Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Intrusion detection (3)
- Anomaly detection (2)
- Image exploitation (2)
- Pattern recognition (2)
- Wavelet transform (2)
-
- Adobe® Acrobat Reader® Introduction – (1)
- Algorithmic implementation (1)
- Alrorithms (1)
- Application layer (1)
- Artificial immune system (1)
- Automated feature extraction (1)
- Bayesian detector (1)
- Buffer overflow (1)
- Buffer overrun (1)
- Clustering (1)
- Cross-layer network protocol (1)
- Denoising (1)
- Denoising Higher-order statistics Wavelet transform (1)
- Detection (1)
- Detection rules (1)
- Dyanamic programming Feature detection Multiresolution Road detection Wavelet transform (1)
- Dynamic programming (1)
- Dynamic routing protocols (1)
- Early detection (1)
- Energy constraints Internet protocols (1)
- Expert systems (1)
- FPA cost (1)
- FPA design (1)
- Feature extraction (1)
- Genetic algorithms (1)
Articles 1 - 27 of 27
Full-Text Articles in Engineering
Extended Hough Methodology For 3d Feature Detection, Rufus H. Cofer, Samuel Peter Kozaitis, Jihun Cha
Extended Hough Methodology For 3d Feature Detection, Rufus H. Cofer, Samuel Peter Kozaitis, Jihun Cha
Electrical Engineering and Computer Science Faculty Publications
In an effort to make automatically detect image features for pattern recognition, we described a 3-dimensional (3-D) Hough transform. We describe two interlocking theoretical extensions to greatly enhance the Hough transform's ability to handle finite lineal features and allow directed search for various features while balancing memory and computational complexity. We computed the 2-D Hough transform of 1-D slices of an image which results in a 2-D to 3-D transform. Features such as line segments will cluster in a particular location so that both line orientation and spatial extent can be determined. This approach allows the Hough transform to be …
Hgcdte Focal Plane Array Cost Modeling, Thomas J. Sanders, Glenn T. Hess
Hgcdte Focal Plane Array Cost Modeling, Thomas J. Sanders, Glenn T. Hess
Electrical Engineering and Computer Science Faculty Publications
Focal plane arrays (FPAs) are used in many applications for detecting infrared (IR) radiation where normal sight with light in the visible spectrum is not possible. To effectively detect this IR radiation, complex semiconductor diodes, cooled to low temperatures, are usually used. The most common of these semiconductor materials is the II-VI alloy semiconductor system using HgCdTe, which is often called MCT. Focal plane arrays with over 1000 pixels have been fabricated. The cost of these very complex systems is becoming a very important consideration in decisions of where to use these FPAs. The focal plane array actually consists of …
Line Detection Using Wavelet Filters, Somkait Udomhunsakul, Samuel Peter Kozaitis, Uthai Thai Sritheeravirojana, A. Khempila
Line Detection Using Wavelet Filters, Somkait Udomhunsakul, Samuel Peter Kozaitis, Uthai Thai Sritheeravirojana, A. Khempila
Electrical Engineering and Computer Science Faculty Publications
We proposed a new line detection method in noisy images using Mexican hat wavelet filters. In our approach, we applied the wavelet transform in a multiresolution sense by forming the products of wavelet coefficients at the different scales to locate and identify lines at different scales. In addition, we also considered shifting line locations through multiple scales for robust line detection in the presence of noise. We found that our approach leads to an effective method to form the basis of a line detection approach.
Reduction Of Multiplicative Noise Using Higher-Order Statistics, Samuel Peter Kozaitis, Anurat Ingun, Rufus H. Cofer
Reduction Of Multiplicative Noise Using Higher-Order Statistics, Samuel Peter Kozaitis, Anurat Ingun, Rufus H. Cofer
Electrical Engineering and Computer Science Faculty Publications
We used a higher-order correlation-based method for signal denoising of images corrupted by multiplicative noise. Using the logarithm of an image, we applied a third-order correlation technique for identification of wavelet coefficients that contained mostly signal. In our approach, we examined wavelet coefficients in an environment where the contribution from the second-order moment of the noise had been reduced. Our results compared favorably and were less sensitive to threshold selection when compared to a second-order wavelet denoising method.
A Concept For Early Cancer Detection And Therapy, Ronald W. Waynant, Ilko K. Ilev, Kunal Mitra
A Concept For Early Cancer Detection And Therapy, Ronald W. Waynant, Ilko K. Ilev, Kunal Mitra
Biomedical Engineering and Sciences Faculty Publications
Early detection and treatment of breast cancer is least costly in terms of dollars, morbidity and mortality. With new early detection x-ray technology, tumors can be found, diagnosed and treated at a much smaller size than is currently possible. This paper proposes the development of a high resolution, high quality imaging system. It is a laser-driven x-ray system with time-gated detection that removes scattering noise in the image and produces resolution on the order of 10 μm. This higher resolution and higher image quality will enable the detection of one or two millimeter tumors hopefully detecting them before metastasis. We …
Linear Feature Detection Of Rural Imagery Using Multiresolution Filters, Samuel Peter Kozaitis, Rufus H. Cofer
Linear Feature Detection Of Rural Imagery Using Multiresolution Filters, Samuel Peter Kozaitis, Rufus H. Cofer
Electrical Engineering and Computer Science Faculty Publications
We detected roads in aerial imagery using a method based on lineal feature detection. Our method used the products of wavelet coefficients at several scales were to identify and locate lineal features. Using our approach effectively increased the size of the region we examined when looking for possible road pixels, and decreased the probability of false positive road pixels. Then, we used a shortest path algorithm to link road pixels to form road networks. Our approach restricted possible road network solutions based on the initial detection of road pixels. We found that our approach leads to an effective method for …
Extended Hough Methodology In Geo-Spatial Image Exploitation, Rufus H. Cofer, Samuel Peter Kozaitis, Jihun Cha
Extended Hough Methodology In Geo-Spatial Image Exploitation, Rufus H. Cofer, Samuel Peter Kozaitis, Jihun Cha
Electrical Engineering and Computer Science Faculty Publications
Hough transform theory provides a heuristically appealing approach toward finding lineal features in imagery. Unfortunately direct algorithmic implementation of its theory results in many practical problems. We provide two interlocking theoretical extensions to greatly enhances the Hough transform's ability to handle finite lineal features and allow directed search for parallel lines within the scene while balancing memory and computational complexity. Both extensions involve expansion of the Hough space concept to allow easier access to processed data for both dedicated silicon and general-purpose computer implementations.
Wavelet-Based Image Compression Using Perceptual Distortion Metric, Hemen Goswami, Samuel Peter Kozaitis
Wavelet-Based Image Compression Using Perceptual Distortion Metric, Hemen Goswami, Samuel Peter Kozaitis
Electrical Engineering and Computer Science Faculty Publications
Bits are allocated to various subbands to minimize a particular cost function to achieve compression in subband coding. The most common cost function is the L2 norm based on mean squared error (MSE). However, the MSE often fails to correspond to the perceptual quality of the image, especially at low bit rate. In this paper, we allocate bits into various subbands by minimizing the Minkowsky metric - a commonly used perceptual distortion measure. We then design the quantizer for each subband independent of each other based on the allocated bits. Experimental results indicate improved perceptual quality for the compressed images …
Imagery Chain Assessment For Feature Extraction, Rufus H. Cofer, Samuel Peter Kozaitis
Imagery Chain Assessment For Feature Extraction, Rufus H. Cofer, Samuel Peter Kozaitis
Electrical Engineering and Computer Science Faculty Publications
It is shown that the image chain has important effects upon the quality of feature extraction. Exact analytic ROC results are given for the case where arbitrary multivariate normal imagery is passed to a Bayesian feature detector designed for multivariate normal imagery with a diagonal covariance matrix. Plots are provided to allow direct visual inspection of many of the more readily apparent effects. Also shown is an analytic tradeoff that says doubling background contrast is equal to halving sensor to scene distance or sensor noise. It is also shown that the results provide a lower bound to the ROC of …
An Artificial Immune System For Securing Mobile Ad Hoc Networks Against Intrusion Attacks, William S. Hortos
An Artificial Immune System For Securing Mobile Ad Hoc Networks Against Intrusion Attacks, William S. Hortos
Electrical Engineering and Computer Science Faculty Publications
An artificial immune system (AIS) for securing mobile ad hoc networks (MANET) against intrusion attacks was presented. A state vector of features and metrics based on the published Secure Routing Protocol (SRP) for MANETs was constructed to encode network security characteristics. The results were reported along with a performance analysis comparing the AIS approach with competing techniques.
Cross-Layer Protocols Optimized For Real-Time Multimedia Services In Energy-Constrained Mobile Ad Hoc Networks, William S. Hortos
Cross-Layer Protocols Optimized For Real-Time Multimedia Services In Energy-Constrained Mobile Ad Hoc Networks, William S. Hortos
Electrical Engineering and Computer Science Faculty Publications
The optimization of cross-layer protocols for real-time multimedia services in energy-constrained mobile ad hoc networks (MANET) was presented. The cross-layer optimization was based on stochastic dynamic programming conditions derived from time-dependent models of MANET packet flows. The performance of the optimized cross-layer protocols was also determined by using dynamic programming conditions.
Short Pulse Laser Propagation Through Tissues, Champak Das, Ashish Trivedi, Kunal Mitra, Tuan Vo-Dinh
Short Pulse Laser Propagation Through Tissues, Champak Das, Ashish Trivedi, Kunal Mitra, Tuan Vo-Dinh
Biomedical Engineering and Sciences Faculty Publications
An experimental and numerical study is performed to analyze short pulse laser propagation through tissue phantoms without and with inhomogeneities/tumors imbedded in it. Short pulse laser probing techniques has distinct advantages over conventional very large pulse width or cw lasers primarily due to the additional information conveyed about the tissue interior by the temporal variation of the observed signal. Both the scattered temporal transmitted and reflected optical signals are measured experimentally using a streak camera for samples irradiated with a short pulse laser source. Parametric study involving different scattering and absorption coefficients of tissue phantoms and inhomogeneities as well as …
Improving Learning Implicit User Interest Hierarchy With Variable Length Phrases, Hyoung-Rae Kim, Philip K. Chan
Improving Learning Implicit User Interest Hierarchy With Variable Length Phrases, Hyoung-Rae Kim, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
A continuum of general to specific interests of a user called a user interest hierarchy (UIH) represents a user's interests at different abstraction levels. A UIH can be learned from a set of web pages visited by a user. In this paper, we focus on improving learning the UIH by adding phrases. We propose the VPF algorithm that can find variable length phrases without any user-defined parameter. To identify meaningful phrases, we examine various correlation functions with respect to well-known properties and other properties that we propose.
Boundary Detection In Tokenizing Network Application Payload For Anomaly Detection, Rachna Vargiya, Philip K. Chan
Boundary Detection In Tokenizing Network Application Payload For Anomaly Detection, Rachna Vargiya, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
Most of the current anomaly detection methods for network traffic rely on the packet header for studying network traffic behavior. We believe that significant information lies in the payload of the packet and hence it is important to model the payload as well. Since many protocols exist and new protocols are frequently introduced, parsing the payload based on the protocol specification is time-consuming. Instead of relying on the specification, we propose four different characteristics of streams of bytes, which can help us develop algorithms for parsing the payload into tokens. We feed the extracted tokens from the payload to anomaly …
Determining The Number Of Clusters/Segments In Hierarchical Clustering/Segmentation Algorithms, Stan Salvador, Philip K. Chan
Determining The Number Of Clusters/Segments In Hierarchical Clustering/Segmentation Algorithms, Stan Salvador, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
We investigate techniques to automatically determine the number of clusters to return from hierarchical clustering and segmentation algorithms. We propose an efficient algorithm, the L Method, that finds the "knee" in a '# of clusters vs. clustering evaluation metric' graph. Using the knee is well-known but is not a particularly well-understood method to determine the number of clusters. We explore the feasibility of this method, and attempt to determine in which situations it will and will not work.
Identifying Outliers Via Clustering For Anomaly Detection, Muhammad H. Arshad, Philip K. Chan
Identifying Outliers Via Clustering For Anomaly Detection, Muhammad H. Arshad, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
Detecting known vulnerabilities (Signature Detection) is not sufficient for complete security. This has raised recent interest in Anomaly Detection (AD), in which a model is built from normal behavior and significant deviations from this model are flagged anomalous. However, most AD algorithm assume clean training data, which could be hard to obtain. Our proposed algorithm relaxes. For this, we define the notion a strong outlier, which is suspicious at both local and global levels. Finally we illustrate the effectiveness of our approach on the DARPA '99 dataset and find that our approach is at par in number of detections at …
Learning Rules From System Call Arguments And Sequences For Anomaly Detection, Guarav Tandon, Philip K. Chan
Learning Rules From System Call Arguments And Sequences For Anomaly Detection, Guarav Tandon, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
Many approaches have been suggested and various systems have been modeled to detect intrusions from anomalous behavior of systems calls as a result of an attack. Though these techniques have been shown to be quite effective, a key element seems to be missing -- the inclusion and utilization of the system call arguments to create a richer, more valuable signature and to use this information to model the intrusion detection system more accurately. We put forth the idea of adopting a rule learning approach that mobilizes rules based upon system calls and models the system for normal traffic using system …
A Local Search Optimization Algorithm Based On Natural Principles Of Gravitation, Barry Webster, Philip J. Bernhard
A Local Search Optimization Algorithm Based On Natural Principles Of Gravitation, Barry Webster, Philip J. Bernhard
Electrical Engineering and Computer Science Faculty Publications
This paper discusses the concept of an algorithm designed to locate the optimal solution to a problem in a (presumably) very large solution space. The algorithm attempts to locate the optimal solution to the problem by beginning a search at an arbitrary point in the solution space and then searching in the "local" area around the start point to find better solutions. The algorithm completes either when it locates what it thinks is the optimal solution or when predefined halt conditions have been met. The algorithm is repair-based, that is, it begins with a given solution and attempts to "repair" …
Denoising Using Higher-Order Statistics, Samuel Peter Kozaitis, Sunghee Kim
Denoising Using Higher-Order Statistics, Samuel Peter Kozaitis, Sunghee Kim
Electrical Engineering and Computer Science Faculty Publications
We used a higher-order correlation-based method for signal denoising. In our approach, we determined which wavelet coefficients contained mostly noise, or signal, based on higher-order statistics. Because the higher that second-order moments of the Gaussian probability function are zero, the third-order correlation coefficient will not have a statistical contribution from Gaussian noise. We obtained results for both 1-D signals and images. In all cases, our approach showed improved results when compared to a more popular denoising method.
A Representation Scheme For Finite Length Strings, Guarav Tandon, Debasis Mitra
A Representation Scheme For Finite Length Strings, Guarav Tandon, Debasis Mitra
Electrical Engineering and Computer Science Faculty Publications
This study is an attempt to create a canonical representation scheme for finite length strings to simplify the study of the theory behind different classes of patterns and to ease the understanding of the underlying separability issues. This could then be used to determine what kinds of techniques are suitable for what class of separability (linear, multi-linear, or non-linear). This representation can then be used in intrusion detection, biological sequences, pattern recognition/classification and numerous other applications.
A Machine Learning Approach To Anomaly Detection, Philip K. Chan, Matthew V. Mahoney, Muhammad H. Arshad
A Machine Learning Approach To Anomaly Detection, Philip K. Chan, Matthew V. Mahoney, Muhammad H. Arshad
Electrical Engineering and Computer Science Faculty Publications
Much of the intrusion detection research focuses on signature (misuse) detection, where models are built to recognize known attacks. However, signature detection, by its nature, cannot detect novel attacks. Anomaly detection focuses on modeling the normal behavior and identifying significant deviations, which could be novel attacks. In this paper we explore two machine learning methods that can construct anomaly detection models from past behavior. The first method is a rule learning algorithm that characterizes normal behavior in the absence of labeled attack data. The second method uses a clustering algorithm to identify outliers.
Learning States And Rules For Time Series Anomaly Detection, Stan Salvador, Philip K. Chan, John Brodie
Learning States And Rules For Time Series Anomaly Detection, Stan Salvador, Philip K. Chan, John Brodie
Electrical Engineering and Computer Science Faculty Publications
In this paper, we investigate machine learning techniques for discovering knowledge that can be used to monitor the operation of devices or systems. Specifically, we study methods for generating models that can detect anomalies in time series data. The normal operation of a device can usually be characterized in different temporal states. To identify these states, we introduce a clustering algorithm called Gecko that can automatically determine a reasonable number of clusters using our proposed "L" method. We then use the RIPPER classification algorithm to describe these states in logical rules. Finally, transitional logic between the states is added to …
A New Approach To Scalable Lindasystems Based On Swarms, Ronaldo Menezes, Robert Tolksdorf
A New Approach To Scalable Lindasystems Based On Swarms, Ronaldo Menezes, Robert Tolksdorf
Electrical Engineering and Computer Science Faculty Publications
Natural forming multi-agent systems (aka Swarms) have the ability to grow to enormous sizes without requiring any of the agents to oversee the entire system. The success of these systems comes from the fact that agents are simple and the interaction with the environment and neighboring agents is local in nature. In this paper we look at abstractions in the field of swarms and study their applicability in the context of coordination systems. In particular, we focus on the problematic issue of scalability of Linda systems. The purpose of this work is to look at abstractions yielded from observations of …
Testing With Hostile Data Streams, Alan A. Jorgensen
Testing With Hostile Data Streams, Alan A. Jorgensen
Electrical Engineering and Computer Science Faculty Publications
This note describes a method of testing software for response to malicious data streams. Systems that process data streams obtained from an external source such as the Internet are vulnerable to security issues if malicious data is not processed correctly. This note describes a testing method that creates malicious data streams, applies them to a software application and checks the appropriateness of the application response. The note begins with a description of the problem: inadequate testing of software response to malicious data streams. I present a method of testing the response to malicious data streams and introduce the concepts of …
An Analysis Of The 1999 Darpa/Lincoln Laboratory Evaluation Data For Network Anomaly Detection, Matthew V. Mahoney, Philip K. Chan
An Analysis Of The 1999 Darpa/Lincoln Laboratory Evaluation Data For Network Anomaly Detection, Matthew V. Mahoney, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
We investigate potential simulation artifacts and their effects on the evaluation of network anomaly detection systems in the 1999 DARPA/MIT Lincoln Laboratory off-line intrusion detection evaluation data set. A statistical comparison of the simulated background and training traffic with real traffic collected from a university departmental server suggests the presence of artifacts that could allow a network anomaly detection system to detect some novel intrusions based on idiosyncrasies of the underlying implementation of the simulation, with an artificially low false alarm rate. The evaluation problem can be mitigated by mixing real traffic into the simulation. We compare five anomaly detection …
Heat: Runtime Interception Of Win32 Functions, Michael M. Andrews
Heat: Runtime Interception Of Win32 Functions, Michael M. Andrews
Electrical Engineering and Computer Science Faculty Publications
When researching in any field, it is always important to build upon existing work. In most research disciplines, the core base is well defined and widely documented. However, the basis of innovative research in computer science, especially at the systems level, can often be proprietary information. This can be a major problem as unless you have source code available you must be granted access to the proprietary information (by usually signing non-disclosure documents) which comes with barriers on access, ownership and the ability to publish results. As an example, Microsoft's Windows operating system (all versions) can be a good base …
Learning Rules For Anomaly Detection Of Hostile Network Traffic, Matthew V. Mahoney, Philip K. Chan
Learning Rules For Anomaly Detection Of Hostile Network Traffic, Matthew V. Mahoney, Philip K. Chan
Electrical Engineering and Computer Science Faculty Publications
We introduce an algorithm called LERAD that learns rules for finding rare events in nominal time-series data with long range dependencies. We use LERAD to find anomalies in network packets and TCP sessions to detect novel intrusions. LERAD outperforms the original participants in the 1999 DARPA/Lincoln Laboratory intrusion detection evaluation, and detected most attacks that eluded a firewall in a university departmental server environment.