Meier Yilmaz (leveltiger00)

This article proposes three new methods to enlarge the feasible region for guaranteeing stability for generalized neural networks having time-varying delays based on the Lyapunov method. First, two new zero equalities in which three states are augmented are proposed and inserted into the results of the time derivative of the constructed Lyapunov-Krasovskii functionals for the first time. SB939 cell line Second, inspired by the Wirtinger-based integral inequality, new Lyapunov-Krasovskii functionals are introduced. Finally, by utilizing the relationship among the augmented vectors and from the original equation, newly augmented zero equalities are established and Finsler's lemma are applied. Through three numerical examples, it is verified that the proposed methods can contribute to enhance the allowable region of maximum delay bounds.Process mining is a suitable method for knowledge extraction from patient pathways. Structured in event logs, medical events are complex, often described using various medical codes. An efficient labeling of these events before applying process mining analysis is challenging. This paper presents an innovative methodology to handle the complexity of events in medical event logs. Based on autoencoding, accurate labels are created by clustering similar events in latent space. Moreover, the explanation of created labels is provided by the decoding of its corresponding events. Tested on synthetic events, the method is able to find hidden clusters on sparse binary data, as well as accurately explain created labels. A case study on real healthcare data is performed. Results confirm the suitability of the method to extract knowledge from complex event logs representing patient pathways.We propose a new generic type of artificial neurons called q-neurons. A q-neuron is a stochastic neuron with its activation function relying on Jackson's discrete q-derivative for a stochastic parameter q. We show how to generalize neural network architectures with q-neurons and demonstrate the scalability and ease of implementation of q-neurons into legacy deep learning frameworks. We report experimental results that consistently improve performance over state-of-the-art standard activation functions, both on training and test loss functions.Non-coding RNAs (ncRNAs) play an important role in various biological processes and are associated with diseases. Distinguishing between coding RNAs and ncRNAs, also known as predicting coding potential of RNA sequences, is critical for downstream biological function analysis. Many machine learning-based methods have been proposed for predicting coding potential of RNA sequences. Recent studies reveal that most existing methods have poor performance on RNA sequences with short Open Reading Frames (sORF, ORF length less then 303nt). In this work, we analyze the distribution of ORF length of RNA sequences, and observe that the number of coding RNAs with sORF is inadequate and coding RNAs with sORF are much less than ncRNAs with sORF. Thus, there exists the problem of local data imbalance in RNA sequences with sORF. We propose a coding potential prediction method CPE-SLDI, which uses data oversampling techniques to augment samples for coding RNAs with sORF so as to alleviate local data imbalance. Compared with existing methods, CPE-SLDI produces the better performances, and studies reveal that the data augmentation by various data oversampling techniques can enhance the performance of coding potential prediction, especially for RNA sequences with sORF. The implementation of the proposed method is available at https//github.com/chenxgscuec/CPESLDI.In this work, we present a paradigm bridging electromagnetic (EM) and molecular communication through a stimuli-responsive intra-body model. It has been established that protein molecules, which play a key role in governing cell behavior, can be selectively stimulated using Terahertz (THz) band frequencies. By triggering protein vibrational m