Effective tissue clutter filtering is critical for non-contrast ultrasound imaging of slow blood flow in small vessels. Independent component analysis (ICA) has been considered by other groups for ultrasound clutter filtering in the past and was shown to be superior to principal component analysis (PCA)-based methods. However, it has not been considered specifically for slow flow applications or revisited since the onset of other slow flow-focused advancements in beamforming and tissue filtering, namely angled plane wave beamforming and full spatiotemporal singular value decomposition (SVD) (i.e., PCA-based) tissue filtering. In this work, we aim to develop a full spatiotemporal ICA-based tissue filtering technique facilitated by plane wave applications and compare it to SVD filtering. We compare ICA and SVD filtering in terms of optimal image quality in simulations and phantoms as well as in terms of optimal correlation to ground truth blood signal in simulations. Additionally, we propose an adaptive blood independent component sorting and selection method. We show that optimal and adaptive ICA can consistently separate blood from tissue better than principal component analysis (PCA)-based methods using simulations and phantoms. Additionally we demonstrate initial in vivo feasibility in ultrasound data of a liver tumor.

The goal of this paper is to develop a cognitive developmental approach for a humanoid robot so that it can provisionally discover self-affordance relations between certain arm limb movements and corresponding motor units by exploring the outcomes of its random arm movements while in a crawling position. Learning of the right and the left arm affordances is based on self-exploration and a set of experience similarly to how a human baby discovers action-effect relations of own arm movements. We address the early development of self-affordances, similar to infants, which encodes the relationships between actions, objects, and the effect on the environment.

Due to their ability to detect clusters with irregular boundaries, minimum spanning tree-based clustering algorithms have been widely used in practice. However, in such clustering algorithms, the search for nearest neighbor in the construction of minimum spanning trees is the main source of computation and the standard solutions take O(N^{2}) time. In this paper, we present a fast minimum spanning tree-inspired clustering algorithm, which, by using an efficient implementation of the cut and the cycle property of the minimum spanning trees, can have much better performance than O(N^{2}).

Abstract –Research has shown that the voice itself contains important information about immediate psychological state and certain vocal parameters are capable of distinguishing speaking patterns of speech signal affected by emotional disturbances (i.e., clinical depression). In this study, the GMM based feature of the vocal tract system response and spectral energy have been studied and found to be a primary acoustic feature set for separating two groups of female patients carrying a diagnosis of depression and suicidal risk. Index Terms : suicidal speech, depression, vocal tract, energy 1. Introduction Suicide is a common outcome in persons with serious mental disorders. However, it remains a phenomenon that is underresearched and poorly understood. Moreover, methods to help to identify persons who are at an elevated risk are sorely needed in clinical practice. This study represents an attempt to identify characteristic vocal patterns in persons with imminent suicidal potential which could lead to the development of new technology to aid in the assessment of suicidal potential. This project is to study vocal acoustic properties in suicidal states. Two study groups will be contrasted in this work: near–term suicidal and depressed. In the early 1980’s the Silvermans began to collect and analyze recorded suicide notes and interviews made shortly before suicide attempts. Their results suggested that voice can provide important information about immediate psychological state. They have described that the depressed patients have the same vocal speech as suicidal patients but the tonal quality of speech changes significantly when patients become suicidal. As reported in [1], [2], [3], the emotional arousal produces changes in the speech production scheme by affecting the respiratory, phonatory, and articulatory processes that in turn are encoded in the acoustic signal. The emotional content of the voice can be associated with acoustical variables such as thelevel, range, contour, and perturbation of the fundamental frequency, the distribution of energy in frequency spectrum, the location, bandwidth and intensity of formant frequencies, and a variety of temporal measures. The measurable change in vocal parameters affected by emotional disturbances is able to be evaluated by utilizing an appropriate speech processing approach associated with certain acoustic features. Researches have shown that depression has a major effect on the acoustic characteristics of voice when compared to the normal controls. Certain changes in acoustic properties of the affective speech are possibly specific to the near–term suicidal states in persons. In the published pilot studies [4], [6], analytical techniques have been developed to determine if subjects were in one of three mental states: healthy control, non–suicidal depressed, or high–risk suicidal. Several studies have used the vocal tract (VT) measures (i.e., formants) and prosody to classify the emotional disorders. France et. al [4] found the formants and percentages of total energy in frequency spectrum over a frequency range of 0–2,000 Hz to be the most distinguishing acoustic feature set for classifying groups of control, major depressed, and suicidal subjects. These features were recently re–investigated and extracted from a new speech database recorded in a better controlled environment. The experimental results have shown that the investigated feature set was still found as powerful acoustic discriminators in distinguishing suicidal, depressed and remitted patients [1]. Ozdas et. al [6] used a set of low order mel–cepstral coefficients to identify speakers who were diagnosed to be major depressed, suicidal, and normal by a psychiatrist. Her comparative result of classification performance as a measure of group separation was significantly high. Moore et al. compared the results of speaking pattern recognition by employing the prosody, formant and glottal ratio/spectrum in classifying normal controls and depressed patients. The optimal classifiers designated by the glottal ratio/spectrum and formant performed most effectively to separate two individual groups [7]. In this work, the characterization of the vocal tract system and distribution of energy in frequency spectrum of speech signal are focused. The speech processing algorithm to solve a specific problem of extracting the vocal features representing the characteristics of the VT system response is implemented and proposed. The estimate of smoothed magnitude spectrum is determined via the cepstrum analysis and the spectral structure contained in that magnitude spectrum is modeled by a mixture of Gaussian density components whose model parameters are estimated via a well–known “Expectation–Maximization” (EM) algorithm.This paper is organized as follows: Section 2 provides the descriptions of database, feature extraction, primary feature selection, and performance evaluation. Section 3 presents the results. Finally, section 4 concludes all findings from this work.

In some pattern recognition tasks, the dimension of the sample space is larger than the number of samples in the training set. This is known as the "small sample size problem". Linear discriminant analysis (LDA) techniques cannot be applied directly to the small sample size case. The small sample size problem is also encountered when kernel approaches are used for recognition. In this paper, we attempt to answer the question of "How should one choose the optimal projection vectors for feature extraction in the small sample size case?" Based on our findings, we propose a new method called the kernel discriminative common vector method. In this method, we first nonlinearly map the original input space to an implicit higher dimensional feature space, in which the data are hoped to be linearly separable. Then, the optimal projection vectors are computed in this transformed space. The proposed method yields an optimal solution for maximizing a modified Fisher's linear discriminant criterion, discussed in the paper. Thus, under certain conditions, a 100% recognition rate is guaranteed for the training set samples. Experiments on test data also show that, in many situations, the generalization performance of the proposed method compares favorably with other kernel approaches.

In face recognition tasks, the dimension of the sample space is typically larger than the number of the samples in the training set. As a consequence, the within-class scatter matrix is singular and the Linear Discriminant Analysis (LDA) method cannot be applied directly. This problem is known as the "small sample size" problem. In this paper, we propose a new face recognition method called the Discriminative Common Vector method based on a variation of Fisher's Linear Discriminant Analysis for the small sample size case. Two different algorithms are given to extract the discriminative common vectors representing each person in the training set of the face database. One algorithm uses the within-class scatter matrix of the samples in the training set while the other uses the subspace methods and the Gram-Schmidt orthogonalization procedure to obtain the discriminative common vectors. Then, the discriminative common vectors are used for classification of new faces. The proposed method yields an optimal solution for maximizing the modified Fisher's Linear Discriminant criterion given in the paper. Our test results show that the Discriminative Common Vector method is superior to other methods in terms of recognition accuracy, efficiency, and numerical stability.

Teams of humans and robots working together can provide effective solutions to problems. In such applications, effective human-robot teaming relies on being able to communicate information about the current perception or understanding of the environment. In this paper, human-robot teaming on navigational tasks is discussed. The role of the human user will be to specify the goal point(s) for the robot, and also to interact with the robot in the event of perceptual errors. A novel navigation method, Egocentric Navigation (ENav), has been developed based on egocentric representations. In this paper, two knowledge sharing methods are described which exploit the characteristics of ENav. In the first method, robots share Landmark EgoSpheres, and in the second method the robot shares it Sensory EgoSphere with the human user for visual perception correction.

In this research, a taxonomy is introduced to cover important considerations for human-robot interactions. As an application of passive human-robot interaction, two modalities for localizing humans based on sound source localization and infrared motion detection were developed and integrated with the face-tracker system of a humanoid ISAC (intelligent soft arm control), in order to direct ISACs attention and to prevent it from being quickly distracted. The sound source localization and passive infrared motion detection systems are used to provide the face-tracker system with candidate regions for finding a face. In order to avoid the situation where the robot appears to be "hyperactive" and cannot give sufficient attention to a newly discovered face, these sensing modules should not directly gain control of the tracking if the system has recently acquired a new face. Our goal is to allow a human to redirect the attention of the system but give the system a method to ignore the distraction if recently engaged.

Many recent content-based image retrieval techniques utilize relevance feedback (RF) from the user to adjust the system response to better meet user expectations. One school of RF-based methods uses a weighted Minkowski distance metric to assess similarity, and adjusts the weights to refine query response. A new method of estimating these weight vectors is presented which outperforms existing methods, particularly for the important case of limited training data. A new objective function is presented for an iterative optimization routine which more closely aligns optimization goals with true system goals. A new analysis framework is presented in the derivation of this technique which is useful for understanding the limitations of many RF methods.

This paper proposes a method to obtain optimal 2nd-order approximation preserving prefilters for a given orthogonal unbalanced multiwavelet basis. This procedure uses the prefilter construction introduced in Hardin et al., (1998). The prefilter optimization scheme exploits the Taylor series expansion of the prefilter combined with the multiwavelet. Using the DGHM multiwavelet with the obtained optimal prefilter, we find that quadratic input signals are annihilated by the high-pass portion of the filter bank at the first level of decomposition.

Prefiltering a given discrete signal has been shown to be an essential and necessary step in applications using unbalanced multiwavelets. In this paper, we develop two methods to obtain optimal second-order approximation preserving prefilters for a given orthogonal multiwavelet basis. These procedures use the prefilter construction introduced in part I of this paper. The first prefilter optimization scheme exploits the Taylor series expansion of the prefilter combined with the multiwavelet. The second one is achieved by minimizing the energy compaction ratio (ECR) of the wavelet coefficients for an experimentally determined average input spectrum. We use both methods to find prefilters for the cases of the DGHM and Chui-Lian (CL) multiwavelets. We then compare experimental results using these filters in an image compression scheme. Additionally, using the DGHM multiwavelet with the optimal prefilters from the first scheme, we find that quadratic input signals are annihilated by the high-pass portion of the filter bank at the first level of decomposition.

In order for a humanoid robot to be accepted in society and perform as an intelligent human assistant or companion, it must exhibit robust human-humanoid interaction (HHI). Additionally, the humanoid must be able to recognize if it is working properly, and if not, why. We describe our development of a framework for HHI. This framework includes a high-level agent called the Self Agent; part of its role is to maintain information about the status of the humanoid. To accomplish this, we have developed a technique called system status evaluation that the humanoid uses to detect and localize failures. We present the results of the use of SSE on a humanoid system called ISAC.

Among the many clinical decisions that psychiatrists must make, assessment of a patient's risk of committing suicide is definitely among the most important, complex and demanding. Clinical experience has shown that successful predictions of suicidality were often based on the patient's voice independent of content. Vocal patterns associated with dynamic expressiveness were designated as one of the most distinguishable features in the voices of suicidal patients at imminent risk. This paper investigates this phenomenon in an effort to explore the discriminating ability of jitter (period-to-period fluctuations in fundamental frequency) among suicidal and nonsuicidal patients. First, a wavelet transform based glottal cycle duration estimation technique is employed for the voiced/unvoiced decision and fundamental frequency (F0) estimation. Second, F0 perturbations are computed for each voiced segment in the F0 contour. Statistical analyses showed that F0 perturbations differ significantly (p=0.0069) between suicidal and nonsuicidal subjects' speech. Finally, a maximum likelihood classifier was developed, which obtained a correct classification score of 80%.

An active vision system enables the selective capture of important information for various applications. With an active vision system, the control of gaze direction toward a visual target can simplify many of the robot's interactions with the world. This work presents the implementation of a camera head control system for a mobile robot, called HelpMate. Helpmate's binocular head is composed of two Sony color cameras mounted on two independent pan-tilt heads. The camera head control behavior is designed to be similar to that of human eyes, which include saccade, smooth pursuit, vergence and vestibulo-ocular reflex. Saccade allows the robot to quickly direct its gaze to the target, smooth pursuit keeps both cameras fixated on the moving target, vergence makes sure that the two cameras are looking at the same object, and vestibulo-ocular reflex compensates the camera motion for the robot body's movement. Control methods have been designed and tested through experimentation. By using color segmentation, HelpMate can detect and locate a human holding a specific colored object, who is approaching within its range. Once the target is located, the two cameras are fixated, and HelpMate's body turns toward the target. The camera head then smoothly tracks the moving target and guides the robot to follow the target as it moves.

At the Intelligent Robotics Laboratory of the Center for Intelligent Systems at Vanderbilt University, we have been developing a humanoid system called ISAC, (Intelligent Soft-Arm Control), over the past several years. As people work with a humanoid system, the interaction should be natural and robust. Our framework for human-humanoid interaction (HHI) considers various aspects of HHI and the paper presents information about the development of one key element of this system: the human agent.

The face tracker system of a humanoid, ISAC (Intelligent Soft Arm Control), is integrated with two modalities for localizing humans in order to direct ISAC's attention and to prevent ISAC from being quickly distracted. The sound source localization and passive infrared (PIR) motion detection systems are used to provide the face tracker system with candidate regions for finding a face. However, the sensing modules should not directly gain control of the tracking if the system has recently acquired a new face. Our goal is to allow a human to redirect the attention of the system, but give the system a method to ignore the distraction if recently engaged.

Modern manufacturing system have to deal with dynamic situations such as customer specification changes, machine break-down, emergency orders and other kinds of disturbances. This requires the manufacturing system to be adaptive to handle such situations. The holonic concept has been proposed as an efficient paradigm for developing such an adaptive manufacturing system. There are still some critical issues to be investigated such as how to define the holons for a given application context and make them reusable, what should be an appropriate system architecture and how to design the system cooperation mechanisms for better system performance. The Intelligent Machine Architecture (IMA) is a software architecture developed at Vanderbilt University. It provides a framework for developing reusable components and constructing reconfigurable, extensible systems. Although it is mainly used for robots, it is also a suitable development tool for designing adaptive manufacturing systems. The authors explain how to build reusable, reconfigurable and extensible holonic manufacturing systems based on the IMA framework.

This paper proposes a simple method for localization using an electronic compass. Electronic compasses are often used to detect the heading of mobile robots. However, electronic compasses have one drawback when used inside a building: they can easily be disturbed by electromagnetic sources (e.g., power lines) or large ferro-magnetic structures (e.g., bookshelves). However, this paper introduces another indoor application of electronic compasses. We take advantage of the magnetic field disturbances by using them as distinctive place recognition signatures. We first gather information about the changing heading as our robot travels along the hallway outside the lab, and then store this information. As the robot traverses the hallway, it gathers the information from the electronic compass and matches it with the pre-stored data. If a match is found, the robot can determine its current position. We use a sequential least-squares approximation approach for matching the signature. The simulation results will show that the robot can distinguish its location by using these signatures.

This paper describes how fuzzy control can be applied to a sonar-based mobile robot. Behavior-based fuzzy control for HelpMate behaviors was designed using sonar sensors. The fuzzy controller provides a mechanism for combining sensor data from all sonar sensors which present different information. The behavior-based approach is implemented as an individual high priority behavior. The highest level behavior is called the task-oriented behavior, which consists of two subtasks, wall following and goal seeking. The middle level behavior is obstacle avoidance. The lowest level is an emergency behavior. Each behavior was built as an atomic agent based on the intelligent machine architecture (IMA). The results demonstrate that each behavior works correctly. The HelpMate robot can follow the wall, go to the goal, and avoid obstacles detected by the sonar sensors.

Due to a continuous increase in the need to provide more services to health care through robotic aid systems developed for the disabled, the need for addressing human-robot interaction (HRI) has gained the utmost importance. HRI is based on a multi-agent architecture, the Intelligent Machine Architecture (IMA) (R.A. Peters II et al., 1999; W.A. Alford et al., 1999), a new approach for software design for intelligent machines that are principally limited by difficulty in integrating existing algorithms, models, and subsystems. A system of interactive software agents, designed within IMA, encapsulates the various hardware elements, environmental elements, behaviors and tasks. IMA suggests "a society of agents" (M. Minsky, 1985) paradigm to create complex high-level functionality from any sublevels of components. The high-level agents currently employ finite state machines to sequence the activation and suppression of behavior agents. A state machine is realized by two components: state machine engine and state machine representation. Model Integrated Computing (MIC) (G. Nordstrom et al., 1998) is used to model the behavior of the IMA agents. The paper presents a toolkit that designs the agent's behavior through a state-transition metamodeling environment and builds the agent with the help of an existing Agent Builder application.

In this paper, we address the problem of estimating the parameters of a noncausal autoregressive (AR) signal from estimates of the higher-order cumulants of noisy observations. The proposed family of techniques uses both 3rd-order and 4th order cumulants of the observed output data. Consequently, at low SNR, they provide superior performance to methods based on autocorrelations. The measurement noise is assumed to be Gaussian and may be colored. The AR model parameters here are directly related to the solution of a generalized eigenproblem. The performance is illustrated by means of simulation examples.

This paper presents a simple but effective method for integrating sensors and actuators in both real and virtual environments using an interactive simulator over the Internet. Our research explores the combination of visual feedback and force feedback to enhance our 3D collision avoidance approach for a dual-arm humanoid robot. The robot control server uses 3D vision-based position estimates of obstacles, such as a human hand or objects on the table, to compute a collision-free path in real-time. The dual-arm robot is capable of performing multiple interactive tasks while avoiding collisions between its own arms or with other objects. The interactive simulator provides visual feedback to the user and sends the user's commands to the robot server and the stereo camera server via the Internet. Thus, it is well-designed for robot teleassistance applications. Force feedback effects are generated, using an inexpensive commercially available joystick, to enhance the sensation of the real environment while interacting with the simulation. Finally, experimental results using our collision avoidance approach are presented to demonstrate the performance of this system.

In this paper we present the design and implementation of a novel low-cost active vision system for robotic applications. The system is comprised of two parts: A 4-DOF trinocular active camera head and a DSP-based image acquisition and processing board. Design issues and tradeoffs are discussed. The performance of the system is evaluated by running an edge-based object tracking algorithm that is also presented in this paper. Experimental results show that the system is capable of tracking objects at 30 frames/sec.

The concepts of least squares and total least squares as applied to a system of linear equations are standard techniques in mathematical analysis. They have become an indispensable tool in the development of signal processing algorithms. The notion of constrained total least squares is introduced and its applications to the problems of exponential data modeling and system identification are briefly developed. It is shown that a significant improvement in performance is achieved over conventional methods.>

Much research has focused on the problem of estimating the model order of autoregressive moving average (ARMA) processes. The most well-known of the proposed solutions for this problem include the final prediction error (FPE), Akaike information criterion (AIC), and minimum description length (MDL). A new approach for model order determination based on the MDL criterion is proposed and shown to depend on the minimum eigenvalue of a covariance matrix derived from the observed data. As a result, a new selection procedure for estimating the model order via MDL is proposed. Examples that illustrate the significantly improved accuracy of the proposed technique are given.>

An order-recursive iterative algorithm (named the C-RISE algorithm, since it combines the C-RITE and RISE algorithms) is presented for the generalized eigendecomposition of a Hermitian pencil. An important feature is the inherent computational parallelism of the resulting algorithm, pointing to the potential for VLSI implementation. The order-recursive nature presents the potential for solving problems of an a priori unknown, adequate minimal size rather than a single maximum size only. It is shown that the recursive nature is not detrimental to numerical performance, as it is competitive with standard algorithms solving the single maximum size problem only.>

A signal enhancement algorithm is described which achieves the objective of modification of the given data set that then serves as a cleansing process whereby corrupting noise, measurement distortion, or theoretical mismatch present in the given data set is removed. Particular attention is directed toward properties that are describable using a singular value decomposition of a data generated matrix. An example is given demonstrating a significant improvement in the performance of subspace-based frequency estimation techniques. The algorithm is shown to provide a useful means for solving a variety of important signal processing problems. It has been successfully applied to the missing data problem, deconvolution, high-dimensional filter synthesis, and image synthesis.>

Structurally adaptive and dynamically reconfigurable systems are presented as important ingredients in the design and development of robust large-scale signal-processing systems for operation in complex nonstationary environments. The multigraph programming and execution environment (MPEE) is a complete, parallel, fully integrated programming and execution environment for structurally adaptive signal-processing systems. It provides a user-friendly environment for designing, programming, and executing such a signal-processing system. The MPEE is shown to have many advantages, due to graph-based processing, dynamic scheduling, multiprocessor programming capabilities, a hierarchical approach to system design, and graphic editors.>

The harmonic decomposition of a random process into a sum of sinusoids in white noise is an important problem with applications in a number of different areas. As a result of the work of V.F. Pisarenko, it has been shown that the sinusoidal frequencies and the white noise power are determined by the minimum eigenvalue and the corresponding eigenvector of the autocorrelation matrix. Many authors have formulated adaptive versions of the Pisarenko solution for the purpose of spectral line tracking, but most have concentrated only on stationary sinusoids. In most of the interesting applications, however, the frequencies of the sinusoids change, thus they are nonstationary. In this paper we concentrate on the nonstationary case, and propose a novel fast iterative technique for real-time tracking of the time-varying frequencies. Simulation examples are given which compare the iterative method to other data-adaptive techniques. These examples show that the proposed method converges to good estimates of the frequencies much more quickly than the adaptive techniques as well as being able to perform better in tracking nonstationary sinusoids.

In multipulse LPC speech coding, there are a number of important issues which need to be addressed. The purpose of this paper is to report some of our work related to two of these issues. The first pertains to how one measures the quality of the synthetic speech for a given set of multipulse parameters. In this paper, we present a general set of frequency domain weighting functions which may incorporate various spectral characterizations of the speech. The second issue relates to how one determines the optimal set of pulse positions for a given set of of LPC filter coefficients. Current methods involve a sequential procedure, which is suboptimal compared with simultaneous positioning of pulses throughout an entire analysis frame. We therefore discuss an algorithm for simultaneous pulse positioning based on Pisarenko's harmonic decomposition.