TU Delft Open Access Journals
Not a member yet
3113 research outputs found
Sort by
The Structuralist Debate: Conceptual Architecture (1969-1974) between Formalism and Ideology
Full text linkIn 1967 structuralism underwent a theoretical acceleration, establishing its scientific basis through linguistics and semiotics, which allowed it to question its metaphysical and anti-historical premises through its critique of anthropocentrism, and it began to enter into relations with other disciplines, including architecture.
Peter Eisenman’s interest in the conceptual began with the various versions of his manifesto ‘Notes on Conceptual Architecture: Towards a Definition’, published between 1970 and 1974; in all these texts, he speaks of formal universals, deep structures, conceptual structures and sign systems capable of generating meaning.
The Conceptual Architecture was immediately criticised by Diana Agrest and Mario Gandelsonas, who denounced this structuralist appropriation as an ideological consumption of theory. From 1974 onwards, Conceptual Architecture began to show signs of weakness, but it was only after the critique by Agrest and Gandelsonas, which questioned both its assumptions and its entire intellectual trajectory, that Eisenman\u27s theoretical agenda evolved towards a new, hermetic and unknowable code: the exact opposite of what had been advocated
AI-Driven Raw Material Demand Forecasting: Towards Project Management Practices
Full text linkAccurate forecasting of raw material demand is critical for effective decision-making in project management, particularly in the construction sector. Demand fluctuations in this industry can severely disrupt workflows and cause project delays. Reliable demand predictions help maintain operational stability and reduce risks, especially under uncertain conditions. In such environments, maintaining appropriate Target Stock Levels (TSL) and setting effective Reorder Points (RP) are essential to ensure project continuity and customer satisfaction. This study investigates the potential of Artificial Intelligence (AI) to enhance demand forecasting accuracy within service-based supply chains. Five forecasting models were evaluated: four machine learning approaches—Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), Random Forest (RF), and Gaussian Regression (GR)—and one traditional statistical method, the Autoregressive Integrated Moving Average (ARIMA) model. The models were trained and tested using historical raw material consumption data collected from a construction project over a four-year period (2019–2023). The results show that the Machine Learning Models significantly outperformed the ARIMA model in terms of predictive accuracy. The coefficients of determination (R²) were 0.93 for LSTM, 0.91 for XGBoost, 0.89 for GR, and 0.88 for RF, compared to 0.75 for ARIMA. Among all models, LSTM achieved the highest forecasting accuracy and the lowest deviation on the test dataset. Its implementation for the 2024 planning horizon led to substantial inventory optimization, reducing overstock volumes by 66.5%. This improvement translated into significant cost savings and enhanced the overall efficiency of material management and decision-making processes
Trade-offs in multi-channel delivery network design with perishable and non-perishable goods
Full text linkThis study focuses on optimizing last-mile delivery in e-commerce by balancing cost efficiency and customer preferences, particularly for mixed perishable and non-perishable goods distribution. As online grocery shopping grows, ensuring the timely and efficient delivery of perishable products while maintaining quality remains a critical challenge. The problem is modelled as a variant of the multi-objective Vehicle Routing Problem (VRP), where customer utility and operational costs are incorporated as two objectives. Customer utility is computed with parameters estimated using the Best-Worst Method (BWM). The multi-objective model is solved by linearizing the non-linear objectives and using a weighted sum method. The model evaluates home delivery, attended pickup points, and lockers, revealing that cost-driven strategies shift deliveries toward self-pickup, with perishable items primarily assigned to attended pickup points due to temperature control. The findings provide insights for improving delivery network design, enhancing service quality, and optimizing the distribution of both perishable and non-perishable products
When is explainable AI useful?
Full text linkIn this paper I assess the ethical and epistemic utility of explainable AI algorithms. I first distinguish between different types of outputs that AI can have. The first class of outputs are verifiable (either through a third-party or in virtue of contributing to a win in a game scenario) – that is, there is a way to independently verify the outputs of the model. The second class of outputs are non-verifiable and include outputs like ideals (finding the best of something) and generative AI. While there is some epistemic value gained by explaining the outputs of verifiable AI, there is no intersection between explanations offered by xAI and ethically useful explanations. Therefore, if there is an ethical problem with the use of opaque AI systems, explainable AI won’t be able to help solve it
Placing Technology: An Interview with Yuk Hui
Full text linkIn this interview, the editors met with Professor Yuk Hui, the originator of the notion of cosmotechnics, to discuss the implications of cosmotechnical thinking for architecture, urbanism and design. While Hui\u27s work contains strong implications for architecture and spatial disciplines, he has rarely addressed them directly. In this far-ranging discussion, Hui brings together diverse topics, including the philosophy of Lewis Mumford, the cross-cultural history of cybernetics, and technology\u27s connection to sacred space
Everyone Knows Who is Stupid Around Here
Full text linkFar from alien to our daily lives, stupidity seems evident to most people. However, discerning what is stupid may not be as easy as it looks, especially when talking about architecture. To specify what architectural stupidity is, we must acknowledge that not all failures of architecture are ‘errors’, some are worse. This article discusses the already architecturally situated concept of error and distinguishes it from stupidity in terms of ‘technicities’ that fail. The Simondonian concept of technicity helps to locate error and stupidity according to their mutative potentials. We argue that the difference between the two is materialised in a failed theme park in Ankara. Planned as one of the municipality’s signature projects of the 2010s, Ankapark damages the tangible and intangible relationships within the land it sits on, Atatürk Forest Farm. This park, with its seemingly erroneous processes of engagement with the built environment and human and non-human inhabitants, bypasses any rationale and transforms a productive urban territory into an intransitive field for knowledge systems, institutions and disciplines. The cancerous mutation it feeds does not inform any knowledge system to the point that ‘it can no longer stand itself’, providing only ‘stupidity in stupidity’
Reviews and Responses for Sampling-Based Aircraft Path Planning with Soft Actor-Critic
Full text linkSee detailed reviews and responses in the PDF file.
DOI for the original paper: https://doi.org/10.59490/joas.2025.787
Assessing Climate Effects Resulting From Airspace Closures Following the Ukrainian Crisis
Full text linkClosures of the Russian and Ukrainian airspace following the Russian invasion of Ukraine in February 2022 have influenced international air transport. Flights have to be re-routed leading to increases in mission distance, flight time, fuel consumption and CO2 emissions. However, the climate impact of aviation is also significantly determined by non-CO2 effects which do not only depend on emission quantities but also emission location and time. Therefore, this paper aims to quantify the climate impact from Russian and Ukrainian airspace closures in context of the Ukrainian crisis. The analysis is built on open-source flight track data as provided by The OpenSky Network applied in the Integrated Trajectory Calculation Module. Climate impact evaluation is performed in a climatological approach using climate chemistry response model AirClim. The analysis confirms an increase in fuel consumption and CO2 effects for a mission-specific comparison of pre invasion and post invasion air traffic scenarios. By contrast, the climate impact from non-CO2 species decreases disproportionately leading to a slight reduction of the total climate impact. This is caused by changes in emission latitude and altitude. On a larger temporal scale, a comparison of annual pre and post invasion scenarios is also influenced by changes in flight plans and fleet composition. While airspace closures have significantly influenced aviation in terms of fuel consumption, flight time and operating cost leading to economic disadvantages, an environmental disadvantage regarding the climate impact of aviation cannot be confirmed
An improved approach for denoising acoustic signals of subsea gas pipeline leak using hybrid algorithms
Full text link Detecting leaks in subsea gas pipelines is a complex challenge because ambient noise often compromises the accuracy of detection. Effective noise removal from pipeline leak signals is essential for improving the precision of leak identification in subsea pipelines. In this study, a hybrid intelligent algorithm is designed to enhance the denoising capability of subsea gas pipeline leak signals. The key parameters of the Variational Mode Decomposition (VMD) were optimized using the Archimedes Optimization Algorithm (AOA) to ensure efficient and accurate signal decomposition. The optimized VMD decomposes a noisy signal into multiple Intrinsic Mode Functions (IMFs), each containing distinct signal components. These IMFs were filtered by calculating their correlation with the original signal. The principal components of the leak signal retained after this screening process were reconstructed. The Wavelet Transform (WT) was applied to further eliminate residual noise and enhance the signal quality. The results demonstrate that the optimized VMD significantly improves the decomposition accuracy and efficiency compared to traditional parameter selection methods. Furthermore, the joint AOA-VMD-WT denoising algorithm outperformed the other methods across common denoising metrics, showing superior noise reduction performance.
One sentence summary: This study presents a novel approach to subsea leak signal processing, showing that AOA-VMD-WT boosts acoustic quality, simplifying preprocessing and making reliable signal analysis accessible for real-time pipeline monitoring
Investigation of Point Merge Utilization Worldwide Using Opensky Network Data
Full text linkPoint Merge (PM) arrival procedures are currently in use at 44 airports across 20 countries worldwide. These procedures come in various design variants, including overlapping, partially overlapping, or separated sequencing legs. The positioning of sequencing legs within or outside of the Terminal Maneuvering Area (TMA) and the geometry of the arrival flows to PM or merging points impact the associated trade-offs between the PM system capacity and efficiency. In our study, we analyze the utilization of PM procedures at several airports implementing PM, using open-access ADS-B-based data from the Opensky Network. To identify flights that adhere to the PM procedures, we propose a catchment algorithm. The accuracy of the algorithm depends on the quality and completeness of the data, the specific design of the algorithm, and the complexity of the PM procedures. Generally, a well-designed catchment algorithm can achieve high accuracy by considering factors such as aircraft positions, speeds, and adherence to sequencing instructions. Then, we quantify PM utilization using performance indicators specifically tailored for this purpose.
This paper builds upon previous research presented at the 11th OpenSky Symposium in 2023. We introduce an additional step to enhance the accuracy of the catchment algorithm and conduct a comprehensive sensitivity analysis of the catchment area size employed in the initial stage. We quantify the algorithm’s accuracy by considering false-positive and false-negative filtered trajectories. Furthermore, we compare the results of our proposed approach with the PM identification tool available in the Traffic Library.