Psycholinguistic Preconditions of Speech Formation of Children with General Speech Retardation

The article addresses psycholinguistic preconditions for development of the communicative component of speech activity in 5-year-olds with general speech retardation (GSR). The development of speech activity is analyzed through the lens of psycholinguistic motivation for the emergence of speech units. The authors for the first time identified psychological mechanisms that underlie disorders in the development of the communication component of speech activity in 5-year-olds with GSR and suggested effective interventions. The research involved a study of probability prediction within the structure of the communicative component of speech activity of 5-year-olds with GSR. The author-developed classification of non-verbal and verbal probability prediction formed the basis for a theory-based diagnostic tool to assess the communicative component of speech activity in 5-year-olds with GSR. The research demonstrated the importance of probability prediction as a dynamic process and indicator of practical realization of utterance and holistically developed coherent speech. The analysis of disorders in cognitive and speech operations and functions identified in the study points to the dominant role of weak probability prediction function at non-verbal and verbal levels. Weak probability prediction was defined as the cause of poorly developed communication component of speech activity in 5-year-olds with GSR.

Identification of Survival and Therapeutic Response-Related Ferroptosis Regulators in Bladder Cancer through Data Mining and Experimental Validation

Ferroptosis has been reported to regulate tumorigenesis, metastasis, drug resistance and the immune response. However, the potential roles of ferroptosis regulators in the advancement of bladder cancer remain to be explored. We systematically evaluated the multidimensional alteration landscape of ferroptosis regulators in bladder cancer and checked if their expression correlated with the ferroptosis index. We used least absolute shrinkage and selection operator regression to form a signature consisting of seven ferroptosis regulator. We confirmed the signature’s prognostic and predictive accuracy with five independent datasets. A nomogram was built to predict the overall survival and risk of death of patients. The relative expression of the genes involved in the signature was also clarified by real-time quantitative PCR. We found the risk score was related to tumor progression and antitumor immunity-related pathways. Moreover, there existed negative association between the relative antitumor immune cell infiltration level and the risk score, and higher tumor mutation burden was found in the group of lower risk score. We used The Tumor Immune Dysfunction and Exclusion database and IMvigor210 cohort having immunotherapy efficacy results to confirm the prediction function of the risk score. Furthermore, the ferroptosis regulator signature could also reflect the chemotherapy sensitivity of bladder cancer.

Generating Residential Layout Based on AI in the View of Wind Environment

There is a contradiction between the high-density residential area development form and comfortable outdoor physical environment. The existing studies on wind environment of high-rise residential areas only provide the guidance for the simple general layouts, which cannot cope with the fact that most high-rise residential areas are mixed of point buildings and board buildings, and it would cost a lot of time and resources to carry out computer simulation of each layout. This paper presents a new tool, which uses the automatic optimization function of genetic algorithm and the prediction function of fully convolutional neural network to integrates three functions: the automatic generation of high-rise residential layout, the simulation of wind environment and the comparison for optimization, to learn plan scheduling and obtain the optimal solution for high-rise residential layout under specific plot ratio and plot conditions, provides guidance for today’s fast-paced architectural design.

A novel method for inference of acyclic chemical compounds with bounded branch-height based on artificial neural networks and integer programming

Analysis of chemical graphs is becoming a major research topic in computational molecular biology due to its potential applications to drug design. One of the major approaches in such a study is inverse quantitative structure activity/property relationship (inverse QSAR/QSPR) analysis, which is to infer chemical structures from given chemical activities/properties. Recently, a novel two-phase framework has been proposed for inverse QSAR/QSPR, where in the first phase an artificial neural network (ANN) is used to construct a prediction function. In the second phase, a mixed integer linear program (MILP) formulated on the trained ANN and a graph search algorithm are used to infer desired chemical structures. The framework has been applied to the case of chemical compounds with cycle index up to 2 so far. The computational results conducted on instances with n non-hydrogen atoms show that a feature vector can be inferred by solving an MILP for up to $$n=40$$ n = 40 , whereas graphs can be enumerated for up to $$n=15$$ n = 15 . When applied to the case of chemical acyclic graphs, the maximum computable diameter of a chemical structure was up to 8. In this paper, we introduce a new characterization of graph structure, called “branch-height” based on which a new MILP formulation and a new graph search algorithm are designed for chemical acyclic graphs. The results of computational experiments using such chemical properties as octanol/water partition coefficient, boiling point and heat of combustion suggest that the proposed method can infer chemical acyclic graphs with around $$n=50$$ n = 50 and diameter 30.

Closing the BIG-LID: An Effective Local Intrinsic Dimensionality Defense for Nonlinear Regression Poisoning

Nonlinear regression, although widely used in engineering, financial and security applications for automated decision making, is known to be vulnerable to training data poisoning. Targeted poisoning attacks may cause learning algorithms to fit decision functions with poor predictive performance. This paper presents a new analysis of local intrinsic dimensionality (LID) of nonlinear regression under such poisoning attacks within a Stackelberg game, leading to a practical defense. After adapting a gradient-based attack on linear regression that significantly impairs prediction capabilities to nonlinear settings, we consider a multi-step unsupervised black-box defense. The first step identifies samples that have the greatest influence on the learner's validation error; we then use the theory of local intrinsic dimensionality, which reveals the degree of being an outlier of data samples, to iteratively identify poisoned samples via a generative probabilistic model, and suppress their influence on the prediction function. Empirical validation demonstrates superior performance compared to a range of recent defenses.

Towards Personalized Medicine: Non-Coding RNAs and Endometrial Cancer

Endometrial cancer (EC) is the most frequent female cancer associated with excellent prognosis if diagnosed at an early stage. The risk factors on which clinical staging is based are constantly updated and genetic and epigenetic characteristics have recently been emerging as prognostic markers. The evidence shows that non-coding RNAs (ncRNAs) play a fundamental role in various biological processes associated with the pathogenesis of EC and many of them also have a prognosis prediction function, of remarkable importance in defining the therapeutic and surveillance path of EC patients. Personalized medicine focuses on the continuous updating of risk factors that are identifiable early during the EC staging to tailor treatments to patients. This review aims to show a summary of the current classification systems and to encourage the integration of various risk factors, introducing the prognostic role of non-coding RNAs, to avoid aggressive therapies where not necessary and to treat and strictly monitor subjects at greater risk of relapse.

Calculation and realization of new method grey residual error correction model

Aiming at the problem of prediction accuracy of stochastic volatility series, this paper proposes a method to optimize the grey model(GM(1,1)) from the perspective of residual error. In this study, a new fitting method is firstly used, which combines the wavelet function basis and the least square method to fit the residual data of the true value and the predicted value of the grey model(GM(1,1)). The residual prediction function is constructed by using the fitting method. Then, the prediction function of the grey model(GM(1,1)) is modified by the residual prediction function. Finally, an example of the wavelet residual-corrected grey prediction model (WGM) is obtained. The test results show that the fitting accuracy of the wavelet residual-corrected grey prediction model has irreplaceable advantages.

A Combined Model and Data-Driven Approach for the Determination of Rotor Temperature in an Induction Machine

The need for protection of electrical machines comes as a demand of safety regulations in the automotive industry as well as a result of the general desire to obtain a robust and reliable electric powertrain. This paper introduces a hybrid method for estimating the temperature of the rotor of an Induction Machine (IM) based on a Nonlinear Autoregressive Network with Exogenous inputs (NARX) used as a prediction function within a particle filter. The temperature of the stator case is measured, and the information is used as an input to a NARX network and as a variable to a thermal process with first-order dynamics which serves as an observation function. Uncertainties of the NARX and thermal model are determined and used to correct the posterior estimate. Experimental data are used from a real IM test-bench and the results prove the applicability and good performance.

Generalized neural network trained with a small amount of base samples: Application to event detection and phase picking in downhole microseismic monitoring

The deep learning method has been successfully applied to many geophysical problems to extract features from seismic big data. However, some applications may not have sufficient available data to directly train a generalized neural network. We apply data augmentation on a significantly small number of samples to train a generalized neural network for microseismic event detection and phase picking, which could be used in different project settings and areas. We use the U-Net architecture consisting of 2D convolutional layers to create the prediction function, and map the waveforms recorded by using multiple receivers to the P/S arrival time labels; thus, the neural network can learn the P/S moveout features from multiple receivers. The training set is generated by simulating various realizations of the data based on ten original samples from the beginning of a hydraulic fracturing stage. The trained neural network is then used to detect the events and pick the P/S phases from the continuous data for different stages and projects. A grid search from a precalculated traveltime table is performed to determine the event location after an event is detected. We build a real-time event detection and location workflow without human intervention by combining the neural network and grid search method, and apply the workflow to a different stage from the training events and a completely independent project that the neural network has not encountered. The results show that microseismic events are successfully detected and located, and the picking performance of the neural network is superior to that of a traditional auto regression picker.