- Research Article
1
- 10.1016/j.rineng.2026.109496
A GRU-based deep learning framework for IoT-based measurement and prediction of ambient noise levels in Taiwan
- Mar 01, 2026
- Results in Engineering
- Sakshi Saraswat + 4 more +4
Publications from 2021 to 2026
Showing 10 of 32 papers
A GRU-based deep learning framework for IoT-based measurement and prediction of ambient noise levels in Taiwan
From the Cloud to the Edge: The Technical Characteristics and Application Scenarios of Fog Computing
International Telecommunication Union clearly defines IoT (Internet of Things) as “a phenomenon where every standalone object is connected”, this shows that as connectivity and communications technology gradually mature, various linking devices and equipment will be able to connect and create a more rich and diverse service scenario. However, as this trend is being established, these connected devices will produce large amount of data, which in turn will cause two problems that need to be solved: first, the increasing number of connected devices will lead to data congestion. The current solution is to process data in batches to divert data flow, but this will still result in latency and inability to respond to the issue immediately; second, with the advent of more wireless and cable-connected devices, service operators will have to invest more into the installation of cloud infrastructure. Aside from the initial installation, follow-up maintenance will also require huge costs, bumping up service prices. In response to the problems with the IoT, the structure of edge computing called “fog computing” was created. It can be defined as “an emerging method of computing with the main goal of shifting computing and connecting units from the cloud to the edge or nearedge position to help devices preemptively and autonomously process information and data created by connected devices, creating a computing structure that can operate without relying on the center.
Read moreEast vs. West, The Decibel Duel. A Comparative Systematic Review of Noise Pollution Research
BACKGROUND AND AIM: Environmental noise is a growing concern in urban areas across the globe, impacting the health of millions of people. This systematic literature review aims to compare researches conducted on environmental noise exposure in the East and West. METHOD: The review followed PRISMA guidelines for selection of all research articles published in the year 2022. Separate searches were conducted for the East and West using keywords for each region. The search was conducted using Google Scholar, Web of Science, and PubMed databases. The articles obtained from PubMed search were further evaluated for quality. RESULTS: The systematic search resulted in 1200 and 1960 studies on Google Scholar, 18,908 and 14,114 studies on Web of Science, and 126 and 174 studies on PubMed for East and West respectively with majority of studies from China, Japan, and South Korea in the East, and the United States and various European countries in the West. Studies conducted in the West generally had higher quality with larger sample sizes, intricate methodologies, and meticulous findings as compared to the East. Moreover, studies in the East primarily focused on community noise, while those in the West focused on individual-specific noise. CONCLUSIONS: These differences in the number and quality of studies between the East and West can be attributed to differences in research funding, institutional support, and cultural attitudes towards noise. The high number of studies from China may be due to the country's rapidly growing urbanization, resulting in increased noise pollution. However, the lower quality of studies from the East is concerning due to the region's large population and the significant public health concern of environmental noise exposure. There is an urgent need for more high-quality research on noise exposure in Asia to understand its effects and help policymakers take action to mitigate its negative impact and improve public health outcomes.
Read moreSession 2A : Wireless, Mobile Communication 2
Application of normalized difference vegetation index in classifying land cover change over Bangli regency by using Landsat 8 imagery
The information on land cover changes is very important in regional spatial planning. Remote sensing technology can minimize the cost and time in analyzing land cover changes. Normalized Difference Vegetation Index (NDVI) is a vegetation index that combines red and near-infrared channels so that it can provide approximate information about land cover in an area. The objective of this study is to extract land cover change information from Landsat 8 images based on NDVI values in Bangli Regency in 2015 and 2021. The classification method used to estimate the type of land cover is supervised classification. The results reveal the decrease of the land cover in the category of water body, sand, dry land/soil, rice fields, and vegetation, which are 1.62%, 14.14%, 7.93%, 8.63%, and 2.45%, respectively, while an increase in the settlement category by 30.12%. The overall accuracy of land cover classification result based on NDVI value is 86.54%.
Read moreTraveling wave solutions to the Allen–Cahn equation
For the Allen–Cahn equation, it is well known that there is a monotone standing wave joining the balanced wells of the potential. In this paper we study the existence of traveling wave solutions for the Allen–Cahn equation on an infinite channel. Such traveling wave solutions possess a large number of oscillations and they are obtained with the aid of variational arguments.
Read moreTable of Contents
Seismicity along the Santorini-Amorgos zone and its relationship with active tectonics and fluid distribution
Mapping Intrinsic and Scattering Attenuation in the Southern Aegean Crust Using <i>S</i> Wave Envelope Inversion and Sensitivity Kernels Derived From Perturbation Theory
Abstract We applied sensitivity kernels based on perturbation theory to map the crustal intrinsic and scattering attenuation of S wave envelopes in the southern Aegean. The southern Aegean crust is under extension due to the rollback of the Nubian plate, which is subducting beneath the Aegean plate. The waveforms of 104,531 crustal events (<40 km) were used to calculate S wave envelopes in four frequency bands. The S wave envelopes were modeled using the 3‐D isotropic solution of the radiative transfer equation with a factor for energy leakage. A two‐stage grid search with linear least squares was applied to estimate the attenuation parameters from each S wave envelope. Then we calculated the 2‐D scattering and absorption sensitivity kernels for each wave path based on perturbation theory. These kernels and the envelope attenuation parameters were inverted using the Markov chain Monte Carlo algorithm to obtain maps of intrinsic and scattering attenuation (Qi−1 and Qsc−1). High Qi−1 has thermal origin associated with fluids while high Qsc−1 stems from velocity contrasts caused by deformed structure such as faults, folds, or fractures. The Corinth rift, the Santorini‐Amorgos zone, and the Gulf of Gökova show strong extensional deformation, which may produce high Qsc−1. The deformed oceanic material accreted below the continental crust and fractures generated by large thrust earthquakes likely produce high Qsc−1 in Crete. The Corinth rift with its repeated earthquake swarms demonstrates fluid activity, which can explain high Qi−1. Thermal contrasts generated by metamorphic core complexes are a potential source of Qi−1 in Cyclades and Crete.
Read moreMULTI-CRITERIA ANALYSIS ON THE STRATEGIES TO THE TELECOMMUNICATIONS DEVELOPMENT – A CASE STUDY IN TAIWAN
Telecommunications development is rapid in the world. Telecommunications service markets in Taiwan have been diversified with competitiveness. Even though the 4G, ADSL and Wi-Fi are operated, cable access still could not satisfy the public's increasing broadband access. For enhancing the competitions of services, in 2007, Taiwan’s supervisory authority has decided to open wireless broadband access business that is the Worldwide Interoperability for Microwave Access (WiMAX). However, the development of WiMAX in Taiwan had been delayed. The research would find and analyze those impact factors. The study took the methods of Multiple Criteria Decision Making (MCDM) -- a hybrid MADM model combining the Decision Making Trial and Evaluation Laboratory (DEMATEL). The DEMATEL is based on the Analytic Network Process (DANP) with VIKOR. This systematic assessment would obtain the factors’ rank, and then analyze those impact factors. The government supervision should be the first one of the most important factors. And then, the factors would be considering for business management and profit. Through the VIKOR, the largest gap from aspired level would be business management. However, the item would be pushed by government supervision level. So, the government supervision level should be the first one to improve.
Read more