Taiwan Association of Engineering and Technology Innovation: E-Journals
Not a member yet
887 research outputs found
Sort by
Evaluation of Local Interpretable Model-Agnostic Explanation and Shapley Additive Explanation for Chronic Heart Disease Detection
Get PDFThis study aims to investigate the effectiveness of local interpretable model-agnostic explanation (LIME) and Shapley additive explanation (SHAP) approaches for chronic heart disease detection. The efficiency of LIME and SHAP are evaluated by analyzing the diagnostic results of the XGBoost model and the stability and quality of counterfactual explanations. Firstly, 1025 heart disease samples are collected from the University of California Irvine. Then, the performance of LIME and SHAP is compared by using the XGBoost model with various measures, such as consistency and proximity. Finally, Python 3.7 programming language with Jupyter Notebook integrated development environment is used for simulation. The simulation result shows that the XGBoost model achieves 99.79% accuracy, indicating that the counterfactual explanation of the XGBoost model describes the smallest changes in the feature values for changing the diagnosis outcome to the predefined output
Compact Circularly Polarized Monopole Antenna Using Characteristic Mode Analysis
Get PDFThis study aims to design a circularly polarized compact antenna using characteristic mode analysis (CMA). The proposed antenna consists of a substrate with a slotted annular ring-shaped patch and partial ground. The excitation position of the antenna and its optimal dimensions are determined through the analysis of different operation modes with CMA. After that, an optimized antenna is designed, and an antenna prototype is fabricated for validation. The experimental results show that the reflection coefficient achieves a -10dB impedance bandwidth of 6.85 GHz, a 3dB-axial ratio bandwidth of 0.7 GHz, and a peak gain of 3.2 dBi. These characteristics agree with simulations and make the circularly polarized compact antenna suit for C-band and sub-6 GHz 5G wireless applications
Effect of PIN Diode Integration on Patch Antennas for Frequency Reconfigurable Antenna Applications
Get PDFPIN diodes are commonly used to design reconfigurable antennas owing to their sufficient isolation, lower cost, and ease of fabrication. This study aims to explore the effect of biasing conditions of a PIN diode radio frequency (RF) switch on a frequency-reconfigurable antenna. This approach investigates the contribution of the forward diode current and the reversed biased voltage on the shift in the operating band, the impedance matching, and the radiation efficiency of a reconfigurable antenna. The benefits and drawbacks of different approaches to modeling PIN diode RF switches are demonstrated on Ansys electromagnetic switch. The result shows a significant match between simulated and measured operating bands, impedance matching, and radiation efficiency. The proposed RF switch model can be used as a practical simulation model for implementing various reconfigurable microwave components
A Simulation Study on von Karman Vortex Shedding with Navier-Stokes and Shallow-Water Models
Get PDFThis study aims to investigate the advantages of employing numerical models based on Shallow-water equations for simulating von Karman vortex shedding. Furthermore, a comparative analysis with Navier-Stokes equations will be conducted to assess their effectiveness. In addition to Reynolds number (Re), Froude number (Fr), relevant to water depth, plays an important role in the Shallow-Water modeling of the von Karman vortex. In this study, simulations of 2D von Karman vortex shedding are performed using the Navier-Stokes model and Shallow-Water model, employing the least-squares finite-element method for space discretization and θ-method for time integration. The computed vortices characteristics, including the recirculation zone behind the cylinder, vortices size, and frequency, are presented. In the Navier-Stokes modeling, the computed results indicate that the size of vortices in space decreases and the Strouhal number increases as Re increases. In the Shallow-Water modeling for the same Re condition, the size of vortices increases and the Strouhal number decreases as Fr increases
A Novel Paradigm for Sentiment Analysis on COVID-19 Tweets with Transfer Learning Based Fine-Tuned BERT
Get PDFThe rapid escalation in global COVID-19 cases has engendered profound emotions of fear, agitation, and despondency within society. It is evident from COVID-19-related tweets that spark panic and elevate stress among individuals. Analyzing the sentiment expressed in online comments aids various stakeholders in monitoring the situation. This research aims to improve the performance of pre-trained bidirectional encoder representations from transformers (BERT) by employing transfer learning (TL) and fine hyper-parameter tuning (FT). The model is applied to three distinct COVID-19-related datasets, and each of the datasets belongs to a different class. The evaluation of the model’s performance involves six different machine learning (ML) classification models. This model is trained and evaluated using metrics such as accuracy, precision, recall, and F1-score. Heat maps are generated for each model to visualize the results. The performance of the model demonstrates accuracies of 83%, 97%, and 98% for Class-5, Class-3, and binary classifications, respectively
An Optimal Energy Control System for Campus Microgrid Using Crow Search Algorithm Considering Economic Dispatch
Get PDFThis article presents an optimal energy control system that considers economic dispatch (ED) for a campus microgrid to reduce its operating cost. A newly developed crow search algorithm (CSA) is used to enforce the ED in this work. To achieve this purpose, an optimal size of distributed energy resources (DERs) in the campus microgrid is assumed. CSA is used to optimize the energy control system and find the minimum operating cost of the campus microgrid. To indicate the effectiveness of CSA, several scenarios under various load demand conditions in grid-connected and stand-alone microgrid modes are investigated in this work. According to the findings, the suggested model is capable of sufficient power supply in all scenarios and reduces the operating costs more effectively than the reference delineated in the same case. The outcomes confirm that the suggested model’s performance is optimal for the energy control system of a campus microgrid
Online MEMS-Based Specific Gravity Measurement for Lead-Acid Batteries
Get PDFTraditional methods for measuring the specific gravity (SG) of lead-acid batteries are offline, time-consuming, unsafe, and complicated. This study proposes an online method for the SG measurement to estimate the state-of-charge (SoC) of lead-acid batteries. This proposed method is based on an air purge system integrating with a micro electro mechanical system sensor. Through the proposed strategy, the SoC measurement achieves up to ±1% accuracy. The technique has an SG accuracy of ±0.002% which is better than the glass hydrometer accuracy of ±0.005% in the battery charge reading. The experimental results show that the high accuracy and precise measurements of SG and SoC can be conducted by using the proposed method
Analysis of Outer Race Bearing Damage by Calculation of Sound Signal Frequency Based on the FFT Method
Get PDFThis study aims to identify the outer race bearing needed to protect an induction motor from severe damage. Faults are diagnosed using a non-invasive technique through the sound signal from an induction motor. The diagnosis aims to assess the damage to the bearings on the fan or main shaft. Moreover, this study discusses the type of damage, loading variations, and the diagnostic accuracy with the damage to the outer race bearing placed on the fan or main shaft rotor. The disturbance detection approach is used to analyze the sound spectrum to identify the harmonic components near the disturbance frequency. The damage frequency characteristics are also calculated to determine the sound spectrum peak value. The results show that the detection is slightly affected by the damage severity and the incorrect placement of the bearings on the rotor shaft. The lowest detection accuracy in testing the outer race bearing damage on the fan shaft is 91.66%. However, the accuracy percentage is 100% with the outer race bearing damage on the main shaft
Evaluation of Activation Energy for Agricultural Residues with Ignition Temperature
Get PDFThe objective of this study is to evaluate the activation energy of agricultural residues with their ignition characteristics. The ignition temperature of agricultural residues (peanut shell, rice hull, and rice straw) is determined by measuring particle temperature, particle luminosity, and gas temperature for samples weighing 2.0, 2.5, and 3.0 grams. The maximal slope of the particle temperature versus furnace temperature is used to determine the occurrence of ignition. Values of activation energy are analyzed by the Semenov model with the measured ignition temperature. Results show that the particle ignition temperature is 317, 324, and 330°C for rice straw, peanut shell, and rice hull, respectively. The results also indicate that the particle ignition temperature reduces as the volatile content increases and the sample amount decreases. The value of activation energy is 157.2, 170.3, and 192.8 kJ/mole for rice straw, peanut shell, and rice hull, respectively
Optimization of Centrifugal Pump Based on Impeller-Volute Interactions
Get PDFThe design and off-design performance of a centrifugal pump largely depends on geomechanical parameters. This study aims at enhancing the performance by optimizing three geomechanical parameters of impeller-volute interactions. The present optimization is carried out using the Taguchi method combined with a numerical approach. A comparison between the base and optimized pumps is presented under the design and off-design conditions based on numerical and experimental analyses. The numerical results reveal that, compared to the base pump, the optimized pump shows the improved performance through uniform pressure distribution in the impeller, the reduced low-pressure region towards a blade’s leading edge, and the stable total pressure at the impeller-volute interaction zone. The experimental results suggest that the optimized pump covers a wider range of operation, and its best efficiency point (BEP) is 10%, 5%, and 12% higher in flow rate, head, and efficiency, as compared to the base one