CEDI: A Neural Model of Colour Vision, with Applications to Image Processing and Classification

Air Force Office of Scientific Research (F49620-01-1-0423); National Geospatial-Intelligence Agency (NMA 201-01-1-2016); National Science Foundation (SBE-035437, DEG-0221680); Office of Naval Research (N00014-01-1-0624)

ARTSCENE: A Neural System for Natural Scene Classification

How do humans rapidly recognize a scene? How can neural models capture this biological competence to achieve state-of-the-art scene classification? The ARTSCENE neural system classifies natural scene photographs by using multiple spatial scales to efficiently accumulate evidence for gist and texture. ARTSCENE embodies a coarse-to-fine Texture Size Ranking Principle whereby spatial attention processes multiple scales of scenic information, ranging from global gist to local properties of textures. The model can incrementally learn and predict scene identity by gist information alone and can improve performance through selective attention to scenic textures of progressively smaller size. ARTSCENE discriminates 4 landscape scene categories (coast, forest, mountain and countryside) with up to 91.58% correct on a test set, outperforms alternative models in the literature which use biologically implausible computations, and outperforms component systems that use either gist or texture information alone. Model simulations also show that adjacent textures form higher-order features that are also informative for scene recognition.

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.

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.

ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network

This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This supervised learning system is built up from a pair of Adaptive Resonance Theory modules (ARTa and ARTb) that are capable of self-organizing stable recognition categories in response to arbitrary sequences of input patterns. During training trials, the ARTa module receives a stream {a^(p)} of input patterns, and ARTb receives a stream {b^(p)} of input patterns, where b^(p) is the correct prediction given a^(p). These ART modules are linked by an associative learning network and an internal controller that ensures autonomous system operation in real time. During test trials, the remaining patterns a^(p) are presented without b^(p), and their predictions at ARTb are compared with b^(p). Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms, and achieves 100% accuracy after training on less than half the input patterns in the database. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. This computation increases the vigilance parameter ρa of ARTa by the minimal amount needed to correct a predictive error at ARTb· Parameter ρa calibrates the minimum confidence that ARTa must have in a category, or hypothesis, activated by an input a^(p) in order for ARTa to accept that category, rather than search for a better one through an automatically controlled process of hypothesis testing. Parameter ρa is compared with the degree of match between a^(p) and the top-down learned expectation, or prototype, that is read-out subsequent to activation of an ARTa category. Search occurs if the degree of match is less than ρa. ARTMAP is hereby a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success. As a result, rare but important events can be quickly and sharply distinguished even if they are similar to frequent events with different consequences. Between input trials ρa relaxes to a baseline vigilance pa When ρa is large, the system runs in a conservative mode, wherein predictions are made only if the system is confident of the outcome. Very few false-alarm errors then occur at any stage of learning, yet the system reaches asymptote with no loss of speed. Because ARTMAP learning is self stabilizing, it can continue learning one or more databases, without degrading its corpus of memories, until its full memory capacity is utilized.

Fuzzy ART: An Adaptive Resonance Algorithm for Rapid, Stable Classification of Analog Patterns

The Fuzzy ART system introduced herein incorporates computations from fuzzy set theory into ART 1. For example, the intersection (n) operator used in ART 1 learning is replaced by the MIN operator (A) of fuzzy set theory. Fuzzy ART reduces to ART 1 in response to binary input vectors, but can also learn stable categories in response to analog input vectors. In particular, the MIN operator reduces to the intersection operator in the binary case. Learning is stable because all adaptive weights can only decrease in time. A preprocessing step, called complement coding, uses on-cell and off-cell responses to prevent category proliferation. Complement coding normalizes input vectors while preserving the amplitudes of individual feature activations.

Construction of Neural Network Classification Expert Systems Using Switching Theory Algorithms

A new family of neural network architectures is presented. This family of architectures solves the problem of constructing and training minimal neural network classification expert systems by using switching theory. The primary insight that leads to the use of switching theory is that the problem of minimizing the number of rules and the number of IF statements (antecedents) per rule in a neural network expert system can be recast into the problem of minimizing the number of digital gates and the number of connections between digital gates in a Very Large Scale Integrated (VLSI) circuit. The rules that the neural network generates to perform a task are readily extractable from the network's weights and topology. Analysis and simulations on the Mushroom database illustrate the system's performance.

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.

Digital signal processing and artificial intelligence for the automated classification of food allergy

As a by-product of the ‘information revolution’ which is currently unfolding, lifetimes of man (and indeed computer) hours are being allocated for the automated and intelligent interpretation of data. This is particularly true in medical and clinical settings, where research into machine-assisted diagnosis of physiological conditions gains momentum daily. Of the conditions which have been addressed, however, automated classification of allergy has not been investigated, even though the numbers of allergic persons are rising, and undiagnosed allergies are most likely to elicit fatal consequences. On the basis of the observations of allergists who conduct oral food challenges (OFCs), activity-based analyses of allergy tests were performed. Algorithms were investigated and validated by a pilot study which verified that accelerometer-based inquiry of human movements is particularly well-suited for objective appraisal of activity. However, when these analyses were applied to OFCs, accelerometer-based investigations were found to provide very poor separation between allergic and non-allergic persons, and it was concluded that the avenues explored in this thesis are inadequate for the classification of allergy. Heart rate variability (HRV) analysis is known to provide very significant diagnostic information for many conditions. Owing to this, electrocardiograms (ECGs) were recorded during OFCs for the purpose of assessing the effect that allergy induces on HRV features. It was found that with appropriate analysis, excellent separation between allergic and nonallergic subjects can be obtained. These results were, however, obtained with manual QRS annotations, and these are not a viable methodology for real-time diagnostic applications. Even so, this was the first work which has categorically correlated changes in HRV features to the onset of allergic events, and manual annotations yield undeniable affirmation of this. Fostered by the successful results which were obtained with manual classifications, automatic QRS detection algorithms were investigated to facilitate the fully automated classification of allergy. The results which were obtained by this process are very promising. Most importantly, the work that is presented in this thesis did not obtain any false positive classifications. This is a most desirable result for OFC classification, as it allows complete confidence to be attributed to classifications of allergy. Furthermore, these results could be particularly advantageous in clinical settings, as machine-based classification can detect the onset of allergy which can allow for early termination of OFCs. Consequently, machine-based monitoring of OFCs has in this work been shown to possess the capacity to significantly and safely advance the current state of clinical art of allergy diagnosis

Thomas Wolfe and the genre question: Beyond the "charge of autobiography"

The North Carolinian author Thomas Wolfe (1900‐1938) has long suffered under the “charge of autobiography,” which lingers to this day in critical assessments of his work. Criticism of Wolfe is frequently concerned with questions of generic classification, but since the 1950s, re‐assessments of Wolfe’s work have suggested that Wolfe’s “autobiographical fiction” exhibits a complexity that merits further investigation. Strides in autobiographical and narrative theory have prompted reconsiderations of texts that defy the artificial boundaries of autobiography and fiction. Wolfe has been somewhat neglected in the canon of American fiction of his era, but deserves to be reconsidered in terms of how he engages with the challenges and contradictions of writing about or around the self. This thesis investigates why Wolfe’s work has been the source of considerable critical discomfort and confusion with regard to the relationship between Wolfe’s life and his writing. It explores this issue through an examination of elements of Wolfe’s work that problematise categorisation. Firstly, it investigates the concept of Wolfe as “storyteller.” It explores the motivations and philosophies that underpin Wolfe’s work and his concept of himself as a teller of tales, and examines aspects of Wolfe’s writing process that have their roots in medieval traditions of the memorisation and recitation of tales. The thesis then conducts a detailed examination of how Wolfe describes the process of transforming his memory into narrative through writing. The latter half of the thesis examines narrative techniques used by Wolfe, firstly analysing his extensive use of the iterative and pseudo‐iterative modes, and then his unusual deployment of narrators and focalization. This project sheds light on elements of Wolfe’s approach to writing and narrative strategies that he employs that have previously been overlooked, and that have created considerable critical confusion with regard to the supposedly “autobiographical” genesis of his work.

Neonatal EEG classification using atomic decomposition

The electroencephalogram (EEG) is an important noninvasive tool used in the neonatal intensive care unit (NICU) for the neurologic evaluation of the sick newborn infant. It provides an excellent assessment of at-risk newborns and formulates a prognosis for long-term neurologic outcome.The automated analysis of neonatal EEG data in the NICU can provide valuable information to the clinician facilitating medical intervention. The aim of this thesis is to develop a system for automatic classification of neonatal EEG which can be mainly divided into two parts: (1) classification of neonatal EEG seizure from nonseizure, and (2) classifying neonatal background EEG into several grades based on the severity of the injury using atomic decomposition. Atomic decomposition techniques use redundant time-frequency dictionaries for sparse signal representations or approximations. The first novel contribution of this thesis is the development of a novel time-frequency dictionary coherent with the neonatal EEG seizure states. This dictionary was able to track the time-varying nature of the EEG signal. It was shown that by using atomic decomposition and the proposed novel dictionary, the neonatal EEG transition from nonseizure to seizure states could be detected efficiently. The second novel contribution of this thesis is the development of a neonatal seizure detection algorithm using several time-frequency features from the proposed novel dictionary. It was shown that the time-frequency features obtained from the atoms in the novel dictionary improved the seizure detection accuracy when compared to that obtained from the raw EEG signal. With the assistance of a supervised multiclass SVM classifier and several timefrequency features, several methods to automatically grade EEG were explored. In summary, the novel techniques proposed in this thesis contribute to the application of advanced signal processing techniques for automatic assessment of neonatal EEG recordings.

Genetic Studies Identify Critical Biomarkers and Refine the Classification of Malignant Gliomas

Gliomagenesis is driven by a complex network of genetic alterations and while the glioma genome has been a focus of investigation for many years; critical gaps in our knowledge of this disease remain. The identification of novel molecular biomarkers remains a focus of the greater cancer community as a method to improve the consistency and accuracy of pathological diagnosis. In addition, novel molecular biomarkers are drastically needed for the identification of targets that may ultimately result in novel therapeutics aimed at improving glioma treatment. Through the identification of new biomarkers, laboratories will focus future studies on the molecular mechanisms that underlie glioma development. Here, we report a series of genomic analyses identifying novel molecular biomarkers in multiple histopathological subtypes of glioma and refine the classification of malignant gliomas. We have completed a large scale analysis of the WHO grade II-III astrocytoma exome and report frequent mutations in the chromatin modifier, alpha thalassemia mental retardation x-linked (ATRX), isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2), and mutations in tumor protein 53 (TP53) as the most frequent genetic mutations in low grade astrocytomas. Furthermore, by analyzing the status of recurrently mutated genes in 363 brain tumors, we establish that highly recurrent gene mutational signatures are an effective tool in stratifying homogeneous patient populations into distinct groups with varying outcomes, thereby capable of predicting prognosis. Next, we have established mutations in the promoter of telomerase reverse transcriptase (TERT) as a frequent genetic event in gliomas and in tissues with low rates of self renewal. We identify TERT promoter mutations as the most frequently mutated gene in primary glioblastoma. Additionally, we show that TERT promoter mutations in combination with IDH1 and IDH2 mutations are able to delineate distinct clinical tumor cohorts and are capable of predicting median overall survival more effectively than standard histopathological diagnosis alone. Taken together, these data advance our understanding of the genetic alterations that underlie the transformation of glial cells into neoplasms and we provide novel genetic biomarkers and multi – gene mutational signatures that can be utilized to refine the classification of malignant gliomas and provide opportunity for improved diagnosis.

Night-time neuronal activation of Cluster N in a day- and night-migrating songbird.

Magnetic compass orientation in a night-migratory songbird requires that Cluster N, a cluster of forebrain regions, is functional. Cluster N, which receives input from the eyes via the thalamofugal pathway, shows high neuronal activity in night-migrants performing magnetic compass-guided behaviour at night, whereas no activation is observed during the day, and covering up the birds' eyes strongly reduces neuronal activation. These findings suggest that Cluster N processes light-dependent magnetic compass information in night-migrating songbirds. The aim of this study was to test if Cluster N is active during daytime migration. We used behavioural molecular mapping based on ZENK activation to investigate if Cluster N is active in the meadow pipit (Anthus pratensis), a day- and night-migratory species. We found that Cluster N of meadow pipits shows high neuronal activity under dim-light at night, but not under full room-light conditions during the day. These data suggest that, in day- and night-migratory meadow pipits, the light-dependent magnetic compass, which requires an active Cluster N, may only be used during night-time, whereas another magnetosensory mechanism and/or other reference system(s), like the sun or polarized light, may be used as primary orientation cues during the day.

The ocean sampling day consortium.

Ocean Sampling Day was initiated by the EU-funded Micro B3 (Marine Microbial Biodiversity, Bioinformatics, Biotechnology) project to obtain a snapshot of the marine microbial biodiversity and function of the world's oceans. It is a simultaneous global mega-sequencing campaign aiming to generate the largest standardized microbial data set in a single day. This will be achievable only through the coordinated efforts of an Ocean Sampling Day Consortium, supportive partnerships and networks between sites. This commentary outlines the establishment, function and aims of the Consortium and describes our vision for a sustainable study of marine microbial communities and their embedded functional traits.

Sheep carcasse classification as a tool to improve the marketing system

p.103-111