The mean absolute percentage error (MAPE) is one of the most widely used measures of forecast accuracy, due to its advantages of scale-independency and interpretability. However, MAPE has the ...significant disadvantage that it produces infinite or undefined values for zero or close-to-zero actual values. In order to address this issue in MAPE, we propose a new measure of forecast accuracy called the mean arctangent absolute percentage error (MAAPE). MAAPE has been developed through looking at MAPE from a different angle. In essence, MAAPE is a slope as an angle, while MAPE is a slope as a ratio, considering a triangle with adjacent and opposite sides that are equal to an actual value and the difference between the actual and forecast values, respectively. MAAPE inherently preserves the philosophy of MAPE, overcoming the problem of division by zero by using bounded influences for outliers in a fundamental manner through considering the ratio as an angle instead of a slope. The theoretical properties of MAAPE are investigated, and the practical advantages are demonstrated using both simulated and real-life data.
All existing secured loans, including crypto-secured loans, are provided under the condition that the collateral entrusted by the borrower is kept safe during the loan term. In other words, they use ...a one-way collateral function. Thus, a frequent drawback of these loans is that the collateral value increases if and only if the collateral price increases. To resolve this problem, this paper proposes a new crypto-secured lending system incorporating a new two-way collateral function. It would allow a borrower to invest proportions of their own collateral by predicting the market in both directions to make profits irrespective of whether the price of the collateral increases or decreases. This benefits the borrower since profit can be made even if the price of the collateral drops, by betting on the price decrease. This new lending system could include a new hedged portion, unlike traditional secured lending systems. As a result, larger loans can be made under this arrangement; further, this portion provides the advantage of reducing the underlying collateral price volatility risk.
This study proposes three-phase saturation identification using X-ray computerized tomography (CT) images of gas hydrate (GH) experiments considering critical GH saturation (SGH,C) based on the ...machine-learning method of random forest. Eight GH samples were categorized into three low and five high GH saturation (SGH) groups. Mean square error of test results in the low and the high groups showed decreases of 37% and 33%, respectively, compared to that of the total eight. Additionally, a universal test set was configured from the total eight and tested with two trained machines for the low and high GH groups. Results revealed a boundary at ~50% of SGH signifying different saturation identification performance and the ~50% was estimated as SGH,C in this study. The trained machines for the low and high SGH groups had less performance on the larger and smaller values, respectively, of SGH,C. These findings conclude that we can take advantage of suitable separation of obtained training data, such as GH CT images, under the criteria of SGH,C. Moreover, the proposed data-driven method not only serves as a saturation identification method for GH samples in real time, but also provides a guideline to make decisions for data acquirement priorities.
Previous ordinal classification methods implicitly assume that the class distribution within a dataset is balanced, which is often not the case for real-world datasets. If the dataset is imbalanced, ...the previous methods tend to be biased toward the majority class. The authors propose a new method for ordinal classification that attempts to mitigate the impact of imbalanced datasets. They propose a modified version of the weighted k-nearest neighbors method that determines the class membership using the αth quantile of the estimated class probability distribution and thus mitigates the impact of the class imbalance.
History matching is a calibration of reservoir models according to their production history. Although ensemble-based methods (EBMs) have been researched as promising history matching methods, ...reservoir parameters updated using EBMs do not have ideal geological features because of a Gaussian assumption. This study proposes an application of spectral clustering algorithm (SCA) on ensemble smoother with multiple data assimilation (ES-MDA) as a parameterization technique for non-Gaussian model parameters. The proposed method combines discrete cosine transform (DCT), SCA, and ES-MDA. After DCT is used to parameterize reservoir facies to conserve their connectivity and geometry, ES-MDA updates the coefficients of DCT. Then, SCA conducts a post-process of rock facies assignment to let the updated model have discrete values. The proposed ES-MDA with SCA and DCT gives a more trustworthy history matching performance than the preservation of facies ratio (PFR), which was utilized in previous studies. The SCA considers a trend of assimilated facies index fields, although the PFR classifies facies through a cut-off with a pre-determined facies ratio. The SCA properly decreases uncertainty of the dynamic prediction. The error rate of ES-MDA with SCA was reduced by 42% compared to the ES-MDA with PFR, although it required an extra computational cost of about 9 min for each calibration of an ensemble. Consequently, the SCA can be proposed as a reliable post-process method for ES-MDA with DCT instead of PFR.
Selective laser etching is a promising candidate for the mass production of glass interposers. It comprises two steps: local modification by an ultrashort-pulsed laser and chemical etching of the ...modified volume. According to previous studies, when an ultrashort-pulsed laser beam is irradiated on the sample, electron excitation occurs, followed by phonon vibration. In general, the electron excitation occurs for less than a few tens of picoseconds and phonon vibration occurs for more than 100 picoseconds. Thus, in order to compare the electric absorption and thermal absorption of photons in the commercial glass, we attempt to implement an additional laser pulse of 213 ps and 10 ns after the first pulse. The modified glass sample is etched with 8 mol/L KOH solution with 110 °C to verify the effect. Here, we found that the electric absorption of photons is more effective than the thermal absorption of them. We can claim that this result helps to enhance the process speed of TGV generation.
In a previous paper (Kim, 2019), an analytical framework based on the constraint satisfaction problems was proposed to reveal the characteristics of households using event logs from smart door lock ...systems. This work provides a more rigorous justification for the previous approach. This paper proposes a novel parameter estimation method called the maximum feasibility estimation (MFE). The MFE does not rely on any assumption about the parametric family of probability densities from which a random observation is drawn. Instead, we assume that constraints are imposed on observations and that some of the constraints are a function of a parameter of interest. The proposed estimator maximizes the feasible region, a set of all possible observations that satisfy those constraints. The method proposed is validated using synthetic data as well as real streaming event log data.
This study conducts saturation modeling in a gas hydrate (GH) sand sample with X-ray CT images using the following machine learning algorithms: random forest (RF), convolutional neural network (CNN), ...and support vector machine (SVM). The RF yields the best prediction performance for water, gas, and GH saturation in the samples among the three methods. The CNN and SVM also exhibit sufficient performances under the restricted conditions, but require improvements to their reliability and overall prediction performance. Furthermore, the RF yields the lowest mean square error and highest correlation coefficient between the original and predicted datasets. Although the GH CT images aid in approximately understanding how fluids act in a GH sample, difficulties were encountered in accurately understanding the behavior of GH in a GH sample during the experiments owing to limited physical conditions. Therefore, the proposed saturation modeling method can aid in understanding the behavior of GH in a GH sample in real-time with the use of an appropriate machine learning method. Furthermore, highly accurate descriptions of each saturation, obtained from the proposed method, lead to an accurate resource evaluation and well-guided optimal depressurization for a target GH field production.
A miniaturized pump to manipulate liquid flow in microchannels is the key component of microfluidic devices. Many researchers have demonstrated active microfluidic pumps, but most of them still ...required additional large peripherals to operate their micropumps. In addition, those micropumps were made of polymer materials so that their application may be limited to a variety of fields that require harsh conditions at high pressures and temperatures or organic solvents and acid/base. In this work, we present a 3D miniaturized magnetic-driven glass centrifugal pump for microfluidic devices. The pump consists of a volute structure and a 3D impeller integrated with two magnet disks of Φ1 mm. The 3D pump structure was 13 mm × 10.5 mm × 3 mm, and it was monolithically fabricated in a fused silica sheet by selective laser-induced etching (SLE) technology using a femtosecond laser. The pump operation requires only one motor rotating two magnets. It was Φ42 mm × 54 mm and powered by a battery. To align the shaft of the motor to the center of the 3D glass pump chip, a housing containing the motor and the chip was fabricated, and the overall size of the proposed micropump device was 95 mm × 70 mm × 75 mm. Compared with other miniaturized pumps, ours was more compact and portable. The output pressure of the fabricated micropump was between 215 Pa and 3104 Pa, and the volumetric flow rate range was 0.55 mL/min and 7.88 mL/min. The relationship between the motor RPM and the impeller RPM was analyzed, and the flow rate was able to be controlled by the RPM. With its portability, the proposed pump can be applied to produce an integrated and portable microfluidic device for point-of-care analysis.
It is necessary to monitor, acquire, preprocess, and classify microseismic data to understand active faults or other causes of earthquakes, thereby facilitating the preparation of early-warning ...earthquake systems. Accordingly, this study proposes the application of machine learning for signal–noise classification of microseismic data from Pohang, South Korea. For the first time, unique microseismic data were obtained from the monitoring system of the borehole station PHBS8 located in Yongcheon-ri, Pohang region, while hydraulic stimulation was being conducted. The collected data were properly preprocessed and utilized as training and test data for supervised and unsupervised learning methods: random forest, convolutional neural network, and K-medoids clustering with fast Fourier transform. The supervised learning methods showed 100% and 97.4% of accuracy for the training and test data, respectively. The unsupervised method showed 97.0% accuracy. Consequently, the results from machine learning validated that automation based on the proposed supervised and unsupervised learning applications can classify the acquired microseismic data in real time.