The complexity of a supply chain makes product safety or quality issues extremely difficult to track, especially for the basic agricultural food supply chains of people's daily diets. The existing agricultural food supply chains present several major problems, such as numerous participants, inconvenient communication caused by long supply chain cycles, data distrust between participants and the centralized system. The emergence of blockchain technology effectively solves the pain-point problem existing in the traceability system of agricultural food supply chains. This paper proposes a framework based on the consortium and smart contracts to track and trace the workflow of agricultural food supply chains, implement traceability and shareability of supply chains, and break down the information islands between enterprises as much as possible to eliminate the need for the central institutions and agencies and improve the integrity of the transaction records, reliability and security. At the same time, farmers record details of the environment and crop growth data in the InterPlanetary File System (IPFS) and store file IPFS hashes in smart contracts, which not only increases data security but also alleviates the blockchain storage explosion problem. This framework has been applied in Shanwei Lvfengyuan Modern Agricultural Development Co., Ltd. Although there are still many defects, the framework has successfully realized functions such as disintermediation and tracing of agricultural product information through QR codes. Thus, the framework proposed in this paper is of great significance and reference value for enterprises to ensure product quality and safety traceability.

Recently, the attention mechanism combining spatial and channel information has been widely used in various deep convolutional neural networks (CNNs), proving its great potential in improving model performance. However, this usually uses 2D global pooling operations to compress spatial information or scaling methods to reduce the computational overhead in channel attention. These methods will result in severe information loss. Therefore, we propose a Spatial channel attention mechanism that captures cross-dimensional interaction, which does not involve dimensionality reduction and brings significant performance improvement with negligible computational overhead. The proposed attention mechanism can be seamlessly integrated into any convolutional neural network since it is a lightweight general module. Our method achieves a performance improvement of 2.08% on ResNet and 1.02% on MobileNetV2 in top-one error rate on the ImageNet dataset.

Preventing faults of sensors, wireless transmitters and gateways are essential for water quality management in intensive aquaculture. It remains a challenging task to achieve high fault diagnostic accuracy of water quality monitoring and controlling devices. This study proposes a hybrid water quality monitoring devices fault diagnosis model based on multiclass support vector machines (MSVM) in combination with rule-based decision trees (RBDT).In the modeling process, the rule-based decision trees (RBDT) is used to diagnose the gateway fault and wireless transmitter fault at the same time as a feature selection tool to reduce the number of features. Multiclass support vector machine classifier is employed to diagnose the faults of water quality sensors due to its robustness and generalization. We adopted an RBDT-MSVM algorithm to construct a fault diagnosis model. The diagnostic results indicate that RBDT-MSVM model has great potential for fault diagnosis of online water quality devices. RBDT-MSVM was tested and compared with other algorithms by applying it to diagnose faults of water quality monitoring devices in river crab culture ponds. The diagnostic results indicate that the model has great potential for fault diagnosis of online water quality devices. The experimental results show that the proposed model RBDT-MSVM can achieve classification accuracy as high as 92.86%, which is superior to the other three fault diagnosis methods. The results clearly confirm the superiority of the developed model in terms of classification accuracy, and that it is a suitable and effective method for fault diagnosis of water quality monitoring devices in intensive aquaculture.

Dissolved oxygen content is a key indicator of water quality in aquaculture environment. Because of its nonlinearity, dynamics, and complexity, which makes traditional methods face challenges in the accuracy and speed of dissolved oxygen content prediction. As a solution to these issues, this study introduces a hybrid model consisting of the Light Gradient Boosting Machine (LightGBM) and the Bidirectional Simple Recurrent Unit (BiSRU). Firstly, Linear interpolation and smoothing were used to identify significant parameters. LightGBM algorithm then determines the significance of dissolved oxygen by eliminating irrelevant variables and predicting dissolved oxygen in intensive aquaculture. Finally, the attention method was implemented to map the weighting and learning parameter matrices, so enabling the BiSRU’s hidden states to be assigned different weights. The findings shown that the presented prediction model can accurately anticipate the fluctuating trend of dissolved oxygen over a 10-day period in just 122 seconds, and the accuracy rate reached 96.28%. Comparing the model effects of LightGBM -BiSRU, LightGBM - GRU, LightGBM-LSTM, and BiSRU - Attention takes the least time. Its higher prediction accuracy can provide an essential reference for intensive aquaculture water quality regulation.

Metabolic syndrome (MetS) has a high prevalence and is prone to many complications. However, current MetS diagnostic methods require blood tests that are not conducive to self-testing, so a user-friendly and accurate method for predicting MetS is needed to facilitate early detection and treatment. In this study, a MetS prediction model based on a simple, small number of Traditional Chinese Medicine (TCM) clinical indicators and biological indicators combined with machine learning algorithms is investigated. Electronic medical record data from 2040 patients who visited outpatient clinics at Guangdong Chinese medicine hospitals from 2020 to 2021 were used to investigate the fusion of Bayesian optimization (BO) and eXtreme gradient boosting (XGBoost) in order to create a BO-XGBoost model for screening nineteen key features in three categories: individual bio-information, TCM indicators, and TCM habits that influence MetS prediction. Subsequently, the predictive diagnostic model for MetS was developed. The experimental results revealed that the model proposed in this paper achieved values of 93.35 %, 90.67 %, 80.40 %, and 0.920 for the F1, sensitivity, FRS, and AUC metrics, respectively. These values outperformed those of the seven other tested machine learning models. Finally, this study developed an intelligent prediction application for MetS based on the proposed model, which can be utilized by ordinary users to perform self-diagnosis through a web-based questionnaire, thereby accomplishing the objective of early detection and intervention for MetS.

Smoke detection based on video surveillance is important for early fire warning. Because the smoke is often small and thin in the early stage of a fire, using the collected smoke images for the identification and early warning of fires is very difficult. Therefore, an improved lightweight network that combines the attention mechanism and the improved upsampling algorithm has been proposed to solve the problem of small and thin smoke in the early fire stage. Firstly, the dataset consists of self-created small and thin smoke pictures and public smoke pictures. Secondly, an attention mechanism module combined with channel and spatial attention, which are attributes of pictures, is proposed to solve the small and thin smoke detection problem. Thirdly, to increase the receptive field of the smoke feature map in the feature fusion network and to solve the problem caused by the different smoke scenes, the original upsampling has been replaced with an improved upsampling algorithm. Finally, extensive comparative experiments on the dataset show that improved detection model has demonstrated an excellent effect.