Low power sensing networks often operate in open and potentially hostile environments. Ensuring that only legitimate devices communicate with the network is paramount. Authentication serves as the first line of defense in securing communication and data integrity, thereby protecting the network and devices from unauthorized access and data breaches. However, the ease of access to devices and sensors in the Internet-Of-Things (IoT) makes it easier for an attacker to replace legitimate devices and implant rogue ones in their stead; or physically tamper with devices (e.g., by moving them to another location). In this paper, we propose a resilient machine learning approach to uniquely identify deployment environments based on the link quality footprints of the devices that transmit from these environments. Our approach complements device identification based on unique RF transmission footprints. To the best of our knowledge, this is the first approach that attempts to uniquely identify the deployment environment despite considerable variations in both external and internal factors that affect signal propagation. We employ two different machine learning models, one based on a Convolutional Neural Network (CNN) and the other based on a Residual Network (ResNet). Through independent experiments involving actual deployments in five different environments in Miami, Florida (land, lake, Biscayne Bay, South Beach, and Crandon Beach), we attest that both models were able to uniquely identify the deployment environments with an average accuracy exceeding 99%. Furthermore, our models were able to distinguish between specific deployment configurations. In general, the ResNet model correctly identified the type of prototypes used with 100% accuracy (and CNN, with 98% accuracy). Both models were able to identify the types of radio used for transmission with 99% accuracy.

Mental health is a growing concern, especially among young adults, but gathering data from this demographic presents distinct challenges. Crowdsensing is a research approach that has become increasingly popular due to its ability to collect data from many individuals continuously and at scale. However, it is equally important to ensure that the data collected is of high quality, as it depends on many factors. In this paper, we discuss the data quality issues encountered during our crowdsensing study conducted from October 2022 to August 2023, which aimed at collecting data to study college students' emotions and mental wellness. We present our findings on data quality issues related to participant recruitment, device usability, data quantity, compliance, consistency, privacy concerns, and incentive mechanisms. We discuss the strategies to address these challenges and plans for future improvements. Our results and discussion highlight the effectiveness of crowdsensing in data collection for this demographic. Additionally, we identified positive and negative emotional drivers and potential stressors affecting this group's mental wellness. The insights from this work can aid the design of future crowdsensing applications and studies.

Research in the field of speech emotion recognition (SER) relies on the availability of comprehensive datasets to make it possible to design accurate emotion detection models.This study introduces the Multimodal Emotion Recognition and Sentiment Analysis (MERSA) dataset, which includes both natural and scripted speech recordings, transcribed text, physiological data, and self-reported emotional surveys from 150 participants collected over a two-week period.This work also presents a novel emotion recognition approach that uses a transformer-based model, integrating pre-trained wav2vec 2.0 and BERT for feature extractions and additional LSTM layers to learn hidden representations from fused representations from speech and text.Our model predicts emotions on dimensions of arousal, valence, and dominance.We trained and evaluated the model on the MSP-PODCAST dataset and achieved competitive results from the best-performing model regarding the concordance correlation coefficient (CCC).Further, this paper demonstrates the effectiveness of this model through crossdomain evaluations on both IEMOCAP and MERSA datasets.

Parkinson’s Disease (PD) is a neurodegenerative disorder characterized by both motor and non-motor symptoms, including significant changes in neurocognitive functions (NFs). Dopamine synthesis, a critical process in PD, is heavily impacted by genetic factors, contributing to motor dysfunction and neurocognitive impairment. While some genetic mutations have been linked to PD-related neurocognitive impairments, the specific impact of these mutations on NFs remains unclear. This study explores the relationship between mutations in dopamine synthesis-related genes and NFs in PD patients and healthy controls (HC). Using a gene sequencing dataset (INDELs and SNPs) from the PPMI repository that includes 171 dopamine synthesis-related genes, we applied t-tests to identify 34 significantly mutated genes. We considered subjective (self-reported) responses from the MDS-UPDRS for seven NFs (i.e., motor, autonomic function, behavior/psychological, executive function, sensory, sleep, and speech). To investigate the link between significantly mutated genes and neurocognitive performance, participants were grouped into healthy and PD groups, and then each group was split into mutated and non-mutated samples. For healthy controls, presence of mutation in CAMK2D, and NOSTRIN and absence of mutation in DDX17 found related to NF worsening. In case of PD samples, the presence of mutations in genes like B3GALT5, CHRNA2, SNX27, TRIP4, and UBQLN4 and absence of mutation in genes like ABCA7, INTS4, MYLK3, PRKG1, and PRKN were linked to worsening neurocognitive outcomes. Overall, these findings provide a deeper understanding of the genetic influences on neurocognitive functions in PD and highlight potential targets for future research and therapeutic strategies.

Mild traumatic brain injury (mTBI) is challenging to diagnose due to its subtle and transient symptoms, making noninvasive diagnostic tools crucial for early detection. This study explores the use of a custom ResNet deep learning model combined with the Grad-CAM interpretability technique for mTBI detection via speech analysis. Speech data were transformed into Mel-spectrograms and fed into the model for binary classification between concussed and control individuals. The Grad-CAM method provided insights into which frequency regions of the Mel-spectrogram were most important for the model's predictions, with higher-frequency regions identified as significant for the model in detecting mTBI. Using Monte Carlo Cross-Validation (MCCV), we evaluated 50 different subject train-test split configurations to gain insights into the model's performance stability and variability. This analysis can assess the model's ability to learn consistent patterns within the dataset and suggest potential generalization tendencies. The variability observed in the performance metrics distribution underscores the importance of robust evaluation methods, particularly when working with small datasets. The combination of deep learning, robust evaluation technique and interpretability in this study contributes to the development of clinically viable, speech-based tools for mTBI detection, with potential applications in sports and healthcare settings.

The use of Automatic Speech Recognition (ASR) systems in medical applications is receiving rapidly growing interest due to their ability to reduce distractions and the cognitive workload of physicians, particularly during critical medical procedures. However, state-of-the-art ASR systems still experience recognition errors, especially in noisy environments where speakers rely on medical-domain terminologies. This paper proposes a customized language model and a neural network based sequence-to-sequence (seq2seq) error correction module for medical ASR systems to provide domain adaptation and more reliable transcription results. Specifically, the error correction module learns the error patterns in noisy scenarios and is able to correct such errors during inference. Our experiments show that the proposed method can reduce the sentence error rate (SER) by up to 81% for formatted input and up to 31% SER for unformatted input in noisy environments.

When high school students leave their homes for a college education, they often face enormous changes and challenges in life, such as meeting new people, more responsibilities in life, and being away from family and their comfort zones. These sudden changes often lead to an elevation of stress and anxiety, affecting a student’s health and well-being. Situations can even get worse in the age of global pandemics, such as COVID-19, when regular life and social activities are significantly disrupted due to lockdown or stay-at-home orders. Therefore, predicting phone call patterns (a measure of social engagement) based on various factors and activities of a person can be helpful to foster social engagement and promote health and well-being during sudden lifestyle changes. In this work, we investigate a cohort of 370 on-campus college students over three consecutive semesters and breaks between them to find various geo-temporal factors and activities that affect students’ phone call behaviors and develop models that can predict the next call duration with a correlation of up to 0.89 between the actual and predicted duration using individual-level generalized linear models. Findings from this work can further be extended to other populations, and thereby, our findings will enable the design and delivery of new smartphone-based health interventions (guided feedback) to help people to adapt and cope up with situations that affect their lifestyle and social activities.

Mobile edge computing (MEC) is an emerging paradigm that supports low-latency applications in resource-constrained scenarios, such as the Internet of Things (IoT) and vehicular networks. MEC makes it feasible to process and handle massive amounts of data and service requests generated by mobile end users or IoT devices and to deliver timely responses or interventions. However, the computers forming an MEC system typically have limited computing resources, which must be shared by multiple tasks and many simultaneous service requests. How to dispatch and schedule computational tasks from end users in an MEC system is a challenging problem, especially for latency-sensitive applications. In this paper, we propose a self-adaptive task dispatching and scheduling scheme to deliver low-latency service responses in a resource-efficient way. The proposed approach prioritizes computational tasks based on their attributes (e.g., CPU and RAM requirements, priority level, and expiration time) and solves the scheduling problem using a reinforcement learning approach. The feasibility and effectiveness of the proposed scheme are verified using simulation and a small-scale case study on an MEC testbed, demonstrating that the proposed scheme is effective and efficient.

Modern smartphones and wearables are able to continuously collect significant amounts of sensor data, where such data can be helpful to study a user's mobility or social interaction patterns, but also to deliver various services based on a user's presence at different places during certain times of the day. Therefore, it is important to accurately identify personal places of interest (POIs), such as a user's workplace or home. Such places are usually determined using segmentation of location traces, but frequent gaps in the data (i.e., missing location readings) can result in a large number of small and incomplete segments that should actually be grouped together into a single large segment. This paper presents a segmentation approach that utilizes a user's personal data obtained from multiple sensor sources and devices such as the battery recharge behavior (measured on smartphones), step counts, and sleep patterns (measured by wearables), to opportunistically fill gaps in the user's location traces. Using the data from a mobile crowd sensing study of more than 450 users over a 2-year period, we show that our approach is able to generate fewer, but more complete segments compared to the state of the art.

Depression and anxiety are critical public health issues affecting millions of people around the world. To identify individuals who are vulnerable to depression and anxiety, predictive models have been built that typically utilize data from one source. Unlike these traditional models, in this study, we leverage a rich heterogeneous dataset from the University of Notre Dame’s NetHealth study that collected individuals’ (student participants’) social interaction data via smartphones, health-related behavioral data via wearables (Fitbit), and trait data from surveys. To integrate the different types of information, we model the NetHealth data as a heterogeneous information network (HIN). Then, we redefine the problem of predicting individuals’ mental health conditions (depression or anxiety) in a novel manner, as applying to our HIN a popular paradigm of a recommender system (RS), which is typically used to predict the preference that a person would give to an item (e.g., a movie or book). In our case, the items are the individuals’ different mental health states. We evaluate four state-of-the-art RS approaches. Also, we model the prediction of individuals’ mental health as another problem type—that of node classification (NC) in our HIN, evaluating in the process four node features under logistic regression as a proof-of-concept classifier. We find that our RS and NC network methods produce more accurate predictions than a logistic regression model using the same NetHealth data in the traditional non-network fashion as well as a random-approach. Also, we find that the best of the considered RS approaches outperforms all considered NC approaches. This is the first study to integrate smartphone, wearable sensor, and survey data in a HIN manner and use RS or NC on the HIN to predict individuals’ mental health conditions.

As the economy progresses and new technologies emerge, more people are struggling with sleep-related difficulties. Poor sleep quality adversely affects people's health and well-being, productivity, academic success, and cognitive capability. These impairments can also affect traffic and industrial safety, and national economic developments. To better tackle these problems, it is important to accurately understand people's sleep quality. In this work, we present approaches to accurately estimate a user's sleep duration, which will facilitate better estimation of sleep quality. We apply generalized linear model (GLM) and generalized linear mixed model (GLMM), which takes person variability into consideration in addition to fixed effects, such as various temporal factors (sleep start time, days of a week, etc.), weather, a user's daily activities and calendar entries to estimate sleep duration. Through our analysis of a longitudinal sensor dataset collected from the smartphones and Fitbits of a cohort of 18 on-campus college students over an extended period of time, we show the feasibility of the work with correlations of up to 0.745 between the pairs of actual and estimated sleep durations.

With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks. Previous efforts to address this concern have focused primarily on single-channel audio. In this paper, we introduce a novel neural network-based replay attack detection model that further leverages spatial information of multi-channel audio and is able to significantly improve the replay attack detection performance.

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft attention to reallocate distant outliers to their most similar parts, while others adjust part granularity to incorporate more distant positions for learning the relationships. Others seek to generalize part-based methods by introducing a dropout mechanism on consecutive regions of the feature map to enhance distant region relationships. However, only few prior efforts model the distant or non-local positions of the feature map directly for the person re-ID task. In this paper, we propose a novel attention mechanism to directly model long-range relationships via second-order feature statistics. When combined with a generalized DropBlock module, our method performs equally to or better than state-of-the-art results for mainstream person re-identification datasets, including Market1501, CUHK03, and DukeMTMC-reID.

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can observe the entire original sample and then add a perturbation at any point of the sample. These attack approaches are not applicable to situations where the target model takes streaming input, i.e., an attacker is only able to observe past data points and add perturbations to the remaining (unobserved) data points of the input. In this paper, we propose a real-time adversarial attack scheme for machine learning models with streaming inputs.

This paper introduces a new database of voice recordings with the goal of supporting research on vulnerabilities and protection of voice-controlled systems (VCSs).In contrast to prior efforts, the proposed database contains both genuine voice commands and replayed recordings of such commands, collected in realistic VCSs usage scenarios and using modern voice assistant development kits.Specifically, the database contains recordings from four systems (each with a different microphone array) in a variety of environmental conditions with different forms of background noise and relative positions between speaker and device.To the best of our knowledge, this is the first publicly available database 1 that has been specifically designed for the protection of state-of-the-art voice-controlled systems against various replay attacks in various conditions and environments.

The Internet of Things (IoT) is increasingly empowering people with an interconnected world of physical objects ranging from smart buildings to portable smart devices, such as wearables. With recent advances in mobile sensing, wearables have become a rich collection of portable sensors and are able to provide various types of services, including tracking of health and fitness, making financial transactions, and unlocking smart locks and vehicles. Most of these services are delivered based on users' confidential and personal data, which are stored on these wearables. Existing explicit authentication approaches (i.e., PINs or pattern locks) for wearables suffer from several limitations, including small or no displays, risk of shoulder surfing, and users' recall burden. Oftentimes, users completely disable security features out of convenience. Therefore, there is a need for a burden-free (implicit) authentication mechanism for wearable device users based on easily obtainable biometric data. In this paper, we present an implicit wearable device user authentication mechanism using combinations of three types of coarse-grain minute-level biometrics: behavioral (step counts), physiological (heart rate), and hybrid (calorie burn and metabolic equivalent of task). From our analysis of over 400 Fitbit users from a 17-month long health study, we are able to authenticate subjects with average accuracy values of around .93 (sedentary) and .90 (non-sedentary) with equal error rates of .05 using binary SVM classifiers. Our findings also show that the hybrid biometrics perform better than other biometrics and behavioral biometrics do not have a significant impact, even during non-sedentary periods.

As the economy progresses and new technology emerges, more people are struggling with sleep-related difficulties. Researchers have previously identified that smartphone use may be associated with poor sleep quality. However, smartphones have become an indispensable part of modern life. Therefore, it is important to investigate the potential impacts of smartphone use patterns on an individual's health. In this paper, we investigate sleep quality variations between two sets of pre-sleep phone use patterns: phone use before bed-time and phone use during bed-time (before sleep). Our analysis, based on a multi-year mobile crowdsensed data collection effort on more than 400 college students, shows significant sleep quality variations when a phone is used in either of these two usage patterns compared to when it is not used. However, the results also show that phone use during bed-time leads to a significantly worse sleep quality. We expect that these findings will be useful for individuals, public authorities, and smartphone developers to improve smartphone users' sleep quality.

Over the last few years, a rapidly increasing number of Internet-of-Things (IoT) systems that adopt voice as the primary user input have emerged. These systems have been shown to be vulnerable to various types of voice spoofing attacks. Existing defense techniques can usually only protect from a specific type of attack or require an additional authentication step that involves another device. Such defense strategies are either not strong enough or lower the usability of the system. Based on the fact that legitimate voice commands should only come from humans rather than a playback device, we propose a novel defense strategy that is able to detect the sound source of a voice command based on its acoustic features. The proposed defense strategy does not require any information other than the voice command itself and can protect a system from multiple types of spoofing attacks. Our proof-of- concept experiments verify the feasibility and effectiveness of this defense strategy.

A longitudinal cohort study is a popular research method to observe a group of people over a prolonged period of time, e.g., to learn about their health, wellness, and social habits. Smartphones have become a very popular tool to perform such studies at a large scale. Location is an essential form of sensor data that can not only be used to monitor users' mobility and social interaction patterns, but also to identify places of personal significance, i.e., places where a user spends a significant amount of time, such as a user's home, workplace, and preferred social gathering places. However, continuously tracking a user's location can have significant impacts on the battery lifetime of a smartphone. Therefore, instead of frequent period location sensing, this paper identifies smartphone events that can be used to trigger location sensing at a much lower rate (and therefore more energy-efficiently), while still providing accurate location data. In this work, we demonstrate that this approach allows us to determine a user's significant places with an accuracy of 85%, while saving over 60% in computational and energy overheads.

Pedestrians are particularly vulnerable traffic participants with a very high fatality rate. An important component of Advanced Driver Assistant Systems is the accurate localization of pedestrians and other vulnerable traffic participants using various sensors and other technologies. Localization using radio frequency (RF) signals is commonly used, because of the widespread availability of wireless radios, ease of deployment, and the fact that RF-based ranging will work in all weather and light conditions. However, the accuracy of RF-based ranging in vehicular networks is easily affected by high device dynamics and mobility, leading to varying impacts of shadowing and multipath fading. In this paper, we introduce a new ranging algorithm that first uses a novel filtering scheme that reduces the impact of mutipath fading and shadowing. Then, we use an exhaustive search method to minimize an MSE function that represents the difference between the filtered RSSI values and the expected RSSI values (based on the channel model) to estimate the distance between transmitter and receiver. The performance of the proposed ranging algorithm is evaluated using real field measurements in terms of accuracy and convergence time.

It is becoming increasingly important to accurately detect a user's presence at certain locations during certain times of the day, e.g., to study the user's patterns with respect to mobility, behavior, or social interactions and to enable the delivery of targeted services. However, instead of geographic locations, it is often more important to determine a locale that is relevant to the user, e.g., the place of work, home, homes of family and friends, social gathering places, etc. These significant personal places can be determined through analysis, e.g., via segmentation of location traces into a discrete sequence of places. However, segmentation of traces with many gaps (e.g., due to loss of network connectivity or GPS signal) results in a large number of small segments, where many of these segments actually belong together. This work proposes a novel segmentation approach that opportunistically fills gaps in a user's location trace by borrowing location data from other co-located users utilizing the power of mobile crowd sensing and computing (MCSC) paradigm. Through our analysis of four separate large-scale crowd sensing study datasets, we show that our approach yields more and larger segments than the state-of-the-art, where each segment accurately represents the presence of a user at a significant personal place.

Code offloading is a popular technique for extending the natural capabilities of mobile devices by migrating processor‐intensive tasks to resource‐rich surrogates. Despite multiple platforms for offloading being available in academia, these frameworks have yet to permeate the industry. One of the primary reasons for this is limited experimentation in practical settings and lack of reliability, scalability, and options for distribution. This paper introduces MobiCOP, a new code offloading framework designed from the ground up with these requirements in mind. It features a novel design fully self‐contained in a library and offers compatibility with most stock Android devices available today. Compared to local task executions, MobiCOP offers performance improvements of up to 17x and increased battery efficiency of up to 25x, shows minimum performance degradation in environments with unstable networks, and features an autoscaling module that allows its server counterpart to scale to an arbitrary number of offloading requests. It is compatible with the most relevant Android technologies optimized for heavy computation (NDK and Renderscript) and has so far been well received by fellow mobile developers. We hope MobiCOP will help bring mobile code offloading closer to the industry realm.

Wearables, such as Fitbit, Apple Watch, and Microsoft Band, with their rich collection of sensors, facilitate the tracking of healthcare- and wellness-related metrics. However, the assessment of the physiological metrics collected by these devices could also be useful in identifying the user of the wearable, e.g., to detect unauthorized use or to correctly associate the data to a user if wearables are shared among multiple users. Further, researchers and healthcare providers often rely on these smart wearables to monitor research subjects and patients in their natural environments over extended periods of time. Here, it is important to associate the sensed data with the corresponding user and to detect if a device is being used by an unauthorized individual, to ensure study compliance. Existing one-time authentication approaches using credentials (e.g., passwords, certificates) or trait-based biometrics (e.g., face, fingerprints, iris, voice) might fail, since such credentials can easily be shared among users. In this paper, we present a continuous and reliable wearable-user authentication mechanism using coarse-grain minute-level physical activity (step counts) and physiological data (heart rate, calorie burn, and metabolic equivalent of task). From our analysis of 421 Fitbit users from a two-year long health study, we are able to statistically distinguish nearly 100% of the subject-pairs and to identify subjects with an average accuracy of 92.97%.

This paper shows that extraction and analysis of various acoustic features from speech using mobile devices can allow the detection of patterns that could be indicative of neurological trauma. This may pave the way for new types of biomarkers and diagnostic tools. Toward this end, we created a mobile application designed to diagnose mild traumatic brain injuries (mTBI) such as concussions. Using this application, data were collected from youth athletes from 47 high schools and colleges in the Midwestern United States. In this paper, we focus on the design of a methodology to collect speech data, the extraction of various temporal and frequency metrics from that data, and the statistical analysis of these metrics to find patterns that are indicative of a concussion. Our results suggest a strong correlation between certain temporal and frequency features and the likelihood of a concussion.

It is becoming increasingly important to accurately detect a user's presence at certain locations during certain times of the day, e.g., to study the user's patterns with respect to mobility, behavior, or social interactions and to enable the delivery of targeted services. However, instead of geographic locations, it is often more important to determine a locale that is important to the user, e.g., the place of work, home, homes of family and friends, social gathering places, etc. These significant personal places can be determined through analysis, e.g., via segmentation of location traces into a discrete sequence of places. However, segmentation of traces with many gaps (e.g., due to loss of network or GPS signal) results in a large number of small segments, where many of these segments actually belong together. This work proposes a new segmentation approach that opportunistically fills gaps in location traces with the help of data from other (co-located) users. Using data from 195 users, collected over a 2-year period, we show that this approach yields fewer and larger segments, where each segment accurately represents the presence of a user at a significant personal place.

The increasing importance of location-aware computing and context-dependent services have led to a growing interest in low-cost indoor positioning with sub-meter accuracy. Bluetooth positioning has received increasing attention from both academia and industry due to its wide availability, ease of deployment, and low power consumption. However, Bluetooth positioning is primarily based on the Received Signal Strength Indicator (RSSI), which has been shown to be an unreliable indicator of distance. In this work, we present measurements to highlight various challenges in using RSSI for localization and the impact of these challenges on localization accuracy. Further, we propose and evaluate a novel multi-ranges beaconing approach to address RSSI-based ranging challenges.

Routing algorithms for cognitive radio networks should consider various objectives and constraints. Constraint-based routing (CBR) algorithms select a route satisfying constraints that are either administrative-oriented (policy routing), or service-oriented (QoS routing). In cognitive radio networks, a primary user's interference constraint is the most important objective for the activities of secondary users. Beside the interference constraints, transmission delay is another important constraint for delay-sensitive services. In this paper, we propose a CBR algorithm that considers interference and delay constraints for a cognitive radio network. While these constraints address the QoS requirements for a cognitive radio network, to also consider the routing policy in the proposed CBR, we use the Pareto-optimal concept to allow the secondary users to transmit based on the network policy and resource constraints. The evaluation results of the proposed CBR scheme show that it can outperform other recently proposed CBR approaches.

Continuous (24/7) smartphone sensing applications are on the rise, especially in the field of health and wellness, e.g., to monitor physical activity, to quickly detect emergencies (e.g., falls), and to provide various context-specific services and tools. Smartphones are able to monitor a large array of human activities and patterns, including a user's mobility, physical activities, social interactions, mobile app usage, or communication events. However, building smartphone sensing applications that operate reliably and efficiently on a continuous basis is challenging. Specifically, in this paper, we describe our experience with building a sensing service for the iOS platform, that has been running on more than 400 devices continuously for more than 9 months to date. We present and discuss a variety of technical and non-technical obstacles and challenges and how they were addressed.

Vehicle-to-vehicle safety communications based on the dedicated short-range communication technology have the potential to enable a set of applications that help avoid traffic accidents. The performance of these applications, largely affected by the reliability of communication links, stringently ties back to the MAC and PHY layer design, which has been standardized as IEEE 802.11p. The link reliabilities depend on the signal-to-interference-plus-noise ratio (SINR), which, in turn, depends on the locations and transmit power values of the transmitting nodes. Hence, an accurate network model needs to take into account the network geometry. For such geometric models, however, there is a lack of mathematical understanding of the characteristics and performance of IEEE 802.11p. Important questions such as the scalability performance of IEEE 802.11p have to be answered by simulations, which can be very time consuming and provide limited insights to future protocol design. In this paper, we investigate the performance of IEEE 802.11p by proposing a novel mathematical model based on queuing theory and stochastic geometry. In particular, we extend the Matérn hard-core type-II process with a discrete and nonuniform distribution, which is used to derive the temporal states of backoff counters. By doing so, concurrent transmissions from nodes within the carrier sensing ranges of each other are taken into account, leading to a more accurate approximation to real network dynamics. A comparison with Network Simulator 2 (ns2) simulations shows that our model achieves a good approximation in networks with different densities.

Route discovery and node localization are two strongly correlated concepts in wireless sensor networks (WSNs) and many different techniques have been proposed for both challenges. However, many of these solutions assume homogeneous network conditions, e.g., Identical sensor hardware, fixed transmission powers, or uniform node deployment. In heterogeneous networks, where these parameters are allowed to differ or change over time, many of these solutions fail to ensure accurate localization and route discovery that covers the entire network. This paper introduces a new approach that combines both route discovery and sensor node localization into one protocol that considers the heterogeneous nature of many WSNs. The proposed approach does not require any extra hardware and performs both a probabilistic ad-hoc route discovery process (based on sensor transmission ranges) and energy-efficient localization of sensor nodes. The performance of this approach is evaluated in terms of localization accuracy, energy efficiency, and network coverage.

Concussions are Mild Traumatic Brain Injuries (mTBI) that are common in contact sports and are often difficult to diagnose due to the delayed appearance of symptoms. This paper explores the feasibility of using speech analysis for detecting mTBI. Recordings are taken on a mobile device from athletes participating in a boxing tournament following each match. Vowel sounds are isolated from the recordings and acoustic features are extracted and used to train several one-class machine learning algorithms in order to predict whether an athlete is concussed. Prediction results are verified against the diagnoses made by a ringside medical team at the time of recording and performance evaluation shows prediction accuracies of up to 98%.

Today's modern mobile devices (e.g., smartphones and tablets) present great potential for building large-scale mobile sensing and information sharing systems which can be highly beneficial to minimize the fatalities of human lives during emergency response. This paper presents a framework, called BREathing rate MONitoring (BREMON) that allows paramedics to monitor the breathing activities of multiple patients at once using their smartphones. BREMON uses the smartphone accelerometer to measure the accelerations during the breathing activities of a patient. These raw acceleration data are then processed to calculate the number of Breaths Per Minute (BPM) and periodically sent to the smartphones used by the paramedics over a multi-hop network. BREMON makes use of an underlying service sharing infrastructure, called SPontaneous Information and Resource sharing InfrasTructure (SPIRIT) that allows mobile devices to share the breathing activity data as services within the infrastructure.

Maintaining a common notion of time among communicating nodes in mobile multihop networks is crucial to the correctness of many distributed real-time applications such as target tracking, data fusion, and environmental monitoring. Achieving both synchronization accuracy and efficiency (in terms of communication and energy overheads) are important goals of a time synchronization mechanism. While these goals have been addressed by numerous approaches for stationary or homogeneous networks that rely on uniform clock drift models and synchronization accuracy requirements, these existing approaches are not optimal when applied in networks that are mobile or where synchronization accuracies and clock drift rates differ among nodes. This paper proposes a novel opportunistic and on-demand synchronization mechanism called Mobi-Sync, which has two important characteristics. First, it avoids network-wide flooding or frequent reconstructing of rigid structures that are often unavoidable in other approaches when applied to mobile networks. Second, it (re-)synchronizes nodes only when necessary, thereby customizing the synchronization interval to each node's specified accuracy requirement. Our results demonstrate that Mobi-Sync satisfies the nodes' synchronization requirements in mobile networks, while significantly reducing the synchronization overhead compared to existing solutions.

We consider wireless real-time systems that execute computationally-intensive applications and must transmit packets over the network in a timely manner. Existing methods do not consider the importance (i.e., urgency) of a packet as perceived by end users in conjunction with energy consumption, real-time task deadlines, and packet deadlines, inadvertently causing packet priority inversion during transmissions and possibly starvation of some streams. We present an online holistic scheduling framework that explicitly considers packet importance to select packets to transmit and guarantee their deadline requirements using both packet and energy-aware job assignment and scheduling. Our framework is applicable to wireless real-time systems equipped with either a single processor or a multicore system. Based on extensive simulations, we show that our proposed method allows for timely transmissions of the most important packets, which helps to control packet urgency, while saving processor(s) energy.

Reservation-based (as opposed to contention-based) channel access in WLANs provides predictable and deterministic transmission and is therefore able to provide timeliness guarantees for wireless and embedded real-time applications. Also, reservation-based channel access is energy-efficient since a wireless adaptor is powered on only during its exclusive channel access times. While scheduling for Quality of Service at the central authority (e.g., base station) has received extensive attention, the problem of determining the actual resource requirements of an individual node in a wireless real-time system has been largely ignored. This work aims at finding the minimum channel bandwidth reservation that meets the real-time constraints of all periodic streams of a given node. Keeping the bandwidth reservation of a node to a minimum leads to reduced energy and resource requirements and leaves more bandwidth for future reservations by other nodes. To obtain a solution to the minimum bandwidth reservation problem, we transform it to a generic uniprocessor task schedulability problem, which is then addressed using a generic algorithm. This algorithm works for a subclass of priority-driven packet scheduling policies, including three common ones: fixed-priority, EDF, and FIFO. Moreover, we then specialize the generic algorithm to these three policies according to their specific characteristics. Their computation complexities and bandwidth reservation efficiencies are evaluated and guidelines for choosing scheduling policies and stream parameters are presented.

Retasking and remote programming of sensor networks is an essential functionality to make these networks practical and effective. As the availability of more capable sensor nodes increases and new functional implementations continue to be proposed, these large collections of wireless nodes will need the ability to update and upgrade the software packages they are running. In order to do this, the new binary file must be distributed to all nodes in the network. Making a physical connection with each individual node is impractical in large wireless networks. Standard flooding mechanisms are too energy-costly and computationally expensive and they may interfere with the network's current tasks. A reliable method for distributing new code or binary files to every node in a wireless sensor network is needed. We propose a reprogramming/retasking framework for sensor networks that is energy efficient, responsive, and reliable, while maintaining a stable network.

Exclusive access to the wireless medium, e.g., as provided by bandwidth-reservation mechanisms, limits contention and therefore is capable of providing effective real-time support to periodic communications. Furthermore, to preserve energy, wireless cards can be powered down between periodic accesses without loss of data. However, packet schedulers must be aware of the limited communication opportunities to ensure that packets are transmitted before their deadlines, CPU schedulers must execute jobs such that the packets generated by these jobs are available for transmission in time, and DVS algorithms must choose processor speeds such that job execution and therefore packet generation are not unduly delayed. This paper proposes a co-scheduling approach to integrate CPU, network, and energy management for wireless real-time systems that rely on bandwidth reservations. Both simulation and experimentation indicate significant improvements in meeting packet deadlines (up to 40%) with only small increases in overall energy consumption (less than 10%) compared to the state of the art.

Wireless mesh networks are increasingly used as multipurpose networks, i.e., they serve multiple objectives and different applications simultaneously. As a consequence, a one-size-fits-all routing solution is difficult to achieve, particularly when the performance and QoS expectations of these applications differ. This work proposes CMR (Configurable Mesh Routing), a toolkit that supports the discovery of routes based on any combination of a number of supported QoS metrics. This enables network users to use customized routes that meet their unique needs. Our experiments illustrate how CMR can be used to (a) implement novel routing protocols on-the-fly and (b) emulate an existing reactive routing protocol.

introduction Share on Introduction to the special issue on self-adaptive and self-organizing wireless networking systems Authors: Michael Lemmon Department of Electrical Engineering, University of Notre Dame, USA Department of Electrical Engineering, University of Notre Dame, USAView Profile , Christian Poellabauer Department of Computer Science and Engineering, University of Notre Dame, USA Department of Computer Science and Engineering, University of Notre Dame, USAView Profile , Liqiang Zhang Department of Computer and Information Sciences, Indiana University South Bend, USA Department of Computer and Information Sciences, Indiana University South Bend, USAView Profile , Xiaobo Zhou Department of Computer Science, University of Colorado at Colorado Springs, USA Department of Computer Science, University of Colorado at Colorado Springs, USAView Profile Authors Info & Claims ACM Transactions on Autonomous and Adaptive SystemsVolume 4Issue 3Article No.: 15pp 1–4https://doi.org/10.1145/1552297.1552298Published:24 July 2009Publication History 1citation361DownloadsMetricsTotal Citations1Total Downloads361Last 12 Months1Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Reservation-based channel access has been shown to be effective in providing Quality of Service (QoS) guarantees (e.g., timeliness) in wireless embedded real-time applications such as mobile media streaming and networked embedded control systems. While the QoS scheduling at the central authority (i.e., base station) has received extensive attention recently, the computation of resource requirements at each individual node has been widely ignored. An inappropriate resource requirement may lead to degraded support for real-time traffic and overprovisioning of scarce network resources. This work addresses this issue by presenting a strategy for nodes to determine minimal resource reservations that guarantee the real-time constraints of their network traffic. In addition, this paper examines the relationship between timeliness constraints of the traffic and resource requirements.

Maintaining synchronization of clocks between wireless systems is a well known problem of which significant research has been performed. This has lead to a variety of methods introduced to maintain clock synchronization. Typically, works are heavy weight in that they require constant communication between systems in order to maintain clock synchronization on the order of microseconds. Unfortunately, for many applications the cost of constant communication to ensure clock synchronization is neither desirable nor acceptable. Additionally, for applications such as link state routing, delay measurements and quality of service measurements, clock synchronization on the order of microseconds is not necessary, and synchronization on the order of milliseconds is sufficient. Thus, in this work we present a light weight technique for correcting for clock drift between systems that will allow for millisecond accuracy during long periods of time while requiring no special hardware nor constant communication between systems. Experimental studies of the measured delay between two systems are performed, showing that with a training period, clocks can remained synchronized within a few milliseconds over long periods of time.

The demand for rich multimedia content is continuously increasing as exemplified by the success of sites such as YouTube, Google Video, and others. Critically, the richness of multimedia content places significant demands on the limited bandwidth available in wireless networks. To that end, this paper proposes a novel mechanism, opportunistic wireless broadcast (OWB), that opportunistically aggregates redundant content over short timescales into unified broadcasts in order to dramatically improve the efficiency of streaming media. Unlike end-to-end techniques such as application-layer multicast (ALM) or native IP multicast, OWB does not require modifications to the server or client applications, thus offering a practical transition for deployment. Experimental studies are presented showing that even with a minimal amount of redundancy, OWB can significantly improve network throughput and quality of service in terms of end-to-end delay.

Re-tasking and remote programming of sensor networks is an essential functionality to make these networks practical and effective. As the availability of more capable sensor nodes increases and new functional implementations continue to be proposed, these large collections of wireless nodes will need the ability to update and upgrade the software packages they are running. Standard flooding mechanisms are too energy-costly and computationally expensive and they may interfere with the network's current tasks. A reliable method for distributing new code or binary files to every node in a wireless sensor network is needed. This paper proposes a more effective method, called PALER (push aggressively with lazy error recovery), which builds upon the previously proposed PSFQ protocol [1], a reliable transport protocol which slowly paces the propagation of file segments, but uses an aggressive local recovery method to avoid packet implosion due to loss propagation. PALER uses a more aggressive pushing mechanism and reduces the recovery mechanism to a single inclusive NACK. Furthermore, PALER uses local neighbor information to reduce redundant transmissions. This paper studies this new protocol's energy efficiency and shows that it scales well to higher densities and field sizes.

Even though their capacities are still orders of magnitude lower than those of hard disks, flash storage systems are rapidly gaining importance in energy-constrained systems. This paper focuses on USB flash drives, which can provide portable storage to mobile systems or storage to systems that otherwise do not have persistent storage opportunities (e.g., low-power sensor devices). The paper presents studies relating to power consumption, energy overheads and benefits, and performance impacts of USB flash drives. The key insights obtained from these experiments are that (i) read/write costs are not significantly greater than idle costs and (ii) the size of the flash itself has only limited bearing on energy consumption.

Wireless enabled devices are ubiquitous in todaypsilas computing environment. Businesses, universities, and home users alike are taking advantage of the easy deployment of wireless devices to provide network connectivity without the expense associated with wired connections. Unfortunately, the wireless medium is inherently unreliable resulting in significant work having been performed to better understand the characteristics of the wireless environment. Notably, many works attribute the primary source of wireless losses to errors in the physical medium. In contrast, our work shows that the wireless device itself plays a significant role in 802.11 packet loss. In our experiments, we found that the correlation of loss between multiple closely located (within one lambda) receivers is low with the majority of loss instances only occurring at one of the receivers. We conducted extensive experiments on the individual loss characteristics of five common wireless cards, showing that while the cards behave similarly on the macro-level (e.g. similar overall loss rates), the cards perform quite differently on the micro-level (e.g. burstiness, correlation, and consistency).

Previous work on routing in MANETs has resulted in numerous routing protocols that aim at satisfying constraints such as minimum hop or low energy. Existing routing protocols often fail to discover stable routes between source and sink when route availability is transient, i.e., due to mobile devices switching their network cards into low-power sleep modes whenever no communication is taking place. In this paper, we introduce a stability aware dynamic source routing protocol (SA-DSR) that is capable of predicting the stability (i.e., expiration time) of multiple routes. SA-DSR then selects the route that minimizes hop count while staying available for the expected duration of packet transmission. Comparisons of SA-DSR to the original DSR (Dynamic Source Routing) protocol indicate a significant (up to 60%) increase in route discovery success rate with comparable route establishment and maintenance overheads.

This work is based on the observation that existing energy management techniques for mobile devices, such as dynamic voltage scaling (DVS), are non-cooperative in the sense that they reduce the energy consumption of a single device, disregarding potential consequences for other constraints (e.g., end-to- end deadlines) and/or other devices (e.g., energy consumption on neighboring devices). This paper argues that energy management in distributed real-time systems has to be end-to-end in nature, requiring a coordinated approach among communicating devices. A cooperative distributed energy management technique (Co-DVS) is proposed that: i) adapts and maintains end-to-end latencies within specified timeliness requirements (deadlines); and ii) enhances energy savings at the nodes with the highest pay-off factors that represent the relative benefits or significance of conserving energy at a node. The proposed technique employs a feedback-based approach to dynamically distribute end-to-end slack among the devices based on their pay-off factors.

Streaming real-time applications require the timely distribution of information in mobile ad-hoc and sensor networks. At the same time, such networks must operate energy-efficiently to maximize the lifetime of mobile devices and applications. In multi-hop networks, multiple communication paths between a single sender and receiver can be established, with varying real-time and energy characteristics of each path. This paper introduces the DETOUR (Delay- and Energy- aware mulTi- cOUrse Routing) protocol that applies feedback-driven path diversification, where traffic load is balanced across two or more paths to ensure both timeliness and energy-efficiency. We apply the (m,k) model for firm real-time communication to wireless networks, i.e., the protocol aims to meet at least m end-to- end deadlines out of k packet transmissions, thereby sacrificing additional improvement in latency in order to maximize the lifetime of the network by minimizing energy consumption. The experimental results of this paper show the protocols ability to reduce energy consumptions (up to 35%) while meeting the data streams firm real-time constraints.

Reducing energy consumption is an important consideration in embedded real-time system development. This work examines systems that contain a DVFS managed CPU executing packet producing tasks and a DPM-controlled network interface. We introduce a novel approach to minimize energy consumed by the network resource on such a system, through careful selection of voltage and frequency levels on the CPU. Contrary to existing claims which state that DVFS should not be employed when the CPU is not a significant consumer of energy, we show that our DVFS technique can reduce system energy by as much as 35%, even when the CPU energy consumption is negligible. Furthermore, we motivate the need to balance the CPU and network energy and present two techniques to do so. One is based on off-line analysis and the other is a conservative on-line approach. We then validate the proposed methods using both simulation and an implementation in the Linux kernel

Dynamic voltage scaling (DVS) is a frequently used technique in mobile and embedded systems, aimed at reducing the energy consumption of mobile processors. In systems with a discrete number of frequency levels, existing dual-speed DVS approaches compute an optimal theoretical CPU speed and approximate it by choosing the two neighboring discrete speed levels. By comparing experimentally the energy savings attained with different frequency combinations on a mobile platform, this work shows that choosing the two neighboring frequency levels does not necessarily yield the highest energy savings. As a result of the above observation, this work introduces an online approach to dual-speed DVS that a) formulates a model for speed selection based on the workload characteristics of the current task set, b) computes a frequency pair that yields the best possible energy savings for a given taskset and workload

Dynamic voltage and frequency scaling is increasingly being used to reduce the energy requirements of embedded and real-time applications by exploiting idle CPU resources, while still maintaining all application's real-time characteristics. Accurate predictions of task run-times are key to computing the frequencies and voltages that ensure that all tasks' real-time constraints are met. Past work has used feedback-based approaches, where applications' past CPU utilizations are used to predict future CPU requirements. Mispredictions in these approaches can lead to missed deadlines, suboptimal energy savings, or large overheads due to frequent changes to the chosen frequency or voltage. One shortcoming of previous approaches is that they ignore other 'indicators' of future CPU requirements, such as the frequency of I/O operations, memory accesses, or interrupts. This paper addresses the energy consumptions of memory-bound real-time applications via a feedback loop approach, based on measured task run-times and cache miss rates. Using cache miss rates as indicator for memory access rates introduces a more reliable predictor of future task run-times. Even in modern processor architectures, memory latencies can only be hidden partially, therefore, cache misses can be used to improve the run-time predictions by considering potential memory latencies. The results shown in this paper indicate improvements in both the number of deadlines met and the amount of energy saved.

Dynamic voltage scaling (DVS [1]) is a popular technique in energy-aware systems: when a CPU is under-utilized, reduce its speed and voltage, thereby trading off increased execution times with reduced energy costs, while meeting real-time tasks' deadline constraints. However, DVS and other energy-saving techniques are 'selfish' in nature, i.e., they are only concerned with reducing their local energy consumptions, disregarding the consequences their use may have on other devices. Consider two devices A and B, where A captures and compresses video images, sends them to B, where they will be decompressed, processed, and displayed. The latest point in time an image has to be received, processed, and displayed by B denotes an end-to-end deadline (E2E) Td. Figure 1 visualizes the problem: the shaded areas show periods of CPU activity (image processing), with the height of the area indicating the power costs, the arrows denote communications between devices, and the vertical line shows Td for a given image. When both A and B use DVS, their processing times increase, introducing delays that may cause the deadline to be missed. The consequence is that A and B need to negotiate the allowable slow-down (and delay) each device can introduce. This negotiation is driven by the current battery charge levels and the overall goal of the system, e.g., if B is essential to the operation of the distributed system, but at the same time the more energy-constrained device, it should be allowed to fully utilize DVS, while A can utilize DVS only to an extent that does not cause deadlines misses.

Consider the following scenario taken from the mobile and wireless computing domain. Energy has been receiving increasing attention, resulting in a number of different energy management techniques, including Dynamic Voltage Scaling (DVS) [1]. DVS is based on the concept of reducing the speed/voltage of a CPU when it is under-utilized, thereby reducing its power consumption while increasing the task execution times. In real-time systems, DVS algorithms have to compute energy-saving speed/voltage levels while ensuring that task deadlines are met. The figure below visualizes this problem for two devices A and B, where shaded areas indicate times of power consumption caused by the CPU and arrows indicate communication between two devices. The vertical line indicates the end-to-end deadline Td, i.e., the processing and communication steps of both devices A and B have to be concluded before Td. Typical examples for such scenarios are sensor networks with in-network data aggregation or mobile multimedia. For example, device A captures an image, compresses it, and sends it to B, which decompresses and displays it. The figure shows the same scenario twice, once without DVS and once with DVS. In the latter case, both devices reduce their energy overheads, but device B also misses its deadline. As a consequence, either one or both devices have to increase their clock frequencies to ensure that the deadline is met, increasing their energy costs. However, if both devices operate in isolation, A -- unaware of the missed end-to-end deadline -- would continue to operate at its low speed, while B has to increase its speed. Now assume that B is essential to the operation of the distributed system, but at the same time it is also the more energy-constrained device (e.g., the remaining battery lifetime is lower than A's). In this case, it is desirable that A reduces its use of DVS, such that B can continue to fully exploit its DVS capability to prolong its battery life. To achieve that, it is necessary for A and B to negotiate limits to the use of DVS, e.g., by introducing a deadline on A, called virtual deadline Tv (rightmost graph in above figure). This deadline forces A to run faster (limiting the extent to which A can exploit DVS), but allowing B to fully utilize DVS.

To meet end users' quality-of-service (QoS) requirements, online quality management for multimedia applications must include appropriate allocation of the underlying computing platform's resources. Previous work has developed novel operating system (OS) functionality for dynamic QoS management, including multimedia or real-time CPU schedulers and OS extensions for online performance monitoring and for adaptations, as well as QoS-aware applications that adapt their behavior to gain additional benefits from such functionality. This article describes a general OS mechanism that may be used to implement a wide variety of online quality management functions. ECalls is a communication mechanism that implements multiple cross-domain calling conventions that can be customized to the quality management needs of applications. The ECalls mechanism is based on the notions of events, event channels, and event handlers. Using events, applications can share relevant QoS attributes with OS services, and OS-level resource management services can efficiently provide monitoring data to target applications or application managers. Dynamically generated event handlers can be used to customize event delivery to meet diverse application needs, for example, to achieve high scalability for Web servers or small jitter for real-time data delivery.

Summary form only given. Heterogeneous computing platforms constitute a challenging execution environment for distributed applications. This article presents a 'systems' view of effective platform usage, by demonstrating the need for application software to be continuously 'aware' of the resources currently available on their underlying heterogeneous computing platforms. Our approach to the implementation of resource awareness is one that (1) provides a 'thin' middleware layer of resource aware services that permit applications to react to changes in resource availability and resources to be managed in accordance with application needs, and that (2) develops compiler- and application-level techniques for dynamic 'service morphing', the goal being to make it easy for application-level services to adjust to runtime changes in application needs or in platform resources. The specific results presented in this article are focused on large-data applications, for which the IQ-services "morphing" layer implements the data manipulations necessary to permit wide-area interactive or multimedia applications to proceed smoothly despite variations in underlying computing and network resources. Experimental results demonstrate substantial performance improvements attained by coordinating network-level with service-level adaptations of the data being transported and by permitting end users to dynamically deploy and use application-specific services for manipulating data in ways suitable for their current needs.

In distributed systems, transcoding techniques have been used to customize multimedia objects, utilizing trade-offs between the quality and sizes of these objects to provide differentiated services to clients. Our research uses transcoding techniques in wireless systems to customize video streams to the requirements of users, while minimizing the energy costs. We introduce an approach to dynamically determine which transcoders to execute and where to execute them (e.g., client or server). The goal is to select appropriate transcoders (a) to provide clients with the quality of service they desire while (b) minimizing the energy consumption of the end-hosts in accordance with application-specific global energy management directives. This paper investigates sample transcoder functions for video streaming on handheld devices and introduces a mechanism for selecting the most appropriate transcoders and transcoder parameters.

Sleep modes of wireless network cards are used to switch these cards into low-power state when idle, but large timeout periods and frequent wake-ups can reduce the utility of this approach. Modern processors offer the ability to switch CPU voltages or clock frequencies and therefore reduce CPU energy consumption, however, that can reduce the sleep durations of a network device, adversely affecting the achievable energy savings. This paper describes an approach in which multiple resource managers cooperate to reduce a mobile device's energy consumption. This system-level approach is based on the integrated management of a real-time CPU scheduler, the frequency scaling capabilities of a modern processor, a QoS packet scheduler, and the low-power sleep mode of a wireless network card.

We describe an algorithm for scheduling packets in real-time multimedia data streams. Common to these classes of data streams are service constraints in terms of bandwidth and delay. However, it is typical for real-time multimedia streams to tolerate bounded delay variations and, in some cases, finite losses of packets. We have therefore developed a scheduling algorithm that assumes streams have window-constraints on groups of consecutive packet deadlines. A window-constraint defines the number of packet deadlines that can be missed (or, equivalently, 'must be met) in a window of deadlines for consecutive packets in a stream. Our algorithm, called dynamic window-constrained scheduling (DWCS), attempts to guarantee no more than re out of a window of y deadlines are missed for consecutive packets in real-time and multimedia streams. Using DWCS, the delay of service to real-time streams is bounded, even when the scheduler is overloaded. Moreover, DWCS is capable of ensuring independent delay bounds on streams, while, at the same time, guaranteeing minimum bandwidth utilizations over tunable and finite windows of time. We show the conditions under which the total demand for bandwidth by a set of window-constrained streams can exceed 100 percent and still ensure all window-constraints are met. In fact, we show how it is possible to strategically skip certain deadlines in overload conditions, yet fully utilize all available link capacity and guarantee worst-case per-stream bandwidth and delay constraints. Finally, we compare DWCS to the "distance-based" priority (DBP) algorithm, emphasizing the trade-offs of both approaches.

Monitoring the resources of distributed systems is essential to the successful deployment and execution of grid applications, particularly when such applications have well-defined QoS requirements. The dproc system-level monitoring mechanisms implemented for standard Linux kernels have several key components. First, utilizing the familiar /proc filesystem, dproc extends this interface with resource information collected from both local and remote hosts. Second, to predictably capture and distribute monitoring information, dproc uses a kernel-level group communication facility, termed KECho, which is based on events and event channels. Third and the focus of this paper is dproc's run-time customizability for resource monitoring, which includes the generation and deployment of monitoring functionality within remote operating system kernels. Using dproc, we show that: (a) data streams can be customized according to a client's resource availabilities (dynamic stream management); (b) by dynamically varying distributed monitoring (dynamic filtering of monitoring information), appropriate balance can be maintained between monitoring overheads and application quality; and (c) by performing monitoring at kernel-level, the information captured enables decision making that takes into account the multiple resources used by applications.

This paper presents Q-fabric, which is a set of lightweight, kernel-level abstractions for cooperative, distributed resource management and system/application adaptation. The basis of Q-fabric is its kernel-level, anonymous, asynchronous event service. With this mechanism, (1) applications can monitor and manage the local and remote resources they are using, (2) system-level resource managers can customize their actions to meet the needs of individual applications, and (3) policies can be developed that combine application adaptation with distributed resource management. Results presented in this paper demonstrate the Q-fabric's ability to effectively adapt and manage the resources of a distributed multimedia application. In this application, media streams are adapted at application-level via data down-sampling, and their resources are managed at system-level (e.g., task scheduling) to cope with run-time variations in resource availability. The Q-fabric is implemented as kernel modules on standard Linux platforms.

Distributed multimedia applications require support from the underlying operating system to achieve and maintain their desired Quality of Service (QoS). This has led to the creation of novel task and message schedulers and to the development of QoS mechanisms that allow applications to explicitly interact with relevant operating system services. However, the task scheduling techniques developed to date are not well equipped to take advantage of such interactions. As a result, important events such as position update messages in virtual environments may be ignored. If a CPU scheduler ignores these events, players will experience a lack of responsiveness or even inconsistencies in the virtual world. This paper argues that real-time and multimedia applications can benefit from coordinatedel event delivery mechanism, termed ECalls, that supports such coordination. We then show ECalls's ability to reduce variations in inter-frame times for media streams.

Operating system enhancements to support real-time and multimedia appl ications often include specializations and extensions of kernel functionality, as with the kernel HTTP daemon (khttpd) in Linux, for instance. To enable efficient and flexible interactions of such extensions with user-level functionality, we have developed ECalls, a lightweight, bidirectional kernel/user event delivery facility, which not only supports the timely delivery of events, but it also reduces the cost and frequency of kernel/user boundary crossings. ECalls is a communication tool that allows (a) kernel extensions to register their offered services and (b) applications to register their interest in these services. Using ECalls, applications use lightweight system calls to generate events, while kernel extensions raise real-time signals or invoke handler functions (residing in either user or kernel space), or they may use kernel threads to handle events on behalf of applications. ECalls can also influence the CPU scheduler such that a process with pending events is given preference over other processes. To demonstrate its utility, this paper implements an I/O event delivery mechanism using ECalls. This mechanism is shown to improve the performance of two applications: a distributed video player and a web server.

Describes how dynamic window-constrained scheduling (DWCS) can guarantee real-time service to packets from multiple streams with different performance objectives. We show that: (1) DWCS can guarantee that no more than x packets miss their deadlines for every y consecutive packets requiring service, as long as the minimum aggregate bandwidth requirement of all real-time packet streams does not exceed the available bandwidth; (2) using DWCS, the delay of service to real-time packer streams is bounded even when the scheduler is overloaded; (3) DWCS can ensure that the delay bound of any given stream is independent of other streams; and (4) a fast response time for best-effort packet streams, in the presence of real-time packet streams, is possible. Furthermore, if a feasible schedule exists, each stream is guaranteed a minimum fraction of available bandwidth over a finite window of time.