Evaluating Scaling Frameworks for Multiscale Geomorphometric Analysis

Multiscale methods have become progressively valuable in geomorphometric analysis as data have become increasingly detailed. This paper evaluates the theoretical and empirical properties of several common scaling approaches in geomorphometry. Direct interpolation (DI), cubic convolution resampling (RES), mean aggregation (MA), local quadratic regression (LQR), and an efficiency optimized Gaussian scale-space implementation (fGSS) method were tested. The results showed that when manipulating resolution, the choice of interpolator had a negligible impact relative to the effects of manipulating scale. The LQR method was not ideal for rigorous multiscale analyses due to the inherently non-linear processing time of the algorithm and an increasingly poor fit with the surface. The fGSS method combined several desirable properties and was identified as an optimal scaling method for geomorphometric analysis. The results support the efficacy of Gaussian scale-space as a general scaling framework for geomorphometric analyses.

Artificial Neural Network Assisted Variable Step Size Incremental Conductance MPPT Method with Adaptive Scaling Factor

In conventional adaptive variable step size (VSS) maximum power point tracking (MPPT) algorithms, a scaling factor is utilized to determine the required perturbation step. However, the performance of the adaptive VSS MPPT algorithm is essentially decided by the choice of scaling factor. In this paper, a neural network assisted variable step size (VSS) incremental conductance (IncCond) MPPT method is proposed. The proposed method utilizes a neural network to obtain an optimal scaling factor that should be used in current irradiance level for the VSS IncCond MPPT method. Only two operating points on the characteristic curve are needed to acquire the optimal scaling factor. Hence, expensive irradiance and temperature sensors are not required. By adopting a proper scaling factor, the performance of the conventional VSS IncCond method can be improved, especially under rapid varying irradiance conditions. To validate the studied algorithm, a 400 W prototyping circuit is built and experiments are carried out accordingly. Comparing with perturb and observe (P&O), α-P&O, golden section and conventional VSS IncCond MPPT methods, the proposed method can improve the tracking loss by 95.58%, 42.51%, 93.66%, and 66.14% under EN50530 testing condition, respectively.

Hybrid Optimization-Based Robust Watermarking Using Denoising Convolutional Neural Network

Colour images have been widely used in many aspects of life; however, copyright violation issues related to these images motivate research efforts. This paper aims to develop an enhanced watermarking algorithm for producing a watermarked image using hybrid optimisation with high imperceptibility and robustness. The algorithm is based on spatial and transform domains and begins by embedding multiple secret marks into cover media using an optimal scaling factor. The multi-type mark contributes an additional level of authenticity to the proposed algorithm. Furthermore, the marked image is encrypted using an improved encryption scheme, and the denoising convolutional neural network (DnCNN) is employed to enhance the robustness of the proposed algorithm. The results reveal that the proposed watermarking algorithm yields low computational overhead, excellent watermark capacity, imperceptibility, and robustness to common filtering attacks. Moreover, the comparison shows that the proposed algorithm outperforms other competing methods.

TRAJECTORY OF AGE-ASSOCIATED CHANGES IN THE MICROBIAL COMMUNITY OF THE SMALL INTESTINE OF HEALTHY PERSONS IN THE CONTEXT OF METAORGANISM

The study of the small intestine microbiota in humans is difficult due to the low availability of biomaterial. Non-invasive methods of metabolomics and bioinformatic data analysis can expand our understanding of the structure and role the small intestine microbiota in maintaining homeostasis of the body. The article presents the trajectory of age-related changes in the microbial community of the small intestine in healthy individuals in the context of interaction with the cytokine and neuroendocrine systems within the metaorganism, using the methods of gas chromatography - mass spectrometry of microbial markers (GCMS MM) and optimal scaling. 110 practically healthy individuals: children, adults and elderly, were included into the study. The number of the main types of small intestine microbiota (Bacteroidetes, Firmicutes, Actinobacteria, Proteobacteria, and Fusobacteria) was determined in peripheral blood by the GCMS MM method. To construct the trajectories of changes in the small intestine microbiota and indicators of the cytokine and neuroendocrine systems with age, the optimal scaling technique based on the multivariate Gifi transformation (CATPCA method) was used. It was found, that the bacterial community of the small intestine of both children and the elderly and seniors has a significantly low total number of microorganisms, due to the low content of bacteria of the types Firmicutes and Actinobacteria against the background of a high number of representatives of the types Proteobacteria and Fusobacteria, in comparison with similar indicators in adults. Assessment of the trajectory of age-associated changes in the microbiota of the small intestine showed: 1) children have strong dynamic fluctuations in the number and connections within the community of microorganisms against the background of the formation of connections between the main regulatory systems of the metaorganism – immune and neuroendocrine; 2) adults present the plasticity and consistency of the functioning of the immune and nervous systems, what determine the state of dynamic balance of the small intestine microbiota; 3) healthy aging characterize by hight degree of cooperation between the main members of the bacterial community, which ensures the stability of the system at a new level, as one of the mechanisms of adaptation of the organism. Thus, the using the methods of GCMS MM and optimal scaling, allows us to expand our understanding of the age-associated trajectory of changes in the small intestine microbiota and its cooperation with the immune and neuroendocrine systems within the metaorganism, which can be used in the development of new methods of therapy of an infectious and non-infectious diseases.

Speech & Song Emotion Recognition Using Multilayer Perceptron and Standard Vector Machine

herein, we have compared the performance of SVM and MLP in emotion recognition using speech and song channels of the RAVDESS dataset. We have undertaken a journey to extract various audio features, identify optimal scaling strategy and hyperparameter for our models. To increase sample size, we have performed audio data augmentation and addressed data imbalance using SMOTE. Our data indicate that optimised SVM outperforms MLP with an accuracy of 82 compared to 75%. Following data augmentation, the performance of both algorithms was identical at ~79%, however, overfitting was evident for the SVM. Our final exploration indicated that the performance of both SVM and MLP were similar in which both resulted in lower accuracy for the speech channel compared to the song channel. Our findings suggest that both SVM and MLP are powerful classifiers for emotion recognition in a vocal-dependent manner.

On Recovery Guarantees for One-Bit Compressed Sensing on Manifolds

This paper studies the problem of recovering a signal from one-bit compressed sensing measurements under a manifold model; that is, assuming that the signal lies on or near a manifold of low intrinsic dimension. We provide a convex recovery method based on the Geometric Multi-Resolution Analysis and prove recovery guarantees with a near-optimal scaling in the intrinsic manifold dimension. Our method is the first tractable algorithm with such guarantees for this setting. The results are complemented by numerical experiments confirming the validity of our approach.