Discovering the business process model from an organisation’s records of its operational processes is an active area of research in process mining. The discovered model may be used either during a new system rollout or to improve an existing system. In this paper, we present a process model discovery approach based on the recently proposed bio-inspired Manta Ray Foraging Optimization algorithm (MRFO). Since MRFO is designed to solve real-valued optimization problems, we adapted a binary version of MRFO to suit the domain of process mining. The proposed approach is compared with state-of-the-art process discovery algorithms on several synthetic and real-life event logs. The results show that compared to other algorithms, the proposed approach exhibits faster convergence and yields superior quality process models.

We present an epistemic language for representing an artificial player’s beliefs and actions in the context of the Yōkai board game. Yōkai is a cooperative game which requires a combination of Theory of Mind (ToM), temporal and spatial reasoning to be played effectively by an artificial agent. We show that the language properly accounts for these three dimensions and that its satisfiability problem is NP-complete. This opens up the possibility of exploiting SAT techniques for automating reasoning of an artificial player in the context of the Yōkai board-game.

Static node embedding algorithms applied to snapshots of real-world applications graphs are unable to capture their evolving process. As a result, the absence of information about the dynamics in these node representations can harm the accuracy and increase processing time of machine learning tasks related to these applications. Aiming at fill the gap regarding the inability of static methods to capture evolving processes on dynamic networks, we propose a biased random walk method named Evolving Node Embedding (EVNE). EVNE leverages the sequential relationship of graph snapshots by incorporating historic information when generating embeddings for the next snapshot. It learns node representations through a neural network, but differs from existing methods as it: (i) incorporates previously run walks at each step; (ii) starts the optimization of the current embedding from the parameters obtained in the previous iteration; and (iii) uses two time-varying parameters to regulate the behavior of the biased random walks over the process of graph exploration. Through a wide set of experiments we show that our approach generates better embeddings, outperforming baselines by up to 20% in a downstream node classification task. EVNE’s embeddings achieve better performance than others, based on experiments with four classifiers and five datasets. In addition, we present seven variations of our model to show the impact of each of EVNE’s mechanisms.

Swarm intelligence optimization algorithm has been proved to perform well in the field of parameter optimization. In order to further improve the performance of intelligent optimization algorithm, this paper proposes an improved and adaptive tunicate swarm algorithm (IMATSA) based on tunicate swarm algorithm (TSA). IMATSA improves TSA in the following four aspects: population diversity, local search convergence speed, jumping out of local optimal position, and balancing global and local search. Firstly, IMATSA adopts Tent map and quadratic interpolation to initialize population and enhance the diversity. Secondly, IMATSA uses Golden-Sine algorithm to accelerate the convergence of local search. Thirdly, in the process of global development, IMATSA adopts Levy flight and the improved Gauss disturbance method to adaptively improves and coordinates the ability of global development and local search. Then, this paper verifies the performance of IMATSA based on 14 benchmark functions experiment, ablation experiment, parameter optimization experiments of Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT), Wilcoxon signed rank test and image multi-threshold segmentation experiment with the performance metrics are convergence speed, convergence value, significance level P-value, Peak Signal-to-Noise Ratio (PSNR) and Standard Deviation (STD). Experimental results show that IMATSA performs better in three kinds of benchmark functions; each component of IMATSA has a positive effect on the performance; IMATSA performs better in parameter optimization experiments of SVM experiment and GBDT; there is significant difference between IMATSA and other algorithms by Wilcoxon signed rank test; in image segmentation, the performance is directly proportional to the number of thresholds, and compared with other algorithms, IMATSA has better comprehensive performance.

A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and other multi-policy reinforcement learning techniques can learn multiple tasks but may generate many policies. This paper presents two novel contributions, namely 1) Lifetime Policy Reuse, a model-agnostic policy reuse algorithm that avoids generating many policies by optimising a fixed number of near-optimal policies through a combination of policy optimisation and adaptive policy selection; and 2) the task capacity, a measure for the maximal number of tasks that a policy can accurately solve. Comparing two state-of-the-art base-learners, the results demonstrate the importance of Lifetime Policy Reuse and task capacity based pre-selection on an 18-task partially observable Pacman domain and a Cartpole domain of up to 125 tasks.

Clustering-based unsupervised domain adaptive person re-identification methods have achieved remarkable progress. However, existing works are easy to fall into local minimum traps due to the optimization of two variables, feature representation and pseudo labels. Besides, the model can also be hurt by the inevitable false assignment of pseudo labels. In order to solve these problems, we propose the Doubly Stochastic Subdomain Mining (DSSM) to prevent the nonconvex optimization from falling into local minima in this paper. And we also design a novel reweighting algorithm based on the similarity correlation coefficient between samples which is referred to as Maximal Heterogeneous Similarity (MHS), it can reduce the adverse effect caused by noisy labels. Extensive experiments on two popular person re-identification datasets demonstrate that our method outperforms other state-of-the-art works. The source code is available at https://github.com/Tchunansheng/DSSM.

Lung cancer is the leading cause of cancer death worldwide, and most patients are diagnosed with advanced stages for lack of symptoms in the early stages of the disease, leading to poor prognosis. It is thus of great importance to detect lung cancer in the early stages which can reduce mortality and improve patient survival significantly. Although there are many computer aided diagnosis (CAD) systems used for detecting pulmonary nodules, there are still few CAD systems for detection and segmentation, and their performance on small nodules is not ideal. Thus, in this paper, we propose a deep cascaded multitask framework called mobilenet split-attention Yolo unet, the mobilenet split-attention Yolo(Msa-yolo) greatly enhance the feature of small nodules and boost up their performance, the overall result shows that the mean accuracy precision (mAP) of our Msa-Yolo compared to Yolox has increased from 85.10% to 86.64% on LUNA16 dataset, and from 90.13% to 94.15% on LCS dataset compared to YoloX. Besides, we get only 8.35 average number of candidates per scan with 96.32% sensitivity on LUNA16 dataset, which greatly outperforms other existing systems. At the segmentation stage, the mean intersection over union (mIOU) of our CAD system has increased from 71.66% to 76.84% on LCS dataset comparing to baseline. Conclusion: A fast, accurate and robust CAD system for nodule detection, segmentation and classification is proposed in this paper. And it is confirmed by the experimental results that the proposed system possesses the ability to detect and segment small nodules.

Session-based recommendation aims at predicting the next behavior when the current interaction sequence is given. Recent advances evaluate the effectiveness of dual cross-domain information for the session-based recommendation. However, we discover that accurately modeling the session representations is still a challenging problem due to the complexity of preference interactions in the cross-domain, and various methods are proposed to only model the common features of cross-domain, while ignoring the specific features and enhanced features for the dual cross-domain. Without modeling the complete features, the existing methods suffer from poor recommendation accuracy. Therefore, we propose an end-to-end dual cross-domain with multi-channel interaction model (DCMI), which utilizes dual cross-domain session information and multiple preference interaction encoders, for session-based recommendation. In DCMI, we apply a graph neural network to generate the session global preference and local preference. Then, we design a cross-preference interaction module to capture the common, specific, and enhanced features for cross-domain sessions with local preferences and global preferences. Finally, we combine multiple preferences with a bilinear fusion mechanism to characterize and make recommendations. Experimental results on the Amazon dataset demonstrate the superiority of the DCMI model over the state-of-the-art methods.

As the research community focuses on improving the reliability of deep learning, identifying out-of-distribution (OOD) data has become crucial. Detecting OOD inputs during test/prediction allows the model to account for discriminative features unknown to the model. This capability increases the model’s reliability since this model provides a class prediction solely at incoming data similar to the training one. Although OOD detection is well-established in computer vision, it is relatively unexplored in other areas, like time series-based human activity recognition (HAR). Since uncertainty has been a critical driver for OOD in vision-based models, the same component has proven effective in time-series applications. In this work, we propose an ensemble-based temporal learning framework to address the OOD detection problem in HAR with time-series data. First, we define different types of OOD for HAR that arise from realistic scenarios. Then we apply our ensemble-based temporal learning framework incorporating uncertainty to detect OODs for the defined HAR workloads. This particular formulation also allows a novel approach to fall detection. We train our model on non-fall activities and detect falls as OOD. Our method shows state-of-the-art performance in a fall detection task using much lesser data. Furthermore, the ensemble framework outperformed the traditional deep-learning method (our baseline) on the OOD detection task across all the other chosen datasets.