Business processes are prone to unexpected changes, as process workers may suddenly or gradually start executing a process differently in order to adjust to changes in workload, season, or other external factors. Early detection of business process changes enables managers to identify and act upon changes that may otherwise affect process performance. Business process drift detection refers to a family of methods to detect changes in a business process by analyzing event logs extracted from the systems that support the execution of the process. Existing methods for business process drift detection are based on an explorative analysis of a potentially large feature space and in some cases they require users to manually identify specific features that characterize the drift. Depending on the explored feature space, these methods miss various types of changes. Moreover, they are either designed to detect sudden drifts or gradual drifts but not both. This paper proposes an automated and statistically grounded method for detecting sudden and gradual business process drifts under a unified framework. An empirical evaluation shows that the method detects typical change patterns with significantly higher accuracy and lower detection delay than existing methods, while accurately distinguishing between sudden and gradual drifts.

There are two competing paradigms in successful SAT solvers: Conflict-driven clause learning (CDCL) and stochastic local search (SLS). CDCL uses systematic exploration of the search space and has the ability to learn new clauses. SLS examines the neighborhood of the current complete assignment. Unlike CDCL, it lacks the ability to learn from its mistakes. This work revolves around the question whether it is beneficial for SLS to add new clauses to the original formula. We experimentally demonstrate that clauses with a large number of correct literals w. r. t. a fixed solution are beneficial to the runtime of SLS. We call such clauses high-quality clauses. Empirical evaluations show that short clauses learned by CDCL possess the high-quality attribute. We study several domains of randomly generated instances and deduce the most beneficial strategies to add high-quality clauses as a preprocessing step. The strategies are implemented in an SLS solver, and it is shown that this considerably improves the state-of-the-art on randomly generated instances. The results are statistically significant.

Neighbourhood Evaluation Criteria is a heuristical approximate algorithm that attempts to solve the Minimum Vertex Cover. degree count is kept in check for each vertex and the highest count based vertex is included in our cover set. In the case of multiple equivalent vertices, the one with the lowest neighbourhood influence is selected. In the case of still existing multiple equivalent vertices, the one with the lowest remaining active vertex count (the highest Independent Set enabling count) is selected as a tie-breaker.

Methods for generating synthetic data have become of increasing importance to build large datasets required for Convolution Neural Networks (CNN) based deep learning techniques for a wide range of computer vision applications. In this work, we extend existing methodologies to show how 2D thermal facial data can be mapped to provide 3D facial models. For the proposed research work we have used tufts datasets for generating 3D varying face poses by using a single frontal face pose. The system works by refining the existing image quality by performing fusion based image preprocessing operations. The refined outputs have better contrast adjustments, decreased noise level and higher exposedness of the dark regions. It makes the facial landmarks and temperature patterns on the human face more discernible and visible when compared to original raw data. Different image quality metrics are used to compare the refined version of images with original images. In the next phase of the proposed study, the refined version of images is used to create 3D facial geometry structures by using Convolution Neural Networks (CNN). The generated outputs are then imported in blender software to finally extract the 3D thermal facial outputs of both males and females. The same technique is also used on our thermal face data acquired using prototype thermal camera (developed under Heliaus EU project) in an indoor lab environment which is then used for generating synthetic 3D face data along with varying yaw face angles and lastly facial depth map is generated.

Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.

In the variational relevance vector machine, the gamma distribution is representative as a hyperprior over the noise precision of automatic relevance determination prior. Instead of the gamma hyperprior, we propose to use the inverse gamma hyperprior with a shape parameter close to zero and a scale parameter not necessary close to zero. This hyperprior is associated with the concept of a weakly informative prior. The effect of this hyperprior is investigated through regression to non-homogeneous data. Because it is difficult to capture the structure of such data with a single kernel function, we apply the multiple kernel method, in which multiple kernel functions with different widths are arranged for input data. We confirm that the degrees of freedom in a model is controlled by adjusting the scale parameter and keeping the shape parameter close to zero. A candidate for selecting the scale parameter is the predictive information criterion. However the estimated model using this criterion seems to cause over-fitting. This is because the multiple kernel method makes the model a situation where the dimension of the model is larger than the data size. To select an appropriate scale parameter even in such a situation, we also propose an extended prediction information criterion. It is confirmed that a multiple kernel relevance vector regression model with good predictive accuracy can be obtained by selecting the scale parameter minimizing extended prediction information criterion.

Your teams have spent years building your organization's networked systems and connected applications. With so many employees working remotely, your business depends on reliable IT applications and services to keep their operations going, employees productive, and customers happy. A single major incident can jeopardize business operations when we depend on our technology more than ever. But with IT analytics, organizations can recognize possible threats before they have a chance to cause major service disruptions. Using Machine Learning (ML), an IT analytics solution can identify signals that act as warning signs for an impending major incident.

Not so long ago, the concept of a fully automated store seemed something of a curiosity. Now, in the midst of the COVID-19 pandemic, the idea of relying on computers and robotics, and checking out groceries by simply picking them off the shelf doesn't seem so peculiar after all. Part of my research involves looking at how we deal with complex artificial intelligence (AI) systems that can learn and make decisions without any human involvement, and how these types of AI technologies challenge our current understanding of law and its application. How should we govern these systems that are sometimes called disruptive, and at other times labelled transformative? I am particularly interested in whether -- and how -- AI technologies amplify the social injustice that exists in society.

After the'top AI books' reading list was so well received, we reached out to some of our community to find out which papers they believe everyone should have read! All of the below papers are free to access and cover a range of topics from Hypergradients to modeling yield response for CNNs. Each expert also included a reason as to why the paper was picked as well as a short bio. We spoke to Jeff back in January and at that time he couldn't pick just one paper as a must-read, so we let him pick two. This paper unpacks two key talking points, the limitations of sparse training data and also if recurrent networks can support meta-learning in a fully supervised context.

We are seeing an increased interest in the area of artificial intelligence (AI) from regulators recently. In this blog post, I will provide a summary of regulatory papers published in the US and the Netherlands last year. In the US, the Casualty Actuarial and Statistical Task Force (CASTF) published a paper in May 2019 aimed at identifying best practices when reviewing predictive models and analytics filed by insurers with regulators to justify rates, and providing state guidance for review of rate filings based on predictive models. In the Netherlands, the Dutch supervisors Authority for Financial Markets (AFM) and De Nederlandsche Bank (DNB) published two articles in July 2019 discussing the use of AI in the Dutch financial sector and specifically among Dutch insurers. The CASTF paper begins by defining what a best practice is and discusses whether regulators need best practices to review predictive models.