Search

Bayesian Personalized Ranking (BPR) is a representative pairwise learning method for optimizing recommendation models. It is widely known that the performance of BPR depends largely on the quality of negative sampler. In this paper, we make two contributions with respect to BPR. First, we find that sampling negative items from the whole space is unnecessary and may even degrade the performance. Second, focusing on the purchase feedback of E-commerce, we propose a negative sampler for BPR by leveraging the additional view data. In our proposed sampler, users’ viewed interactions are considered as an intermediate feedback between the purchased and unobserved interactions. We jointly learn the pairwise rankings of user preference among these three types of interactions and design a user-oriented weighting strategy during learning process, which is more effective and flexible. Compared to the vanilla BPR that applies a uniform sampler on all candidates, our view-enhanced sampler enhances BPR with a relative improvement over 36.64 and 16.40 percent on Beibei and Tmall datasets, respectively. Empirical studies demonstrate the importance of considering users’ additional feedback when modeling their preference on different items, which can effectively improve the quality of sampled negative items towards learning a better personalized ranking function. Our implementation is available at https://github.com/dingjingtao/NegativeSamplerBPR. [ABSTRACT FROM AUTHOR]

As online video service continues to grow in popularity, video content providers compete hard for more eyeball engagement. Some users visit multiple video sites to enjoy videos of their interest while some visit exclusively one site. However, due to the isolation of data, mining and exploiting user behaviors in multiple video websites remain unexplored so far. In this work, we try to model user preferences in six popular video websites with user viewing records obtained from a large ISP in China. The empirical study shows that users exhibit both consistent cross-site interests as well as site-specific interests. To represent this dichotomous pattern of user preferences, we propose a generative model of Multi-site Probabilistic Factorization (MPF) to capture both the cross-site as well as site-specific preferences. Besides, we discuss the design principle of our model by analyzing the sources of the observed site-specific user preferences, namely, site peculiarity and data sparsity. Through conducting extensive recommendation validation, we show that our MPF model achieves the best results compared to several other state-of-the-art factorization models with significant improvements of F-measure by 12.96, 8.24 and 6.88 percent, respectively. Our findings provide insights on the value of integrating user data from multiple sites, which stimulates collaboration between video service providers. [ABSTRACT FROM AUTHOR]

Smartphone mobile application (App) usage prediction, i.e., which Apps will be used next, is beneficial for user experience improvement. Through an in-depth analysis on a real-world dataset, we find that App usage is highly spatio-temporally correlated and personalized. Given the ability to model complex spatio-temporal contexts, we aim to apply deep learning to achieve high prediction accuracy. However, the personalization yields a problem: training one network for each individual suffers from data scarcity, yet training one deep neural network for all users often fails to uncover user preference. In this article, we propose a novel App usage prediction framework, named DeepApp, to achieve context-aware prediction via multi-task learning. To tackle the challenge of data scarcity, we train one general network for multiple users to share common patterns. To better utilize the spatio-temporal contexts, we supplement a location prediction task in the multi-task learning framework to learn spatio-temporal relations. As for the personalization, we add a user identification task to capture user preference. We evaluate DeepApp on the large-scale dataset by extensive experiments. Results demonstrate that DeepApp outperforms the start-of-the-art baseline by 6.44%. [ABSTRACT FROM AUTHOR]

Human mobility prediction techniques are instrumental for many important applications including service management and city planning. Previous work looks at the inherent patterns of a user's historical trajectories to predict his/her future location. Such method suffers when only a small number of historical locations are available, which is a main challenge for mobility prediction on sparse trajectory datasets. In this paper, we propose a multi-task learning based algorithm to predict users’ mobility by learning the mobility behaviors of different users at the same time and exploiting the similarities among them to overcome the sparse issue and improve the prediction performance. Specifically, we use a Bayesian mixture model to describe users’ spatio-temporal mobility patterns, where we introduce a novel von Mises distribution to model the temporal distribution of users’ mobility to better preserve its continuity across time. Then, we use the hierarchical Dirichlet process to perform joint prediction of all users’ mobility. This model allows us to leverage similar mobility patterns among users to improve the prediction performance for users with sparse trajectory data. We conduct extensive evaluations using data collected by a cellular network operator and mobile applications. Our evaluations show that our algorithms achieve prediction accuracy of 53.9% on average and 73.2% for users with high-quality mobility data, with the performance gap over 8.7% on average compared with the state-of-the-art algorithms, demonstrating the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Device-to-device (D2D) communication standardization is underway and considered as one of the key technologies in the 5G ecosystem. Eavesdropping is a well-known security risk for D2D communications. Thus, ensuring information security for both cellular users (CUs) and D2D pairs in an underlay network is quite challenging. In this paper, we look into the problem of physical-layer secure transmission jointly with resource allocation in D2D communications. Existing research works for D2D underlay networks considered perfect channel state information (CSI), which is usually unrealistic in practical networks due to the wireless channels’ dynamic nature. Hence, unlike the previous works, we are considering imperfect CSI that include estimation errors. We leverage social-domain and frame a coalitional game approach, enabling multiple D2D pairs to share CU spectral resource. We assume heterogeneous cellular network based practical scenario considering multiple eavesdroppers, intra-cell interference, and inter-cell interference to evaluate achievable performances in terms of sum-rate and secrecy capacity for both CUs and D2D pairs. Moreover, we prove our proposed algorithm stability, convergence, and computational complexity. The simulation results establish the effectiveness of our proposed approach that not only maximizes the sum rate (i.e., 10 $ \%$ –60 $ \%$) but also improves the secrecy capacity (i.e., 20 $ \%$ –67 $ \%$) in comparison to the baseline schemes. [ABSTRACT FROM AUTHOR]

With the explosion growth of mobile data demands for proximal services, device-to-device communication is proposed as a vital technology for the next generation cellular network. With the extensive increase in personal mobile devices, content transmission of proximal devices underlaying cellular networks is gaining considerable attention. However, due to the mobility constraint of mobile devices, content transmission underlaying cellular networks greatly affects the overall transmission capacity of these proximal devices. In this paper, we investigate the problem of mobility assisted content transmission and resource allocation by exploiting the contact patterns regulated by these proximal devices’ mobility. We formulate the content transmission and resource allocation with the help of the statistic property of contact rates, and then utilize convex optimization to determine the successful content transmission and resource allocation scheme. We present the optimal resource allocated content transmission algorithm based on the pseudo-polynomial time algorithm using dynamic programming to solve the optimization problem. Real data traces are utilized in our proposed algorithm to find out the natural strategies of mobile homophily. Extensive simulations under the realistic human mobility factors are evaluated to demonstrate the efficiency of our proposed scheme. [ABSTRACT FROM AUTHOR]

Recent proliferation of mobile networks and smart devices drives the rapid growth of mobile video traffic. Caching popular video content at any possible place of the network near to users could significantly increase their delivery efficiency. However, fundamental problems of how cache behaves and what is the principle for cache deployment in a mobile network under large-scale video views are still unknown, which include three closely relevant problems: 1) what is the best scale of regions to deploy cache appliances; 2) how many contents should be cached; and 3) which contents should be cached. In this paper, we synthetically study these problems by analyzing 10 million video view requests of six most popular content providers, in the city of Shanghai, China. We first aggregate videos from different providers by topics to measure user interests, and divide the city into nonoverlapping regions of different sizes to investigate the influence of scale. Then, we define metrics of view concentration, popular topic number, cache revenue, and popular topic similarity to quantitatively characterize cache behaviors and consequently answer the three problems. Our studies reveal that: 1) it is effective to deploy cache in regions of a wide range of different scales; 2) the larger scale region and the regions with more views should cache more contents; and 3) different regions, especially small scale ones, should cache different contents. Furthermore, based on trace-driven evaluation, we show that the overall cache hit ratio can increase by up to 30% when we apply above guidelines for cache deployment. [ABSTRACT FROM PUBLISHER]

In a device-to-device (D2D) communication underlying cellular network, a user equipment is desired to operate cooperatively and unselfishly to transmit data as relays. However, most users more or less behave in a selfish way, which makes user selfishness a key factor that affects the performance of the whole communication system. We focus on the impact of user selfishness on D2D communications. First, we distinguish user selfishness into two types in accordance with D2D transmission modes, namely the connected transmission and opportunistic transmission modes. The user selfishness in these two types of transmissions are modeled separately. Then, we propose a time-varying graph model that characterizes the impacts of both individual and social selfishness on the D2D communications. Simulation results obtained under the realistic networking settings indicate that the interaction between connected and opportunistic selfishness worsens the impairment caused by individual selfishness. Additionally, when concerning social selfishness, inside-community selfishness can be ignored in some occasions, while otherwise its role is heavily influenced by community numbers. [ABSTRACT FROM PUBLISHER]

Small cells in millimeter-wave (mmWave) band are able to provide multigigabit access data rates and have emerged as a cost-efficient solution to offer interference-free device-to-device (D2D) communications. In order to improve system performances and enhance user experiences, direct transmissions between devices need to be scheduled properly. We first propose a transmission scheduling scheme for radio access of small cells in the mmWave band, termed directional D2D medium access control (D3MAC), whereby a path-selection criterion is designed to enable D2D transmissions. Through extensive simulations, we demonstrate that D3MAC achieves near-optimal performances and outperforms other schemes significantly in terms of delay and throughput. Based on this near-optimal scheme, we then evaluate the impact of user behaviors, including the traffic mode and traffic load, as well as user density, denseness, and mobility, on the performance of D2D communications in mmWave small cells. Our study reveals that the performance of D2D communications is improved, as the user density and denseness increase, but this effect is only obvious under heavy traffic loads. Furthermore, user mobility is shown to be another important factor that influences the performance of D2D communications. The system performance is first improved, as the average user speed increases from static, but the performance is degraded significantly when the user speed becomes high. [ABSTRACT FROM PUBLISHER]

With huge unlicensed bandwidth available in most parts of the world, millimeter-wave (mmWave) communications in the 60-GHz band has been considered as one of the most promising candidates to support multigigabit wireless services. Due to high propagation loss of mmWave channels, beamforming is likely to be adopted as an essential technique. Consequently, transmission in the 60-GHz band is inherently directional. Directivity enables concurrent transmissions (spatial reuse), which can be fully exploited to improve network capacity. In this paper, we propose a multipath multihop scheduling scheme, which is known as multipath multihop (MPMH), for mmWave wireless personal area networks (WPANs), where the traffic across links of low channel quality is transmitted through multiple paths of multiple hops to unleash the potential of spatial reuse. We formulate the problem of MPMH as a mixed-integer linear program (MILP), which is generally NP-hard. To enable the implementation of the multipath multihop transmission in practice, we propose a heuristic scheme including path selection, traffic distribution, and MPMH to efficiently solve the formulated problem. Finally, through extensive simulations, we demonstrate that MPMH achieves near-optimal network performance in terms of transmission delay and throughput and enhances network performance significantly, compared with existing protocols. [ABSTRACT FROM AUTHOR]

With the explosive growth of mobile demand, small cells in millimeter-wave (mmWave) bands underlying macrocell networks have attracted intense interest from both academia and industry. MmWave communications in the 60-GHz band are able to utilize the huge unlicensed bandwidth to provide multiple Gb/s transmission rates. In this case, device-to-device (D2D) communications in mmWave bands should be fully exploited because there is no interference with the macrocell networks and higher achievable transmission rates. In addition, because there is less interference by directional transmission, multiple links including D2D links can be scheduled for concurrent transmissions (spatial reuse). With the popularity of content-based mobile applications, popular content downloading in the small cells needs to be optimized to improve network performance and enhance user experience. In this paper, we develop an efficient scheduling scheme for popular content downloading in mmWave small cells called popular content downloading scheduling (PCDS), where both D2D communications in close proximity and concurrent transmissions are exploited to improve transmission efficiency. In PCDS, a transmission path selection algorithm is designed to establish multihop transmission paths for users, aiming at better utilization of D2D communications and concurrent transmissions. After transmission path selection, a concurrent transmission scheduling algorithm is designed to maximize the spatial reuse gain. Through extensive simulations under various traffic patterns, we demonstrate that PCDS achieves near-optimal performance in terms of delay and throughput, as well as superior performance, compared with other existing protocols, particularly under heavy load. The impact of the maximum number of hops of transmission paths on its performance is also analyzed for a better understanding of the role of D2D communications. [ABSTRACT FROM AUTHOR]

With the emergence of ever-growing advanced vehicular applications, the challenges to meet the demands from both communication and computation are increasingly prominent. Without powerful communication and computational support, various vehicular applications and services will still stay in the concept phase and cannot be put into practice in the daily life. Thus, solving this problem is of great importance. The existing solutions, such as cellular networks, roadside units (RSUs), and mobile cloud computing, are far from perfect because they highly depend on and bear the cost of additional infrastructure deployment. Given tremendous number of vehicles in urban areas, putting these underutilized vehicular resources into use offers great opportunity and value. Therefore, we conceive the idea of utilizing vehicles as the infrastructures for communication and computation, named vehicular fog computing (VFC), which is an architecture that utilizes a collaborative multitude of end-user clients or near-user edge devices to carry out communication and computation, based on better utilization of individual communication and computational resources of each vehicle. By aggregating abundant resources of individual vehicles, the quality of services and applications can be enhanced greatly. In particular, by discussing four types of scenarios of moving and parked vehicles as the communication and computational infrastructures, we carry on a quantitative analysis of the capacities of VFC. We unveil an interesting relationship among the communication capability, connectivity, and mobility of vehicles, and we also find out the characteristics about the pattern of parking behavior, which benefits from the understanding of utilizing the vehicular resources. Finally, we discuss the challenges and open problems in implementing the proposed VFC system as the infrastructures. Our study provides insights for this novel promising paradigm, as well as research topics about vehicular information infrastructures. [ABSTRACT FROM PUBLISHER]

Heterogeneous networks, which deploy small cells in the mmWave band underlying the macrocell network, have attracted intense interest from both academia and industry. Different from the communication systems using lower carrier frequencies, mmWave communications have unique features, such as high propagation loss, directional communications, and sensitivity to blockage. Aiming to overcome the challenging problems in mmWave networks, such as interference management, spatial reuse, anti-blockage, QoS guarantee, and load balancing, we architecturally borrow the ideas of heterogeneous cloud radio access networks and software-defined networking to propose a software-defined mmWave mobile broadband system via a cross-layer design approach. In this architecture, a centralized controller is introduced by abstracting the control functions from the network layer to the physical layer. Through quantitative simulations in a realistic indoor scenario, we demonstrate the performance advantages of our system in terms of network throughput and flow throughput. This work is the first cross-layer and software-defined design for mmWave communications, which opens up an opportunity for mmWave communications to make a significant impact on future 5G networks. [ABSTRACT FROM PUBLISHER]

Background: Despite consensus that vaccines play an important role in combatting the global spread of infectious diseases, vaccine inequity is still a prevalent issue due to a deep-seated mentality of self-priority. We aimed to evaluate the existence and possible outcomes of a more equitable global vaccine distribution and explore a concrete incentive mechanism that promotes vaccine equity., Methods: We designed a metapopulation epidemiological model that simultaneously considers global vaccine distribution and human mobility, which we then calibrated by the number of infections and real-world vaccination records during the coronavirus disease 2019 (COVID-19) pandemic from March 2020 to July 2021. We explored the possibility of the enlightened self-interest incentive mechanism, which comprises improving one's own epidemic outcomes by sharing vaccines with other countries, by evaluating the number of infections and deaths under various vaccine sharing strategies using the proposed model. To understand how these strategies affect the national interests, we distinguished imported from local cases for further cost-benefit analyses that rationalise the enlightened self-interest incentive mechanism behind vaccine sharing., Results: The proposed model accurately reproduces the real-world cumulative infections for both global and regional epidemics (R 2 >0.990), which can support the following evaluations of different vaccine sharing strategies: High-income countries can reduce 16.7 (95% confidence interval (CI) = 8.4-24.9, P < 0.001) million infection cases and 82.0 (95% CI = 76.6-87.4, P < 0.001) thousand deaths on average by more actively sharing vaccines in an enlightened self-interest manner, where the reduced internationally imported cases outweigh the threat from increased local infections. Such vaccine sharing strategies can also reduce 4.3 (95% CI = 1.2-7.5, P < 0.01) million infections and 7.0 (95% CI = 5.7-8.3, P < 0.001) thousand deaths in middle- and low-income countries, effectively benefiting the whole global population. Lastly, the more equitable vaccine distribution could help largely reduce the global mobility reduction needed for pandemic control., Conclusions: The incentive mechanism of enlightened self-interest we explored here could motivate vaccine equity by realigning the national interest to more equitable vaccine distributions. The positive results could promote multilateral collaborations in global vaccine redistribution and reconcile conflicted national interests, which could in turn benefit the global population., Competing Interests: Disclosure of interest: The authors completed the ICMJE Disclosure of Interest Form (available upon request from the corresponding author) and disclose no relevant interests., (Copyright © 2023 by the Journal of Global Health. All rights reserved.)

Effective spatial planning of urban communities plays a critical role in the sustainable development of cities. Despite the convenience brought by geographic information systems and computer-aided design, determining the layout of land use and roads still heavily relies on human experts. Here we propose an artificial intelligence urban-planning model to generate spatial plans for urban communities. To overcome the difficulty of diverse and irregular urban geography, we construct a graph to describe the topology of cities in arbitrary forms and formulate urban planning as a sequential decision-making problem on the graph. To tackle the challenge of the vast solution space, we develop a reinforcement learning model based on graph neural networks. Experiments on both synthetic and real-world communities demonstrate that our computational model outperforms plans designed by human experts in objective metrics and that it can generate spatial plans responding to different circumstances and needs. We also propose a human-artificial intelligence collaborative workflow of urban planning, in which human designers can substantially benefit from our model to be more productive, generating more efficient spatial plans with much less time. Our method demonstrates the great potential of computational urban planning and paves the way for more explorations in leveraging computational methodologies to solve challenging real-world problems in urban science., (© 2023. The Author(s), under exclusive licence to Springer Nature America, Inc.)

Cities grow in a bottom-up manner, leading to fractal-like urban morphologies characterized by scaling laws. The correlated percolation model has succeeded in modeling urban geometries by imposing strong spatial correlations; however, the origin of the underlying mechanisms behind spatially correlated urban growth remains largely unknown. Our understanding of human movements has recently been revolutionized thanks to the increasing availability of large-scale human mobility data. This paper introduces a computational urban growth model that captures spatially correlated urban growth with a micro-foundation in human mobility behavior. We compare the proposed model with three empirical datasets, discovering that strong social interactions and long-term memory effects in human movements are two fundamental principles responsible for fractal-like urban morphology, along with the three important laws of urban growth. Our model connects the empirical findings in urban growth patterns and human mobility behavior., (© 2021. The Author(s), under exclusive licence to Springer Nature America, Inc.)

The trend for dense deployment in future 5G mobile communication networks makes current wired backhaul infeasible owing to the high cost. Millimetre-wave (mm-wave) communication, a promising technique with the capability of providing a multi-gigabit transmission rate, offers a flexible and cost-effective candidate for 5G backhauling. By exploiting highly directional antennas, it becomes practical to cope with explosive traffic demands and to deal with interference problems. Several advancements in physical layer technology, such as hybrid beamforming and full duplexing, bring new challenges and opportunities for mm-wave backhaul. This article introduces a design framework for 5G mm-wave backhaul, including routing, spatial reuse scheduling and physical layer techniques. The associated optimization model, open problems and potential solutions are discussed to fully exploit the throughput gain of the backhaul network. Extensive simulations are conducted to verify the potential benefits of the proposed method for the 5G mm-wave backhaul design.