Search

Additional file 2. Figure S2: GSEA results of specific enrichment set. (A, B) The 10 significantly enriched GO terms in high and low-risk ESCC patients. (C, D) KEGG pathways of different risk groups. GSEA, gene set enrichment analysis; GO, Gene Ontology; KEGG, Kyoto Encyclopedia of Genes and Genomes; ESCC, esophageal squamous cell carcinoma

Additional file 1. Figure S1: Establishment of prognostic model in ESCC. (A) LASSO coefficients of the five prognostic DDRGs. (B) Identifying LASSO deviance profiles using cross-validation. (C) The forest plot shows prognostic DDRGs using univariate Cox regression analysis. (D) The five prognostic DDRGs and 50 related genes. ESCC, esophageal squamous cell carcinoma; DDRGs, DNA damage repair genes.

Federated Recommendation can mitigate the systematical privacy risks of traditional recommendation since it allows the model training and online inferring without centralized user data collection. Most existing works assume that all user devices are available and adequate to participate in the Federated Learning. However, in practice, the complex recommendation models designed for accurate prediction and massive item data cause a high computation and communication cost to the resource-constrained user device, resulting in poor performance or training failure. Therefore, how to effectively compress the computation and communication overhead to achieve efficient federated recommendations across ubiquitous mobile devices remains a significant challenge. This paper introduces split learning into the two-tower recommendation models and proposes STTFedRec, a privacy-preserving and efficient cross-device federated recommendation framework. STTFedRec achieves local computation reduction by splitting the training and computation of the item model from user devices to a performance-powered server. The server with the item model provides low-dimensional item embeddings instead of raw item data to the user devices for local training and online inferring, achieving server broadcast compression. The user devices only need to perform similarity calculations with cached user embeddings to achieve efficient online inferring. We also propose an obfuscated item request strategy and multi-party circular secret sharing chain to enhance the privacy protection of model training. The experiments conducted on two public datasets demonstrate that STTFedRec improves the average computation time and communication size of the baseline models by about 40 times and 42 times in the best-case scenario with balanced recommendation accuracy.

In view of the problems of waste of water resources, high labor intensity and unscientific irrigation during farmland irrigation, and the shortcomings of ZigBee technology in the water-saving irrigation system network, such as short transmission distance, complicated network structure, and signals that are easily interfered during transmission. This paper designs a farmland environment information collection and monitoring system based on NB-IoT. The system consists of a terminal collection node, a wireless communication module and a host computer. Farmland environment monitoring system based on wireless sensor network includes wireless temperature and humidity sensor, wireless nitrogen, phosphorus and potassium sensor, Arduino MEGA development board NB-IoT communication module, gateway and Wasp mobile network, real-time collection, processing and wireless of farmland moisture data Transmission function, using NI LabVIEW software to compile the monitoring interface, real-time display of soil moisture in the form of waveform graph, and automatically control the opening and closing of the valve according to the soil moisture information. The system has flexible layout, long transmission distance, simple structure and integrated modules. It can achieve the purpose of precise irrigation and water saving, and is suitable for field planting, which has certain promotion significance.

This chapter investigates consumer finance in China from the perspective of the retail industry’s development. This chapter discusses the current situation and history of China’s retail industry, particularly the prepaid card business. Consumer finance in China has chosen a different development path than Japan and South Korea.

(1) Passivation of aluminum in 1M LiBOB/EC+DMC Cyclic voltammograms (CV), in which the potential was swept to maximum values of 4.5, 5.5, and 6.5V, were obtained for aluminum in 1.0 M LiBOB/EC+DMC. Even when the potential reached 6.5 V, no corrosion was detected on the surface of aluminum. The combined results of CV, electrochemical impedance spectroscopy (EIS), and electrochemical quartz crystal microbalance (EQCM) measurements indicate a passive film is formed on aluminum anodically polarized in 1.0 M LiBOB/EC+DMC and the film’s thickness increases with increasing potential. Specifically, (i) CV curves exhibited a pronounced hysteresis, (ii) capacitances, as measured by EIS decreased with increasing potential, and (iii) aluminum’s mass, as measured by EQCM, increased with increasing potential.

This article reviews the achievements and history of telecommunications development in China, and analyzes the development of the telecommunications services market in China. The analysis is mainly focused on total turnover of telecommunications services, the development of telecommunications services, and competition in the market. Finally, it analyzes issues on policies and regulations for telecommunications, and gives development targets for the future.

The paper reviews achievements and history of telecommunications development and regulatory system reform in China, discusses the evolution of reform, analyses influence of regulatory system reform to China’s telecommunication industry, and finally makes some suggestions on the development of China Telecom.

not Available.