Search

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures. We present the Continuous Convolutional Neural Network (CCNN): a single CNN able to process data of arbitrary resolution, dimensionality and length without any structural changes. Its key component are its continuous convolutional kernels which model long-range dependencies at every layer, and thus remove the need of current CNN architectures for task-dependent downsampling and depths. We showcase the generality of our method by using the same architecture for tasks on sequential ($1{\rm D}$), visual ($2{\rm D}$) and point-cloud ($3{\rm D}$) data. Our CCNN matches and often outperforms the current state-of-the-art across all tasks considered.

Nowadays, the deployment of deep learning models on edge devices for addressing real-world classification problems is becoming more prevalent. Moreover, there is a growing popularity in the approach of early classification, a technique that involves classifying the input data after observing only an early portion of it, aiming to achieve reduced communication and computation requirements, which are crucial parameters in edge intelligence environments. While early classification in the field of time series analysis has been broadly researched, existing solutions for multivariate time series problems primarily focus on early classification along the temporal dimension, treating the multiple input channels in a collective manner. In this study, we propose a more flexible early classification pipeline that offers a more granular consideration of input channels and extends the early classification paradigm to the channel dimension. To implement this method, we utilize reinforcement learning techniques and introduce constraints to ensure the feasibility and practicality of our objective. To validate its effectiveness, we conduct experiments using synthetic data and we also evaluate its performance on real datasets. The comprehensive results from our experiments demonstrate that, for multiple datasets, our method can enhance the early classification paradigm by achieving improved accuracy for equal input utilization.

no abstract available

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact., Comment: 12 pages

In the context of MDPs with high-dimensional states, reinforcement learning can achieve better results when using a compressed, low-dimensional representation of the original input space. A variety of learning objectives have therefore been used to learn useful representations. However, these representations usually lack interpretability of the different features. We propose a representation learning algorithm that is able to disentangle latent features into a controllable and an uncontrollable part. The resulting representations are easily interpretable and can be used for learning and planning efficiently by leveraging the specific properties of the two parts. To highlight the benefits of the approach, the disentangling properties of the algorithm are illustrated in three different environments., Comment: 14 pages (9 main paper pages), 9 figures

Novel prediction methods should always be compared to a baseline to know how well they perform. Without this frame of reference, the performance score of a model is basically meaningless. What does it mean when a model achieves an $F_1$ of 0.8 on a test set? A proper baseline is needed to evaluate the `goodness' of a performance score. Comparing with the latest state-of-the-art model is usually insightful. However, being state-of-the-art can change rapidly when newer models are developed. Contrary to an advanced model, a simple dummy classifier could be used. However, the latter could be beaten too easily, making the comparison less valuable. This paper presents a universal baseline method for all binary classification models, named the Dutch Draw (DD). This approach weighs simple classifiers and determines the best classifier to use as a baseline. We theoretically derive the DD baseline for many commonly used evaluation measures and show that in most situations it reduces to (almost) always predicting either zero or one. Summarizing, the DD baseline is: (1) general, as it is applicable to all binary classification problems; (2) simple, as it is quickly determined without training or parameter-tuning; (3) informative, as insightful conclusions can be drawn from the results. The DD baseline serves two purposes. First, to enable comparisons across research papers by this robust and universal baseline. Secondly, to provide a sanity check during the development process of a prediction model. It is a major warning sign when a model is outperformed by the DD baseline.

In current research, machine and deep learning solutions for the classification of temporal data are shifting from single-channel datasets (univariate) to problems with multiple channels of information (multivariate). The majority of these works are focused on the method novelty and architecture, and the format of the input data is often treated implicitly. Particularly, multivariate datasets are often treated as a stack of univariate time series in terms of input preprocessing, with scaling methods applied across each channel separately. In this evaluation, we aim to demonstrate that the additional channel dimension is far from trivial and different approaches to scaling can lead to significantly different results in the accuracy of a solution. To that end, we test seven different data transformation methods on four different temporal dimensions and study their effect on the classification accuracy of five recent methods. We show that, for the large majority of tested datasets, the best transformation-dimension configuration leads to an increase in the accuracy compared to the result of each model with the same hyperparameters and no scaling, ranging from 0.16 to 76.79 percentage points. We also show that if we keep the transformation method constant, there is a statistically significant difference in accuracy results when applying it across different dimensions, with accuracy differences ranging from 0.23 to 47.79 percentage points. Finally, we explore the relation of the transformation methods and dimensions to the classifiers, and we conclude that there is no prominent general trend, and the optimal configuration is dataset- and classifier-specific., Comment: IEEE ICMLA 2022

Additional file 1: Table S1. Parameter bounds. Table S2. Parameter categories. Table S3. Feature derivations. Table S4. Included features. Table S5. Hyper parameter optimization. Table S6. Feature Importance Metrics. Table S7. Patient characteristics. Table S8. ROC AUC score. Table S9. F1-score. Table S10. Sensitivity Analysis Minimal Prone Duration. Table S11. Sensitivity Analysis Cut-off Values. Table S12. Ranked Feature Importance. Table S13. Feature Importance Values. Figure S1. PaO2/FiO2 ratio difference in mmHg over time after starting prone position. Prone positions which continued for longer than 24 hours were filtered out.

Additional file 1: Figure S1. Patient selection. Figure S2. Selection of observations throughout the course of IMV. Figure S3. Nested cross-validation. Figure S4. Importance of the top 10 predictors for the prediction of ventilator free days, as well as the difference for predictors over time. Figure S5. SHAP plot ICU mortality (XGBoost). Figure S6. SHAP plot for ICU free days (XGBoost). Figure S7. SHAP plot for ventilator free days (XGBoost). Figure S8. PDPs. Table S1. Overview of all predictors used in the model with a definition where applicable. Table S2. Overall algorithm performance for each of the different outcomes. Table S3. Statistical results for a regression model per outcome. Table S4. Predictor correlations.

Additional file 3: Table S1. Overview of derived clinical score.

Time-series forecasting plays an important role in many domains. Boosted by the advances in Deep Learning algorithms, it has for instance been used to predict wind power for eolic energy production, stock market fluctuations, or motor overheating. In some of these tasks, we are interested in predicting accurately some particular moments which often are underrepresented in the dataset, resulting in a problem known as imbalanced regression. In the literature, while recognized as a challenging problem, limited attention has been devoted on how to handle the problem in a practical setting. In this paper, we put forward a general approach to analyze time-series forecasting problems focusing on those underrepresented moments to reduce imbalances. Our approach has been developed based on a case study in a large industrial company, which we use to exemplify the approach.

Additional file 1. Table S1 Overview of machine learning studies that investigate extubation readiness. Table S2 Model performance. Figure S1 PD-plot for BMI

Additional file 2. Institutional review board documentation.

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori. In this work, we show that all these problems can be solved by formulating convolutional kernels in CNNs as continuous functions. The resulting Continuous Kernel Convolution (CKConv) allows us to model arbitrarily long sequences in a parallel manner, within a single operation, and without relying on any form of recurrence. We show that Continuous Kernel Convolutional Networks (CKCNNs) obtain state-of-the-art results in multiple datasets, e.g., permuted MNIST, and, thanks to their continuous nature, are able to handle non-uniformly sampled datasets and irregularly-sampled data natively. CKCNNs match or perform better than neural ODEs designed for these purposes in a faster and simpler manner.

Inducing symmetry equivariance in deep neural architectures has resolved into improved data efficiency and generalization. In this work, we utilize the concept of scale and translation equivariance to tackle the problem of learning on time-series from raw waveforms. As a result, we obtain representations that largely resemble those of the wavelet transform at the first layer, but that evolve into much more descriptive ones as a function of depth. Our empirical results support the suitability of our Wavelet Networks which with a simple architecture design perform consistently better than CNNs on raw waveforms and on par with spectrogram-based methods.

Trace clustering has increasingly been applied to find homogenous process executions. However, current techniques have difficulties in finding a meaningful and insightful clustering of patients on the basis of healthcare data. The resulting clusters are often not in line with those of medical experts, nor do the clusters guarantee to help return meaningful process maps of patients' clinical pathways. After all, a single hospital may conduct thousands of distinct activities and generate millions of events per year. In this paper, we propose a novel trace clustering approach by using sample sets of patients provided by medical experts. More specifically, we learn frequent sequence patterns on a sample set, rank each patient based on the patterns, and use an automated approach to determine the corresponding cluster. We find each cluster separately, while the frequent sequence patterns are used to discover a process map. The approach is implemented in ProM and evaluated using a large data set obtained from a university medical center. The evaluation shows F1-scores of 0.7 for grouping kidney injury, 0.9 for diabetes, and 0.64 for head/neck tumor, while the process maps show meaningful behavioral patterns of the clinical pathways of these groups, according to the domain experts.

Clustering of users underlies many of the personalisation algorithms that are in use nowadays. Such clustering is mostly performed in an offline fashion. For a health and wellbeing setting, offline clustering might however not be suitable, as limited data is often available and patient states can also quickly evolve over time. Existing online clustering algorithms are not suitable for the health domain due to the type of data that involves multiple time series evolving over time. In this paper we propose a new online clustering algorithm called CluStream-GT that is suitable for health applications. By using both artificial and real datasets, we show that the approach is far more efficient compared to regular clustering, with an average speedup of 93%, while only losing 12% in the accuracy of the clustering with artificial data and 3% with real data.CCS CONCEPTS• Computing methodologies$\rightarrow$ Cluster analysis.

Trace clustering has increasingly been applied to find homogenous process executions. However, current techniques have difficulties in finding a meaningful and insightful clustering of patients on the basis of healthcare data. The resulting clusters are often not in line with those of medical experts, nor do the clusters guarantee to help return meaningful process maps of patients’ clinical pathways. After all, a single hospital may conduct thousands of distinct activities and generate millions of events per year. In this paper, we propose a novel trace clustering approach by using sample sets of patients provided by medical experts. More specifically, we learn frequent sequence patterns on a sample set, rank each patient based on the patterns, and use an automated approach to determine the corresponding cluster. We find each cluster separately, while the frequent sequence patterns are used to discover a process map. The approach is implemented in ProM and evaluated using a large data set obtained from a university medical center. The evaluation shows F1-scores of 0.7 for grouping kidney injury, 0.9 for diabetes, and 0.64 for head/neck tumor, while the process maps show meaningful behavioral patterns of the clinical pathways of these groups, according to the domain experts.

Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architectures consider the set of all possible transformations in a transformation group when learning feature representations. Contrarily, the human visual system is able to attend to the set of relevant transformations occurring in the environment and utilizes this information to assist and improve object recognition. Based on this observation, we modify conventional equivariant feature mappings such that they are able to attend to the set of co-occurring transformations in data and generalize this notion to act on groups consisting of multiple symmetries. We show that our proposed co-attentive equivariant neural networks consistently outperform conventional rotation equivariant and rotation & reflection equivariant neural networks on rotated MNIST and CIFAR-10., Proceedings of the 8th International Conference on Learning Representations (ICLR), 2020

Trace clustering has increasingly been applied to find homogenous process executions. However, current techniques have difficulties in finding a meaningful and insightful clustering of patients on the basis of healthcare data. The resulting clusters are often not in line with those of medical experts, nor do the clusters guarantee to help return meaningful process maps of patients’ clinical pathways. After all, a single hospital may conduct thousands of distinct activities and generate millions of events per year. In this paper, we propose a novel trace clustering approach by using sample sets of patients provided by medical experts. More specifically, we learn frequent sequence patterns on a sample set, rank each patient based on the patterns, and use an automated approach to determine the corresponding cluster. We find each cluster separately, while the frequent sequence patterns are used to discover a process map. The approach is implemented in ProM and evaluated using a large data set obtained from a university medical center. The evaluation shows F1-scores of 0.7 for grouping kidney injury, 0.9 for diabetes, and 0.64 for head/neck tumor, while the process maps show meaningful behavioral patterns of the clinical pathways of these groups, according to the domain experts.

Personalization is very powerful in improving the effectiveness of health interventions. Reinforcement learning (RL) algorithms are suitable for learning these tailored interventions from sequential data collected about individuals. However, learning can be very fragile. The time to learn intervention policies is limited as disengagement from the user can occur quickly. Also, in e-Health intervention timing can be crucial before the optimal window passes. We present an approach that learns tailored personalization policies for groups of users by combining RL and clustering. The benefits are two-fold: speeding up the learning to prevent disengagement while maintaining a high level of personalization. Our clustering approach utilizes dynamic time warping to compare user trajectories consisting of states and rewards. We apply online and batch RL to learn policies over clusters of individuals and introduce our self-developed and publicly available simulator for e-Health interventions to evaluate our approach. We compare our methods with an e-Health intervention benchmark. We demonstrate that batch learning outperforms online learning for our setting. Furthermore, our proposed clustering approach for RL finds near-optimal clusterings which lead to significantly better policies in terms of cumulative reward compared to learning a policy per individual or learning one non-personalized policy across all individuals. Our findings also indicate that the learned policies accurately learn to send interventions at the right moments and that the users workout more and at the right times of the day.

Research has shown that personalization of health interventions can contribute to an improved effectiveness. Reinforcement learning algorithms can be used to perform such tailoring. In this paper, we present a cluster-based reinforcement learning approach which learns optimal policies for groups of users. Such an approach can speed up the learning process while still giving a level of personalization. We apply both online and batch learning to learn policies over the clusters and introduce a publicly available simulator which we have developed to evaluate the approach. The results show batch learning significantly outperforms online learning. Furthermore, near-optimal clustering is found which proves to be beneficial in learning significantly better policies compared to learning per user and learning across all users.

Gaining insight on the effect of policies upon the agricultural domain is essential for policy makers, famers and the agribusiness sector. A variety of models have therefore been developed that enable a prediction of agricultural development under different policies. Most models do however not make predictions on a fine grained level and are weak in accounting for specific factor market and resource constraints farmers (agents) face at farm level. The paper presents an agent-based model where each farm is modeled by means of an agent and studies the effect of milk quota abolishment. Two simulations policy simulations are made: 1) abolition of the milk quota; and 2) land-tied sustainable dairy scenario. Outcomes are analyzed and compared with the predictions of sector models.

One of the unique features of the organization in honey bee societies is the ability to adapt to environmental circumstances in a highly decentralized way. This adaptation takes the form of changes in the allocation of bees to roles, whereby bees individually decide to take up certain roles that require attention. Within the domain of computational modeling of multiagent systems, a trend has developed to model such systems from an organizational perspective. Usually this is done by describing multiagent systems as organizations using structural elements such as roles and groups and behavioral properties of these elements, for example, expressions for role behavior, specifying how agents should behave once they fulfill a certain role. In dynamic environments, changes in environmental circumstances may require changes in such organizations as well. In this chapter, the change process as seen in honey bee colonies has been modeled by means of techniques from the domain of multiagent organizations. This results in an adaptive multiagent organizational model that is able to cope with changing environmental circumstances.