This PDF file contains the front matter associated with SPIE Proceedings Volume 7704, including the Title Page, Copyright information, Table of Contents, and the Conference Committee listing.

Although more information than ever before is available to support the knowledge discovery and decision making processes, the vast proliferation of types of data, devices, and protocols makes it increasingly difficult to ensure that the right information is received by the right people at the right time. It becomes even more challenging when the information has security classifications that need to be processed as well. This paper investigates methods and procedures for handling and disseminating information to users and groups of users that possess varying constraints, including security classifications. The cross-­domain implications are critical in that certain users must only be allowed access to information that meets their clearance level and need-­to-­know. The ability to securely manage and deliver critical knowledge and actionable intelligence to the decision maker regardless of device configuration (bandwidth, processing speed, etc.), classification level or location in a reliable manner, would provide anytime access to useable information. There are several important components to an intuitive system that can provide timely information in a receiver-­preferred manner. Besides the ability to format information to accommodate the user's device and profiles, it's very important to address multi-­level security, which could provide ability to properly send classified information across different domains, thus enabling faster dissemination of time critical information. One factor that may simplify this process is the information provider's disregard for the recipient's device limitations. The system that provides or "proxies" the transfer of information should handle the presentation to the receiver. These topics will be the main theme of this paper.

Determining methods to secure the process of data fusion against attacks by compromised nodes in wireless sensor networks (WSNs) and to quantify the uncertainty that may exist in the aggregation results is a critical issue in mitigating the effects of intrusion attacks. Published research has introduced the concept of the trustworthiness (reputation) of a single sensor node. Reputation is evaluated using an information-theoretic concept, the Kullback- Leibler (KL) distance. Reputation is added to the set of security features. In data aggregation, an opinion, a metric of the degree of belief, is generated to represent the uncertainty in the aggregation result. As aggregate information is disseminated along routes to the sink node(s), its corresponding opinion is propagated and regulated by Josang's belief model. By applying subjective logic on the opinion to manage trust propagation, the uncertainty inherent in aggregation results can be quantified for use in decision making. The concepts of reputation and opinion are modified to allow their application to a class of dynamic WSNs. Using reputation as a factor in determining interim aggregate information is equivalent to implementation of a reputation-based security filter at each processing stage of data fusion, thereby improving the intrusion detection and identification results based on unsupervised techniques. In particular, the reputation-based version of the probabilistic neural network (PNN) learns the signature of normal network traffic with the random probability weights normally used in the PNN replaced by the trust-based quantified reputations of sensor data or subsequent aggregation results generated by the sequential implementation of a version of Josang's belief model. A two-stage, intrusion detection and identification algorithm is implemented to overcome the problems of large sensor data loads and resource restrictions in WSNs. Performance of the twostage algorithm is assessed in simulations of WSN scenarios with multiple sensors at edge nodes for known intrusion attacks. Simulation results show improved robustness of the two-stage design based on reputation-based NNs to intrusion anomalies from compromised nodes and external intrusion attacks.

Malware are analogs of viruses. Viruses are comprised of large numbers of polypeptide proteins. The shape and function of the protein strands determines the functionality of the segment, similar to a subroutine in malware. The full combination of subroutines is the malware organism, in analogous fashion as a collection of polypeptides forms protein structures that are information bearing. We propose to apply the methods of Bioinformatics to analyze malware to provide a rich feature set for creating a unique and novel detection and classification scheme that is originally applied to Bioinformatics amino acid sequencing. Our proposed methods enable real time in situ (in contrast to in vivo) detection applications.

Newly emerging advances in both measurement as well as bio-inspired computation techniques have facilitated the development of so-called lipidomics technologies and offer an excellent opportunity to understand regulation at the molecular level in many diseases such as cancer. The analysis and the understanding of the global interactional behavior of lipidomic networks remains a challenging task and can not be accomplished solely based on intuitive reasoning. The present contribution aims at developing novel computational approaches to assess the topological and functional aspects of lipidomic networks and discusses their benefits compared to recently proposed techniques. Graph-clustering methods are introduced as powerful correlation networks which enable a simultaneous exploration and visualization of co-regulation in glioblastoma data. The dynamic description of the lipidomic network is given through multi-mode nonlinear autonomous stochastic systems to model the interactions at the molecular level and to study the success of novel gene therapies for eradicating the aggressive glioblastoma. These new paradigms are providing unique "fingerprints" by revealing how the intricate interactions at the lipidome level can be employed to induce apoptosis (cell death) and are thus opening a new window to biomedical frontiers.

Efficient Global Optimization (EGO) minimizes expensive cost function evaluations by correlating evaluated parameter sets and respective solutions to model the optimization space. For optimizations requiring destructive testing or lengthy simulations, this computational overhead represents a desirable tradeoff. However, the inspection of the predictor space to determine the next evaluation point can be a time-intensive operation. Although DACE predictor evaluation may be conducted for limited parameters by exhaustive sampling, this method is not extendable to large dimensions. We apply EGO here to the 11-dimensional optimization of a wide-band fragmented patch antenna and present an alternative genetic algorithm approach for selecting the next evaluation point. We compare results achieved with EGO on this optimization problem to previous results achieved with a genetic algorithm.

EGO is an evolutionary, data-adaptive algorithm which can be useful for optimization problems with expensive cost functions. Many antenna design problems qualify since complex computational electromagnetics (CEM) simulations can take significant resources. This makes evolutionary algorithms such as genetic algorithms (GA) or particle swarm optimization (PSO) problematic since iterations of large populations are required. In this paper we discuss multiparameter optimization of a wideband, single-element antenna over a metamaterial ground plane and the interfacing of EGO (optimization) with a full-wave CEM simulation (cost function evaluation).

Wind is an important renewable energy source. The energy and economic return from building wind farms justify the expensive investments in doing so. However, without an effective monitoring system, underperforming or faulty turbines will cause a huge loss in revenue. Early detection of such failures help prevent these undesired working conditions. We develop three tests on power curve, rotor speed curve, pitch angle curve of individual turbine. In each test, multiple states are defined to distinguish different working conditions, including complete shut-downs, under-performing states, abnormally frequent default states, as well as normal working states. These three tests are combined to reach a final conclusion, which is more effective than any single test. Through extensive data mining of historical data and verification from farm operators, some state combinations are discovered to be strong indicators of spindle failures, lightning strikes, anemometer faults, etc, for fault detection. In each individual test, and in the score fusion of these tests, we apply multidimensional scaling (MDS) to reduce the high dimensional feature space into a 3-dimensional visualization, from which it is easier to discover turbine working information. This approach gains a qualitative understanding of turbine performance status to detect faults, and also provides explanations on what has happened for detailed diagnostics. The state-of-the-art SCADA (Supervisory Control And Data Acquisition) system in industry can only answer the question whether there are abnormal working states, and our evaluation of multiple states in multiple tests is also promising for diagnostics. In the future, these tests can be readily incorporated in a Bayesian network for intelligent analysis and decision support.

Biological systems have proven a rich source of inspiration for engineered systems with highly desirable properties, such as distribution, decentralization, and dynamic adaptation. However, the inspiration has been selective. Certain features, such as interaction through a shared environment, are very widely imitated. Others are less frequently exploited. These include the process of speciation, courtship signals, and death. Based on twenty-five years of experience in engineering biomimetic systems for real-world applications, this paper considers the potential contributions of some of these less-used mechanisms to solving real-world problems.

Many image processing algorithms utilize the discrete wavelet transform (DWT) to provide efficient compression and near-perfect reconstruction of image data. Defense applications often require the transmission of data at high levels of compression over noisy channels. In recent years, evolutionary algorithms (EAs) have been utilized to optimize image transform filters that outperform standard wavelets for bandwidth-constrained compression of satellite images. The optimization of these filters requires the use of training images appropriately chosen for the image processing system's intended applications. This paper presents two robust sets of fifty images each intended for the training and validation of satellite and unmanned aerial vehicle (UAV) reconnaissance image processing algorithms. Each set consists of a diverse range of subjects consisting of cities, airports, military bases, and landmarks representative of the types of images that may be captured during reconnaissance missions. Optimized algorithms may be "overtrained" for a specific problem instance and thus exhibit poor performance over a general set of data. To reduce the risk of overtraining an image filter, we evaluate the suitability of each image as a training image. After evolving filters using each image, we assess the average compression performance of each filter across the entire set of images. We thus identify a small subset of images from each set that provide strong performance as training images for the image transform optimization problem. These images will also provide a suitable platform for the development of other algorithms for defense applications. The images are available upon request from the contact author.

State-of-the-art image compression and reconstruction schemes utilize wavelets. Quantization and thresholding are commonly used to achieve additional compression, but cause permanent, irreversible information loss. This paper describes an investigation into whether evolutionary computation (EC) may be used to optimize forward (compression-only) transforms capable of matching or exceeding the compression capabilities of a selected wavelet, while reducing the aggregate error in images subsequently reconstructed by that wavelet. Transforms are independently trained and tested using three sets of images: digital photographs, fingerprints, and satellite images.

Vision is typically considered the primary and most important of all the human senses. Motion detection, being a noncontact sense, allows us to extract vast quantities of information about our environment remotely and safely. The main motivation of this research contribution is the implementation of an architecture of a biologically inspired motion algorithm tuned specially to correct optical flow (motion) to breast MRI. Neuromorphic engineering is used, borrowing nature's templates as inspiration in the design of algorithms and architectures. The architectures used can be enhanced using psychophysical and bioinspired properties according to biological vision in order to mimic the performance of the mammalians.

Autonomous situational awareness (SA) requires an ability to learn situations. It is mathematically difficult because in every situation there are many objects nonessential for this situation. Moreover, most objects around are random, unrelated to understanding contexts and situations. We learn in early childhood to ignore these irrelevant objects effortlessly, usually we do not even notice their existence. Here we consider an agent that can recognize a large number of objects in the world; in each situation it observes many objects, while only few of them are relevant to the situation. Most of situations are collections of random objects containing no relevant objects, only few situations "make sense," they contain few objects, which are always present in these situations. The training data contains sufficient information to identify these situations. However, to discover this information all objects in all situations should be sorted out to find regularities. This "sorting out" is computationally complex; its combinatorial complexity exceeds by far all events in the Universe. The talk relates this combinatorial complexity to Gödelian limitations of logic. We describe dynamic logic (DL) that quickly learns essential regularities-relevant, repeatable objects and situations. DL is related to mechanisms of the brain-mind and we describe brain-imaging experiments that have demonstrated these relations.

We describe a robust new approach to extract semantic concept information based on explicitly encoding static image appearance features together with motion information. For high-level semantic concept identification detection in broadcast video, we trained multi-modality classifiers which combine the traditional static image features and a new motion feature analysis method (MoSIFT). The experimental result show that the combined features have solid performance for detecting a variety of motion related concepts and provide a large improvement over static image analysis features in video.

We predicted human emotion using a Genetic Algorithm (GA) based lip feature extractor from facial images to classify all seven universal emotions of fear, happiness, dislike, surprise, anger, sadness and neutrality. First, we isolated the mouth from the input images using special methods, such as Region of Interest (ROI) acquisition, grayscaling, histogram equalization, filtering, and edge detection. Next, the GA determined the optimal or near optimal ellipse parameters that circumvent and separate the mouth into upper and lower lips. The two ellipses then went through fitness calculation and were followed by training using a database of Japanese women's faces expressing all seven emotions. Finally, our proposed algorithm was tested using a published database consisting of emotions from several persons. The final results were then presented in confusion matrices. Our results showed an accuracy that varies from 20% to 60% for each of the seven emotions. The errors were mainly due to inaccuracies in the classification, and also due to the different expressions in the given emotion database. Detailed analysis of these errors pointed to the limitation of detecting emotion based on the lip features alone. Similar work [1] has been done in the literature for emotion detection in only one person, we have successfully extended our GA based solution to include several subjects.

Association of audio events with video events presents a challenge to a typical camera-microphone approach in order to capture AV signals from a large distance. Setting up a long range microphone array and performing geo-calibration of both audio and video sensors is difficult. In this work, in addition to a geo-calibrated electro-optical camera, we propose to use a novel optical sensor - a Laser Doppler Vibrometer (LDV) for real-time audio sensing, which allows us to capture acoustic signals from a large distance, and to use the same geo-calibration for both the camera and the audio (via LDV). We have promising preliminary results on association of the audio recording of speech with the video of the human speaker.

Circular aerial video provides a persistent view over a scene and generates a large amount of imagery, much of which is redundant. The interesting features of the scene are the 3D structural data, moving objects, and scenery changes. Mosaic-based scene representations work well in detecting and modeling these features while greatly reducing the amount of storage required to store a scene. In the past, mosaic-based methods have worked well for video sequences with straight camera paths in a dominant motion direction11. Here we expand on this method to handle circular camera motion. By using a polar transformation about the center of the scene, we are able to transform circular motion into an approximate linear motion. This allows us to employ proven 3D reconstruction and moving object detection methods that we have previously developed. Once features are found, they only need to be transformed back to the Cartesian space from the polar coordinate system.

Automated classification and tracking approaches suffer from the high-dimensionality of the data and information space, which frequently rely upon both discriminative feature selection and efficient, accurate supervised classification strategies. Feature selection strategies have the benefit of representing the data in a modified reduced space to improve the efficacy of data mining, machine learning, and computer vision approaches. We have developed feature-selection methods involving feature ranking and assimilation to discover reduced feature sets that produce accurate results in classification for automated classifiers with significant specificity and sensitivity. We have tested a wide range of spatial, texture, and wavelet-based feature sets for electro-optical (EO) aerial imagery and infrared (IR) land-based image sequences on several machine-learning algorithms for classification for performance evaluation and comparison. A detailed experimental evaluation is provided for the classification efficacy of the features and classifiers on the particular data sets, and is accompanied by a discussion of the particular success or failure. In the second section, we detail our novel feature set that combines moment and edge descriptors and produces high, robust accuracy when evaluated for classification. Our method leverages information previously calculated in the detection stage, which includes wavelet decomposition and texture statistics. We demonstrate the results of our feature set implementation and discuss methods for creating classifier decision rules to choose a particular classification algorithm dependent on certain operating conditions or data types adaptively.

Image registration is a fundamental enabling technology in computer vision. Developing an accurate image registration algorithm will significantly improve the techniques for computer vision problems such as tracking, fusion, change detection, autonomous navigation. In this paper, our goal is to develop an algorithm that is robust, automatic, can perform multi-modality registration, reduces the Root Mean Square Error (RMSE) below 4, increases the Peak Signal to Noise Ratio (PSNR) above 34, and uses the wavelet transformation. The preliminary results show that the algorithm is able to achieve a PSNR of approximately 36.7 and RMSE of approximately 3.7. This paper provides a comprehensive discussion of wavelet-based registration algorithm for Remote Sensing applications.

We present a novel implementation of multi-scale graph-theoretic image segmentation using wavelet decomposition. This bottom-up segmentation through a weighted agglomeration approach utilizes the specific statistical characteristics of vehicles to quickly detect regions of interest in image frames. The method incorporates pixel intensity, texture, and boundary values to detect salient segments at multiple scales. Wavelet decomposition creates gradient and image approximations at multiple scales for fast edge weighting between nodes in the graph. Nodes with strong edge weights merge to form a single node at a higher level, where new internal statistics are calculated and edges are created with nodes at the new scale. Top-down saliency energy values are then calculated for each pixel on every scale, with the pixel labeled as a member of the node (segment) at the scale of highest energy. Salient node information is then used for binary classification as a potential object or non-object passes to classification and tracking algorithms. The method provides multi-scale segmentations by agglomerating nodes that consist of finer node agglomerations (lower scales). Criteria for weights between nodes include multi-level features, such as average intensity, variance, and boundary completion values. This method has been successfully tested on an electro-optical (EO) data set with multiple varying operating conditions (OCs). It has been shown to successfully segment both fully and partially occluded objects with minimal false alarms and false negatives. This method can easily be extended to produce more accurate segmentations through the sensor fusion of registered data types.

Understanding and organizing data is the first step toward exploiting sensor phenomenology for dismount tracking. What image features are good for distinguishing people and what measurements, or combination of measurements, can be used to classify the dataset by demographics including gender, age, and race? A particular technique, Diffusion Maps, has demonstrated the potential to extract features that intuitively make sense [1]. We want to develop an understanding of this tool by validating existing results on the Civilian American and European Surface Anthropometry Resource (CAESAR) database. This database, provided by the Air Force Research Laboratory (AFRL) Human Effectiveness Directorate and SAE International, is a rich dataset which includes 40 traditional, anthropometric measurements of 4400 human subjects. If we could specifically measure the defining features for classification, from this database, then the future question will then be to determine a subset of these features that can be measured from imagery. This paper briefly describes the Diffusion Map technique, shows potential for dimension reduction of the CAESAR database, and describes interesting problems to be further explored.

In this paper, we describe results from experimental analysis of a model designed to recognize activities and functions of moving and static objects from low-resolution wide-area video inputs. Our model is based on representing the activities and functions using three variables: (i) time; (ii) space; and (iii) structures. The activity and function recognition is achieved by imposing lexical, syntactic, and semantic constraints on the lower-level event sequences. In the reported research, we have evaluated the utility and sensitivity of several algorithms derived from natural language processing and pattern recognition domains. We achieved high recognition accuracy for a wide range of activity and function types in the experiments using Electro-Optical (EO) imagery collected by Wide Area Airborne Surveillance (WAAS) platform.

Layered sensing is a relatively new construct in the repertoire of the US Air Force. Under the layered sensing paradigm, an area is surveyed by a multitude of sensors at varying altitudes, and operating across many modalities. One of the recent pushes is to incorporate multi-sensor systems and create from them a single image. However, if the sensor parameters are not properly adjusted, the contrast amongst the images from camera to camera will vary greatly. This can create issues when performing tracking and analysis work. The contribution of this paper is to explore and provide an evaluation of various techniques for histogram equalization of Electro-Optical (EO) video sequences whose views are centered on a city. In this paper, the performance of several methods on histogram equalization are evaluated under the layered sensing construction.

A number of potential advantages associated with a new concept denoted as Sensor Agnostic Networks are discussed. For this particular paper, the primary focus is on integrated wireless networks that contain one or more MAVs (Micro Unmanned Aerial Vehicle). The development and presentation includes several approaches to analysis and design of Sensor Agnostic Networks based on the assumption of canonically structured architectures that are comprised of lowcost wireless sensor node technologies. A logical development is provided that motivates the potential adaptation of distributed low-cost sensor networks that leverage state-of-the-art wireless technologies and are specifically designed with pre-determined hooks, or facets, in-place that allow for quick and efficient sensor swaps between cost-low RF Sensors, EO Sensors, and Chem/Bio Sensors. All of the sample design synthesis procedures provided within this paper conform to the structural low-cost electronic wireless network architectural constraints adopted for our new approach to generalized sensing applications via the conscious integration of Sensor Agnostic capabilities.