Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building different network architectures or learning models. Quantifying uncertainty accompanied by point estimation is essential because it mitigates model unfairness and permits practitioners to develop trustworthy systems which abstain from suboptimal decisions due to low confidence. Explicitly, assessing uncertainties associated with DNNs predictions is critical in real-world card fraud detection settings for characteristic reasons, including (a) fraudsters constantly change their strategies, and accordingly, DNNs encounter observations that are not generated by the same process as the training distribution, (b) owing to the time-consuming process, very few transactions are timely checked by professional experts to update DNNs. Therefore, this study proposes three uncertainty quantification (UQ) techniques named Monte Carlo dropout, ensemble, and ensemble Monte Carlo dropout for card fraud detection applied on transaction data. Moreover, to evaluate the predictive uncertainty estimates, UQ confusion matrix and several performance metrics are utilized. Through experimental results, we show that the ensemble is more effective in capturing uncertainty corresponding to generated predictions. Additionally, we demonstrate that the proposed UQ methods provide extra insight to the point predictions, leading to elevate the fraud prevention process.

We propose a novel framework that detects conflicts in IoT-based smart homes. Conflicts may arise during interactions between the resident and IoT services in smart homes. We propose a generic knowledge graph to represent the relations between IoT services and environment entities. We also profile a generic knowledge graph to a specific smart home setting based on the context information. We propose a conflict taxonomy to capture different types of conflicts in a single resident smart home setting. A conflict detection algorithm is proposed to identify potential conflicts using the profiled knowledge graph. We conduct a set of experiments on real datasets and synthesized datasets to validate the effectiveness and efficiency of our proposed approach.

Businesses keep finding new ways to generate value with HPE's real-time global collaboration solution. HPE Pointnext Services can help your organization do the same. Most people are familiar with some type of virtual reality experience from the consumer space, perhaps from trying out some gaming equipment – even if it's borrowed from the kids! If you've ever found yourself immersed in one of those engaging virtual worlds, you'll understand why so many organizations are craving ways to translate augmented reality into the business world. Use cases range from training and education to performing maintenance on facilities and equipment.

Hospitals in Victoria's South West, including public health agencies under the South West Alliance of Rural Health and Barwon Health in Geelong, are set to roll out a data platform capable of real-time analysis using AI, machine learning, as well as business and clinical intelligence. The health organisations will be deploying the IRIS for Health platform by global tech provider InterSystems. The data platform, according to InterSystems's website, is specifically engineered to extract value from healthcare data. It is a standards-based platform that is able to read and write Health Level 7's Fast Healthcare Interoperability Resources (HL7 FHIR) for developing healthcare applications. It is also capable of ingesting, processing and storing transaction data "at high rates" while simultaneously processing high volume analytic workloads involving historical and real-time data. While the health providers have interconnected systems, including clinical and patient administration systems, specialist healthcare applications and data analytics solutions, they don't have a single data repository supporting real-time data analysis.

Volcanologists can predict when volcanos are going to erupt if they have a full detail of its eruptions. But for potentially apocalyptic supervolcanoes, such as the one bubbling under Yellowstone National Park, it's nearly impossible, given how varied their known eruptions have been, according to a new study. Researchers at Cardiff University noted there is not a'single model' that can help scientists understand how eruptions from supervolcanoes happen, making it difficult to understand when they might occur in the future. The researchers looked at geochemical and petrological evidence of 13 supereruptions that have happened over the past 2 million years, including the most recent one, Taupō volcano in New Zealand, which happened more than 24,000 years ago. Experts said there is not a'single model' that can help them understand how eruptions from supervolcanoes happen There was no'single, unified mode' that showed how each of the 13 played out, with some starting gradually over a period of weeks to months, while others exploded suddenly and violently. The researchers also found that the eruptions lasted for varying times, some as short as a period of days or weeks, while others lasted decades.

Robotics is one of the major disruptive technologies helping multiple industries and organizations to boost productivity efficiently and effectively with moving, gripping, cleaning, and lifting objects. The world has already seen the development of multiple types of robots ranging from big industrial ones to micro-robots for assistance in the manufacturing, automotive as well as healthcare sectors. Recently, scientists and Robotics engineers have discovered that suction cups can be used in Robotics and their mission was also successful. Let's explore how suction cups in Robotics introduced wall-climbing robots into the world. It has been observed that multiple robots are assisting human employees in some horizontal areas such as a body, object, water, floor, etc.

Recent advances in the areas of multimodal machine learning and artificial intelligence (AI) have led to the development of challenging tasks at the intersection of Computer Vision, Natural Language Processing, and Embodied AI. Whereas many approaches and previous survey pursuits have characterised one or two of these dimensions, there has not been a holistic analysis at the center of all three. Moreover, even when combinations of these topics are considered, more focus is placed on describing, e.g., current architectural methods, as opposed to also illustrating high-level challenges and opportunities for the field. In this survey paper, we discuss Embodied Vision-Language Planning (EVLP) tasks, a family of prominent embodied navigation and manipulation problems that jointly use computer vision and natural language. We propose a taxonomy to unify these tasks and provide an in-depth analysis and comparison of the new and current algorithmic approaches, metrics, simulated environments, as well as the datasets used for EVLP tasks. Finally, we present the core challenges that we believe new EVLP works should seek to address, and we advocate for task construction that enables model generalizability and furthers real-world deployment.

Graph clustering and community detection are central problems in modern data mining. The increasing need for analyzing billion-scale data calls for faster and more scalable algorithms for these problems. There are certain trade-offs between the quality and speed of such clustering algorithms. In this paper, we design scalable algorithms that achieve high quality when evaluated based on ground truth. We develop a generalized sequential and shared-memory parallel framework based on the LambdaCC objective (introduced by Veldt et al.), which encompasses modularity and correlation clustering. Our framework consists of highly-optimized implementations that scale to large data sets of billions of edges and that obtain high-quality clusters compared to ground-truth data, on both unweighted and weighted graphs. Our empirical evaluation shows that this framework improves the state-of-the-art trade-offs between speed and quality of scalable community detection. For example, on a 30-core machine with two-way hyper-threading, our implementations achieve orders of magnitude speedups over other correlation clustering baselines, and up to 28.44x speedups over our own sequential baselines while maintaining or improving quality.

Emotion classification in text is typically performed with neural network models which learn to associate linguistic units with emotions. While this often leads to good predictive performance, it does only help to a limited degree to understand how emotions are communicated in various domains. The emotion component process model (CPM) by Scherer (2005) is an interesting approach to explain emotion communication. It states that emotions are a coordinated process of various subcomponents, in reaction to an event, namely the subjective feeling, the cognitive appraisal, the expression, a physiological bodily reaction, and a motivational action tendency. We hypothesize that these components are associated with linguistic realizations: an emotion can be expressed by describing a physiological bodily reaction ("he was trembling"), or the expression ("she smiled"), etc. We annotate existing literature and Twitter emotion corpora with emotion component classes and find that emotions on Twitter are predominantly expressed by event descriptions or subjective reports of the feeling, while in literature, authors prefer to describe what characters do, and leave the interpretation to the reader. We further include the CPM in a multitask learning model and find that this supports the emotion categorization. The annotated corpora are available at https://www.ims.uni-stuttgart.de/data/emotion.

The inexpressive Description Logic (DL) $\mathcal{FL}_0$, which has conjunction and value restriction as its only concept constructors, had fallen into disrepute when it turned out that reasoning in $\mathcal{FL}_0$ w.r.t. general TBoxes is ExpTime-complete, i.e., as hard as in the considerably more expressive logic $\mathcal{ALC}$. In this paper, we rehabilitate $\mathcal{FL}_0$ by presenting a dedicated subsumption algorithm for $\mathcal{FL}_0$, which is much simpler than the tableau-based algorithms employed by highly optimized DL reasoners. Our experiments show that the performance of our novel algorithm, as prototypically implemented in our $\mathcal{FL}_o$wer reasoner, compares very well with that of the highly optimized reasoners. $\mathcal{FL}_o$wer can also deal with ontologies written in the extension $\mathcal{FL}_{\bot}$ of $\mathcal{FL}_0$ with the top and the bottom concept by employing a polynomial-time reduction, shown in this paper, which eliminates top and bottom. We also investigate the complexity of reasoning in DLs related to the Horn-fragments of $\mathcal{FL}_0$ and $\mathcal{FL}_{\bot}$.