Search

The success of near-infrared spectroscopy (NIRS) analysis hinges on the precision and robustness of the calibration model. Shallow learning (SL) algorithms like partial least squares discriminant analysis (PLS-DA) often fall short in capturing the interrelationships between adjacent spectral variables, and the analysis results are easily affected by spectral noise, which dramatically limits the breadth and depth of applications of NIRS. Deep learning (DL) methods, with their capacity to discern intricate features from limited samples, have been progressively integrated into NIRS. In this paper, two discriminant analysis problems, including wheat kernels and Yali pears as examples, and several representative calibration models were used to research the robustness and effectiveness of the model. Additionally, this article proposed a near-infrared calibration model, which was based on the Gramian angular difference field method and coordinate attention convolutional neural networks (G-CACNNs). The research results show that, compared with SL, spectral preprocessing has a smaller impact on the analysis accuracy of consensus learning (CL) and DL, and the latter has the highest analysis accuracy in the modeling results using the original spectrum. The accuracy of G-CACNNs in two discrimination tasks was 98.48% and 99.39%. Finally, this research compared the performance of various models under noise to evaluate the robustness and noise resistance of the proposed method. [ABSTRACT FROM AUTHOR]

The electromechanical planetary gear system has high work efficiency and long service life, but factors such as heat, wear, and electrical signals can affect the transmission performance of electromechanical planetary gears. This article comprehensively considers factors such as temperature, tooth surface wear, lubrication, current and voltage, damping ratio, etc. Based on the principle of thermal deformation, Archard wear model, and equivalent circuit principle, a dynamic model of electromechanical planetary gears is established. The existing literature has not comprehensively analyzed the effects of temperature, wear, and electrical signal changes on the nonlinear characteristics of electromechanical planetary gear systems. The results show that when the motor current is between 7 A and 18 A and the voltage is lower than the rated voltage, the system is in a stable state; as the temperature rises, the system tends to stabilize; the gear wear exceeds 30 μm, and the bifurcation characteristics of the system are more pronounced. [ABSTRACT FROM AUTHOR]

This article proposes an analytical methodology for the optimal design of a magnetorheological (MR) valve constrained in a specific volume. The analytical optimization method is to identify geometric dimensions of the MR valve, and to determine whether the performance of the valve has undergone major improvement. Initially, an enhanced radial MR valve structure with effective annular and radial composite flow paths was designed. After describing the schematic configuration and operating principle of the proposed MR valve, a mathematical model of the pressure drop was derived on the basis of the Bingham model of a MR fluid. Sequentially, the multi-objective optimization problem had been formulated for the constructed approximate model exploiting the NSGA-II algorithm to find the global optimum geometrical dimensions of the enhanced radial MR valve. Meanwhile, influences of the geometrical design variables of the MR valve were analytically investigated by mapping finite element analysis numerical responses with response surface techniques. Lastly, the experimental test rig was setup to explore the pressure drop and dynamic response time of the initial and optimal MR valve, as well as the dynamic performance of the enhanced radial MR valve controlled cylinder system under different excitation conditions. The experimental results revealed that under the applied current of 1.6 A, the pressure drop and power consumption of the optimal MR valve improved significantly with values of 4.46 MPa and 16.84 W, respectively, when compared to 4.03 MPa and 27.65 W of their respective initial values. Additionally, the average response time efficiency improved by 14.29%, with its optimal value being 81 ms and initial value as 94.5 ms. Moreover, the damping force of the optimal MR valve-controlled cylinder system was 4.34 kN, which was 12.44% larger than the initial one of 3.86 kN at the applied current of 1.6 A. [ABSTRACT FROM AUTHOR]

Neural precursor cell-expressed, developmentally-downregulated 9 (NEDD9) is a multi-domain skeleton protein that serves an important role in the cell signaling process via modulating invasion, metastasis, proliferation and apoptosis of tumor cells. The present study identified that the expression levels of NEDD9 in colorectal cancer were elevated. Therefore, the effect of downregulating the expression of NEDD9 in terms of invasion and migration of colorectal cancer cells was investigated and the role of the JNK pathway in these processes was also investigated. The data revealed that downregulation of NEDD9 and JNK inhibitors suppressed invasion and migration, decreased expression levels of phosphorylated JNK, increased the expression levels of E-cadherin and decreased the expression levels of vimentin. In summary, NEDD9 promotes invasion and migration of colorectal cancer cells via the JNK pathway. [ABSTRACT FROM AUTHOR]

Background: The care of traumatized children would benefit significantly from accurate predictive models for Posttraumatic Stress Disorder (PTSD), using information available around the time of trauma. Machine Learning (ML) computational methods have yielded strong results in recent applications across many diseases and data types, yet they have not been previously applied to childhood PTSD. Since these methods have not been applied to this complex and debilitating disorder, there is a great deal that remains to be learned about their application. The first step is to prove the concept: Can ML methods - as applied in other fields - produce predictive classification models for childhood PTSD? Additionally, we seek to determine if specific variables can be identified - from the aforementioned predictive classification models - with putative causal relations to PTSD. Methods: ML predictive classification methods - with causal discovery feature selection - were applied to a data set of 163 children hospitalized with an injury and PTSD was determined three months after hospital discharge. At the time of hospitalization, 105 risk factor variables were collected spanning a range of biopsychosocial domains. Results: Seven percent of subjects had a high level of PTSD symptoms. A predictive classification model was discovered with significant predictive accuracy. A predictive model constructed based on subsets of potentially causally relevant features achieves similar predictivity compared to the best predictive model constructed with all variables. Causal Discovery feature selection methods identified 58 variables of which 10 were identified as most stable. Conclusions: In this first proof-of-concept application of ML methods to predict childhood Posttraumatic Stress we were able to determine both predictive classification models for childhood PTSD and identify several causal variables. This set of techniques has great potential for enhancing the methodological toolkit in the field and future studies should seek to replicate, refine, and extend the results produced in this study. [ABSTRACT FROM AUTHOR]

Conventional research methodologies and data analytic approaches in psychiatric research are unable to reliably infer causal relations without experimental designs, or to make inferences about the functional properties of the complex systems in which psychiatric disorders are embedded. This article describes a series of studies to validate a novel hybrid computational approach–the Complex Systems-Causal Network (CS-CN) method–designed to integrate causal discovery within a complex systems framework for psychiatric research. The CS-CN method was first applied to an existing dataset on psychopathology in 163 children hospitalized with injuries (validation study). Next, it was applied to a much larger dataset of traumatized children (replication study). Finally, the CS-CN method was applied in a controlled experiment using a ‘gold standard’ dataset for causal discovery and compared with other methods for accurately detecting causal variables (resimulation controlled experiment). The CS-CN method successfully detected a causal network of 111 variables and 167 bivariate relations in the initial validation study. This causal network had well-defined adaptive properties and a set of variables was found that disproportionally contributed to these properties. Modeling the removal of these variables resulted in significant loss of adaptive properties. The CS-CN method was successfully applied in the replication study and performed better than traditional statistical methods, and similarly to state-of-the-art causal discovery algorithms in the causal detection experiment. The CS-CN method was validated, replicated, and yielded both novel and previously validated findings related to risk factors and potential treatments of psychiatric disorders. The novel approach yields both fine-grain (micro) and high-level (macro) insights and thus represents a promising approach for complex systems-oriented research in psychiatry. [ABSTRACT FROM AUTHOR]