Publisher Copyright: © 2026 IEEE.

| openaire: EC/HE/101070533/EU//EMIL

Publisher Copyright: © 2026 Owner/Author.

Flex sensors are widely used in e-textiles for detecting joint motions and, subsequently, full-body movements. A critical initial step in utilizing these sensors is determining the optimal placement on the body to accurately capture human motions. This task requires a combination of expertise in fields such as anatomy, biomechanics, and textile design, which is seldom found in a single practitioner. Generative AI, such as Large Language Models (LLMs), has recently shown promise in facilitating design. However, to our knowledge, the extent to which LLMs can aid in the e-textile design process remains largely unexplored in the literature. To address this open question, we conducted a case study focusing on shoulder motion detection using flex sensors. We enlisted three human designers to participate in an experiment involving human-AI collaborative design. We examined design efficiency across three scenarios: designs produced by LLMs alone, by humans alone, and through collaboration between LLMs and human designers. Our quantitative and qualitative analyses revealed an intriguing relationship between expertise and outcomes: the least experienced human designer achieved continuous improvement through collaboration, ultimately matching the best performance achieved by humans alone, whereas the most experienced human designer experienced a decline in performance. Additionally, the effectiveness of human-AI collaboration is affected by the granularity of feedback - incremental adjustments outperformed sweeping redesigns - and the level of abstraction, with observation-oriented feedback producing better outcomes than prescriptive anatomical directives. These findings offer valuable insights into the opportunities and challenges associated with human-AI collaborative e-textile design.

Vehicular Edge Computing (VEC) is an essential part of the Internet of Vehicles (IoV) due to its low latency by moving the computational resources close to the edge. Although the introduction of network slicing into VEC improves resource utilization through dynamic resource allocation based on real-time demands and priorities, it increases the deployment and operational costs. In view of this, this paper envisions a resource allocation strategy for VEC based on network slicing technique, in which the tasks involved are not only dynamic but also heterogeneous. To minimize the system cost (including resource consumption and computation, network slice maintenance and reconfiguration costs), this paper proposes CST-RL, a confidence-based self-adjusting two-timescale reinforcement learning algorithm. This solution performs resource allocation and activation scheduling for network slices on a large timescale, while allocating slices to heterogeneous tasks on a short timescale to meet dynamic demands. In addition, we innovatively utilize critic in reinforcement learning to predict and compare the expected benefits of network slices with versus without reconfiguration. We introduce the Random Network Distillation (RND) technique to assess the confidence level of these benefits, thus providing guidance for network slices to automatically decide whether and when to undergo reconfiguration. Finally, we demonstrate the effectiveness and superiority of CST-RL through simulations. Results show that CST-RL yields 27.77% lower system cost compared to the scheme without network slicing and 15.15% lower system cost compared to performing constant network slicing configuration, with guaranteed Quality-of-Service.

Video-based activity recognition has a wide array of applications across various industries. A persistent challenge in practice is the scarcity of labeled datasets from target domains needed for training machine learning models capable of accurate activity recognition. Cross-Domain Few-Shot Learning (CDFSL) offers a promising solution by facilitating knowledge transfer from a label-rich source domain to a data-scarce target domain. However, existing CDFSL approaches often overlook the similarities between the source and target domains on the achievable performance of activity recognition in the target domain. Existing metrics for measuring domain similarity, such as Maximum Mean Discrepancy, focus primarily on data distribution and fail to provide actionable guidance for selecting source domains. To address this gap, we explore domain similarities and their effects from various angles, including video attributes like camera angle, background scene, and label granularity. For our case study, we focus on activity recognition within industrial environments as the target application and apply state-of-the-art CDFSL methods across diverse source-target combinations, using open datasets such as Kinetics-100, HMDB51, HA-VID, and Meccano. Our results offer valuable insights into the influence of domain similarities, which can aid in the selection of source domains.

Cameras are widely deployed for visual inspection in manufacturing and construction industries, generating massive volumes of image and video data that demand automated solutions for defect detection. Knowledge distillation has shown strong potential for unsupervised industrial visual anomaly detection, a task of increasing importance in such large-scale, data-intensive environments. However, the conventional single-student-single-teacher framework often yields suboptimal learning of normal patterns, primarily due to the absence of specific constraints and potential feature loss. To address these challenges, we propose S2TKD, a novel dual-student-single-teacher architecture. It incorporates a pre-trained teacher network, an Anomalous Feature Denoising Student (AFDS) network, and a Normal Feature Student (NFS) network. The AFDS network focuses on filtering out anomalies by imposing stronger constraints on anomalous data, while the NFS network extracts normal features to recover subtle patterns suppressed by the AFDS network. To further improve the richness of feature representations within each student network, we integrate a multi-scale feature fusion module Dual Pyramid Network (DPN) between the encoder and the decoder. Furthermore, we propose a Dual Fusion Network (DFN) that accurately identifies anomalous regions by fusing the similarity of the outputs of each student and teacher network to obtain multi-scale similarity maps, which are then adaptively aggregated to generate the final anomaly map. Experimental results on four benchmark datasets demonstrate S2TKD's outperforms compared to the state-of-the-art. On the representative MVTec AD dataset, the I-AUROC, P-AUROC, and PRO reached 99.5%, 99.1%, and 96.9%, respectively, with the PRO showing a 1.9% increase over the current best result. The results highlight S2TKD’s effectiveness and scalability for large-scale industrial visual anomaly detection, making it a promising solution for real-world big data inspection systems.

Detecting social bots is crucial for mitigating the spread of misinformation and preserving online conversation authenticity. State-of-the-art solutions typically leverage graph neural networks (GNNs) to model user representations from social relationships and metadata. However, these approaches overlook two key factors: the similarity of a user and her neighbors, as well as the coordinated behaviors of social bots, resulting in a suboptimal detection performance. To address these issues, we propose HyperScan, a novel representation learning method for social bot detection. Specifically, we introduce three effective learners to capture pair-wise, hop-wise, and group-wise relations. HyperScan learns pair-wise user representations based on social relations and user features. It then enhances user representations by building hop-wise interactions across the learned pair-wise user representations for capturing the structure-level proximity information. Subsequently, it models user representations by constructing higher-order (group-wise) relations derived from user profiles, tweets, and social relations to capture the feature-level proximity knowledge. By leveraging hop-wise interactions and higher-order relations, HyperScan significantly improves bot detection performance. Our extensive experiments demonstrate that HyperScan outperforms state-of-the-art methods on three benchmark datasets. Additional studies validate the robustness and effectiveness of each component of HyperScan.

Uncrewed aerial vehicle (UAV)-enabled ISAC systems have received widespread attention due to the high mobility of UAVs with good line-of-sight (LoS) paths to ensure communication and sensing performance. However, the existing works on UAV-enabled ISAC mainly focus on optimizing communication performance (e.g., sum rate) and sensing performance, resulting in excessive energy consumption and reducing the flight endurance of the UAV. Motivated by this, we draw a trade-off between such performance and energy consumption to achieve robust and efficient UAV-enabled ISAC. In this work, we aim to maximize the worst-case energy efficiency in UAV-enabled ISAC by jointly designing the beamforming and the UAV trajectory, while ensuring the UAV energy constraints and the ISAC performance. Nevertheless, solving this problem is non-trivial due to its non-convex nature, and the high coupling of the transmit beamforming vectors and the UAV dynamics adds an additional layer of complexity. To effectively address this non-convex issue, we alternately optimize the transmit communication and sense beamforming, as well as the UAV dynamic variables to obtain a sub-optimal solution, and the algorithm complexity is lower than the existing algorithms. Experimental results show a trade-off between energy efficiency and average sum rate. Furthermore, they indicate the superiority of the proposed algorithm to enhance energy efficiency by significantly reducing energy consumption without causing excessive sum rate loss.

Uncrewed aerial vehicle (UAV)-assisted integrated sensing, computation, and communication (ISCC) network enables the entire data analysis process for practical applications. The existing works of UAV-assisted ISCC merely consider a single data source, and there still exist gaps in the collection of environmental data via multiple sources. Motivated by this, we envision a novel UAV-assisted air-ground collaborative ISCC network that fully explores the cooperation between aerial UAVs and ubiquitous ground Internet of Things (IoT) devices. To achieve effective, efficient, and fair joint task scheduling and resource allocation, an optimization is established to minimize two novel indicators, i.e., computation offloading and sensing penalty indices, subject to constraints of boundary, anti-collision, and UAV energy consumption. To tackle this problem, a deep reinforcement learning (DRL) framework is proposed where three advanced DRL algorithms are included under centralized and decentralized control schemes. In former scheme, the central controller makes globally optimal decisions. In latter scheme, multiple agents decide independently based on local information. We demonstrate a forest fire monitoring use case simulated in a national forest park. Results show the mutually interfering, competitive, and beneficial relationships among triple functionalities. Besides, our solution outperforms three state-of-the-art baselines in terms of effectiveness and efficiency.

The Domain Name System (DNS) serves as a foundational networking service, yet its inherent time-to-live (TTL)-based cache mechanism presents a conundrum—striving for both low query latency and robust cache consistency proves challenging. To address this, we introduce Aeacus: a middleware seamlessly integrated into the 5G core, engineered to optimize name resolution for QUIC. Aeacus adeptly fortifies DNS with substantial cache consistency by capitalizing on QUIC handshake states to detect cache inconsistency, without compromising query delay. Furthermore, Aeacus orchestrates the amalgamation of DNS queries and QUIC handshake messages, effectively truncating one round-trip of message exchange and reviving expired DNS cache to bolster cache hit rates. Our dual-pronged deployment, encompassing both commercial and test 5G networks, demonstrates Aeacus’ prowess. In direct comparison with DNS, Aeacus successfully truncates connection setup delays by a remarkable 8.9% to 71.8%, all while introducing a mere 5.9% overhead attributed to supplementary packet processing and forwarding expenses. Importantly, existing DNS-based systems reap the benefits of Aeacus without necessitating modifications. We demonstrate Aeacus’ seamless enhancement of DNS-based load balancers, extending QUIC's 0-RTT handshake to include 0-RTT connection setup and service migration.

As the number of vehicles grows in urban cities, planning vehicle routes to avoid congestion and decrease commuting time is important. In this paper, we study the shortest path problem (SPP) withmultiplesource-destination pairs, namely MSD-SPP, to minimize the average travel time of all routing paths. The asynchronous setting in MSD-SPP, i.e., vehicles may not simultaneously complete routing actions, makes it challenging for cooperative route planning among multiple agents and leads to ineffective route planning. To tackle this issue, in this paper, we propose a two-stage framework of inter-region and intra-region route planning by dividing an entire road network into multiple sub-graph regions. Next, the proposed asyn-MARL model allows efficient asynchronous multi-agent learning by three key techniques. Firstly, the model adopts a low-dimensional global state to implicitly represent the high-dimensional joint observations and actions of multi-agents. Secondly, by a novel trajectory collection mechanism, the model can decrease the redundancy in training trajectories. Additionally, with a novel actor network, the model facilitates the cooperation among vehicles towards the same or close destinations, and a reachability graph can prevent infinite loops in routing paths. On both synthetic and real road networks, the evaluation result demonstrates that asyn-MARL outperforms state-of-the-art planning approaches.

Deep Reinforcement Learning (DRL) has rapidly gained traction as a viable method for optimizing control in real-time video streaming. Recent research endeavors are shifting towards enabling direct DRL control over multiple streaming parameters, moving away from traditional bitrate only control. Despite this growing interest, there is a notable absence of a dedicated open-source framework to facilitate such research.

Joint task scheduling and resource allocation for unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) in emergency rescue activities has become an essential and challenging problem. However, the existing works have only considered such a problem for standalone UAV networks without considering the cooperation between UAVs and ground base stations (BSs), nor have they considered the uncertainty in terms of the availability of BSs due to damage/reconstruction in disaster events. In this paper, we consider a novel post-disaster UAV-assisted ISAC system where the UAVs are used to supplement the networking capacity of out-of-service ground BSs while using their radio signals for sensing. We apply transfer learning with deep reinforcement learning (DRL) to learn task scheduling and resource allocation strategies that can rapidly adapt to uncertainty in the environment. Experimental results show that the proposed algorithm outperforms the state-of-the-art in both communication and sensing performance and convergence speed. Moreover, the transfer learning-based DRL shows faster convergence and better robustness when the availability of BSs suddenly changes.

The design of thermal experiences, often only associated with hot and cold sensations, encompasses a much wider range of qualities that can evoke emotional and sensory effects on users extending beyond this basic binary nature. Through a phenomenological study of a traditional Finnish sauna, we delve into how individuals perceive and express full-body heat sensations using both verbal and non-verbal methods and infer dimensions and parameters of heat that can inform future thermal experience design. Findings from participants’ expressions lead to formulating experiential dimensions such as the dynamic nature of heat, the aesthetics of discomfort, considerations of texture and heaviness, interoception, and personal memories that expand our understanding what heat as a design material consists of and the various possibilities it may hold. Furthermore, we propose three thermal parameters of motion, timbre, and distribution which can contribute to designing more intricate heat experiences and pave the way for further research in temperature interfaces.

The temporal patterns of code submissions, denoted as work rhythms, provide valuable insight into the work habits and productivity in software development. In this paper, we investigate the work rhythms in software development and their effects on technical performance by analyzing the profiles of developers and projects from 110 international organizations and their commit activities on GitHub. Using clustering, we identify four work rhythms among individual developers and three work rhythms among software projects. Strong correlations are found between work rhythms and work regions, seniority, and collaboration roles. We then define practical measures for technical performance and examine the effects of different work rhythms on them. Our findings suggest that moderate overtime is related to good technical performance, whereas fixed office hours are associated with receiving less attention. Furthermore, we survey 92 developers to understand their experience with working overtime and the reasons behind it. The survey reveals that developers often work longer than required. A positive attitude towards extended working hours is associated with situations that require addressing unexpected issues or when clear incentives are provided. In addition to the insights from our quantitative and qualitative studies, this work sheds light on tangible measures for both software companies and individual developers to improve the recruitment process, project planning, and productivity assessment.

Human mobility trajectories are fundamental resources for analyzing mobile behaviors in urban computing applications. However, these trajectories, typically collected from location-based services, often suffer from sparsity and irregularity in time. To support the development of mobile applications, there is a need to recover or estimate missing locations of unobserved time slots in these trajectories at a fine-grained spatial-temporal resolution. Existing methods for trajectory recovery rely on either individual user trajectories or collective mobility patterns from all users. The potential to combine individual and collective patterns for precise trajectory recovery remains unexplored. Additionally, current methods are sensitive to the heterogeneous temporal distributions of the observable trajectory segments. In this paper, we propose CLMove (where CL stands for contrastive learning), a novel model designed to capture multilevel mobility patterns and enhance robustness in trajectory recovery. CLMove features a two-stage location encoder that captures collective and individual mobility patterns. The graph neural network based networks in CLMove explore location transition patterns within a single trajectory and across various user trajectories. We also design a trajectory-level contrastive learning task to improve the robustness of the model. Extensive experimental results on three representative real-world datasets demonstrate that our CLMove model consistently outperforms state-of-the-art methods in terms of trajectory recovery accuracy.

Accurate and up-to-date 3D maps, often represented as point clouds, are crucial for autonomous vehicles. Crowd-sourcing has emerged as a low-cost and scalable approach for collecting mapping data utilizing widely available dashcams and other sensing devices. However, it is still a non-trivial task to utilize crowdsourced data, such as dashcam images and video, to efficiently create or update high-quality point clouds using technologies like Structure from Motion (SfM). This study assesses and compares different image matching options available in open-source SfM software, analyzing their applicability and limitations for mapping urban scenes in different practical scenarios. Furthermore, the study analyzes the impact of various camera setups (i.e., the number of cameras and their placement) and weather conditions on the quality of the generated 3D point clouds in terms of completeness and accuracy. Based on these analyses, our study provides guidelines for creating more accurate point clouds.

The rapid proliferation of learning systems in an arbitrarily changing environment mandates the need to manage tensions between exploration and exploitation. This work proposes a quantum-inspired bandit learning approach for the learning-and-adapting-based offloading problem where a client observes and learns the costs of each task offloaded to the candidate resource providers, e.g., fog nodes. In this approach, a new action update strategy and novel probabilistic action selection are adopted, provoked by the amplitude amplification and collapse postulate in quantum computation theory. We devise a locally linear mapping between a quantum-mechanical phase in a quantum domain, e.g., Grover-type search algorithm, and a distilled probability-magnitude in a value-based decision-making domain, e.g., adversarial multi-armed bandit algorithm. The proposed algorithm is generalized, via the devised mapping, for better learning weight adjustments on favorable/unfavorable actions, and its effectiveness is verified via simulation.

Up-to-date and accurate road maps with traffic rules are crucial for traffic safety and efficiency. However, detecting changes in traffic rules, particularly in road signs in an efficient manner still remains an open challenge. This paper proposes a method to detect and classify seven types of changes, relying on observable traffic flow changes like average vehicle speed. Our method employs a deep learning-based binary relevance approach, treating each type of change as a separate binary classification task. Input data comprise information from citywide induction loops, detailing congestion levels and average speed for each road, which vary with time and location. Our model outputs change type probabilities for 2.5 km2city regions for every 10 minutes. Unlike GPS traces of buses and taxis, which provide merely a partial view of the traffic, induction loop data offers a comprehensive, cost-effective view of traffic. However, there are three key challenges of utilizing induction loop data for change detection and classification, including sparse deployment of induction loops, high dimensionality of input data, and severe class imbalance. To address the first two challenges, we introduce novel strategies comprising dimensionality reduction, multi-dimensional sliding windows, neural network architectural choices such as residual connections and stateful recurrency, and data augmentation. Regarding the class imbalance, we apply sample weighing in the loss function. These novel design choices result in effective solutions with F1-scores exceeding 80% in experiments with simulated and real-world traffic data.

Autonomous driving requires 3-D maps that provide accurate and up-to-date information about semantic landmarks. Since cameras present wider availability and lower cost compared with laser scanners, vision-based mapping solutions, especially, the ones using crowdsourced visual data, have attracted much attention from academia and industry. However, previous works have mainly focused on creating 3-D point clouds, leaving automatic change detection as open issue. We propose a pipeline for initiating and updating 3-D maps with dashcam videos, with a focus on automatic change detection based on comparison of metadata (e.g., the types and locations of traffic signs). To improve the performance of metadata generation, which depends on the accuracy of 3-D object detection and localization, we introduce a novel deep learning-based pixelwise 3-D localization algorithm. The algorithm, trained directly with Structure from Motion (SfM) point cloud data, accurately locates objects in 3-D space by estimating not only depth from monocular images but also lateral and height distances. In addition, we also propose a point clustering and thresholding algorithm to improve the robustness of the system to errors. We have performed experiments with different types of cameras, lighting, and weather conditions. The changes were detected with an average accuracy above 90%. The errors in the campus area were mainly due to traffic signs seen from a far distance to the vehicle and intended for pedestrians and cyclists only. We also conducted cause analysis of the detection and localization errors to measure the impact from the performance of the background technology in use.

Online developer communities like GitHub allow a massive number of developers to collaborate. However, the openness of the communities makes them vulnerable to different types of malicious attacks, since attackers can easily join these communities and interact with legitimate users. In this work, we propose GitSec, a deep learning-based solution for detecting malicious accounts in online developer communities. GitSec distinguishes malicious accounts from legitimate ones based on the account profiles, dynamic activity characteristics, as well as social interactions. First, GitSec introduces two user activity sequences and applies a parallel neural network design with an attention mechanism to process the sequences. Second, GitSec constructs two graphs to represent the interactions between users according to their repository operations. Especially, graph neural networks and structural hole theory are employed to deal with the two constructed graphs. Third, GitSec makes use of the descriptive features to enhance the detection performance. The final judgement is made by a decision maker implemented by a supervised machine learning-based classifier. Based on the real-world data of GitHub users, our comprehensive evaluations show that GitSec achieves a better performance than state-of-the-art solutions, with an AUC value of 0.916.

Mobile crowd sensing (MCS) with human participants has been proposed as an efficient way of collecting data for smart cities applications. However, there often exist situations where humans are not able or reluctant to reach the target areas, due to for example traffic jams or bad road conditions. One solution is to complement manual data collection with autonomous data collection using unmanned aerial vehicles (UAVs) equipped with various sensors. In this paper, we focus on the scenarios of UAV-assisted MCS and propose a task allocation method, called “UMA” (UAV-assistedMulti-taskAllocation method) to optimize the sensing coverage and data quality. The method incentivizes human participants to contribute sensing data from nearby points of interest (PoIs), with a limited budget. Meanwhile, the method jointly considers the optimization of task assignment and trajectory scheduling. It schedules the trajectories of UAVs, considering the locations of human participants, other UAVs and PoIs which are rarely visited by human participants. In detail, UAVs take care of two tasks in our proposal. One is to calibrate the data collected by the human participants whom the UAVs come across along their trajectories. The other is to collect data from the PoIs which are not covered by other UAVs or human participants. We apply deep reinforcement learning to schedule UAVs moving trajectories and sensing activities in order to minimize the overall energy cost. We evaluate the proposed scheme via simulation using two real data sets. The results show that our proposal outperforms the compared methods, in terms of coverage completed ratio, calibrating ratio, energy efficiency, and task fairness.

Real-time deep video analytic at the edge is an enabling technology for emerging applications, such as vulnerable road user detection for autonomous driving, which requires highly accurate results of model inference within a low latency. In this paper, we investigate the accuracy-latency trade-off in the design and implementation of real-time deep video analytic at the edge. Without loss of generality, we select the widely used YOLO-based object detection and WebRTC-based video streaming for case study. Here, the latency consists of both networking latency caused by video streaming and the processing latency for video encoding/decoding and model inference. We conduct extensive measurements to figure out how the dynamically changing settings of video streaming affect the achieved latency, the quality of video, and further the accuracy of model inference. Based on the findings, we propose a mechanism for adapting video streaming settings (i.e. bitrate, resolution) online to optimize the accuracy of video analytic within latency constraints. The mechanism has proved, through a simulated setup, to be efficient in searching the optimal settings.

With the emergence of compute-intensive and latency-sensitive vehicular applications, vehicular fog computing (VFC) has been proposed for catering to the thriving demands for computing and communication resources close to vehicles. In VFC scenarios where multiple tasks need to be offloaded simultaneously, the data, often coming from multiple sources, must be transmitted at a high data-rate in parallel. An antenna array system, a set of multiple connected antennas which work together as a single antenna, could achieve a significantly higher data-rate than a traditional single antenna. However, data-rate of the antenna array system may decrease due to the presence of interference. On the other hand, an antenna array system consumes more energy than a single antenna, which is antagonistic to vehicles powered by limited electricity. To address these challenges, we propose EAAV, a multi-task allocation strategy that enables multiple tasks to be offloaded concurrently in antenna array empowered VFC. EAAV aims at reducing the transmission power consumption while maintaining a high transmission data-rate, taking into account the mobility of vehicles and communication interference. We transform the multi-task allocation problem into a convex solvable one and evaluate the effectiveness of EAAV based on real-world vehicle trajectories. Compared with the existing task allocation strategy, EAAV improves the average transmission data-rate by up to 8.2% and reduces the average power consumption by up to 38.3%.

3D convolutional networks, as direct inheritors of 2D convolutional networks for images, have placed their mark on action recognition in videos. Combined with pretraining on large-scale video data, high classification accuracies have been obtained on numerous video benchmarks. In an effort to better understand why 3D convolutional networks are so effective, several works have highlighted their bias towards static appearance and towards the scenes in which actions occur. In this work, we seek to find the source of this bias and question whether the observed biases towards static appearances are inherent to 3D convolutional networks or represent limited significance of motion in the training data. We resolve this by presenting temporality measures that estimate the data-to-model motion dependency at both the layer-level and the kernel-level. Moreover, we introduce two synthetic datasets where motion and appearance are decoupled by design, which allows us to directly observe their effects on the networks. Our analysis shows that 3D architectures are not inherently biased towards appearance. When trained on the most prevalent video sets, 3D convolutional networks are indeed biased throughout, especially in the final layers of the network. However, when training on data with motions and appearances explicitly decoupled and balanced, such networks adapt to varying levels of temporality. To this end, we see the proposed measures as a reliable method to estimate motion relevance for activity classification in datasets and use them to uncover the differences between popular pre-training video collections, such as Kinetics, IG-65M and Howto100 m.

The strict latency constraints of emerging vehicular applications make it unfeasible to forward sensing data from vehicles to the cloud for processing. To shorten network latency, vehicular fog computing (VFC) moves computation to the edge of the Internet, with the extension to support the mobility of distributed computing entities [a.k.a fog nodes (FNs)]. In other words, VFC proposes to complement stationary FNs co-located with cellular base stations with mobile ones carried by moving vehicles (e.g., buses). Previous works on VFC mainly focus on optimizing the assignments of computing tasks among available FNs. However, capacity planning, which decides where and how much computing resources to deploy, remains an open and challenging issue. The complexity of this problem results from the spatiotemporal dynamics of vehicular traffic, varying computing resource demand generated by vehicular applications, and the mobility of FNs. To solve the above challenges, we propose a data-driven capacity planning framework that optimizes the deployment of stationary and mobile FNs to minimize the installation and operational costs under the quality-of-service constraints, taking into account the spatiotemporal variation in both demand and supply. Using real-world traffic data and application profiles, we analyze the cost efficiency potential of VFC in the long term. We also evaluate the impacts of traffic patterns on the capacity plans and the potential cost savings. We find that high traffic density and significant hourly variation would lead to dense deployment of mobile FNs and create more savings in operational costs in the long term.

Recent advances in deep learning have granted unrivaled performance to sensor-based human activity recognition (HAR) . However, in a real-world scenario, the HAR solution is subject to diverse changes over time such as the need to learn new activity classes or variations in the data distribution of the already-included activities. To solve these issues, previous studies have tried to apply directly the continual learning methods borrowed from the computer vision domain, where it is vastly explored. Unfortunately, these methods either lead to surprisingly poor results or demand copious amounts of computational resources, which is infeasible for the low-cost resource-constrained devices utilized in HAR. In this paper, we provide a resource-efficient and high-performance continual learning solution for HAR. It consists of an expandable neural network trained with a replay-based method that utilizes a highly-compressed replay memory whose samples are selected to maximize data variability. Experiments with four open datasets, which were conducted on two distinct microcontrollers, show that our method is capable of achieving substantial accuracy improvements over baselines in continual learning such as Gradient Episodic Memory, while utilizing only one-third of the memory and being up to 3× faster.

Today, Internet service deployment is typically implemented with server replication at multiple locations. Domain name system (DNS), which translates human-readable domain names into network-routable IP addresses, is typically used for distributing users to different server replicas. However, DNS relies on several network-based queries and the queries delay the connection setup process between the client and the server replica. In this article, we propose Artemis, a practical low-latency naming and routing system that supports optimal server (replica) selection based on user-defined policies and provides lower query latencies than DNS. Artemis uses a DNS-like domain name-IP mapping for replica selection and achieves low query latency by combining the name resolution process with the transport layer handshake process. In Artemis, all server replicas at different locations share the same anycast IP address, called Service Address. Clients use the Service Address to establish a transport layer connection with the server. The client's initial handshake packet is routed over an overlay network to reach the optimal server. Then the server migrates the transport layer connection to its original unicast IP address after finishing the handshake process. After that, service discovery is completed, and the client communicates with the server directly via IP addresses. To validate the effectiveness of Artemis, we evaluate its performance via both real trace-driven simulation and real-world deployment. The result shows that Artemis can handle a large number of connections and reduce the connection setup latency compared with state-of-the-art solutions. More specifically, our deployment across 11 Google data centers shows that Artemis reduces the connection setup latency by 39.4% compared with DNS.

Deep learning has permitted unprecedented performance in sensor-based human activity recognition (HAR). However, deep learning models often present high computational overheads, which poses challenges to their implementation on resource-constraint devices such as microcontrollers. Usually, the computational overhead increases with the input size. One way to reduce the input size is by constraining the number of sensor channels. We refer to sensor channel as a specific data modality (e.g. accelerometer) placed on a specific body location (e.g. chest). Identifying and removing irrelevant and redundant sensor channels is feasible via exhaustive search only in cases where few candidates exist. In this paper, we propose a smarter and more efficient way to optimize the sensor channel selection during the training of deep neural networks for HAR. Firstly, we propose a light-weight deep neural network architecture that learns to minimize the use of redundant and irrelevant information in the classification task, while achieving high performance. Secondly, we propose a sensor channel selection algorithm that utilizes the knowledge learned by the neural network to rank the sensor channels by their contribution to the classification task. The neural network is then trimmed by removing the sensor channels with the least contribution from the input and pruning the corresponding weights involved in processing them. The pipeline that consists of the above two steps iterates until the optimal set of sensor channels has been found to balance the trade-off between resource consumption and classification performance. Compared with other selection methods in the literature, experiments on 5 public datasets showed that our proposal achieved significantly higher F1-scores at the same time as utilizing from 76% to 93% less memory, with up to 75% faster inference time and as far as 76% lower energy consumption.

National roaming, multi-SIM and edge computing constitute key 5G technologies for the cooperative perception and remote driving of L4 (automated) vehicles. To that end, this article reports our progress to trial these technologies at the multi-PLMN experimental 5G SA testbed of Aalto University, Finland. Overall, the objective is to qualify 5G as a core connectivity for connected, cooperative and automated mobility.

Vehicle-based visual crowdsourcing is an emerging paradigm where the visual data collected from dash cameras are analyzed with the aim of measuring phenomena of common interest. To ensure the efficiency in vehicle-based visual crowdsourcing, there remain at least two technical challenges. First, to maximize the Quality of Information (QoI), which measures the amount of information extracted from the collected data, the context of data collection (e.g., camera position and orientation) must be taken into account in the process of task allocation. Second, intensive data collection from dense measurement points is key to ensure timely and accurate sensing of the targets of interest, whereas there exists a trade-off between the amount and rate of data collection and the computing and communication resources required to fulfill the latency constraint. To solve these challenges, we propose gathering and processing the collected data at the edge of the network and design a context-aware task allocation scheme, called FlexSensing, to jointly optimize the QoI and processing latency. We target application scenarios where commercial vehicles are turned into vehicular fog nodes (VFNs). These nodes gather and process the visual data collected from other vehicles within their coverage areas. The key idea of FlexSensing is to determine the rate of data collection for each sensing vehicle in the targeted area and to assign processing tasks to VFNs based on the estimated QoI and the workload of the VFNs. Given the excessive computational complexity of task allocation in this context, we formulate task allocation as a Markov decision process and apply a deep Q-network (DQN) to learn the optimized task allocation strategies for increasing the QoI of collected data while reducing the processing latency. To evaluate the effectiveness of FlexSensing, we simulate the mobility of different vehicles involved in the scenario at different times of the day based on real-world traffic data collected from the city of Helsinki and select a real-time object detection application for a case study. As compared with the existing task allocation strategies, the DQN-based task allocation strategies reduce the average processing latency by up to 51% and increase the QoI of the collected data by up to 34%.

Summary Wearable Cognitive Assistance (WCA) amplifies human cognition in real time through a wearable device and low‐latency wireless access to edge computing infrastructure. It is inspired by, and broadens, the metaphor of GPS navigation tools that provide real‐time step‐by‐step guidance, with prompt error detection and correction. WCA applications are likely to be transformative in education, health care, industrial troubleshooting, manufacturing, assisted driving, and sports training. Today, WCA application development is difficult and slow, requiring skills in areas such as machine learning and computer vision that are not widespread among software developers. This paper describesAjalon,an authoring toolchain for WCA applications that reduces the skill and effort needed at each step of the development pipeline. Our evaluation shows that Ajalon significantly reduces the effort needed to create new WCA applications.

Online social networks (OSNs) have become a commodity in our daily life. As an important concept in sociology and viral marketing, the study of social influence has received a lot of attentions in academia. Most of the existing proposals work well on dominant OSNs, such as Twitter, since these sites are mature and many users have generated a large amount of data for the calculation of social influence. Unfortunately, cold-start users on emerging OSNs generate much less activity data, which makes it challenging to identify potential influential users among them. In this work, we propose a practical solution to predict whether a cold-start user will become an influential user on an emerging OSN, by opportunistically leveraging the user’s information on dominant OSNs. A supervised machine learning-based approach is adopted, transferring the knowledge of both the descriptive information and dynamic activities on dominant OSNs. Descriptive features are extracted from the public data on a user’s homepage. In particular, to extract useful information from the fine-grained dynamic activities that cannot be represented by the statistical indices, we use deep learning technologies to deal with the sequential activity data. Using the real data of millions of users collected from Twitter (a dominant OSN) and Medium (an emerging OSN), we evaluate the performance of our proposed framework to predict prospective influential users. Our system achieves a high prediction performance based on different social influence definitions.

Accurate traffic speed prediction is an important and challenging topic for transportation planning. Previous studies on traffic speed prediction predominately used spatio-temporal and context features for prediction. However, they have not made good use of the impact of traffic incidents. In this work, we aim to make use of the information of incidents to achieve a better prediction of traffic speed. Our incident-driven prediction framework consists of three processes. First, we propose a critical incident discovery method to discover traffic incidents with high impact on traffic speed. Second, we design a binary classifier, which uses deep learning methods to extract the latent incident impact features. Combining above methods, we propose a Deep Incident-Aware Graph Convolutional Network (DIGC-Net) to effectively incorporate traffic incident, spatio-temporal, periodic and context features for traffic speed prediction. We conduct experiments using two real-world traffic datasets of San Francisco and New York City. The results demonstrate the superior performance of our model compared with the competing benchmarks.

In this work, we investigate activity recognition using multimodal inputs from heterogeneous sensors. Activity recognition is commonly tackled from a single-modal perspective using videos. In case multiple signals are used, they come from the same homogeneous modality, e.g. in the case of color and optical flow. Here, we propose an activity network that fuses multimodal inputs coming from completely different and heterogeneous sensors. We frame such a heterogeneous fusion as a non-local operation. The observation is that in a non-local operation, only the channel dimensions need to match. In the network, heterogeneous inputs are fused, while maintaining the shapes and dimensionalities that fit each input. We outline both asymmetric fusion, where one modality serves to enforce the other, and symmetric fusion variants. To further promote research into multimodal activity recognition, we introduce GloVid, a first-person activity dataset captured with video recordings and smart glove sensor readings. Experiments on GloVid show the potential of heterogeneous non-local fusion for activity recognition, outperforming individual modalities and standard fusion techniques.

The advancement of artificial intelligence and wearable computing triggers the radical innovation of cognitive applications. In this work, we propose VIMES, an augmented reality-based memory assistance system that helps recall declarative memory, such as whom the user meets and what they chat. Through a collaborative method with 20 participants, we design VIMES, a system that runs on smartglasses, takes the first-person audio and video as input, and extracts personal profiles and event information to display on the embedded display or a smartphone. We perform an extensive evaluation with 50 participants to show the effectiveness of VIMES for memory recall. VIMES outperforms (90% memory accuracy) other traditional methods such as self-recall (34%) while offering the best memory experience (Vividness, Coherence, and Visual Perspective all score over 4/5). The user study results show that most participants find VIMES useful (3.75/5) and easy to use (3.46/5).

Mobile crowd sensing (MCS) acts as a key component of Internet of Things (IoT), which has attracted much attention. In an MCS system, participants play an important role, since all the data are collected and provided by them. It is challenging but essential to recruit credible participants and motive them to contribute high-quality data. In this article, we propose a learning-based credible participant recruitment strategy (LC-PRS), which aims to maximize the platform and participants' profits at the same time via MCS participation. Specifically, the LC-PRS consists of two mechanisms, that a learning-based reward allocation mechanism (L-RAM) first calculates the maximum offered reward for different locations based on the number of participants in each location. Under a budget constraint, the proposed L-RAM prefers to collect sensing data from locations in which relatively few data have so far been collected. Furthermore, for each location, we develop a credible participant recruitment mechanism (C-PRM), which employs semi-Markov model and game theory to predict the quality of data provided by each participant and to recruit participants based on the predictions and the maximum offered reward calculated by L-RAM. We formally show LC-PRS has the desirable properties of computational efficiency, selection efficiency, individual rationality, and truthfulness. We evaluate the proposed scheme via simulation using three real data sets. Extensive simulation results well justify the effectiveness of the proposed approach in comparison with the other two methods.

Being a leading online service providing both local search and social networking functions, Foursquare has attracted tens of millions of users all over the world. Understanding the user behavior of Foursquare is helpful to gain insights for location-based social networks (LBSNs). Most of the existing studies focus on a biased subset of users, which cannot give a representative view of the global user base. Meanwhile, although the user-generated content (UGC) is very important to reflect user behavior, most of the existing UGC studies of Foursquare are based on the check-ins. There is a lack of a thorough study on tips, the primary type of UGC on Foursquare. In this article, by crawling and analyzing the global social graph and all published tips, we conduct the first comprehensive user behavior study of all 60+ million Foursquare users around the world. We have made the following three main contributions. First, we have found several unique and undiscovered features of the Foursquare social graph on a global scale, including a moderate level of reciprocity, a small average clustering coefficient, a giant strongly connected component, and a significant community structure. Besides the singletons, most of the Foursquare users are weakly connected with each other. Second, we undertake a thorough investigation according to all published tips on Foursquare. We start from counting the numbers of tips published by different users and then look into the tip contents from the perspectives of tip venues, temporal patterns, and sentiment. Our results provide an informative picture of the tip publishing patterns of Foursquare users. Last but not least, as a practical scenario to help third-party application providers, we propose a supervised machine learning-based approach to predict whether a user is an influential by referring to the profile and UGC, instead of relying on the social connectivity information. Our data-driven evaluation demonstrates that our approach can reach a good prediction performance with an F1-score of 0.87 and an AUC value of 0.88. Our findings provide a systematic view of the behavior of Foursquare users and are constructive for different relevant entities, including LBSN service providers, Internet service providers, and third-party application providers.

Online developer communities like GitHub provide services such as distributed version control and task management, which allow a massive number of developers to collaborate online. However, the openness of the communities makes themselves vulnerable to different types of malicious attacks, since the attackers can easily join and interact with legitimate users. In this work, we formulate the malicious account detection problem in online developer communities, and propose GitSec, a deep learning-based solution to detect malicious accounts. GitSec distinguishes malicious accounts from legitimate ones based on the account profiles as well as dynamic activity characteristics. On one hand, GitSec makes use of users' descriptive features from the profiles. On the other hand, GitSec processes users' dynamic behavioral data by constructing two user activity sequences and applying a parallel neural network design to deal with each of them, respectively. An attention mechanism is used to integrate the information generated by the parallel neural networks. The final judgement is made by a decision maker implemented by a supervised machine learning-based classifier. Based on the real-world data of GitHub users, our extensive evaluations show that GitSec is an accurate detection system, with an F1-score of 0.922 and an AUC value of 0.940.

Today, Internet service deployment is typically implemented with server replication at multiple locations for the purpose of load balancing, failure tolerance, and user experience optimization. Domain name system (DNS) is responsible for translating human-readable domain names into network-routable IP addresses. When multiple replicas exist, upon the arrival of a query, DNS selects one replica and responds with its IP address. Thus, the delay caused by the process of DNS query including the selection of replica is part of the connection setup latency.

Accurate prediction of traffic congestion at the granularity of road segment is important for planning travel routes and optimizing traffic control in urban areas. Previous works often calculated only the average congestion levels of a large region covering many road segments and did not take into account spatial correlation between road segments, resulting in inaccurate and coarse-grained prediction. To overcome these issues, we propose in this paper CPM-ConvLSTM, a spatiotemporal model for short-term prediction of congestion level in each road segment. Our model is built on a spatial matrix which incorporates both the congestion propagation pattern and the spatial correlation between road segments. The preliminary experiments on the traffic data set collected from Helsinki, Finland prove that CPM-ConvLSTM greatly outperforms 6 counterparts in terms of prediction accuracy.

Recent years have witnessed unprecedented amounts of telecommunication (Telco) data generated by Telco radio and core equipment. For example, measurement records (MRs) are generated to report the connection states, e.g., received signal strength at the mobile device, when mobile devices give phone calls or access data services. Telco historical data (e.g., MRs) have been widely analyzed to understand human mobility and optimize the applications such as urban planning and traffic forecasting. The key of these applications is to precisely localize outdoor mobile devices from these historical MR data. Previous works calculate the location of a mobile device based on each single MR sample, ignoring the sequential and temporal locality hidden in the consecutive MR samples. To address the issue, we propose a deep neural network (DNN)-based localization framework namely DeepLoc to ensemble a recently popular sequence learning model LSTM and a CNN. Without skillful feature design and post-processing steps, DeepLoc can generate a smooth trajectory consisting of accurately predicted locations. Extensive evaluation on 6 datasets collected at three representative areas (core business, urban and suburban areas in Shanghai, China) indicates that DeepLoc greatly outperforms 10 counterparts.

| openaire: EC/H2020/815191/EU//PriMO-5G

Smartphone-based indoor navigation services are desperately needed in indoor environments. However, the adoption of them has been relatively slow, due to the lack of fine-grained and up-to-date indoor maps, or the potentially high deployment and maintenance cost of infrastructure-based indoor localization solutions. This work proposes ViNav, a scalable and cost-efficient system that implements indoor mapping, localization, and navigation based on visual and inertial sensor data collected from smartphones. ViNav applies structure-from-motion (SfM) techniques to reconstruct 3D models of indoor environments from crowdsourced images, locates points of interest (POI) in 3D models, and compiles navigation meshes for path finding. ViNav implements image-based localization that identifies users' positions and facing directions, and leverages this feature to calibrate dead-reckoning-based user trajectories and sensor fingerprints collected along the trajectories. The calibrated information is utilized for building more informative and accurate indoor maps, and lowering the response delay of localization requests. According to our experimental results in a university building and a supermarket, the system works properly and our indoor localization achieves competitive performance compared with traditional approaches: in a supermarket, ViNav locates users within 2 seconds, with a distance error less than 1 meter and a facing direction error less than 6 degrees.

Visual crowdsourcing (VCS) offers an inexpensive method to collect visual data for implementing tasks, such as 3D mapping and place detection, thanks to the prevalence of smartphone cameras. However, without proper guidance, participants may not always collect data from desired locations with a required Quality-of-Information (QoI). This often causes either a lack of data in certain areas, or extra overheads for processing unnecessary redundancy. In this work, we propose SnapTask, a participatory VCS system that aims at creating complete indoor maps by guiding participants to efficiently collect visual data of high QoI. It applies Structure-from-Motion (SfM) techniques to reconstruct 3D models of indoor environments, which are then converted into indoor maps. To increase coverage with minimal redundancy, SnapTask determines locations for the next data collection tasks by analyzing the coverage of the generated 3D model and the camera views of the collected images. In addition, it overcomes the limitations of SfM techniques by utilizing crowdsourced annotations to reconstruct featureless surfaces (e.g. glass walls) in the 3D model. According to a field test in a library, the indoor map generated by SnapTask successfully reconstructs 100% of the library walls and 98.12% of objects and traversal areas within the library. With the same amount of input data our design of guided data collection increases the map coverage by 20.72% and 34.45%, respectively, compared with unguided participatory and opportunistic VCS.

This paper proposes a low-cost solution for mapping and locating UHF-band RFID tags in a 3D space using reader-equipped smartphones. Our solution includes a mobile augmented reality application for data collection and information visualization, and a cloud-based application server for calculating locations of the reader-equipped smartphones and the read RFID tags. Our solution applies computer vision and motion sensing techniques to track 3D locations of the RFID reader based on the visual and inertial sensor data collected from the companion smartphones. Meanwhile, it obtains the exact locations of RFID tags by calculating their relative positions from the readers based on the Angle of Arrival (AoA) concept. Our solution can be implemented with any low-cost fixed transmit power RFID readers, since it only requires the readers to report identifiers of read RFID tags. Furthermore, our solution does not require machine-controlled uniform movement of RFID readers, as it can handle the bias in the readings collected from randomly scattered positions. We have evaluated our solution with experiments in real environments using a commercially-off-the-shelf RFID reader and an Android phone. Results show that the average error in the positions of RFID tags is around 25cm for each of orthogonal axes on the floor plane, with the orders of RFID tags correctly detected in most cases.

Emerging vehicular applications, such as real-time situational awareness and cooperative lane change, demand for sufficient computing resources at the edge to conduct time-critical and data-intensive tasks. This paper proposes Fog Following Me (Folo), a novel solution for latency and quality balanced task allocation in vehicular fog computing. Folo is designed to support the mobility of vehicles, including ones generating tasks and the others serving as fog nodes. We formulate the process of task allocation across stationary and mobile fog nodes into a joint optimization problem, with constraints on service latency, quality loss, and fog capacity. As it is a NP-hard problem, we linearize it and solve it using Mixed Integer Linear Programming. To evaluate the effectiveness of Folo, we simulate the mobility of fog nodes at different times of day based on real-world taxi traces, and implement two representative tasks, including video streaming and real-time object recognition. Compared with naive and random fog node selection, the latency and quality balanced task allocation provided by Folo achieves higher performance. More specifically, Folo shortens the average service latency by up to 41\% while reducing the quality loss by up to 60\%.

When Telecommunication (Telco) networks provide phone call and data services for mobile users, measurement record (MR) data is generated by mobile devices during each call/session. MR data reports the connection states, e.g., signal strength, between mobile devices and nearby base stations. Given the MR data, the literature has proposed various Telco localization approaches, to localize mobile devices. Unfortunately, such approaches typically estimate the individual position independently, and could compromise the temporal and spatial locality in underlying mobility patterns. To address this issue, in this paper, we propose a deep neural network-based localization approach, namely RecuLSTM, to automatically extract contextual features and predict the positions of mobile devices from an input sequence of MR data. Our preliminary experiment validates that RecuLSTM greatly outperforms three recent works [1, 2, 4] which suffer from 3.2×, 1.91× and 3.56× median errors on the dataset in a 2G GSM suburban area, respectively.

Self-driving and connected vehicles, communicating with one another and with the road infrastructure are expected to revolutionize the automotive industry and our life in the future. We propose a distributed heuristic algorithm based on 5G-V2X technology to solve the motion planning problem of industrial vehicles, especially passing through intersections in industrial parks. Autonomous industrial vehicles must not only ensure that vehicles do not collide with each other through intersections, but also ensure the safety of pedestrians. So this case demands highly on the communication and mutual cooperation among vehicles. To solve this problem, we employ 5G-V2X technology to ensure low delay and highly reliable communications. Then, we propose a distributed heuristic algorithm to solve the mutual cooperation problem among vehicles. Specifically speaking, intersection safety information system will download LDM (Local Dynamic Map) information to vehicle closest to the intersection, and then our solution will give higher priority to paths that have more vehicles and no pedestrians. Starting with highest priority approach, our solution sets a time period for the vehicle to establish a timetable for it to cross the intersection. Preliminary experiments results showed that on the premise of ensuring the safety of pedestrians, the industrial vehicles can pass through the intersection smoothly and have the lowest delay at the same time.

With the popularity of sensor-rich mobile devices (e.g., smart phones and wearable devices), mobile crowdsourcing (MCS) has emerged as an effective method for data collection and processing. Compared with traditional wireless sensor networking, MCS holds many advantages such as mobility, scalability, cost-efficiency, and human intelligence. However, MCS still faces many challenges with regard to security, privacy, and trust. This paper provides a survey of these challenges and discusses potential solutions. We analyze the characteristics of MCS, identify its security threats, and outline essential requirements on a secure, privacy-preserving, and trustworthy MCS system. Further, we review existing solutions based on these requirements and compare their pros and cons. Finally, we point out open issues and propose some future research directions.

The recent proliferation of mobile devices such as smartphones and wearable devices has given rise to crowdsourcing Internet of Things (IoT) applications, such as urban mobility monitoring, virtual/augmented reality, smart city management, and indoor floor plan reconstruction and mapping. Various data collected by mobile devices with small or big volumes can be further processed, analyzed, and mined in order to support multifarious promising services with intelligence.

An increasing number of online services are hosted on public clouds. However, since a centralized cloud architecture imposes high network latency, researchers suggested moving latency sensitive applications, such as virtual and augmented reality ones, to the edge of the network. Nevertheless, little has been done for edge layer capacity estimation resulting in a great need towards practical tools and techniques for initial capacity planning. In this work we provide a novel capacity planning solution for hierarchical edge cloud that considers QoS requirements in terms of response delay, and diverse demands for CPU, GPU and network resources. Our solution improves edge utilization by combining complementary resource demands while satisfying QoS requirements. We prove effectiveness of our solution through a case study where we plan edge capacity for deploying an AR navigation and information system.

Using crowdsourced visual and inertial sensor data for indoor mapping has attracted much attention in recent years. Nevertheless, the opportunities and challenges of indoor tracking using crowdsourced maps have not been fully explored. In this work, we aim at tackling the challenges due to incomplete obstacle information in crowdsourced indoor maps, especially at the initialization stage of crowdsourcing. We propose a novel solution for particle-filtering-based indoor tracking, using the crowdsourced maps derived from image-based 3D point clouds. Our solution enhances particle filtering with density-based collision detection and history-based particle regeneration. Evaluation with real user traces demonstrates that our solution outperforms the state-of-the-art. In particular, it reduces the average distance error of indoor tracking by 47% when using crowdsourced 3D point clouds.

Energy consumption of data center has become an important challenge due to high electric cost and carbon dioxide emissions. Previous work has mainly focused on saving energy cost of servers, though the energy consumption of data center networks (DCNs), consisting of networking equipments like switches, also takes a significant part of the overall energy consumption. In this paper, we propose ProCons, an energy saving mechanism that dynamically consolidates traffic flows onto a small set of networking equipments in order to shut down idle ones for energy saving. Different from previous works that assume the traffic demands to be stable, ProCons takes into account the variance of traffic demand over time, and predicts future demand based on historical statistics. The traffic flows are then scheduled based on the predicted future demands and the capacity of each link. We evaluate ProCons with real life traces collected from data centers using a flow-level simulator. Our experimental results show that using ProCons, 40% of energy savings for DCNs can be gained while maintaining the good performance of flow transmission.

Utilizing network traffic scheduling to improve the energy efficiency of smartphones has been studied extensively in the past few years. These studies usually take certain approaches and make some assumptions concerning traffic predictability, regardless of whether these assumptions hold or whether the approaches have been studied before. In this paper, we conduct an analysis of existing work to find common approaches and assumptions among the proposed solutions. We find out the following: 1. A large part of the solutions target a specific (single) application or category of applications, and do not schedule the whole traffic transmitted on the smartphone. 2. A common assumption is that network traffic for smart phones is predictable. The focus of our work is to test these assumptions against real-world data and analyze whether the approaches presented in the literature are feasible. By leveraging two data sets from NetSense, we make several major contributions: 1. We demonstrate clearly, based on a large dataset, that background apps are the largest energy consumers for smart phones. 2. although some traffic traces exhibit long-term trends, in general traffic from a single app or a user is not predictable in the short-term. 3. achieving energy savings is difficult by scheduling traffic only from a specific app, since multi-app scenarios are so prevalent on today's smartphones. We also pinpoint future directions for traffic scheduling schemes.

The adoption of indoor navigation for smartphones has been relatively slow in the past years, although it would be direly needed in complex indoor areas. The primary barriers for its adoption include the lack of fine-grained and up-to-date indoor maps and the potential deployment and maintenance cost. In this paper we investigate the feasibility of utilizing crowdsourced data for building a smartphone-based indoor navigation system, focusing on the technical challenges caused by the varying quality of crowdsourced data. We developed iMoon, an indoor navigation system based on sensor-enriched 3D models of indoor environment, and evaluated its performance via a field study in a public building covering around 1,100 square meters.

The indoor location market is growing rapidly. However, fine-grained and up-to-date indoor maps are rarely available, and the existing indoor localization and navigation services mostly require extra infrastructures to provide accurate locations. In this demonstration we show iMoon, an indoor navigation system that provides indoor mapping, localization and navigation services using photos and sensor data collected from widely available mobile devices. The demonstration leverages a cohesive suite of computer vision, mobile sensing, and wireless networking techniques.

Wireless data transmission consumes a significant part of the overall energy consumption of smartphones, due to the popularity of Internet applications. In this paper, we investigate the energy consumption characteristics of data transmission over Wi-Fi, focusing on the effect of Internet flow characteristics and network environment. We present deterministic models that describe the energy consumption of Wi-Fi data transmission with traffic burstiness, network performance metrics like throughput and retransmission rate, and parameters of the power saving mechanisms in use. Our models are practical because their inputs are easily available on mobile platforms without modifying low-level software or hardware components. We demonstrate the practice of model-based energy profiling on Maemo, Symbian, and Android phones, and evaluate the accuracy with physical power measurement of applications including file transfer, web browsing, video streaming, and instant messaging. Our experimental results show that our models are of adequate accuracy for energy profiling and are easy to apply.

We propose a scalable Internet system for continuous collection of crowd-sourced video from devices such as Google Glass. Our hybrid cloud architecture, GigaSight, is effectively a Content Delivery Network (CDN) in reverse. It achieves scalability by decentralizing the collection infrastructure using cloudlets based on virtual machines~(VMs). Based on time, location, and content, privacy sensitive information is automatically removed from the video. This process, which we refer to as denaturing, is executed in a user-specific VM on the cloudlet. Users can perform content-based searches on the total catalog of denatured videos. Our experiments reveal the bottlenecks for video upload, denaturing, indexing, and content-based search. They also provide insight on how parameters such as frame rate and resolution impact scalability.

Searching for mobile data offloading solutions has been topical in recent years. In this paper, we present a collaborative WiFi-based mobile data offloading architecture - Metropolitan Advanced Delivery Network (MADNet), targeting at improving the energy efficiency for smartphones. According to our measurements,WiFi-based mobile data offloading for moving smartphones is challenging due to the limitation ofWiFi antennas deployed on existing smartphones and the short contact duration with WiFi APs. Moreover, our study shows that the number of open-accessible WiFi APs is very limited for smartphones in metropolitan areas, which significantly affects the offloading opportunities for previous schemes that use only open APs. To address these problems, MADNet intelligently aggregates the collaborative power of cellular operators, WiFi service providers and end-users. We design an energy-aware algorithm for energy-constrained devices to assist the offloading decision. Our design enables smartphones to select the most energy efficient WiFi AP for offloading. The experimental evaluation of our prototype on smartphone (Nokia N900) demonstrates that we are able to achieve more than 80% energy saving. Our measurement results also show that MADNet can tolerate minor errors in localization, mobility prediction, and offloading capacity estimation.

Offloading computation to cloud has been widely used for extending battery life of mobile devices. However, little effort has been invested in applying the offloading techniques to communication-related tasks. We propose SmartDiet, a toolkit to identify the constraints that reduce offloading opportunities and to calculate the energy-saving potential of offloading communication-related tasks. SmartDiet traces the method-level application execution and estimates the allocation of communication energy cost from traffic traces. We discuss key features of SmartDiet and show some preliminary results using a prototype implementation.

Energy consumption of wireless data transmission heavily depends on the shape of the outgoing traffic of the mobile device. In this paper, we propose a traffic scheduler that shapes the packets into consistent bursts based on per-packet performance constraints in order to reduce the overall transmission cost. Our scheduler takes into account the scenarios where multiple network applications run concurrently on the mobile device. We evaluate the traffic scheduler with real-life traffic traces from delay-sensitive applications, e.g. Internet radio and YouTube, and delay-tolerant applications e.g. Web browsing. The results show that depending on scenarios 23% to 72% energy savings can be achieved without noticeable performance degradation. Furthermore, our traffic scheduler is of low time complexity O(n), which makes it suitable to be deployed on proxies or directly on mobile devices.

Energy consumption of wireless data transmission, a significant part of the overall energy consumption on a mobile device, is context-dependent—it depends on both internal and external contexts, such as application workload and wireless signal strength. In this paper, we propose an event-driven framework that can be used for efficient power management on mobile devices. The framework adapts the behavior of a device component or an application to the changes in contexts, defined as events, according to developer-specified event-condition-action (ECA) rules that describe the power management mechanism. In contrast to previous work, our framework supports complex event processing. By correlating events, complex event processing helps to discover complex events that are relevant to power consumption. Using our framework developers can implement and configure power management applications by editing event specifications and ECA rules through XML-based interfaces. We evaluate this framework with two applications in which the data transmission is adapted to traffic patterns and wireless link quality. These applications can save roughly 12 percent more energy compared to normal operation.

Energy consumption caused by wireless transmission poses a big challenge to the battery lifetime of mobile devices. While the potential of using lossless compression for saving energy has been long acknowledged, no general solution has been proposed for applying lossless compression to energy adaptation for mobile services. We propose a proxy-based energy adaptation framework, in which the data to be transmitted is losslessly compressed on a proxy server according to context-aware policies. The context includes factors relevant to computational and communication cost, as well as the user's preferences. We showcase a context-aware policy which aims at minimizing clientside energy consumption caused by transmission and decompression. Using our framework, we implement an energy-aware mobile e-mail service, and present power measurement results that show significant energy savings.