Bo Xie

A lightweight Sybil attack detection method based on an improved received signal strength indicator (RSSI) and collaborative node verification is presented to ensure the integrity of data collected from wireless sensor networks (WSNs) for machine learning applications. Sybil attacks can tamper with data, leading to misleading model outputs and reducing the algorithmic performance. To address this challenge, the proposed approach employs an adaptive moving average–Kalman hybrid filtering (AMA-KF) algorithm to optimize RSSI measurements by mitigating multipath interference and environmental noise. The filtered RSSI is then incorporated into a multi-node cooperative positioning mechanism that detects Sybil nodes through spatial signal consistency analysis. Under this mechanism, detection strategies are dynamically adapted to network types: distance consistency is verified in fixed-power networks, while RSSI ratios are analyzed in adjustable-power networks. Simulation results demonstrate a detection rate of 94% and a false positive rate of only 3%, outperforming existing methods. This approach offers a lightweight and effective solution to ensure reliable data acquisition in WSNs for trustworthy machine learning model training.

The COVID-19 pandemic has not only brought a virus to the public, but also spawned a large number of rumors. The Internet has made it very convenient for media websites to record and spread rumors, while the official government, as the subject of rumor control, can release rumor-refutation information to reduce the harm of rumors. Therefore, this study took into account information-carrying variables, such as media websites and official governments, and expanded the classic ISR rumor propagation model into a five-dimensional, two-level rumor propagation model that interacts between the main body layer and the information layer. Based on the constructed model, the mean field equation was obtained. Through mathematical analysis, the equilibrium point and the basic reproduction number of rumors were calculated. At the same time, stability analysis was conducted using the Routh Hurwitz stability criterion. Finally, a numerical simulation verified that when the basic regeneration number was less than 1, rumors disappeared in the system; when the basic regeneration number was greater than 1, rumors continued to exist in the system and rumors erupted. The executive power of the official government to dispel rumors, that is, the effectiveness of the government, played a decisive role in suppressing the spread of rumors.

With the upgrading of people’s consumption patterns, the omni-channel supply chain becomes the mainstream form of e-commerce platform enterprise development. Aiming at two different e-commerce enterprises, we construct an evolutionary game model for enterprises’ “online+offline” omni-channel construction strategy by self-build or cooperating with brick-and-mortar stores. It is based on the Stackelberg and Cournot competition model, combined with the omni-channel pricing strategy, using the theory of perfect rationality and bounded rationality, and combing the non-cooperative game and evolutionary game to realize. Moreover, the evolutionary game process is simulated. Through the dynamic changes of the system, the strategy selection behavior mechanism of the retail channel subjects is deeply analyzed. It is found that enterprises’ strategy choices are influenced by both competitors and profits, and evolutionary stabilization strategies are not unique. In addition, changes in consumer loyalty, physical feelings, and sharing ratio during the evolutionary process will affect the stability rate of enterprises’ behavioral choices.

Recycling channel construction plays an important role in the development of closed-loop supply chains. In particular, the emergence of online recycling channels has made up for the shortcomings of traditional recycling channels with poor information and limited markets. This paper constructs an evolutionary game model to investigate the cooperation between manufacturers and e-commerce platforms with government intervention or not. The result shows that whether an enterprise actively participates in the cooperative recycling depends on the actual cost of establishing the cooperative recycling system. Additionally, the government support and supervision will affect the actual cost of cooperation. When the actual cost of establishing a collaborative recovery system is very large, under the influence of government interventions, there will be two kinds of evolutionary results for enterprises, either with cooperation or not at the same time. On the contrary, when the actual cost is small or medium, both manufacturers and the platforms will choose to cooperate. Thus, government participation in a cooperative recovery system is the best strategic option.

Consumers’ awareness of environmental protection is gradually strengthened, and they often consider environmental protection characteristics of products during purchasing products. Based on the characteristic of consumers’ dual preferences for product quality and environmental friendliness, this paper constructs a novel closed-loop supply chain with network externalities for new products and remanufactured products under different waste product recycling channel strategies. It discusses the influence of product recycling channel strategies and network externalities on the optimal decision of the company. By establishing the Stackelberg game model, the analysis found that the retail price of new products and remanufactured products is not affected by network externalities and recycling channel strategies, even if the wholesale price of remanufactured products increases with the influence of network externalities. The changing trend of market demand for new products and remanufactured products is different between products with network externalities and without network externalities. When the cost of remanufactured products is within certain range, the existence of network externalities makes the market demand for new products and remanufactured products increase simultaneously. Our study also found that even if products have positive network externalities that increases consumer utility, when the cost of remanufactured products is outside certain range, the company’s profit will be higher when products have no network externalities than that when products have network externalities.

A closed-loop supply chain operation is an effective way to improve the dual benefits of economy and environment. Inspired by the practice of closed-loop supply chain coordination, this paper attempts to investigate the supply chain operation strategies of different recycling modes and patent licensing strategies and consider the impact of government subsidies. We construct a multi-player game model of an original manufacturer, a remanufacturer, and a retailer under a waste product recycling mode, patent licensing strategy, and government subsidy system. We provide the operation strategies under different strategy combinations in the closed-loop supply chain, and then analyze their differences and the interests of various subjects. We further analyze the impact of government subsidies on the operation strategies of the supply chain. The results illustrate that when the original manufacturer adopts the fixed fee patent licensing strategy, the recycling price of waste products is higher. When the original manufacturer adopts the unit fee patent licensing strategy and the retailer and the remanufacturer participate in the recycling of waste products simultaneously, the original manufacturer will increase the unit patent licensing fee. When the remanufacturer recycles waste products alone, consumers can obtain greater unit income in the waste product recycling market. Different government subsidies have different effects on the wholesale price and the retail price of new products and remanufactured products.

This article studies the cooperative advertising problem of a two-period online supply chain consisting of a manufacturer and an online retail platform. The manufacturer provides national advertising in the first period to build the brand image and increase the awareness of the product. And the online retail platform provides platform advertising for selling the product to consumers on its platform during two periods. The manufacturer and the online retail platform may choose different cooperative advertising strategies for national advertising and platform advertising, which are one-way subsidy strategy, two-way subsidy strategy, and revenue-share strategy. We formulate a Stackelberg game model to study the cooperative advertising problem by taking price and advertising effect into account and analyze how the profit is influenced in different cooperative advertising strategies. We find that under the revenue-share strategy, the manufacturer provides a higher subsidy rate for the online retail platform advertising than that in other cooperative advertising strategies. Interestingly, there are conditions where, while just the manufacturer contributes a percentage of the platform advertising and the online retail platform has no effort on the national advertising, the total profit would be better than that in revenue-share strategy even in revenue-share strategy, the cooperative relationship is closer between the manufacture and the online retail platform.

Evaluating the regional trends of air pollution disaster risk in areas of heavy industry and economically developed cities is vital for regional sustainable development. Until now, previous studies have mainly adopted a traditional weighted comprehensive evaluation method to analyze the air pollution disaster risk. This research has integrated principal component analysis (PCA), a genetic algorithm (GA) and a backpropagation (BP) neural network to evaluate the regional disaster risk. Hazard risk, hazard-laden environment sensitivity, hazard-bearing body vulnerability and disaster resilience were used to measure the degree of disaster risk. The main findings were: (1) the air pollution disaster risk index of Liaoning Province, Beijing, Shanghai and Guangdong Province increased year by year from 2010 to 2019; (2) the mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) of each regional air pollution disaster risk index in 2019, as predicted by the PCA-GA-BP neural network, were 0.607, 0.317 and 20.3%, respectively; (3) the predicted results were more accurate than those using a PCA-BP neural network, GA-BP neural network, traditional BP neural network, support vector regression (SVR) or extreme gradient boosting (XGBoost), which verified that machine learning could be used as a method of air pollution disaster risk assessment to a considerable extent.

The simple and robust log-likelihood ratio (LLR) computation of coded Multiple Phase Shift Keying (MPSK) signals in Wireless Sensor Networks (WSNs) is considered under both phase noncoherent and Rayleigh fading channels for healthcare applications. We first simplify the optimal LLR for phase noncoherent channel, the estimation of the instantaneous channel state information (CSI) for both the fading amplitude and the additive white Gaussian noise (AWGN) is successfully avoided, and the complexity-intensive process for zero-order Bessel function of the first kind is also perfectly eliminated. Furthermore, we also develop the simplified LLR under Rayleigh fading channel. Correspondingly, the variance estimation for both AWGN and the statistical characteristic of the fading amplitude is no longer required, and the complicated process for implementation of the exponential function is also successfully avoided. Compared to the calculation of optimal LLR with full complexity, the proposed method is implementation-friendly, which is practically desired for energy-limited WSNs. The simulations are developed in the context of low-density parity-check (LDPC) codes, and the corresponding results show that the detection performance is extremely close to that of the full-complexity LLR metrics. That is, the performance degradation is efficiently prevented, whereas complexity reduction is also successfully achieved.