Heterogeneous Users Research Articles

Task Offloading With Multi-Tier Computing Resources in Next Generation Wireless Networks

With the development of next-generation wireless networks, the Internet of Things (IoT) is evolving towards the intelligent IoT (iIoT), where intelligent applications usually have stringent delay and jitter requirements. In order to provide low-latency services to heterogeneous users in the emerging iIoT, multi-tier computing was proposed by effectively combining edge computing and fog computing. More specifically, multi-tier computing systems compensate for cloud computing through task offloading and dispersing computing tasks to multi-tier nodes along the continuum from the cloud to things. In this paper, we investigate key techniques and directions for wireless communications and resource allocation approaches to enable task offloading in multi-tier computing systems. A multi-tier computing model, with its main functionality and optimization methods, is presented in detail. We hope that this paper will serve as a valuable reference and guide to the theoretical, algorithmic, and systematic opportunities of multi-tier computing towards next-generation wireless networks.

Frame aggregation aware cluster based association management for heterogeneous users

Frame aggregation aware cluster based association management for heterogeneous users

Examining User Heterogeneity in Digital Experiments

Digital experiments are routinely used to test the value of a treatment relative to a status quo control setting — for instance, a new search relevance algorithm for a website or a new results layout for a mobile app. As digital experiments have become increasingly pervasive in organizations and a wide variety of research areas, their growth has prompted a new set of challenges for experimentation platforms. One challenge is that experiments often focus on the average treatment effect (ATE) without explicitly considering differences across major sub-groups — heterogeneous treatment effect (HTE). This is especially problematic because ATEs have decreased in many organizations as the more obvious benefits have already been realized. However, questions abound regarding the pervasiveness of user HTEs and how best to detect them. We propose a framework for detecting and analyzing user HTEs in digital experiments. Our framework combines an array of user characteristics with double machine learning. Analysis of 27 real-world experiments spanning 1.76 billion sessions and simulated data demonstrates the effectiveness of our detection method relative to existing techniques. We also find that transaction, demographic, engagement, satisfaction, and lifecycle characteristics exhibit statistically significant HTEs in 10% to 20% of our real-world experiments, underscoring the importance of considering user heterogeneity when analyzing experiment results, otherwise personalized features and experiences cannot happen, thus reducing effectiveness. In terms of the number of experiments and user sessions, we are not aware of any study that has examined user HTEs at this scale. Our findings have important implications for information retrieval, user modeling, platforms, and digital experience contexts, in which online experiments are often used to evaluate the effectiveness of design artifacts.

Development of a Knowledge-Based Expert System for Diagnosing Post-Harvest Diseases of Apple

Post-harvest diseases are one of the main causes of economical losses in the apple fruit production sector. Therefore, this paper presents an application of a knowledge-based expert system to diagnose post-harvest diseases of apple. Specifically, we detail the process of domain knowledge elicitation for constructing a Bayesian network reasoning system. We describe the developed expert system, dubbed BN-DSSApple, and the diagnostic mechanism given the evidence provided by the user, as well as a likelihood evidence method, learned from the estimated consensus of users’ and expert’s interactions, to effectively transfer the performance of the model to different cohorts of users. Finally, we detail a novel technique for explaining the provided diagnosis, thus increasing the trust in the system. We evaluate BN-DSSApple with three different types of user studies, involving real diseased apples, where the ground truth of the target instances was established by microbiological and DNA analysis. The experiments demonstrate the performance differences in the knowledge-based reasoning mechanism due to heterogeneous users interacting with the system under various conditions and the capability of the likelihood-based method to improve the diagnostic performance in different environments.

Befriended to polarise? The impact of friend identity on review polarisation—A quasi‐experiment

AbstractOpinion polarisation in social media has recently become a significant issue. The existing literature mainly attributes polarisation to online friends' informational social influence, that is, users are more likely to interact with others with similar opinions, which leads to the echo chamber effect. However, the impact of social interaction on individual polarisation may also result from normative social influence, which varies with social settings on the platform. In this paper, we leverage a quasi‐experiment to investigate the normative social influence of online friends on focal users' review polarity. We use fixed effects and difference‐in‐differences approaches, along with propensity score matching, to address the potential endogeneity in users' friend function adoption decisions. Our results indicate that adopting the friend function leads users to post less extreme ratings. We further separate the reviews into positive and negative, finding that the reduction in the review polarity for positive reviews is more prominent than for negative ones. Regarding user heterogeneity, our causal forest analysis uncovers that users with a higher engagement level on the platform are less affected by adopting the friend function than those with less engagement. Our study has clear implications for managers and platform designers, highlighting the importance of social function design in reducing social media induced polarisation.

Multi-UAV Relay Connectivity Optimization for Heterogeneous Users Based on Load Balancing and Throughput Maximization

By relaying messages between users, unmanned aerial vehicles (UAVs), which are frequently utilized in the communication industry, can be used as airborne communication relays to resolve connectivity problems. In order to effectively connect a large number of heterogeneous users dispersed on the ground, we deploy a large number of UAVs for reliable relay coverage and message transmission between users. We initially put forth a relay coverage algorithm that continuously optimizes the position of UAVs and the cell division of terrestrial users in order to provide users with full coverage. Second, we study several relay message forwarding methods between UAVs while taking into account the features of heterogeneous users. A relay selection method, which takes the relay link throughput as the optimization goal, is proposed to ensure full connectivity between UAVs. Finally, we contrast and analyze how various relay forwarding methods affect the effectiveness of the relay network. The experimental results demonstrate that the proposed relay coverage algorithm can balance the UAV relay load better and reduce transmission delay, while the suggested relay selection strategy can minimize the number of isolated UAVs and maximize the throughput of UAV relay links.

Superactive: a priority, latency, and SLA-aware resource management scheme for software defined space-air-ground integrated networks

The software-defined space-air-ground integrated network (SAGIN) is regarded as future-generation networking solution due to its wide-area coverage and seamless communication support for ground networks and resource-intensive application support for space-air networks. The SDN-based literary works are restricted only to resource management for space-air or ground networks, not both. The resource scheduling for multi-users caching, computing and data-transfer task accomplishment over software-defined SAGIN were out of their investigations by taking proactive local SDN, heterogenous users and applications, SLA requirements, priority, latency, and users' budget into account. To outperform the problems, this paper advocates a proactive SDN-based resource management scheme considering SLA requirements, latency, priority, and users' budget for multi-user task completion over software-defined SAGIN. This paper contributes an analytical model that covers task completion time, energy expenditure, financial cost, and SLA fulfilment metrics. The performance results illustrate that proposed scheme produces 72% time and 69% financial gain over the compared scheme.

Effects of congestion charging and subsidy policy on vehicle flow and revenue with user heterogeneity.

Traffic congestion is a major issue in urban traffic networks. Both congestion charging and subsidy policy can solve traffic congestion to some extent, but which one is better? Based on this, this paper constructs a typical transit network consisting of three travel tools in four common travel modes. Travelers' values of time affect their choice of transportation in the congestion network, thus a stochastic user equilibrium model is established by considering travelers' heterogenous values of time to evaluate the effects of different combinations of congestion charging and subsidy policies on vehicle flow and revenue. Numerical results indicate that the effectiveness of congestion charging and subsidy policy in alleviating traffic congestion depends on the object of charging or subsidizing. Congestion charging for private cars can reduce traffic flow and alleviate traffic congestion, but charging for ridesharing cars does not reduce traffic flow and may even cause traffic congestion. Subsidizing public buses does not reduce traffic flow, but it can ease congestion by coordinating traffic flow on both edges of the dual-modal transport. The combination of no subsidy for public buses and charging for both private cars and ridesharing cars can obtain the greatest revenue, but it does not alleviate traffic congestion. Although the combination of charging for private cars and subsidizing public buses does not bring the most benefits, it can reduce traffic flow, and its revenue is also considerable. This study can provide quantitative decision support for the government to ease traffic congestion and improve government revenue.

UPRec: User-aware Pre-training for sequential Recommendation

Recent years witness the success of pre-trained models to alleviate the data sparsity problem in recommender systems. However, existing pre-trained models for recommendation mainly focus on leveraging universal sequence patterns from user behavior sequences and item information, whereas ignore heterogeneous user information to capture personalized interests, which has been shown to contribute to the personalized recommendation. In this paper, we propose a simple yet effective model, called User-aware Pre-training for Recommendation (UPRec), which could flexibly encode heterogeneous user information into the sequential modeling of user behaviors. Specifically, UPRec first encodes the sequential behavior to generate user embeddings, and then jointly optimizes the model with the sequential objective and user-aware objective constructed from the user attributes and structured social graphs. Comprehensive experimental results on two real-world large-scale recommendation datasets demonstrate that UPRec can effectively enrich the user representations with user attributes and social relations and thus provide more appropriate recommendations for users.

Sensitivity to user mischaracterizations in electric vehicle charging

In this paper, we consider electric vehicle charging facilities that offer various levels of service for varying prices such that rational users choose a level of service that minimizes the total cost to themselves including an opportunity cost that incorporates users' value of time. In this setting, we study the sensitivity of the expected occupancy at the facility to mischaracterizations of user profiles and uncharacterized heterogeneity. For user profile mischaracterizations, we first provide a fundamental upper bound for the difference between the expected occupancy under any two different distributions on a user's impatience (i.e., value of time) that only depends on the minimum and maximum charging rate offered by the charging facility. Next, we consider the case when a user's impatience is a discrete random variable and study the sensitivity of the expected occupancy to the probability masses and attained values of the random variable. We show that the expected occupancy varies linearly with respect to the probability masses and is piecewise constant with respect to the attained values. Furthermore, we study the effects on the expected occupancy from the occurrence of heterogeneous user populations. In particular, we quantify the effect on the expected occupancy from the existence of sub-populations that may only select a subset of the offered service levels. Lastly, we quantify the variability of early departures on the expected occupancy. These results demonstrate how the facility operator might design prices such that the expected occupancy does not vary much under small changes in the distribution of a user's impatience, variable and limited user service needs, or uncharacterized early departure, quantities which are generally difficult to characterize accurately from data. We further demonstrate our results via examples.

Toward Spectrum Efficiency and Reliability for Heterogeneous Users in CR-Enabled Social Internet of Things

Toward Spectrum Efficiency and Reliability for Heterogeneous Users in CR-Enabled Social Internet of Things

Short Video Activism With and on Douyin: An Innovative Repertoire of Contention for Chinese Consumers

This article examines consumer video activism tactics in China and their impact on Chinese consumers and society. Drawing upon 56 semistructured interviews and a case study analysis of Chinese online consumer protest in 2018, we argue that short-video-activism tactics have become an innovative repertoire of contention for Chinese consumers and Douyin, the “sister app” of TikTok, has become a real-time updated database of this repertoire. Using Douyin as a case study, we argue that it plays three key roles in mediating Chinese consumer activism: a techno-cultural construct that affords highly heterogeneous users to present everyday experiences via short videos; a multisided market that profoundly affects the tactics consumers choose to amplify their voices; and a governing entity that both moderates content for its users and simultaneously is subject to government regulations.

Automated File Labeling for Heterogeneous Files Organization Using Machine Learning

File labeling techniques have a long history in analyzing the anthological trends in computational linguistics. The situation becomes worse in the case of files downloaded into systems from the Internet. Currently, most users either have to change file names manually or leave a meaningless name of the files, which increases the time to search required files and results in redundancy and duplications of user files. Currently, no significant work is done on automated file labeling during the organization of heterogeneous user files. A few attempts have been made in topic modeling. However, one major drawback of current topic modeling approaches is better results. They rely on specific language types and domain similarity of the data. In this research, machine learning approaches have been employed to analyze and extract the information from heterogeneous corpus. A different file labeling technique has also been used to get the meaningful and `cohesive topic of the files. The results show that the proposed methodology can generate relevant and context-sensitive names for heterogeneous data files and provide additional insight into automated file labeling in operating systems.

Upgraded Software and Embedded Improvements: A Puzzle of User Heterogeneity

Upgraded Software and Embedded Improvements: A Puzzle of User Heterogeneity

Influential factors in customer satisfaction of transit services: Using crowdsourced data to capture the heterogeneity across individuals, space and time

In a rapidly evolving and highly competitive transportation market, increasing customer satisfaction and ridership retention are essential for transit agencies. Understanding how different market segments perceive transit services can help service providers to identify potential priority areas and develop specialised strategies to address their varying travel concerns. However, traditional studies have predominantly investigated the variations across socioeconomic cohorts or travel characteristics but ignored the complex effect of spatial, temporal, and user heterogeneity. Recently social media data has attracted growing interest from academia as an alternative way to compensate public attitude surveys with a high volume of semantic, spatial, and temporal information. This study collected 177,807 microblogs from Sina Weibo to understand how customer satisfaction varies among different market segments characterised by social, temporal, and spatial heterogeneity. Methodologically, this study applies sentiment analysis as a real-time measurement of customers' satisfaction towards transit services, covering safety, crowdedness, reliability, personnel behaviour, and comfort. A beta regression model is then applied to identify the most important explanatory factors and the extent to which explanatory factors affect customers' satisfaction, respectively. The result indicates that age, gender, travel mode, time, and space significantly contribute to customers’ satisfaction with the transit system. Their varying impacts on different service attributes are also identified in this study. This study also reveals the highly polarised nature of online sentiment, explaining gendered attitudes. Our research framework could be used as a benchmark for other service industries to conduct similar market segment analysis and integrate it into the policy decision process.

Dynamic Discrimination Pricing and Freelance Drivers to Rebalance Mixed-Fleet Carsharing Systems

This paper presents pricing strategies for the relocation problem in mixed carsharing systems with heterogeneous users. On the demand side, a dynamic discriminatory pricing approach is introduced, which can obviate the need for operation-based repositioning, partially or fully. Moreover, it’s assumed that there are earnings-sensitive freelance drivers who may decide to participate in relocation operations, and their decisions depend on the wages are offered by the operation manager. As the operational decisions (trip pricing, relocators hiring, and charging scheduling) are tightly connected, and their interplay can significantly affect the performance of the carsharing system, an integrated model is proposed to optimize trip price and staff wage problems along with vehicle allocation and charge scheduling. To cope with computation difficulties for solving the proposed model, this paper presents a solution framework based on a rolling horizon approach. Through extensive numerical experiments, the performance and effectiveness of the proposed model are investigated under different assumptions and parameter settings. The results confirm that the proposed pricing strategies outperform common strategies in the literature and can significantly improve the performances of carsharing systems. The sensitivity analysis of several key parameters provides managerial insights into the operations management of carsharing systems.

On the Generalizability of Motion Models for Road Users in Heterogeneous Shared Traffic Spaces

Modeling mixed-traffic motion and interactions is crucial to assess safety, efficiency, and feasibility of future urban areas. The lack of traffic regulations, diverse transport modes, and the dynamic nature of mixed-traffic zones like shared spaces make realistic modeling of such environments challenging. This paper focuses on the generalizability of the motion model, i.e., its ability to generate realistic behavior in different environmental settings, an aspect which is lacking in existing works. Specifically, our first contribution is a novel and systematic process of formulating general motion models for pedestrians and cars, and application of this process is to extend our Game-Theoretic Social Force Model (GSFM) towards a general model for generating a large variety of motion behaviors of pedestrians and cars from different shared spaces. Our second contribution is to consider different motion patterns of pedestrians and cars by calibrating motion-related features of individual road users and clustering them into groups. We analyze three clustering approaches. The calibration and evaluation of our model are performed on three different shared space data sets. The results indicate that our model can realistically simulate a wide range of motion behaviors and interaction scenarios, and that model performance improves by considering heterogeneity in road users’ motion.

A User Segmentation Method in Heterogeneous Open Innovation Communities Based on Multilayer Information Fusion and Attention Mechanisms

The heterogeneity and diversity of users and external knowledge resources is a hallmark of open innovation communities (OICs). Although user segmentation in heterogeneous OICs is a prominent and recurring issue, it has received limited attention in open innovation research and practice. Most existing user segmentation methods ignore the heterogeneity and embedded relationships that link users to communities through various items, resulting in limited accuracy of user segmentation. In this study, we propose a user segmentation method in heterogeneous OICs based on multilayer information fusion and attention mechanisms. Our method stratifies the OIC and creates user node embeddings based on different relationship types. Node embeddings from different layers are then merged to form a global representation of user fusion embeddings based on a semantic attention mechanism. The embedding learning of nodes is optimized using a multi-objective optimized node representation based on the Deep Graph Infomax (DGI) algorithm. Finally, the k-means algorithm is used to form clusters of users and partition them into distinct segments based on shared features. Experiments conducted on datasets collected from four OICs of business intelligence and analytics software show that our method outperforms multiple baseline methods based on unsupervised and supervised graph embeddings. This study provides methodological guidance for user segmentation based on structured community data and semantic social relations and provides insights for its practice in heterogeneous OICs.

What drives me to use TikTok: A latent profile analysis of users' motives.

With TikTok rising in social media, the heterogeneity of users creates diversity in motives for using it. The issue of which profiles of TikTok use motives can be identified warrants greater understanding. Conducting latent profile analyses for a sample of 384 TikTok users, we identified four profiles, namely overall low motives, overall medium motives, overall high motives, and escapist addiction and novelty motives profiles. The former three profiles reflect different levels of motivations across four motives (socially rewarding self-presentation, trendiness, escapist addiction, and novelty). It is worth noting that TikTok users in the escapist addiction and novelty motives profile are mainly motivated by escapist addiction and novelty, but not socially rewarding self-presentation or trendiness motives. Through multivariate analysis of variance (MANOVA) and multinomial logistic regression, we further explore the differences in TikTok use between the profiles and the extent to which users' background characteristics and TikTok use predict their profile membership. The four profiles differ significantly in terms of the scores of almost all TikTok use motives. The frequency of TikTok use and video posting are the most notable predictors of profile membership. These results make theoretical contributions to the extant literature on social media use profiles by exploring the number and types of latent profiles of TikTok use motives, which also inform opportunities for enhancing user experience and imply tailored content recommendations to both achieve maximized gratifications and maintain mental wellbeing based on user profiles.

Dynamic Pricing and Mean Field Analysis for Controlling Age of Information

Today many mobile users in various zones are invited to sense and send back real-time useful information to keep the freshness of the content updates in such zones. However, due to the sampling cost in sensing and transmission, a user may not have the incentive to contribute real-time information to help reduce the age of information (AoI). We propose dynamic pricing for each zone to offer age-dependent monetary returns and encourage users to sample information at different rates over time. This dynamic pricing design problem needs to well balance the monetary payments as rewards to users and the AoI evolution, and is challenging to solve especially under the incomplete information about users’ arrivals and their private sampling costs. After formulating the problem as a nonlinear constrained dynamic program, to avoid the curse of dimensionality, we first propose to approximate the dynamic AoI reduction as a time-average term and successfully solve the approximate dynamic pricing in closed-form. Further, we extend the AoI control from a single zone to many zones with heterogeneous user arrival rates and initial ages, where each zone cares not only its own AoI dynamics but also the average AoI of all the zones in a mean field game system to provide a holistic service. Accordingly, we propose decentralized mean field pricing for each zone to self-operate by using a mean field term to estimate the average age dynamics of all the zones, which does not even require many zones to exchange their local data with each other.