A new computational approach for the determination of 2,2-diphenyl-1-picrylhydrazyl free radical scavenging activity (DPPH-RSA) in food is reported, based on the concept of machine learning. Trolox standard was mix with DPPH at different concentrations to produce different colors from purple to yellow. Artificial neural network (ANN) was trained on a typical set of images of the DPPH radical reacting with different levels of Trolox. This allowed the neural network to classify future images of any sample into the correct class of RSA level. The ANN was then able to determine the DPPH-RSA of cinnamon, clove, mung bean, red bean, red rice, brown rice, black rice and tea extract and the results were compared with data obtained using a spectrophotometer. The application of ANN correlated well to the spectrophotometric classical procedure and thus do not require the use of spectrophotometer, and it could be used to obtain semi-quantitative results of DPPH-RSA.
A stable chromogenic radical 2,2-diphenyl-1-picrylhydrazyl (DPPH) is commonly used for the determination of antioxidant activity. In this paper, DPPH was dried into 96 well microplate to produce DPPH dry reagent array plate, based on which the highly sensitive and high throughput determination of antioxidant activities was achieved. The spectrophotometric characterization of the microplate containing dried or fresh DPPH free radicals was reported. The response of the DPPH dry reagent array towards different standard antioxidants was studied. The reaction for DPPH in fresh or dry reagent array with Trolox was reported and compared. The DPPH dry reagent array was used to study the antioxidant activity of banana, green tea, pink guava, and honeydew and the results were compared to the samples reacted with freshly prepared DPPH. The proposed method is comparable to the classical DPPH method, more convenient, simple to operate with minimal solvent required and excellent sensitivity.