, С. 199 - 208

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

Advancing medicinal plant agriculture: integrating technology and precision agriculture for sustainability DOI Creative Commons
Vinay Kumar, Ashwini Zadokar, Pankaj Kumar

и другие.

PeerJ, Год журнала: 2025, Номер 13, С. e19058 - e19058

Опубликована: Апрель 4, 2025

To strengthen the agriculture sector, it is crucial to combine efforts of industrialization (field mechanization and fertilizer production), technology (genome editing manipulation), information sector (for application current technologies in precision agriculture). The challenge modern sustainable increasing agricultural output while using least amount resources capital expenditure possible considering variables contributing environmental damage. Different factors adversely affect medicinal plant populations, leading extinction these valuable species. These difficulties drew attention international scientific community farm sustainability energy efficiency studies that put forth idea (site-specific crop management) plants. It a systems-based method monitors responds changes intra- inter-field conditions for environmentally friendly optimum output. Farming systems have significantly benefited from visualization morphological analysis areas (both open fields greenhouse experiments) remote sensing technology, geographic (GIS), scouting, variable rate (VRT), Global Positioning System (GPS). form backbone fourth technological revolution, Agriculture 4.0. This review concisely summarizes innovative technologies’ use potential future advancements intended researchers, professionals cultivation, herbal medicine research, science, related fields.

Язык: Английский

Процитировано

0

Deep Learning-Assisted Multiplexed Electrochemical Fingerprinting for Chinese Tea Identification DOI
Yuyu Tan, Min Luo, Chao Xu

и другие.

Analytical Chemistry, Год журнала: 2025, Номер unknown

Опубликована: Апрель 10, 2025

Selectively differential identification of natural components with similar chemical structures in complex matrices is still a challenging task by conventional analytical strategies. Herein, we developed landmark (DaXing airport)-inspired laser engraving sensor array that combined multiplex electrochemical fingerprinting technology one-dimensional convolutional neural network (1D-CNN) for rapidly precise detection three tea polyphenols and the differentiation 24 distinct types Chinese teas. This sensing strategy employs diverse different working electrode configurations as multivariate (bare electrode, nanoenzyme bioenzyme electrode), generating fingerprints samples. By utilizing self-designed 1D-CNN algorithm feature extraction, significantly improved, thereby enhancing predictive accuracy platform successfully achieves polyphenols, distinguishing six series varieties rates 98.84 97.68%, respectively. Notably, deep learning-assisted multiplexed technique better compared other representative machine learning methods. advancement offers rapid reliable approach to development authentication processes agricultural products.

Язык: Английский

Процитировано

0