Saved in:
Bibliographic Details
Main Author: Isselkou, Ahmed
Format: Recurso digital
Language:English
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.17292447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902334496309248
author Isselkou, Ahmed
author_facet Isselkou, Ahmed
contents <div> <div>This thesis presents the design, implementation, and evaluation of GRASS, a near real-time MLOps pipeline for crowd sentiment detection from audio. The system addresses the challenge of inferring collective audience sentiment from ambient audio signals, a task relevant to atmosphere monitoring and crowd management in football stadiums.</div> <br> <div>Developed within a Design Science Research (DSR) framework, the pipeline integrates a C++/FFTW backend for sliding-window segmentation, spectrogram generation, and a ResNet-18 classifier, orchestrated through an MLOps stack of Dagster, MLflow, MinIO, InfluxDB, and Grafana, with human-in-the-loop retraining supported via Label Studio and FastAPI. On the Emotional Crowd Sound Dataset (ECSD), GRASS achieved an F1-score of 96%. In addition, a real-time streaming experiment using a laptop microphone demonstrated average per-segment inference latency of 143.6 ms and an end-to-end response time of 336.9 ms per 2 s audio clip, confirming that the pipeline processes input well within near real-time requirements.</div> <br> <div>The scope of validation remains limited. ECSD is proxy data that does not capture the acoustic and cultural complexity of football crowds, and the streaming experiment was restricted to a single-microphone local setup, not a full stadium deployment. As a result, the accuracy of sentiment detection in authentic football stadium environments remains unresolved.</div> <br> <div>The contribution of this thesis is therefore architectural and methodological: the realization of a reproducible, extensible pipeline and its validation as a proof-of-concept on available data. Future work must focus on testing with authentic stadium recordings, scaling to multi-microphone deployments, and embedding ethical safeguards to ensure responsible deployment.</div> </div>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17292447
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Design and Implementation of an MLOps Pipeline for Audio-Based Crowd Sentiment Analysis in Stadiums
Isselkou, Ahmed
<div> <div>This thesis presents the design, implementation, and evaluation of GRASS, a near real-time MLOps pipeline for crowd sentiment detection from audio. The system addresses the challenge of inferring collective audience sentiment from ambient audio signals, a task relevant to atmosphere monitoring and crowd management in football stadiums.</div> <br> <div>Developed within a Design Science Research (DSR) framework, the pipeline integrates a C++/FFTW backend for sliding-window segmentation, spectrogram generation, and a ResNet-18 classifier, orchestrated through an MLOps stack of Dagster, MLflow, MinIO, InfluxDB, and Grafana, with human-in-the-loop retraining supported via Label Studio and FastAPI. On the Emotional Crowd Sound Dataset (ECSD), GRASS achieved an F1-score of 96%. In addition, a real-time streaming experiment using a laptop microphone demonstrated average per-segment inference latency of 143.6 ms and an end-to-end response time of 336.9 ms per 2 s audio clip, confirming that the pipeline processes input well within near real-time requirements.</div> <br> <div>The scope of validation remains limited. ECSD is proxy data that does not capture the acoustic and cultural complexity of football crowds, and the streaming experiment was restricted to a single-microphone local setup, not a full stadium deployment. As a result, the accuracy of sentiment detection in authentic football stadium environments remains unresolved.</div> <br> <div>The contribution of this thesis is therefore architectural and methodological: the realization of a reproducible, extensible pipeline and its validation as a proof-of-concept on available data. Future work must focus on testing with authentic stadium recordings, scaling to multi-microphone deployments, and embedding ethical safeguards to ensure responsible deployment.</div> </div>
title Design and Implementation of an MLOps Pipeline for Audio-Based Crowd Sentiment Analysis in Stadiums
url https://doi.org/10.5281/zenodo.17292447