Radio frequency (RF) communication has become essential for critical infrastructure including healthcare, transportation, and government services. While numerous ML models have been developed for RF security, many require cloud computing due to computational demands, introducing latency and privacy concerns. With advances in AI edge computing, there is growing opportunity to deploy models directly on edge devices. This work presents the first benchmark study evaluating ML models for RF anomaly detection on the NVIDIA Jetson Orin Nano platform.

We present MATRICS, a traffic-aware multi-agent reinforcement learning (MARL)-based intelligent lane-change system designed for autonomous vehicles (AVs). While existing research primarily focuses on enhancing the local impact of the ego vehicle’s lane-change decisions, MATRICS stands out by optimizing both local and global performance, i.e., aiming not only to improve the traffic efficiency, driving safety, and driver comfort of the ego vehicle, but also to enhance overall traffic flow within a designated road segment. Through an extensive review of the transportation literature, we construct a novel state space integrating local traffic information collected from surrounding vehicles and global traffic data obtained from roadside units (RSUs). We develop a reward function to guide judicious lane-change decisions, considering both ego vehicle performance and traffic flow enhancement. Our local density-aware multi-agent double deep Q-network (DDQN) algorithm facilitates effective cooperation among agents in executing lane-change maneuvers. Simulation results demonstrate MATRICS’ superior performance across metrics of traffic efficiency, driving safety, and driver comfort in comparison with a state-of-the-art MARL model.

The vehicle routing problem with drones (VRPD) involves determining the optimal routes for trucks and drones to collaboratively deliver parcels to customers, aiming to minimize total operational costs. While various heuristic algorithms have been developed to address the problem, existing solutions are built based on simplistic cost models, overlooking the temporal dynamics of the costs, which fluctuate depending on the dynamically changing traffic conditions. In this paper, we present a novel problem called the vehicle routing problem with drones under dynamically changing traffic conditions (Adapt-VRPD) to address the limitation of existing VRPD solutions. We design a novel cost model that factors in the actual travel distance and projected travel time, computed using a machine learning-driven travel time prediction algorithm. A variable neighborhood descent (VND) algorithm is developed to find the optimal truck-drone routes under the dynamics of traffic conditions through incorporation of the travel time prediction model. A simulation study was performed to compare our algorithm with a state-of-the-art VRPD heuristic. Our algorithm outperformed the benchmark, reducing the average and maximum discrepancies from the actual cost by 37.6% and 27.6%, respectively, across various delivery scenarios.

The Vehicle Routing Problem with Drones (VRPD) seeks to optimize the routing paths for both trucks and drones, where the trucks are responsible for delivering parcels to customer locations, and the drones are dispatched from these trucks for parcel delivery, subsequently being retrieved by the trucks. Given the NP-Hard complexity of VRPD, numerous heuristic approaches have been introduced. However, improving solution quality, the definition of which can vary depending on various heuristic approaches, e.g., the total operation time, remain significant challenges. In this paper, we conduct a comprehensive examination of heuristic methods designed for solving VRPD, distilling and standardizing them into core elements. We then develop a novel reinforcement learning (RL) framework that is seamlessly integrated with the heuristic solution components, establishing a set of universal principles for incorporating the RL framework with heuristic strategies in an aim to improve both the solution quality and computation speed, regardless of how the solution quality is defined. This integration has been applied to a state-of-the-art heuristic solution for VRPD, showcasing the substantial benefits of incorporating the RL framework. Our evaluation results demonstrated that the heuristic solution incorporated with our RL framework not only elevated the quality of solutions but also achieved rapid computation speeds, especially when dealing with extensive customer locations.

Cybersecurity is critical for national infrastructure, governments at all levels, the military, industry, and individual privacy. Both the government and industrial sectors in the U.S. foresee a substantial need for a proficient cybersecurity workforce. To tackle this challenge, the National Security Agency (NSA) and the National Science Foundation (NSF) jointly sponsored the GenCyber program with the goal of sparking K-12 students' interest in cybersecurity and enhancing their knowledge of cybersecurity practices and safe online behavior. In support of the GenCyber program, this paper presents the first-of-its-kind autonomous R/C car-based cybersecurity summer camp for high school students, featuring an inclusive curriculum that seamlessly integrates concepts of machine learning (ML)/artificial intelligence (AI) and cybersecurity through the lens of an important ML application-autonomous vehicles. Beginning with an introduction to basic cybersecurity topics and technical concepts, the curriculum enables students to explore ML through hands-on experiences such as collecting front-camera images and training an autonomous driving ML model. Additionally, a series of engaging cybersecurity projects are developed focusing on secure shell (SSH) password cracking, buffer overflow attacks, and man-in-the-middle attacks. These projects are designed to launch various cybersecurity attacks against the students' self-built autonomous driving models, enhancing the teaching effectiveness and awareness of cybersecurity. Our pre- and post-camp surveys demonstrate that the camp significantly boosted students' confidence in computing, cybersecurity, and ML/AI.

The pedestrian crossing intention prediction problem is to estimate whether or not the target pedestrian will cross the street. State-of-the-art techniques heavily depend on visual data acquired through the front camera of the ego-vehicle to make a prediction of the pedestrian's crossing intention. Hence, the efficiency of current methodologies tends to decrease notably in situations where visual input is imprecise, for instance, when the distance between the pedestrian and ego-vehicle is considerable or the illumination levels are inadequate. To address the limitation, in this paper, we present the design, implementation, and evaluation of the first-of-its-kind pedestrian crossing intention prediction model based on integration of motion sensor data gathered through the smartwatch (or smartphone) of the pedestrian. We propose an innovative machine learning framework that effectively integrates motion sensor data with visual input to enhance the predictive accuracy significantly, particularly in scenarios where visual data may be unreliable. Moreover, we perform an extensive data collection process and introduce the first pedestrian intention prediction dataset that features synchronized motion sensor data. The dataset comprises 255 video clips that encompass diverse distances and lighting conditions. We trained our model using the widely-used JAAD and our own datasets and compare the performance with a state-of-the-art model. The results demonstrate that our model outperforms the current state-of-the-art method, particularly in cases where the distance between the pedestrian and the observer is considerable (more than 70 meters) and the lighting conditions are inadequate.

A platoon refers to a group of vehicles traveling together in very close proximity using automated driving technology. Owing to its immense capacity to improve fuel efficiency, driving safety, and driver comfort, platooning technology has garnered substantial attention from the autonomous vehicle research community. Although highly advantageous, recent research has uncovered that an excessively small intra-platoon gap can impede traffic flow during highway on-ramp merging. While existing control-based methods allow for adaptation of the intra-platoon gap to improve traffic flow, making an optimal control decision under the complex dynamics of traffic conditions remains a challenge due to the massive computational complexity. In this paper, we present the design, implementation, and evaluation of a novel reinforcement learning framework that adaptively adjusts the intra-platoon gap of an individual platoon member to maximize traffic flow in response to dynamically changing, complex traffic conditions for highway on-ramp merging. The framework's state space has been meticulously designed in consultation with the transportation literature to take into account critical traffic parameters that bear direct relevance to merging efficiency. An intra-platoon gap decision making method based on the deep deterministic policy gradient algorithm is created to incorporate the continuous action space to ensure precise and continuous adaptation of the intra-platoon gap. An extensive simulation study demonstrates the effectiveness of the reinforcement learning-based approach for significantly improving traffic flow in various highway on-ramp merging scenarios.

Drone-based last-mile delivery is an emerging technology that uses drones loaded onto a truck to deliver parcels to customers. In this paper, we introduce a fully automated system for drone-based last-mile delivery through incorporation of autonomous vehicles (AVs). A novel problem called the autonomous vehicle routing problem with drones (A-VRPD) is defined. A-VRPD is to select AVs from a pool of available AVs based on crowd sourcing, assign selected AVs to customer groups, and schedule routes for selected AVs to optimize the total operational cost. We formulate A-VRPD as a Mixed Integer Linear Program (MILP) and propose an optimization framework to solve the problem. A greedy algorithm is also developed to significantly improve the running time for large-scale delivery scenarios. Extensive simulations were conducted taking into account real-world operational costs for different types of AVs, traveled distances calculated considering the real-time traffic conditions using Google Map API, and varying load capacities of AVs. We evaluated the performance in comparison with two different state-of-the-art solutions: an algorithm designed to address the traditional vehicle routing problem with drones (VRP-D), which involves human-operated trucks working in tandem with drones to deliver parcels, and an algorithm for the two echelon vehicle routing problem (2E-VRP), wherein parcels are first transported to satellite locations and subsequently delivered from those satellites to the customers. The results indicate a substantial increase in profits for both the delivery company and vehicle owners compared with the state-of-the-art algorithms.

The Bluetooth special interest group (Bluetooth SIG) has introduced a new feature for highly accurate localization called Direction Finding in the Bluetooth core specification 5.1. Since this new localization feature is relatively new, despite the significant interest of industry and academia in the accurate positioning of Bluetooth devices/tags, there are only a handful of experimental studies conducted to evaluate the performance of the new technology. Furthermore, these experimental studies are constrained to only indoor environments or performed with hardware emulation of Bluetooth 5.1 via Universal Software Radio Peripherals (USRPs). To address these limitations, in this paper, we perform an experimental study on the positioning accuracy of Direction Finding using COTS Bluetooth 5.1 devices in both indoor and outdoor environments to provide insights on the performance gap between these heterogeneous experimental settings. Our results demonstrate that the average angular error in an outdoor environment is 0.28◦, significantly improving the angular error measured in an indoor environment by 73%. It is also demonstrated that the average positioning accuracy measured in an outdoor environment is 22cm which is 39.7% smaller than that measured in an indoor environment.

Low-Power Wide-Area Network (LPWAN) is an emerging communication standard for Internet of Things (IoT) that has strong potential to support connectivity of a large number of roadside sensors with an extremely long communication range. However, the high operation cost to manage such a large-scale roadside sensor network remains as a significant challenge. In this article, we propose Low Operation-Cost LPWAN (LOC-LPWAN), a novel optimization framework that is designed to reduce the operation cost using the cross-technology communication (CTC). LOC-LPWAN allows roadside sensors to offload sensor data to passing vehicles that in turn forward the data to a LPWAN server using CTC aiming to reduce the data subscription cost. LOC-LPWAN finds the optimal communication schedule between sensors and vehicles to maximize the throughput given an available budget. Furthermore, LOC-LPWAN optimizes the fairness among sensors by preventing certain sensors from dominating the channel for data transmission. LOC-LPWAN can also be configured to ensure that data packets are received within a specific time bound. Extensive numerical analysis performed with real-world taxi data consisting of 40 vehicles with 24-hour trajectories demonstrate that LOC-LPWAN reduces the cost by 50% compared with the baseline approach where no vehicle is used to relay packets. The results also show that LOC-LPWAN improves the throughput by 72.6%, enhances the fairness by 65.7%, and reduces the delay by 28.8% compared with a greedy algorithm given the same amount of budget.

Vehicle platooning is an automated driving technology that enables a group of vehicles to travel very closely together as a single unit to improve fuel efficiency and driving safety. These advantages of platooning attract huge interests from academia and industry, especially logistics companies that can utilize the platooning technology for their heavy-duty trucks due to the huge cost savings. In this paper, we demonstrate that existing platooning solutions, however, fail to support formation of a ‘long’ platoon consisting of many vehicles especially long-body heavy-duty trucks due to the limited range of vehicle-to-vehicle communication such as DSRC and device-to-device communication for C-V2X. To address this problem, we proposeL-Platooning, the first platooning protocol that enables seamless, reliable, and rapid formation of a long platoon. We introduce a novel concept calledVirtual Leaderthat refers to a vehicle that acts as a platoon leader to extend the coverage of the original platoon leader. A virtual leader election algorithm is developed to effectively designate a virtual leader based on the novel metric called theVirtual Leader Quality Index (VLQI)which quantifies the effectiveness of a vehicle serving as a platoon leader. We also develop mechanisms forL-Platooningto support the vehicle join and leave maneuvers specifically for a long platoon. Through extensive simulations, we demonstrate thatL-Platooningenables vehicles to form a long platoon effectively by allowing them to maintain the desired inter-vehicle distance accurately. We also show thatL-Platooninghandles seamlessly the vehicle join and leave maneuvers for a long platoon.

We present a novel adaptive cruise control (ACC) system namely SAINT-ACC: {S}afety-{A}ware {Int}elligent {ACC} system (SAINT-ACC) that is designed to achieve simultaneous optimization of traffic efficiency, driving safety, and driving comfort through dynamic adaptation of the inter-vehicle gap based on deep reinforcement learning (RL). A novel dual RL agent-based approach is developed to seek and adapt the optimal balance between traffic efficiency and driving safety/comfort by effectively controlling the driving safety model parameters and inter-vehicle gap based on macroscopic and microscopic traffic information collected from dynamically changing and complex traffic environments. Results obtained through over 12,000 simulation runs with varying traffic scenarios and penetration rates demonstrate that SAINT-ACC significantly enhances traffic flow, driving safety and comfort compared with a state-of-the-art approach.

An Adaptive Cruise Control (ACC) system allows vehicles to maintain a desired headway distance to a preceding vehicle automatically. It is increasingly adopted by commercial vehicles. Recent research demonstrates that the effective use of ACC can improve the traffic flow through the adaptation of the headway distance in response to the current traffic conditions. In this paper, we demonstrate that a state-of-the- art intelligent ACC system performs poorly on highways with ramps due to the limitation of the model-based approaches that do not take into account appropriately the traffic dynamics on ramps in determining the optimal headway distance. We then propose a dynamic adaptive cruise control system (D- ACC) based on deep reinforcement learning that adapts the headway distance effectively according to dynamically changing traffic conditions for both the main road and ramp to optimize the traffic flow. Extensive simulations are performed with a combination of a traffic simulator (SUMO) and vehicle-to- everything communication (V2X) network simulator (Veins) under numerous traffic scenarios. We demonstrate that D-ACC improves the traffic flow by up to 70% compared with a state- of-the-art intelligent ACC system in a highway segment with a ramp.

Location service is one of the most widely used features on a smartphone. More and more apps are built based on location services. As such, demand for accurate positioning is ever higher. Mobile brand Xiaomi has introduced Mi 8, the world's first smartphone equipped with a dual-frequency GNSS chipset which is claimed to provide up to decimeter-level positioning accuracy. Such unprecedentedly high location accuracy brought excitement to industry and academia for navigation research and development of emerging apps. On the other hand, there is a significant knowledge gap on the energy efficiency of smartphones equipped with a dual-frequency GNSS chipset. In this paper, we bridge this knowledge gap by performing an empirical study on power consumption of a dual-frequency GNSS phone. To the best our knowledge, this is the first experimental study that characterizes the power consumption of a smartphone equipped with a dual-frequency GNSS chipset and compares the energy efficiency with a single-frequency phone. We demonstrate that a smartphone with a dual-frequency GNSS chipset consumes 37% more power on average outdoors, and 28% more power indoors, in comparison with a singe-frequency GNSS phone.

Unmanned aerial vehicles (UAVs) have been widely used in many applications. The limited flight time of UAVs, however, still remains as a major challenge. Although numerous approaches have been developed to recharge the battery of UAVs effectively, little is known about optimal methodologies to deploy charging stations. In this paper, we address the charging station deployment problem with an aim to find the optimal number and locations of charging stations such that the system performance is maximized. We show that the problem is NP-Hard and propose UBAT, a heuristic framework based on the ant colony optimization (ACO) to solve the problem. Additionally, a suite of algorithms are designed to enhance the execution time and the quality of the solutions for UBAT. Through extensive simulations, we demonstrate that UBAT effectively performs multi-objective optimization of generation of UAV trajectories and placement of charging stations that are within 8.3% and 7.3% of the true optimal solutions, respectively.

A traffic monitoring system (TMS) is an integral part of Intelligent Transportation Systems (ITS). It is an essential tool for traffic analysis and planning. One of the biggest challenges is, however, the high cost especially in covering the huge rural road network. In this paper, we propose to address the problem by developing a novel TMS called DeepWiTraffic. DeepWiTraffic is a low-cost, portable, and non-intrusive solution that is built only with two WiFi transceivers. It exploits the unique WiFi Channel State Information (CSI) of passing vehicles to perform detection and classification of vehicles. Spatial and temporal correlations of CSI amplitude and phase data are identified and analyzed using a machine learning technique to classify vehicles into five different types: motorcycles, passenger vehicles, SUVs, pickup trucks, and large trucks. A large amount of CSI data and ground-truth video data are collected over a month period from a real-world two-lane rural roadway to validate the effectiveness of DeepWiTraffic. The results validate that DeepWiTraffic is an effective TMS with the average detection accuracy of 99.4% and the average classification accuracy of 91.1% in comparison with state-of-the-art non-intrusive TMSs.

Walking speed estimation is an essential component of mobile apps in various fields such as fitness, transportation, navigation, and health-care. Most existing solutions are focused on specialized medical applications that utilize body-worn motion sensors. These approaches do not serve effectively the general use case of numerous apps where the user holding a smartphone tries to find his or her walking speed solely based on smartphone sensors. However, existing smartphone-based approaches fail to provide acceptable precision for walking speed estimation. This leads to a question: is it possible to achieve comparable speed estimation accuracy using a smartphone over wearable sensor based obtrusive solutions? We find the answer from advanced neural networks. In this paper, we present DeepWalking, the first deep learning- based walking speed estimation scheme for smartphone. A deep convolutional neural network (DCNN) is applied to automatically identify and extract the most effective features from the accelerometer and gyroscope data of smartphone and to train the network model for accurate speed estimation. Experiments are performed with 10 participants using a treadmill. The average root- mean-squared-error (RMSE) of estimated walking speed is 0.16m/s which is comparable to the results obtained by state-of- the-art approaches based on a number of body- worn sensors (i.e., RMSE of 0.11m/s). The results indicate that a smartphone can be a strong tool for walking speed estimation if the sensor data are effectively calibrated and supported by advanced deep learning techniques.

With ever increasing number of vehicles, shortage of parking space is becoming a serious problem. Going to shopping, school, and workplace can be a headache as finding an available parking spot is getting harder causing wasted time and gas. In this paper, we present WiParkFind: a low-cost, non-intrusive, and real- time parking occupancy monitoring system based on WiFi signals. The channel state information (CSI) of received WiFi signals is analyzed by using a machine learning technique to capture distinctive characteristics of CSI data that are strongly correlated with the number of empty parking slots in order to detect whether there is an empty slot, and how many empty slots are available. Compared with contemporary approaches based on magnetic sensors deployed on individual parking slots, WiParkFind utilizes low-cost off- the-shelf WiFi devices, dramatically reducing the cost for purchasing, installing, and maintaining a large number of sensors, and backend server systems. A proof-of-concept system of WiParkFind was developed and deployed in a department parking lot. The results demonstrate that the average classification accuracy of WiParkFind over a week of data collection is 78.2%, and the accuracy is improved to 90.8% with a tolerance of one empty slot.

The traffic monitoring system is an imperative tool for traffic analysis and transportation planning. In this paper, we present WiTraffic: the first WiFi-based traffic monitoring system. Compared with existing solutions, it is non-intrusive, cost- effective, and easy-to-deploy. Unique WiFi Channel State Information (CSI) patterns of passing vehicles are captured and analyzed to effectively perform vehicle classification, lane detection, and speed estimation. A machine learning technique is adopted to train vehicle classification models and efficiently categorize vehicles. An Earth Mover's Distance (EMD)-based vehicle lane detection algorithm and vehicle speed estimation mechanism are proposed to further utilize WiFi CSI to identify the lane in which a vehicle is located and to estimate the vehicle speed. We implemented WiTraffic with off-the-shelf WiFi devices and performed real-world experiments with over a week of field data collection in both local roads and highways. The results show that the mean classification accuracy, lane detection accuracy for both local road and highway settings are around 96%, and 95%, respectively. The average root-mean- square error (RMSE) of the proposed CSI-based speed estimation method on a highway was 5mph in our experimental settings.

With ever-increasing number of car-mounted electronic devices that are accessed, managed, and controlled with smartphones, car apps are becoming an important part of the automotive industry. Audio classification is one of the key components of car apps as a front-end technology to enable human-app interactions. Existing approaches for audio classification, however, fall short as the unique and time-varying audio characteristics of car environments are not appropriately taken into account. Leveraging recent advances in mobile sensing technology that allow for effective and accurate driving environment detection, in this paper, we develop an audio classification framework for mobile apps that categorizes an audio stream into music, speech, speech+music, and noise, adaptably depending on different driving environments. A case study is performed with four different driving environments, i.e., highway, local road, crowded city, and stopped vehicle. More than 420 minutes of audio data are collected including various genres of music, speech, speech+music, and noise from the driving environments. The results demonstrate that the proposed approach improves the average classification accuracy by up to 166%, and 64% for speech, and speech+music, respectively, compared with a non-adaptive approach in our experimental settings.

Explosive growth in the number of portable devices like smartphones, tablets, and smart-watches has escalated the demand for localization-based services, spurring development of numerous indoor localization techniques. Especially, widespread deployment of wireless LANs prompted ever increasing commercial interests in WiFi-based indoor localization mechanisms. However, a critical shortcoming of such localization techniques is that collecting WiFi fingerprints of an entire target area is an extremely time and labor intensive task. In this paper, we propose to automate this WiFi fingerprint collection process using a group of nano-scale unmanned aerial vehicles. Since these vehicles explore a 3D space, the WiFi fingerprints of a 3D space can be obtained without user intervention. The proposed system is implemented on a commercially available miniature open-source quadcopter platform by integrating a contemporary WiFi-fingerprint-based localization system. Experimental results demonstrate that the localization error is about 2m, which exhibits only about 20cm of accuracy degradation compared with manual WiFi fingerprint survey methods.

In the past decade, we have witnessed explosive growth in the number of low-power embedded and Internet-connected devices, reinforcing the new paradigm, Internet of Things (IoT). The low power wide area network (LPWAN), due to its long-range, low-power and low-cost communication capability, is actively considered by academia and industry as the future wireless communication standard for IoT. However, despite the increasing popularity of `mobile IoT', little is known about the suitability of LPWAN for those mobile IoT applications in which nodes have varying degrees of mobility. To fill this knowledge gap, in this paper, we conduct an experimental study to evaluate, analyze, and characterize LPWAN in both indoor and outdoor mobile environments. Our experimental results indicate that the performance of LPWAN is surprisingly susceptible to mobility, even to minor human mobility, and the effect of mobility significantly escalates as the distance to the gateway increases. These results call for development of new mobility-aware LPWAN protocols to support mobile IoT.

Traffic jams often occur without any obvious reasons such as traffic accidents, roadwork, or closed lanes. Under moderate to high traffic density, minor perturbations to traffic flow (e.g., a strong braking motion) are easily amplified into a wave of stop-and-go traffic. This is known as a phantom jam. In this paper, we aim to mitigate phantom jams leveraging the three-phase traffic theory and vehicle-to-vehicle (V2V) communication. More specifically, an efficient phantom jam control protocol is proposed in which a fuzzy inference system is integrated with a V2V-based phantom jam detection algorithm to effectively capture the dynamics of traffic jams. Per-lane speed difference under traffic congestion is taken into account in the protocol design, so that a phantom jam is controlled separately for each lane, improving the performance of the proposed protocol. We implemented the protocol in the Jist/SWAN traffic simulator. Simulations with artificially generated traffic data and real-world traffic data collected from vehicle loop detectors on Interstate 880, California, USA, demonstrate that our approach has by up to 9% and 4.9% smaller average travel times (at penetration rates of 10%) compared with a state-of-the-art approach, respectively.

We present WiTraffic: the first WiFi-based traffic monitoring system. The unique WiFi Channel State Information (CSI) patterns of passing vehicles are captured and analyzed to perform vehicle classification. We implemented WiTraffic with off-the-shelf WiFi devices and performed real-world experiments with over a week of field data collection. The results show that the classification accuracy is around 96%.

Fatal accidents occur frequently on low-volume rural roads, and the accident rates are up to 4 times higher at curves. It is thus of paramount importance to perform road inventory of rural roads to develop safety plans. However, most states in U.S. face a challenge to maintain a database for low-volume rural roads due to limited funds for road inventory. In this paper, we propose to significantly reduce the cost for road inventory specifically focusing on horizontal curve detection by developing a mobile road inventory system based on off-the-shelf smartphones. The proposed system is capable of accurately detecting various kinds of horizontal curves by synthesizing heterogeneous smartphone sensor data to generate curve models by exploiting a machine learning technique. We implemented the system on iOS-based smartphones and tested with more than 400-miles of field data. We demonstrate that the proposed system achieves a median of 93.8% curve identification accuracy with a median of 5% false positive rates.

In this article, we present RE2MR, the first hybrid multicast routing protocol that builds on the strengths of existing topology-based, hierarchical and geographic multicast solutions, while addressing their limitations. In RE2MR, the multicast path search problem is formulated as the capacitated concentrator location problem (CCLP) which yields the network topology that minimizes the sum of path lengths from the multicast root to multicast members. Furthermore, its trajectory-based lightweight hole detection (THLD) discovers deployment area irregularities (i.e., network holes) that affect its solution and autonomously take them into account to generate updated routing paths, and its Energy-efficient Packet Forwarding (EPF) and Multi-level Facility Computation (MFC) reduce computational and communication overheads. We implement RE2MR in TinyOS and evaluate it extensively using TOSSIM for relatively large-scale simulations (400 nodes); we also implement RE2MR on real-hardware and perform experiments on a testbed consisting of 42 TelosB motes. Through the simulations and experiments on real-hardware, we demonstrate that RE2MR reduces the energy consumption by up to 57 percent and the end-to-end delay by up to 8 percent, when compared with the state-of-the-art multicast routing protocols.

Despite the advances in hardware for hand-held mobile devices, resource-intensive applications (e.g., video and image storage and processing or map-reduce type) still remain off bounds since they require large computation and storage capabilities. Recent research has attempted to address these issues by employing remote servers, such as clouds and peer mobile devices. For mobile devices deployed in dynamic networks (i.e., with frequent topology changes because of node failure/unavailability and mobility as in a mobile cloud), however, challenges of reliability and energy efficiency remain largely unaddressed. To the best of our knowledge, we are the first to address these challenges in an integrated manner for both data storage and processing in mobile cloud, an approach we call k-out-of-n computing. In our solution, mobile devices successfully retrieve or process data, in the most energy-efficient way, as long as k out of n remote servers are accessible. Through a real system implementation we prove the feasibility of our approach. Extensive simulations demonstrate the fault tolerance and energy efficiency performance of our framework in larger scale networks.

In this work, we address a fundamental problem of distinguishing the driver from passengers using a fusion of embedded sensors (accelerometers, gyroscopes, microphones, and magnetic sensors) in a smart phone. Compared with the state-of-the-art solutions, a key property of our solution is non-intrusiveness, i.e., enabling accurate driver phone detection without relying on any particular situations, events, and dedicated hardware devices. Our system only utilizes naturally arising driver motions, i.e., sitting down sideways, closing the vehicle door, and starting the vehicle, to determine whether the user enters the vehicle from left or right and whether the user is seated in the front or rear seats.

Geographic routing is well suited for large-scale wireless sensor networks (WSNs) because it is nearly stateless. One important challenge is that network holes may arbitrarily increase the routing path length. Fortunately, recent studies have shown that constant path stretch is achievable using nonlocal information. The constant stretch, however, is possible at the cost of high communication and storage overhead: a source node must complete a “path-setup” process prior to data transmission by exchanging a message with a destination node using a default geographic routing (e.g., GPSR). In this article, we propose the first geographic routing protocol (LVGR) that provably achieves worst-case stretch of Θ (D/γ) (where D is the diameter of the network and γ is the communication range of nodes) with low communication and storage overhead . LVGR represents a hole as a convex hull, the internal structure of which is represented as a local visibility graph . Based on the convex hulls and local visibility graphs, LVGR generates paths with guaranteed stretch. Through theoretical analysis and extensive simulations, we prove the worst-case stretch of LVGR and demonstrate that LVGR reduces communication overhead by up to 97% and storage overhead by up to 60%, compared with the state of the art.

Network simulation is an essential tool for the design and evaluation of wireless network protocols, and realistic channel modeling is essential for meaningful analysis. Recently, several network protocols have demonstrated substantial network performance improvements by exploiting the capture effect, but existing models of the capture effect are still not adequate for protocol simulation and analysis. Physical-level models that calculate the signal-to-interference-plus-noise ratio (SINR) for every incoming bit are too slow to be used for large-scale or long-term networking experiments, and link-level models such as those currently used by the NS2 simulator do not accurately predict protocol performance. In this article, we propose a new technique called the capture modeling algorithm (CAMA) that provides the simulation fidelity of physical-level models while achieving the simulation time of link-level models. We confirm the validity of CAMA through comparison with the empirical traces of the experiments conducted by various numbers of CC1000 and CC2420-based nodes in different scenarios. Our results indicate that CAMA can accurately predict the packet reception, corruption, and collision detection rates of real radios, while existing models currently used by the NS2 simulator produce substantial prediction error.

Resource Allocation has been widely used for improving various performance metrics in wireless networks. Applying resource allocation to a Mobile Ad Hoc Network (MANET), however, is a challenging problem because of dynamic network topology. In this paper, we develop a novel resource allocation scheme designed for MANETs that minimizes the communication cost for accessing distributed resources while improving the reliability by adopting the k-out-of-n system, a widely used technique for reliability control. Specifically, we propose a scheme that allocates resources to n nodes, called service centers, such that the expected energy consumption for nodes to access k service centers out of the n service centers (k⩽n) is minimized. Our scheme accounts for dynamic network topology by estimating the failure probabilities of nodes and monitoring the network for significant topology changes. In addition, an Importance Sampling technique is used to reduce the computation-overhead. To evaluate the performance, we build a mobile distributed file system based on our resource allocation scheme. Through both extensive simulations and real hardware implementation on Smartphones, we show that our resource allocation scheme effectively reduces energy consumption by up to 45% and increases the successful data retrieval rate by up to 50% in comparison with a greedy algorithm.

With the advance of mobile devices, cloud computing has enabled people to access data and computing resources without spatiotemporal constraints. A common assumption is that mobile devices are well connected to remote data centers and the data centers securely store and process data. However, for systems like mobile cloud deployed in infrastructureless dynamic networks (i.e., with frequent topology changes because of node failure/unavailability and mobility), reliability and energy efficiency remain largely unaddressed challenges. To address these issues, we develop the first 'k-out-of-n computing' framework that ensures nodes retrieve or process data stored in mobile cloud with minimum energy consumption as long as k out of n storage/processing nodes are accessible. We demonstrate the feasibility and performance of our framework through both hardware implementation and extensive simulations.

Time is a critical factor in the Urban Search & Rescue operations immediately following natural and man-made disasters. Building on our collaboration with first responders we identify a set of areas for improving response times: victim detection in collapsed buildings, information storage and collection about buildings (collapsed or not), detection of first responder team separation and lost tools, and throughput and latency of data delivered to first responders. In this paper, we present the design (i.e., software/hardware architectures, and the guiding design principles), implementation and realistic evaluation of DistressNet, a system that targets the aforementioned areas for reducing the Urban Search & Rescue response time. DistressNet, built on COTS hardware and on open standards and protocols, pushes complexity that the very diverse Urban Search & Rescue scenarios pose, to user level applications (apps). Apps in DistressNet run on unmodified hardware ranging from smartphones, to motes and wireless routers. For the benefit of the research community, we also share some lessons learned during our experiences in the design, building and evaluation of DistressNet.

In this paper we present RE2MR, an energy efficient and robust multicast routing protocol suitable for large scale real-world WSN deployments. RE2MR, a hybrid multicast protocol, builds on the strengths of existing topology-based, hierarchical and geographic multicast solutions, and addresses their limitations. RE2MR establishes a network topology in which multicast member nodes are connected to the root node via near-optimal multicast routing paths. RE2MR discovers deployment area irregularities (e.g., holes) that affect the optimality of multicast routing and considers them when recomputing the near-optimal solution. RE2MR incurs little computational overhead on forwarding nodes, a negligible communication overhead and ensures reliable multicast packet delivery. We implement RE2MR in Tiny OS and evaluate it extensively using TOSSIM. RE2MR reduces the energy consumption by up to 57% and the end-to-end delay by up to 8%, when compared with state of art solutions.

Wireless Sensor Networks (WSNs) often suffer from disrupted connectivity caused by its numerous aspects such as limited battery power of a node and unattended operation vulnerable to hostile tampering. The disruption of connectivity, often referred to as network cut, leads to ill-informed routing decisions, data loss, and waste of energy. A number of protocols have been proposed to efficiently detect network cuts, they focus solely on a cut that disconnects nodes from the base station. However, a cut detection scheme is truly useful when a cut is defined with respect to multiple destinations (i.e., target nodes), rather than a single base station. Thus, we extend the existing notion of cut detection, and propose an algorithm that enables sensor nodes to autonomously monitor the connectivity to multiple target nodes. We introduce a novel reactive cut detection solution, the Point-to-Point Cut Detection, where given any pair of source and destination, a source is able to locally determine whether the destination is reachable or not. Furthermore, we propose a lightweight proactive cut detection algorithm specifically designed for a small set of target destinations. We prove the effectiveness of the proposed algorithms through extensive simulations.

Geographic routing is well suited for large scale sensor networks deployments, because the per node state it maintains is independent of the network size. However, due to the “local minimum” caused by holes/obstacles, the path stretch of geographic routing can grow as O(c2), where c is the length of the optimal path. Recently, VIGOR, a geographic routing protocol based on the visibility graph, shows that a constant path stretch can be achieved. This, however, is possible with increased overhead. To address this issue, we propose GOAL (Geometric Routing using Abstracted Holes), a routing protocol that provably achieves a constant path stretch, with lower message, space and computational overhead. We develop a novel distributed convex hull construction (DCC) algorithm that compactly describes holes. This compact representation of a hole is leveraged by nodes to make locally optimal routing decisions. Our theoretical analysis proves the constant stretch property and average stretch of GOAL. Through extensive simulations and a hardware implementation, we demonstrate the effectiveness of GOAL and its feasibility for large-scale sensor networks. In our network settings, GOAL reduces the energy consumption by up to 32%, routing table size by an order of magnitude, when compared with VIGOR.

Saving energy while providing end-to-end delay guarantees and robust operation have long been regarded as of paramount importance in real-time adhoc and sensor networks. In this paper we explore how rate-adaptation can save energy in adhoc and sensor networks that have real-time requirements, and how robustness requirements, achieved by multipath routing, affect the achievable energy savings. We formulate the problem of finding the most energy efficient data rate for each link, propose an adaptive data rate selection algorithm, and demonstrate that our scheme can save up to 15 % energy, when compared with state of art, while still meeting the end-to-end delay guarantees.