Hamilton A. Turner

WreckWatch: Automatic Traffic Accident Detection and Notification with Smartphones

Traffic accidents are one of the leading causes of fatalities in the US. An important indicator of survival rates after an accident is the time between the accident and when emergency medical personnel are dispatched to the scene. Eliminating the time between when an accident occurs and when first responders are dispatched to the scene decreases mortality rates by 6%. One approach to eliminating the delay between accident occurrence and first responder dispatch is to use in-vehicle automatic accident detection and notification systems, which sense when traffic accidents occur and immediately notify emergency personnel. These in-vehicle systems, however, are not available in all cars and are expensive to retrofit for older vehicles. This paper describes how smartphones, such as the iPhone and Google Android platforms, can automatically detect traffic accidents using accelerometers and acoustic data, immediately notify a central emergency dispatch server after an accident, and provide situational awareness through photographs, GPS coordinates, VOIP communication channels, and accident data recording. This paper provides the following contributions to the study of detecting traffic accidents via smartphones: (1) we present a formal model for accident detection that combines sensors and context data, (2) we show how smartphone sensors, network connections, and web services can be used to provide situational awareness to first responders, and (3) we provide empirical results demonstrating the efficacy of different approaches employed by smartphone accident detection systems to prevent false positives.

Applying machine learning classifiers to dynamic Android malware detection at scale

The widespread adoption and contextually sensitive nature of smartphone devices has increased concerns over smartphone malware. Machine learning classifiers are a current method for detecting malicious applications on smartphone systems. This paper presents the evaluation of a number of existing classifiers, using a dataset containing thousands of real (i.e. not synthetic) applications. We also present our STREAM framework, which was developed to enable rapid large-scale validation of mobile malware machine learning classifiers.

Smartphone Computing in the Classroom

Smartphone computing platforms are increasingly used for instruction because such devices are becoming as common as traditional desktop computers and they can excite students about computing and networking. This column describes a network application design course at Virginia Tech that uses smartphones as computing platforms. It seeks to provide in-depth descriptions of important and innovative work in education and training in pervasive computing. I welcome your suggestions and comments for future columns.

Bad Parts: Are Our Manufacturing Systems at Risk of Silent Cyberattacks?

Recent cyberattacks have highlighted the risk of physical equipment operating outside designed tolerances to produce catastrophic failures. A related threat is cyberattacks that change the design and manufacturing of a machines part, such as an automobile brake component, so it no longer functions properly. These risks stem from the lack of cyber-physical models to identify ongoing attacks as well as the lack of rigorous application of known cybersecurity best practices. To protect manufacturing processes in the future, research will be needed on a number of critical cyber-physical manufacturing security topics.

Testing variability-intensive systems using automated analysis: an application to Android

Software product lines are used to develop a set of software products that, while being different, share a common set of features. Feature models are used as a compact representation of all the products (e.g., possible configurations) of the product line. The number of products that a feature model encodes may grow exponentially with the number of features. This increases the cost of testing the products within a product line. Some proposals deal with this problem by reducing the testing space using different techniques. However, a daunting challenge is to explore how the cost and value of test cases can be modeled and optimized in order to have lower-cost testing processes. In this paper, we present TESting vAriAbiLity Intensive Systems (TESALIA), an approach that uses automated analysis of feature models to optimize the testing of variability-intensive systems. We model test value and cost as feature attributes, and then we use a constraint satisfaction solver to prune, prioritize and package product line tests complementing prior work in the software product line testing literature. A prototype implementation of TESALIA is used for validation in an Android example showing the benefits of maximizing the mobile market share (the value function) while meeting a budgetary constraint.

Software Frameworks for SDR

This paper describes the state of the art in software frameworks for executing Software Defined Radio (SDR) components. These frameworks are catalyzing drastic changes in signal processing by enabling software engineers and signal processing engineers to work in tandem on core challenges, such as effectively processing large amounts of data in real-time on limited hardware resources. In addition to a historical perspective of this area, we showcase the REDHAWK framework as an example of a modern SDR framework which provides many facilities for distributed SDR deployment.

Multi-core Deployment Optimization Using Simulated Annealing and Ant Colony Optimization

This work introduces a hybrid metaheuristic algorithm for solving the problem of multi-core deployment optimization (MCDO). It extends prior work using Ant Colony Optimization to solve MCDO by initially seeding the pheromone matrix with the output of a Simulated Annealing metaheuristic. This work also removes a number of critical simplifying assumptions from the MCDO model. Across 28, 800 different algorithm inputs, the hybridized algorithm is shown to have a median improvement in makespan time of 7.2% versus the nonhybrid version, as well as a median reduction of 74% in execution time. On a dataset of 50 MCDO problems with known optimal solutions, the median hybrid algorithm solution is 16.5% worse than known optimal.

Verification and Validation of Smartphone Sensor Networks

This paper introduces a subset of mobile wireless sensor networks, called smartphone sensor networks, where large numbers of smartphone devices cooperate to perform sensing tasks. While these emerging networks show high potential, little work has been done on design-time verification and validation to ensure that a designed system will meet the specified goals. This paper introduces Empower, a simulation environment for smartphone sensor networks that simulates smartphone-specific properties of a sensor network, such as data collection policies, and outputs high-level system metrics, such as coverage of the environment being monitored. Experimentation is used to demonstrate that Empower’s ability to derive system design parameters, such as the minimum number of smartphones required for proper operation, or the most appropriate data collection policy for the production environment.

NERD—middleware for IoT human machine interfaces

Industrial control systems (ICS), such as smart grid systems, are frequently composed of hundreds of devices distributed over a large geographic area. While mobile applications have been used with good success in managing ICSs, traditional methods of distributing applications (e.g., app stores) are not well suited to the task of discovering, distributing, and building human machine interfaces (HMIs) for ICS, as the highly individualized and often proprietary individual components of ICSs have vastly different interfaces leading to a need to download hundreds of applications. We propose the No Effort Rapid Development (NERD) middleware framework to address the challenges of in-field HMI discovery, provisioning, communication, and co-evolution with related ICSs. Middleware services offer the ability to simplify on-demand HMI distribution and operation of ICSs. NERD leverages existing ICS device-markers (e.g., QR-codes or RFID tags) or Bluetooth low-energy protocols for rapid cyber-physical discovery and provisioning of HMIs in the field. Device-markers and Bluetooth low-energy protocols have a very limited data capacity and transmission speed, and to achieve on-device storage of HMIs, we propose using a compact data-driven domain-specific language that emphasizes data sources and sinks between the HMI and IC.

Dynamic Tessellation to Ensure K-anonymity

Smart phone-powered data collection systems are rapidly becoming an effective method of gathering field data. One major challenge of using smart phones to collect data is the ability to link smart phone metadata, such as location at a specific time, back to the user -- thereby violating the privacy of that individual. A promising approach to helping ensure user privacy is through geographical k-anonymity, which attempts to ensure that every gathered data reading is geographically indistinguishable from k-1 other readings. The approach helps prevent precise localization of the user or reverse engineering of reported data by leveraging the users known location. This paper presents a dynamic tessellation algorithm for k-anonymity that provides better privacy preservation and data reporting precision than previous static algorithms for k-anonymity. The paper presents empirical results from a real world data set that demonstrate the improvements in privacy provided by the algorithm.