Sensors have been used in various agricultural production scenarios due to significant advances in the Agricultural Internet of Things (Ag-IoT), leading to smart agriculture. Intelligent control or monitoring systems rely heavily on trustworthy sensor systems. Nonetheless, sensor failures are likely due to various factors, including key equipment malfunction or human error. A faulty sensor can produce corrupted measurements, resulting in incorrect decisions. Early detection of potential faults is crucial, and fault diagnosis techniques have been proposed. The purpose of sensor fault diagnosis is to detect faulty data in the sensor and recover or isolate the faulty sensors so that the sensor can finally provide correct data to the user. Current fault diagnosis technologies are based mainly on statistical models, artificial intelligence, deep learning, etc. The further development of fault diagnosis technology is also conducive to reducing the loss caused by sensor failures.

As a non-destructive detection method, an electronic nose can be used to assess the freshness of meats by collecting and analyzing their odor information. Deep learning can automatically extract features and uncover potential patterns in data, minimizing the influence of subjective factors such as selecting features artificially. A transfer-learning-based model was proposed for the electronic nose to detect the freshness of chicken breasts in this study. First, a 3D-printed electronic nose system is used to collect the odor data from chicken breast samples stored at 4 °C for 1–7 d. Then, three conversion to images methods are used to feed the recorded time series data into the convolutional neural network. Finally, the pre-trained AlexNet, GoogLeNet, and ResNet models are retrained in the last three layers while being compared to classic machine learning methods such as K Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machines (SVM). The final accuracy of ResNet is 99.70%, which is higher than the 94.33% correct rate of the popular machine learning model SVM. Therefore, the electronic nose combined with conversion to images shows great potential for using deep transfer learning methods for chicken freshness classification.

Apples are one of the most widely planted fruits in the world, with an extremely high annual production. Several issues should be addressed to avoid the damaging of samples during the quality grading process of apples (e.g., the long detection period and the inability to detect the internal quality of apples). In this study, an electronic nose (e-nose) detection system for apple quality grading based on the K-nearest neighbor support vector machine (KNN-SVM) was designed, and the nasal cavity structure of the e-nose was optimized by computational fluid dynamics (CFD) simulation. A KNN-SVM classifier was also proposed to overcome the shortcomings of the traditional SVMs. The performance of the developed device was experimentally verified in the following steps. The apples were divided into three groups according to their external and internal quality. The e-nose data were pre-processed before features extraction, and then Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were used to reduce the dimension of the datasets. The recognition accuracy of the PCA–KNN-SVM classifier was 96.45%, and the LDA–KNN-SVM classifier achieved 97.78%. Compared with other commonly used classifiers, (traditional KNN, SVM, Decision Tree, and Random Forest), KNN-SVM is more efficient in terms of training time and accuracy of classification. Generally, the apple grading system can be used to evaluate the quality of apples during storage.

Based on hyperspectral imaging technology, rapid and efficient prediction of soil moisture content (SMC) can provide an essential basis for the formulation of precise agricultural programs (e.g., forestry irrigation and environmental management). To build an efficient inversion model of SMC, this paper collected 117 cultivated soil samples from the Chair Hill area and tested them using the GaiaSorter hyperspectral sorter. The collected soil reflectance dataset was preprocessed by wavelet transform, before the combination of competitive adaptive reweighted sampling algorithm and successive projections algorithm (CARS-SPA) was used to select the bands optimally. Seven wavelengths of 695, 711, 736, 747, 767, 778, and 796 nm were selected and used as the factors of the SMC inversion model. The popular linear regression algorithm was employed to construct this model. The result indicated that the inversion model established by the multiple linear regression algorithm (the predicted R² was 0.83 and the RMSE was 0.0078) was feasible and highly accurate, indicating it could play an important role in predicting SMC of cultivated soils over a large area for agricultural irrigation and remote monitoring of crop yields.

Rice seed variety purity, an important index for measuring rice seed quality, has a great impact on the germination rate, yield, and quality of the final agricultural products. To classify rice varieties more efficiently and accurately, this study proposes a multimodal l fusion detection method based on an improved voting method. The experiment collected eight common rice seed types. Raytrix light field cameras were used to collect 2D images and 3D point cloud datasets, with a total of 3194 samples. The training and test sets were divided according to an 8:2 ratio. The experiment improved the traditional voting method. First, multiple models were used to predict the rice seed varieties. Then, the predicted probabilities were used as the late fusion input data. Next, a comprehensive score vector was calculated based on the performance of different models. In late fusion, the predicted probabilities from 2D and 3D were jointly weighted to obtain the final predicted probability. Finally, the predicted value with the highest probability was selected as the final value. In the experimental results, after late fusion of the predicted probabilities, the average accuracy rate reached 97.4%. Compared with the single support vector machine (SVM), k-nearest neighbors (kNN), convolutional neural network (CNN), MobileNet, and PointNet, the accuracy rates increased by 4.9%, 8.3%, 18.1%, 8.3%, and 9%, respectively. Among the eight varieties, the recognition accuracy of two rice varieties, Hannuo35 and Yuanhan35, by applying the voting method improved most significantly, from 73.9% and 77.7% in two dimensions to 92.4% and 96.3%, respectively. Thus, the improved voting method can combine the advantages of different data modalities and significantly improve the final prediction results.