Conception et évaluation d'une plateforme de gestion des déchets ménagers intelligents

Thesis Abstract

The escalating challenges of urban waste management, characterized by inefficient collection processes, excessive environmental pollution, and escalating operational costs, necessitate innovative technological solutions to optimize household waste handling and promote sustainable urban environments. This study aims to design and evaluate an intelligent waste management platform tailored to household needs, integrating Internet of Things (IoT) devices, data analytics, and user-centric interfaces to enhance waste segregation, collection efficiency, and community engagement. The specific objectives include developing a functional prototype of the platform, assessing its usability and performance, and evaluating its impact on waste management practices within urban neighborhoods. The research adopts a mixed-methods approach, combining qualitative and quantitative data collection and analysis techniques. The population comprises approximately 1,200 households across four distinct urban districts with diverse socio-economic backgrounds; a stratified random sampling technique was employed to select a sample of 300 households ensuring representative diversity. Data collection instruments include structured questionnaires to assess user acceptance, semi-structured interviews with waste management officials, and system logs capturing platform utilization data. Validation and reliability of survey instruments were confirmed through Cronbach’s alpha exceeding 0.85 and pilot testing. Analytical procedures consist of descriptive statistics, inferential analyses such as multiple regression to identify determinants of user engagement, and thematic analysis for qualitative interview data. The study also employs system performance evaluations based on response time, data accuracy, and operational stability metrics, complemented by comparison against baseline waste management practices. It is anticipated that the findings will demonstrate significant improvements in waste segregation rates, operational efficiencies, and user participation attributable to the platform. Advanced techniques like regression analysis are expected to elucidate key factors influencing behavioral adoption, while thematic analysis will identify contextual barriers and facilitators. The proposed platform's design, grounded in the Technology Acceptance Model (TAM) and the Theory of Planned Behavior (TPB), offers insights into behavioral predictors of platform acceptance and sustained use. The anticipated contribution of this research lies in providing empirical evidence on the efficacy of integrated IoT-enabled waste management systems and establishing a scalable framework adaptable to various urban contexts. Furthermore, it will offer practical recommendations for policymakers, urban planners, and waste management authorities to incorporate intelligent digital solutions into existing waste infrastructure. The study concludes that deploying an intelligent waste management platform can significantly enhance household participation, reduce operational costs, and mitigate environmental impacts. Recommendations include developing tailored awareness campaigns, fostering public-private partnerships for technology deployment, and iterating platform features based on user feedback. Future research avenues suggested include longitudinal studies to assess long-term behavioral change and integration with smart city initiatives to optimize urban resource management comprehensively. Overall, this research advances the understanding of digital transformation in municipal waste management and provides a comprehensive blueprint for deploying intelligent systems to foster sustainable urban ecosystems.