KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Start date: 2020Subject: search.filters.subject.Artificial Neural Network

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    FRACTIONAL-ORDER SENSITIVITY ANALYSIS OF LEPTOSPIROSIS TREATMENT DYNAMICS IN THE PRESENCE OF AN ENVIRONMENTAL BACTERIAL RESERVOIR WITH ARTIFICIAL NEURAL NETWORK SUPPORT
    (2026-01-01)
    Irshad, Ateeq Ur Rehman
    ;
    Ullah, Naeem
    ;
    Hassaballa, Abaker A.
    ;
    Jeelani, Mdi Begum
    ;
    Fatima, Nahid
    In this study, we develop and analyze a deterministic fractional-order human–animal–environment transmission model using the Caputo fractional-order derivative (CFOD) to investigate leptospirosis transmission dynamics, explicitly incorporating treatment for infected humans in the human population. The model accounts for indirect transmission through an environmental bacterial reservoir and shedding from infected animals. The qualitative features of the suggested model, such as positivity, boundedness, existence and uniqueness of solution, equilibrium points, and biological well-posedness of the solutions, are thoroughly demonstrated. The model captures nonlocal and memory-dependent characteristics that cannot be described by classical integer-order derivatives. The next-generation matrix (NGM) approach is used to determine the basic reproduction number (ℛ<inf>0</inf><sup>FV</sup>). The stability properties of the pathogen-extinction steady state and sustained-transmission steady state are investigated. In particular, Lyapunov function techniques are used to check the global stability of the PESS and STSS under suitable conditions, while Ulam–Hyers stability is established to examine the stability of the model solutions under small perturbations. To better understand the influence of model parameters, normalized forward sensitivity analysis is performed, showing that transmission, treatment, and recovery-related parameters exert the strongest influence on disease burden. Numerical simulations are used to verify theoretical results and investigate the effects of key epidemiological parameters on disease transmission. Finally, an artificial neural network (ANN) is employed only as a supplementary computational tool to reproduce the numerically obtained solution trajectories and to provide a consistency check of the computed results. The findings offer a valuable perspective on the dynamics of leptospirosis transmission and could inform disease control and intervention efforts.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    PREDICTION OF STOCK PRICE USING HYBRID NEURAL NETWORK: A CASE OF COAL PRODUCTION COMPANY
    (2025-01-15)
    Kiatcharoenpol, Tossapol
    ;
    Klongboonjit, Sakon
    Stock market prediction is a critical issue in the field of economics. As machine learning technologies advance, an increasing number of algorithms are being utilized to forecast stock price movements. Nonetheless, predicting stock market trends remains a challenging task due to the inherent noise and volatility in stock market data. This paper addresses this challenge by proposing a novel hybrid neural network model designed to predict stock market prices using parameters related to commodity prices and stock indices. A case study company is mainly in coal production business in Thailand, which produce coal, sale, distribute and operate coal-fired power plants as well. The Multiple Linear Regression (MLR) and Back propagation neural network (BPNN) as traditional prediction technique are employed to comparatively investigate the accuracy and performance of the proposed HNN. Experiment results show that the prediction accuracy of HNN is superior to MLR but similar to that of the BPNN model. However, HNN has a good performance both in accuracy, speed and practice. It can help investing analysts and investors make their wise decisions.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The Study and Analysis of Passive Power Filter to Improve Power Quality by Using Deep Learning
    (2022-01-01)
    Dangkong, A.
    ;
    Boonseng, C.
    Passive power filter(PPFs) is widely used in large industries due to their ease of use, durability, and stability. Typically, a passive power filter's lifespan can be up to 14 years, but data has shown that it has a shorter service life because of damage to capacitors for a variety of reasons, such as capacitor's degeneration, overheating in reactor, reactor's vibration, and noise due to the flowing of harmonic current through the power filter excessively. This implies that the passive power filter system is in trouble. Furthermore, it has been found that maintaining the capacitor at a low temperature can keep the %THD level within the IEEE 519-2014 range and extend the life of the capacitor. Eventually, the collected data will be used to create a neural network for capacitor prediction and maintenance for further industrial applications.