Capability Of Neural Network Models Research Articles

DCSPose: A Dual-Channel Siamese Framework for Unseen Textureless Object Pose Estimation

The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities.

Elucidating the prediction capability of neural network model for estimation of crop water stress index of rice

ABSTRACT The crop water stress index is receiving significant attention these days, especially in arid and semiarid regions, for quantifying water stress and effective irrigation scheduling. Nowadays, machine learning techniques such as neural networks are being widely used to determine CWSI. In the present study, Self-Organizing Maps (SOM) and Feed Forward-Back Propagation Artificial Neural Networks (FF-BP-ANN) are compared while determining the CWSI of rice crop. Irrigation field experiments with varying degrees of irrigation were conducted at the irrigation field laboratory of the Indian Institute of Technology, Roorkee, during the growing season of the rice crop. The CWSI of rice was computed empirically by measuring key meteorological variables (relative humidity, air temperature, and canopy temperature). The empirically computed CWSI was compared with SOM and FF-BP-ANN predicted CWSI. For the lower CWSI baseline of rice, a linear relationship between air and canopy temperature difference (Tc-Ta) and, air vapour pressure deficit (AVPD) was developed, whereas air temperature plus 3°C was taken for the upper CWSI baselines. The performance of SOM and FF-BP-ANN were compared by computing Nash–Sutcliffe efficiency (NSE), index of agreement (d), root mean squared error (RMSE), and coefficient of correlation (R2). It is found that FF-BP-ANN (R2 = 0.97, NSE = 0.92, d = 0.95, RMSE = 0.006) performs better than SOM (R2 = 0.88, NSE = 0.87, d = 0.9, RMSE = 0.075).

A Theoretical Framework for Self-Supervised MR Image Reconstruction Using Sub-Sampling via Variable Density Noisier2Noise.

In recent years, there has been attention on leveraging the statistical modeling capabilities of neural networks for reconstructing sub-sampled Magnetic Resonance Imaging (MRI) data. Most proposed methods assume the existence of a representative fully-sampled dataset and use fully-supervised training. However, for many applications, fully sampled training data is not available, and may be highly impractical to acquire. The development and understanding of self-supervised methods, which use only sub-sampled data for training, are therefore highly desirable. This work extends the Noisier2Noise framework, which was originally constructed for self-supervised denoising tasks, to variable density sub-sampled MRI data. We use the Noisier2Noise framework to analytically explain the performance of Self-Supervised Learning via Data Undersampling (SSDU), a recently proposed method that performs well in practice but until now lacked theoretical justification. Further, we propose two modifications of SSDU that arise as a consequence of the theoretical developments. Firstly, we propose partitioning the sampling set so that the subsets have the same type of distribution as the original sampling mask. Secondly, we propose a loss weighting that compensates for the sampling and partitioning densities. On the fastMRI dataset we show that these changes significantly improve SSDU's image restoration quality and robustness to the partitioning parameters.

The way to cover prediction for cytotoxicity for all existing nano-sized metal oxides by using neural network method

The regulatory agencies should fulfil the data gap in toxicity for new chemicals including nano-sized compounds, like metal oxides nanoparticles (MeOx NPs) according to the registration, evaluation, authorisation and restriction of chemicals (REACH) legislation policy. This study demonstrates the perspective capability of neural network models for prediction of cytotoxicity of MeOx NPs to bacteria Escherichia coli (E. coli) for the widest range of metal oxides extracted from Periodic table. The counter propagation artificial neural network (CP ANN) models for prediction of cytotoxicity of MeOx NPs for data sets of 17, 36 and 72 metal oxides were employed in the study. The cytotoxicity of studied metal oxide NPs was correlated with (i) χ-metal electronegativity (EN) by Pauling scale and composition of metal oxides characterised by (ii) number of metal atoms in oxide, (iii) number of oxygen atoms in oxide and (iv) charge of metal cation in oxide. The paper describes the models in context of five OECD principles of validation models accepted for regulatory use. The recommendations were done for the minimal number of cytotoxicity tests needs for evaluation of the large set of MeOx with different oxidation states. The methodology is expected to be useful for potential hazard assessment of MeOx NPs and prioritisation for further testing and risk assessment.

Generalization Capability of Neural Network Models for Temperature-Frequency Correlation Using Monitoring Data

The parametric approach to eliminating the temperature-caused modal variability in vibration-based structural damage detection requires a correlation model between the modal properties and environmental temperatures. This paper examines the generalization capability of neural network models, established using long-term monitoring data, for correlation between the modal frequencies and environmental temperatures. A total of 770 h modal frequency and temperature data obtained from an instrumented bridge are available for this study, which are further divided into three sets: training data, validation data, and testing data. A two-layer back-propagation neural network (BPNN) is first trained using the training data by the conventional training algorithm, in which the number of hidden nodes is optimally determined using the validation data. Then two new BPNNs are configured with the same data by applying the early stopping technique and the Bayesian regularization technique, respectively. The reproduction and prediction capabilities of the two new BPNNs are examined in respect of the training data and the unseen testing data, and compared with the performance of the baseline BPNN model. This study indicates that both the early stopping and Bayesian regularization techniques can significantly ameliorate the generalization capability of BPNN-based correlation models, and the BPNN model formulated using the early stopping technique outperforms that using the Bayesian regularization technique in both reproduction and prediction capabilities.

Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of Soils

Classic constitutive modeling of geomaterials based on the elasticity and plasticity theories suffers from limitations pertaining to formulation complexity, idealization of behavior, and excessive empirical parameters. This article capitalizes on the modeling capabilities of neural networks as substitutes for the classic approaches. The neural network–based modeling overcomes the difficulties encountered in understanding the underlying microscopic processes governing the material's behavior by redirecting the efforts into learning the cause‐effect relations from behavioral examples. Several methodologies are presented and cross‐compared for effectiveness in approximating a theoretical hysteresis model resembling stress‐strain behavior. The most effective methodology was used in modeling the constitutive behavior of an experimentally tested soil and produced models that simulated the real behavior of the soil with high accuracy. Although these models are empirical, they are retrainable and thus, unlike classic constitutive modeling techniques, can be revised and generalized easily when new data become available.

Neural networks for the prediction of the state of Zymomonas mobilis CP4 batch fermentations

The capability of different neural networks for predicting the main state variables (biomass, substrate and ethanol concentrations, the output variables) in Zymomonas mobilis CP4 batch fermentations has been tested. Experimental data recorded from batch fermentations carried out under different conditions (medium composition and temperature) were used to train the net and test its predictions. First a black-box neural network was designed for predicting the three output values given as input values of the present condition of the system. The configuration of the neural network that gives the best results is the one with 10 neurons in the hidden layer (total training error equal to 0.575×10 −3, total testing error equal to 0.719×10 −3). Better results can be obtained using different neural networks for each of the output variables (total testing error equal to 0.527×10 −3). Attempts were made to enhance the prediction capability of neural network models, using the mathematical model that describes the process and a neural network for computing the kinetic parameters in the model. Here, the error is higher than in previous cases. The best prediction is obtained using a neural network with 30 neurons in the hidden layer (total training error equal to 5.535×10 −3, total testing error equal to 2.225×10 −3).

Dynamic monitoring and control of patient anaesthetic and dose levels: time-delay, moving-average neural networks, and principal components analysis

The goal of this study was to examine the capabilities of neural network models for dynamic monitoring and control of patient anaesthetic and dose levels. The network models that we considered are split into two basic groups: static networks and dynamic networks. Static networks are characterised by equations that are memoryless. On the other hand, dynamic networks are systems with memory. Additionally, principal components analysis was used to introduce a further improvement to network design by reducing the dimensionality of the encoded temporal information. Principal components analysis was applied as both pre-processing and post-processing techniques. In the first instance it was used to reduce the dimensionality of the data to more manageable intrinsic information. In the second instance it was employed to understand how the hidden layers separate the data, in order to optimise the network architecture.

COMBINING A RADIAL BASIS NEURAL NETWORK WITH TIME SERIES ANALYSIS TECHNIQUES TO PREDICT MANUFACTURING PROCESS PARAMETERS

The accurate prediction of the values of critical quality parameters of a product during the production stage is a key factor in the success of a manufacturing operation. Neural network algorithms have been used to successfully predict process parameter values. However, techniques to further improve the predictive capability of neural network models are sought. Thus, an analysis was conducted to determine if the predictive capability of the network would he improved if the prediction from a time series model of a manufacturing process parameter were included in the training data set of a radial basis function neural network model. A manufacturing process data set was evaluated, and the use of the time series model prediction significantly improved the neural network's prediction of critical process parameters. Often in a manufacturing environment, the collection of adequate amounts of data for network training is difficult. This integrated technique offers potential for improving network performance witho...

Generalized part family formation using neural network techniques

Abstract The spontaneous generalization capability of neural network models has been exploited for solving the part family formation problem. Our approach combines the useful capacities of the neural network technique with the flexibility of the similarity coefficient method. Notably, the constraint satisfaction model of neural networks is adopted. In generalized part family formation, several practical factors such as sequence of operations, lot size, and multiple process plans are also considered. Our approach proves to be highly flexible in satisfying various requirements and efficient for integration with other manufacturing functions.