Useful modeling techniques

This paper investigates the impact of word embedding techniques on enhancing SMS spam detection models. Traditional statistical methods (BoW, TF-IDF) are compared with advanced techniques (Word2Vec, fastText, GloVe, PhoBERT) using a proprietary dataset.

5p viengfa 28-10-2024 1 1   Download

In this study, we propose a machine learning technique for estimating the shear strength of CRC beams across a range of service periods. To do this, we gathered 158 CRC beam shear tests and used Artificial Neural Network (ANN) to create a forecast model for the considered output.

12p viengfa 28-10-2024 2 1   Download

Light Gradient Boosting Machine is a new machine learning technique developed by Microsoft corporation which has been proposed in the present study to determine the CBR of stabilized expansive soils. Model performance of the ML model are evaluated by different criteria such as correlation coefficient R, root mean square error RMSE and mean absolute error MAE.

8p viengfa 28-10-2024 2 1   Download

This study focuses on optimizing the hyperparameters of the XGB model by a grid search to find an optimal XGB predictive model. In addition, the effect of input parameters on the SCCRF's CS is studied using Shapley Additive exExplanations (SHAP) values technique.

14p viengfa 28-10-2024 2 1   Download

In this study, we propose a novel approach using the oscillation characteristics of the RMS current as the input to machine learning models, combined with the confident learning technique. Using the oscillation characteristics obtained by taking a discrete Fourier transform (DFT) of the RMS current as model input, we aim to reduce the computational requirements of the machine learning models.

12p viling 11-10-2024 1 0   Download

Artificial neural network (ANN), a powerful technique, has been used widely over the last decades in many scientific fields including engineering problems. However, the backpropagation algorithm in ANN is based on a gradient descent approach.

15p vibecca 01-10-2024 0 0   Download

This paper scrutinizes two lane detection methods: image processing in isolation and integrating deep learning techniques with Hough transformation. The deep learning techniques specifically discuss two models, namely YOLOv8 pose estimation and YOLOv8 object detection.

14p vibecca 01-10-2024 3 1   Download

In this paper, an artificial neural network (ANN) model was applied to forecast PM2.5 at the Coc Sau open–pit coal mine (Northern Vietnam) with fine–tuning parameters. It aims to provide the feasibility and insights into controlling air quality in open–pit mines using artificial intelligence techniques.

8p viyoko 01-10-2024 0 0   Download

The implementation duration of road work is critical as it impacts both the cost and outcome of the project. The article examines the techniques used to determine the time required for the completion of road work projects. It explores the approach to estimating the duration of road work projects in low- and middle-income countries (LMICs) based on the ROCKS database created by the World Bank.

13p vifaye 20-09-2024 3 1   Download

In this paper, a new design of cylindrical panels is proposed with two functionally graded carbon nanotube-reinforced composite (FG-CNTRC) face sheets and a corrugated core. The corrugated core layer is modelled by applying the homogeneous technique according to the firstorder shear deformation theory (FSDT). The nonlinear vibration behaviour of first-order shear deformable cylindrical panels with geometric nonlinearities is analysed in the present paper.

10p dathienlang1012 03-05-2024 3 0   Download

This article, we present a thorough and straightforward hydrothermal method towards the production of reduced graphene oxide templated MIL-53(Fe) hybrids RGO@MIL-53(Fe). The structural characteristics of created hybrids were identified by using BET, FESEM, powder X-ray diffraction, and FTIR techniques. Methylene blue (MB) dye (a model water pollutant) was used to evaluate H2O2-assisted photo-catalytic efficiency of RGO@MIL-53(Fe).

9p dianmotminh02 03-05-2024 4 2   Download

n this work, the main aim is to map the potential zones of groundwater in Central Highlands (Vietnam) using a novel ensemble machine learning model, namely CG-LMT, which is a combination of two advanced techniques, namely Cascade Generalization (CG) and Logistics Model Trees (LMT). For this, a total of 501 wells data and a set of twelve affecting factors were gathered and selected to generate training and testing datasets used for building and validating the model.

10p dianmotminh02 03-05-2024 9 2   Download

The purpose of this article is to analyze the performance of companies in the slaughterhouse industry in health and safety issues. The research method is quantitative modeling. The main research technique uses a mixed method based on multi-attribute utility method (MAUT) and artificial neural networks (ANN). The research object is 34 slaughterhouse companies located in Southern Brazil. Then, we ranked the companies and modeled their decision trees using the MAUT method.

9p longtimenosee10 26-04-2024 5 2   Download

The specific research objectives of this study are: 1. The development of a high throughput method for evaluation of alloys (5xxx Al as model materials in this work) subject to pitting; 2. Understanding the roles of variation in functional groups' in determining the inhibition efficiency; 3. Elucidating the inhibition mechanisms; and 4. Unveiling the role of intermetallic present in Al matrix and their contribution to the inhibition mechanism, particularly the long-term durability of the inhibitor systems.

104p runthenight04 02-02-2023 9 2   Download

In this thesis, the limitations of using existing LTE congestion mitigation mechanisms such as Discard Timer and RED have been explored. A different mechanism to analyse the effects of using control theory for congestion mitigation has been developed. Finally, congestion mitigation in LTE networks has been addresses using radio resource allocation techniques with non-cooperative game theory being an underlying mathematical framework.

118p runthenight04 02-02-2023 3 2   Download

The document will be structured as follows: In Chapter 2 outline the methodology, discussing the computational techniques used to evaluate the interaction energies and evaluating the construction of the TT and D3(BJ) correction terms. Chapter 3 attempts to establish a foundational understanding of how these methods model vdW interactions by evaluating the performance of the corrected and uncorrected HF and DFT methods in comparison with CCSD(T) energies for a selection of inert gas dimers, and simple molecule-molecule interactions.

63p runthenight04 02-02-2023 9 2   Download

This research develops a rich theoretical and empirical understanding of embeddedness by way of three dimensions (structural, relational and cultural), and investigates its implications for actors’ value co-creation behaviours and value-in-context outcomes. In addition, the research refines co-creation perspectives by examining a central boundary condition of co-creation processes. The data was collected in an online service environment and was analysed using structural equation modelling techniques.

183p runthenight04 02-02-2023 7 2   Download

Two major areas of the scorecard development process were identified as having much capacity for improving credit scoring models. These are the application of 1) better classifiers and 2) variable selection techniques. However, the application of an artificial immune system for developing scorecards as well as the use of other variable selection techniques, other than stepwise regression, in credit scoring are quite limited as indicated by the scarcity of published materials in these two areas in the current literature.

210p runthenight04 02-02-2023 5 2   Download

The main objective of the study "Role of beliefs and past experience informing resort accommodation purchase behaviour : a study of Australian tourists" is: To segment the tourists using resorts in Australia; to propose a conceptual model which describes the factors that affect the travellers’ choice of resort hotels based on their beliefs along with the effect of past behaviour and; to test the model across the segments using multivariate data analysis techniques.

166p runthenight04 02-02-2023 13 2   Download

The purpose of this thesis is to explore how metaphor-based interactions can enhance the behavioural interactions in project environments to deliver better outcomes. It documents the processes and findings from an action research program to investigate the impact of combining metaphor, conversation and reflective practice techniques into a new model, the Reflective Performance Cycle (RPC) to stimulate richer and more productive interactions between project team members.

217p runthenight04 02-02-2023 4 2   Download