25 research outputs found
Trustworthy and Explainable Artificial Neural Networks for Choice Behaviour Analysis
No full textFor decades, Discrete Choice Models (DCMs) have been used to describe, understand and predict human choice behaviour in a wide variety of contexts including transportation, healthcare and marketing. The field of discrete choice modelling is firmly rooted in economic theory, and most DCMs are based on the assumption that decision-makers, when asked to select an alternative among a set of presented alternatives, make deliberate trade-offs by employing a stable function to assign utility to each alternative, and then select the alternative with thehighest utility.TRAIL Thesis Series no. T2020/11, the Netherlands Research School TRAILTransport and Logistic
An artificial neural network based approach to investigate travellers’ decision rules
No full textThis study develops a novel Artificial Neural Network (ANN) based approach to investigate decision rule heterogeneity amongst travellers. This complements earlier work on decision rule heterogeneity based on Latent Class discrete choice models. We train our ANN to recognise the choice patterns of four distinct decision rules: Random Utility Maximisation, Random Regret Minimisation, Lexicographic, and Random. Next, we apply our trained ANN to classify the respondents from a recent Value-of-Time Stated Choice experiment in terms of their most likely employed decision rule. We cross-validate our findings by comparing our results with those from: (1) single class discrete choice models estimated on subsets of the data, and (2) latent class discrete choice models. The cross-validations provide strong support for the notion that ANNs can be used to identify underlying decision rules in choice data. As such, we believe that ANNs provide a valuable addition to the toolbox of analysts who wish to investigate decision rule heterogeneity. The substantive contribution of this study is that we provide strong empirical evidence for the presence of decision rule heterogeneity amongst travellers.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Transport and Logistic
A dynamic optimization model on the routing and maintenance scheduling of aircraft for individual tasks
No full textIncreasing competition amongst airlines necessitates them to improve the efficiency of their operations. Even though maintenance, repair, and overhaul (MRO) represent a significant portion of an airline’s operational costs, aircraft maintenance scheduling is often still a manual process, producing suboptimal solutions. Airlines typically operate by congregating the bulk of the required maintenance tasks in extensive checks, called letter checks (A, B, C, or D). Letter checks require the aircraft to be taken out of operations and result in many tasks being executed before they are due, leading to more required maintenance over the aircraft's lifetime. The purpose of this study is to develop a methodology that provides flight routes to aircraft and plans the maintenance tasks individually within these routes over a given planning horizon with the objective of maximizing the utilization of the total remaining flying time of the fleet. To achieve this, tasks are planned as late as possible on overlays at a maintenance station, while being given a due date and a remaining number of legal flight hours that can be flown before execution is mandatory. For this purpose, we develop a mixed integer programming (MIP) model based on a city-day network representation. Because the computational burden of exact methods becomes too hefty for increasing problem sizes, several matheuristics have been developed to provide good solutions in quick fashion. The presented matheuristics either decompose the problem by aircraft or into time periods. The former constructs the flight routes and maintenance schedules aircraft per aircraft while the latter constructs them simultaneously in a rolling horizon fashion. For the rolling horizon matheuristics, several forecasting strategies have been designed as well. In an experimental study, one of the selected rolling horizon matheuristics was able to remove the need for aircraft to be taken out of operations for an A-check (the most frequently occurring letter-check), potentially saving up to \$ 7.2 million per aircraft over a time period of ten years. Furthermore, the lost flying time, incurred by planning maintenance tasks before they are due, was decreased by over 98\%, resulting in a higher utilization of the task intervals and less required maintenance over the aircraft's lifetime. Finally, the dissection of the A-check into its individual tasks led to a more phased maintenance schedule by attenuating the peaks in workload for the mechanics workforce. Our presented approach can be used by mid-sized airlines to optimize their maintenance schedules through increasing aircraft availability and reducing maintenance costs over the aircraft's lifetime.Mechanical Engineering | Transport Engineering and Logistic
Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis
No full textArtificial Neural Networks (ANNs) are increasingly used for discrete choice analysis. But, at present, it is unknown what sample size requirements are appropriate when using ANNs in this particular context. This paper fills this knowledge gap: we empirically establish a rule-of-thumb for ANN-based discrete choice analysis based on analyses of synthetic and real data. To investigate the effect of complexity of the data generating process on the minimum required sample size, we conduct extensive Monte Carlo analyses using a series of different model specifications with different levels of model complexity, including RUM and RRM models, with and without random taste parameters. Based on our analyses we advise to use a minimum sample size of fifty times the number of weights in the ANN; it should be noted, that the number of weights is generally much larger than the number of parameters in a discrete choice model. This rule-of-thumb is considerably more conservative than the rule-of-thumb that is most often used in the ANN community, which advises to use at least ten times the number of weights.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Transport and Logistic
‘Computer says no’ is not enough: Using prototypical examples to diagnose artificial neural networks for discrete choice analysis
No full textArtificial Neural Networks (ANNs) are increasingly used for discrete choice analysis, being appreciated in particular for their strong predictive power. However, many choice modellers are critical – and rightfully so – about using ANNs, for the reason that they are hard to diagnose. That is, for analysts it is hard to see whether a trained (estimated) ANN has learned intuitively reasonable relationships, as opposed to spurious, inexplicable or otherwise undesirable ones. As a result, choice modellers often find it difficult to trust an ANN, even if its predictive performance is strong. Inspired by research from the field of computer vision, this paper pioneers a low-cost and easy-to-implement methodology to diagnose ANNs in the context of choice behaviour analysis. The method involves synthesising prototypical examples after having trained the ANN. These prototypical examples expose the fundamental relationships that the ANN has learned. These, in turn, can be evaluated by the analyst to see whether they make sense and are desirable, or not. In this paper we show how to use such prototypical examples in the context of choice data and we discuss practical considerations for successfully diagnosing ANNs. Furthermore, we cross-validate our findings using techniques from traditional discrete choice analysis. Our results suggest that the proposed method helps build trust in well-functioning ANNs, and is able to flag poorly trained ANNs. As such, it helps choice modellers use ANNs for choice behaviour analysis in a more reliable and effective way.Transport and Logistic
Why did you predict that? Towards explainable artificial neural networks for travel demand analysis
No full textArtificial Neural Networks (ANNs) are rapidly gaining popularity in transportation research in general and travel demand analysis in particular. While ANNs typically outperform conventional methods in terms of predictive performance, they suffer from limited explainability. That is, it is very difficult to assess whether or not particular predictions made by an ANN are based on intuitively reasonable relationships embedded in the model. As a result, it is difficult for analysts to gain trust in ANNs. In this paper, we show that often-used approaches using perturbation (sensitivity analysis) are ill-suited for gaining an understanding of the inner workings of ANNs. Subsequently, and this is the main contribution of this paper, we introduce to the domain of transportation an alternative method, inspired by recent progress in the field of computer vision. This method is based on a re-conceptualisation of the idea of ‘heat maps’ to explain the predictions of a trained ANN. To create a heat map, a prediction of an ANN is propagated backward in the ANN towards the input variables, using a technique called Layer-wise Relevance Propagation (LRP). The resulting heat map shows the contribution of each input value –for example the travel time of a certain mode– to a given travel mode choice prediction. By doing this, the LRP-based heat map reveals the rationale behind the prediction in a way that is understandable to human analysts. If the rationale makes sense to the analyst, the trust in the prediction, and, by extension, in the trained ANN as a whole, will increase. If the rationale does not make sense, the analyst may choose to adapt or re-train the ANN or decide not to use it at all. We show that by reconceptualising the LRP methodology towards the choice modelling and travel demand analysis contexts, it can be put to effective use in application domains well beyond the field of computer vision, for which it was originally developed.</p
A study of changing character showed by Jodi in The Silent Wife novel by A.S.A Harrison
Get PDFJodi is the character in the novel The Silent Wife who touches the deep truths about Jodi is life and love tragic relationship. She is a counselor who has a clinic that she services her client if they want to tell of the all about their problems. However, on the other she is a murder. This thesis focuses on analyzing the changing characters of Jodi in the story line novel and also how are the causes of the changing characters of Jodi. This is basically uses New Criticism theory, in the process of analyzing, the writer uses telling technique, how the author directly describes about the character looks like, his or her attitude, his or her personality, and the rest, and showing technique, the author shows a reader something about character that can emerge from the way he or she speak, reacts, or thanks to study about Jodi character. The writer concludes that using interrelationship of the formal elements, the study find that one could find that Jodi changing character show the problems her faces make the character changes that make the worst impact in her life
Možnost rozvoje střední venkovské obce na příkladu Žabčic
No full textThe bachelor thesis is focused on the development possibilities of middle-country municipality Zabcice. It is mainly describing the economic function of the municipality -- its income and expenses, inhabitants, transport, services. The work is also focusing on the biggest economic subjects in the municipality -- A.S.A. company, Moracell, nursing home, Sand Zabcice Ltd. In the part about agribusiness, the thesis is giving a description of the university farm and Czech Union of Allotment and Leisure Gardeners. It is defining the position of the municipality Zabcice within the wider relationship with villages Unkovice, Prisnotice and cities Zidlochovice, Brno. In the practical part, the author is providing group conversation about the possibilities of development of the village and then using SWOT analyzis evaluate the overall view of the village Zabcice
Design and numerical simulation of a semi-symmetrical groove type resonator at millimeter waves
No full textSevgi, Levent (Dogus Author) -- Conference full title: 2003 IEEE International Symposium on Electromagnetic Compatibility, EMC 2003; Istanbul; Turkey; 11 May 2003 through 16 May 2003.A semi-symmetrical groove guide resonator at millimeter waves is investigated both experimentally and numerically. The structure is made of duraluminium and fabricated with a maximum relative tolerance of less than 0.5%. Its resonance frequencies are measured. The simulations are performed via the powerful time domain simulator FDTD (Finite Difference Time Domain). The comparisons will be presented and the results will be discussed
A study of changing character showed by Jodi in The Silent Wife novel by A.S.A Harrison
Get PDFJodi is the character in the novel The Silent Wife who touches the deep truths about Jodi is life and love tragic relationship. She is a counselor who has a clinic that she services her client if they want to tell of the all about their problems. However, on the other she is a murder. This thesis focuses on analyzing the changing characters of Jodi in the story line novel and also how are the causes of the changing characters of Jodi. This is basically uses New Criticism theory, in the process of analyzing, the writer uses telling technique, how the author directly describes about the character looks like, his or her attitude, his or her personality, and the rest, and showing technique, the author shows a reader something about character that can emerge from the way he or she speak, reacts, or thanks to study about Jodi character. The writer concludes that using interrelationship of the formal elements, the study find that one could find that Jodi changing character show the problems her faces make the character changes that make the worst impact in her life
