Computer Sciences Commons^™

Crime Pattern Detection Using Online Social Media, Raja Ashok Bolla

Masters Theses

"In this research, we show online social networks can be used to study crime detection problems. Crime is defined as an act harmful not only to the individual involved, but also to the community as a whole. It is also a forbidden act that is punishable by law. Crimes are social nuisances that place heavy financial burdens on society. Here we look at use of data mining followed by sentiment analysis on online social networks, to help detect the crime patterns. Twitter is an online social networking and microblogging service that enables users to post brief text updates, also referred …

Energy Efficient Scheduling And Allocation Of Tasks In Sensor Cloud, Rashmi Dalvi

Masters Theses

"Wireless Sensor Network (WSN) is a class of ad hoc networks that has capability of self-organizing, in-network data processing, and unattended environment monitoring. Sensor-cloud is a cloud of heterogeneous WSNs. It is attractive as it can change the computation paradigm of wireless sensor networks. In Sensor-Cloud, to gain profit from underutilized WSNs, multiple WSN owners collaborate to provide a cloud service. Sensor Cloud users can simply rent the sensing services which eliminates the cost of ownership, enabling the usage of large scale sensor networks become affordable. The nature of Sensor-Cloud enables resource sharing and allows virtual sensors to be scaled …

Top-K With Diversity-M Data Retrieval In Wireless Sensor Networks, Kiran Kumar Puram

Masters Theses

"Wireless Sensor Network is a network of a few to several thousand sensors deployed over an area to sense data and report that data back to the base station. There are many applications of wireless sensor networks including environment monitoring, wildlife tracking, troop tracking etc. The deployed sensors have many constraints like limited battery, limited memory and very little processing capacity. These constraints show direct effect on the network life time.

In many applications of Wireless Sensor Networks, such as monitoring chemical leak, the user is not interested in all the data points from the entire region, but may want …

On Temporal And Frequency Responses Of Smartphone Accelerometers For Explosives Detection, Srinivas Chakravarthi Thandu

Masters Theses

"The increasing frequency of explosive disasters throughout the world in recent years have created a clear need for the systems to monitor for them continuously for better detection and to improve the post disaster rescue operations. Dedicated sensors deployed in the public places and their associated networks to monitor such explosive events are still inadequate and must be complemented for making the detection more pervasive and effective. Modern smart phones are a rich source of sensing because of the fact that they are equipped with wide range of sensors making these devices an appealing platform for pervasive computing applications. The …

M-Grid : A Distributed Framework For Multidimensional Indexing And Querying Of Location Based Big Data, Shashank Kumar

Masters Theses

"The widespread use of mobile devices and the real time availability of user-location information is facilitating the development of new personalized, location-based applications and services (LBSs). Such applications require multi-attribute query processing, handling of high access scalability, support for millions of users, real time querying capability and analysis of large volumes of data. Cloud computing aided a new generation of distributed databases commonly known as key-value stores. Key-value stores were designed to extract value from very large volumes of data while being highly available, fault-tolerant and scalable, hence providing much needed features to support LBSs. However complex queries on multidimensional …

Scale-Up And On-Line Monitoring Of Gas-Solid Systems Using Advanced And Non-Invasive Measurement Techniques, Muthanna H. Al-Dahhan, Shreekanta Aradhya, Faraj Zaid, Neven Ali, Thaar Aljuwaya

Chemical and Biochemical Engineering Faculty Research & Creative Works

Industry relies on gas-solid systems for numerous processes. Flow dynamics play an important role in achieving the desired results. The present study proposes, validates and demonstrates a novel mechanistic scale-up approach based on maintaining similar radial profile or cross sectional distribution of gas holdup in two different gas-solid systems in order to achieve hydrodynamics similarity using advanced measurement techniques. This new methodology for scale-up and design has been implemented on gas-solid spouted bed which has been used for drying, granulation and coating. The development can be extrapolated to other gas-solid systems encountered in phosphate processes.

Adaptive Resonance Theory And Diffusion Maps For Clustering Applications In Pattern Analysis, Donald C. Wunsch, David J. Morris, Rui Xu

Electrical and Computer Engineering Faculty Research & Creative Works

Adaptive Resonance is primarily a theory that learning is regulated by resonance phenomena in neural circuits. Diffusion maps are a class of kernel methods on edge-weighted graphs. While either of these approaches have demonstrated success in image analysis, their combination is particularly effective. These techniques are reviewed and some example applications are given.

Fixed Final-Time Near Optimal Regulation Of Nonlinear Discrete-Time Systems In Affine Form Using Output Feedback, Qiming Zhao, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, the fixed final-time near optimal output regulation of affine nonlinear discrete-time systems with unknown system dynamics is considered. First, a neural network (NN)-based observer is proposed to reconstruct both the system state vector and control coefficient matrix. Next, actor-critic structure is utilized to approximate the time-varying solution of the Hamilton-Jacobi-Bellman (HJB) equation or value function. To satisfy the terminal constraint, a new error term is defined and incorporated in the NN update law so that the terminal constraint error is also minimized over time. A NN with constant weights and time-dependent activation function is employed to approximate …

Adaptive Neural Network-Based Optimal Control Of Nonlinear Continuous-Time Systems In Strict-Feedback Form, H. Zargarzadeh, T. Dierks, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper focuses on neural network (NN) based optimal control of nonlinear continuous-time systems in strict-feedback form when the system dynamics are known by using an adaptive backstepping approach. A single NN-based adaptive approach is designed to learn the solution of the infinite horizon continuous-time Hamilton-Jacobi-Bellman (HJB) equation while the corresponding optimal control input that minimizes the HJB equation is calculated in a forward-in-time manner without using value and policy iterations. First, the optimal control problem is solved for a generic multi-input and multi-output nonlinear system with a state feedback approach. Then the approach is extended to a single-input and …

An Online Outlier Identification And Removal Scheme For Improving Fault Detection Performance, Hasan Ferdowsi, Sarangapani Jagannathan, Maciej Jan Zawodniok

Electrical and Computer Engineering Faculty Research & Creative Works

Measured data or states for a nonlinear dynamic system is usually contaminated by outliers. Identifying and removing outliers will make the data (or system states) more trustworthy and reliable since outliers in the measured data (or states) can cause missed or false alarms during fault diagnosis. In addition, faults can make the system states nonstationary needing a novel analytical model-based fault detection (FD) framework. In this paper, an online outlier identification and removal (OIR) scheme is proposed for a nonlinear dynamic system. Since the dynamics of the system can experience unknown changes due to faults, traditional observer-based techniques cannot be …

Energy Efficient And Latency Aware Adaptive Compression In Wireless Sensor Networks, Thomas Mark Daniel Szalapski

Doctoral Dissertations

"Wireless sensor networks are composed of a few to several thousand sensors deployed over an area or on specific objects to sense data and report that data back to a sink either directly or through a series of hops across other sensor nodes. There are many applications for wireless sensor networks including environment monitoring, wildlife tracking, security, structural heath monitoring, troop tracking, and many others. The sensors communicate wirelessly and are typically very small in size and powered by batteries. Wireless sensor networks are thus often constrained in bandwidth, processor speed, and power. Also, many wireless sensor network applications have …

Automated Classification Of Malignant Melanoma Based On Detection Of Atypical Pigment Network In Dermoscopy Images Of Skin Lesions, Nabin K. Mishra

Doctoral Dissertations

“Melanoma causes more deaths than any other form of skin cancer. Early melanoma detection is important to prevent progression to a more deadly stage. Automated computer-based identification of melanoma from dermoscopic images of skin lesions is the most efficient method in early diagnosis. An automated melanoma identification system must include multiple steps, involving lesion segmentation, feature extraction, feature combination and classification. In this research, a classifier-based approach for automatically selecting a lesion border mask for segmentation of dermoscopic skin lesion images is presented. A logistic regression based model selects a single lesion border mask from multiple border masks generated by …

Energy Efficient Security And Privacy Management In Sensor Clouds, Vimal Kumar

Doctoral Dissertations

"Sensor Cloud is a new model of computing for Wireless Sensor Networks, which facilitates resource sharing and enables large scale sensor networks. A multi-user distributed system, however, where resources are shared, has inherent challenges in security and privacy. The data being generated by the wireless sensors in a sensor cloud need to be protected against adversaries, which may be outsiders as well as insiders. Similarly the code which is disseminated to the sensors by the sensor cloud needs to be protected against inside and outside adversaries. Moreover, since the wireless sensors cannot support complex, energy intensive measures, the security and …

Analyzing The Effect Of Client Queue Size On Voip And Tcp Traffic Over An Ieee 802.11e Wlan, Sajib Datta, Sajal Das

Computer Science Faculty Research & Creative Works

In this paper we introduce a mathematical model to analyze the performance of Wi-Fi networks carrying voice calls and TCP controlled file downloads. We derive the voice call capacity, the TCP throughput, and the bandwidth utilization using the proposed five-dimensional Markov model. We show that there exists a correlation among the queue size of client nodes and the capacity and throughput of the network. We also demonstrate how bandwidth utilization is affected by variable packet arrival rates. The analytical results match well with the simulation results generated by QualNet simulator. Moreover, we conduct an experimental study of the Enhanced Distributed …

A Neural Network Based Outlier Identification And Removal Scheme, H. Ferdowsi, S. Jagannathan, M. Zawodniok

Electrical and Computer Engineering Faculty Research & Creative Works

Identifying and removing the outliers is important in order to make the data more trustworthy and improve the reliability of fault detection, since outliers in the measured data can cause false alarms. An online outlier identification and removal (OIR) scheme, suitable for nonlinear dynamic systems, is proposed in this paper. A neural network (NN) is utilized to estimate the actual outlier-free system states using only the measured system states which involve outliers. Outlier identification is performed online by finding the difference between measured and estimated states and comparing it with its median and standard deviation over a dynamic time window. …

A Decentralized Fault Accommodation Scheme For Nonlinear Interconnected Systems, H. Ferdowsi, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a novel decentralized detection and accommodation (FDA) methodology is proposed for interconnected nonlinear continuous-time systems by using local subsystem states alone in contrast with traditional distributed FDA schemes where the entire measured or the estimated state vector is needed. First, the detection scheme is revisited where a network of local fault detectors (LFD) is proposed. A fault is detected by generating a residual from the measured and estimated state vectors locally and the fault dynamics are estimated by using an online approximator upon detection. Subsequently, a fault accommodation scheme is initiated in the subsystem by using a …

Context Aware Identity Management Using Smart Phones, Vamsi Paruchuri, Sriram Chellappan

Computer Science Faculty Research & Creative Works

Cell phones are personal devices that are seldom used by more than one individual. Today's smartphone not only serves as the key computing and communication mobile device of choice, but it also comes with a rich set of embedded sensors. In other words, smartphones can be considered less of a "phone" in the traditional sense and more of an identity management device. Furthermore, the unique array of sensors on a smartphone can communicate its owner's identity to the world. Smartphones are pervasive computing devices that ubiquitously accompany humans and must adapt accordingly. In this paper, we propose architecture to fully …

A Hadoop Approach To Advanced Sampling Algorithms In Molecular Dynamics Simulation On Cloud Computing, Jin Niu, Shuju Bai, Ebrahim Khosravi, Seung Jong Park

Computer Science Faculty Research & Creative Works

Cloud computing has emerged as a prevalent computing paradigm with the advantages of virtualization, scalability, fault tolerance, and a usage-based pricing model. It has been widely used in various computational research fields. Replica exchange molecular dynamics (REMD) and replica exchange statistical temperature molecular dynamics (RESTMD) are two sampling algorithms in molecular dynamics. Due to the inherent parallel feature of REMD and RESTMD, it is practical to convert them into cloud computing applications. However, the performance of REMD and RESTMD on clouds has not been extensively investigated. In our work, we implemented REMD and RESTMD in cloud computing environment through Hadoop, …

Pip: Privacy And Integrity Preserving Data Aggregation In Wireless Sensor Networks, Vimal Kumar, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

With the exponential rise of pervasive computing applications, data privacy has become much more of an important issue than before. When data is aggregated at each hop in a sensor network, it becomes harder to protect its privacy. A number of privacies preserving data aggregation algorithms have recently appeared for wireless sensor networks (WSNs), very few of them however also address the issue of data integrity along with privacy. Data privacy and integrity are two contrasting objectives to achieve in general. In a privacy preserved data aggregation, it becomes easier for an attacker to inject false data hence, we suggest …

Efficient Privacy-Preserving Range Queries Over Encrypted Data In Cloud Computing, Bharath K. Samanthula, Wei Jiang

Computer Science Faculty Research & Creative Works

With the growing popularity of data and service outsourcing, where the data resides on remote servers in encrypted form, there remain open questions about what kind of query operations can be performed on the encrypted data. In this paper, we focus on one such important query operation, namely range query. One of the basic security primitives that can be used to evaluate range queries is secure comparison of encrypted integers. However, the existing secure comparison protocols strongly rely on the encrypted bit-wise representations rather than on pure encrypted integers. Therefore, in this paper, we first propose an efficient method for …

Afcd: An Approximated-Fair And Controlled-Delay Queuing For High Speed Networks, Lin Xue, Suman Kumar, Cheng Cui, Praveenkumar Kondikoppa, Chui Hui Chiu, Seung Jong Park

Computer Science Faculty Research & Creative Works

High speed networks have characteristics of high bandwidth, long queuing delay, and high burstiness which make it difficult to address issues such as fairness, low queuing delay and high link utilization. Current high-speed networks carry heterogeneous TCP flows which makes it even more challenging to address these issues. Since sender centric approaches do not meet these challenges, there have been several proposals to address them at router level via queue management (QM) schemes. These QM schemes have been fairly successful in addressing either fairness issues or large queuing delay but not both at the same time. We propose a new …

Differences In Internet Usage Patterns With Stress And Anxiety Among College Students, Levi Malott, Sai Preethi Vishwanathan, Sriram Chellappan

Computer Science Faculty Research & Creative Works

Stress and Anxiety negatively affect mental health and can lead a number of debilitating impacts to overall health and wellbeing. In the recent past, adolescents are becoming increasingly afflicted with Stress and Anxiety. In this paper, we report our findings on a six-week study of 70 students at a college campus on associations between Stress and Anxiety with respect to Internet usage of students. Using Cisco NetFlow records, on-campus Internet usage of students was collected continuously and unobtrusively in a privacy-preserving manner. Using the Depression Anxiety and Stress Scale (DASS), students were separated based on normal scores and high scores …

Implementation Of Freedm Smart Grid Distributed Load Balancing Using Iec 61499 Function Blocks, Sandeep Patil, Valeriy Vyatkin, Bruce M. Mcmillin

Computer Science Faculty Research & Creative Works

This paper presents implementation of one of the Distributed Grid Intelligence (DGI) applications: Load Balancing, using the IEC61499 architecture. This enables system level design of distributed load balancing application with a direct pathway to deployment to hardware. The use of IEC 61499 improves scalability, re-configurability and maintainability of automation software. The application was deployed to commercial programmable automation devices and embedded controller (ARM based TS-7800). The application was verified using co-simulation approach: control and power system simulated using Matlab on PC networked with the number of distributed hardware running load balance algorithm. The use of IEC 61499 facilitates deployment of …

Chc-Tscm: A Trustworthy Service Composition Method Based On An Improved Chc Genetic Algorithm, Cao Buqing, Liu Jianxun, Xiaoqing Frank Liu, Li Bing, Zhou Dong

Computer Science Faculty Research & Creative Works

Trustworthy service composition is an extremely important task when service composition becomes infeasible or even fails in an environment which is open, autonomic, uncertain and deceptive. This paper presents a trustworthy service composition method based on an improved Cross generation elitist selection, Heterogeneous recombination, Cataclysmic mutation (CHC) Trustworthy Service Composition Method (CHC-TSCM) genetic algorithm. CHC-TSCM firstly obtains the total trust degree of the individual service using a trust degree measurement and evaluation model proposed in previous research. Trust combination and computation then are performed according to the structural relation of the composite service. Finally, the optimal trustworthy service composition is …

What You Like In Design Use To Correct Bad-Smells, Marouane Kessentini, Rim Mahaouachi, Khaled Ghedira

Computer Science Faculty Research & Creative Works

Over the past decades, many techniques and tools have been developed to support maintenance activities in order to improve software quality. One of the most efficient ones is software refactoring to eliminate bad smells. A majority of existing work propose "standard" refactoring solutions that can be applied by hand for each kind of defect. However, it is difficult to prove or ensure the generality of these solutions to any kind of bad-smells or software codes. In this paper, we propose an approach to correct bad smells using well-designed code. We use genetic algorithms to generate correction solutions defined as a …

Finite Horizon Stochastic Optimal Control Of Uncertain Linear Networked Control System, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, finite horizon stochastic optimal control issue has been studied for linear networked control system (LNCS) in the presence of network imperfections such as network-induced delays and packet losses by using adaptive dynamic programming (ADP) approach. Due to an uncertainty in system dynamics resulting from network imperfections, the stochastic optimal control design uses a novel adaptive estimator (AE) to solve the optimal regulation of uncertain LNCS in a forward-in-time manner in contrast with backward-in-time Riccati equation-based optimal control with known system dynamics. Tuning law for unknown parameters of AE has been derived. Lyapunov theory is used to show …

Adjust Decision-Making Targets Based On Psychological Thresholds, Jian Liu, Shun Xiang Wu, Si Feng Liu, Qiao Wang

Electrical and Computer Engineering Faculty Research & Creative Works

This paper study the impact of psychological thresholds (PTs) on the decision maker's (DM's) decision target when making decision. A new approach of decision making is proposed in this paper. First, we construct criterion expected functions according to three different types of criteria: profit type, cost-type and intermediate-type, respectively. Then, we calculate the local degree of satisfaction (LDS) of each object when PTs exists, in order to adjust the initial decision target to make up new decision table. Later, by weighting the criteria reaching the DM's degree of satisfaction (DS) along with information aggregation algorithm, we obtain the overall satisfaction …

Zero-Sum Two-Player Game Theoretic Formulation Of Affine Nonlinear Discrete-Time Systems Using Neural Networks, Shahab Mehraeen, Travis Dierks, S. Jagannathan, Mariesa L. Crow

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, the nearly optimal solution for discrete-time (DT) affine nonlinear control systems in the presence of partially unknown internal system dynamics and disturbances is considered. The approach is based on successive approximate solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which appears in optimal control. Successive approximation approach for updating control and disturbance inputs for DT nonlinear affine systems are proposed. Moreover, sufficient conditions for the convergence of the approximate HJI solution to the saddle point are derived, and an iterative approach to approximate the HJI equation using a neural network (NN) is presented. Then, the requirement of full knowledge …

An Mpi-Enabled Mapreduce Framework For Molecular Dynamics Simulation Applications, Shuju Bai, Ebrahim Khosravi, Seung Jong Park

Computer Science Faculty Research & Creative Works

Computational technologies have been extensively investigated to be applied into many application domains. Since the presence of Hadoop, an implementation of MapReduce framework, scientists have applied it to biological sciences, chemistry, medical sciences, and other areas to efficiently process huge data sets. Although Hadoop is fault-tolerant and processes data in parallel, it does not support MPI in computing. The Map/Reduce tasks in Hadoop have to be serial, which results in inefficient scientific computations wrapped in Map/Reduce tasks. In the real world, many applications require MPI techniques due to their nature. Molecular dynamics simulation is one of them. In our research, …

Solutions To Finite Horizon Cost Problems Using Actor-Critic Reinforcement Learning, Ivo Grondman, Hao Xu, Sarangapani Jagannathan, Robert Babuska

Electrical and Computer Engineering Faculty Research & Creative Works

Actor-critic reinforcement learning algorithms have shown to be a successful tool in learning the optimal control for a range of (repetitive) tasks on systems with (partially) unknown dynamics, which may or may not be nonlinear. Most of the reinforcement learning literature published up to this point only deals with modeling the task at hand as a Markov decision process with an infinite horizon cost function. In practice, however, it is sometimes desired to have a solution for the case where the cost function is defined over a finite horizon, which means that the optimal control problem will be time-varying and …