This is the authors' abstract. We don't add key points for this paper.
We present a machine-learning approach in developing a smartphone-based rapid and point-of-use (PoU) trace-level detection of chromium (III and VI) ions using a nanosensor comprising dithiolated diethylenetriaminepentaacetic acid-functionalized gold nanoparticles (DTDTPA-GNP). The bright red color of DTDTPA-GNP turned blue with Cr III/VI ions in an aqueous medium. The nanosensor exhibited good linearity for Cr III/VI detection in a concentration range of 0.001–10 ppm with a detection limit of 0.001 ppm. A smartphone was used to acquire images of the distinct color change due to the DTDTPA-GNP–Cr III/VI interactions. Two features, that is, saturation and chroma component of red color difference were extracted from the color information of the acquired images. The extracted features from training samples were utilized to build a support vector machine-based regression (SVR) model to predict the accurate concentration of chromium (III and VI) in water and an aqueous extract of ferrochrome industrial waste (collected from the alloy industry as waste slag). The accurate prediction of 0.027 ppm Cr III/VI concentration in the industrial waste sample with a 100% recovery rate confirms the colorimetric-based SVR model as an efficient sensing platform for Cr III/VI ion detection. The mean squared error for Cr III/VI prediction was 0.00039 with 404 support vectors and a bias value of 0.1473. This highly selective and sensitive smartphone-based approach thus established the use of DTDTPA-GNP for PoU detection of Cr III/VI, specifically in day-to-day monitoring of water quality.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Priyadarshni et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: