European Journal of Engineering Science and Technology

Modified Deep Learning Model for Efficient Recyclable Waste Classification: A Comparative Study of Convolutional Network Architectures

Tamuno-Omie J Alalibo, Nkolika O Nwazor, Lawrence Oborkhale — Tue, 30 Dec 2025 00:00:00 +0000

Solid waste recycling management in Nigeria remains a challenge, necessitating efficient waste classification for environmental sustainability. This study proposes CiteWasteRN50, a modified ResNet50 Convolutional Neural Network (CNN), to classify waste into six groups. Key modifications include input image rescaling for enhanced feature extraction, three fully connected layers with dropout, and a SoftMax layer for probabilistic output. The model was trained and validated in MATLAB environment using the TrashNet dataset—75% for training over 7, 15, 30, and 45 epochs, and 25% for validation. CiteWasteRN50 was compared to eight other CNN models under identical conditions. At 15 epochs, CiteWasteRN50 achieved the highest classification accuracy of 98.09%, outperforming ResNet50, ResNet-18, DenseNet201, ResNet-101, EfficientNetB0, VggNet16, VggNet19, and InceptionV3 by 6.04%, 6.98%, 4.12%, 4.29%, 5.39%, 8.24%, 13.17%, and 5.08%, respectively. It also recorded the highest precision (0.9821), recall (0.9838), and F1-score (0.9819). Findings highlight CiteWasteRN50's strong accuracy and applicability for real-world waste classification.

Circular Compliance: Aligning EV Battery Waste Management with the EU Battery Regulation 2023/1542

Hamid Safarzadeh — Tue, 30 Dec 2025 00:00:00 +0000

The rapid growth of electric vehicle (EV) adoption in Europe presents both opportunities and challenges for sustainable energy transitions. A critical issue lies in the management of end-of-life (EoL) batteries, which contain scarce and hazardous materials yet offer high potential for recovery and reuse. The EU Battery Regulation 2023/1542 establishes ambitious provisions, including mandatory recovery rates of 70% lithium and 95% cobalt/nickel by 2030, carbon footprint disclosure, digital battery passports, and extended producer responsibility (EPR) schemes. This study evaluates how circular economy strategies can align with these requirements to ensure sustainable EV battery waste management. A policy–technology mapping framework was developed to analyze compliance potential across four strategies: design-for-circularity, second-life applications, recycling innovations, and material recovery optimization. Results indicate that recycling innovations and material recovery achieve the highest regulatory alignment, with hydrometallurgical processes currently reaching 90–95% cobalt/nickel recovery and projected 70% lithium recovery by 2030. Design-for-circularity reduces lifecycle impacts by 15–20%, while second-life applications extend battery utility by 20–30% and lower lifecycle carbon emissions by 10–15%. A national case study of Italy reveals accelerating EV adoption (>25% annual growth) but highlights limited recycling capacity, with only 30% of EoL batteries processed domestically, underscoring urgent infrastructure needs. The findings demonstrate that no single strategy ensures full compliance, but integrated approaches combining modular design, advanced recycling, and second-life deployment can deliver both regulatory compliance and sustainability benefits. This framework provides actionable insights for policymakers and industry stakeholders, strengthening Europe’s pathway toward a circular, low-carbon mobility system.

International Recognition of Aviation Patents: New Standards for Pilot Training

Nicolas Jean Lejeune — Tue, 30 Dec 2025 00:00:00 +0000

Aviation regulators increasingly rely on competency-based training and high-fidelity simulation to manage operational risk, yet cross-border recognition of training technologies remains uneven. This paper asks how aviation training patents can act as socio-technical reference architectures that support regulatory convergence in simulator qualification, data governance, and continuous oversight. We adopt a desk-based comparative policy analysis combined with case-oriented document review of three patented training architectures: a cyber-physical flight simulator that transforms real flight telemetry into adaptive scenarios, a virtual-reality pilot training system, and an AI-avatar-enabled universal simulator. Findings show that patents influence standards not only via legal protection but via explicit modularization, audit-ready data interfaces, and traceable performance metrics that can be mapped to ICAO/EASA/FAA qualification criteria. Building on this mapping, we operationalize the notion of continuous certification by specifying auditable artifacts (scenario provenance, model versioning, instructor interventions, and qualification test guides) and propose a lifecycle in which certification is maintained through evidence streams rather than episodic re-qualification. The paper contributes a practical evaluation framework for regulators and training organizations and clarifies limitations and governance risks, including data protection constraints and confirmation bias in single-inventor narratives.