Using Machine Learning to Predict Indoor Acoustic Indicators of Multi-Functional Activity Centers

Abstract

In Taiwan, activity centers such as school auditoriums and gymnasiums are common multi-functional spaces that are often used for performances, singing, and speeches. However, most cases are designed using only Sabine’s equation for architectural acoustics. Although that estimation formula is simple and fast, the calculation process ignores many details. Furthermore, while more accurate analysis can be obtained through acoustics simulation software, it is more complicated and time-consuming and thus is rarely used in practical design. The purpose of this study is to use machine learning to propose a predictive model of acoustic indicators as a simple evaluation tool for the architectural design and interior decoration of multi-functional activity centers. We generated 800 spaces using parametric design, adopting Odeon to obtain acoustic indicators. The machine learning model was trained with basic information of the space. We found that through GBDT and ANN algorithms, almost all acoustic indicators could be predicted within JND ± 2, and the JND of C50, C80, STI, and the distribution of SPL could reach within ±1. Through machine learning methods, we established a convenient, fast, and accurate prediction model and were able to obtain various acoustic indicators of the space without 3D-modeling or simulation software.

Inferring Drumhead Damping and Tuning from Sound Using Finite Difference Time Domain (FDTD) Models

“…Adjusting pitch, i.e., the fundamental frequency, is achieved by a respective adjustment of the ratio of tension to mass distribution, according to Equation (2). Leather drumheads are commonly heated to increase membrane tension and as a result their fundamental frequency.…”

“…In Equation (2), fmn is the modal frequency of the vibrational mode that consists of n radial nodes and m nodal diameters. Figure 2 presents the shape and the ratio of the frequency of each mode to the fundamental frequency, for the first twelve modes of an ide- To adjust the sound of their instruments, percussionists may alter the tension or the mass of the membrane.…”

“…This revival can be attributed to the proliferation of high-performance computing facilities and the remarkable performance of deep learning methodologies. Illustrative instances of this trend are provided across various domains of industrial product development, encompassing areas such as urban planning [1], architectural acoustics [2], mechanical acoustics [3], underwater acoustics [4], and, more pertinent to this study, musical acoustics. In the process of designing and manufacturing musical instruments, a prominent concern relates to identifying geometries and materials capable of producing a desired sound texture.…”

A Review on Indoor Environment Quality of Indian School Classrooms

“…The most-used computational techniques in various studies are Fuzzy rule based, the Multi-Objective Genetic Algorithm (MOGA), Multi-Objective Non-Dominated Sorting Genetic Algorithm (NSGA-II), Genetic Algorithm (GA), Linear Regression (LR), and Support Vector Machine (SVM). [333][334][335]. Most researchers used various acoustic comfort parameters as inputs to predict and optimize the AcC in different indoor scenarios.…”