An Active Pattern Recognition Architecture for Mobile Robots

An active, attentionally-modulated recognition architecture is proposed for object recognition and scene analysis. The proposed architecture forms part of navigation and trajectory planning modules for mobile robots. Key characteristics of the system include movement planning and execution based on environmental factors and internal goal definitions. Real-time implementation of the system is based on space-variant representation of the visual field, as well as an optimal visual processing scheme utilizing separate and parallel channels for the extraction of boundaries and stimulus qualities. A spatial and temporal grouping module (VWM) allows for scene scanning, multi-object segmentation, and featural/object priming. VWM is used to modulate a tn~ectory formation module capable of redirecting the focus of spatial attention. Finally, an object recognition module based on adaptive resonance theory is interfaced through VWM to the visual processing module. The system is capable of using information from different modalities to disambiguate sensory input.

Fusion Artmap: A Neural Network Architecture for Multi-Channel Data Fusion and Classification

Fusion ARTMAP is a self-organizing neural network architecture for multi-channel, or multi-sensor, data fusion. Single-channel Fusion ARTMAP is functionally equivalent to Fuzzy ART during unsupervised learning and to Fuzzy ARTMAP during supervised learning. The network has a symmetric organization such that each channel can be dynamically configured to serve as either a data input or a teaching input to the system. An ART module forms a compressed recognition code within each channel. These codes, in turn, become inputs to a single ART system that organizes the global recognition code. When a predictive error occurs, a process called paraellel match tracking simultaneously raises vigilances in multiple ART modules until reset is triggered in one of them. Parallel match tracking hereby resets only that portion of the recognition code with the poorest match, or minimum predictive confidence. This internally controlled selective reset process is a type of credit assignment that creates a parsimoniously connected learned network. Fusion ARTMAP's multi-channel coding is illustrated by simulations of the Quadruped Mammal database.

Evaluation of Speaker Normalization Methods for Vowel Recognition Using Fuzzy ARTMAP and K-NN

A procedure that uses fuzzy ARTMAP and K-Nearest Neighbor (K-NN) categorizers to evaluate intrinsic and extrinsic speaker normalization methods is described. Each classifier is trained on preprocessed, or normalized, vowel tokens from about 30% of the speakers of the Peterson-Barney database, then tested on data from the remaining speakers. Intrinsic normalization methods included one nonscaled, four psychophysical scales (bark, bark with end-correction, mel, ERB), and three log scales, each tested on four different combinations of the fundamental (Fo) and the formants (F1 , F2, F3). For each scale and frequency combination, four extrinsic speaker adaptation schemes were tested: centroid subtraction across all frequencies (CS), centroid subtraction for each frequency (CSi), linear scale (LS), and linear transformation (LT). A total of 32 intrinsic and 128 extrinsic methods were thus compared. Fuzzy ARTMAP and K-NN showed similar trends, with K-NN performing somewhat better and fuzzy ARTMAP requiring about 1/10 as much memory. The optimal intrinsic normalization method was bark scale, or bark with end-correction, using the differences between all frequencies (Diff All). The order of performance for the extrinsic methods was LT, CSi, LS, and CS, with fuzzy AHTMAP performing best using bark scale with Diff All; and K-NN choosing psychophysical measures for all except CSi.

The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.

Fusion ARTMAP: An Adaptive Fuzzy Network for Multi-Channel Classification

Fusion ARTMAP is a self-organizing neural network architecture for multi-channel, or multi-sensor, data fusion. Fusion ARTMAP generalizes the fuzzy ARTMAP architecture in order to adaptively classify multi-channel data. The network has a symmetric organization such that each channel can be dynamically configured to serve as either a data input or a teaching input to the system. An ART module forms a compressed recognition code within each channel. These codes, in turn, beco1ne inputs to a single ART system that organizes the global recognition code. When a predictive error occurs, a process called parallel match tracking simultaneously raises vigilances in multiple ART modules until reset is triggered in one of thmn. Parallel match tracking hereby resets only that portion of the recognition code with the poorest match, or minimum predictive confidence. This internally controlled selective reset process is a type of credit assignment that creates a parsimoniously connected learned network.

The Hippocampus and Cerebellum in Adaptively Timed Learning, Recognition, and Movement

The concepts of declarative memory and procedural memory have been used to distinguish two basic types of learning. A neural network model suggests how such memory processes work together as recognition learning, reinforcement learning, and sensory-motor learning take place during adaptive behaviors. To coordinate these processes, the hippocampal formation and cerebellum each contain circuits that learn to adaptively time their outputs. Within the model, hippocampal timing helps to maintain attention on motivationally salient goal objects during variable task-related delays, and cerebellar timing controls the release of conditioned responses. This property is part of the model's description of how cognitive-emotional interactions focus attention on motivationally valued cues, and how this process breaks down due to hippocampal ablation. The model suggests that the hippocampal mechanisms that help to rapidly draw attention to salient cues could prematurely release motor commands were not the release of these commands adaptively timed by the cerebellum. The model hippocampal system modulates cortical recognition learning without actually encoding the representational information that the cortex encodes. These properties avoid the difficulties faced by several models that propose a direct hippocampal role in recognition learning. Learning within the model hippocampal system controls adaptive timing and spatial orientation. Model properties hereby clarify how hippocampal ablations cause amnesic symptoms and difficulties with tasks which combine task delays, novelty detection, and attention towards goal objects amid distractions. When these model recognition, reinforcement, sensory-motor, and timing processes work together, they suggest how the brain can accomplish conditioning of multiple sensory events to delayed rewards, as during serial compound conditioning.

ART 2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition

This article introduces ART 2-A, an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders of magnitude faster. Analysis and simulations show how the ART 2-A systems correspond to ART 2 dynamics at both the fast-learn limit and at intermediate learning rates. Intermediate learning rates permit fast commitment of category nodes but slow recoding, analogous to properties of word frequency effects, encoding specificity effects, and episodic memory. Better noise tolerance is hereby achieved without a loss of learning stability. The ART 2 and ART 2-A systems are contrasted with the leader algorithm. The speed of ART 2-A makes practical the use of ART 2 modules in large-scale neural computation.

The broad-scale distribution and abundance of Scyphomedusae in Irish waters

Scyphomedusae are receiving increasing recognition as key components of marine ecosystems. However, information on their distribution and abundance beyond coastal waters is generally lacking. Organising access to such data is critical to effectively transpose findings from laboratory, mesocosm and small scale studies to the scale of ecological processes. These data are also required to identify the risks of detrimental impacts of jellyfish blooms on human activities. In Ireland, such risks raise concerns among the public, but foremost amongst the professionals of the aquaculture and fishing sectors. The present work looked at the opportunity to get access to new information on the distribution of jellyfish around Ireland mostly by using existing infrastructures and programmes. The analysis of bycatch data collected during the Irish groundfish surveys provided new insights into the distribution of Pelagia noctiluca over an area >160 000 km2, a scale never reached before in a region of the Northeast Atlantic (140 sampling stations). Similarly, 4 years of data collected during the Irish Sea juvenile gadoid fish survey provided the first spatially, explicit, information on the abundance of Aurelia aurita and Cyanea spp. (Cyanea capillata and Cyanea lamarckii) throughout the Irish Sea (> 200 sampling events). In addition, the use of ships of opportunity allowed repeated samplings (N = 37) of an >100 km long transect between Dublin (Ireland) and Holyhead (Wales, UK), therefore providing two years of seasonal monitoring of the occurrence of scyphomedusae in that region. Finally, in order to inform the movements of C. capillata in an area where many negative interactions with bathers occur, the horizontal and vertical movements of 5 individual C. capillata were investigated through acoustic tracking.

Multi-sensor classification of tennis strokes

In this work, we investigate tennis stroke recognition using a single inertial measuring unit attached to a player’s forearm during a competitive match. This paper evaluates the best approach for stroke detection using either accelerometers, gyroscopes or magnetometers, which are embedded into the inertial measuring unit. This work concludes what is the optimal training data set for stroke classification and proves that classifiers can perform well when tested on players who were not used to train the classifier. This work provides a significant step forward for our overall goal, which is to develop next generation sports coaching tools using both inertial and visual sensors in an instrumented indoor sporting environment.

Form-focused instruction in Irish-medium immersion education: a critical examination of teachers' perspectives and practices. A small-scale qualitative case study

It has been suggested that the less than optimal levels of students’ immersion language “persist in part because immersion teachers lack systematic approaches for integrating language into their content instruction” (Tedick, Christian and Fortune, 2011, p.7). I argue that our current lack of knowledge regarding what immersion teachers think, know and believe and what immersion teachers’ actual ‘lived’ experiences are in relation to form-focused instruction (FFI) prevents us from fully understanding the key issues at the core of experiential immersion pedagogy and form-focused integration. FFI refers to “any planned or incidental instructional activity that is intended to induce language learners to pay attention to linguistic form” (Ellis, 2001b, p.1). The central aim of this research study is to critically examine the perspectives and practices of Irish-medium immersion (IMI) teachers in relation to FFI. The study ‘taps’ into the lived experiences of three IMI teachers in three different IMI school contexts and explores FFI from a classroom-based, teacher-informed perspective. Philosophical underpinnings of the interpretive paradigm and critical hermeneutical principles inform and guide the study. A multi-case study approach was adopted and data was gathered through classroom observation, video-stimulated recall and semistructured interviews. Findings revealed that the journey of ‘becoming’ an IMI teacher is shaped by a vast array of intricate variables. IMI teacher identity, implicit theories, stated beliefs, educational biographies and experiences, IMI school cultures and contexts as well as teacher knowledge and competence impacted on IMI teachers’ FFI perspectives and practices. An IMI content teacher identity reflected the teachers’ priorities as shaped by pedagogical challenges and their educational backgrounds. While research participants had clearly defined instructional beliefs and goals, their roadmap of how to actually accomplish these goals was far from clear. IMI teachers described the multitude of choices and pedagogical dilemmas they faced in integrating FFI into experiential pedagogy. Significant gaps in IMI teachers’ declarative knowledge about and competence in the immersion language were also reported. This research study increases our understanding of the complexity of the processes underlying and shaping FFI pedagogy in IMI education. Innovative FFI opportunities for professional development across the continuum of teacher education are outlined, a comprehensive evaluation of IMI is called for and areas for further research are delineated.

Multi-touch accceptance: perceived disorientation and consequences on task engagement

The research project takes place within the technology acceptability framework which tries to understand the use made of new technologies, and concentrates more specifically on the factors that influence multi-touch devices’ (MTD) acceptance and intention to use. Why be interested in MTD? Nowadays, this technology is used in all kinds of human activities, e.g. leisure, study or work activities (Rogowski and Saeed, 2012). However, the handling or the data entry by means of gestures on multi-touch-sensitive screen imposes a number of constraints and consequences which remain mostly unknown (Park and Han, 2013). Currently, few researches in ergonomic psychology wonder about the implications of these new human-computer interactions on task fulfillment.This research project aims to investigate the cognitive, sensori-motor and motivational processes taking place during the use of those devices. The project will analyze the influences of the use of gestures and the type of gesture used: simple or complex gestures (Lao, Heng, Zhang, Ling, and Wang, 2009), as well as the personal self-efficacy feeling in the use of MTD on task engagement, attention mechanisms and perceived disorientation (Chen, Linen, Yen, and Linn, 2011) when confronted to the use of MTD. For that purpose, the various above-mentioned concepts will be measured within a usability laboratory (U-Lab) with self-reported methods (questionnaires) and objective indicators (physiological indicators, eye tracking). Globally, the whole research aims to understand the processes at stakes, as well as advantages and inconveniences of this new technology, to favor a better compatibility and adequacy between gestures, executed tasks and MTD. The conclusions will allow some recommendations for the use of the DMT in specific contexts (e.g. learning context).

Informatic Opacity: Biometric Facial Recognition and the Aesthetics and Politics of Defacement

Confronting the rapidly increasing, worldwide reliance on biometric technologies to surveil, manage, and police human beings, my dissertation Informatic Opacity: Biometric Facial Recognition and the Aesthetics and Politics of Defacement charts a series of queer, feminist, and anti-racist concepts and artworks that favor opacity as a means of political struggle against surveillance and capture technologies in the 21st century. Utilizing biometric facial recognition as a paradigmatic example, I argue that today's surveillance requires persons to be informatically visible in order to control them, and such visibility relies upon the production of technical standardizations of identification to operate globally, which most vehemently impact non- normative, minoritarian populations. Thus, as biometric technologies turn exposures of the face into sites of governance, activists and artists strive to make the face biometrically illegible and refuse the political recognition biometrics promises through acts of masking, escape, and imperceptibility. Although I specifically describe tactics of making the face unrecognizable as "defacement," I broadly theorize refusals to visually cohere to digital surveillance and capture technologies' gaze as "informatic opacity," an aesthetic-political theory and practice of anti- normativity at a global, technical scale whose goal is maintaining the autonomous determination of alterity and difference by evading the quantification, standardization, and regulation of identity imposed by biometrics and the state. My dissertation also features two artworks: Facial Weaponization Suite, a series of masks and public actions, and Face Cages, a critical, dystopic installation that investigates the abstract violence of biometric facial diagramming and analysis. I develop an interdisciplinary, practice-based method that pulls from contemporary art and aesthetic theory, media theory and surveillance studies, political and continental philosophy, queer and feminist theory, transgender studies, postcolonial theory, and critical race studies.

Automatic and effective multi-dimensional parallelisation of structured mesh based codes

The most common parallelisation strategy for many Computational Mechanics (CM) (typified by Computational Fluid Dynamics (CFD) applications) which use structured meshes, involves a 1D partition based upon slabs of cells. However, many CFD codes employ pipeline operations in their solution procedure. For parallelised versions of such codes to scale well they must employ two (or more) dimensional partitions. This paper describes an algorithmic approach to the multi-dimensional mesh partitioning in code parallelisation, its implementation in a toolkit for almost automatically transforming scalar codes to parallel form, and its testing on a range of ‘real-world’ FORTRAN codes. The concept of multi-dimensional partitioning is straightforward, but non-trivial to represent as a sufficiently generic algorithm so that it can be embedded in a code transformation tool. The results of the tests on fine real-world codes demonstrate clear improvements in parallel performance and scalability (over a 1D partition). This is matched by a huge reduction in the time required to develop the parallel versions when hand coded – from weeks/months down to hours/days.

Macro-segregation of multi-component alloys in shape casting simulation

The objective of this work is to present a new scheme for temperature-solute coupling in a solidification model, where the temperature and concentration fields simultaneously satisfy the macro-scale transport equations and, in the mushy region, meet the constraints imposed by the thermodynamics and the local scale processes. A step-by-step explanation of the macrosegregation algorithm, implemented in the finite volume unstructured mesh multi-physics modelling code PHYSICA, is initially presented and then the proposed scheme is validated against experimental results obtained by Krane for binary and a ternary alloys.

Multi-physics modelling for microelectronics and microsystems - current capabilities and future challenges

At present the vast majority of Computer-Aided- Engineering (CAE) analysis calculations for microelectronic and microsystems technologies are undertaken using software tools that focus on single aspects of the physics taking place. For example, the design engineer may use one code to predict the airflow and thermal behavior of an electronic package, then another code to predict the stress in solder joints, and then yet another code to predict electromagnetic radiation throughout the system. The reason for this focus of mesh-based codes on separate parts of the governing physics is essentially due to the numerical technologies used to solve the partial differential equations, combined with the subsequent heritage structure in the software codes. Using different software tools, that each requires model build and meshing, leads to a large investment in time, and hence cost, to undertake each of the simulations. During the last ten years there has been significant developments in the modelling community around multi- physics analysis. These developments are being followed by many of the code vendors who are now providing multi-physics capabilities in their software tools. This paper illustrates current capabilities of multi-physics technology and highlights some of the future challenges