AR-based product displays are widely used across various applications. While there is extensive research on the comparative advantages of AR over traditional displays, a critical gap persists in understanding the effects of the AR order (AR-first or AR-later) on consumer decision-making. This study reveals that, compared to AR-later display, AR-first display significantly reduces decision-making difficulty. This effect is mediated by cognitive load, moderated by purchase motive, AR vividness and need for cognition. For products associated with hedonic motives, AR with high vividness, and consumers with low need for cognition, the impact of AR order on consumer decision-making difficulty is stronger. Consequently, AR-first can yield many benefits, such as reducing cognitive load and decision-making difficulty. These findings align with and enrich the SEAD framework in AR marketing, offering valuable theoretical and practical insights for further exploring the dynamic mechanisms of AR marketing and optimization of practical applications.

With the rapid development of social media and mobile Internet, short reviews, such as Weibo and Twitter, have exploded online. Discovering topics from short reviews is significant for many practical applications. It can effectively not only identify users’ attitudes and emotions but also enhance customer satisfaction and shopping experience. Because reviews are relatively short, the sparsity of reviews considerably restricts the quality of topic discovery. To improve the efficiency of topic discovery, we introduce the concept of data enhancement and strengthen the data in sentences and words in short reviews based on the weight of importance. We then propose a topic model for reviews to topic discovery based on data enhancement (shorted as DE-LDA). We verify the rationality and feasibility of DE-LDA on real datasets. Results show that the proposed method outperforms benchmarks in topic discovery and also has better clustering effects.

Outlier detection is an important task in data mining, and many technologies for it have been explored in various applications. However, owing to the default assumption that outliers are not concentrated, unsupervised outlier detection may not correctly identify group anomalies with higher levels of density. Although high detection rates and optimal parameters can usually be achieved by using supervised outlier detection, obtaining a sufficient number of correct labels is a time-consuming task. To solve these problems, we focus on semi-supervised outlier detection with few identified anomalies and a large amount of unlabeled data. The task of semi-supervised outlier detection is first decomposed into the detection of discrete anomalies and that of partially identified group anomalies, and a distribution construction sub-module and a data augmentation sub-module are then proposed to identify them, respectively. In this way, the dual multiple generative adversarial networks (Dual-MGAN) that combine the two sub-modules can identify discrete as well as partially identified group anomalies. In addition, in view of the difficulty of determining the stop node of training, two evaluation indicators are introduced to evaluate the training status of the sub-GANs. Extensive experiments on synthetic and real-world data show that the proposed Dual-MGAN can significantly improve the accuracy of outlier detection, and the proposed evaluation indicators can reflect the training status of the sub-GANs.

In this paper, we address the capacity and coverage optimization (CCO) problem for LTE networks by means of self-organizing network (SON) techniques. A novel hybrid two-layer optimization framework is proposed to enhance the network capacity and coverage, where on the top layer a network entity of eCoordinator is implemented to ensure overall network coverage by optimizing the antenna tilt and capacity-coverage weight of each cell in a centralized manner, and on the bottom layer individual eNB optimizes cell-specific capacity and coverage by tuning its pilot power in a distributed manner. A heuristic algorithm is developed for the eCoordinator operation at large time granularity and the Genetic Programming (GP) approach is exploited for the eNB operation at small time granularity, for the purpose of tracking overall network performance as well as adapting to network dynamics. Our simulation results have demonstrated the usefulness of the proposed algorithms by enhancing network capacity and coverage performance under various system requirements.

In cognitive OFDMA networks, spectrum sensing is highly needed to accurately observe the spectrum environment, so as to avoid harmful interference to licensed users. However, to save energy, selfish users may not be willing to perform sensing. In order to encourage cognitive users to sense the multiple channels as well as guarantee fairness among the sensing users, this paper presents a joint PHY-MAC framework for cognitive OFDMA systems. In this framework, a higher access priority in the MAC layer will be rewarded to sensing users and the scheduling decision is made based on both the channel quality and sensing contribution of each user. The throughput for the cognitive system and the fairness for each cognitive user are analyzed under the joint framework. Simulation results will then show that the proposed protocol can achieve fairness and efficiency for cognitive users.

In cognitive radio systems, cooperative spectrum sensing in the physical layer is highly desired to detect the primary user accurately and to guarantee the quality of service (QoS) of the primary user. Due to the energy consumption in sensing the channels, the selfish users may not be willing to contribute to the cooperative sensing while they want to occupy more idle channels observed. To deal with this problem, we propose in this paper a game theoretic approach which will advocate users to spend power to sense the channel by using the access opportunity in the MAC layer as a payoff. In this protocol, the users who sense the channel are given higher priority to access the idle channel and meanwhile, the multiuser diversity in the MAC layer is exploited to increase the throughput for cognitive systems. The expressions for the average throughput and consumed power for a single user will be derived and then Nash equilibrium will be studied for the game model. It will be shown that the game will be characterized by the prisoner's dilemma. To guarantee the fairness and achieve higher throughput, we will design an evolutionary game protocol in which the Nash equilibrium can be dynamically changed based on the behaviors of cognitive users. Simulation results will show that the proposed protocol can achieve fairness and efficiency for cognitive users.

In cognitive radio systems, secondary users can share the spectrum with the primary user as long as the quality of service (QoS) of the primary system is guaranteed. However, the system throughput of the cognitive system will be limited when the QoS requirement is stringent. Recently cooperative diversity has been proposed as a powerful method that can provide dramatic gains in wireless environments. In this paper, we investigate the problem of spectrum sharing together with adaptive user cooperation in heterogeneous cognitive relay system. To maximize the throughput of the cognitive system, one best relay will be selected and besides, optimal power allocation is performed between the source and the relay. In addition, beamforming is applied to further reduce the interference and improve the system performance. Simulation results show the improvement of the throughput as opposed to the direct transmission.

In cognitive radio systems, secondary users can be coordinated to perform cooperative spectrum sensing so as to detect the primary user more accurately. However, when the sensing observations are forwarded to a common receiver through fading channels, the sensing performance can be severely degraded. In this paper, we propose a cluster-based cooperative spectrum sensing method to improve the sensing performance. By separating all the secondary users into a few clusters and selecting the most favorable user in each cluster to report to the common receiver, the proposed method can exploit the user selection diversity so that the sensing performance can be enhanced. Furthermore, decision fusion and energy fusion are both studied and the analytical performance results are given. Numerical results show that the sensing performance is improved significantly as opposed to conventional spectrum sensing.

In cognitive radio systems, cooperative spectrum sensing is conducted among the cognitive users so as to detect the primary user accurately. However, when the number of cognitive users tends to be very large, the bandwidth for reporting their sensing results to the common receiver will be very huge. In this paper, the authors employ a censoring method with quantization to decrease the average number of sensing bits to the common receiver. By censoring the collected local observations, only the users with enough information will send their local one bit decisions (0 or 1) to the common receiver. The performance of spectrum sensing is investigated for both perfect and imperfect reporting channels. Numerical results show that the average number of sensing bits decreases greatly at the expense of a little sensing performance loss.