Research Summary

When optimizing the performance of neural network-based chatbots, determining the optimizer is one of the most important aspects. Optimizers primarily control the adjustment of model parameters such as weight and bias to minimize a loss function during training. Adaptive optimizers such as ADAM have become a standard choice and are widely used for their invariant parameter updates' magnitudes concerning gradient scale variations, but often pose generalization problems. Alternatively, Stochastic Gradient Descent (SGD) with Momentum and the extension of ADAM, the ADAMW, offers several advantages. This study aims to compare and examine the effects of these optimizers on the chatbot CST dataset. The effectiveness of each optimizer is evaluat

In this work, results from an optical technique (laser speckle technique) for measuring surface roughness was done by using statistical properties of speckle pattern from the point of view of computer image texture analysis. Four calibration relationships were used to cover wide range of measurement with the same laser speckle technique. The first one is based on intensity contrast of the speckle, the second is based on analysis of speckle binary image,  the third is on size of speckle pattern spot, and the latest one is based on characterization of the energy feature of the gray level co-occurrence matrices for the speckle pattern. By these calibration relationships surface roughness of an object surface can be evaluated within the

Segmentation of urban features is considered a major research challenge in the fields of photogrammetry and remote sensing. However, the dense datasets now readily available through airborne laser scanning (ALS) offer increased potential for 3D object segmentation. Such potential is further augmented by the availability of full-waveform (FWF) ALS data. FWF ALS has demonstrated enhanced performance in segmentation and classification through the additional physical observables which can be provided alongside standard geometric information. However, use of FWF information is not recommended without prior radiometric calibration, taking into account all parameters affecting the backscatter energy. This paper reports the implementation o

The purpose of this paper is to study a new types of compactness in the dual bitopological spaces. We shall introduce the concepts of L-pre- compactness and L-semi-P- compactness .

The differential protection of power transformers appears to be more difficult than any type of protection for any other part or element in a power system. Such difficulties arise from the existence of the magnetizing inrush phenomenon. Therefore, it is necessary to recognize between inrush current and the current arise from internal faults. In this paper, two approaches based on wavelet packet transform (WPT) and S-transform (ST) are applied to recognize different types of currents following in the transformer. In WPT approach, the selection of optimal mother wavelet and the optimal number of resolution is carried out using minimum description length (MDL) criteria before taking the decision for the extraction features from the WPT tree

 A mixture model is used to model data that come from more than one component. In recent years, it became an effective tool in drawing inferences about the complex data that we might come across in real life. Moreover, it can represent a tremendous confirmatory tool in classification observations based on similarities amongst them. In this paper, several mixture regression-based methods were conducted under the assumption that the data come from a finite number of components. A comparison of these methods has been made according to their results in estimating component parameters. Also, observation membership has been inferred and assessed for these methods. The results showed that the flexible mixture model outperformed the

 A mixture model is used to model data that come from more than one component. In recent years, it became an effective tool in drawing inferences about the complex data that we might come across in real life. Moreover, it can represent a tremendous confirmatory tool in classification observations based on similarities amongst them. In this paper, several mixture regression-based methods were conducted under the assumption that the data come from a finite number of components. A comparison of these methods has been made according to their results in estimating component parameters. Also, observation membership has been inferred and assessed for these methods. The results showed that the flexible mixture model outperformed the others