Fresh pork is prone to spoilage during storage, transportation, and sale, resulting in reduced freshness. The total viable count (TVC) and total volatile basic nitrogen (TVB-N) content are key indicators for evaluating the freshness of fresh pork, and when they reach unacceptable limits, this seriously threatens dietary safety. To realize the on-site, low-cost, rapid, and non-destructive testing and evaluation of fresh pork freshness, a miniaturized detector was developed based on a cost-effective multi-channel spectral sensor. The partial least squares discriminant analysis (PLS-DA) model was used to distinguish fresh meat from deteriorated meat. The detector consists of microcontroller, light source, multi-channel spectral sensor, heat-dissipation modules, display system, and battery. In this study, the multispectral data of pork samples with different freshness levels were collected by the developed detector, and its ability to distinguish pork freshness was based on different spectral shape features (SSF) (spectral ratio (SR), spectral difference (SD), and normalized spectral intensity difference (NSID)) were compared. The experimental results show that compared with the original multispectral modeling, the performance of the model based on spectral shape features is significantly improved. The model established by optimizing the spectral shape feature variables has the best performance, and the discrimination accuracy of its prediction set is 91.67%. In addition, the validation accuracy of the optimal model was 86.67%, and its sensitivity and variability were 87.50% and 85.71%, respectively. The results show that the detector developed in this study is cost-effective, compact in its structure, stable in its performance, and suitable for the on-site digital rapid non-destructive testing of freshness during the storage, transportation, and sale of fresh pork.

Soluble solids content (SSC) is one of the main quality indicators of apples, and it is important to improve the precision of online SSC detection of whole apple fruit. Therefore, the spectral pre-processing method of spectral-to-spectral ratio (S/S), as well as multiple characteristic wavelength member model fusion (MCMF) and characteristic wavelength and non-characteristic wavelength member model fusion (CNCMF) methods, were proposed for improving the detection performance of apple whole fruit SSC by diffuse reflection (DR), diffuse transmission (DT) and full transmission (FT) spectra. The modeling analysis showed that the S/S- partial least squares regression models for all three mode spectra had high prediction performance. After competitive adaptive reweighted sampling characteristic wavelength screening, the prediction performance of all three model spectra was improved. The particle swarm optimization–extreme learning machine models of MCMF and CNCMF had the most significant enhancement effect and could make all three mode spectra have high prediction performance. DR, DT, and FT spectra all had some prediction ability for apple whole fruit SSC, with FT spectra having the strongest prediction ability, followed by DT spectra. This study is of great significance and value for improving the accuracy of the online detection model of apple whole fruit SSC.