Master of Science, University of Toledo, 0, Engineering (Computer Science)

This thesis presents a study on implementing the multilayer perceptron neural network on the wireless sensor network in a parallel and distributed way. We take advantage of the topological resemblance between the multilayer perceptron and wireless sensor network. A single neuron in the multilayer perceptron neural network is implemented on a wireless sensor node, and the connections between neurons are achieved by the wireless links between nodes. While the computation of the multilayer perceptron benefits from the massive parallelism and the fully distribution when the wireless sensor network is serving as the hardware platform, it is still unknown whether the delay and drop phenomena for message packets carrying neuron outputs would prohibit the multilayer perceptron from getting a decent performance. A simulation-based empirical study is conducted to assess the performance profile of the multilayer perceptron on a number of different problems. Simulation study is performed using a simulator which is developed in-house for the unique requirements of the study proposed herein. The simulator only simulates the major effects of wireless sensor network operation which influence the running of multilayer perceptron. A model for delay and drop in wireless sensor network is proposed for creating the simulator. The setting of the simulation is well defined. Back-Propagation with Momentum learning is employed as the learning algorithms for the neural network. A formula for the number of neurons in the hidden layer neuron is chosen by empirical study. The simulation is done under different network topology and condition of delay and drop for the wireless sensor network. Seven data sets, namely Iris, Wine, Ionosphere, Dermatology, Handwritten Numerical, Isolet and Gisette, with the attributes counts up to 5000 and instances counts up to 7797 are employed to profile the performance. The simulation results are compared with those from the literature and through the non- (open full item for complete abstract)

Committee: Gursel Serpen (Advisor); Mohsin Jamali (Committee Member); Ezzatollah Salari (Committee Member) Subjects: Artificial Intelligence; Computer Science

PhD, University of Cincinnati, 2008, Engineering : Computer Science and Engineering

Wireless Ad Hoc Networks have emerged as an advanced networking paradigm based on collaborative efforts among multiple self-organized wireless communication devices. Without the requirement of a fixed infrastructure support, wireless ad hoc networks can be quickly deployed anywhere at any time when needed. The decentralized nature, minimal configuration and quick deployment of wireless ad hoc networks make them suitable for various applications, from disaster rescue, target tracking to military conflicts. Wireless ad hoc networks can be further categorized into mobile ad hoc networks (MANETs), wireless sensor networks (WSNs), and wireless mesh networks (WMNs) depending on their applications.Security is a big challenge in wireless ad hoc networks due to the lack of any infrastructure support, dynamic network topology, shared radio medium, and resource-constrained wireless users. Most existing security mechanisms applied for the Internet or traditional wireless networks are neither applicable nor suitable for wireless ad hoc network environments. In MANETs, routing security is an extremely important issue, as the majority of the standard routing protocols assume non-hostile environments. Once deployed in a hostile environment and working in an unattended mode, existing routing protocols are vulnerable to various attacks. To address these concerns, we propose an anonymous secure routing protocol for MANETs in this dissertation, which can be incorporated with existing routing protocols and achieve enhanced routing security with minimum additional overheads. In WSNs, key distribution and management is the core issue of any security approaches. Due to extremely resource-constrained sensor nodes and lack of any infrastructure support, traditional public-key based key distribution and management mechanisms are commonly considered as too expensive to be employed in WSNs. In this dissertation, we propose two efficient pairwise key pre-distribution and management mechanisms f (open full item for complete abstract)

Committee: Dharma Agrawal (Committee Chair); Jerome Paul (Committee Member); Wen-Ben Jone (Committee Member); Chia-Yung Han (Committee Member); Ernest Hall (Committee Member) Subjects: Communication; Computer Science

Doctor of Philosophy in Engineering, University of Toledo, 2012, College of Engineering

This dissertation research proposes embedding artificial neural networks into wireless sensor networks in parallel and distributed processing framework to implant intelligence for in-network processing, wireless protocol or application support, and infusion of adaptation capabilities. The goal is to develop in-network "intelligent computation" and "adaptation" capability for wireless sensor networks to improve their functionality, utility and survival aspects. The characteristics of wireless sensor networks bring many challenges, such as the ultra large number of sensor nodes, complex dynamics of network operation, changing topology structure, and the most importantly, the limited resources including power, computation, storage, and communication capability. All these require the applications and protocols running on wireless sensor network to be not only energy-efficient, scalable and robust, but also "adapt" to changing environment or context, and application scope and focus among others, and demonstrate intelligent behavior. The expectation from the research endeavor is to introduce computational intelligence capability for the wireless sensor networks to become adaptive to changes within a variety of operational contexts and to exhibit intelligent behavior. The proposed novel approach entails embedding a wireless sensor network with an artificial neural network algorithm while preserving the parallelism and distributed nature of computations associated with the neural network algorithm. The procedure of embedding an artificial neural network, which may be configured for a problem either at wireless protocol or application levels, into the wireless sensor network hardware platform, which is a parallel and distributed processing system that is composed of a network of motes, is defined. This procedure is demonstrated for a case study with a Hopfield neural network and a minimum weakly connected dominating set problem as the model of wireless sensor network backbon (open full item for complete abstract)

Committee: Gursel Serpen (Committee Chair); Junghwan Kim (Committee Member); Mohsin Jamali (Committee Member); Jackson Carvalho (Committee Member); Eddie Chou (Committee Member) Subjects: Computer Science; Electrical Engineering

Doctor of Philosophy, The Ohio State University, 2005, Computer and Information Science

Ad Hoc wireless networks have been gaining importance in the communication world for the past decade. Wireless network extends the access to the network by removing the restriction of physical wires. Ad hoc network further improves the network coverage and availability to places without infrastructure support. Clock synchronization and dominating set are two of the fundamental issues in the wireless ad hoc networks. They are important for the correctness and/or performance of many protocols and applications. We focus on IEEE 802.11 wireless ad hoc networks in this dissertation due to the wide deployments of 802.11 networks. The theories and practices are definitely extensible to other types of ad hoc networks. IEEE 802.11 wireless network depends heavily on the distribution of timing information to all the stations in the network. Clock synchronization is important for frequency hopping, power saving and wireless medium reservation. We review the Timing Synchronization Function (TSF) of Ad Hoc mode defined in the 802.11 standard. It is well-known that the 802.11 TSF is not scalable. We carefully analyze the root causes of the scalability problem and design new schemes to overcome the problem. Our new schemes show great improvement over the 802.11 TSF and other solutions in the fields. Our solutions have nice characteristics: scalable, accurate, bounded and adaptive to station mobility. We are able to control the maximum clock differences under 25 micro seconds and 50 micro seconds in single hop and multihop networks respectively. The performance improvement is at least 200% or more compared with the current solutions. Dominating set has been widely used in multihop ad hoc networks (MANET) by numerous routing, broadcast and collision avoidance protocols. The problem to construct a minimum sized dominating set is known to be NP-hard. We propose a protocol that is simple, distributed, inexpensive, and adaptive to station mobility. We show that our protocol can construc (open full item for complete abstract)

Committee: Ten-Hwang Lai (Advisor) Subjects: Computer Science

Doctor of Philosophy, Case Western Reserve University, 2015, EMC - Mechanical Engineering

This dissertation presents a theoretical framework and algorithms for distributed wireless sensor networks and their physical implementations on tangible geometric games (TAG-Games) to assess cognitive and motor skills automatically using sensor integrated geometric blocks (SIG-Blocks) with an interactive graphical user interface. To allow for a variety of possible game designs, single and multiple blocks were used to form different geometrical configurations. To resolve communication issues between the blocks as well as reliability issues with sensing, the following distributed wireless sensor network algorithms were developed: 1) self-synchronization technique in a local network, 2) a hybrid wireless network, 3) an assembly detection algorithm, and 4) a motion sensing algorithm. The theoretical framework of this paper is that distributed wireless sensor network is fault tolerant, scalable, and a dynamic solution to complex multi-agent systems. To evaluate the validity of the TAG-Games with the developed algorithms and proposed theoretical framework, 86 participants were recruited to the human subject evaluation aging from 18 to 30. The results confirmed that the TAG-Games is suitable as an automatic assessment tool. The developed algorithms and theoretical framework are applied to three extended applications, including swarm robots, wearable sensors, and origami robots. First, two swarm robotic platforms were developed and the wireless algorithms were implemented. One of them is a group of mobile robots with corner reflectors to localize using directional received signal strength. The other one is the InchBots, a cubic inch-sized omnidirectional swarm robotic platform with a stackable hardware feature for customization. The robotic swarm aims to achieve a global goal by using a large number of robots, each with limited capabilities. In this application, the hybrid wireless network, assembly detection algorithm, and the self-synchronization algorithm were utili (open full item for complete abstract)

Committee: Kiju Lee (Committee Chair); Roger Quinn (Committee Member); Frank Merat (Committee Member); M. Cenk Cavusoglu (Committee Member) Subjects: Engineering; Robotics

Doctor of Philosophy, The Ohio State University, 2008, Computer and Information Science

Applications of wireless sensor networks are moving from simply monitoring based to control based ones and from static network based to pervasive and mobility-centric ones. But while the applications are rising in scale and complexity, the underlying network is still resource-constrained and bandwidth limited, prone to contention and fading. Thus the demands of applications are growing at a faster rate than the resources in the underlying network. My thesis has addressed the challenge of reliable application design using wireless sensor networks, by the design and implementation of network abstractions that bridge the gap between the application and the network and provide performance guarantees to applications. My dissertation considers the reliable design of 4 wireless sensor network applications: (1) distributed pursuer evader tracking with requirement of eventual catch, (2) distributed pursuer evader tracking with optimal interception, (3) object classification and track monitoring and (4) distributed control of flexible structures. For each of these applications, we come up with an appropriate design considering limitations of the underlying network and characterize the network abstractions that meet application requirements. The network abstractions are then implemented appropriately sometimes using middle-ware services running in the form distributed / centralized programs, sometimes by suitably designing the network with the right density, placement of sensors or sometimes using both.

Committee: Anish Arora (Advisor); Prasun Sinha (Committee Member); Paul Sivilotti (Committee Member); Tamal Dey (Committee Member) Subjects: Computer Science