Boongasame, Laor

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Enhanced Feature Selection via Hierarchical Concept Modeling
(2024-12-01)
Saelee, Jarunee
;
Wetchapram, Patsita
;
Wanichsombat, Apirat
;
Intarasit, Arthit
;
Muangprathub, Jirapond
The objectives of feature selection include simplifying modeling and making the results more understandable, improving data mining efficiency, and providing clean and understandable data preparation. With big data, it also allows us to reduce computational time, improve prediction performance, and better understand the data in machine learning or pattern recognition applications. In this study, we present a new feature selection approach based on hierarchical concept models using formal concept analysis (FCA) and a decision tree (DT) for selecting a subset of attributes. The presented methods are evaluated based on all learned attributes with 10 datasets from the UCI Machine Learning Repository by using three classification algorithms, namely decision trees, support vector machines (SVM), and artificial neural networks (ANN). The hierarchical concept model is built from a dataset, and it is selected by top-down considering features (attributes) node for each level of structure. Moreover, this study is considered to provide a mathematical feature selection approach with optimization based on a paired-samples t-test. To compare the identified models in order to evaluate feature selection effects, the indicators used were information gain (IG) and chi-squared (CS), while both forward selection (FS) and backward elimination (BS) were tested with the datasets to assess whether the presented model was effective in reducing the number of features used. The results show clearly that the proposed models when using DT or using FCA, needed fewer features than the other methods for similar classification performance.
Some of the metrics are blocked by your
consent settings
Laor Initialization: A New Weight Initialization Method for the Backpropagation of Deep Learning
(2025-07-01)
Boongasame, Laor
;
Muangprathub, Jirapond
;
Thammarak, Karanrat
This paper presents Laor Initialization, an innovative weight initialization technique for deep neural networks that utilizes forward-pass error feedback in conjunction with k-means clustering to optimize the initial weights. In contrast to traditional methods, Laor adopts a data-driven approach that enhances convergence’s stability and efficiency. The method was assessed using various datasets, including a gold price time series, MNIST, and CIFAR-10 across the CNN and LSTM architectures. The results indicate that the Laor Initialization achieved the lowest K-fold cross-validation RMSE (0.00686), surpassing Xavier, He, and Random. Laor demonstrated a high convergence success (final RMSE = 0.00822) and the narrowest interquartile range (IQR), indicating superior stability. Gradient analysis confirmed Laor’s robustness, achieving the lowest coefficients of variation (CV = 0.2230 for MNIST, 0.3448 for CIFAR-10, and 0.5997 for gold price) with zero vanishing layers in the CNNs. Laor achieved a 24% reduction in CPU training time for the Gold price data and the fastest runtime on MNIST (340.69 s), while maintaining efficiency on CIFAR-10 (317.30 s). It performed optimally with a batch size of 32 and a learning rate between 0.001 and 0.01. These findings establish Laor as a robust alternative to conventional methods, suitable for moderately deep architectures. Future research should focus on dynamic variance scaling and adaptive clustering.
Some of the metrics are blocked by your
consent settings
Design and Implement Deepfake Video Detection Using VGG-16 and Long Short-Term Memory
(2024-01-01)
Boongasame, Laor
;
Boonpluk, Jindaphon
;
Soponmanee, Sunisa
;
Muangprathub, Jirapond
;
Thammarak, Karanrat
This study aims to design and implement deepfake video detection using VGG-16 in combination with long short-term memory (LSTM). In contrast to other studies, this study compares VGG-16, VGG-19, and the newest model, ResNet-101, including LSTM. All the models were tested using Celeb-DF video dataset. The result showed that the VGG-16 model with 15 epochs and 32 batch sizes had the highest performance. The results showed that the VGG-16 model with 15 epochs and 32 batch sizes exhibited the highest performance, with 96.25% accuracy, 93.04% recall, 99.20% specificity, and 99.07% precision. In conclusion, this model can be implemented practically.
Some of the metrics are blocked by your
consent settings
Portfolio Risk and Return with a New Simple Moving Average of Price Change Ratio
(2020-12-01)
Muangprathub, Jirapond
;
Intarasit, Arthit
;
Boongasame, Laor
;
Phaphoom, Nattakarn
Cluster analysis is a commonly used technique by investors to create a diversified portfolio. The approach aims at maximizing returns for a tolerable degree of risks. To diversify effectively, investors use similarity measures to enable clustering. Traditional price indexes, such as Return on Asset and Return on Equity, are known to perform inconsistently in identifying acceptable clusters. Our study proposes a novel indicator, Simple Moving Average of Price Change Ratios (SMA-PCR-N), for use as a similarity measure. It is an adjusted version of the traditional Simple Moving Average (SMA) calculated based on stocks’ closing price over a number of time periods, to observe price trend and potential changes. Instead, the SMA-PCR-N considers the daily opening prices, the closing prices and the average price of stocks. We demonstrate the use of k-means clustering with SMA-PCR-N to create a diversified stock portfolio. Data on approximately three hundred stocks were retrieved from the Stock Exchange of Thailand for the fiscal years 2015–2017, and were used experiments to evaluate the effectiveness of our SMA-PCR-N diversification approach. The results show that SMA-PCR-N based portfolios gave higher returns than portfolios created based on SMA clusters, in most cases.
1

Boongasame, Laor

Filters

Settings

Sort By

Results per page