Silent, eyes-free text entry remains challenging when speech and conventional touch input are impractical. Prior wearable systems often required custom sensors or limited users to a small vocabulary. We present MorsEar, an IMU-only earable framework that maps near-ear micro-gestures such as taps for dot/dash; slide/pull/circle for space/delete/send into character-level Morse, enabling unrestricted character composition while using a compact lexicon solely for lightweight on-device autocorrect. The result is a low-bandwidth, reduced-exposure communication channel that works eyes-free and voice-free in accessibility scenarios, silent zones, and constrained environments. MorsEar infers words using a physics-aware preprocessing stack and compact CNN feed a tempo-adaptive segmentation with rolling buffers; an on-device decoder with lightweight autocorrect provides real-time feedback entirely on-phone. In a 24-participant study (with four accessibility users) across Silent, Cafe, and Metro, MorsEar achieved CER 7.3% and WER 12.5% → 7.8% (Autocorrect), with median 9.3/9.1/5.8 WPM, respectively. Similar to other accessibility-oriented encodings such as Braille, Morse requires a brief familiarization period to learn the timing and rhythm of dots and dashes; after which, MorsEar shows that commodity earable IMUs can support discreet, low-exposure text entry that scales beyond discrete commands to language-level interaction.

Indoor carbon dioxide (CO2) can rapidly accumulate to form invisible pollution hotspots, posing significant health risks due to its odorless and colorless nature. Despite growing interest in wearable or stationary sensors for pollutant detection, effectively visualizing CO2 levels and engaging individuals remains an ongoing challenge. In this paper, we develop a portable wrist-sized pollution sensor that detects CO2 in real time at any indoor location and reveals CO2 bubbles by highlighting sudden spikes. In order to promote better ventilation habits and user awareness, we also develop a smartphone-based augmented reality (AR) game for users to locate and disperse these high-CO2 zones. A user study with 35 participants demonstrated increased engagement and heightened understanding of CO2’s health impacts. Our system’s usability evaluations yielded a median score of 1.88, indicating its strong practicality.

Wrist micro-behaviors during daily activities such as typing, handwriting, cooking, or carrying objects are valuable indicators for early detection of wrist disorders like Carpal Tunnel Syndrome and tendonitis. However, continuous personalized monitoring remains challenging without intrusive setups or hand-crafted rules. We present WristSense, a real-time, wrist-worn sensing system that introduces: (i) a magnetometer-stabilized quaternion fusion pipeline for orientation-agnostic tracking, (ii) a lightweight 1D-CNN + HMM model to distinguish functional gestures from strain-related coping behaviors, and (iii) an inertial tokenization scheme that converts events into structured prompts for a pretrained LLM. This enables zero-shot ergonomic feedback without per-user calibration. Evaluations across 12 participants show accurate posture tracking (< 10° MAE), high gesture recognition (macro F1 = 0.91), and improved usability (SUS = 85.2), with significantly higher user compliance compared to rule-based methods. WristSense demonstrates the potential of combining inertial sensing with LLMs for scalable, personalized ergonomic monitoring and early intervention.

We present SpineSense , an interactive earable-based framework for continuous monitoring of cervical spine posture and discomfort-related behavior in daily life. Leveraging inertial data from commercial off-the-shelf (COTS) earables (e.g., Apple AirPods Pro 2), SpineSense models the cervical vertebral chain (C1–C7) using SLERP-interpolated quaternions to estimate craniovertebral (CV) angles and identify early pain-relief gestures (e.g., neck rubbing, circular head rolls) that are associated with early signs of musculoskeletal fatigue, as informed by clinical observation. A real-time feedback loop delivers posture-based alerts and weekly compliance summaries to support user awareness and long-term posture correction. Central to our design is a clinician-in-the-loop methodology: clinical experts (including orthopedic surgeons and physiotherapists) informed threshold selection (e.g., CV angle cutoffs), interpreted common discomfort behaviors, and iteratively guided the structure of weekly feedback reports. We evaluate the system on 20 participants and achieve low spine angle estimation error (MAE: 0.876° , RMSE: 1.02° , r = 0.95), and discomfort gesture classification accuracy of F 1 = 0.97. Usability studies across diverse activities show high acceptance (SUS = 84.75, NASA-TLX = 32.7, PSSUQ = 2.13), with formal ANOVA tests validating statistically significant improvements over baseline interfaces. Together, our findings establish the feasibility of engineering interactive cervical health systems using COTS earables that support real-time feedback, clinician-informed reporting, and pervasive deployment in naturalistic settings.

Runtime application observability is crucial not only for system provenance but also for the orchestration of deployed microservices in dynamic sandboxed distributed computing environments. Also, log extraction and aggregation in highly distributed and sandboxed environments pose significant challenges, especially when preserving the causal order of the events triggered by different asynchronous microservices running over multiple hosts. However, ensuring causally consistent logging of application events is challenging, although it is vital for continuously tracing and profiling the underlying platform. This paper proposesXPLOG, a scalable, pluggable, easily deployable, and dynamic runtime observability framework for distributed sandboxed computing platforms that leverages the capability of extended Berkeley Packet Filters (eBPF) to intercept system-level events within the host while capturing and amalgamating relevant application and system logs to produce globally causally-consistent log streams. Through qualitative and quantitative analysis, we observe thatXPLOGsignificantly improves log richness with minimum system overhead while preserving the causality of log-generating events across multiple microservices.

Blockchain interoperability is increasingly recognized as the centerpiece for robust interactions among decentralized services. Blockchain ledgers are generally tamper-proof and thus enforce non-repudiation for transactions recorded within the same network. However, such a guarantee does not hold for cross blockchain transactions. When disruptions occur due to malicious activities or system failures within one blockchain network, foreign networks can take advantage by denying legitimate claims or mounting fraudulent liabilities against the defenseless network. In response, this paper introduces InterSnap, a novel blockchain snapshot archival methodology, for enabling auditability of cross blockchain transactions, enforcing non-repudiation. InterSnap introduces cross-chain transaction receipts that ensure their irrefutability. Snapshots of ledger data along with these receipts are utilized as non-repudiable proof of bilateral agreements among different networks. InterSnap enhances system resilience through a distributed snapshot generation process, need-based snapshot scheduling process, and archival storage and sharing via decentralized platforms. Through a prototype implementation based on Hyperledger Fabric, we conducted experiments using on-premise machines, AWS public cloud instances, as well as a private cloud infrastructure. We establish that InterSnap can recover from malicious attacks while preserving cross chain transaction receipts. Additionally, our proposed solution demonstrates adaptability to increasing loads while securely transferring snapshot archives with minimal overhead.

Automated dietary monitoring is essential for gaining insights into eating behaviors, especially for managing chronic conditions such as obesity, diabetes, and hypercholesterolemia. Earable-based inertial sensing has been found promising for detecting chewing and eating activities; however, further insights like what, when, and how much is being eaten are crucial information for effective dietary assessment. Therefore, we propose BiteSense, an earable-based system that leverages inertial sensors (IMU) to monitor food intake and classify various food types. Using a hierarchical classification model, the system analyzes masticatory kinematics to detect food states, textures, nutritional value, and cooking methods, ultimately identifying specific foods consumed, as well as estimating food intake amount and meal type. A semi-controlled user study involving 38 participants from diverse backgrounds demonstrated the system’s high accuracy, with an F1 score of 0.86 for detecting the masticatory process using a leave-one-subject-out (LOSO) approach, while exhibiting significant improvement over benchmark algorithms in extensive experiments by 8-12%.

Maintaining a safe distance from the vehicle ahead is critical for safe driving. While LiDAR sensors can be used for distance measurement, their high cost and the large number of vehicles without such sensors—especially in developing regions—necessitate a low-cost yet effective alternative. To address this, we introduce CarVision, a system that utilizes a commercially available single-chip mmWave radar mounted on a car’s dashboard for vehicle ranging. CarVision detects vehicles within the radar’s field of view (FoV) and computes both the distance and relative speed of the vehicles in front. Our system employs a novel hybrid vehicle detection and tracking approach, combining deep neural network-based detection with range tracking in a streamlined pipeline to optimize accuracy and speed. Additionally, we’ve developed a smartphone-based alert system that warns drivers if a vehicle approaches within a critical distance (approximately 2 meters). CarVision demonstrates reliable ranging performance in daytime and nighttime conditions, with accurate measurements up to 50 meters.

In this work, we introduce RadarTrack, an innovative ego-speed estimation framework utilizing a single-chip millimeter-wave (mmWave) radar to deliver robust speed estimation for mobile platforms. Unlike previous methods that depend on cross-modal learning and computationally intensive Deep Neural Networks (DNNs), RadarTrack utilizes a novel phase-based speed estimation approach. This method effectively overcomes the limitations of conventional ego-speed estimation approaches which rely on doppler measurements and static surroundings. RadarTrack is designed for low-latency operation on embedded platforms, making it suitable for real-time applications where speed and efficiency are critical. Our key contributions include the introduction of a novel phase-based speed estimation technique solely based on signal processing and the implementation of a real-time prototype validated through extensive real-world evaluations. By providing a reliable and lightweight solution for ego-speed estimation, RadarTrack holds significant potential for a wide range of applications, including micro-robotics, augmented reality, and autonomous navigation.

In this demonstration we introduce a novel approach to ego-speed estimation using a single-chip Commercial-Off-the-Shelf (COTS) millimeter-wave (mmWave) radar. Contrary to previous approaches that are cross-modal learning based and dependent on the computationally expensive nature of DNN's, our proposed approach RadarTrack is based on a phase-based approach to speed estimation. Our approach successfully overcomes the drawbacks of traditional ego-speed estimation methods that are doppler-based and static environment dependent. RadarTrack is intended to support low-latency execution on embedded systems such that it can be used in real-time applications where efficiency and speed are equally important. We have also created a real-time visualizer which is capable of recording the phasebased ego-speed together with state-of-the-art doppler-based speed estimation and comparatively demonstrate how phasebased ego-speed estimation can better record the speed of an ego-vehicle.

Traditional human-in-the-loop-based annotation for time-series data like inertial data often requires access to alternate modalities like video or audio from the environment. These alternate sources provide the necessary information to the human annotator, as the raw numeric data are often too obfuscated even for an expert. However, this traditional approach has many concerns surrounding overall cost, efficiency, storage of additional modalities, time, scalability, and privacy. Interestingly, recent large language models (LLMs) are also trained with vast amounts of publicly available alphanumeric data, which allows them to comprehend and perform well on tasks beyond natural language processing. Naturally, this opens up a potential avenue to explore the opportunities in using these LLMs as virtual annotators where the LLMs will be directly provided the raw sensor data for annotation instead of relying on any alternate modality. Naturally, this could mitigate the problems of the traditional human-in-the-loop approach. Motivated by this observation, we perform a detailed study in this article to assess whether the state-of-the-art (SOTA) LLMs can be used as virtual annotators for labeling time-series physical sensing data. To perform this in a principled manner, we segregate the study into two major phases. In the first phase, we investigate the challenges an LLM like GPT-4 faces in comprehending raw sensor data. Considering the observations from Phase 1, in the next phase, we investigate the possibility of encoding the raw sensor data using SOTA SSL approaches and utilizing the projected time-series data to get annotations from the LLM. Detailed evaluation with four benchmark HAR datasets shows that SSL-based encoding and metric-based guidance allow the LLM to make more reasonable decisions and provide accurate annotations without requiring computationally expensive fine-tuning or sophisticated prompt engineering.

Continuous detection of human activities and presence is essential for developing a pervasive interactive smart space. Existing literature lacks robust wireless sensing mechanisms capable of continuously monitoring multiple users’ activities without prior knowledge of the environment. Developing such a mechanism requires simultaneous localization and tracking of multiple subjects. In addition, it requires identifying their activities at various scales, some being macro-scale activities like walking, squats, etc., while others are micro-scale activities like typing or sitting, etc. In this paper, we develop a holistic system called MARS using a single Commercial off-the-shelf (COTS) Millimeter Wave (mmWave) radar, which employs an intelligent model to sense both macro and micro activities. In addition, it uses a dynamic spatial time-sharing approach to sense different subjects simultaneously. A thorough evaluation of MARS shows that it can infer activities continuously with an accuracy of > 93% and an average response time of ≈ 2 sec, with 5 subjects and 19 different activities.

Developing robust wireless sensing mechanisms for continuously monitoring human activities and presence is crucial for creating pervasive interactive intelligent spaces. The existing literature lacks solutions that continuously monitor multiple users’ activities without prior knowledge of the environment. This requires simultaneous localization and tracking of multiple subjects and identifying their activities at various scales, including macro-scale activities like walking and squats and micro-scale activities like typing or sitting. In this demo, we present MARS , a holistic system using a single off-the-shelf mmWave radar. MARS employs an intelligent model to sense both macro and micro activities and uses a dynamic spatial time-sharing approach to sense different subjects simultaneously. Our thorough evaluation demonstrates that MARS can continuously infer activities with over 93% accuracy and an average response time of approximately 2 seconds, even with five subjects performing 19 different activities.

Precise ego-motion measurement is crucial for various applications, including robotics, augmented reality, and autonomous navigation. In this poster, we propose mmPhase, an odometry framework based on single-chip millimetre-wave (mmWave) radar for robust ego-motion estimation in mobile platforms without requiring additional modalities like the visual, wheel, or inertial odometry. mmPhase leverages a phase-based velocity estimation approach to overcome the limitations of conventional doppler resolution. For real-world evaluations of mmPhase we have developed an ego-vehicle prototype. Compared to the state-of-the-art baselines, mmPhase shows superior performance in ego-velocity estimation.

In recent years, indoor air pollution has posed a significant threat to our society, claiming over 3.2 million lives annually. Developing nations, such as India, are most affected since lack of knowledge, inadequate regulation, and outdoor air pollution lead to severe daily exposure to pollutants. However, only a limited number of studies have attempted to understand how indoor air pollution affects developing countries like India. To address this gap, we present spatiotemporal measurements of air quality from 30 indoor sites over six months during summer and winter seasons. The sites are geographically located across four regions of type: rural, suburban, and urban, covering the typical low to middle-income population in India. The dataset contains various types of indoor environments (e.g., studio apartments, classrooms, research laboratories, food canteens, and residential households), and can provide the basis for data-driven learning model research aimed at coping with unique pollution patterns in developing countries. This unique dataset demands advanced data cleaning and imputation techniques for handling missing data due to power failure or network outages during data collection. Furthermore, through a simple speech-to-text application, we provide real-time indoor activity labels annotated by occupants. Therefore, environmentalists and ML enthusiasts can utilize this dataset to understand the complex patterns of the pollutants under different indoor activities, identify recurring sources of pollution, forecast exposure, improve floor plans and room structures of modern indoor designs, develop pollution-aware recommender systems, etc.

Road traffic congestion affects not only the commute delay but also a city's overall social, economic, and environmental growth. Existing approaches for road congestion mitigation primarily adopt a reactive approach by detecting congestion after it occurs and recommending alternate routes to the vehicles, which fails to prevent congestion cascading. In contrast, we propose a pervasive platform called ProCon that proactively infers the driving micro-behaviors that can contribute to congestion formation and assist the drivers in avoiding such maneuvers in real-time during the navigation. Thorough evaluations over multiple real-life and simulated datasets indicate that ProCon can reduce congestion for more than 60% of the scenarios on average while significantly reducing the travel time of the vehicles.

The ubiquitousness of smart and wearable devices with integrated acoustic sensors in modern human lives presents tremendous opportunities for recognizing human activities in our living spaces through ML-driven applications. However, their adoption is often hindered by the requirement of large amounts of labeled data during the model training phase. Integration of contextual metadata has the potential to alleviate this since the nature of these meta-data is often less dynamic (e.g. cleaning dishes, and cooking both can happen in the kitchen context) and can often be annotated in a less tedious manner (a sensor always placed in the kitchen). However, most models do not have good provisions for the integration of such meta-data information. Often, the additional metadata is leveraged in the form of multi-task learning with sub-optimal outcomes. On the other hand, reliably recognizing distinct in-home activities with similar acoustic patterns (e.g. chopping, hammering, knife sharpening) poses another set of challenges. To mitigate these challenges, we first show in our preliminary study that the room acoustics properties such as reverberation, room materials, and background noise leave a discernible fingerprint in the audio samples to recognize the room context and proposed AcouDL as a unified framework to exploit room context information to improve activity recognition performance. Our proposed self-supervision-based approach first learns the context features of the activities by leveraging a large amount of unlabeled data using a contrastive learning mechanism and then incorporates this feature induced with a novel attention mechanism into the activity classification pipeline to improve the activity recognition performance. Extensive evaluation of AcouDL on three datasets containing a wide range of activities shows that such an efficient feature fusion-mechanism enables the incorporation of metadata that helps to better recognition of the activities under challenging classification scenarios with 0.7-3.5% macro F1 score improvement over the baselines.

Road safety remains a critical global concern, with millions of crashes reported annually. Understanding the safety of individual road junctions is vital, especially in areas prone to road rage and reckless driving. However, current navigation systems lack detailed safety information, increasing risk for drivers and pedestrians. Recognizing this need, this paper introduces øurmethod that automatically annotates the road segments with a driving safety level to aid cautious maneuvering and safe driving practices. By leveraging onboard sensors, øurmethod identifies causal chains behind poor driving maneuvers, enabling the modeling of safety levels for various road segments. We perform a thorough evaluation of øurmethod over publicly available and collected datasets from multiple countries and observe >80% accuracy (in terms of F1-score) in correctly annotating the safety concerns. In addition, a thorough user study indicates the generalizability and usability of the proposed approach for its practical deployment considerations.

Multi-cloud environments such as OnApp and Cloudflare have turned the cloud marketplace towards a new horizon where end-users can host applications transparently over different cloud service providers (CSPs) simultaneously by taking the best from each. Existing cloud federations are typically driven by a broker service which provides a trusted interface allowing the participant CSPs and end-users to coordinate. However, such a broker has the limitations of any centralized trusted authority like risk of manipulation, bias, censorship, single point of failure, etc. In this paper, we propose a decentralized trustless cloud federation architecture calledCollabCloudwhich eliminates any central mediator while addressing the challenges introduced by byzantine participants.CollabCloudutilizes blockchain, and introduces a novel interoperability protocol bridging a permissionless blockchain as an open interface for the end-users, and a permissioned blockchain as a coordination platform for the CSPs. We have implementedCollabCloudwith Ethereum, Hyperledger Fabric and Burrow platforms. Experiments with a proof-of-concept testbed emulating 3 CSPs show thatCollabCloudcan operate within an acceptable response latency for resource allocation, while scaling upto 64 parallel requests per second. Scalability analysis over Mininet emulation platform indicates that the platform can scale well with minimal impact on the response latency as the number of participating CSPs increases. % for resource scheduling and allocation. %trustless, transparency, immutability properties of %By utilizing trustless, transparency, immutability and verifiability features of a distributed ledger technology, % Such multi-cloud environments bring the notion of cloud federation where various CSPs can buy and sell cloud resources, and thus collaborate among themselves to provide better capacity with less capital expenditure. %The novelty ofCollabCloudis in designing the interfacing between the two different blockchain platforms, through which the end-users access resources over multi-clouds in a secured way. %Need to reduce to 200 words. %The broker works like a trusted entity that takes care of various management tasks of the federation. %as the decentralized federation marketplace needs to provide a unified interface to the end-users while maintaining an agreement on pricing, fair scheduling of resources and securing resource access to the end-users. %InCollabCloud, we achieve the above goals by developing a unique interface through interconnecting a public (permissionless) blockchain platform with a private (permissioned) blockchain platform. %Cloud federation helps multiple cloud service providers to come into collaboration and share their resources for their overall benefit. However, the current implementations of federated clouds depend on a trusted federation broker that takes care of the handling end-user requests, resource allocation as well as scheduling and pricing for the shared resources under the federation. This central broker provides a unified interface to the end-users, through which they can access the federation as a single entity. The unified interface presents the federation as a single larger cloud provider which can fulfill a broader set of user demands and at a better pricing. Although the cloud broker plays a crucial role in the federation, it has the limitations of any centralized trusted authority like risk of manipulation, biasness, censorship, single point of failure, etc.. In this work, we propose a trustless, decentralized and democratic architecture for cloud federations which is free from any cloud broker. This democratic system leverages a combination of permissionless and permissioned blockchain which keeps all the functionalities of a broker based federation intact. Our system provides a trustless unified interface for the federation as well as brokerless scheduling, transfer of resources, catalog maintainance etc.. We implement the system with a fair scheduling smart contract and evaluate it with respect to end-to-end request processing time and analyze its overheads. The outcome of the analysis gives a clear view that the proposed system keeps all functionalities of cloud federation intact, while maintaining the required quality of experience(QoE) to the end-users.

With the push towards HTTP/3, most modern browsers have started supporting it. HTTP/3 uses QUIC, which runs on top of UDP. However, a few Internet middle-boxes tend to block or rate-limit UDP traffic; therefore, the browsers ensure compatibility by enabling connection racing via simultaneously initiating a TCP connection with the QUIC one. Each time the QUIC protocol suffers, connection racing is activated, and whichever protocol wins the race is further used for the application. In this paper, we study how browsers implement this connection racing mechanism and analyze its impact on applications that require a long-lived Internet connection, such as video streaming. We perform a large-scale measurement study across different browsers (Chrome/Chromium and Firefox), which helps to analyze why and how the repeated connection racing between protocols affects adaptive streaming QoE over 6013 YouTube sessions covering 5474 hours of streaming. Interestingly, we observe that YouTube QoE over an HTTP/3 supported browser suffers many times, and repeated connection racing is one of the major reasons that hinder the performance. We modified the Chromium browser source code to disable the connection racing altogether and observed that it improves the QoE for YouTube streaming over this modified browser. We then design and implement a solution that dynamically decides when to enable connection racing. We observe that it improves the QoE compared to the original browser. The analysis presented in this paper highlights the requirement of revisiting how browsers handle and switch between protocols through connection racing to ensure compatibility with middleboxes.

Drive tourism has become increasingly popular in the past decade; however, driving through a new city is challenging because the road and traffic environments vary significantly across cities. A driver used to driving in one city may face severe difficulty in adapting to a different driving environment, leading to road fatalities. This article develops GRIDS , an explainable model for guidelines recommendation for inter-domain driving safety, which learns the driving rules behind the changing environment and recommends the necessary personalized guidelines to a driver while driving through a new city. We develop an explainable domain adaptation model to provide customized recommendations in terms of driving guidelines, broadly categorized into four major feature categories of a driving environment. A thorough evaluation over the CARLA driving simulator shows that the recommendations generated through GRIDS can help improve driving safety.

Facial expressions have been considered a metric reflecting a person’s engagement with a task. While the evolution of expression detection methods is consequential, the foundation remains mostly on image processing techniques that suffer from occlusion, ambient light, and privacy concerns. In this paper, we propose ExpresSense, a lightweight application for standalone smartphones that relies on near-ultrasound acoustic signals for detecting users’ facial expressions. ExpresSense has been tested on different users in lab-scaled and large-scale studies for both posed as well as natural expressions. By achieving a classification accuracy of over various basic expressions, we discuss the potential of a standalone smartphone to sense expressions through acoustic sensing.

The concept of a decentralized web has been realized with the idea of Web 3.0 through interconnecting over multiple blockchain-based networks. However, blockchain incurs significant time and space overhead. This problem can be solved using snapshots that store the blockchain’s states compactly. But, the existing snapshot mechanism used in Hyperledger Fabric is limited to siloed operations on a single blockchain only. In this paper, we contribute towards overcoming this drawback by developing a novel mechanism for peer selection, snapshot archival, and cross-blockchain sharing of the snapshot. We extend the snapshot collection mechanism in Hyperledger Fabric to implement the above idea and test it over two blockchain networks emulating a decentralized web architecture.

Provenance tracking has been widely used in the recent literature to debug system vulnerabilities and find the root causes behind faults, errors, or crashes over a running system. However, the existing approaches primarily developed graph-based models for provenance tracking over monolithic applications running directly over the operating system kernel. In contrast, the modern DevOps-based service-oriented architecture relies on distributed platforms, like serverless computing that uses container-based sandboxing over the kernel. Provenance tracking over such a distributed micro-service architecture is challenging, as the application and system logs are generated asynchronously and follow heterogeneous nomenclature and logging formats. This paper develops a novel approach to combining system and micro-services logs together to generate a Universal Provenance Graph (UPG) that can be used for provenance tracking over serverless architecture. We develop a Loadable Kernel Module (LKM) for runtime unit identification over the logs by intercepting the system calls with the help from the control flow graphs over the static application binaries. Finally, we design a regular expression-based log optimization method for reverse query parsing over the generated UPG. A thorough evaluation of the proposed UPG model with different benchmarked serverless applications shows the system’s effectiveness.

HTTP/3 is a new application layer protocol supported by most browsers. It uses QUIC as an underlying transport protocol. QUIC provides multiple benefits, like faster connection establishment, reduced latency, and improved connection migration. Hence, most popular browsers like Chrome/Chromium, Microsoft Edge, Apple Safari, and Mozilla Firefox have started supporting it. In this paper, we present an HTTP/3-supported browser dataset collection tool named H3B. It collects the application and network-level logs during YouTube streaming. We consider YouTube, as it the most popular video streaming application supporting QUIC. Using this tool, we collected a dataset of over 5936 YouTube sessions covering 5464 hours of streaming over 5 different geographical locations and 5 different bandwidth patterns. We believe our tool and as well as the dataset could be used in multiple applications such as a better configuration of application/transport protocols based on the network conditions, intelligent integration of network and application, predicting YouTube's QoE etc. We analyze the dataset and observe that during an HTTP/3 streaming not all requests are served by HTTP/3. Instead whenever the network condition is not favorable the browser chooses to fallback, and the application requests are transmitted using HTTP/2 over the old-standing transport protocol TCP. We observe that such switching of protocols impacts the performance of video streaming applications.

Driving is a complex task carried out under the influence of diverse spatial objects and their temporal inter-actions. Therefore, a sudden fluctuation in driving behavior can be due to either a lack of driving skill or the effect of various on-road spatial factors such as pedestrian movements, peer vehicles' actions, etc. Therefore, understanding the context behind a degraded driving behavior just-in-time is necessary to ensure on-road safety. In this paper, we develop a system called DriCon that exploits the information acquired from a dashboard-mounted edge-device to understand the context in terms of micro-events from a diverse set of on-road spatial factors and in-vehicle driving maneuvers taken. DriCon uses the live in-house testbed and the largest publicly available driving dataset to generate human interpretable explanations against the unexpected driving events. Also, it provides a better insight with an improved similarity of 80% over 50 hours of driving data than the existing driving behavior characterization techniques.

Detecting dangerous driving has been of critical interest for the past few years. However, a practical yet minimally intrusive solution remains challenging as existing technologies heavily rely on visual features or physical proximity. With this motivation, we explore the feasibility of purely using mm Wave radars to detect dangerous driving behaviors. We first study characteristics of dangerous driving and find some unique patterns of range-doppler caused by 9 typical dangerous driving actions. We then develop a novel Fused-CNN model to detect dangerous driving instances from regular driving and classify 9 different dangerous driving actions. Through extensive experiments with 5 volunteer drivers in real driving environments, we observe that our system can distinguish dangerous driving actions with an average accuracy of 97(±2)%. We also compare our approach with existing state-of-the-art baselines to establish their significance,

The exponential growth of communication devices such as Internet of Things (IoT) devices, Augmented Reality/Virtual Reality (AR/VR) devices, sensors/actuators, mobile devices, and many others have led to a substantial increase in the quantity of traffic generated. This heavy traffic may cause significant delays for delay-sensitive applications and burden the fronthaul in Cloud-RAN architecture. Supporting all types of communications with the C-RAN architecture will be expensive and inefficient for telecom network operators (TNOs) and devices. Consequently, a fog computing-based RAN has evolved to reduce the heavy burden on fronthaul and ensure timely delivery of requested content for delay-sensitive applications. Fog computing resolves this problem by bringing computational resources and networking closer to users or devices, which is particularly useful for delay-sensitive applications. The cloud has extensive computing and resource capabilities, but its latency is more significant than fog computing-based RAN. In this paper, we examine a market in which TNOs lease third-party deployed fog access points (F-APs) in order to optimize the utilization of fog computing-based RAN architecture and F-APs resources. By employing a fog computing paradigm and efficiently using available fog node resources, the fronthaul infrastructure can relieve some of its burdens. Reducing service latency for end users is one of the most promising advantages of the fog paradigm. A user agrees to utilize fog resources in this endeavor and vice versa. Users and fog nodes do not provide usable utility and cost functions, so we implement a market controller to regulate the market. To maximize the social welfare of the network for participating users and fog nodes, we devise a two-sided auction method to assign computational resources and appropriate compensation.

Applications hosted in commercial clouds are typically multi-tier and comprise multiple tightly coupled virtual machines (VMs). Service providers (SPs) cater to the users using VM instances with different configurations and pricing depending on the location of the data center (DC) hosting the VMs. However, selecting VMs to host multi-tier applications is challenging due to the trade-off between cost and quality of service (QoS) depending on the placement of VMs. This paper proposes a multi-cloud broker model calledCoMCLOUDto select a sub-optimal VM coalition for multi-tier applications from an SP with minimum coalition pricing and maximum QoS. To strike a trade-off between the cost and QoS, we use an ant-colony-based optimization technique. The overall service selection game is modeled as a first-price sealed-bid auction aimed at maximizing the overall revenue of SPs. Further, as the hosted VMs often face demand spikes, we present a parallel migration strategy to migrate VMs with minimum disruption time. Detailed experiments show that our approach can improve the federation profit up to 23% at the expense of increased latency of approximately 15%, compared to the baselines.

Intelligent city transportation systems are one of the core infrastructures of a smart city. The true ingenuity of such an infrastructure lies in providing the commuters with real-time information about citywide transport like public buses, allowing them to pre-plan their travel. However, providing prior information for transportation systems like public buses in real-time is inherently challenging because of the diverse nature of different stay-locations where a public bus stops. Although straightforward factors like stay duration extracted from unimodal sources like GPS at these locations look erratic, a thorough analysis of public bus GPS trails for 1,335.365 km at the city of Durgapur, a semi-urban city in India, reveals that several other fine-grained contextual features can characterize these locations accurately. Accordingly, we develop BuStop , a system for extracting and characterizing the stay-locations from multi-modal sensing using commuters’ smartphones. Using this multi-modal information BuStop extracts a set of granular contextual features that allows the system to differentiate among the different stay-location types. A thorough analysis of BuStop using the collected in-house dataset indicates that the system works with high accuracy in identifying different stay-locations such as regular bus stops, random ad hoc stops, stops due to traffic congestion, stops at traffic signals, and stops at sharp turns. Additionally, we develop a proof-of-concept setup on top of BuStop to analyze the potential of the framework in predicting expected arrival time, a critical piece of information required to pre-plan travel at any given bus stop. Subsequent analysis of the PoC framework, through simulation over the test dataset, shows that characterizing the stay-locations indeed helps make more accurate arrival time predictions with deviations less than 60 seconds from the ground-truth arrival time.

Adaptive Bitrate (ABR) Streaming over cellular networks has been well studied in the literature; however, existing ABR algorithms primarily focus on improving the end-user Quality of Experience (QoE) while ignoring the resource consumption aspect of the underlying device. Consequently, proactive attempts to download video data to maintain the user’s QoE often impact the battery life of the underlying device unless the download attempts are synchronized with the network’s channel condition. In this work, we develop EnDASH-5G – a wrapper over the popular DASH-based ABR streaming algorithm, which establishes this synchronization by utilizing a network-aware video data download mechanism. EnDASH-5G utilizes a novel throughput prediction mechanism for 5G mmWave networks by upgrading the existing throughput prediction models with a transfer learning-based approach, leveraging publicly available 5G datasets. It then exploits deep reinforcement learning to dynamically decide the playback buffer length and the video bitrate using the predicted throughput. This ensures that the data download attempts get synchronized with the underlying network condition, thus saving the device’s battery power. From a thorough evaluation of EnDASH-5G, we observe that it achieves a near 30.5% decrease in the maximum energy consumption than the state-of-the-art Pensieve ABR algorithm while performing almost at par in term of QoE.

Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this article propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.

Virtual machine (VM) migration enables cloud service providers (CSPs) to balance workload, perform zero-downtime maintenance, and reduce applications’ power consumption and response time. Migrating a VM consumes energy at the source, destination, and backbone networks, i.e., intermediate routers and switches, especially in a Geo-distributed setting. In this context, we propose a VM migration model called Low Energy Application Workload Migration (LEAWM) aimed at reducing the per-bit migration cost in migrating VMs over Geo-distributed clouds. With a Geo-distributed cloud connected through multiple Internet Service Providers (ISPs), we develop an approach to find out the migration path across ISPs leading to the most feasible destination. For this, we use the variation in the electricity price at the ISPs to decide the migration paths. However, reduced power consumption at the expense of higher migration time is intolerable for real-time applications. As finding an optimal relocation is$\mathcal {NP}$-Hard, we propose anAnt Colony Optimization(ACO) based bi-objective optimization technique to strike a balance between migration delay and migration power. A thorough simulation analysis of the proposed approach shows that the proposed model can reduce the migration time by 25%–30% and electricity cost by approximately 25% compared to the baseline.

Blockchain has widely been adopted to design accountable federated learning frameworks; however, the existing frameworks do not scale for distributed model training over multiple independent blockchain networks. For storing the pre-trained models over blockchain, current approaches primarily embed a model using its structural properties that are neither scalable for cross-chain exchange nor suitable for cross-chain verification. This paper proposes an architectural framework for cross-chain verifiable model training using federated learning, called Proof of Federated Training (PoFT), the first of its kind that enables a federated training procedure span across the clients over multiple blockchain networks. Instead of structural embedding, PoFT uses model parameters to embed the model over a blockchain and then applies a verifiable model exchange between two blockchain networks for cross-network model training. We implement and test PoFT over a large-scale setup using Amazon EC2 instances and observe that cross-chain training can significantly boosts up the model efficacy. In contrast, PoFT incurs marginal overhead for inter-chain model exchanges.

Interoperation between permissioned consortium blockchain networks relies on their abilities to discover and validate the identities of each others’ participant organizations. These organizations may possess self-sovereign decentralized identities and verifiable credentials issued by well-known certification authorities. Two mutually untrusting networks of organizations can establish a basis for interoperation if they have one or more certification authorities in common. Yet, for privacy reasons, neither of them may want to expose a priori their entire lists of authorities, necessitating a negotiation process through which common authorities can be identified. In this paper, we analyze this negotiation problem, and propose and analyze two solution approaches, one involving active participation of the trust anchors and the other without involving them.

In this paper, we present the idea of using acoustic sensing over smartphones to understand the internal structure of hollow objects. In the core, we use an elegant, yet lightweight, signal processing pipeline that intelligently uses acoustic chirps to understand the internal structure of the hollow objects. Preliminary experiments on regularly used hollow objects show the potential of the idea.

Multiuser activity recognition has been the core of different context-aware services. However, the development of such services is often plagued by the dearth of multiuser datasets. This paper presents a strategy for generating synthetic multiuser datasets by augmenting existing real-life datasets. The described strategy exploits pre-cise time synchronization and well-known audio augmentation approaches to generate a multimodal activity recognition dataset with locomotive and acoustic signatures.

Monitoring driving behavior is essential to ensure on-road safety. Although driving is a collective, cooperative task among the drivers of the neighboring vehicles, existing platforms for driving behavior analysis solely rely on different on-road maneuvers taken by a driver. By analyzing a large volume of publicly available data over two countries and in-house collected data, this paper argues that analyzing driving behavior needs treatment over different factors which compel a driver to take maneuvers that are otherwise recommended to be avoided. Consequently, we develop DriBe. This smartphone-based pervasive sensing system utilizes video, GPS, and inertial sensor data to investigate the causes and consequences of driving maneuvers to score a driver based on a thorough understanding of their on-road driving behavior. Considering that the causality factors are very much specific to a particular driving environment (like a country), DriBe also incorporates a domain-adaptive architecture by utilizing a transfer learning framework. Thorough evaluation of DriBe with datasets from three countries shows that a score based on such causal factors provides a more accurate representation of driving behavior compared to baselines.

Severe road accidents are reported regularly across the globe due to drivers getting distracted while using their smartphones. To prevent such fatalities, one possible approach is to make the smartphone intelligent enough to detect whether it is being used by the driver, thus providing restricted access to the applications while driving. However, this problem is challenging as the driver can behave like an adversary to fool the system; therefore, additional devices or forward communication cannot be used. This paper proposes a novel approach of smartphone localization within a car by exploiting the ambient mechanical noise within the vehicle. We utilize the periodic nature of such mechanical noises to develop a simple yet satisfactorily accurate approach, called Blah, that can utilize the acoustic properties from the ambient mechanical noise within the car to detect whether the driver or the passenger is using the smartphone while the car is on the road.

An individual’s cognitive and functional abilities are commonly assessed through physical and mental status examination, observational performance measures, surveys and proxy reports of symptoms. These strategies are not ideal for early impairment detection as the individual needs to be present physically at the clinic to avail the assessments, especially for older adults who require assistance from a caregiver, and experience mobility, cognitive and functional disabilities from neurodegenerative disorders. Moreover, these strategies rely on self-reporting and proxy reports for evaluation which often leads to under-reporting of symptoms and decrease the validity of these measures. We argue that an early assessment of functional, and cognitive health impairment can be obtained from the individual’s daily activities captured through accelerometry. In this work, we postulate to learn high-level motion related representations from accelerometer data to better correlate with underlying functional and cognitive health parameters of older adults using a contrastive and multi-task learning framework. In particular, we posit a novel indicator, Impairment Indicator using the proposed multi-task learning framework that can indicate functional or cognitive decline as neurodegenerative disease progresses. An extensive 24-hour data collection from 25 older adults with the clinician in-the-loop was carried out in a retirement community center with IRB approval. We collected the activity patterns using wearables in their homes in addition to survey-based assessments and observational performance measures recorded by a clinical evaluator to infer their current cognitive and functional impairment status. Our evaluation on the acquired dataset reveals that the representations learned using contrastive learning aids in improving the detection of activities, activity performance score, and stage of dementia to 92%, 97%, and 98%, respectively.

In recent years, non-invasive human activity recognition (HAR) has gathered huge momentum using locomotive sensors. However, for effective HAR, there is a need for a significant volume of annotated data. Typically, the conventional practices for gathering HAR annotations have relied on human annotators. Nevertheless, the growing volume of data often leads to the collection of shallow annotations, which in most cases ignore the fine-grained micro-activities that constitute any complex activities of daily living (ADL). Understanding this, we, in this paper, try to develop the framework AmicroN that can automatically generate micro-activity annotations using locomotive signatures. To achieve this, in the backend, AmicroN applies change-point detection for the precise detection of activity boundaries followed by zero-shot learning with verb attributes to identify the unseen micro-activities without any external supervision. Rigorous evaluation on a publicly available Kitchen dataset shows that AmicroN can identify the micro-activities with a median F1-score of$\geq \mathbf{0.75}$for all the subjects, which can help develop novel pervasive applications.

This demo presents AmicroN which automatically generates fine-grained annotations using locomotive signatures. In the backend, AmicroN exploits short-duration macro labels already present in a pre-annotated dataset. It uses zero-shot learning to identify the finer micro-activities present within a coarse-grain macro-activity label.

Monitoring students’ engagement and understanding their learning pace in a virtual classroom becomes challenging in the absence of direct eye contact between the students and the instructor. Continuous monitoring of eye gaze and gaze gestures may produce inaccurate outcomes when the students are allowed to do productive multitasking, such as taking notes or browsing relevant content. This paper proposes Stungage – a software wrapper over existing online meeting platforms to monitor students’ engagement in real-time by utilizing the facial video feeds from the students and the instructor coupled with a local on-device analysis of the presentation content. The crux of Stungage is to identify a few opportunistic moments when the students should visually focus on the presentation content if they can follow the lecture. We investigate these instances and analyze the students’ visual, contextual, and cognitive presence to assess their engagement during the virtual classroom while not directly sharing the video captures of the participants and their screens over the web. Our system achieves an overall F2-score of 0.88 for detecting student engagement. Besides, we obtain 92 responses from the usability study with an average SU score of 74.18.

Large gatherings may cause the existing radio frequency (RF) network to reach its user capacity limit in the deployment area. So, to provide reliable communication to the users, we can deploy visible light communication (VLC) enabled unmanned aerial vehicles (UAVs) as an auxiliary network to the existing RF infrastructure. Our paper proposes a strategy for the efficient deployment of these VLC-enabled UAVs. It ensures the guaranteed quality of service without inter-UAV interference and does not violate the UAV’s user capacity limit. We compare the performance of the proposed algorithm for VLC-enabled UAV network with random, genetic, and K-means deployment algorithms in terms of outage and number of VLC-enabled UAVs for a fixed number of user equipments. Further, we performed an exhaustive analysis concerning the variation of irradiance and illumination with the different UAV parameters like altitude and coverage radius.

The profuse popularity of video conferencing has led to a simultaneous rise in the opportunity for the participants to multitask. Productive multitasking, such as taking notes, browsing for relevant information, etc., can help promote the cognitive attentiveness of participants. However, existing approaches of tagging inattentive participants solely based on their visual concentration on the meeting app fail to work in such instances. This paper proposes EmotiConf -- a novel real-time framework to monitor participants' attentiveness and a non-real-time framework for visual multitask detection without explicitly relying on their visual concentration. EmotiConf utilizes an unconventional observation where the emotional states of attentive participants, captured through their facial expressions, correlate and also correspond to the vocal expression of the speaker and the intent of the speech. Accordingly, EmotiConf develops a software wrapper to tag the inattentive participants while also characterizing visual multitasking instances performed by them. A thorough evaluation of EmotiConf confirms its usability with a high score of >80.

For the rapid increase in resource requirements in large scale Data Centers (DCs), enterprises have brought hyperconverged architecture where the storage pool is built up by the individual storage components associated with different servers, and it is shared among all the Virtual Machines (VMs) or containers through a common network infrastructure. Due to the sharing of network bandwidth among the application generated network traffic and the storage traffic from shared storage infrastructure, quality of service (QoS) performances of networking and storage intensive applications are affected, which further impacts VM or container migrations with dynamic workload scenarios. In this article, we propose NetStor to ensure QoS for various collocated network and storage intensive workloads over a hyperconverged architecture and ensure QoS during VM or container migration. NetStor uses a workload estimation strategy for VMs and containers, and applies the strategic decisions for resource allocation and migration based on environmental learning and workload characterization. NetStor supports a dynamic QoS provisioning that is workload-agnostic catering to both VMs and containers, and is unique to the best of our knowledge. We have implemented NetStor over a hyperconverged DC architecture on a testbed and found that NetStor can enhance network performance significantly compared to other related mechanisms discussed in the literature.

Commuter comfort in cab rides affects driver rating as well as the reputation of ride-hailing firms like Uber/Lyft. Existing research has revealed that commuter comfort not only varies at a personalized level but also is perceived differently on different trips for the same commuter. Furthermore, there are several factors, including driving behavior and driving environment, affecting the perception of comfort. Automatically extracting the perceived comfort level of a commuter due to the impact of the driving behavior is crucial for a timely feedback to the drivers, which can help them to meet the commuter’s satisfaction. In light of this, we surveyed around 200 commuters who usually take such cab rides and obtained a set of features that impact comfort during cab rides. Following this, we develop a system Ridergo which collects smartphone sensor data from a commuter, extracts the spatial time series feature from the data, and then computes the level of commuter comfort on a five-point scale with respect to the driving. Ridergo uses a Hierarchical Temporal Memory model-based approach to observe anomalies in the feature distribution and then trains a multi-task learning-based neural network model to obtain the comfort level of the commuter at a personalized level. The model also intelligently queries the commuter to add new data points to the available dataset and, in turn, improve itself over periodic training. Evaluation of Ridergo on 30 participants shows that the system could provide efficient comfort score with high accuracy when the driving impacts the perceived comfort.

With the rapid adoption of new technologies and applications, e.g., the Internet of Things, 5G/6G communication networks, big data analytics, and artificial intelligence, a deluge of devices are being connected to the network, thus generating a large amount of data. The collection, processing, and analysis of this vast amount of data are essential to help people and enterprises gain valuable information, make sensible decisions, and subsequently improve the quality of people’s lives. However, the underlying communication networks are thus facing a new number of unprecedented challenges. Managing these large numbers of devices in a scalable and secure manner is bringing significant challenges to the infrastructure construction, maintenance, and management of the communication networks. Recurring data privacy breaches and the lack of control make Internet users and enterprises less willing to provide valuable data for processing and analysis.

With the increasing adoption of private blockchain platforms, consortia operating in various sectors such as trade, finance, logistics, etc., are becoming common. Despite having the benefits of a completely decentralized architecture which supports transparency and distributed control, existing private blockchains limit the data, assets, and processes within its closed boundary, which restricts secure and verifiable service provisioning to the end-consumers. Thus, platforms such as e-commerce with multiple sellers or cloud federation with a collection of cloud service providers cannot be decentralized with the existing blockchain platforms. This paper proposes a decentralized gateway architecture interfacing private blockchain with end-users by leveraging the unique combination of public and private blockchain platforms through interoperation. Through the use case of decentralized cloud federations, we have demonstrated the viability of the solution. Our testbed implementation with Ethereum and Hyperledger Fabric, with three service providers, shows that such consortium can operate within an acceptable response latency while scaling up to 64 parallel requests per second for cloud infrastructure provisioning. Further analysis over the Mininet emulation platform indicates that the platform can scale well with minimal impact over the latency as the number of participating service providers increases.

Smartphones are ubiquitous nowadays, be it for setting a reminder, quick messaging, or an email reply, which requires typing through a soft-keyboard. However, people with medical issues like dactylitis, sarcopenia, joint pains might feel difficulty in typing, using the conventional approach. Existing gaze or voice-based approaches do not work well without commercial trackers or in noisy environments. In this paper, we develop a novel technique called Nosype, a contact-free text entry system for such users. Nosype’s core functionality lies in nose-tip tracking and projection and allows the users to draw alphanumeric characters in the air for constructing a text. With 11 users with different clinical conditions, on a lab-scale, we observe that Nosype can help in typing with an average typing error rate of 6.9% and a typing-speed of 6.31 words/minute. A large-scale usability study with 60 participants, including 10 participants having clinical disabilities, shows an average usability score of 77.708.

With increasing advancements in technologies for capturing 360° videos, advances in streaming such videos have become a popular research topic. However, streaming 360° videos require high bandwidth, thus escalating the need for developing optimized streaming algorithms. Researchers have proposed various methods to tackle the problem, considering the network bandwidth or attempt to predict future viewports in advance. However, most of the existing works either (1) do not consider video contents to predict user viewport, or (2) do not adapt to user preferences dynamically, or (3) require a lot of training data for new videos, thus making them potentially unfit for video streaming purposes. We develop PARIMA, a fast and efficient online viewport prediction model that uses past viewports of users along with the trajectories of prime objects as a representative of video content to predict future viewports. We claim that the head movement of a user majorly depends upon the trajectories of the prime objects in the video. We employ a pyramid-based bitrate allocation scheme and perform a comprehensive evaluation of the performance of PARIMA. In our evaluation, we show that PARIMA outperforms state-of-the-art approaches, improving the Quality of Experience by over 30% while maintaining a short response time.

Public city bus services across various developing cities inhabit multiple stay-locations on the routes due to ad-hoc bus stops to provide on-demand passenger boarding and alighting services. Characterizing these stay-locations is essential to correctly develop models for bus transit patterns used in various digital navigation services. In this poster, we create a deep learning-driven methodology to characterize ad-hoc stay-locations over bus routes based on crowd-sensing contextual information. Experiments over 720km of bus travel data in a semi-urban city in India indicate promising results from the model in terms of good detection accuracy.

In the presence of latency sensitive geo-distributed applications, users require fast service for their queries. Cloud computing provides physical servers from its data center in order to process user requests. The cloud data center consumes a huge amount of energy due to lack of management of the data center servers as the container-based service consolidation is a nontrivial task. Since the containers require less resource footprint, consolidating it in servers might make resource availability sparse. In order to reduce the energy consumption of the cloud data center, we have proposed a green container-based consolidation of the services so that the maximum number of servers can be put into idle mode without affecting the application quality of experience. The service consolidation problem has been formulated as an optimization problem considering minimization of total energy consumption of the data center as the objective, and an algorithm named Energy Aware Service consolidation using baYesian optimization (EASY) has been proposed to solve the optimization. We have evaluated the EASY algorithm in simulation using python. The experimental results have shown that EASY improves the total energy consumption of the data centers. This improvement comes at the cost of a small increase of service response time as there exists a trade-off between energy consumption and service response time.

Annotated IMU sensor data from smart devices and wearables are essential for developing supervised models for fine-grained human activity recognition, albeit generating sufficient annotated data for diverse human activities under different environments is challenging. Existing approaches primarily use human-in-the-loop based techniques, including active learning; however, they are tedious, costly, and time-consuming. Leveraging the availability of acoustic data from embedded microphones over the data collection devices, in this paper, we propose LASO, a multimodal approach for automated data annotation from acoustic and locomotive information. LASO works over the edge device itself, ensuring that only the annotated IMU data is collected, discarding the acoustic data from the device itself, hence preserving the audio-privacy of the user. In the absence of any pre-existing labeling information, such an auto-annotation is challenging as the IMU data needs to be sessionized for different time-scaled activities in a completely unsupervised manner. We use a change-point detection technique while synchronizing the locomotive information from the IMU data with the acoustic data, and then use pre-trained audio-based activity recognition models for labeling the IMU data while handling the acoustic noises. LASO efficiently annotates IMU data, without any explicit human intervention, with a mean accuracy of $0.93$ ($\pm 0.04$) and $0.78$ ($\pm 0.05$) for two different real-life datasets from workshop and kitchen environments, respectively.

Dynamic bandwidth operation in IEEE 802.11ac helps wireless access points to tune channel widths based on carrier sensing and bandwidth requirements of associated wireless stations. However, wide channels result in a reduction in the carrier sensing range, which leads to the problem of channel sensing asymmetry. As a consequence, access points face hidden channel interference that may lead to as high as 60% reduction in the throughput under certain scenarios of dense deployments of access points. Existing approaches handle this problem by detecting the hidden channels once they occur and affect the channel access performance. In a different direction, in this paper, we develop a method for avoiding hidden channels by meticulously predicting the channel width that can reduce interference as well as can improve the average communication capacity. The core of our approach is a deep probabilistic machinery based on point process modeling over the evolution of channel width selection process. The proposed approach, SmartBond, has been implemented and deployed over a testbed with 8 commercial wireless access points. The experiments show that the proposed model can significantly improve the channel access performance although it is lightweight and does not incur much overhead during the decision making process.

Container resource management is non-trivial over hyperconverged platforms where the storage is shared among host servers. Therefore, the same backbone network is used by storage and regular network traffic. In this paper, we first characterize this problem by analyzing the nature of the traffic from storage workloads and its impact on the network workloads in a container-based virtualization environment. Accordingly, we develop CONtrol, a resource management approach for assuring network workloads' performance in the presence of storage workloads. CONtrol uses a proportional-integral-derivative controller to dynamically decide the bandwidth redistribution among various workloads. Additionally, it uses a container migration strategy for balancing the workloads across different servers of a hyperconverged platform. We have implemented CONtrol over a hyperconverged platform with 5 physical servers. Thorough testing indicates that it can significantly improve the performance of various benchmark applications over a containerized hyper-converged platform.

Facebook’s “Mark Yourself Safe” or Google Person Finder are quite popular nowadays. Such applications generate crisis maps based on crowdsourced information during or after disasters. Crisis maps are inevitably an extremely effective digital dashboard application for rescue and reliefs. But what if there is even a partial Internet blackout after the disaster strikes? This is indeed a common scenario, but today’s crisis mapping solutions heavily depend on the Internet. In this paper, we discuss a thorough background study and design details of Soteria, an end-to-end solution for smartphone-based opportunistic crisis mapping in the fate of Internet blackouts. Soteria uses intelligent and energy-efficient mechanisms for opportunistic ad-hoc information collection and filtering along with data summarization and dashboard application for crisis mapping over end-users’ smartphones. The smartphone application intelligently incorporates and tunes the existing network systems and services at the backend to make the system work even when the conventional network infrastructure fails. We evaluate the performance of Soteria from multiple field-trials for over five years, and the observed quantitative and qualitative performance is extremely promising for its mass-scale adoption at the disaster-prone areas.

Most of the latest context-based applications capture the mobility of a user using Inertial Measurement Unit (IMU) sensors like accelerometer and gyroscope which do not need explicit user-permission for application access. Although these sensors provide highly accurate mobility context information, existing studies have shown that they can lead to undesirable leakage of location information. To evade this breach of location privacy, many of the state-of-the-art studies suggest to impose stringent restrictions over the usage of IMU sensors. However, in this paper, we show that typing and smartphone engagement patterns can act as an alternative modality to sniff the mobility context of a user, even if the IMU sensors are not sampled at all. We develop an adversarial framework, named ConType, which exploits the signatures exposed by typing and smartphone engagement patterns to track the mobility of a user. Rigorous experiments with in-the-wild dataset show that ConType can track the mobility contexts with an average micro-F1of 0.87 (±0.09), without using IMU data. Through additional experiments, we also show that ConType can track mobility stealthily with very low power and resource footprints, thus further aggravating the risk.

Existing street light monitoring systems use vehicle-borne sensor platforms, LiDAR etc. which are obtrusive for in-the-wild deployments. In this paper, we propose BikeL; a crowd sensed system to monitor street lighting conditions in a novel approach using smartphone sensors during Bike navigation. We identify the underlying issues and challenges from pilot experiments to make the system phone-invariant, robust, and user-friendly. We used regression models and unsupervised clustering to resolve these issues. We have carried out extensive experiments under various road type illumination scenarios and phones type covering more than 400 km. Over 80 night trips collecting 10,000 functional light pole samples to tune the system parameters. Results show that the overall system successfully detects both functioning and non-functioning light poles with good accuracy (F1 score > 0.85) and can produce uniformly calibrated illumination levels. This viable, economical, and easy to deploy solution can work effectively for under-developed regions of low and middle-economy countries.

The rapid proliferation of Massive Open Online Courses (MOOC) has resulted in many-fold increase in sharing the global classrooms through customized online platforms, where a student can participate in the classes through her personal devices, such as personal computers, smartphones, tablets, etc. However, in the absence of direct interactions with the students during the delivery of the lectures, it becomes difficult to judge their involvements in the classroom. In academics, the degree of student's attention can indicate whether a course is efficacious in terms of clarity and information. An automated feedback can hence be generated to enhance the utility of the course. The precision of discernment in the context of human attention is a subject of surveillance. However, visual patterns indicating the magnitude of concentration can be deciphered by analyzing the visual emphasis and the way an individual visually gesticulates, while contemplating the object of interest. In this paper, we develop a methodology called Gestsatten which captures the learner's attentiveness from his visual gesture patterns. In this approach, the learner's visual gestures are tracked along with the region of focus. We consider two aspects in this approach -- first, we do not transfer learner's video outside her device, so we apply in-device computing to protect her privacy; second, considering the fact that a majority of the learners use handheld devices like smartphones to observe the MOOC videos, we develop a lightweight approach for in-device computation. A three level estimation of learner's attention is performed based on these information. We have implemented and tested Gestatten over 48 participants from different age groups, and we observe that the proposed technique can capture the attention level of a learner with high accuracy (average absolute error rate is 8.68%), which meets her ability to learn a topic as measured through a set of cognitive tests.

Although public transport vehicles such as buses have always been an economical means of commuting in the cities of many developing countries, it is always considered as a secondary mode of transport owing to poor infrastructure, chaotic and reckless driving habits, and absence of any proper information system in buses. Based on rigorous experiments carried out over a period of two years and multiple surveys, we have tried to learn the problems faced by bus commuters. As a solution, in this article, we develop a novel energy-efficient system which would help commuters navigate through their journey safely. Along with making them aware of any upcoming points of concerns (PoCs) such as sudden bumps, sharp turns, and bad roads, we also inform commuters about the expected time of arrival at the destination. The system makes use of several landmarks such as speed breakers, turns, and bus stops on a trail stored in a specialized data structure, the probabilistic timed automata. We conducted extensive experiments using 25 volunteers over 50 trails. The system showed an average localization error of only 50 m and mean estimated time of arrival (ETA) error of 2.5 mins and a fairly high alert prediction accuracy while consuming significantly less energy when compared to GPS.

Internet of Things (IoT) platforms use a large number of low-cost resource constrained devices and generates millions of short-flows. In-network processing is gaining popularity day by day to handle IoT applications and services. However, traditional software-defined networking (SDN) based management systems are not suitable to handle the plug and play nature of such systems. In this paper, we propose Aloe, an auto-scalable SDN orchestration framework. Aloe exploits in-network processing framework by using multiple lightweight controller instances in place of service grade SDN controller applications. The proposed framework ensures the availability and significant reduction in flow-setup delay by deploying instances in the vicinity the resource constraint IoT devices dynamically. Aloe supports fault-tolerance with recovery from network partitioning by employing self-stabilizing placement of migration capable controller instances. Aloe also provides resource reservation for micro-controllers so that they can ensure the quality of services (QoS). The performance of the proposed system is measured by using an in-house testbed along with a large scale deployment in Amazon Web services (AWS) cloud platform. The experimental results from these two testbeds show significant improvement in response time for standard IoT based services. This improvement of performance is due to the reduction in flow-setup time. We found that Aloe can improve flow-setup time by around 10%-30% in comparison to one of the states of the art orchestration framework.

IEEE 802.11ac high throughput extension for wireless local area network comes with a large number of link layer configuration parameters, such as 4 different channel bonding levels, 10 different modulation and coding schemes, frame aggregation setup etc. However, the optimal combination of link configuration parameters, which maximizes the link layer performance, depends on the perceived channel quality based on the signal strength, channel noise and external interference. Considering the highly dynamic, nonlinear and time-varying nature of wireless channel quality, a dynamic adaptation of link configuration parameters gives a stable and optimized link layer performance. Nevertheless, the existing literature fails to design a robust mechanism for handling all the parameters simultaneously. In this article, we develop a control theoretic approach governed by a deep probabilistic machinery to design a robust and scalable dynamic link parameter adaptation mechanism. We apply deep neural network based Gaussian process regression to predict the link layer throughput and model predictive control based approach to find out the link configuration parameter that optimizes the overall link layer performance. The proposed mechanism is implemented and tested over a testbed setup, and we observe that it can significantly boost up the link layer performance compared to various baseline mechanisms.

This paper proposes a virtual machine (VM) migration model to reduce the power consumption while migrating a set of VMs over geo-distributed clouds. We develop an approach to find out the migration path across different Internet Service Providers (ISPs) leading to the most feasible destination. For this, we make use of the variation in the electricity price at the ISPs for deciding the migration paths. However, reduced power consumption at the expense of higher migration time is intolerable for real-time applications. Hence, we propose an Ant Colony Optimization (ACO) based bi-objective optimization technique to strike a balance between the power consumption and the migration time to make the implementation realistic. Thorough simulation analysis of the proposed approach shows that it can achieve low power consumption cost with acceptable migration time.

In the presence of the Internet of Things (IoT) devices, the end-users require a response within a short amount of time which the cloud computing alone cannot provide. Fog computing plays an important role in the presence of IoT devices in order to meet such delay requirements. Though beneficial in these latency-sensitive scenarios, the fog has several implementation challenges. In order to solve the problem of micro-service placement in the fog devices, we propose a framework with the objective of achieving low response time. This problem has been formulated as an optimization problem to improve the response time by considering the time-varying resource availability of the fog devices as constraints. We propose an orchestration framework named Pick-Test-Choose (PTC) to solve the problem. PTC uses Bayesian Optimization based iterative reinforcement learning algorithm to find out a micro-service allocation based on the current workload of the fog devices. PTC employs containers for service isolation and migration of the micro-services. The proposed architecture is implemented over an in-house testbed as well as in iFogSim simulator. The experimental results show that the proposed framework performs better in terms of response time compared to various other baselines.

Management of networked Internet of Things (IoT) infrastructure with in-network processing capabilities is becoming increasingly difficult due to the volatility of the system with low-cost resource-constraint devices. Traditional software-defined networking (SDN) based management systems are not suitable to handle the plug and play nature of such systems. Therefore, in this paper, we propose Aloe, an elastically auto-scalable SDN orchestration framework. Instead of using service grade SDN controller applications, Aloe uses multiple lightweight controller instances to exploit the capabilities of in-network processing infrastructure. The proposed framework ensures the availability and significant reduction in flow-setup delay by deploying instances near the resource constraint IoT devices dynamically. Aloe supports fault-tolerance and can recover from network partitioning by employing self-stabilizing placement of migration capable controller instances. The performance of the proposed system is measured by using an in-house testbed along with a large scale deployment in Amazon web services (AWS) cloud platform. The experimental results from these two testbed show significant improvement in response time for standard IoT based services. This improvement of performance is due to the reduction in flow-setup time. We found that Aloe can improve flow-setup time by around 10%-30% in comparison to one of the state of the art orchestration framework.

Accurate modeling of network traffic has a wide variety of applications. In this paper, we propose Network Transmission Point Process (NTPP), a probabilistic deep machinery that models the traffic characteristics of hosts on a network and effectively forecasts the network traffic patterns, such as load spikes. Existing stochastic models relied on the network traffic being self-similar in nature, thus failing to account for traffic anomalies. These anomalies, such as short-term traffic bursts, are very prevalent in certain modern-day traffic conditions, e.g. datacenter traffic, thus refuting the assumption of self-similarity. Our model is robust to such anomalies since it effectively leverages the self-exciting nature of the bursty network traffic using a temporal point process model.On seven diverse datasets collected from the fields of cyberdefense exercises (CDX), website access logs, datacenter traffic, and P2P traffic, NTPP offers a substantial performance boost in predicting network traffic characteristics against several baselines, ranging from forecasting the network traffic volume to detecting traffic spikes. We also demonstrate an application of our model to a caching scenario, showing that it can be used to effectively lower the cache miss rate.

The growth in the market for cab companies like Uber has opened the door to high-income options for drivers. However, in order to boost their income, drivers many a time resort to accepting trips which increases their stress resulting in poor driving quality and accidents in serious cases. Every driver handles stress differently and the trip recommendation thus needs to be on a personalized level. In this paper, we explore historical trip data to compute the driving stress and its impact on various driving behavioral features, captured through vehicle-mounted GPS and inertial sensors. We utilize a Multi-task Learning based Neural Network model to learn both the common features and the personalized features from the driving data to predict the stress level of a driver. We further establish a causal relationship between the stress level of a driver and his driving behavior. Finally, we develop a trip recommendation system for cab drivers to avoid stress driving. The models have been tested over both a publicly available dataset with 6 drivers for 500 minutes of driving data and an in-house collected dataset from 8 drivers over 1700 trips for 5 months. We observe that the proposed model gives an average prediction accuracy of 94% with low false-positive rates. We also observed that the driving behavior is improved when a driver akes a recommended trip.

Most existing UE association techniques consider signal strength from eNBs as the primary metric for handover decisions. This may result in unbalanced distribution of UEs to eNBs in a dense LTE network with large number of users, even though a UE may have multiple good eNB options for association. In this paper we propose a load balancing framework that can be applied over any existing handover algorithm periodically to balance eNB loads. The framework uses a novel metric based on eNB-availability-option of UEs for choosing the set of UEs to handover to balance load and their target eNBs, while ensuring good signal quality. A specific algorithm based on the framework is proposed and evaluated by simulating on NS-3 over five existing handover algorithms.

Cloud Radio Access Network (C-RAN) has been proposed as a new paradigm shift in the Radio Access Network (RAN) technology as a part of the fifth generation Long-Term Evolution Advanced (LTE-A) networks to support better spectral and energy efficiency along with the high availability. In this paper, we discuss implementation details of a C-RAN Fronthaul with the help of USRP-based transceivers and LabView platform. To the best of our knowledge, this is the first implementation of a C-RAN architecture that functionally splits the radio resource head (RRH) and the baseband processing unit (BBU) at the physical layer (Split 8) and transfers the completely unprocessed raw signal elements from the RRH to the BBU pool at the cloud for signal processing. We explore TCP and UDP as alternate protocols for fronthaul data transfer to the cloud. In order to evaluate the performance of a C-RAN fronthaul and the interplay of different performance parameters for fronthaul data transfer, we observe various metrics like the receiver goodput and the latency and compare the performance between a C-RAN setup and a generic distributed RAN setup.We observe that TCP works better for Ethernet fronthauling compared to UDP, as it provides reliable data delivery. The analysis discussed in this paper gives insights about the implementation and performance of a C- RAN environment which is essential for designing efficient fronthauling and functional splits of a C-RAN architecture.

Network traffic classification is an important tool for network administrators in enabling monitoring and service provisioning. Traditional techniques employed in classifying traffic do not work well for mobile app traffic due to lack of unique signatures. Encryption renders this task even more difficult since packet content is no longer available to parse. More recent techniques based on statistical analysis of parameters such as packet-size and arrival time of packets have shown promise; such techniques have been shown to classify traffic from a small number of applications with a high degree of accuracy. However, we show that when employed to a large number of applications, the performance falls short of satisfactory. In this paper, we propose a novel set of bit-sequence based features which exploit differences in randomness of data generated by different applications. These differences originating due to dissimilarities in encryption implementations by different applications leave footprints on the data generated by them. We validate that these features can differentiate data encrypted with various ciphers (89% accuracy) and key-sizes (83% accuracy). Our evaluation shows that such features can not only differentiate traffic originating from different categories of mobile apps (90% accuracy), but can also classify 175 individual applications with 95% accuracy.

In an organization, individuals preferto form various formal and informal groups for mutual interactions. Therefore, ubiquitous identification of such groups and understanding their dynamics are important to monitor activities, behaviors, and well-being of the individuals. In this paper, we develop a lightweight, yet near-accurate, methodology, called GroupSense, to identify various interacting groups based on collective sensing through users' smartphones. Group detection from sensor signals is not straightforward because users in proximity may not always be under the same group. Therefore, we use acoustic context extracted from audio signals to infer the interaction pattern among the subjects in proximity. We have developed an unsupervised and lightweight mechanism for user group detection by taking cues from network science and measuring the cohesivity of the detected groups regarding modularity. Taking modularity into consideration, GroupSense can efficiently eliminate incorrect groups, as well as adapt the mechanism depending on the role played by the proximity and the acoustic context in a specific scenario. The proposed method has been implemented and tested under many real-life scenarios in an academic institute environment, and we observe that GroupSense can identify user groups with on an average 0:9(±0:14) F1-Score even in a noisy environment.

IEEE 802.11ax high-throughput wireless access networks support multi-user multiple-input multiple-output (MU-MIMO)-based communication, where a set of spatially apart wireless stations forms a user group and uses different spatial streams for simultaneous transmission and reception. In this architecture, dynamic user group selection is an important aspect for maintaining high-throughput fair channel access. In addition, the physical and media access control parameters, like channel bonding levels, modulation, and coding schemes need to be tuned based on the selected user group to utilize the maximum available capacity. In this paper, we design an online learning-based approach over a centralized logical control architecture, called intelligent MU-MIMO user selection with link adaptation (IMMULA), where a central controller collects the performance statistics under various configuration space and applies a reinforcement learning strategy to select the best-suited configurations dynamically at periodic intervals. The performance of IMMULA is analyzed over a testbed consisting of 6 IEEE 802.11ac access points and 20 wireless stations. The results show that IMMULA improves network performances significantly compared to other baseline mechanisms.

With the increase in road fatalities due to various factors like aggressive driving and road rage, quantifying and monitoring the stress level of a driver is an important task for the preparation of driving rosters for the cab companies. Stress monitoring using physiological sensors is a costly and obstructive task, while stress factors impact differently for different individuals based on their personality traits. In this paper, we develop a learning-based model to predict the stress level of a driver and its effect on his driving behavior, solely based on spatio-temporal driving data collected through GPS and inertial sensors. We further establish a correlation between the stress level of a driver and his driving behavior; thus, we develop a complete system to infer stress profiling and its impact on driving behavior based on spatio-temporal driving data. The model has been tested over a publicly available dataset with 6 drivers for 500 minutes of driving data. We observe that the proposed model gives an average prediction accuracy of 79% with low false-positive rates.

Enterprise data center architectures have gone through a major change during the last couple of years with widespread developments of software defined platforms and virtualization technologies, in the form of storage virtualization and network virtualization. As a consequence, the industries are gradually being shifted towards a shared storage software defined data center (SDDC) platform, where all the resources like computing, storage and network are virtualized within a single box and managed by a single controller. However, with such kind of shared storage architecture, network can be a performance bottleneck, as the network also needs to carry the storage workload. Because of this reason, virtual machine (VM) migration over a started storage SDDC platform can be an issue in the presence of storage workload. In this paper, we provide a thorough performance study of VM migration performance over shared storage SDDC platform under various different types of workloads. We first discuss a methodology to develop a shared storage SDDC platform using open source softwares and tools, and then perform thorough experimentation of VM migration performance in terms of application quality of service (QoS) under various different workloads. We observe that VM migration with either network or storage workload may get affected due to shared storage data synchronization over the network. From this performance analysis, we conclude that although shared storage SDDC provides a flexible, cost-effective, energy-efficient and easy-manageable solution for data centers, there are multiple performance bottlenecks that need to be addressed for getting the best out of it.

In day to day life, people meet strangers while commuting in public transports, roaming around in a shopping mall, waiting at airport boarding areas etc., and thus form passively encountering groups. Detection and analysis of such groups are essential for providing services like targeted advertisements, supply chain management, information broadcasting and so on. However, identifying such groups is challenging because of the underlying dynamics, where an encounter between two subjects is entirely instantaneous without having a specific pattern. This problem has two steps - (a) identification of subjects in proximity and (b) detecting groups from the proximity information. In this paper, we develop an unsupervised model to identify subjects in proximity based on WiFi signal information and assign a proximity score to each pair of subjects based on a novel metric defining the degree of proximity. With the help of these concepts from network science, we then utilize a community detection mechanism to infer the passively encountering groups from the proximity score. The proposed model has been implemented and deployed over an academic institute campus. A study over 25 subjects for six months reveals that the proposed model can detect passively encountering groups with more than 90\% accuracy, even with heterogeneous devices under various real-life scenarios.

A large fraction of video content providers have adopted adaptive bitrate streaming over HTTP. The client player typically runs an adaptive bitrate (ABR) algorithm to decide upon the most optimal quality for the next few seconds of video playback. State-of-the-art ABR algorithms attempt to achieve an optimal trade-off among the competing objectives of high bitrate, less rebuffering, and high smoothness, in the face of unpredictable bandwidth variability. However, optimal bandwidth utilization does not necessarily ensure high quality of experience (QoE). Different users have different content preferences even within the same video, due to differences in team loyalties (in sport), character preferences (in movies and soaps), and so on. In this work, we present HotDASH, a system which enables opportune prefetching of user-preferred temporal video segments (called hotspots). HotDASH implements a prefetch module in the open source DASH player dash.js, which is powered by an optimal prefetch and bitrate decision engine. The decision engine is designed as a cascaded reinforcement learning (RL) model, implemented using a state-of-the-art actor-critic RL algorithm over a neural network. We train the neural network using trace-driven simulations over a large variety of bandwidth conditions. HotDASH outperforms all baseline algorithms, with a 16.2% QoE improvement over the best-performing baseline, and achieves 14.31% better average bitrate due to its ability to prefetch opportunistically.

Recent context detection techniques in smartphones leverage on the embedded motion sensors, which in turn increases the potential of side-channel attacks. We in this paper propose an alternative modality for obtaining mobility context using smartphone keyboard interaction patterns using a personalized framework. Experimental results show that the framework can predict the mobility context at an average F1 score (both micro and macro) greater than 0.6 across all subjects.

This work presents a software-centric visible light communication (VLC) system in full duplex mode with CSMA/CA and RTS-CTS in mobile environment. We focus on channel access mechanism problems in the same environment. To solve these we modify Distributed Coordination function (DCF) by adding ambient light measurement slot. The result shows modified DCF can handle the problems.

Side-channel attacks, which exploit deficiencies in the implementations of theoretically secure systems, have been known to take a variety of forms on the mobile platforms. In this work, we present Magneto, a magnetic field based app classification mechanism. Magneto captures the Hall effect due to energy consumption by different components in a smartphone, and fingerprints apps based on data captured with a Hall sensor, and a phone magnetometer. We demonstrate that our mechanism can identify magnetic field changes due to varying levels of energy consumption. We further show that Magento can not only classify between apps in the same scenario, but also can tell apart scenarios when the phone is being charged (with an AC adapter, wireless charger, or powerbank) or not. We perform validation experiments with 5 different apps, and achieve ~85% accuracy with 3 Android apps, subject to 3 different charging scenarios.

Passenger comfort is a major factor influencing a commuter's decision to avail public transport. Existing studies suggest that factors like overcrowding, jerkiness, traffic congestion etc. correlate well to passenger's (dis)comfort. An online survey conducted with more than 300 participants from 12 different countries reveals that different personalized and context dependent factors influence passenger comfort during a travel by public transport. Leveraging on these findings, we identify correlations between comfort level and these dynamic parameters, and implement a smartphone based application, ComfRide, which recommends the most comfortable route based on user's preference honoring her travel time constraint. We use a 'Dynamic Input/Output Automata' based composition model to capture both the wide varieties of comfort choices from the commuters and the impact of environment on the comfort parameters. Evaluation of ComfRide, involving 50 participants over 28 routes in a state capital of India, reveals that recommended routes have on average 30% better comfort level than Google map recommended routes, when a commuter gives priority to specific comfort parameters of her choice.

Handover, the process of transferring a call or data session from one base station to another without disconnection, is an important problem in LTE networks. Several handover algorithms have been proposed for LTE networks in general. However, they mostly use the current signal strengths for making handover decisions, which can cause spurious handovers in a dense eNB deployment. In this paper, we investigate the use of look-ahead signal strength information for reducing spurious handovers. We first propose a novel graph-based framework that uses signal strength information along the mobile trajectory of the UE to make better handover decisions. Two algorithms are then presented based on this framework. The first algorithm assumes that exact signal measurements at the UE from all eNBs in its trajectory are available a priori for all time instances, and provides a baseline reference for finding the minimum number of handovers that can be achieved. The second algorithm uses the exact signal measurement for the current time instance only, and estimates the signal strengths for future time instances. The performances of the algorithms are compared with four existing LTE handover algorithms using simulation on real world data. It is shown that the proposed algorithms significantly reduce the number of handovers while still maintaining good signal quality for communication throughout the trajectory of the UE.

The primary objective behind the development of Multipath TCP (MPTCP) is to aggregate throughput by creating multiple sub-flows via different network interfaces. A difference in end-to-end path characteristics for the sub-flows may generate out of order segments, causing head of line (HOL) blocking at the receiver. An intelligent selection of a subset of the available sub-flows can reduce the number of out of order segments; thus sub-flow selection can enhance the performance of MPTCP. In this paper, we first propose a Markov model for the performance of MPTCP in terms of end-to-end sub-flow characteristics. Based on the theoretical model, we present an optimization framework for active sub-flow selection by exploiting the controller functionalities over a software defined network (SDN) architecture. Finally, experimental results are obtained to demonstrate performance improvements of MPTCP in terms of aggregated throughput.

City transit maps are one of the important resources for public navigation in today's digital world. However, the availability of transit maps for many developing countries is very limited, primarily due to the various socio-economic factors that drive the private operated and partially regulated transport services. Public transports at these cities are marred with many factors such as uncoordinated waiting time at bus stoppages, crowding in the bus, sporadic road conditions etc., which also need to be annotated so that commuters can take informed decision. Interestingly, many of these factors are spatio-temporal in nature. In this paper, we develop CityMap, a system to automatically extract transit routes along with their eccentricities from spatio-temporal crowdsensed data collected via commuters' smart-phones. We apply a learning based methodology coupled with a feature selection mechanism to filter out the necessary information from raw smart-phone sensor data with minimal user engagement and drain of battery power. A thorough evaluation of CityMap, conducted for more than two years over 11 different routes in 3 different cities in India, show that the system effectively annotates bus routes along with other route and road features with more than 90% of accuracy.

IEEE 802.11ac supports Dynamic Bandwidth Channel Access (DBCA), where a wireless station dynamically selects the channel bandwidth based on the availability of the secondary channels. Although DBCA reduces the possibility of starvation due to non-availability of secondary channels, however, to the best of our knowledge, no existing works look into the performance benefits of IEEE 802.11ac DBCA based on theoretical modeling. In this paper, we develop a two dimensional Markov chain approach to model the performance of DBCA under various channel bonding conditions. We validate the proposed model based on a real testbed implementation. From the thorough analysis of the numerical results obtained from the model, we show that although DBCA improves channel utilization for secondary channels, it requires proper channel allocations and bonding level distributions across the wireless channels for reducing unfairness in the network. We observe that under certain circumstances, the secondary channel users can affect the throughput of primary channel users, which may introduce a short-term unfairness and a significant performance drop in the network.

The current developments of software defined networking (SDN) paradigm provide a flexible architecture for network control and management, in the cost of deploying new hardwares by replacing the existing routing infrastructure. Further, the centralized controller architecture of SDN makes the network prone to single point failure and creates performance bottleneck. To avoid these issues and to support network manageability over the existing network infrastructure, we develop Flipper in this paper, that uses only software augmentation to convert existing off-the-shelf routers to network policy design and enforcement points (PDEP). We develop a distributed self-stabilized architecture for dynamic role change of network devices from routers to PDEPs, and make the architecture fault-tolerant. The performance of Flipper has been analyzed from both simulation over synthetic networks, and emulation over real network protocol stacks, and we observe that Flipper is scalable, flexible and fail-safe that can significantly boost up the manageability of existing network infrastructure.

Among the mobile applications contributing to the surging Internet traffic, video applications are some of the biggest contributors. Most of these video applications use HTTP/HTTPS tunneling making it difficult to apply port based or packet data based identification of flows. This makes it challenging for network operators to enforce bandwidth regulation policies for app based service differentiation due to lack of flow identification mechanisms for mobile apps. We explore a packet data agnostic feature of video flows, namely packet-size, to identify the flows. We show that it is possible to train a classifier that can distinguish packets from streaming and interactive video apps with high accuracy. We design and implement a system, called MoViDiff, with this classifier at the core, that allows bandwidth regulation between video traffic of two different categories, streaming and interactive. We show that we can achieve an average accuracy of 96% in classifying the traffic, with the maximum accuracy reaching as high as 98%.

Wi-Fi enabled hand-held devices have quickly occupied the consumer market as a result of the remarkable customer acceptance of IEEE 802.11 standard. In this regard, the demand of high throughput introduces high throughput standards such as IEEE 802.11ac. It supports Dynamic Bandwidth Channel Access (DBCA), where a wireless station selects channel bandwidth dynamically based on the availability of the secondary channels. But the widely-used contention based medium access mechanism provides an opportunistic access of secondary channels and affects the performance of DBCA. Consequently, unfairness in channel access is increased in DBCA, which further reduces average throughput of stations. In this paper, we develop a hybrid adaptive resource reservation mechanism, Hybrid Adaptive DBCA (HA-DBCA), for supporting fair channel access in DBCA. In HA-DBCA, a polling based online learning mechanism is designed to avoid starvation of primary channel users. Through IEEE 802.11ac testbed implementation, we show that HA-DBCA improves throughput fairness in DBCA significantly along with other performance parameters.

High fluctuation of signal strength is evident in wireless channel under mobile environment. IEEE 802.11n and IEEE 802.11ac based wireless technologies experience a challenge for selecting link configuration parameters, like number of spatial streams, channel bonding, advanced modulation and coding schemes, frame aggregation etc., dynamically under mobility. Selection of the best possible data rate by tuning link parameters is a challenging issue due to the channel asymmetry in mobile environment. In this paper, we propose an adaptive learning mechanism, HT-MobiRate, for high throughput dynamic link adaptation under mobile scenario. HT-MobiRate is based on Thompson sampling and inspired from multi-armed bandit approach. To the best of our knowledge, this invention is first in the direction of link adaptation for IEEE 802.11ac under mobile environment. We analyze the performance of HT-MobiRate with a practical high throughput wireless testbed built over 6 IEEE 802.11ac supported access points and 20 IEEE 802.11ac clients (both client boards as well as smart-phones). We recognize that it performs considerably better than other competing schemes proposed in the literature for link adaptation in static environment.

The nature of Internet traffic has changed dramatically within the last few years, where a large volume of traffic is originated from mobile applications (known as apps), web based multimedia streaming, computation offloading like cloud computing and Internet of Things (IoT) etc. These types applications generate multiple parallel short lived end-to-end connections. However, the three major requirements of todays' end-to-end traffic over the Internet, such as (a) support for mobility of devices, (b) capacity improvement through multipath end-to-end transmissions, and (c) support for short-lived parallel connections, are not substantiated through the widely-deployed transmission control protocol (TCP). Further, the recent developments of multi-path TCP (MPTCP) as well as User Datagram Protocol (UDP) based Google's Quick UDP Internet Connections (QUIC) also fail to support all the above three requirements. As a consequence, in this paper, we develop a new end-to-end transmission protocol, called Viscous, to support the above three requirements over the Internet. Viscous is developed as a wrapper between the application and the transport layer, that works on top of the UDP and supports end-to-end reliability as well as congestion control while transmitting short-lived flows over multiple end-to-end paths. We introduce a number of novel concepts at Viscous, such as parallel and sequential flow multiplexing, decoupling of flow and congestion control etc. to overcome the problems associated with the current transport protocols. Viscous has been implemented and tested over a variety of environments, and we observe that it can significantly boost up the performance of the end-to-end data transmission compared to TCP, MPTCP and QUIC.

This paper explores the feasibility of automatically discriminating users from the activity as well as temporal information of their daily routine. We observe that everyone pursues a daily semi-regular activity pattern. Based on this observation, we have developed a system UDAT and experimented on Microsoft Geolife as well as UDAT datasets. With Geolife transportation activity log and UDAT motion-static activity log, the system achieves 73.3% and 80.68% accuracy, respectively. Although the overall system accuracy is moderate, the system achieves the highest accuracy when the users belong to the different activity buckets. This signifies the utility of two-phase classification for user discrimination.

This poster provides an in-depth analysis of the primary path effect in Multi-path TCP using thorough experimentation over a realistic network setup. We observe the impact of various primary path parameters, like bandwidth, delay and loss, over the end-to-end performance. It is shown that under certain circumstances overall network performance can be improved by more than 50% with proper primary path selection. This study may drive the research community towards the design of new segment scheduling algorithms considering the effect of primary path selection over Multi-path TCP.

YouTube has emerged as the largest player among video streaming services, serving video content for users using DASH. Research studies on various aspects of YouTube, especially its streaming service, abound in the literature. However, these works study YouTube streaming from the periphery, and report results based on their understanding of general DASH recommendations. In this study, we explore in depth YouTube's implementation of the DASH client. We identify important parameters in YouTube's rate adaptation algorithm, and study their roles. In a departure from existing literature, we observe that YouTube opportunistically adapts segment length, in addition to quality level, in response to bandwidth fluctuations. We report that this scheme results in a much lower average data wastage ratio (0.82x10-6), than reported earlier. We also propose an analytical model, augmented with a machine learning based classifier (with average accuracy of 85.75%), to predict data consumption for a playback session in advance.

Public bus services in many cities in countries like India are controlled by private owners, hence, building up a database for all the bus routes is non-trivial. In this paper, we leverage smart-phone based sensing to crowdsource and populate the information repository for bus routes in a city. We have developed an intelligent data logging module for smart-phones and a server side processing mechanism to extract roads and bus routes information. From a 3 month long study involving more than 30 volunteers in 3 different cities in India, we found that the developed system, CrowdMap, can annotate bus routes with a mean error of 10m, while consuming 80% less energy compared to a continuous GPS based system.

Internet access via wireless hotspots is an ever increasing demand with the inception of smart cities, where most of the users connect the Internet with their WiFi enabled devices. A set of wireless devices forms a basic service set (BSS) connected to an access point (AP). However, large number of APs are deployed in the form of extended service set (ESS) to balance the traffic load and to provide seamless data connectivity. Recent studies show that in a public WiFi hotspot, a mobile device remains in the overlapping region of multiple APs. Due to geographically sparse distributions of mobile devices, an AP may need to keep its interfaces on to serve only a few devices which otherwise can be shifted to another active AP. In this paper, we develop CrowdAP, an energy balancing AP coordination mechanism; where the minimum number of APs are computed such that the underlying mobile devices can be served without any degradation in performance, while the rest of the APs can go to the sleep state to save power. We analyze the performance of CrowdAP through simulation as well as from testbed, and show that it is able to save significant energy in the network.

Public transport in suburban cities (covers 80% of the urban landscape) of developing regions suffer from the lack of information in Google Transit, unpredictable travel times, chaotic schedules, absence of information board inside the vehicle. Consequently, passengers suffer from lack of information about the exact location where the bus is at present as well as the estimated time to be taken to reach the desired destination. We find that off-the-shelf deployment of existing (non-GPS) localization schemes exhibit high error due to sparsity of stable and structured outdoor landmarks (anchor points). Through rigorous experiments conducted over a month however, we realize that there are a certain class of volatile landmarks which may be useful in developing efficient localization scheme. Consequently, in this paper, we design a novel generalized energy-efficient outdoor localization scheme - UrbanEye, which efficiently combines the volatile and non-volatile landmarks using a specialized data structure, the probabilistic timed automata. UrbanEye uses speed-breakers, turns and stops as landmarks, estimates the travel time with a mean accuracy of ±2.5 mins and produces a mean localization accuracy of 50 m. Results from several runs taken in two cities, Durgapur and Kharagpur, reveal that UrbanEye provides more than 50% better localization accuracy compared to the existing system Dejavu [1], and consumes significantly less energy.

High throughput wireless access networks based on IEEE 802.11ac show a significant challenge in dynamically selecting the link configuration parameters based on channel conditions due to large pool of design set, like number of spatial streams, channel bonding, guard intervals, frame aggregation and different modulation and coding schemes. In this paper, we develop a learning based approach for link adaptation motivated by the multi-armed bandit based distributed learning algorithm. The proposed link adaptation algorithm, BanditLink, explores different possible configuration options based on observing their impact over the network performance at various channel conditions. We analyze the performance of BanditLink from simulation results, and observe that it performs significantly better compared to other competing mechanisms proposed in the literature.

The IEEE 802.11s wireless mesh networking standard supports power save mode where a mesh station can switch from the awake state to the doze state when there is no data to transmit. In the standard, the doze state is peer specific and has two different modes of operations - light sleep mode and deep sleep mode. This paper analytically evaluates the performance of a mesh basic service set under the operation of different power save modes, with the help of a queuing Petri net modeling. The analytical model gives several insights of the power save mode operations, which are further validated using simulation results as well as results from a practical mesh networking testbed. Our analysis reveals that there exists interesting performance tradeoffs among light sleep mode and deep sleep mode, that can be explored to design an efficient power profile for mesh networks.

This paper proposes an opportunistic approach to mitigating the hidden and exposed node problem in a high-throughput mesh network, by exploiting the frame aggregation and block acknowledgment (BACK) capabilities of IEEE 802.11n/ac wireless networking standard. Hidden nodes significantly drop down the throughput of a wireless mesh network by increasing data loss due to collision, whereas exposed nodes cause under-utilization of the achievable network capacity. The problem becomes worse in IEEE 802.11n/ac supported high-throughput mesh networks, due to the large physical layer frame size and prolonged channel reservation from frame aggregation. The proposed approach uses the standard carrier sense multiple access (CSMA) technology along with an opportunistic collision avoidance (OCA) method that blocks the communication for hidden nodes and opportunistically allows exposed nodes to communicate with the peers. The performance of the proposed CSMA/OCA mechanism for high throughput mesh networks is studied using the results from an IEEE 802.11n+s wireless mesh networking testbed, and the scalability of the scheme has been analyzed using simulation results.

IEEE 802.11s mesh networking standard supports Mesh Coordinated Channel Access (MCCA) to provide better quality of service (QoS) through channel reservation during the MAC layer channel access. According to the current QoS specifications, network traffic can be broadly classified into four classes-voice, video, background and best effort. However, MCCA does not directly support the standard service differentiation that is essential for service level QoS assurance. Further, assuring fairness among the flows of similar service classes is required for effective bandwidth utilization. Providing service differentiation along with the fairness is challenging in a distributed environment due to their non-linearity and non-additive properties. This paper uses the concept of (α, p)-proportional fairness to design a distributed method for providing service differentiation with minimum fairness guarantee. An admission control mechanism is designed over standard mesh protocols to manage the minimum service guarantee for existing flows in the network. The effectiveness of the proposed scheme is analyzed using experimental results from an IEEE 802.11n+s mesh networking testbed. The scalability and performance bound of the proposed scheme is further analyzed using simulation results.

Current deployment of wireless community networks and wireless municipal services utilizes multi-hop backbone mesh network technology to provide ubiquitous Internet connectivity to the end users. IEEE 802.11s Wireless Mesh Network (WMN) is a promising technology to increase spatial reuse in a mesh backbone using high gain directional antennas. Uses of directional communication in a multi-interface mesh network introduce the problem of unbalanced traffic allocation among the end-to-end flows that results in inefficient channel access using the standard EDCA mechanism. Furthermore, the forwarding protocol should coordinate with the channel access to improve the network performance. In this paper, a localized distributed mechanism is proposed to share the channel bandwidth effectively among interfering interfaces based on the solution of the balanced traffic allocation problem. The standard forwarding algorithm is augmented to use the channel access information effectively in a dynamic network scenario. The performance of the proposed scheme is evaluated through the results obtained from a practical indoor IEEE 802.11n+s directional multi-interface mesh testbed.

The IEEE 802.11 standard for wireless local area networks defines a power management algorithm for Independent Basic Service Set (IBSS) allowing it to save critical battery energy in low powered wireless devices. The power management algorithm for IBSS uses beacon intervals (BIs) as the time unit, where every BI consists of an Announcement Traffic Indication Message (ATIM) window and a data window. The stations that have data to send need to go through a handshaking procedure in the ATIM window. If this handshaking is successful, the station remains awake in the data window and participates in the data communication. Otherwise, it goes into the sleep mode. This paper presents an analytical model to compute the throughput, expected delay and expected power consumption in an IEEE 802.11 IBSS in power save mode (PSM) for different traffic conditions in the network. The impact of data arrival rate, network size, and size of the BI on the performance of the IEEE 802.11 DCF in PSM is also analyzed. This analysis reveals a clear trade-off among throughput, delay, and average power consumption. The trade-off analysis is useful for designing efficient power consumption algorithms while maintaining the consistence performance of the network in terms of throughput and delay.

Wireless sensor networks have grown significant attentions among researchers for providing a flexible and low-cost framework to design an architecture for Intelligent Transport Systems. The inherent challenges in distribution and management of sensor networks along the road require an application-specific protocol support for the network connectivity, the sensing coverage, the reliable data forwarding, and the network lifetime improvement. This paper introduces the concept of k-strip length coverage along the road, which ensures a better sensing coverage for the detection of moving vehicles compared with the conventional barrier coverage and full area coverage, in terms of the availability of sufficient information for statistical processing and the number of sensors required to be active. To extend the network lifetime, every sensor follows a sleep-wakeup schedule maintaining the network connectivity and the k-strip length coverage. This scheduling problem is modeled as a graph optimization, the NP-hardness of which motivates to design a centralized heuristic, providing an approximate solution. As a sensor network is inherently distributed in nature, properties of the centralized heuristic are explored to design a per-node solution based on local information. Performance of the proposed scheme is analyzed through simulation results.

IEEE 802.11 Community wireless hotspots are widely used to provide ubiquitous Internet connections to the end-users in public areas such as airports and restaurants. The recent analysis of the traffic pattern in a wireless hotspot shows more APs are deployed in a public area than required, though the users visit only a few APs. As a consequence, severe load imbalance is observed in a hotspot local area network (LAN), that results in performance degradation in terms of quality of service (QoS) for the network and quality of experience (QoE) for the end-users. This paper proposes a set of bandwidth management policies to achieve this goal, and the effectiveness of these policies is analyzed theoretically. According to the theoretical foundation, a context aware handover management scheme for proper load distribution in a public IEEE 802.11 network, supporting the class-aware bandwidth management policies, is designed in this paper. The performance of the proposed scheme is evaluated using an IEEE 802.11g+e wireless LAN testbed, and compared with other schemes proposed in the literature.

Data gathering or converge cast is one of the most popular applications of road side sensor network where the data sensed from the road are accumulated in the road side gateways or sinks for traffic monitoring purpose. The required delay sensitivity and reliability of the application as well as the scarcity of sensor resources make the task challenging. In this paper, a novel tree based data gathering scheme has been proposed exploiting the strip like structure of the road network. Sensor nodes are distributed in several virtual blocks along the road and a converge cast tree is constructed selecting one active node from each block. Implementation of efficient scheduling assures both the coverage and critical power savings of sensor nodes. The network connectivity is guaranteed throughout by the proposed tree maintenance module that handles the sensor node joining and leaving events. Simulation results show that the tree maintenance overhead in terms of both delay and control message communication is nominal.

Sensor networks deployed for the border area monitoring requires a high degree of reliability for the data gathering in spite of any arbitrary node or sink failures. This paper proposes RelBAS, a robust data gathering scheme specially designed for the border area network to provide a guaranteed delivery of sensory data. The proposed protocol aims to find out multiple node-disjoint paths to multiple sinks so that the disconnectivity in one path due to a node failure does not disrupt the delivery of data to the sink. The forwarding path selection at every node in RelBAS is based on the combination of three parameters - the hop-count, the residual energy and the number of children for for parent of the corresponding tree. This helps in adapting the protocol to the application requirement depending on the delay, energy efficiency and data aggregation. Moreover, RelBAS is capable of detecting an affected zone due to multiple node failures. The effectiveness of the proposed scheme has been analyzed using the simulation results.

The lifetime of sensor network depends on the efficient utilization of resource-constrained sensor nodes. Several MAC protocols like DMAC and its variants have been proposed to save critical sensor resources through sleep-wakeup scheduling over data gathering tree. For applications where data aggregation is not possible, the sleep duration decreases gradually from the leaves to the root of the data gathering tree. This results early failure of sensor nodes near the sink, and affects network connectivity and coverage. Deploying redundant sensors can solve this problem where a faulty node is replaced by a redundant node to maintain network connectivity and coverage. However, the amount of redundancy depends on the node failure pattern, and thus more number of redundant nodes required to be deployed near the sink. This paper proposes a gradient based sensor deployment scheme for energy-efficient data gathering exploring the trade-off among connectivity, coverage, fault-tolerance and redundancy. The density of deployment is estimated based on the distance of a node from the sink while dealing with connectivity, coverage and fault-tolerance. The effectiveness of the proposed scheme has been analyzed both theoretically and with the help of simulation.

IEEE 802.11s provides Hybrid Wireless Mesh Protocol (HWMP) to find out the forwarding path in a mesh network based on mesh peering and MAC layer scheduling information. However, both proactive and reactive modes of HWMP perform poorly for multi-radio mesh network because of inefficient radio selection, time-varying channel conditions and interference among the radios. This paper proposes an improved opportunistic path selection protocol over HWMP for multi-radio support that goes beyond the traditional routing mechanisms, operates either in proactive, reactive or hybrid mode. The efficiency of the proposed scheme is analyzed using simulation results.

Single channel multi-interface IEEE 802.11s Wireless Mesh Network(WMN) is a promising technology for increasing spatial reuse of wireless channel using high gain directional antennas. Use of single channel in WMN is advantageous for providing different services (like community mesh networking, vehicular mesh networking etc.) by different frequency channels so that several wireless networking services can co-exist. However, for effective use of multi-interface multi-beam directional antennas in single channel environment, proper scheduling of interfaces and prioritization among different beams are required to minimize channel interference. In this paper a distributed mechanism is proposed to share bandwidth effectively among different interfaces in a probabilistic way based on local communication and interference information. A beam prioritization mechanism is used based on IEEE 802.11s EDCA to minimize under-use or overuse of channel bandwidth by a directional beam and maximize concurrent packet transmission. Simulation result shows that the proposed scheme improves efficiency of the network over standard IEEE 802.11s EDCA based MAC protocol.

Event driven data gathering or convergecast through sensor nodes requires efficient and correct delivery of data at the sink. A tree rooted at the sink is an ideal topology for data gathering which utilizes sensor resources properly. Resource constrained sensor nodes are highly prone to sudden crash. A set of algorithms, proposed in this paper, builds a data gathering tree rooted at the sink. The tree eventually becomes a Breadth First Search (BFS) tree where each node maintains the shortest distance in hop-count to the root to reduce the routing delay and power consumption. The data gathering tree is repaired locally within a constant round of message transmissions after any random node fails. Simulation result shows that the repairing delay is very less in average, and the proposed scheme can repair from arbitrary node failure using constant number of message passing.

Wireless Mesh Network is a promising technology to construct backbone of vehicular network where multi-path communication can be used effectively to communicate between vehicular clients and Internet gateways. The performance of such network can be increased using high-gain smart antennas and beam-forming technology. The mesh access points use multi-interface multi-beam smart antenna technology to communicate with vehicular clients and neighboring access points. MAC layer channel access and scheduling is an important issue in this network architecture such that the interference is minimized among different communications. In this paper, a dynamic TDMA channel access mechanism based on HiperLAN/2 is designed to improve network capacity using efficient beam-scheduling. Simulation result shows the efficiency of the proposed scheme in terms of network throughput, end-to-end fairness and cumulative packet transmission ratio.