The current study was conducted in 2013 to identify the seeds of three species of Amaranthus, Amaranthus viridis L., Amaranthus retroflexus L. and Amaranthus albus L., by using the artificial neural network (ANN) and canonical discriminant analysis (CDA) methods. To begin with, photographs were taken of the seeds and 13 morphological characteristics of each seed extracted as predictor variables. Backward regression was used to find the most influential variables and seven variables were derived. Thus, predictor variables were divided into two sets of 13 and seven morphological characteristics. The results showed that the recognition accuracy of the ANN made using 13 and seven predictor variables was 81.1 and 80.3%, respectively. Meanwhile, recognition accuracy of the CDA using the seven and 13 predictor variables was 74.0 and 75.7%, respectively. Therefore, in comparison to CDA, ANN showed higher identification accuracy; however, the difference was not statistically significant. Identification accuracy for A. retroflexus was higher using the CDA method than ANN, while the ANN method had higher recognition accuracy for A. viridis than CDA. In addition, use of 13 predictor variables yielded a greater identification accuracy than seven. The results of the current study showed that using seed morphological characteristics extracted by computer vision could be effective for reliable identification of the similar seeds of Amaranthus species.

There is a recent surge in research activities around “deep neural networks” (DNN). While the notion of neural networks have enjoyed cycles of enthusiasm, which may continue its ebb and flow, concrete advances now abound. Significant performance improvements have been shown in a number of pattern recognition tasks. As a technical topic, DNN is important in classes and tutorial articles and related learning resources are available. Streams of questions, nonetheless, never subside from students or researchers and there appears to be a frustrating tendency among the learners to treat DNN simply as a black box. This is an awkward and alarming situation in education. This paper thus has the intent to help the reader to properly understand DNN, not just its mechanism (what and how) but its motivation and justification (why). It is written from a developmental perspective with a comprehensive view, from the very basic but oft-forgotten principle of statistical pattern recognition and decision theory, through the problem stages that may be encountered during system design, to key ideas that led to the new advance. This paper can serve as a learning guide with historical reviews and important references, helpful in reaching an insightful understanding of the subject.

Many studies have assessed visual short-term memory (VSTM) abilities in children with specific language impairment (SLI), with contrasting results: some studies observed preserved VSTM capacities, while others reported impaired VSTM. The present study explores the hypothesis that the complexity of the visual information to be encoded and stored might underlie these discrepancies. Four VSTM conditions were administered to a group of 15 children with SLI, as well as to two groups of typically developing children, matched for chronological age and for VSTM capacity for visually simple stimuli, respectively. The stimuli to be remembered varied in their visual similarity and in the number of their visual features. Across the four VSTM conditions, children with SLI showed significantly reduced performance relative to an age-matched control group, and they were more strongly affected by visual similarity and number of features when compared to a control group matched for VSTM capacity for visually simple stimuli. The present results support the hypothesis that stimulus complexity is a determining factor of the poor VSTM performances in children with SLI. (JINS, 2012, 18, 501–510)

Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities (including “distributed representations”) or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explore systematically the complex interaction between learning and representation, as we try to demonstrate through the analysis of several large networks.

A descriptive function method was used to measure the detection, discrimination, and identification performance of a large population of single neurons recorded from within the primary visual cortex of the monkey and the cat, along six stimulus dimensions: contrast, spatial position, orientation, spatial frequency, temporal frequency, and direction of motion. First, the responses of single neurons were measured along each stimulus dimension, using analysis intervals comparable to a normal fixation interval (200 ms). Second, the measured responses of each neuron were fitted with simple descriptive functions, containing a few free parameters, for each stimulus dimension. These functions were found to account for approximately 90% of the variance in the measured response means and response standard deviations. (A detailed analysis of the relationship between the mean and the variance showed that the variance is proportional to the mean.) Third, the parameters of the best-fitting descriptive functions were utilized in conjunction with Bayesian (optimal) decision theory to determine the detection, discrimination, and identification performance for each neuron, along each stimulus dimension. For some of the cells in monkey, discrimination performance was comparable to behavioral performance; for most of the cells in cat, discrimination performance was better than behavioral performance. The behavioral contrast and spatial-frequency discrimination functions were similar in shape to the envelope of the most sensitive cells; they were also similar to the discrimination functions obtained by optimal pooling of the entire population of cells. The statistics which summarize the parameters of the descriptive functions were used to estimate the response of the visual cortex as a whole to a complex natural image. The analysis suggests that individual cortical neurons can reliably signal precise information about the location, size, and orientation of local image features.

Pigeons were trained on four different visual discrimination tasks: (1) concept of natural stimuli (food vs. non-food object discrimination); (2) arbitrary classification of natural stimuli (pseudoconcept); (3) concept of artificial stimuli (triangles generated by computer graphics); and (4) discrimination of one pair of artificial stimuli. Then, lesions of the ectostriatum were carried out. The ectostriatal lesions impaired the arbitrary classification of natural stimuli and the concept of artificial pattern but did not impair the natural concept or the simple discrimination of fixed two stimuli. Lesions in the neostriatum did not cause deficits in any discrimination task. The birds had to learn individual stimuli for the arbitrary classification of stimuli and the stimulus generalization test after the artificial pattern concept discrimination indicated that the pigeons formed a concept more complicated than “triangle” in human language. These results suggest that the ectostriatum plays a role in task discrimination that requires much visual processing to classify stimuli.

We suggest a new pretopological model for pattern recognition which was introduced to study complex economic systems. The model has its origin in the concept of “neighbour”, which is both primitive and fundamental in pattern recognition. Pretopology enables us to develop a perceptive and topological approach for patterns and to see that problems, apparently different, are in fact identical e.g. clustering and recognition, search of skeletons in image processing and search of an informative learning set. It should be noted that the suggeted model is more than a descriptive one.

Pattern recognition and object localization, using various sensors such as vision and tactile sensors, are two important areas of research in the application of robotic systems. This paper demonstrates the feasibility of using some relatively inexpensive array of pressure sensors and a neural network approach to achieve object localization and pattern recognition. The sensors that are used are force sensing resistors (FSRs), more specifically, a 16 x 16 array of FSRs. Because of the nonlinearity associated with a FSR, three possible approaches for gathering output from the sensor array are used. The neural network that is used consists of two 2-layer counterpropagation networks (CPNs). One of the CPNs is trained to recognize contact signatures of different objects placed on a fixed reference position on the sensor array.

Structural features like defects or heterointerfaces in crystals or amorphous phases give rise to different local patterns in high-resolution electron micrographs or object wave functions. Pattern recognition techniques can be used to identify these typical patterns that constitute the image itself, as was already demonstrated for compositional changes in isostructural heterostructures, where the patterns within unit cells of the lattice were analyzed. To extend such analyses to more complex materials, we examined patterns in small circular areas centered on intensity maxima of the image. Nonsupervised clustering, namely, Ward's clustering method, was applied to these patterns. In two examples, a highly defective ZnMnTe layer on GaAs and a tunnel magneto resistance device, we demonstrate how typical patterns are identified by this method and how these results can be used for a further investigation of the microstructural properties of the sample.

The upper limb radiograph is an extremely common request with trauma. The practising radiographer requires familiarity with normal and abnormal appearances. Recognition of fractures and dislocations is essential and illustrated in this article. This is especially so with the difficult paediatric elbow and suggestions are given for recognising fractures and often subtle dislocations such as the dislocated internal epicondyle. Lines of assessment at the elbow and the value of the elbow fat pad are highlighted.

The glycosylphosphatidylinositol (GPI) anchor of Plasmodium falciparum is thought to function as a critical toxin that contributes to severe malarial pathogenesis by eliciting the production of proinflammatory responses by the innate immune system of mammalian hosts. Analysis of the fine structure of P. falciparum GPI suggests a requirement for the presence of both core glycan and lipid moieties in the recognition and signalling of parasite glycolipids by host immune cells. It has been demonstrated that GPI anchors of various parasitic protozoa can mediate cellular immune responses via members of the Toll-like family of pattern recognition receptors (TLRs). Recent studies indicate that GPI anchors of P. falciparum and other protozoa are preferentially recognized by TLR-2, involving the MyD88-dependent activation of specific signalling pathways that mediate the production of proinflammatory cytokines and nitric oxide from host macrophages in vitro. However, the contribution of malaria GPI toxin to severe disease syndromes and the role of specific TLRs or other pattern recognition receptors in innate immunity in vivo is only just beginning to be characterized. A better understanding of the molecular mechanisms underlying severe malarial pathogenesis may yet lead to substantial new insights with important implications for the development of novel therapeutics for malaria treatment.

The last few years have witnessed important new developments inthe theory and practice of pattern classification. We intend tosurvey some of the main new ideas that have led to theserecent results.

Given a class Γ of curves in [0, 1]2, we ask: in a cloud of n uniform random points, how many points can lie on some curve γ ∈ Γ? Classes studied here include curves of length less than or equal to L, Lipschitz graphs, monotone graphs, twice-differentiable curves, and graphs of smooth functions with m-bounded derivatives. We find, for example, that there are twice-differentiable curves containing as many as OP(n1/3) uniform random points, but not essentially more than this. More generally, we consider point clouds in higher-dimensional cubes [0, 1]d and regular hypersurfaces of specified codimension, finding, for example, that twice-differentiable k-dimensional hypersurfaces in Rd may contain as many as OP(nk/(2d-k)) uniform random points. We also consider other notions of ‘incidence’, such as curves passing through given location/direction pairs, and find, for example, that twice-differentiable curves in R2 may pass through at most OP(n1/4) uniform random location/direction pairs. Idealized applications in image processing and perceptual psychophysics are described and several open mathematical questions are identified for the attention of the probability community.

the lower limb radiograph is an extremely common request with trauma and the practising radiographer requires familiarity with normal and abnormal appearances. normal variations in anatomy and the variable ossification centres often lead to some confusion. recognition of a haemarthrosis at the knee is clinically very useful and especially with tibial plateau fractures. suggestions for recognition of calcaneal fractures (boehler's angle) and midfoot/forefoot dislocations are illustrated.

The concentrations of major, minor and trace metals were measured in water samples collected from five shallow Antarctic lakes (Carezza, Edmonson Point (No 14 and 15a), Inexpressible Island and Tarn Flat) found in Terra Nova Bay (northern Victoria Land, Antarctica) during the Italian Expeditions of 1993-2001. The total concentrations of a large suite of elements (Al, As, Ba, Ca, Cd, Ce, Co, Cr, Cs, Cu, Fe, Ga, Gd, K, La, Li, Mg, Mn, Mo, Na, Nd, Ni, Pb, Pr, Rb, Sc, Si, Sr, Ta, Ti, U, V, Y, W, Zn and Zr) were determined using spectroscopic techniques (ICP-AES, GF-AAS and ICP-MS). The results are similar to those obtained for the freshwater lakes of the Larsemann Hills, East Antarctica, and for the McMurdo Dry Valleys. Principal Component Analysis (PCA) and Cluster Analysis (CA) were performed to identify groups of samples with similar characteristics and to find correlations between the variables. The variability observed within the water samples is closely connected to the sea spray input; hence, it is primarily a consequence of geographical and meteorological factors, such as distance from the ocean and time of year. The trace element levels, in particular those of heavy metals, are very low, suggesting an origin from natural sources rather than from anthropogenic contamination.