Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (1876)
- Chemistry (670)
- Computer Sciences (618)
- Engineering (617)
- Education (261)
-
- Computer Engineering (237)
- Polymer Chemistry (203)
- Environmental Sciences (200)
- Mathematics (161)
- Medicine and Health Sciences (99)
- Statistics and Probability (99)
- Chemical Engineering (97)
- Civil and Environmental Engineering (84)
- Science and Mathematics Education (82)
- Earth Sciences (80)
- Electrical and Computer Engineering (78)
- Electrical and Electronics (74)
- Life Sciences (72)
- Physics (72)
- Operations Research, Systems Engineering and Industrial Engineering (71)
- Social and Behavioral Sciences (70)
- Industrial Engineering (69)
- Business (59)
- Operational Research (55)
- Construction Engineering and Management (53)
- Civil Engineering (52)
- Educational Assessment, Evaluation, and Research (44)
- Biotechnology (41)
- Geology (40)
- Educational Administration and Supervision (27)
Articles 1021 - 1050 of 2807
Full-Text Articles in Entire DC Network
Genetic Algorithm Based Deep Multi-Route Self-Attention For Single Image Super-Resolution, Nisawan Ngambenjavichaikul
Genetic Algorithm Based Deep Multi-Route Self-Attention For Single Image Super-Resolution, Nisawan Ngambenjavichaikul
Chulalongkorn University Theses and Dissertations (Chula ETD)
Image restoration, such as single image super-resolution (SISR), is a long-established low-level vision issue that intends to regenerate high-resolution (HR) images from low-resolution (LR) input counterparts. While state-of-the-art image super-resolution models are based on the well-known convolutional neural network (CNN), many self-attention-based or transformer-based experiment attempts have been conducted. They have shown promising performance on vision problems. A powerful baseline model based on the swin transformer adopts the shifted window approach. It enhances the capability by restricting the model to compute the self-attention function only on non-superimpose local windows while enabling cross-window relations. However, the architecture design is manually fixed. …
A Linear Matrix Inequality Approach To Design State Feedback Control For Non-Polynomial Nonlinear Systems, Phing Lim
Chulalongkorn University Theses and Dissertations (Chula ETD)
This thesis aims to design a state feedback controller for non-polynomial systems with bounded control inputs. The problem formulation begins by transforming the non-polynomial systems into polynomial systems. This can be done by defining non-polynomial terms as new state variables with algebraic constraints satisfying the non-polynomial properties. This method avoids the approximation of the recast polynomial systems. Then we design the state feedback control based on the extended Lyapunov stability theorem and the quadratic performance criterion. Two state feedback control laws are proposed: Theorem 1 for static Lyapunov matrix variables and Theorem 2 for polynomial ones. For Theorem 1, the …
Effect Of Drop-Out Layers Inside Recurrent Neural Networks In Household Load Forecast Application, Sanaullah Soomro
Effect Of Drop-Out Layers Inside Recurrent Neural Networks In Household Load Forecast Application, Sanaullah Soomro
Chulalongkorn University Theses and Dissertations (Chula ETD)
Ensuring precise power load forecasting is highly important in planning the secure, steady, and cost-effective functioning of the power system. Grid planning and decision-making can be based on accurate long- and short-term power load forecasting. Recently, machine learning techniques have gained widespread adoption for both long- and short-term power load forecasting. Specifically, the Long Short-Term Memory (LSTM) is customized for time series data analysis. This research proposes an LSTM model for forecasting the power load of a single house containing electrical appliances over the next 20 days. We conducted a comparative analysis of the impact of dropout layers in load …
Deep Consecutive Attention Network For Video Super-Resolution, Talha Saleem
Deep Consecutive Attention Network For Video Super-Resolution, Talha Saleem
Chulalongkorn University Theses and Dissertations (Chula ETD)
In the video application, slow motion is visually attractive and gets more attention in video super resolution. To generate the high-resolution (HR) slow motion video frames from the low-resolution (LR) frames, two sub-tasks are required, including video super-resolution (VSR) and video frame interpolation (VFI). However, the interpolation approach is not successful to extract low level feature attention to get the maximum advantage from the property of space-time relation. To this extent, we propose a deep consecutive attention network-based method. The multi-head attention and an attentive temporal feature module are designed to achieve better prediction of interpolation feature frame. Bi-directional deformable …
Applications Of Deep Learning Framework And Localization To Intelligent Radio Spectrum Monitoring, Truong Thanh Le
Applications Of Deep Learning Framework And Localization To Intelligent Radio Spectrum Monitoring, Truong Thanh Le
Chulalongkorn University Theses and Dissertations (Chula ETD)
In this thesis, the author proposed an intelligent radio spectrum monitoring system with implemented deep learning framework. Deep learning is a powerful method to handle hard tasks automatically. The system uses the RTL-SDR USB dongle as the sensor to collect the spectrum data. This dongle is a low-cost device that can measure the signal from 500kHz to 1700MHz. The maximum bandwidth of measurement is 2MHz. The main functions of this system are to collect the spectrum data and then detect the representation signals and extract their characteristics, such as bandwidth, center frequency, modulation type, and capacity. The modulation classification task …
Functional Split In 5g Cloud Radio Access Network Using Particle Swarm Optimization, Wai Phyo
Functional Split In 5g Cloud Radio Access Network Using Particle Swarm Optimization, Wai Phyo
Chulalongkorn University Theses and Dissertations (Chula ETD)
The Cloud Radio Access Network (C-RAN) is an innovative approach that has the potential to significantly reduce the expenses of setting up and operating wireless networks. C-RAN's placement of RAN functions, which strives to reduce bandwidth utilization and computation costs, is a critical component. In this study, our main goal is to reduce the costs associated with functionally placing the RAN while accounting for the computational expense and the front-haul bandwidth usage among various users. To achieve this, we propose to apply Particle Swarm Optimization (PSO) to achieve effective allocation of computational resources and the front-haul bandwidth, ensuring an efficient …
Effects Of The Writing Instructional Model With Integration Of Inquiry-Based Learning And Visual Literacy On 21st Century Skills Of Efl Learners, Patsawut Sukserm
Effects Of The Writing Instructional Model With Integration Of Inquiry-Based Learning And Visual Literacy On 21st Century Skills Of Efl Learners, Patsawut Sukserm
Chulalongkorn University Theses and Dissertations (Chula ETD)
Although a body of research illustrates the potential of inquiry-based learning in promoting the 21st century skills among English as a Foreign Language (EFL) students (AbuRezeq, 2018; Imansyan et al., 2019; Milatasari, 2013; Palupi et al., 2020; Tongjean et al., 2019), other studies have indicated its occasional failure in eliciting students’ engagement (Duschl & Wright, 1989; Gill, 2005), which affects students’ success in language learning. This results in the need to leverage other pedagogical strategies, including visual literacy, to increase the efficacy of inquiry-based learning (Gonzalez-Ledo, 2015; Maricimoi, 2017; Navidinia et al., 2018; Rokhaniyah, 2019, Sulastri, 2019; Tayib, 2015; Villasor, …
Knowledge, Attitude And Practices On Potato Pest Management Of Ethnic Farmers In Southern Shan State, Myanmar, Pyae Pa Pa Aung
Knowledge, Attitude And Practices On Potato Pest Management Of Ethnic Farmers In Southern Shan State, Myanmar, Pyae Pa Pa Aung
Chulalongkorn University Theses and Dissertations (Chula ETD)
Potato is cultivated as the main tuber crop which is essential for ethnic farmers’ household income in Southern Shan State, Myanmar. Most ethnic farmers use chemical pesticides widely to enhance crop yield and to control pests in the farm. The use of chemical pesticides could lead to a series of health impacts of the farmers and environmental issues. The main aim of the study is to explore farmers’ knowledge, attitude and current farm practices on pest management in potato production. The participants of 100 farmers were chosen from each village with a cluster and purposive sampling technique using structured questionnaires …
Application Of Fractional Exponential Feature To Garch Model Variants For Improvement In Value-At-Risk Prediction, Chanet Saisatian
Application Of Fractional Exponential Feature To Garch Model Variants For Improvement In Value-At-Risk Prediction, Chanet Saisatian
Chulalongkorn University Theses and Dissertations (Chula ETD)
This research studies about using GARCH model variants as a parametric way in estimation and prediction of daily Value-at-Risk (VaR), one of famous risk measurement especially in financial world. To cope with various stylized facts on market’s volatility, two mixed GARCH models are proposed in this research: HY-GJR-GARCH model, the hybrid between hyperbolic GARCH (HYGARCH) and GJR-GARCH models, and HY-MS-GARCH model as the amalgam between HYGARCH and Markov switching GARCH (MSGARCH) models. These mixed models, along with rich mathematical formulations and benefits from their base models, are expected that their performance in predicting daily VaR is advanced against the performance …
Why Is The Third Principal Component Of The Yield Curve Important: A Point Of View From Reverse Stress Test On Credit Portfolio, Phanuwat Ritpornnarong
Why Is The Third Principal Component Of The Yield Curve Important: A Point Of View From Reverse Stress Test On Credit Portfolio, Phanuwat Ritpornnarong
Chulalongkorn University Theses and Dissertations (Chula ETD)
The focus of this study is to analyze the shape of the yield curve on credit portfolios during crises, specifically those that are exposed to both interest rate and credit risks. To achieve this, We utilized a reverse stress test (RST) and macroeconomic measures (such as GDP and U.S risk-free yields) from the period of 1981 to 2014 to estimate mathematical models. We then utilized a Monte Carlo simulation to determine the most likely scenario for the measures if the portfolio value reaches a pre-specified threshold. The researchers discovered that the shape of the stressed yield curves varied depending on …
Geomorphological Change Of The Upper Yom River In Phrae Province, Kakkhanang Na Nan
Geomorphological Change Of The Upper Yom River In Phrae Province, Kakkhanang Na Nan
Chulalongkorn University Theses and Dissertations (Chula ETD)
Yom River is the main tributary of the Chao Phraya River; the upper Yom River flows through Phrae Province. This research selected the upper Yom River because of meander processing in an active basin, which rapidly migrates and changes landforms all the time, The object of this research is to study geomorphological change, thickness and behavior of the upper Yom River in Phrae Province. By assessing aerial photographs and satellite images from 1954 to 2019, the researchers were able to interpret the geological changes that occurred over the past 65 years. The study identified several geomorphological changes from channel migration …
Typology And Formation Of Pothole Along The Mekong River And Erosional Remnant In Sandstone Of Khorat Group, Ubon Ratchathani Province, Northeastern Thailand, Sirawat Udomsak
Chulalongkorn University Theses and Dissertations (Chula ETD)
Phachan Samphanbok Geopark showcases fascinating erosional features, such as a multitude of potholes in the Mekong River. Additionally, it is home to the largest pedestal rock in Thailand, located in Ubon Ratchathani province in the northeastern part of the country, near the border between Thailand and Laos PDR. The formation of potholes is attributed to the erosive force of swirling sediment within fractures caused by vortex currents. In this research study on pothole evolution, the potholes in the Mekong River were categorized into two main groups: structural control potholes and non-structural control potholes. These types were further divided into five …
Analysis Of Fatty Acid Methyl Esters By Two-Dimensional Gas Chromatography Using Cryogen-Free Modulator, Adrian Jose Sacan
Analysis Of Fatty Acid Methyl Esters By Two-Dimensional Gas Chromatography Using Cryogen-Free Modulator, Adrian Jose Sacan
Chulalongkorn University Theses and Dissertations (Chula ETD)
A simple and environmentally friendly method in two-dimensional gas chromatography coupled with mass spectrometry (GC-MS) and flame ionization detector has been developed for the analysis of fatty acids in commercial milk products. This applies splitter-based non-cryogenic artificial trapping (SNAT) modulator with unique feature imitating the cryogenic modulation process. The method involves chemical derivatization into fatty acid methyl esters (FAME) with methanolic potassium hydroxide, liquid-liquid phase extraction using hexane, and determination of the FAME composition. The GC×GC approach revealed improved separation of FAME using SNAT modulator with better separated peaks, a ten-fold higher total peak capacity and improved compound identification, compared …
Lead Removal From Water By Modified Activated Carbon Produced From Banana Stem, Imelda Octa Tampubolon
Lead Removal From Water By Modified Activated Carbon Produced From Banana Stem, Imelda Octa Tampubolon
Chulalongkorn University Theses and Dissertations (Chula ETD)
Banana stem-activated carbon (BSAC) and modified banana stem-activated carbon, containing sulfur, nitrogen, and oxygen-containing groups derived from banana stem, were prepared and studied for Pb(II) ion removal. The materials were characterized by scanning electron microscopy, X-Ray diffraction, surface area analysis, and Fourier transform infrared spectroscopy. SEM images showed that the materials are porous, and XRD confirmed that the structures are amorphous and resemble the graphitic hexagonal structure of carbon materials. Surface areas of these materials ranged from 517.67 m2/g for the bare banana stem activated carbon to 234.03, 453.74, 252.97, and 22.96 m2/g for sulfur, oxygen, sulfur and oxygen and …
Life Cycle Assessment Of Canned Fish Production In Thailand, Chanya Kraiwed
Life Cycle Assessment Of Canned Fish Production In Thailand, Chanya Kraiwed
Chulalongkorn University Theses and Dissertations (Chula ETD)
The canned fish industry is one of the world's most popular exports in Thailand. Moreover, the canned seafood industry ranks fourth in terms of energy consumption, which compares to all industry group (Wiriyatangsakul, 2021). Commercial competitiveness, on the other hand, must be improved because of the competitive conditions in the global market. Thus, this study evaluates the environmental performance of a factory in Samut Sakhon, Thailand, using Life Cycle Assessment (LCA) with Gate-to-Gate approach and setting functional unit by 1 ton fresh fish entering to process. The study used the SimaPro LCA application with the CML 2 baseline 2000 method, …
The Potential Risk And Occupational Exposure Of Pesticides Among Rice Farmers In Delta Ayeyarwady Division, Myanmar, Moe Thu Khin
The Potential Risk And Occupational Exposure Of Pesticides Among Rice Farmers In Delta Ayeyarwady Division, Myanmar, Moe Thu Khin
Chulalongkorn University Theses and Dissertations (Chula ETD)
This study aims to assess the potential risk and occupational exposure of pesticides among rice farmers in the Delta Ayeyarwady Region, Myanmar. A cross-sectional study was carried out with 454 rice farmers from March-April 2022. Data collection was done through face-to-face interviews used with a semi-structured questionnaire. The study showed that the mean age of farmers was 44.36 years old while the range was 16 and 74 years old. Rice farmers' average weight (± standard deviation) was 56.86 (± 7.30) kg. In this study, over two-thirds of the rice farmers (77 %) had a moderate level of knowledge regarding environmental …
Assessment Of Greenhouse Gases Emissions From Dairy Cattle Production In Thailand, Phoo Pwint Pwint Thu
Assessment Of Greenhouse Gases Emissions From Dairy Cattle Production In Thailand, Phoo Pwint Pwint Thu
Chulalongkorn University Theses and Dissertations (Chula ETD)
Thailand’s agriculture sector plays a vital role in driving economic growth. Globally, livestock production is estimated to contribute about 18% of greenhouse gas (GHG) emissions. Despite its importance, there is a relative lack of research on GHGs assessment in the livestock sector in Thailand. The aim of this research was to estimate GHGs emissions from dairy cattle production in Saraburi and Ratchaburi provinces of Thailand. The 2019 Refinement to the 2006 IPCC guidelines for national greenhouse gas inventories was applied in this research. Twenty dairy farms (n=20) including both small farms (n=10) and medium farms (n=10) were selected as the …
Water-Use Characteristics Of Syzygium Antisepticum And Adinandra Integerrima In A Secondary Tropical Forestin Khao Yai National Park For Environmental Management, Ratchanon Ampornpitak
Water-Use Characteristics Of Syzygium Antisepticum And Adinandra Integerrima In A Secondary Tropical Forestin Khao Yai National Park For Environmental Management, Ratchanon Ampornpitak
Chulalongkorn University Theses and Dissertations (Chula ETD)
Forests in Southeast Asia have been disrupted by widespread deforestation and land use change. Most countries in this region attempt to return the forested areas through reforestation. However, planting trees efficiently is difficult because changing environmental conditions and tree size could affect the water consumption of different tree-species under climate change. Hence, the information regarding water use characteristics of different tree-species in different tree size classes is important to the selection of tree species for reforestation. Nonetheless, available information on species-specific water-use characteristics is less investigated, especially in secondary tropical forests. To gain the information on species-specific water-use characteristics in …
Analyzing Impact Of Economic Indicators On Vietnam Stock Market With Machine Learning Techniques, Nuttawan Sangsawai
Analyzing Impact Of Economic Indicators On Vietnam Stock Market With Machine Learning Techniques, Nuttawan Sangsawai
Chulalongkorn University Theses and Dissertations (Chula ETD)
The study provides an analysis of the Vietnamese stock market using statistical and machine learning models. The dataset shows that all features have a positive linear relationship with the VN Index, but exhibit different scales and degrees of skewness. The Augmented Dickey-Fuller (ADF) unit root test was conducted to identify whether the variables were stationary or non-stationary, and most variables were transformed into stationary data through first differencing. The OLS method was used to construct a short run model, and the results indicated that only three variables, namely CPI, exchange rate, and S&P500 index, exhibited statistical significance. The ARDL Bound …
Multi-Objective Vehicle Loading And Routing Problem For Fresh Fruit And Vegetable Transportation, Supisara Krairiksh
Multi-Objective Vehicle Loading And Routing Problem For Fresh Fruit And Vegetable Transportation, Supisara Krairiksh
Chulalongkorn University Theses and Dissertations (Chula ETD)
Multi-compartment refrigerated vehicles are recently utilized in the cold chain industry, due largely to their flexibility in storage capacities with different temperature settings. To better comprehend the costs and benefits of this vehicle type in fresh fruits and vegetable transportation, a multi-compartment vehicle routing and loading problem (MCVRLP) with three different objectives – namely (i) minimizing total transportation cost, (ii) minimizing CO2 emissions, and (iii) minimizing weight loss of fresh fruits and vegetable – is herein explored and solved by mathematical formulation and genetic-based evolutionary algorithm approaches. Based on our computational results, we find that large and complicated MCVRLP instances …
Bitcoin Candlestick Price Prediction With Recurrent Neural Network, Sutiwat Simtharakao
Bitcoin Candlestick Price Prediction With Recurrent Neural Network, Sutiwat Simtharakao
Chulalongkorn University Theses and Dissertations (Chula ETD)
Bitcoin is a high-risk asset with a potentially high return. Predicting Bitcoin candlestick, i.e., open, high, low, and close (OHLC) prices, can help investors make trading decisions. The objective of this study is to develop a neural network model to predict the candlestick prices of Bitcoin for the next period. Additionally, this study investigates methods to enhance the model's forecasting performance by feature transformations, specifically data normalization. This study employs two neural network algorithms, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), to forecast daily Bitcoin OHLC prices. To enhance the model's performance, we compare sliding window normalization with …
Wastewater-Based Epidemiology And Quantitative Microbial Risk Assessment Associated With Wastewater Contact Of Norovirus In Bangkok, Thailand, Nonnarit Sriporatana
Wastewater-Based Epidemiology And Quantitative Microbial Risk Assessment Associated With Wastewater Contact Of Norovirus In Bangkok, Thailand, Nonnarit Sriporatana
Chulalongkorn University Theses and Dissertations (Chula ETD)
Norovirus is one of the leading causes of acute gastroenteritis worldwide. Wastewater surveillance offer significant benefits such as enhancing our understanding of the disease occurrence in the population, evaluating the effectiveness of pathogen reduction in the treatment process, and tracking the spread of pathogens in the environment which pose a health risk to humans. Hence, wastewater surveillance is crucial. In this study, the influent and effluent samples were collected bi-monthly from March 2020 to March 2021 from three distinct wastewater treatment plants in Bangkok. Wastewater samples were concentrated and subjected to quantitative polymerase chain reaction (qPCR) to assess norovirus concentrations. …
Connected Size Ramsey Numbers Of Matching And Some Graphs, Jirawat Mungtumklang
Connected Size Ramsey Numbers Of Matching And Some Graphs, Jirawat Mungtumklang
Chulalongkorn University Theses and Dissertations (Chula ETD)
No abstract provided.
Eigenvalues Of Unitary Cayley Graph Of Matrix Algebras And Its Subconstituents, Jitsupat Rattanakangwanwong
Eigenvalues Of Unitary Cayley Graph Of Matrix Algebras And Its Subconstituents, Jitsupat Rattanakangwanwong
Chulalongkorn University Theses and Dissertations (Chula ETD)
No abstract provided.
The Cardinality Of The Permutations On A Set With N Non-Fixed Points, Jukkrid Nuntasri
The Cardinality Of The Permutations On A Set With N Non-Fixed Points, Jukkrid Nuntasri
Chulalongkorn University Theses and Dissertations (Chula ETD)
In this thesis, we study relationships between |Sn(A)| and |seqn1-1(A)| as well as |seqn(A)| for infinite sets A, where Sn(A) is the set of permutations of A with n non-fixed points and seqn(A) and seqn1-1(A) are the set of sequences and the set of one-to-one sequences of elements of A with length n, respectively, where n is a natural number greater than 1. With the Axiom of Choice (AC), |Sn(A)|, |seqn1-1(A)|, and |seqn(A)| are equal for all infinite sets A. Among our results, we show, in the Zermelo-Fraenkel set theory (ZF), that |Sn(A)|<=|seqn1-1(A)| for any infinite set A under some weak form of AC and the assumption cannot be removed. In the other direction, we show that |seqn1-1(A)|<=|Sn+1(A)| for any infinite set A and the subscript n+1 cannot be reduced to n. Moreover, we also show that "|Sn(A)|<=|Sn+1(A)| for any infinite set A" is not provable in ZF.
Valuation Of American Commodity Options, Piyapoom Nonsoong
Valuation Of American Commodity Options, Piyapoom Nonsoong
Chulalongkorn University Theses and Dissertations (Chula ETD)
In this dissertation, we present analytical option pricing formulas for European and American options in which the price dynamics of a risky asset follows a meanreverting process with time-dependent parameter. The process can be adapted to describe both nonseasonal and seasonal variation in price, especially, in commodity markets such as agricultural commodities. The formulas are derived based on the solutions of partial differential equations showing that the values of both European and American options can be decomposed into two parts: the payoff of the option at initial time and the time-integral over the lifetime of the option, which is driven …
Threshold Numbers Of Some Complete Multipartite Graphs And Their Complements, Thanaporn Sumalroj
Threshold Numbers Of Some Complete Multipartite Graphs And Their Complements, Thanaporn Sumalroj
Chulalongkorn University Theses and Dissertations (Chula ETD)
No abstract provided.
Development Of Stiffness Sensing And Adaptive Grasping With Soft Pneumatic Grippers, Chaiwuth Sithiwichankit
Development Of Stiffness Sensing And Adaptive Grasping With Soft Pneumatic Grippers, Chaiwuth Sithiwichankit
Chulalongkorn University Theses and Dissertations (Chula ETD)
This study presents a framework for stiffness sensing and adaptive grasping using soft pneumatic grippers (SPGs). The motivation was to imitate the capabilities of human hands. The challenge was the compliance of soft pneumatic actuators (SPAs). The study associated the behaviors of grasped objects with those on SPAs, introduced a new concept of SPA modeling, and proposed a method for stiffness sensing through SPG pincer grasping. Compression testing was conducted for validation. A technique for forecasting deformation and force on grasped objects based on their stiffness was established, and a control law was elaborated. The presented technique and control architecture …
Effect Of Inter-Observer Delineation Variability On Radiomics Features In Nasopharyngeal Cancer, Pongpitch Panyura
Effect Of Inter-Observer Delineation Variability On Radiomics Features In Nasopharyngeal Cancer, Pongpitch Panyura
Chulalongkorn University Theses and Dissertations (Chula ETD)
Nasopharyngeal cancer (NPC) is a type of head and neck cancer that is prevalent in China and Southeast Asia. The standard treatment for NPC is radiation therapy (RT), which requires accurate target volume delineation (TVD) to ensure an effective radiation dose while minimizing damage to surrounding healthy tissues. However, TVD is subject to intra- and inter-observer variability, which can affect the accuracy of RT and lead to unstable results in radiomics analysis. Radiomics is a technique that extracts quantitative data from medical images, but it is currently limited by the manual process of tumor delineation. This study aims to investigate …
Accuracy In Classification Of Liver Lesion Ultrasound Using Artificial Intelligence, Sutthirak Tangruangkiat
Accuracy In Classification Of Liver Lesion Ultrasound Using Artificial Intelligence, Sutthirak Tangruangkiat
Chulalongkorn University Theses and Dissertations (Chula ETD)
B-mode ultrasound imaging is the standard method for hepatocellular carcinoma (HCC) screening. If a lesion has a unique appearance, a conventional detector can be applied. However, if the lesion shares its appearance with other lesion, a large training dataset is required, which may be unavailable. Therefore, a two-stage method is proposed. In the first stage, lesions are detected but not differentiated into any particular class. The detected lesions are then classified in the second stage using a conventional convolutional neural network (CNN). The aims of the dissertation are to design an artificial intelligent system model and to investigate the most …