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 781 - 810 of 2807
Full-Text Articles in Entire DC Network
Parameters Optimization In Chlor-Alkali Ion-Exchange Membrane Electrolysis Process With Artificial Neural Network, Kittapas Sukantowong
Parameters Optimization In Chlor-Alkali Ion-Exchange Membrane Electrolysis Process With Artificial Neural Network, Kittapas Sukantowong
Chulalongkorn University Theses and Dissertations (Chula ETD)
Since ion-exchange membrane electrolysis cell has developed for producing Chlor-Alkali products. New higher efficiency and lower consumption technology are released from licensors yearly, which made the process correlation deviate from the original design. The machine learning is used with “Neural Network Fitting Tool (nftool)” in MATLAB. To find a correlation between 5 inputs consisting of current density (CD, KA/m2), operation day (DOL, day), feed brine flow rate (QFB, m3/h), feed caustic flow rate (QHD, m3/h), cell temperature (T, degC) and one output which is cell voltage (CV, V). Datasets were collected from the plant information management system “exaquantum” historian database. …
Control Of A Polybutylene Succinate (Pbs) Polymerization In A Semi-Batch Reactor By Neural Network Model Based Predictive Controller, Takorn Plengsangsri
Control Of A Polybutylene Succinate (Pbs) Polymerization In A Semi-Batch Reactor By Neural Network Model Based Predictive Controller, Takorn Plengsangsri
Chulalongkorn University Theses and Dissertations (Chula ETD)
Polybutylene succinate (PBS) is a biodegradable plastic known for its strength and versatility in various applications. This research presents a data-driven approach to simulate temperature control in a semi-batch reactor during polymerization, the performance of the proposed approaches was compared against conventional controllers, including PID control and first-principles model MPC control. The study developed neural network model-based predictive control (NNMPC) and multiple neural network model-based predictive control (Multi-NNMPC), using Python and Tensorflow. Neural network models were trained by using a wide range of dynamic data with varying numbers of neurons in hidden layers to investigate the process dynamics under different …
Design Of Process For Recovery Of Gold And Nickel Ions From Wastewater Of Metal Plating Process In Electronics Industry Using Hollow Fiber Supported Liquid Membrane, Wanchalerm Srirachat
Design Of Process For Recovery Of Gold And Nickel Ions From Wastewater Of Metal Plating Process In Electronics Industry Using Hollow Fiber Supported Liquid Membrane, Wanchalerm Srirachat
Chulalongkorn University Theses and Dissertations (Chula ETD)
In the manufacture of printed circuit boards (PCBs), electroless nickel immersion gold (ENIG) plating is widely applied. During the plating process, excess nickel and gold plating solutions, which adheres to the workpiece, is removed. As a result, economical quantities of nickel and gold ions accumulate in the rinse water baths and can then be collected. In this work, the simultaneously selective extraction and recovery of nickel and gold ions using a single-step operation of hollow fiber supported liquid membrane (HFSLM) technique was studied. Real rinse wastewater from the plating process containing trace nickel ions (Ni(II)) of 15 mg/L and gold …
The Study Of Weave-Pattern Effect On Filtration Performance Of Woven Filter Cloths By Computational Fluid Dynamic Modeling, Wisit Bandasak
The Study Of Weave-Pattern Effect On Filtration Performance Of Woven Filter Cloths By Computational Fluid Dynamic Modeling, Wisit Bandasak
Chulalongkorn University Theses and Dissertations (Chula ETD)
An important global problem that has an impact on both human health and the environment is air pollution. Exercise and outdoor activities are essential for human well-being, but they can also have a detrimental effect on health and the environment. For example, PM2.5 and PM10 particles can enter the lungs and cause respiratory and cardiovascular disorders. Moreover, masks must be worn in order to stop the COVID-19 epidemic from spreading. Nevertheless, not all masks are effective in preventing viruses and air pollution. Consequently, selecting the proper mask is essential for avoiding health risks. Using the use of computational fluid dynamics, …
Improvement Of Hydrodynamics And Heat Transfer In Biomass Fluidized Bed Combustor With Immersed Tubes Using Cfd-Dem, Krittin Korkerd
Improvement Of Hydrodynamics And Heat Transfer In Biomass Fluidized Bed Combustor With Immersed Tubes Using Cfd-Dem, Krittin Korkerd
Chulalongkorn University Theses and Dissertations (Chula ETD)
Computational Fluid Dynamics coupled with Discrete Element Method (CFD-DEM) has been extensively utilized for studying hydrodynamics and heat transfer in fluidization processes. This study specifically focuses on improving hydrodynamics and heat transfer in a biomass fluidized bed combustor with immersed tubes. The investigation involves the use of mixed biomass, exploring the effects of biomass types, biomass loading, and blending ratios to propose criteria for selecting suitable biomass fuel for the system. Design parameters related to the immersed tubes, such as the angle between tubes, tube diameters, and distance between tubes, were also considered. A data-driven model was developed based on …
Chemical Constituents From The Fresh Pericarps Of Mature Mangosteen Fruit Garcinia Mangostana, Ahmad Tijani Azeez
Chemical Constituents From The Fresh Pericarps Of Mature Mangosteen Fruit Garcinia Mangostana, Ahmad Tijani Azeez
Chulalongkorn University Theses and Dissertations (Chula ETD)
α-Mangostin has been identified as a major chemical constituent in the pericarps of mangosteen (Garcinia mangostana Linn.) Over time, dried pericarps of mangosteen have been subjected to studies in literature. This study aimed to explore isolation of α-mangostin and other chemical constituents from the fresh pericarps of mature mangosteen fruits and investigate their relative antioxidant and anticancer activities. Repeated column chromatography on ethyl acetate and methanol extracts of fresh mature mangosteen pericarps led to the isolation of α-mangostin (33.25% of crude extracts) as the major compound, beta-mangostin (0.225%) and gartanin (7.57%). Their antioxidant scavenging activity was investigated against 2,2-diphenyl-1-picrylhydrazyl (DPPH) …
Simultaneous Extraction And Colorimetric Detection Of Ions Using Gel Electromembrane, Ali Sahragard
Simultaneous Extraction And Colorimetric Detection Of Ions Using Gel Electromembrane, Ali Sahragard
Chulalongkorn University Theses and Dissertations (Chula ETD)
A total integrated electrocolorimetric sensing approach consisting of gel-based electromembrane extraction and colorimetric detection in one-step process was developed. This system was designed using colorimetric reagents preadded to the agarose gel for the determination of the following two model analytes: iodide for negative ions and nickel for positive ions. In this system, when a voltage was applied, the analytes were extracted and transferred from the sample solution (donor phase) to the gel (acceptor phase). The analytes then simultaneously reacted with the colorimetric reagents inside the gel, yielding blue and pink colors for iodide and nickel ions, respectively. These colors were …
Fluorescent Hydrazine-Naphthalimide Encapsulated By Ethyl Cellulose For Detection Of Long-Chain Aldehydes, Faiza Lawan Isah
Fluorescent Hydrazine-Naphthalimide Encapsulated By Ethyl Cellulose For Detection Of Long-Chain Aldehydes, Faiza Lawan Isah
Chulalongkorn University Theses and Dissertations (Chula ETD)
One of the most common diseases globally which takes numerous lives is lung cancer. The high concentrations of aldehydes found in tobacco smoke and motor vehicle exhaust are among the contributors for lung cancer. There is a lot of interest in developing a nanosensor for identifying long-chain aldehydes. The conventional methods for detecting aldehyde are highly complex, expensive, and time-consuming. To overcome this drawback, alternative detection techniques such as fluorescence techniques are needed for the quick, easy, and affordable identification of aldehydes. Aldehyde molecules and their derivatives are often used as biomarkers to aid in the diagnosis and treatment of …
Deep Eutectic Solvent-Coated Paper-Based Device For Colorimetric Detection Of Chromium(Vi), Fakhry Gripaldi Pandu
Deep Eutectic Solvent-Coated Paper-Based Device For Colorimetric Detection Of Chromium(Vi), Fakhry Gripaldi Pandu
Chulalongkorn University Theses and Dissertations (Chula ETD)
Hexavalent chromium, Cr(VI), is one of the heavy metal ions often found in the environment that is highly toxic and classified as a carcinogen. In this work, rapid screening and onsite monitoring of Cr(VI) using paper-based has been developed. Furthermore, a natural-based deep eutectic solvent, comprising choline chloride and thymol that makes it an environmentally friendly solvent, is applied as a coating medium on the test strips for qualitative and quantitative analysis of Cr(VI) for the first time. 1,5-Diphenylcarbazide was used as an indicator and complexing agent for Cr(VI). The detection was conducted by using a smartphone equipped with an …
Use Of Layered Double Hydroxides As Ionophore For Anion Selective Electrode, Kittipong Konraeng
Use Of Layered Double Hydroxides As Ionophore For Anion Selective Electrode, Kittipong Konraeng
Chulalongkorn University Theses and Dissertations (Chula ETD)
Layered double hydroxides (LDHs) or hydrotalcite compounds are referred to anionic clays with specific anion adsorption and exchanging properties. These behaviors are similar to ionophores and ionic additives in ion selective electrodes (ISEs). Therefore, in this study LDHs was used to function as tailor-made ionophores for particular anions and ionic additives in ISEs. MgAl LDHs were prepared, and then modified the intercalated anions to be NO3-. The selective polymeric membrane was casted using PVC and MgAl LDHs-NO3-. The membrane containing 30%(w/w) MgAl LDHs-NO3- showed the best ISE characteristics toward NO3- with response slopes of -51.31 mV decade-1 in the concentration …
Colorimetric Detection Of Norfloxacin And Ceftazidime By Modified Materials, Lalitphan Hongtanee
Colorimetric Detection Of Norfloxacin And Ceftazidime By Modified Materials, Lalitphan Hongtanee
Chulalongkorn University Theses and Dissertations (Chula ETD)
Novel approaches were developed for the colorimetric detection of norfloxacin and ceftazidime using chemically modified polymer resin and cotton sponge as sensing materials, respectively. For norfloxacin detection, the optimum condition was achieved by using a resin modified with 6.0 µM Congo red at pH 6 to extract norfloxacin in 10 mL of sample at pH 2. The reaction was completed within 15 minutes. Regarding ceftazidime detection, a cotton sponge functionalized with polyethyleneimine (PEI) was fabricated and characterized by FTIR, SEM, and ninhydrin test. To fabricate the PEI-sponge, 170 mM 3-aminopropyl triethoxysilane (APTES) was used to modify 1.0 g cotton fibers …
Nickel Complexes Containing N4 Schiff-Base Macrocycles Dereived From Diphenylamine-2,2'-Dicarboxaldehyde For Catalytic Co2 Reduction, Methasit Juthathan
Nickel Complexes Containing N4 Schiff-Base Macrocycles Dereived From Diphenylamine-2,2'-Dicarboxaldehyde For Catalytic Co2 Reduction, Methasit Juthathan
Chulalongkorn University Theses and Dissertations (Chula ETD)
In this dissertation, nickel(II) complexes featuring N4-Schiff base macrocycles derived from diphenylamine-2,2'-dicarboxaldehyde (1-Ni and 2-Ni) with a new crystal structure ([2-Ni]Me) were synthesized and investigated for electrochemical CO2 reduction (ECR). Cyclic voltammetry (CV) of two nickel complexes, 1-Ni and 2-Ni, illustrated the catalytic response whereas one, [2-Ni]Me, virtually remained peak-shaped in the presence of CO2, indicating the feasibility of ECR activity for these nickel complexes. To develop heterogeneous ECR catalysts in aqueous media, all nickel complexes were adhered on N-doped graphene (NG) through non-covalent interaction, obtaining Ni@NG hybrid catalysts. The Ni@NG catalysts showed satisfactory ECR activity with the faradaic efficiency …
Enhancement Of Ammonia Gas Sensing By Metal Oxide-Polyaniline Nanocomposite, Nattawut Soibang
Enhancement Of Ammonia Gas Sensing By Metal Oxide-Polyaniline Nanocomposite, Nattawut Soibang
Chulalongkorn University Theses and Dissertations (Chula ETD)
Ammonia (NH3) gas is an important chemical in many industries. Employees who work in those industrial areas may exposed to a certain concentration of NH3 which could cause various symptoms such as irritation of skin and eyes and problems in respiratory system. The development of new NH3 sensing material has drawn a great attention. In this study, porous tin dioxide nanofibers (SnO2 NFs) were successfully fabricated by an electrospinning technique. The SnO2 NFs were composited with polyaniline (PANI), conducting polymer and form tin dioxide nanofibers@polyaniline nanocomposite (SnO2 NFs@PANI). The morphology was characterized using SEM-EDS and XRD. The SnO2 NFs@PANI was …
Emulsification Microextraction Using Surfactant Coupled With Colorimetric Detection For Determination Of Synthetic Dyes In Food, Niluh Indria Wardani
Emulsification Microextraction Using Surfactant Coupled With Colorimetric Detection For Determination Of Synthetic Dyes In Food, Niluh Indria Wardani
Chulalongkorn University Theses and Dissertations (Chula ETD)
In this thesis, solidification of floating organic drop-emulsification liquid-liquid microextraction (SFOD-ELLME) was combined with digital image colorimetry (DIC) for the analysis of synthetic dyes, such as rhodamine B (RhB) and crystal violet (CV) in food and drink samples. Here, the extraction was performed by using emulsified fatty acid surfactant and freezing procedure to separate the extracting phase. The solidified floating organic drop was then taken out, liquified and dropped on the paper platform for digital image colorimetric analysis. The response surface methodology-central composite design (RSM-CCD) was used to optimize some variables that influence the extraction efficiency. A sample of 7 …
Development Of Dna Detection System Using G-Quadruplex As Catalyst For Colorimetric Detection With Pyrrolidinyl Peptide Nucleic Acid, Somlawan Thipkunthong
Development Of Dna Detection System Using G-Quadruplex As Catalyst For Colorimetric Detection With Pyrrolidinyl Peptide Nucleic Acid, Somlawan Thipkunthong
Chulalongkorn University Theses and Dissertations (Chula ETD)
Nucleic acid sequence detection is very important for many applications such as the diagnosis of genetic diseases. The development of new, simple yet effective methods is still in great demand. Among several options, colorimetric detection is a technique that does not require complicated instruments and allows the detection by naked eyes. In this work, a new colorimetric DNA detection system was developed using the combination of a pyrrolidinyl peptide nucleic acid (acpcPNA) probe and a G-quadruplex/hemin DNAzyme. The G-quadruplex is formed from G-rich DNA sequences, and in the presence of hemin, a DNAzyme is formed which effectively catalyzes the oxidation …
Prediction Of Soil Sorption Coefficient Of Chemicals By Molecular Modeling Technique, Wasin Pithaktrakool
Prediction Of Soil Sorption Coefficient Of Chemicals By Molecular Modeling Technique, Wasin Pithaktrakool
Chulalongkorn University Theses and Dissertations (Chula ETD)
Soil pollution is one of the pollutions caused by nature and human activities, which are mostly the use of insecticide and chemical fertilizer to make plants grow well and produce more products. However, these chemicals are absorbed by soil. In this research work, properties of chemical compound affecting soil sorption were analyzed, and model that can predict soil sorption coefficient of chemicals (KOC) was examined by using quantitative structure property relationship (QSPR) technique. Totally 1,327 compounds were selected, and their three-dimensional structures were constructed. Semi-empirical PM7 method was used for geometry optimization calculations. A total of 1,536 physicochemical properties were …
An Analytical Network Process (Anp) Model For Choosing Optimal Public-Private Partnership (Ppp) Contract Types For Infrastructure Projects, Su Lae Yee Zaw
An Analytical Network Process (Anp) Model For Choosing Optimal Public-Private Partnership (Ppp) Contract Types For Infrastructure Projects, Su Lae Yee Zaw
Chulalongkorn University Theses and Dissertations (Chula ETD)
With the rapid social and economic development, a great deal of expenditure is crucial for the nation's infrastructure development. Nevertheless, the governments of many developing nations have been experienced with the limited budget and technical inability to deliver effective public infrastructures. Public-private partnership (PPP) has been adopted as an alternative collaboration arrangement between the government and the private sector in many nations to overcome these challenges. PPP can be defined as a long-term contract between a public agency and a private entity for rendering public facilities, including design, construct, finance, operate, and manage the project. The PPP contract types can …
Mediastinal Lymph Node Detection And Segmentation Using Deep Learning, Al-Akhir Nayan
Mediastinal Lymph Node Detection And Segmentation Using Deep Learning, Al-Akhir Nayan
Chulalongkorn University Theses and Dissertations (Chula ETD)
Automatic lymph node (LN) segmentation and detection for cancer staging are critical. In clinical practice, computed tomography (CT) and positron emission tomography (PET) imaging detect abnormal LNs. Despite its low contrast and variety in nodal size and form, LN segmentation remains a challenging task. Deep convolutional neural networks frequently segment items in medical photographs. Most state-of-the-art techniques destroy image's resolution through pooling and convolution. As a result, the models provide unsatisfactory results. Keeping the issues in mind, a well-established deep learning technique UNet++ was modified using bilinear interpolation and total generalized variation (TGV) based upsampling strategy to segment and detect …
Recasnet: Reducing Mismatch Within The Two-Stage Mitosis Detection Framework, Chawan Piansaddhayanon
Recasnet: Reducing Mismatch Within The Two-Stage Mitosis Detection Framework, Chawan Piansaddhayanon
Chulalongkorn University Theses and Dissertations (Chula ETD)
Mitotic count (MC) is an important histological parameter for cancer diagnosis and grading, but the manual process to obtain this metric is tedious and not fully reproducible across different pathologists. To mitigate this problem, several deep learning models have been utilized to speed up the process. Typically, the problem is formulated as a two-stage deep learning pipeline: the detection stage for proposing the potential candidates for mitotic cells and the classification stage for refining prediction confidences from the former stage. However, this paradigm can lead to inconsistencies in the classification stage due to the poor prediction quality of the detection …
Leverage Graph Neural Network For Molecular Properties Prediction, Kamol Punnachaiya
Leverage Graph Neural Network For Molecular Properties Prediction, Kamol Punnachaiya
Chulalongkorn University Theses and Dissertations (Chula ETD)
During the age of deep learning technologies, which have exhibited significant potential in reducing costs and expediting medical development, predicting molecular properties has become a prevalent task that capitalizes on the capabilities of deep learning. This thesis proposed a multimodal Graph Neural Network (GNN) model that utilizes the topology information obtained from molecular graphs through a baseline GNN, facilitating precise property predictions. The thesis improves the baseline CMPNN model by exploring various methods to address potential missing gaps. These methods include incorporating the multimodal module, such as a Bidirectional LSTM module capable of processing text sequences in SMILES format or …
Service Placement Optimization For Location-Based Service, Karnkitti Kittikamron
Service Placement Optimization For Location-Based Service, Karnkitti Kittikamron
Chulalongkorn University Theses and Dissertations (Chula ETD)
Location-based service (LBS) is necessary and useful for several applications including navigation and games. These real-time applications require high accuracy and low delay. In general, the complexity of indoor localization algorithms used in LBS depends on the size of fingerprint data. This can lead to long delays when operating in large-scale areas. In this paper, we propose a novel optimization framework for edge service placement, aiming at minimizing the overall cost of edge computing deployment and service response time. Our placement strategy is used to solve the formulated edge node placement problems. The simulated annealing approach is then used in …
Machine Learning For Wavelet-Based Valve Stiction Detection, Kris Prasopsanti
Machine Learning For Wavelet-Based Valve Stiction Detection, Kris Prasopsanti
Chulalongkorn University Theses and Dissertations (Chula ETD)
Valve stiction presents challenges in industrial process control, leading to oscillations and hindering the regulation of fluid flow. This thesis addresses the detection of valve stiction by exploring the limitations of current methods and proposes a novel approach that combines wavelet reconstruction and convolutional neural networks (CNN) to enhance stiction detection performance. The proposed method utilizes preprocessed process variable versus controller output (PV(OP)) plots as input to the CNN model, capitalizing on the distinctive characteristics of stiction. Training and evaluation employ both simulated and real-world data from the International Stiction Data Base (ISDB), with the F1 score serving as the …
Deep Reinforcement Learning For Electricity Energy Trading, Manassakan Sanayha
Deep Reinforcement Learning For Electricity Energy Trading, Manassakan Sanayha
Chulalongkorn University Theses and Dissertations (Chula ETD)
The deregulation and liberalization of the energy market in the 1990s prompted short-term electricity trading, allowing energy markets to produce net output over a range of time periods as a result of this decentralized system, most commonly minutes to days ahead of time. The energy industry urgently requires a system that has undergone substantial modernization in place to handle a variety of issues, including the current climate, renewable resources, and the energy framework. In this dissertation, we investigate a deep reinforcement learning framework for both wholesale and local energy trading, which probes the challenge of RL to optimize the real-world …
Real-Time Image Classification For Malignant Biliary Strictures On Cholangioscopy Images Based On Deep Learning Approach, Passakron Phuangthongkham
Real-Time Image Classification For Malignant Biliary Strictures On Cholangioscopy Images Based On Deep Learning Approach, Passakron Phuangthongkham
Chulalongkorn University Theses and Dissertations (Chula ETD)
It is challenging to determine if the cause of bile duct strictures is benign or malignant. Currently, endoscopists may more precisely inspect the bile duct thanks to computerized single-operator cholangioscopy. As a result, lesions in the bile duct can be seen with the naked eye. However, endoscopists continue to diagnose patients differently. Consequently, a biopsy is typically regarded as the gold standard. The necessity to repeat operations results from a biopsy sample mistake that results in a false-negative cancer diagnosis. In this study, we suggest a convolutional neural network developed particularly for real-time malignant biliary stricture classification. Our approach, which …
Formal Models For Consent Management In Healthcare Software System Development, Neda Peyrone
Formal Models For Consent Management In Healthcare Software System Development, Neda Peyrone
Chulalongkorn University Theses and Dissertations (Chula ETD)
In the era of data-driven opportunities, many businesses are missing the data-privacy challenge, which leads to risks in safeguarding their customers’ data. To empower individuals (data subjects) to control their data, the General Data Protection Regulation (GDPR) mandated businesses or organizations (data controllers) to protect individuals’ data (personal data) within data protection law. Nevertheless, many businesses still struggle to enhance and develop their software systems to comply with the GDPR because it is difficult to interpret and apply to software development practices. Besides, the processing of personal data begins when the data subject provides explicit consent to the data controller, …
Real-Time Gastric Intestinal Metaplasia Semantic Segmentation With Multiple Abnormalities Using Deep Learning Approach, Passin Pornvoraphat
Real-Time Gastric Intestinal Metaplasia Semantic Segmentation With Multiple Abnormalities Using Deep Learning Approach, Passin Pornvoraphat
Chulalongkorn University Theses and Dissertations (Chula ETD)
This thesis declares the segmentation of gastric intestinal metaplasia (GIM) in real-time. Recently, GIM segmentation of endoscopic images has been conducted to distinguish GIM from a healthy stomach. However, achieving real-time detection is difficult. Challenging conditions include multiple color modes (white light endoscopy and narrow-band imaging), other abnormal lesions (erosion and ulcer), noisy labels, etc. Herein, our model is based on BiSeNet and can overcome the many issues regarding GIM. Applying auxiliary head and loss boosts the performance on multiple color modes. In addition, pre-processing techniques, including location-wise negative sampling, jigsaw augmentation, and label smoothing, are utilized to improve detection …
Multi-Agent Deep Reinforcement Learning For Cryptocurrency Trading, Kittiwin Kumlungmak
Multi-Agent Deep Reinforcement Learning For Cryptocurrency Trading, Kittiwin Kumlungmak
Chulalongkorn University Theses and Dissertations (Chula ETD)
Reinforcement learning has emerged as a promising approach for enhancing profitability in cryptocurrency trading. However, the inherent volatility of the market, especially during bearish periods, poses significant challenges in this domain. Existing literature addresses this issue through the adoption of single-agent techniques such as deep Q-network (DQN), advantage actor-critic (A2C), and proximal policy optimization (PPO), or their ensembles. Despite these efforts, the mechanisms employed to mitigate losses during bearish market conditions within the cryptocurrency context lack robustness. Consequently, the performance of reinforcement learning methods for cryptocurrency trading remains constrained within the current literature. To overcome this limitation, we present a …
Corporate Credit Rating Prediction Using Deep Learning, Napasorn Thavichaigarn
Corporate Credit Rating Prediction Using Deep Learning, Napasorn Thavichaigarn
Chulalongkorn University Theses and Dissertations (Chula ETD)
Corporate credit rating has an important role in reducing asymmetric information between investors and borrowers and assisting investors as a signal of the entities’ performance and creditworthiness for making appropriate investment decisions in a company’s assets. The economic distress has negatively affected various businesses and resulted in company rating transitions. This led to a problem in adjusting investment strategy and a serious loss as there is a lack of time between officially announced credit rating transitions and real transition. This study provides alternative methods for credit rating prediction by applying machine learning models; Support Vector Machine (SVM), Linear Regression, and …
Mathematical Modeling Of The Mechanical Response Of Coupled Inner-Ear Hair Cells With Opposite Polarity, Tanawat Ngampattrapan
Mathematical Modeling Of The Mechanical Response Of Coupled Inner-Ear Hair Cells With Opposite Polarity, Tanawat Ngampattrapan
Chulalongkorn University Theses and Dissertations (Chula ETD)
Hair cells are specialized receptors that detect mechanical forces in the auditory and vestibular systems of vertebrates. In vivo hair-cell bundles are typically anchored to an overlying structure which provides mechanical coupling between neighboring hair cells. Cooperativity between hair bundles has been previously proposed to have strong effects on signal detection. While the coupling of hair cells with the same polarity as those in the auditory organs has been extensively studied, the dynamics of hair cells with opposite polarity in the vestibular system and the inner ear of lizards remain unexplored. In this study, we aim to investigate the dynamics …
Influence Of Cad/Cam Materials On Damping Behavior Of Implant-Supported Crown, Charnikan Sukkasam
Influence Of Cad/Cam Materials On Damping Behavior Of Implant-Supported Crown, Charnikan Sukkasam
Chulalongkorn University Theses and Dissertations (Chula ETD)
This study was to investigate the damping capacity of implant-supported crowns made from various computer-aided design and computer-aided manufacturing (CAD-CAM) restorative materials. A titanium implant fixture was embedded in epoxy resin. Crown specimens were divided into three groups: Zirconia (Z), Lithium disilicate (E), and Polymethyl methacrylate (P). Each crown was subdivided into Uncement (Un) and Adhesive resin cement (RC) subgroups (n=5). Specimens were loaded (0-200N). Strain gauges were attached to measure microstrains at crestal and apical levels. Damping capacity was determined based on load-time curves, microstrain-time curves, and time required to reach the maximum load. A two-way ANOVA with Tukey …