Fusion Of Ridges Research Articles

Multimodal spatio-temporal-spectral fusion for deep learning applications in physiological time series processing: A case study in monitoring the depth of anesthesia

Physiological signals processing brings challenges including dimensionality (due to the number of channels), heterogeneity (due to the different range of values) and multimodality (due to the different sources). In this regard, the current study intended, first, to use time-frequency ridge mapping in exploring the use of fused information from joint EEG-ECG recordings in tracking the transition between different states of anesthesia. Second, it investigated the effectiveness of pre-trained state-of-the-art deep learning architectures for learning discriminative features in the fused data in order to classify the states during anesthesia. Experimental data from healthy-brain patients undergoing operation (N = 20) were used for this study. Data was recorded from the BrainStatus device with single ECG and 10 EEG channels. The obtained results support the hypothesis that not only can ridge fusion capture temporal-spectral progression patterns across all modalities and channels, but also this simplified interpretation of time-frequency representation accelerates the training process and yet improves significantly the efficiency of deep models. Classification outcomes demonstrates that this fusion could yields a better performance, in terms of 94.14% precision and 0.28 s prediction time, compared to commonly used data-level fusing methods. To conclude, the proposed fusion technique provides the possibility of embedding time-frequency information as well as spatial dependencies over modalities and channels in just a 2D array. This integration technique shows significant benefit in obtaining a more unified and global view of different aspects of physiological data at hand, and yet maintaining the desired performance level in decision making.

Large Dimensional Time-Varying GMM Estimation: A New Approach

We develop a novel machine learning method to estimate large dimensional time-varying GMM models via our newly designed ridge fusion regularization scheme. Our method is a one-step procedure and allows for abrupt, smooth and dual type time variation with a fast rate of convergence. It outperforms state-of-the-art smoothed nonparametric methods for both small and large samples. We investigate the pricing ability of dynamic four-factor and consumption-based asset pricing models. We show that a dynamic SDF obtained by our method, which allows a rich set of conditioning variables to jointly determine time variation, has a significantly enhanced pricing ability while enjoying reduced time series errors.

A Study on Defect Identification of Planetary Gearbox under Large Speed Oscillation

Rotational speed of a reference shaft is the key information for planetary gearbox condition monitoring under nonstationary conditions. As the time-variant speed and load of planetary gearboxes result in time-variant characteristic frequencies as well as vibration magnitudes, the conventional methods tracking time-frequency ridge perform a poor robustness, especially for large speed variations. In this paper, two schemes, time-frequency ridge fusion and logarithm transformation, are proposed to track the targeted ridge curve reliably. Meanwhile, the identified ridge curve by logarithm scheme can be further refined by the time-frequency ridge fusion scheme. Hence, a procedure involving the proposed ridge estimation methods is presented to diagnose the planetary gearbox defects. Two simulation signals and a vibration signal collected from a planetary gearbox in practical engineering (provided by the conference on condition monitoring of machinery in nonstationary operations (CMMNO)) are used to verify the proposed methods. It is validated that the proposed methods can well-track the targeted ridge curve compared with two conventional methods. As a result, the characteristic frequency of each component in the planetary gearbox is clearly demonstrated and the inner race defect of one of the planet bearings is successfully discovered in the order spectrum depending on the derived expression of planet bearing fault frequency.

Ridge Fusion in Statistical Learning

This article proposes a penalized likelihood method to jointly estimate multiple precision matrices for use in quadratic discriminant analysis (QDA) and model-based clustering. We use a ridge penalty and a ridge fusion penalty to introduce shrinkage and promote similarity between precision matrix estimates. We use blockwise coordinate descent for optimization, and validation likelihood is used for tuning parameter selection. Our method is applied in QDA and semi-supervised model-based clustering.

Cell organization of barb ridges in regenerating feathers of the quail: implications of the elongation of barb ridges for the evolution and diversification of feathers

AbstractThis ultrastructural study on the regenerating feathers of quail describes the cellular organization of the barb ridges responsible for the ramification of adult feathers. Bilateral symmetry of the barb ridges determines the organization of feather cells into feather branching. The length of the barb ridges, derived from the number of cells associated to form the barbule plates, determines the length of the barbule branching. Long chains of barb cells form long barbs that branch from the rachis with an increase of feather size. Supportive cells function as spacers between the barbule cells. New cells derive from stem cells localized in the collar region of the feather follicle, as indicated from the re‐organization of collar cells into barb ridges (a morphogenetic process inherited from that of embryonic feathers), production of an embryonic type of keratin (feather keratin), permanence of periderm granules (typical embryonic organelles) in barb vane ridge cells. Variations in the process of barb ridge morphogenesis allow the fusion of ridges into a rachis. The differentiation of hooklets contributes to the origin of planar feathers. Separation between rachis and merging barb ridges is by supportive cells, derived from the marginal plates of the barb ridges. Speculations on the evolution and diversification of feathers are presented.

Cell structure of developing downfeathers in the zebrafinch with emphasis on barb ridge morphogenesis

The present ultrastructural and immunocytochemical study on the embryonic feathers of the zebrafinch, an altricial passerine bird, describes cellular differentiation of developing downfeathers. Barb ridges are folds of the original epidermis of the embryonic feather germ in which the basal-apical polarity of epidermal cells is upset. The result is the loss of most germinal activity of basal cells of the barb ridges so that only the embryonic epidermal layers remain. The more external layer is the primary periderm, followed by 4-6 layers of inner-periderm cells that mature into feather sheath and barb vane ridge cells. The following layer, the subperiderm, produces a small type of beta-keratin typical of feathers. In barb ridges, the subperiderm layer is displaced to form barbule plates and barb cells. The formation of branching barbules occurs by the presence of barb vane ridge cells that function as spacers between barbule cells. The fourth layer is homologous to the germinal layer of the epidermis, but in barb ridges it rapidly loses the germinal capability and becomes the cyclindrical layer of marginal plates. The study indicates that a necrotic process determines the carving out of the final feather shape, although apoptosis may also play a role. In fact, after barb and barbule cells have formed a keratinized syncitium, retraction of the vascular bed determines anoxia with the resultant necrosis of all feather cells. Only those of the keratinized syncitium remain to form the feather while supportive cells disappear. The sheath covering the barb and barbule syncitium is lost by the formation of a sloughing layer following degeneration of external barb ridge vane cells and loss of the sheath. It is proposed that the evolution of the morphogenetic process of barb ridge formation was peculiar to tubular outgrowths of the integument of archosaurian reptiles that evolved into birds. Once established in the embryonic programmes of skin morphogenesis of ancient birds, variations in the process of barb ridge morphogenesis allowed the fusion of ridges into large or branched ridges that originated the rachis. This process produced pennaceous feathers, among which were those later used for flight. The present study stresses that the morphogenetic process of barb ridge formation determines the concomitant appearance of barbs and barbules. As a consequence, intermediate forms of evolving feathers with only barbs but not barbules are unlikely or are derived from alteration of the above basic morphogenetic mechanism.

Cell structure of barb ridges in down feathers and juvenile wing feathers of the developing chick embryo: Barb ridge modification in relation to feather evolution

The present study deals with the cell structure and three-dimensional organization of barb and barbule cells within barb ridges of down feathers and juvenile feathers in the chick embryo. Juvenile feathers represent the second generation of feathers in the wing, and replace down feathers some weeks after hatching. Within the follicle of juvenile feathers, at 16-18 days of embryonic development, barb ridges are more numerous than in down feathers. Barb ridges of juvenile feathers contain more cells in their barbule and axial plates with respect to barb ridges of down feathers. This condition determines the formation of longer barbules inserted in the rami of juvenile feathers than barbules of down feathers. Barb ridges of juvenile feathers merge with the rachidial ridge so that pennaceous feathers are formed. Barbule cells are surrounded by cytoplasmic elongation from barb vane ridge cells located in the axial plate, which constitute most of the axial plate. The degeneration of supportive cells among barbule cells branching from barbs determine the formation of spaces between barbules. The study emphasizes that, in addition to the size of the dermal papilla, it is the length of barb ridges and the infiltration of barb ridge vane cells among barbule cells that determine the size and length of feathers. The knowledge of the cell structure of barb ridges allows understanding not only of how feathers develop but also gives insights into their evolution. Based on changes of the process of barb ridge morphogenesis some hypotheses on the evolution of plumulaceous and pennaceous feathers are presented. Feathers derived from the process of carving-out supportive cells within barb ridges and from the specific pattern of fusion of barb/barbule cells. This process initially produced variably branched down feathers and later, after barb ridge fusion, a rachis. From the modulation in the pattern of barb ridge formation various pennaceous feathers later evolved.

Molecular evidence for an activator-inhibitor mechanism in development of embryonic feather branching.

The developmental basis of morphological complexity remains a central question in developmental and evolutionary biology. Feathers provide a unique system to analyze the development of complex morphological novelties. Here, we describe the interactions between Sonic hedgehog (Shh) and bone morphogenetic protein 2 (Bmp2) signaling during feather barb ridge morphogenesis. We demonstrate that activator-inhibitor models of Shh and Bmp2 signaling in the tubular feather epithelium are sufficient to explain the initial formation of a meristic pattern of barb ridges and the observed variation in barb morphogenesis in chick natal down feathers. Empirical tests support the assumptions of the model that, within the feather ectoderm, Shh (activator) up-regulates its own transcription and that of Bmp2 (inhibitor), whereas Bmp2 signaling down-regulates Shh expression. More complex models incorporating a second activator and dorsal/ventral polarized modification of activator signaling can produce all of the barb morphogenesis patterns observed during the growth of more complex branched pennaceous feathers: new barb ridge formation, helical growth, and barb ridge fusion. An integrated model of feather morphogenesis and evolution suggests that plumulaceous feather structure evolved by the establishment of activator-inhibitor interactions between Shh and Bmp2 signaling in the basal epithelium of the feather germ. Subsequently, pennaceous feather structure evolved through the integration of barb ridge morphogenesis with a second, local inhibitor and a dorsal/ventral signal gradient within the feather. The model is congruent with paleontological evidence that plumulaceous feathers are primitive to pennaceous feathers.

Theory of the growth and evolution of feather shape.

We present the first explicit theory of the growth of feather shape, defined as the outline of a pennaceous feather vane. Based on a reanalysis of data from the literature, we propose that the absolute growth rate of the barbs and rachis ridges, not the vertical growth rate, is uniform throughout the follicle. The growth of feathers is simulated with a mathematical model based on six growth parameters: (1) absolute barb and rachis ridge growth rate, (2) angle of helical growth of barb ridges, (3) initial barb ridge number, (4) new barb ridge addition rate, (5) barb ridge diameter, and (6) the angle of barb ramus expansion following emergence from the sheath. The model simulates growth by cell division in the follicle collar and, except for the sixth parameter, does not account for growth by differentiation in cell size and shape during later keratinization. The model can simulate a diversity of feather shapes that correspond closely in shape to real feathers, including various contour feathers, asymmetrical feathers, and even emarginate primaries. Simulations of feather growth under different parameter values demonstrate that each parameter can have substantial, independent effects on feather shape. Many parameters also have complex and redundant effects on feather shape through their influence on the diameter of the follicle, the barb ridge fusion rate, and the internodal distance. Simulated isochrones-the loci, or sets, of feather cells of the same age-have the same oblique chevron-shaped position in the mature feather as fault bars, which are isochronic defects in the barbules created by a disruptions during development. Accurate simulation of fault bar shape and position confirms the uniform absolute growth rate hypothesis and the general realism of the model. The theory defines a six-parameter feather morphospace, and provides many predictions about the developmental determination of feather shape that can be tested with detailed observations and experiments on developing feathers. This theory also provides testable predictions about the changes in developmental mechanisms required to evolve different feather shapes to accomplish various functions.

Avian model for 13-cis-retinoic acid embryopathy: morphological characterization of ventricular septal defects.

In developing an avian model for 13-cis-retinoic acid (13cisRA) embryopathy, we found 13cisRA induced cardiovascular defects, especially Type I ventricular septal defects (VSDs) (Hart et al.: Teratology 41:463-472, '90). As the first step of investigating possible mechanisms, we have examined the light microscopic morphology of RA-induced cardiovascular defects in chick embryos. Fertilized eggs were injected via yolk sac with 150 micrograms 13cisRA in dimethylsulfoxide (DMSO), DMSO or mock injection on embryonic day 5 (E5). On E6, E7, or E8, surviving embryos were sacrificed and fixed in 10% formalin. Thoracic blocks were exised, embedded in paraffin and serially sectioned through the heart, base to apex. Slides were stained, screened for tissue orientation, then coded and evaluated without knowledge of treatment group. Examination of serial sections permitted qualitative evaluation of conotruncal ridge volume, mesenchymal organization, necrosis and extent of fusion. Extent of fusion was the only parameter influenced by 13cisRA treatment. On E6, ridge fusion was incomplete in all groups at comparable levels. On E7, ridge fusion in 13cisRA-treated embryos had not progressed as far proximally as in controls. By E8, there was a significant difference in the extent of fusion between 13cisRA-treated and non-RA-treated groups. We conclude 13cisRA-induced VSDs resulted from defective conotruncal ridge fusion and that the fusion defects did not result from decreased tissue volume, altered mesenchymal organization or increased necrosis.