336 research outputs found
Optimizing maintenance by learning individual treatment effects
No full textThe goal in maintenance is to avoid machine failures and overhauls, while simultaneously minimizing the cost of preventive maintenance. Maintenance policies aim to optimally schedule maintenance by modeling the effect of preventive maintenance on machine failures and overhauls. Existing work assumes the effect of preventive maintenance is (1) deterministic or governed by a known probability distribution, and (2) machine-independent. Conversely, this work proposes to relax both assumptions by learning the effect of maintenance conditional on a machine's characteristics from observational data on similar machines using existing methodologies for causal inference. This way, we can estimate the number of overhauls and failures for different levels of maintenance and, consequently, optimize the preventive maintenance frequency. We validate our proposed approach using real-life data on more than 4,000 maintenance contracts from an industrial partner. Empirical results show that our novel, causal approach accurately predicts the maintenance effect and results in individualized maintenance schedules that are more accurate and cost-effective than supervised or non-individualized approaches
Predict-then-optimize or predict-and-optimize? An empirical evaluation of cost-sensitive learning strategies
No full textsponsorship: This work was supported by the BNP Paribas Fortis Chair in Fraud Analytics and FWO research project G015020N. The computational resources and services used in this work were provided by the VSC (Flemish Supercomputer Center), funded by the Research Foundation - Flanders (FWO) and the Flemish Government - department EWI. (BNP Paribas Fortis Chair in Fraud Analytics, FWO|G015020N, Research Foundation - Flanders (FWO), Flemish Government - department EWI)status: Publishe
Perancangan Aplikasi E-contract Pada Platform Manga Toon Berbasis Web Pada Manga Toon HK Limited
No full textPada zaman industri 4.0, banyak aplikasi atau web yang menyediakan layanan baca komik dan novel secara online, baik berbentuk e-book, aplikasi, maupun web yang memang menyediakan layanan tersebut. Manga Toon adalah salah satu platform penyedia layanan baca komik, novel, dan menonton anime online internasional. Manga Toon juga menyediakan tempat baca novel karya penulis lokal yang bebas dibaca dimanapun dan kapanpun. Author novel yang meng-upload karya memiliki kesempatan bisa mendapatkan penghasilan dari karya tersebut. Namun, sistem penerimaan kontrak di Manga Toon masih semi-komputerisasi, karena masih menghubungi author melalui nomor whatsapp yang sejak awal didaftarkan saat meng-upload karya, lalu menginput data ke surat kontrak secara manual yang dilakukan oleh admin. Kegiatan ini memakan waktu yang cukup banyak sehingga proses pembuatan surat kontrak dan pengiriman kembali surat kontrak yang sudah di approve terhambat. Dengan permasalahan tersebut, maka penulis melakukan analisa melalui beberapa metode pengumpulan data, dengan melakukan kegiatan magang/observasi, melakukan wawancara dan metode studi pustaka untuk menemukan solusi dari permasalahan yang terjadi pada penerimaan kontrak novel di aplikasi Manga Toon. Penulis akan menganalisis dengan menggunakan metode PIECES. Selanjutnya, desain sistem yang dibuat berjalan menggunakan Unified Modeling Language (UML) diantaranya menggunakan Use Case Diagram dan menggunakan Activity Diagram. Dalam hal ini, penulis menganalisa sistem kontrak pada aplikasi Manga Toon diharapkan dapat menggunakan sistem dalam penginputan data ke surat kontrak
Commentary to the recent study by Wang et al.
No full textThe author(s) received no financial support for the research, authorship, and/or publication of this article
Optimizing depth perception for toon-shading in stereoscopic 3D
No full textThe human visual system perceives 3D depth by observing how much points shift between the left eye and right eye. Toon-shaded renders of 3D models often have untextured surfaces with discretized shading, and these flat featureless areas give the eyes few reference points to perceive 3D depth. The primary depth cues come from contour lines and the discrete shading lines dividing bright and dark, so they have to be used to their fullest. This research tries to develop a method for automatically optimizing depth-perception for a 3D toon-shaded scene with smart light placement, local editing of shading, and the generation of effective contour lines.Computer Science | Computer Graphic
Fictionalism and intentionality
No full textThis is the author accepted manuscript. The final version is available from Routledge via the DOI in this recordThis chapter offers a defence of mental fictionalism. Its central claim is that the notion of the mind as an inner world of representations is merely a useful fiction. Mental fictionalism is often said to suffer from “cognitive collapse”, since stating the fictionalist’s position itself involves reference to mental states, such as imagination or make-believe. This chapter shows how mental fictionalism can avoid cognitive collapse. To do so, it explores fictionalism’s broader implications for the nature of intentionality. The key to avoiding cognitive collapse is to see that fictionalism can grant the existence of external, public representations with content, such as written and spoken language. In contrast, the notion of inner representations is what the early fictionalist Hans Vaihinger called a “real fiction”: it is an idea that is not merely false, but incoherent
Operational decision-making with machine learning and causal inference
No full textAbstract: Optimizing operational decisions, routine actions within some business or operational process, is a key challenge across a variety of domains and application areas. The increasing availability of data, computational power, and advanced machine learning (ML) algorithms offers exciting opportunities for data-driven decision support. To advance the potential of ML for optimizing operational decision-making, we explore two research directions, aiming to develop ML models that are decision-focused and causal. This dissertation presents several developments in machine learning in these two areas. ML is effective at making predictions from historical data: for example, estimating a transaction's fraud probability by comparing it to past cases. However, decision-makers not only need to consider these predictions, but also the operational context. For example, the decision-maker uses predicted fraud probabilities to determine which transactions to investigate, while aiming to minimize monetary losses due to fraud and considering the available capacity of the fraud investigations team. Predictions can help reduce uncertainty (e.g., by predicting the fraud probability), but standard ML models are prediction-focused, instead of decision-focused. This distinction involves two challenges for data-driven decision-making. First, prediction-focused models prioritize predictive accuracy instead of the resulting decision quality (e.g., fraud losses recovered by the bank). Second, these models fail to account for operational constraints, such as the available investigation capacity. Decision-focused learning aims to improve data-driven decision-making by addressing these issues and incorporating the operational context into the optimization of ML models. In this dissertation, we analyze cost-sensitive learning within this prediction-optimization framework and evaluate general strategies for making cost-optimal decisions with ML. Additionally, we propose a novel ML method for optimal decision-making under capacity constraints based on learning to rank. To make effective decisions, a decision-maker has to estimate the causal effect of possible interventions in order to choose actions that achieve the desired outcome. Unfortunately, standard ML models identify correlations in the data instead of causal relationships. Because of this, these models cannot guarantee the effectiveness of decisions made based on their predictions. Causal inference provides a formal framework for reasoning about causality and identifying causal effects from data. This dissertation explores the intersection of causality and ML. First, we illustrate the potential of causal ML for optimizing preventive maintenance. Next, we propose novel causal ML methods for predicting causal effect distributions and for addressing informative sampling when predicting treatment outcomes over time. We also argue for a practical, end-to-end perspective for building ML pipelines for causal inference and propose an automated framework doing so. Finally, we combine decision-focused learning with causal inference by introducing ranking metalearners to optimize treatment decisions under capacity constraints
Inner World as a Useful Fiction: An Interview with Adam Toon
No full textAdam Toon is an Associate Professor at the University of Exeter and Director of Egenis, Centre for the Study of Life Sciences. He did his PhD in the Department of History and Philosophy of Science at the University of Cambridge. He works in philosophy of science and philosophy of mind, mainly investigating the idea of representations as fictions. Toon is the author of Mind as Metaphor: A Defence of Mental Fictionalism (Oxford University Press, 2023) and Models as Make-Believe: Imagination, Fiction and Scientific Representation (Palgrave Macmillan, 2012). He is also co-editor (with Tamás Demeter and Ted Parent) of Mental Fictionalism: Philosophical Explorations (Routledge, 2022).Adam Toon gave the Gottlob Frege Lectures in Theoretical Philosophy at the University of Tartu on December 5–7, 2023, under the title “The Story of the Mind: Cartesianism, Behaviourism, and Fictionalism”. The interview took place in Tartu on December 7, 2023
Grammatica Grandonica: the Sanskrit grammar of Johann Ernst Hanxleden S.J. (1681-1732) [introduced and edited by Toon Van Hal & Christophe Vielle, with a photographical reproduction of the original manuscript by Jean-Claude Muller]
No full textIn May 2010, Johann Ernst Hanxleden¿s Grammatica Grandonica was rediscovered in Monte Compatri (Lazio, Rome) by Toon Van Hal. Although historiographers recognized the importance of the nearly oldest western grammar of Sanskrit, the precious manuscript had been lost for several decades. The primary aim of the present digital publication is to offer a photographical reproduction of the manuscript. This facsimile is accompanied by a double edition: a facing diplomatic edition
with the Sanskrit in Malay¿¿am script, followed by a transliterated text. This preliminary edition, devoid of any apparatus, is preceded by an introduction dealing with (1) the missionary context,
(2) the life and works of the author, (3) the contents, peculiarities and history of his grammar, and (4) the editorial principles used
- …
