The development of black-box survival models has created a need for methods that explain their outputs, just as in the case of traditional machine learning methods. Survival models usually predict functions rather than point estimates. This special nature of their output makes it more difficult to explain their operation. We propose a method to generate plausible counterfactual explanations for survival models. The method supports two options that handle the special nature of survival models' output. One option relies on the Survival Scores, which are based on the area under the survival function, which is more suitable for proportional hazard models. The other one relies on Survival Patterns in the predictions of the survival model, which represent groups that are significantly different from the survival perspective. This guarantees an intuitive well-defined change from one risk group (Survival Pattern) to another and can handle more realistic cases where the proportional hazard assumption does not hold. The method uses a Particle Swarm Optimization algorithm to optimize a loss function to achieve four objectives: the desired change in the target, proximity to the explained example, likelihood, and the actionability of the counterfactual example. Two predictive maintenance datasets and one medical dataset are used to illustrate the results in different settings. The results show that our method produces plausible counterfactuals, which increase the understanding of black-box survival models.

The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. This paper proposes a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases. This decomposition enables a more fine-grained analysis of the strengths and weaknesses of survival prediction methods. The usefulness of this decomposition is demonstrated through benchmark comparisons against state-of-the-art and classical models, together with a new variational generative neural-network-based method (SurVED), which is also proposed in this paper. Performance is assessed using four publicly available datasets with varying levels of censoring. The analysis using the C-index decomposition and synthetic censoring shows that deep learning models utilize the observed events more effectively than other models, allowing them to keep a stable C-index in different censoring levels. In contrast, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events. © 2024 The Author(s)

Survival Analysis models usually output functions (survival or hazard functions) rather than point predictions like regression and classification models. This makes the explanations of such models a challenging task, especially using the Shapley values. We propose SurvSHAP, a new model-agnostic algorithm to explain survival models that predict survival curves. The algorithm is based on discovering patterns in the predicted survival curves, the output of the survival model, that would identify significantly different survival behaviors, and utilizing a proxy model and SHAP method to explain these distinct survival behaviors. Experiments on synthetic and real datasets demonstrate that the SurvSHAP is able to capture the underlying factors of the survival patterns. Moreover, SurvSHAP results on the Cox Proportional Hazard model are compared with the weights of the model to show that we provide faithful overall explanations, with more fine-grained explanations of the sub-populations. We also illustrate the wrong model and explanations learned by a Cox model when applied to heterogeneous sub-populations. We show that a non-linear machine learning survival model with SurvSHAP can better model the data and provide better explanations than linear models.

Time-To-Event (TTE) modeling using survival analysis in industrial settings faces the challenge of premature replacements of machine components, which leads to bias and errors in survival prediction. Typically, TTE survival data contains information about components and if they had failed or not up to a certain time. For failed components, the time is noted, and a failure is referred to as an event. A component that has not failed is denoted as censored. In industrial settings, in contrast to medical settings, there can be considerable uncertainty in an event; a component can be replaced before it fails to prevent operation stops or because maintenance staff believe that the component is faulty. This shows up as “no fault found” in warranty studies, where a significant proportion of replaced components may appear fault-free when tested or inspected after replacement.

In this work, we propose an expectation-maximization-like method for discovering such premature replacements in survival data. The method is a two-phase iterative algorithm employing a genetic algorithm in the maximization phase to learn better event assignments on a validation set. The learned labels through iterations are accumulated and averaged to be used to initialize the following expectation phase. The assumption is that the more often the event is selected, the more likely it is to be an actual failure and not a “no fault found”.

Experiments on synthesized and simulated data show that the proposed method can correctly detect a significant percentage of premature replacement cases.

In this work, we use an Evolutionary Algorithm (EA) to discover a novel Neural Network (NN) regression-based survival loss function with the aim of improving the C-index performance. Our contribution is threefold; firstly, we propose an evolutionary meta-learning algorithm SAGA$_{loss}$ for optimizing a neural-network regression-based loss function that maximizes the C-index; our algorithm consistently discovers specialized loss functions that outperform MSCE. Secondly, based on our analysis of the evolutionary search results, we highlight a non-intuitive insight that signifies the importance of the non-zero gradient for the censored cases part of the loss function, a property that is shown to be useful in improving concordance. Finally, based on this insight, we propose MSCE$_{Sp}$, a novel survival regression loss function that can be used off-the-shelf and generally performs better than the Mean Squared Error for censored cases. We performed extensive experiments on 19 benchmark datasets to validate our findings.

There is a major ongoing transition from utilizing fossil fuel to electricity in buses for enabling a more sustainable, environmentally friendly, and connected transportation ecosystem. Batteries are expensive, up to 30% of the total cost for the vehicle (A. Fotouhi 2016), and considered safety-critical components for electric vehicles (EV). As they deteriorate over time, monitoring the health status and performing the maintenance accordingly in a proactive manner is crucial to achieving not only a safe and sustainable transportation system but also a cost-effective operation and thus a greater market satisfaction. As a widely used indicator, the State of Health (SOH) is a measurement that reflects the current capability of the battery in comparison to an ideal condition. Accurate estimation of SOH is important to evaluate the validity of the batteries for the intended application and can be utilized as a proxy to estimate the remaining useful life (RUL) and predict the end-of-life (EOL) of batteries for maintenance planning. The SOH is computed via an on-board computing device, i.e. battery management unit (BMU), which is commonly developed based on controlled experiments and many of them are physical-model based approaches that only depend on the internal parameters of the battery (B. Pattipati 2008; M. H. Lipu 2018). However, the deterioration processes of batteries in hybrid and full-electric buses depend not only on the designing parameters but also on the operating environment and usage patterns of the vehicle. Therefore, utilizing multiple data sources to estimate the health status and EOL of the batteries is of potential internet. In this study, a data-driven prognostic method is developed to estimate SOH and predict EOL for batteries in heterogeneous fleets of hybrid buses, using various types of data sources, e.g. physical configuration of the vehicle, deployment information, on-board sensor readings, and diagnostic fault codes. A set of new features was generated from the existing sensor readings by inducing artificial resets on each battery replacement. A neural network-based regression model achieved accurate estimates of battery SOH status. Another network was used to indicate the EOL of batteries and the result was evaluated using battery replacement based on the current maintenance strategy. © ESREL2020-PSAM15 Organizers. Published by Research Publishing, Singapore.

Batteries are a safety-critical and the most expensive component for electric vehicles (EVs). To ensure the reliability of the EVs in operation, it is crucial to monitor the state of health of those batteries. Monitoring their deterioration is also relevant to the sustainability of the transport solutions, through creating an efficient strategy for utilizing the remaining capacity of the battery and its second life. Electric buses, similar to other EVs, come in many different variants, including different configurations and operating conditions. Developing new degradation models for each existing combination of settings can become challenging from different perspectives such as unavailability of failure data for novel settings, heterogeneity in data, low amount of data available for less popular configurations, and lack of sufficient engineering knowledge. Therefore, being able to automatically transfer a machine learning model to new settings is crucial. More concretely, the aim of this work is to extract features that are invariant across different settings.

In this study, we propose an evolutionary method, called genetic algorithm for domain invariant features (GADIF), that selects a set of features to be used for training machine learning models, in such a way as to maximize the invariance across different settings. A Genetic Algorithm, with each chromosome being a binary vector signaling selection of features, is equipped with a specific fitness function encompassing both the task performance and domain shift. We contrast the performance, in migrating to unseen domains, of our method against a number of classical feature selection methods without any transfer learning mechanism. Moreover, in the experimental result section, we analyze how different features are selected under different settings. The results show that using invariant features leads to a better generalization of the machine learning models to an unseen domain.

Evolutionary Algorithms (EAs) are often challenging to apply in real-world settings since evolutionary computations involve a large number of evaluations of a typically expensive fitness function. For example, an evaluation could involve training a new machine learning model. An approximation (also known as meta-model or a surrogate) of the true function can be used in such applications to alleviate the computation cost. In this paper, we propose a two-stage surrogate-assisted evolutionary approach to address the computational issues arising from using Genetic Algorithm (GA) for feature selection in a wrapper setting for large datasets. We define “Approximation Usefulness” to capture the necessary conditions to ensure correctness of the EA computations when an approximation is used. Based on this definition, we propose a procedure to construct a lightweight qualitative meta-model by the active selection of data instances. We then use a meta-model to carry out the feature selection task. We apply this procedure to the GA-based algorithm CHC (Cross generational elitist selection, Heterogeneous recombination and Cataclysmic mutation) to create a Qualitative approXimations variant, CHC_QX. We show that CHC_QX converges faster to feature subset solutions of significantly higher accuracy (as compared to CHC), particularly for large datasets with over 100K instances. We also demonstrate the applicability of the thinking behind our approach more broadly to Swarm Intelligence (SI), another branch of the Evolutionary Computation (EC) paradigm with results of PSO_QX, a qualitative approximation adaptation of the Particle Swarm Optimization (PSO) method. A GitHub repository with the complete implementation is available. © 2022 The Author(s)

Feature selection is an intractable problem, therefore practical algorithms often trade off the solution accuracy against the computation time. In this paper, we propose a novel multi-stage feature selection framework utilizing multiple levels of approximations, or surrogates. Such a framework allows for using wrapper approaches in a much more computationally efficient way, significantly increasing the quality of feature selection solutions achievable, especially on large datasets. We design and evaluate a Surrogate-Assisted Genetic Algorithm (SAGA) which utilizes this concept to guide the evolutionary search during the early phase of exploration. SAGA only switches to evaluating the original function at the final exploitation phase.

We prove that the run-time upper bound of SAGA surrogate-assisted stage is at worse equal to the wrapper GA, and it scales better for induction algorithms of high order of complexity in number of instances. We demonstrate, using 14 datasets from the UCI ML repository, that in practice SAGA significantly reduces the computation time compared to a baseline wrapper Genetic Algorithm (GA), while converging to solutions of significantly higher accuracy. Our experiments show that SAGA can arrive at near-optimal solutions three times faster than a wrapper GA, on average. We also showcase the importance of evolution control approach designed to prevent surrogates from misleading the evolutionary search towards false optima.

This paper investigates the effects of various randomization techniques on Deep Neural Networks (DNNs) learning performance. We categorize the existing randomness techniques into four key types: injection of noise/randomness at the data, model structure, optimization or learning stage. We use this classification to identify gaps in the current coverage of potential mechanisms for the introduction of randomness, leading to proposing two new techniques: adding noise to the loss function and random masking of the gradient updates. We use a Particle Swarm Optimizer (PSO) for hyperparameter optimization and evaluate over 30,000 configurations across standard computer vision benchmarks. Our study reveals that data augmentation and weight initialization randomness significantly improve performance, and different optimizers prefer distinct randomization types. The complete implementation and dataset are available on GitHub1. This paper for the Hot-off-the-Press track at GECCO 2024 summarizes the original work published at [2]. © 2024 Copyright held by the owner/author(s).

[2] Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, Peyman Sheikholharam Mashhadi, and Julia Handl. 2024. Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks. Information Sciences 667 (2024), 120500.

This paper presents a comprehensive empirical investigation into the interactions between various randomness techniques in Deep Neural Networks (DNNs) and how they contribute to network performance. It is well-established that injecting randomness into the training process of DNNs, through various approaches at different stages, is often beneficial for reducing overfitting and improving generalization. However, the interactions between randomness techniques such as weight noise, dropout, and many others remain poorly understood. Consequently, it is challenging to determine which methods can be effectively combined to optimize DNN performance. To address this issue, we categorize the existing randomness techniques into four key types: data, model, optimization, and learning. We use this classification to identify gaps in the current coverage of potential mechanisms for the introduction of noise, leading to proposing two new techniques: adding noise to the loss function and random masking of the gradient updates.

In our empirical study, we employ a Particle Swarm Optimizer (PSO) to explore the space of possible configurations to answer where and how much randomness should be injected to maximize DNN performance. We assess the impact of various types and levels of randomness for DNN architectures applied to standard computer vision benchmarks: MNIST, FASHION-MNIST, CIFAR10, and CIFAR100. Across more than 30\,000 evaluated configurations, we perform a detailed examination of the interactions between randomness techniques and their combined impact on DNN performance. Our findings reveal that randomness in data augmentation and in weight initialization are the main contributors to performance improvement. Additionally, correlation analysis demonstrates that different optimizers, such as Adam and Gradient Descent with Momentum, prefer distinct types of randomization during the training process. A GitHub repository with the complete implementation and generated dataset is available. © 2024 The Author(s)

We propose a two-stage surrogate-assisted evolutionary approach to address the computational issues arising from using Genetic Algorithm (GA) for feature selection in a wrapper setting for large datasets. The proposed approach involves constructing a lightweight qualitative meta-model by sub-sampling data instances and then using this meta-model to carry out the feature selection task. We define "Approximation Usefulness" to capture the necessary conditions that allow the meta-model to lead the evolutionary computations to the correct maximum of the fitness function. Based on our procedure we create CHC_QX a Qualitative approXimations variant of the GA-based algorithm CHC (Cross generational elitist selection, Heterogeneous recombination and Cataclysmic mutation). We show that CHC_QX converges faster to feature subset solutions of significantly higher accuracy, particularly for large datasets with over 100K instances. We also demonstrate the applicability of our approach to Swarm Intelligence (SI), with results of PSO_QX, a qualitative approximation adaptation of the Particle Swarm Optimization (PSO) method. A GitHub repository with the complete implementation is available². This paper for the Hot-off-the-Press track at GECCO 2023 summarizes the original work published at [3].

References

[1] Mohammed Ghaith Altarabichi, Yuantao Fan, Sepideh Pashami, Peyman Sheikholharam Mashhadi, and Sławomir Nowaczyk. 2021. Extracting invariant features for predicting state of health of batteries in hybrid energy buses. In 2021 ieee 8th international conference on data science and advanced analytics (dsaa). IEEE, 1–6.

[2] Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, and Peyman Sheikholharam Mashhadi. 2021. Surrogate-assisted genetic algorithm for wrapper feature selection. In 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 776–785.

[3] Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, and Peyman Sheikholharam Mashhadi. 2023. Fast Genetic Algorithm for feature selection—A qualitative approximation approach. Expert systems with applications 211 (2023), 118528.

© 2023 Copyright held by the owner/author(s).

Monitoring the condition, detecting faults, and modeling the degradation of industrial equipment are important challenges in Prognostics and Health Management (PHM) field. Our solution to the challenge demonstrated a multi-stage approach for detecting faults in a group of identical industrial equipment, composed of four identical interconnected components, that have been deployed to the evolving environment with changes in operational and environmental conditions. In the first stage, a stacked ensemble of heterogeneous classifiers was applied to predict the state of each component of the equipment individually. In the second stage, a low pass filter was applied to smoothen the predictions cast by stacked ensembles, utilizing temporal information of the prediction sequence. © ESREL2020-PSAM15 Organizers. Published by Research Publishing, Singapore.

In many practical applications data used for training a machine learning model and the deployment data does not always preserve the same distribution. Transfer learning and, in particular, domain adaptation allows to overcome this issue, by adapting the source model to a new target data distribution and therefore generalizing the knowledge from source to target domain. In this work, we present a method that makes the adaptation process more transparent by providing two complementary explanation mechanisms. The first mechanism explains how the source and target distributions are aligned in the latent space of the domain adaptation model. The second mechanism provides descriptive explanations on how the decision boundary changes in the adapted model with respect to the source model. Along with a description of a method, we also provide initial results obtained on publicly available, real-life dataset. © The Author(s) 2024.

Most existing work in information fusion focuses on combining information with well-defined meaning towards a concrete, pre-specified goal. In contradistinction, we instead aim for autonomous discovery of high-level knowledge from ubiquitous data streams. This paper introduces a method for recognition and tracking of hidden conceptual modes, which are essential to fully understand the operation of complex environments. We consider a scenario of analyzing usage of a fleet of city buses, where the objective is to automatically discover and track modes such as highway route, heavy traffic, or aggressive driver, based on available on-board signals. The method we propose is based on aggregating the data over time, since the high-level modes are only apparent in the longer perspective. We search through different features and subsets of the data, and identify those that lead to good clusterings, interpreting those clusters as initial, rough models of the prospective modes. We utilize Bayesian tracking in order to continuously improve the parameters of those models, based on the new data, while at the same time following how the modes evolve over time. Experiments with artificial data of varying degrees of complexity, as well as on real-world datasets, prove the effectiveness of the proposed method in accurately discovering the modes and in identifying which one best explains the current observations from multiple data streams. © 2017 Elsevier B.V. All rights reserved.

The majority of existing machine learning algorithms assume that training examples are already represented with sufficiently good features, in practice ones that are designed manually. This traditional way of preprocessing the data is not only tedious and time consuming, but also not sufficient to capture all the different aspects of the available information. With big data phenomenon, this issue is only going to grow, as the data is rarely collected and analyzed with a specific purpose in mind, and more often re-used for solving different problems. Moreover, the expert knowledge about the problem which allows them to come up with good representations does not necessarily generalize to other tasks. Therefore, much focus has been put on designing methods that can automatically learn features or representations of the data instead of learning from handcrafted features. However, a lot of this work used ad hoc methods and the theoretical understanding in this area is lacking.

We introduce an LSTM-based method for predicting compressor failures using aggregated sensory data, and evaluate it using historical information from over 1000 heavy duty vehicles during 2015 and 2016. The goal is to proactively identify trucks that will require maintenance in the near future, so that component replacement can be scheduled before the failure happens, translating into improved uptime. The problem is formulated as a classification task of whether a compressor failure will happen within the specified prediction horizon. A recurrent neural network using Long Short-Term Memory (LSTM) architecture is employed as the prediction model, and compared against Random Forest (RF), the solution used in industrial deployment at the moment. Experimental results show that while Random Forest slightly outperforms LSTM in terms of AUC score, the predictions of LSTM stay significantly more stable over time, showing a consistent trend from healthy to faulty class. Additionally, LSTM is also better at detecting the switch from faulty class to the healthy one after a repair. We demonstrate that this stability is important for making repair decisions, especially in questionable cases, and therefore LSTM model is likely to lead to better results in practice. © Springer Nature Switzerland AG 2019

Machine activity recognition is important for accurately esti- mating machine productivity and machine maintenance needs. In this paper, we present ongoing work on how to recognize activities of forklift trucks from on-board data streaming on the controller area network. We show that such recognition works across different sites. We first demon- strate the baseline classification performance of a Random Forest that uses 14 signals over 20 time steps, for a 280-dimensional input. Next, we show how a deep neural network can learn low-dimensional representa- tions that, with fine-tuning, achieve comparable accuracy. The proposed representation achieves machine activity recognition. Also, it visualizes the forklift operation over time and illustrates the relationships across different activities. © Springer Nature Switzerland AG 2020

Machine Activity Recognition (MAR) can be used to monitor manufacturing processes and find bottlenecks and potential for improvement in production. Several interesting results on MAR techniques have been produced in the last decade, but mostly on construction equipment. Forklift trucks, which are ubiquitous and highly important industrial machines, have been missing from the MAR research. This paper presents a data-driven method for forklift activity recognition that uses Controller Area Network (CAN) signals and semi-supervised learning (SSL). The SSL enables the utilization of large quantities of unlabeled operation data to build better classifiers; after a two-step post-processing, the recognition results achieve balanced accuracy of 88% for driving activities and 95% for load-handling activities on a hold-out data set. In terms of the Matthews correlation coefficient for five activity classes, the final score is 0.82, which is equal to the recognition results of two non-domain experts who use videos of the activities. A particular success is that context can be used to capture the transport of small weight loads that are not detected by the forklift’s built-in weight sensor. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

The success of domain adaptation relies on high-quality labeled data from the source domain, which is a luxury setup for applied machine learning problems. This article investigates a particular challenge: the source labeled data are neither plentiful nor sufficiently representative. We studied the challenge of limited data with an industrial application, i.e., forklift truck activity recognition. The task is to develop data-driven methods to recognize forklift usage performed in different warehouses with a large scale of signals collected from the onboard sensors. The preliminary results show that using pseudo-labeled data from the source domain can significantly improve classification performance on the target domain in some tasks. As the real-world problems are much more complex than typical research settings, it is not clearly understood in what circumstance the improvement may occur. Therefore, we provided discussions regarding this phenomenon and shared several inspirations on the difficulty of understanding and debugging domain adaptation problems in practice. © 2023 IEEE.

Research on machine activity recognition (MAR) is drawing more attention because MAR can provide productivity monitoring for efficiency optimization, better maintenance scheduling, product design improvement, and potential material savings. A particular challenge of MAR for human-operated machines is the overlap when transiting from one activity to another: during transitions, operators often perform two activities simultaneously, e.g., lifting the fork already while approaching a rack, so the exact time when one activity ends and another begins is uncertain. Machine learning models are often uncertain during such activity transitions, and we propose a novel ensemble-based method adapted to fuzzy transitions in a forklift MAR problem. Unlike traditional ensembles, where models in the ensemble are trained on different subsets of data, or with costs that force them to be diverse in their responses, our approach is to train a single model that predicts several activity labels, each under a different context. These individual predictions are not made by independent networks but are made using a structure that allows for sharing important features, i.e., a context ensemble. The results show that the gated recurrent unit network can provide medium or strong confident context ensembles for 95% of the cases in the test set, and the final forklift MAR result achieves accuracies of 97% for driving and 90% for load-handling activities. This study is the first to highlight the overlapping activity issue in MAR problems and to demonstrate that the recognition results can be significantly improved by designing a machine learning framework that addresses this issue. © 2023 The Author(s)

The phrase “most cruel and revolting crimes” has been used to describe some poor historical treatment of vulnerable impaired persons by precisely those who should have had the responsibility of protecting and helping them. We believe we might be poised to see history repeat itself, as increasingly humanlike aware robots become capable of engaging in behavior which we would consider immoral in a human–either unknowingly or deliberately. In the current paper we focus in particular on exploring some potential dangers affecting persons with dementia (PWD), which could arise from insufficient software or external factors, and describe a proposed solution involving rich causal models and accountability measures: Specifically, the Consequences of Needs-driven Dementia-compromised Behaviour model (C-NDB) could be adapted to be used with conversation topic detection, causal networks and multi-criteria decision making, alongside reports, audits, and deterrents. Our aim is that the considerations raised could help inform the design of care robots intended to support well-being in PWD.

What would happen in a world where people could "see'' others' hidden emotions directly through some visualizing technology Would lies become uncommon and would we understand each other better Or to the contrary, would such forced honesty make it impossible for a society to exist The science fiction television show Black Mirror has exposed a number of darker scenarios in which such futuristic technologies, by blurring the lines of what is private and what is not, could also catalyze suffering. Thus, the current paper first turns an eye towards identifying some potential pitfalls in emotion visualization which could lead to psychological or physical harm, miscommunication, and disempowerment. Then, some countermeasures are proposed and discussed--including some level of control over what is visualized and provision of suitably rich emotional information comprising intentions--toward facilitating a future in which emotion visualization could contribute toward people's well-being. The scenarios presented here are not limited to web technologies, since one typically thinks about emotion recognition primarily in the context of direct contact. However, as interfaces develop beyond today's keyboard and monitor, more information becomes available also at a distance--for example, speech-to-text software could evolve to annotate any dictated text with a speaker's emotional state.

Trucks are designed, configured and marketed for various working environments. There lies a concern whether trucks are used as intended by the manufacturer, as usage may impact the longevity, efficiency and productivity of the trucks. In this paper we propose a framework that aims to extract costumers' vehicle behaviours from Logged Vehicle Data (LVD) in order to evaluate whether they align with vehicle configurations, so-called Global Transport Application (GTA) parameters. Gaussian mixture model (GMM)s are employed to cluster and classify various vehicle behaviors from the LVD. Rule-based machine learning (RBML) was applied on the clusters to examine whether vehicle behaviors follow the GTA configuration. Particularly, we propose an approach based on studying associations that is able to extract insights on whether the trucks are used as intended. Experimental results shown that while for the vast majority of the trucks' behaviors seemingly follows their GTA configuration, there are also interesting outliers that warrant further analysis. © 2020 ACM.

This study applies a data-driven anomaly detection framework based on a Long Short-Term Memory (LSTM) autoencoder network for several subsystems of a public transport bus. The proposed framework efficiently detects abnormal data, significantly reducing the false alarm rate compared to available alternatives. Using historical repair records, we demonstrate how detection of abnormal sequences in the signals can be used for predicting equipment failures. The deviations from normal operation patterns are detected by analysing the data collected from several on-board sensors (e.g., wet tank air pressure, engine speed, engine load) installed on the bus. The performance of LSTM autoencoder (LSTM-AE) is compared against the multi-layer autoencoder (mlAE) network in the same anomaly detection framework. The experimental results show that the performance indicators of the LSTM-AE network, in terms of F1 Score, Recall, and Precision, are better than those of the mlAE network. © 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

One of the main challenges for predictive maintenance in real applications is the quality of the data, especially the labels. In this paper, we propose a methodology to filter out the misleading labels that harm the performance of Machine Learning models. Ideally, predictive maintenance would be based on the information of when a fault has occurred in a machine and what specific type of fault it was. Then, we could train machine learning models to identify the symptoms of such fault before it leads to a breakdown. However, in many industrial applications, this information is not available. Instead, we approximate it using a log of component replacements, usually coming from the sales or maintenance departments. The repair history provides reliable labels for fault prediction models only if the replaced component was indeed faulty, with symptoms captured by collected data, and it was going to lead to a breakdown.

However, very often, at least for complex equipment, this assumption does not hold. Models trained using unreliable labels will then, necessarily, fail. We demonstrate that filtering misleading labels leads to improved results. Our central claim is that the same fault, happening several times, should have similar symptoms in the data; thus, we can train a model to predict them. On the contrary, replacements of the same component that do not exhibit similar symptoms will be confusing and harm the ML models. Therefore, we aim to filter the maintenance operations, keeping only those that can be used to predict each other. Suppose we can train a successful model using the data before a component replacement to predict another component replacement. In that case, those maintenance operations must be motivated by the same, or a very similar, type of fault.

We test this approach on a real scenario using data from a fleet of sterilizers deployed in hospitals. The data includes sensor readings from the machines describing their operations and the service logs indicating the replacement of components when the manufacturing company performs the service. Since sterilizers are complex machines consisting of many components and systems interacting with each other, there is the possibility of faults happening simultaneously.

This paper formulates the problem of predictive maintenance for complex systems as a hierarchical multi-class classification task. This formulation is useful for equipment with multiple sub-systems and components performing heterogeneous tasks. Often, the data available describes the whole system's operation and is not ideal for accurate condition monitoring. In this setup, specialized predictive models analyzing one component at a time rarely perform much better than random. However, using machine learning and hierarchical approaches, we can still exploit the data to build a fault isolation system that provides measurable benefits for technicians in the field. We propose a method for creating a taxonomy of components to train hierarchical classifiers that aim to identify the faulty component. The output of this model is a structured set of predictions with different probabilities for each component. In this setup, traditional machine learning metrics fail to capture the relationship between the performance of the models and its usefulness in the field.We introduce a new metric to evaluate our approach's benefits; it measures the number of tests a technician needs to perform before pinpointing the faulty component. Using a dataset from a real-case problem coming fro the automotive industry, we demonstrate how traditional machine learning performance metrics, like accuracy, fail to capture practical benefits. Our proposed hierarchical approach succeeds in exploiting the information in the data and outperforms non-hierarchical machine learning solutions. In addition, we can identify the weakest link of our fault isolation model, allowing us to improve it efficiently.

The field of predictive maintenance for complex machinery with multiple possible faults is an important but largely unexplored area. In general, one assumes, often implicitly, the existence of monitoring data specific enough to capture every possible fault independently from all the others.

In this paper, we focus on the problem of predicting time-to-failure, or remaining useful life, in situations where the above assumption does not hold. Specifically, what happens when the data is not good enough to uniquely predict every fault, and, more importantly, what happens when different faults share the same symptoms on the recorded data.

We demonstrate that prognostics approaches learning independent models for each fault are inadequate. In particular, in the presence of faults that produce similar failure patterns, they produce false alarms disproportionately often or miss the majority of failures. 

We propose the HMP framework (Hierarchical Multi-fault Prognosis) to solve this problem by extracting a hierarchy of faults based on the similarity of the data they produce. At each node of the hierarchy, we train a regression model to predict the time-to-failure for any of the faults contained in this node. The intuition is that while it might be impossible to predict individual time-to-failure in the presence of similar faults, a model trained on aggregated data can still provide useful information. We demonstrate through experiments the validity of our approach.

In classification problems, as the number of classes increases, correctly classifying a new instance into one of them is assumed to be more challenging than making the same decision in the presence of fewer classes. The essence of the problem is that using the learning algorithm on each decision boundary individually is better than using the same learning algorithm on several of them simultaneously. However, why and when it happens is still not well-understood today. This work’s main contribution is to introduce the concept of heterogeneity of decision boundaries as an explanation of this phenomenon. Based on the definition of heterogeneity of decision boundaries, we analyze and explain the differences in the performance of state of the art approaches to solve multi-class classification. We demonstrate that as the heterogeneity increases, the performances of all approaches, except one-vs-one, decrease. We show that by correctly encoding the knowledge of the heterogeneity of decision boundaries in a decomposition of the multi-class problem, we can obtain better results than state of the art decompositions. The benefits can be an increase in classification performance or a decrease in the time it takes to train and evaluate the models. We first provide intuitions and illustrate the effects of the heterogeneity of decision boundaries using synthetic datasets and a simplistic classifier. Then, we demonstrate how a real dataset exhibits these same principles, also under realistic learning algorithms. In this setting, we devise a method to quantify the heterogeneity of different decision boundaries, and use it to decompose the multi-class problem. The results show significant improvements over state-of-the-art decompositions that do not take the heterogeneity of decision boundaries into account. © 2013 IEEE.

Using hierarchies of classes is one of the standard methods to solve multi-class classification problems. In the literature, selecting the right hierarchy is considered to play a key role in improving classification performance. Although different methods have been proposed, there is still a lack of understanding of what makes a hierarchy good and what makes a method to extract hierarchies perform better or worse.

To this effect, we analyze and compare some of the most popular approaches to extracting hierarchies. We identify some common pitfalls that may lead practitioners to make misleading conclusions about their methods.To address some of these problems, we demonstrate that using random hierarchies is an appropriate benchmark to assess how the hierarchy's quality affects the classification performance.

In particular, we show how the hierarchy's quality can become irrelevant depending on the experimental setup: when using powerful enough classifiers, the final performance is not affected by the quality of the hierarchy. We also show how comparing the effect of the hierarchies against non-hierarchical approaches might incorrectly indicate their superiority.

Our results confirm that datasets with a high number of classes generally present complex structures in how these classes relate to each other. In these datasets, the right hierarchy can dramatically improve classification performance.

Smart Cities and Communities (SCC) constitute a new paradigm in urban development. SCC ideates on a data-centered society aiming at improving efficiency by automating and optimizing activities and utilities. Information and communication technology along with internet of things enables data collection and with the help of artificial intelligence (AI) situation awareness can be obtained to feed the SCC actors with enriched knowledge. This paper describes AI perspectives in SCC and gives an overview of AI-based technologies used in traffic to enable road vehicle automation and smart traffic control. Perception, Smart Traffic Control and Driver Modelling are described along with open research challenges and standardization to help introduce advanced driver assistance systems and automated vehicle functionality in traffic. To fully realize the potential of SCC, to create a holistic view on a city level, the availability of data from different stakeholders is need. Further, though AI technologies provide accurate predictions and classifications there is an ambiguity regarding the correctness of their outputs. This can make it difficult for the human operator to trust the system. Today there are no methods that can be used to match function requirements with the level of detail in data annotation in order to train an accurate model. Another challenge related to trust is explainability, while the models have difficulties explaining how they come to a certain conclusions it is difficult for humans to trust it. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Batteries are a safety-critical and the most expensive component for electric buses (EBs). Monitoring their condition, or the state of health (SoH), is crucial for ensuring the reliability of EB operation. However, EBs come in many models and variants, including different mechanical configurations, and deploy to operate under various conditions. Developing new degradation models for each combination of settings and faults quickly becomes challenging due to the unavailability of data for novel conditions and the low evidence for less popular vehicle populations. Therefore, building machine learning models that can generalize to new and unseen settings becomes a vital challenge for practical deployment. This study aims to develop and evaluate feature selection methods for robust machine learning models that allow estimating the SoH of batteries across various settings of EB configuration and usage. Building on our previous work, we propose two approaches, a genetic algorithm for domain invariant features (GADIF) and causal discovery for selecting invariant features (CDIF). Both aim to select features that are invariant across multiple domains. While GADIF utilizes a specific fitness function encompassing both task performance and domain shift, the CDIF identifies pairwise causal relations between features and selects the common causes of the target variable across domains. Experimental results confirm that selecting only invariant features leads to a better generalization of machine learning models to unseen domains. The contribution of this work comprises the two novel invariant feature selection methods, their evaluation on real-world EBs data, and a comparison against state-of-the-art invariant feature selection methods. Moreover, we analyze how the selected features vary under different settings. © 2024 Copyright for this paper by its authors.

Accurate energy consumption prediction is crucial for optimising the operation of electric commercial heavy-duty vehicles, particularly for efficient route planning, refining charging strategies, and ensuring optimal truck configuration for specific tasks. This study investigates the application of multi-task curriculum learning to enhance machine learning models for forecasting the energy consumption of various onboard systems in electric vehicles. Multi-task learning, unlike traditional training approaches, leverages auxiliary tasks to provide additional training signals, which has been shown to enhance predictive performance in many domains. By further incorporating curriculum learning, where simpler tasks are learned before progressing to more complex ones, neural network training becomes more efficient and effective. We evaluate the suitability of these methodologies in the context of electric vehicle energy forecasting, examining whether the combination of multi-task learning and curriculum learning enhances algorithm generalisation, even with limited training data. We primarily focus on understanding the efficacy of different curriculum learning strategies, including sequential learning and progressive continual learning, using complex, real-world industrial data. Our research further explores a set of auxiliary tasks designed to facilitate the learning process by targeting key consumption characteristics projected into future time frames. The findings illustrate the potential of multi-task curriculum learning to advance energy consumption forecasting, significantly contributing to the optimisation of electric heavy-duty vehicle operations. This work offers a novel perspective on integrating advanced machine learning techniques to enhance energy efficiency in the exciting field of electromobility. © 2024 Copyright for this paper by its authors.

The field of Explainable Predictive Maintenance (PM) is concerned with developing methods that can clarify how AI systems operate in the PM domain. One of the challenges of creating maintenance plans is integrating AI output with human decision-making processes and expertise. For AI to be helpful and trustworthy, fault predictions must be contextualized and easily comprehensible to humans. This involves providing tailored explanations to different actors depending on their roles and needs. For example, engineers can be connected to technical installation blueprints, while managers can evaluate system downtime costs, and lawyers can assess safety-threatening failures' potential liability. In many industries, black-box AI systems analyze sensor data to predict failures by detecting anomalies and deviations from typical behavior with impressive accuracy. However, PM is just one part of a broader context that aims to identify the most probable causes, develop a recovery plan, and estimate remaining useful life while providing alternative solutions. Achieving this requires complex interactions among various actors in industrial and decision-making processes. Our tutorial explores current trends, and promising research directions in Explainable AI (XAI) relevant to Explainable Predictive Maintenance (XPM), and future challenges and open issues on this topic. We will also present three case studies that highlight XPM's challenges in bus and train operations and steel factories. © 2023 Owner/Author.

In the era of big data, it is imperative to assist the human analyst in the endeavor to find solutions to ill-defined problems, i.e. to “detect the expected and discover the unexpected” (Yi et al., 2008). To their aid, a plethora of analysis support systems is available to the analysts. However, these support systems often lack visual and interactive features, leaving the analysts with no opportunity to guide, influence and even understand the automatic reasoning performed and the data used. Yet, to be able to appropriately support the analysts in their sense-making process, we must look at this process more closely. In this paper, we present the results from interviews performed together with data analysts from the automotive industry where we have investigated how they handle the data, analyze it and make decisions based on the data, outlining directions for the development of analytical support systems within the area. © Springer International Publishing Switzerland 2016.

This paper demonstrates how to explore and visualize different types of structure in data, including clusters, anomalies, causal relations, and higher order relations. The methods are developed with the goal of being as automatic as possible and applicable to massive, streaming, and distributed data. Finally, a decentralized learning scheme is discussed, enabling finding structure in the data without collecting the data centrally.

Discovering causal relations from limited amounts of data can be useful for many applications. However, all causal discovery algorithms need huge amounts of data to estimate the underlying causal graph. To alleviate this gap, this paper proposes a novel visualization tool which incrementally discovers causal relations as more data becomes available. That is, we assume that stronger causal links will be detected quickly and weaker links revealed when enough data is available. In addition to causal links, the correlation between variables and the uncertainty of the strength of causal links are visualized in the same graph. The tool is illustrated on three example causal graphs, and results show that incremental discovery works and that the causal structure converges as more data becomes available. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Recent machine learning studies on tabular data show that ensembles of decision tree models are more efficient and performant than deep learning models such as Tabular Transformer models. However, as we demonstrate, these studies are limited in scope and do not paint the full picture. In this work, we focus on how two dataset properties, namely dataset size and feature complexity, affect the empirical performance comparison between tree ensembles and Tabular Transformer models. Specifically, we employ a hypothesis-driven approach and identify situations where Tabular Transformer models are expected to outperform tree ensemble models. Through empirical evaluation, we demonstrate that given large enough datasets, deep learning models perform better than tree models. This gets more pronounced when complex feature interactions exist in the given task and dataset, suggesting that one must pay careful attention to dataset properties when selecting a model for tabular data in machine learning – especially in an industrial setting, where larger and larger datasets with less and less carefully engineered features are becoming routinely available. © The Author(s)

[No abstract available]

In recent years, there have been many attentions in developing technologies with the aim of monitoring and predicting emerging issues such as break downs, component failures, and quality degradations e.g., R, Prytz et al. (2015), as a means to provide predictive maintenance solution in modern vehicle industries. These existing technologies exploit several fault predictions and diagnostic pipelines ranging from statistics methods to machine learning algorithms e.g., M, You et al. (2010), Y, Lei et al. (2016). However, these solutions have not particularly concentrated on the ability to predict the component failures and the cause of the failures taking into consideration vehicle usage patterns and history of failures over time in different seasons.

This is not a trivial task since modern vehicles with their huge functionalities and dependency among their components bring out a challenge to the manufacturer to plan their maintenance strategy in this complex domain. This is truly a complex challenge since failures can be sourced and affected by multiple features, which are highly related to each other and change over time in different contexts (e.g., location, time, season).  

Under such conditions, an advanced early prediction capability is desired, because manufacturers can exceedingly serve from early prediction of potential vehicle component failures, and more specifically the chain of the features and their dependencies which may lead to a failure over time in different seasons.  This is considered important due to the fact that different seasons may have a potential effect on certain component failures, so predicting these dependencies and the actual failure enables a higher level of maintenance for optimally planning and managing total cost and more importantly safety. 

In this study, we build a probabilistic prediction model in a time series, on top of vehicle usage pattern, which is represented by the Live Vehicle Data (LVD). LVD logged and captured using multiple sensors located in Volvo vehicles that includes usage and specification of the vehicles aggregated in a cumulative fashion. We exploit and apply a type of supervised machine learning algorithm called Bayesian Network N, Friedman. (1997), on the engineered LVD (we applied a type of data engineering process to extract hidden patterns from LVD), which is logged through different seasons. These result a very complex network of dependency in each time stamp that indicates how a failure sourced by different features and their quantitative influences. In addition, integrating all these networks reveal how the usage can influence failure over time. Moreover, the quantitative influences allow us to extract the main chain of effect on a failure. This is strongly beneficial for the manufacturers and maintenance strategy to find out the main reason of failures, which can be extracted by vehicle usage pattern during their operation. © ESREL2020-PSAM15 Organizers

Early detection of anomalies, trends and emerging patterns can be exploited to reduce the number and severity of quality problems in vehicles. This is crucially important since having a good understanding of the quality of the product leads to better designs in the future, and better maintenance to solve the current issues. To this end, the integration of large amounts of data that are logged during the vehicle operation can be used to build the model of usage patterns for early prediction. In this study, we have developed a machine learning system for warranty claims by integrating available information sources: Logged Vehicle Data (LVD) and Warranty Claims (WCs). The experimental results obtained from a large data set of heavy duty trucks are used to demonstrate the effectiveness of the proposed system to predict the warranty claims. © Springer Nature Switzerland AG 2019.

Many industries today are struggling with early identification of quality issues, given the shortening of product design cycles and the desire to decrease production costs, coupled with customers' requirement for high uptime. The vehicle industry is no exception, as breakdowns often lead to on-road stops and delays in delivery missions. In this paper we consider quality issues to be an unexpected increase in failure rates of a particular component; those are particularly problematic for the Original Equipment Manufacturers (OEMs) since they lead to unplanned costs and can significantly affect brand value. We propose a new approach towards the early detection of quality issues using Machine Learning (ML) to forecast the failures of a given component across the large population of units.

In this study, we combine the usage information of vehicles with the records of their failures. The former is continuously collected, as the usage statistics are transmitted over telematics connections. The latter is based on invoice and warranty information collected in the workshops. We compare two different ML approaches: the first is an auto-regression model of the failure ratios for vehicles based on past information, while the second is the aggregation of individual vehicle failure predictions based on their individual usage.

We present experimental evaluations on the real data captured from heavy-duty trucks demonstrating how these two formulations have complementary strengths and weaknesses; in particular, they can outperform each other given different volumes of the data. The classification approach surpasses the regressor model whenever enough data is available, i.e., once the vehicles are in-service for a longer time. On the other hand, the regression shows better predictive performance with a smaller amount of data, i.e., for vehicles that have been deployed recently.  © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

Many methods have been proposed over the years for distinguishing causes from effects using observational data only, and new ones are continuously being developed – deducing causal relationships is difficult enough that we do not hope to ever get the perfect one. Instead, we progress by creating powerful heuristics, capable of capturing more and more of the hints that are present in real data.

One type of such hints, quite surprisingly rarely explicitly addressed by existing methods, is in-homogeneities in the data. Clusters are a very typical occurrence that should be taken into account, and exploited, in the process of identifying causes and effects. In this paper, we discuss the potential benefits, and explore the hints that clusters in the data can provide for causal discovery. We propose a new method, and show, using both artificial and real data, that accounting for clusters in the data leads to more accurate learning of causal structures.

Predicting future maintenance needs of equipment can be addressed in a variety of ways. Methods based on machine learning approaches provide an interesting platform for mining large data sets to find patterns that might correlate with a given fault. In this paper, we approach predictive maintenance as a classification problem and use Random Forest to separate data readouts within a particular time window into those corresponding to faulty and non-faulty component categories. We utilize diagnostic trouble codes (DTCs) as an example of event-based data, and propose four categories of features that can be derived from DTCs as a predictive maintenance framework. We test the approach using large-scale data from a fleet of heavy duty trucks, and show that DTCs can be used within our framework as indicators of imminent failures in different components.

The advancements of the telematics and connectivity solutions have provided new opportunities for the field of predictive maintenance. The number of sensors installed on a vehicle is increasing over time, and manufacturers are looking for new ways to improve the uptime of their fleet while at the same time reducing the costs related to unexpected breakdowns. The nature of the aggregated data from vehicles is sequential, and it is interesting to investigate existing methods for modeling partially observable state sequences to detect common patterns of failure. In this paper, we introduce a new approach for predicting turbocharger failures of Volvo trucks. The first step of the method deals with modeling a sequence of readouts from each vehicle using a Markov process. To do so, we identify the most informative signals and then employ spatial similarity clustering on the readouts. We interpret each cluster as a Markov state and further convert the history of a truck into a trajectory of states. This trajectory is then aligned with repairs information to form a standard sequence labeling problem. Finally, we train a hidden Markov model (HMM) classifier for assessing the health condition of the equipment. Empirical evaluations obtained on our realworld dataset of trucks suggest that the proposed method improves the AUC score of the final system up to 6% for predicting failures of a turbocharger.

Mobility as a Service (MaaS) is a relatively new domain where new types of knowledge systems have recently emerged. It combines various modes of transportation and different kinds of data to present personalized services to travellers based on transport needs. A knowledge-based framework based on Artificial Intelligence (AI) is proposed in this paper to integrate, analyze, and process different types of mobility data. The framework includes a knowledge acquisition process to extract and structure data from various sources, including mobility experts and add new information to a knowledge base. The role of AI in this framework is to aid in automatically discovering knowledge from various data sets and recommend efficient and personalized mobility services with explanations. A scenario is also presented to demonstrate the interaction of the proposed framework’s modules.

Mobility as a Service (MaaS) combines various modes of transportation to present mobility services to travellers based on their transport needs. This paper proposes a knowledge-based framework based on Artificial Intelligence (AI) to integrate various mobility data types and provide travellers with customized services. The proposed framework includes a knowledge acquisition process to extract and structure data from multiple sources of information (such as mobility experts and weather data). It also adds new information to a knowledge base and improves the quality of previously acquired knowledge. We discuss how AI can help discover knowledge from various data sources and recommend sustainable and personalized mobility services with explanations. The proposed knowledge-based AI framework is implemented using a synthetic dataset as a proof of concept. Combining different information sources to generate valuable knowledge is identified as one of the challenges in this study. Finally, explanations of the proposed decisions provide a criterion for evaluating and understanding the proposed knowledge-based AI framework. © 2023 by the authors.

The first Workshop on Interactive Data Mining is held in Melbourne, Australia, on February 15, 2019 and is co-located with 12th ACM International Conference on Web Search and Data Mining (WSDM 2019). The goal of this workshop is to share and discuss research and projects that focus on interaction with and interactivity of data mining systems. The program includes invited speaker, presentation of research papers, and a discussion session.

Ensemble learning methods combine multiple models to improve performance by exploiting their diversity. The success of these approaches relies heavily on the dissimilarity of the base models forming the ensemble. This diversity can be achieved in many ways, with well-known examples including bagging and boosting.

It is the diversity of the models within an ensemble that allows the ensemble to correct the errors made by its members, and consequently leads to higher classification or regression performance. A mistake made by a base model can only be rectified if other members behave differently on that particular instance, and provide the aggregator with enough information to make an informed decision. On the contrary, lack of diversity not only lowers model performance, but also wastes computational resources. Nevertheless, in the current state of the art ensemble approaches, there is no guarantee on the level of diversity achieved, and no mechanism ensuring that each member will learn a different decision boundary from the others.

In this paper, we propose a parallel orthogonal deep learning architecture in which diversity is enforced by design, through imposing an orthogonality constraint. Multiple deep neural networks are created, parallel to each other. At each parallel layer, the outputs of different base models are subject to Gram–Schmidt orthogonalization. We demonstrate that this approach leads to a high level of diversity from two perspectives. First, the models make different errors on different parts of feature space, and second, they exhibit different levels of uncertainty in their decisions. Experimental results confirm the benefits of the proposed method, compared to standard deep learning models and well-known ensemble methods, in terms of diversity and, as a result, classification performance. © 2021 The Author(s). Published by Elsevier Ltd.

Predictive Maintenance (PM) is a proactive maintenance strategy that tries to minimize a system’s downtime by predicting failures before they happen. It uses data from sensors to measure the component’s state of health and make forecasts about its future degradation. However, existing PM methods typically focus on individual measurements. While it is natural to assume that a history of measurements carries more information than a single one. This paper aims at incorporating such information into PM models. In practice, especially in the automotive domain, diagnostic models have low performance, due to a large amount of noise in the data and limited sensing capability. To address this issue, this paper proposes to use a specific type of ensemble learning known as Stacked Ensemble. The idea is to aggregate predictions of multiple models—consisting of Long Short-Term Memory (LSTM) and Convolutional-LSTM—via a meta model, in order to boost performance. Stacked Ensemble model performs well when its base models are as diverse as possible. To this end, each such model is trained using a specific combination of the following three aspects: feature subsets, past dependency horizon, and model architectures. Experimental results demonstrate benefits of the proposed approach on a case study of heavy-duty truck turbochargers. © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).