Concept: Pattern recognition
Spike pattern classification is a key topic in machine learning, computational neuroscience, and electronic device design. Here, we offer a new supervised learning rule based on Support Vector Machines (SVM) to determine the synaptic weights of a leaky integrate-and-fire (LIF) neuron model for spike pattern classification. We compare classification performance between this algorithm and other methods sharing the same conceptual framework. We consider the effect of postsynaptic potential (PSP) kernel dynamics on patterns separability, and we propose an extension of the method to decrease computational load. The algorithm performs well in generalization tasks. We show that the peak value of spike patterns separability depends on a relation between PSP dynamics and spike pattern duration, and we propose a particular kernel that is well-suited for fast computations and electronic implementations.
Memristive synapses, the most promising passive devices for synaptic interconnections in artificial neural networks, are the driving force behind recent research on hardware neural networks. Despite significant efforts to utilize memristive synapses, progress to date has only shown the possibility of building a neural network system that can classify simple image patterns. In this article, we report a high-density cross-point memristive synapse array with improved synaptic characteristics. The proposed PCMO-based memristive synapse exhibits the necessary gradual and symmetrical conductance changes, and has been successfully adapted to a neural network system. The system learns, and later recognizes, the human thought pattern corresponding to three vowels, i.e. /a /, /i /, and /u/, using electroencephalography signals generated while a subject imagines speaking vowels. Our successful demonstration of a neural network system for EEG pattern recognition is likely to intrigue many researchers and stimulate a new research direction.
One of the most relevant dermoscopic patterns is the pigment network. An innovative method of pattern recognition is presented for its detection in dermoscopy images.
Uncovering the neural dynamics of facial identity processing along with its representational basis outlines a major endeavor in the study of visual processing. To this end, here, we record human electroencephalography (EEG) data associated with viewing face stimuli; then, we exploit spatiotemporal EEG information to determine the neural correlates of facial identity representations and to reconstruct the appearance of the corresponding stimuli. Our findings indicate that multiple temporal intervals support: facial identity classification, face space estimation, visual feature extraction and image reconstruction. In particular, we note that both classification and reconstruction accuracy peak in the proximity of the N170 component. Further, aggregate data from a larger interval (50-650 ms after stimulus onset) support robust reconstruction results, consistent with the availability of distinct visual information over time. Thus, theoretically, our findings shed light on the time course of face processing while, methodologically, they demonstrate the feasibility of EEG-based image reconstruction.
High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.
Evading detection by predators is crucial for survival. Camouflage is therefore a widespread adaptation, but despite substantial research effort our understanding of different camouflage strategies has relied predominantly on artificial systems and on experiments disregarding how camouflage is perceived by predators. Here we show for the first time in a natural system, that survival probability of wild animals is directly related to their level of camouflage as perceived by the visual systems of their main predators. Ground-nesting plovers and coursers flee as threats approach, and their clutches were more likely to survive when their egg contrast matched their surrounds. In nightjars - which remain motionless as threats approach - clutch survival depended on plumage pattern matching between the incubating bird and its surrounds. Our findings highlight the importance of pattern and luminance based camouflage properties, and the effectiveness of modern techniques in capturing the adaptive properties of visual phenotypes.
Pattern-based identity signatures are commonplace in the animal kingdom, but how they are recognized is poorly understood. Here we develop a computer vision tool for analysing visual patterns, NATUREPATTERNMATCH, which breaks new ground by mimicking visual and cognitive processes known to be involved in recognition tasks. We apply this tool to a long-standing question about the evolution of recognizable signatures. The common cuckoo (Cuculus canorus) is a notorious cheat that sneaks its mimetic eggs into nests of other species. Can host birds fight back against cuckoo forgery by evolving highly recognizable signatures? Using NATUREPATTERNMATCH, we show that hosts subjected to the best cuckoo mimicry have evolved the most recognizable egg pattern signatures. Theory predicts that effective pattern signatures should be simultaneously replicable, distinctive and complex. However, our results reveal that recognizable signatures need not incorporate all three of these features. Moreover, different hosts have evolved effective signatures in diverse ways.
Cluster analysis is aimed at classifying elements into categories on the basis of their similarity. Its applications range from astronomy to bioinformatics, bibliometrics, and pattern recognition. We propose an approach based on the idea that cluster centers are characterized by a higher density than their neighbors and by a relatively large distance from points with higher densities. This idea forms the basis of a clustering procedure in which the number of clusters arises intuitively, outliers are automatically spotted and excluded from the analysis, and clusters are recognized regardless of their shape and of the dimensionality of the space in which they are embedded. We demonstrate the power of the algorithm on several test cases.
Bloodstain pattern analysis (BPA) is the investigation and interpretation of blood deposited at crime scenes. However, the interaction of blood and apparel fabrics has not been widely studied. In this work, the development of bloodstains (passive, absorbed and transferred) dropped from three different heights (500, 1,000, 1,500 mm) on two cotton apparel fabrics (1 × 1 rib knit, drill) was investigated. High-speed video was used to investigate the interaction of the blood and fabric at impact. The effect of drop height on the development of passive, absorbed and transferred bloodstains was investigated using image analysis and statistical tools. Visually, the passive bloodstain patterns produced on the technical face of fabrics from the different drop heights were similar. The blood soaked unequally through to the technical rear of both fabrics. Very little blood was transferred between a bloody fabric and a second piece of fabric. Statistically, drop height did not affect the size of the parent bloodstain (wet or dry), but did affect the number of satellite bloodstains formed. Some differences between the two fabrics were noted, therefore fabric structure and properties must be considered when conducting BPA on apparel fabrics.
Impact of a three-dimensional “hands-on” anatomic teaching module on acetabular fracture pattern recognition by orthopaedic residents
- The Journal of bone and joint surgery. American volume
- Published almost 8 years ago
Much of the difficulty in understanding acetabular fracture patterns is due to the complex three-dimensional relationship of the acetabulum to the greater pelvis. We hypothesized that combining three-dimensional “hands-on” anatomic models with two-dimensional informational teaching sheets would improve the ability of orthopaedic residents to accurately classify acetabular fracture patterns and aid in preoperative surgical approach selection.