Research on Music Classification Technology Based on Deep Learning

With the advent of the digital music era, digital audio sources have exploded. Music classification (MC) is the basis of managing massive music resources. In this paper, we propose a MC method based on deep learning to improve feature extraction and classifier design based on MIDI (musical instrument digital interface) MC task. Considering that the existing classification technology is limited by the shallow structure, it is difficult for the classifier to learn the time sequence and semantic information of music; this paper proposes a MIDIMC method based on deep learning. In the experiment, we use the MC method proposed in this paper to achieve 90.1% classification accuracy, which is better than the existing classification method based on BP neural network, and verify the music with its classification accuracy. The key point is that the music division method used in this paper has correct MC efficiency. However, due to the limited ability and time involved in the interdisciplinary field, the methodology of this paper has certain limitations, which still needs further research and improvement.

Procedure for the Accurate Modelling of Ring Induction Motors

This paper proposes a procedure for the accurate modelling of the ring induction motors (RIMs), based on the Monte Carlo (MC) method and the relations presented in the relevant metrology guidelines. Modelling was carried out based on the measured data for the torque-slip characteristic (TSC) and using the equivalent circuit for the RIM. The parameters included an extended Kloss equation (EKE) and the associated uncertainties were determined using the MC method. The polynomial procedure was applied as a numerical tool to complement the MC method to determine the power losses in the stator iron and the relevant uncertainty. This is in line with international standards for the theory of uncertainty application in the field of engineering. The novelty of this paper refers to the accurate modelling of the RIMs obtained by determining the corresponding uncertainties. The procedure presented in this paper was developed based on the assumption that the parameters of the equivalent circuit are independent of the temperature, influence of core saturation, and the phenomenon of current displacement. Our procedure can be successfully used for both the theoretical calculations related to the modelling of the RIMs, and in practical applications involving detailed measurements and the corresponding uncertainties. The use of the MC method allowed for significant improvement in the modelling results, in terms of both the TSC and EKE.

Critical Buckling Generation of TCA Benchmark by the B1 Theory-Augmented Monte Carlo Calculation and Estimation of Uncertainties

The Korea Atomic Energy Research Institute (KAERI) has developed the DeCART2D 2-dimensional (2D) method of characteristics (MOC) transport code and the MASTER nodal diffusion code and has established its own two-step procedure. For design code licensing, KAERI prepared a critical experiment on the verification and validation (V&V) of the DeCART2D code. DeCART2D is able to perform the MOC calculation only for 2D nuclear fuel systems, such as the fuel assembly. Therefore, critical buckling in the vertical direction is essential for comparison between the results of experiments and DeCART2D. In this study, the B1 theory-augmented Monte Carlo (MC) method was adopted for the generation of critical buckling. To examine critical buckling using the B1 theory-augmented MC method, TCA critical experiment benchmark problems were considered. Based on the TCA benchmark results, it was confirmed that the DeCART2D code with the newly-generated critical buckling predicts the criticality very well. In addition, the critical buckling generated by the B1 theory-augmented MC method was bound to uncertainties. Therefore, utilizing basic equations (e.g., SNU S/U formulation) linking input uncertainties to output uncertainties, a new formulation to estimate the uncertainties of the newly generated critical buckling was derived. This was then used to compute the uncertainties of the critical buckling for a TCA critical experiment, under the assumption that nuclear cross-section data have uncertainties.

Accurate Simulation of Light Propagation in Complex Skin Tissues Using an Improved Tetrahedron-Based Monte Carlo Method

Understanding light transportation in skin tissues can help improve clinical efficacy in the laser treatment of dermatosis, such as port-wine stains (PWS). Patient-specific cross-bridge PWS vessels are structurally complicated and considerably influence laser energy deposition due to shading effects. The shading effect of PWS vessels is investigated using a tetrahedron-based Monte Carlo (MC) method with extended boundary condition (TMCE). In TMCE, body-fitted tetrahedra are generated in different tissues, and the precision of photon–surface interaction can be considerably improved via mesh refinement. Such improvement is difficult to achieve with the widely used voxel-based MC method. To fit the real physical boundary, the extended boundary condition is adapted by extending photon propagation to the semi-infinite tissue layers while restricting the statistics of photon propagation in the computational domain. Results indicate that the shading parameters, such as the cross angle, vessel distance, and geometric shadow (GS), of cross-bridge blood vessel pairs determine the peak characteristics of photon deposition in deep vessels by affecting the relative deposition of collimated and diffused light. Collimated light is shaded, attenuated, and partially transformed into diffused light due to the increase in vessel distance and GS of vessel pairs, resulting in difficulty in treating deep and shallow vessels with one laser pulse. The TMCE method can be used for the individualized and precise forecasting of laser energy deposition based on the morphology and embedding characteristics of vascular lesions.

Comparison of Type Well Generation Methods for Unconventional Reservoirs

Summary Due to ultralow permeability, there is practically no pressure interference between wells producing from tight oil (≈0.1 md average permeability) and shale oil reservoirs (∼0.001 md average permeability). This renders type well methodology as a commonly used tool for forecasting production performance of these “unconventionals.” Several authors proposed different methods for constructing type wells for unconventional reservoirs, but none compared them. In this study, we compare three of the most common types of well generation methods. In the absence of real field data, individual production histories for wells are established by picking Arps decline curve parameters qi, b, and Di, which govern a well’s production performance, from respective distributions of these parameters. Next, we compare type wells constructed using the Monte Carlo (MC) method, final cumulative (FC) method, and time slice (TS) method. Moreover, we study the impact of a possible linear correlation (also linear C) between b and Di (comparable to field observations) on MC, FC, and TS type wells. We also study the effect of well count, and Dmin value, which is the 4th parameter introduced with modified Arps equation for unconventionals. In this paper, we show that type wells generated with TS and FC methods have almost the same behavior, whereas the MC method is affected the most by stochastic experimentation, well count, and Dmin.

Difusi Bebas 1D dan 2D dengan Monte Carlo: Perbandingan Distribusi Bilangan Random Normal dan Seragam dengan Box-Müller

Many biological processes in the human body are based on the diffusion system. Diffusion is defined as a process of random movement of the particle whose the direction is from high concentrations to low concentrations. Many of various study of diffusion have been done both experimentally and computationally. Because the particle interaction is stochastic, the Monte Carlo (MC) method is used in performing particle simulations. The main of MC method is the use of random numbers. Many software have provided uniform random number generators. But based on the analytic results, the solution is normal distribution. Therefore, Box-Müller can be used as a transformation of particle distribution. The software used, MATLAB, has a normal random generator. Therefore, the aims of this study is comparing particle distribution of these two different random number generator with MATLAB and showing the impact of timestep parameter to these random number generator. This result can be used as based for the modelling of more complex biological systems.

Uncertainty analysis of discharge coefficient of circular crested weirs

The circular crested weir (CCW) has been introduced as weirs having a high discharge coefficient (Cd). The ratio of flow head to the radius of the crest (H/R) is the most important parameter affecting the Cd, that the $${\text{Cd}} \approx a\left( {H/R} \right)^{b}$$ Cd ≈ a H / R b can mathematical model their relation. In this study, the parameters of the Cd formula (i.e., a and b) were uncertainty analyzed using Monte Carlo (MC) and Bootstrap methods (BM). To perform these methods, some of the built-in functions of Excel software were utilized. The results declared that the average values of a and b were 1.187 and 0.140. The outcome of the MC method showed that the range of a and b at 95% confidence interval changed between 1.179 to 1.194 and 0.134 to 0.146, respectively, while at the same confidence interval the BM ranged from 1.187 to 1.200 and 0.133 to 0.147.

Endoscopic endonasal cyst fenestration into the sphenoid sinus using the mucosa coupling method for symptomatic Rathke’s cleft cyst: a novel method for maintaining cyst drainage to prevent recurrence

OBJECTIVERathke’s cleft cyst (RCC) is a benign cystic lesion with a relatively high incidence of local recurrence that occasionally requires repeat surgery. To prevent recurrence, simple cyst fenestration and drainage of the cyst contents to the sphenoid sinus is recommended, but it occasionally recurs. The authors postulated that obstruction of fenestration is a main cause of recurrence, and they developed a method, named the “mucosa coupling method (MC method),” that maintains persistent drainage. In this method, the RCC epithelium and the mucosa of the sphenoid sinus are connected, which promotes re-epithelialization between the two epithelia, maintaining persistent drainage. The outcome of this method was compared with that of conventional cyst fenestration.METHODSIn a consecutive series of 40 patients with RCC, the surgical strategy was changed during the study period: from December 2009 to September 2014 (the conventional period), 24 patients were scheduled to be treated using the conventional fenestration method, whereas from September 2014 to September 2017 (the MC period), 16 patients were scheduled to be treated using the MC method. However, because of an intraoperative CSF leak, the fenestration was closed during surgery in 3 patients in the conventional period and 2 in the MC period; therefore, these 5 patients were excluded from the analysis. Twenty-one patients treated with the conventional fenestration method (conventional group) and 14 patients treated with the MC method (MC group) were analyzed. All patients regularly underwent MRI after surgery to detect reaccumulation of cyst contents. The rate of reaccumulation with and without reoperation, visual outcomes, endocrinological outcomes, and postoperative complications were compared between these two groups.RESULTSThe median follow-up period in all 35 patients was 48.0 months (range 1–96 months), 54.0 months (range 1–96 months) in the conventional group and 35.5 months (range 12–51 months) in the MC group. No reaccumulation was detected on MRI in the 14 patients in the MC group, whereas it was noted in 9 (42.9%) of 21 patients in the conventional group, and 2 of these 9 patients required repeat surgery. There were no significant differences in visual and endocrinological outcomes and complications between these two groups.CONCLUSIONSThe MC method for RCC is effective for preventing obstruction of cyst fenestration, which contributes to preventing cyst reaccumulation. Furthermore, this method is equivalent to the conventional fenestration method in terms of visual and endocrinological outcomes and the complication rate.

QMC integration errors and quasi-asymptotics

A crude Monte Carlo (MC) method allows to calculate integrals over a d-dimensional cube. As the number N of integration nodes becomes large, the rate of probable error of the MC method decreases as {O(1/\sqrt{N})}. The use of quasi-random points instead of random points in the MC algorithm converts it to the quasi-Monte Carlo (QMC) method. The asymptotic error estimate of QMC integration of d-dimensional functions contains a multiplier {1/N}. However, the multiplier {(\ln N)^{d}} is also a part of the error estimate, which makes it virtually useless. We have proved that, in the general case, the QMC error estimate is not limited to the factor {1/N}. However, our numerical experiments show that using quasi-random points of Sobol sequences with {N=2^{m}} with natural m makes the integration error approximately proportional to {1/N}. In our numerical experiments, {d\leq 15}, and we used {N\leq 2^{40}} points generated by the SOBOLSEQ16384 code published in 2011. In this code, {d\leq 2^{14}} and {N\leq 2^{63}}.