FedUSC: Collaborative Unsupervised Representation Learning from Decentralized Data for Internet of Things

Federated Learning (FL) lately has shown much promise in improving the shared model and preserving data privacy. However, these existing methods are only of limited utility in the Internet of Things (IoT) scenarios, as they either heavily depend on high-quality labeled data or only perform well under idealized conditions, which typically cannot be found in practical applications. In this paper, we propose a novel federated unsupervised learning method for image classification without the use of any ground truth annotations. In IoT scenarios, a big challenge is that decentralized data among multiple clients is normally non-IID, leading to performance degradation. To address this issue, we further propose a dynamic update mechanism that can decide how to update the local model based on weights divergence. Extensive experiments show that our method outperforms all baseline methods by large margins, including +6.67% on CIFAR-10, +5.15% on STL-10, and +8.44% on SVHN in terms of classification accuracy. In particular, we obtain promising results on Mini-ImageNet and COVID-19 datasets and outperform several federated unsupervised learning methods under non-IID settings. IEEE

Application of Bayesian Network Reasoning Algorithm in Emotion Classification

In the early stage of covid-19 disease transmission, it is easy to lead to public panic and dissatisfaction without timely information feedback. In order to solve this problem, this paper constructs an emotion classification and prediction algorithm based on Bayesian network reasoning by analyzing the variable elimination algorithm, connection tree reasoning algorithm and Gibbs sampling algorithm in Bayesian network reasoning algorithm. The algorithm can quickly identify the emotions of Internet users from the communication with low computational resources, and provide reference for the relevant departments to formulate the correct public opinion guidance strategy. © 2021 IEEE.

A novel sentiment classification based on 'word-phrase' attention mechanism

With the rapid development of the COVID-19 epidemic, people are prone to panic due to delayed and incomplete information received. In order to quickly identify the sentiments of massive Internet users, it provides a good reference for government agencies to formulate healthy public opinion guidance strategies. This paper proposes a novel sentiment classification based on 'word-phrase' attention mechanism (SC-WPAtt). On the basis of TCN, we propose a shallow feature extraction model based on the word attention mechanism, and a deep extraction model based on the phrase attention mechanism. These models can effectively mine the auxiliary information contained in words, phrases (i.e. combined words) and overall comments, as well as their different contributions, so as to achieve more accurate emotion classification. Experiments show that the performance of the SC-WPAtt method proposed in this paper is better than that of the HN-Att method. © 2021 IEEE.

How does leader conscientiousness influence frontline staff under conditions of serious anxiety? An empirical study from integrated resorts (IRs)

Purpose - The objective of this study was to improve understanding of frontline staff's subjective happiness and anxiety during the COVID-19 pandemic by investigating the roles of employees' busy mindset and leader conscientiousness. Design/methodology/approach - The link between employee anxiety and subjective happiness was also explored, and the cross-level mediating effect of employee anxiety was tested using a multilevel design. A survey of 373 frontline staffers and 74 team leaders in the integrated resorts (IRs) was conducted in three waves: April (Time 1), May (Time 2) and June (Time 3) in 2020. The data were analysed with SPSS and Mplus using a hierarchical linear modelling (HLM) method. Findings - The results indicated that during the COVID-19 pandemic, a busy mindset increased frontline staff's anxiety and thus decreased their subjective happiness, and leader conscientiousness remedied the effect of anxiety on subjective happiness. Practical implications - The findings are relevant to frontline staffers, team leaders in the hospitality industry and corporate service departments. Against the background of COVID-19, conscientious leaders can significantly help employees to overcome their anxiety and insecurity and improve their subjective happiness, answering the urgent call to deal with the challenges of the new work-life environment. Originality/value - The study differs from previous other studies in two dimensions: First, the authors explored the interactions of the affective events from the cross-level perspectives, i.e. both team level and individual level. Second, the authors conducted this research on the mental issues of the hospitality frontline staffers in the context of the COVID-19 pandemic, which remains a black box to be explored.

Analysis on the causes of PM2.5 pollution in Nanning City in February 2020

During the novel coronavirus (COVID-19) lock down from 31st January to 2nd February, a regional atmospheric PM2.5 pollution episode had arosed concerns of society in Guangxi. Based on Nanning as an sampling site, Monitor for Aerosols and Gases in Ambient Air (MARGA), particulate LiDAR, surface meteorological and environmental data, satellite remote sensing data and modeled HYSPLIT4 trajectory were used to analyze the cause of PM2.5 pollution. According to the air quality sub-index, the observation durations were classified as the superior period, the fine period and the polluted period. The results indicated that K+ and Cl- concentrations closely related to biomass burning (BB) increased significantly during the polluted period. The average concentrations of K+ and Cl- in polluted period were 3.6 and 17.0 times higher than those corresponding figures of the superior period. The total concentration of eight water-soluble ions accounted for about 30% of PM2.5 in all three periods. The total concentration of three secondary water-soluble ions accounted for 83.33%~89.18% of the total concentration of eight ions. The high proportion of secondary inorganic components was related to the secondary transformation promoted by BB. The variation trends of proportion and levels of secondary water-soluble ions were not consistent, which was not only attributed to the emission characteristics of straw combustion, but also related to the formation mechanism and main influencing factors of different secondary inorganic ions. Straw burning spots were centralized around Nanning city during the fine period. The accumulation of direct emissions of particulate and gaseous pollutants caused by open burning of straw during the fine period under decreased boundary layer height, increased humidity and low wind speed were the main causes for atmospheric PM2.5 pollution in Nanning. During the polluted period, there was no obvious vertical transmission process of particulate matter in Nanning. The near ground was mainly affected by the southward airflow from the Beibu Gulf of Guangxi and Guangdong coastal, which indicated the regional pollution transmissions were insignificant. © 2021, Science Press. All right reserved.