No abstract

Federated learning is a promising strategy for indoor localization that can reduce the labor cost of constructing a fingerprint dataset in a distributed training manner without privacy disclosure. However, the traffic generated during the whole training process of federated learning is a burden on the up-and-down link, which leads to huge energy consumption for mobile devices. Moreover, the non-independent and identically distributed (Non-IID) problem impairs the global localization performance during the federated learning. This paper proposes a communication-efficient FedAvg method for federated indoor localization which is improved by the layerwise asynchronous aggregation strategy and layerwise swapping training strategy. Energy efficiency can be improved by performing asynchronous aggregation between the model layers to reduce the traffic cost in the training process. Moreover, the impact of the Non-IID problem on the localization performance can be mitigated by performing swapping training on the deep layers. Extensive experimental results show that the proposed methods reduce communication traffic and improve energy efficiency significantly while mitigating the impact of the Non-IID problem on the precision of localization.

During the growth and development of tomato plants, its different cells or tissues would store external environmental information and express it in the form of ion transportation. In order to better examine the storage model of tomato plants, the tomato individual tissue and whole plant biological circuit models were closely examined based on the idea of modal theory. According to the parameter inversion theory, in the frequency range of 0.1Hz - 1MHz, the impedance spectrum measurement and dielectric properties of tomato plants in four modal periods of germination stage were carried out. The stages were namely the seedling stage, flowering and fruit setting stage, and fruiting stage respectively. Impedance spectrum fitting was performed with the ZSimpWin software. Then, the biological circuit model of each tissue of tomato plant was obtained. Next, the parameter inversion was used to calculate the value of each element of the biological circuit model. Lastly, the biological circuit model of the tomato plant body in each period was obtained. Through the charging and discharging test of the model of the tomato plant body at each stage, the corresponding parameter value relationship was obtained according to the capacitance characteristics. This would be compared with the component values obtained from the parameter inversion in the model. Results showed that the errors were all less than 4.8%, which verified the rationality of the model. This system acted as a theoretical guidance for the research on the growth and development of tomato and other plants.

No abstract

In order to solve the problem that the complex pig house environment leads to the difficulty and low accuracy of abnormal detection of group pigs. The video of 9 adult fattening pigs were collected, and the video key frames were obtained by the frame differential method as the training set, and the YOLOX model for abnormal detection of group pigs was constructed. The results show that the average accuracy of YOLOX model on the test set is 98.0%. The research results can provide a reference for the detection of pig anomalies in the breeding environment of pig farms.