• Corpus ID: 239009551

Using DeepProbLog to perform Complex Event Processing on an Audio Stream

  title={Using DeepProbLog to perform Complex Event Processing on an Audio Stream},
  author={Marc Roig Vilamala and Tianwei Xing and Harrison Taylor and Luis Garcia and Mani B. Srivastava and Lance M. Kaplan and Alun David Preece and Angelika Kimmig and Federico Cerutti},
In this paper, we present an approach to Complex Event Processing (CEP) that is based on DeepProbLog. This approach has the following objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining the flexibility and modularity on the definitions of complex event rules, (iii) allowing the system to be trained in an end-to-end manner and (iv) being robust against adversarial conditions. Our approach makes use of DeepProbLog to use a hybrid neuro-symbolic architecture that… 

Figures and Tables from this paper

A Neuro-Symbolic Approach for Real-World Event Recognition from Weak Supervision

It is shown how by incorporating simple knowledge involving the relative order of atomic events and constraints on their duration, the approach substantially outperforms a fully neural solution in terms of recognition accuracy, when little or even no supervision is available on the atomic events.

Context-aware Collaborative Neuro-Symbolic Inference in IoBTs

The key challenges in developing context-aware collaborative neuro-symbolic inference in IoBTs are identified and some recent progress in addressing these gaps are reviewed.

A Brain-Inspired Hierarchical Reasoning Framework for Cognition-Augmented Prosthetic Grasping

Overall, this paper aims to illustrate how HD computing can constitute a mathematical formalism capable of integrating various levels of cognition under a common hierarchical framework.



Neuroplex: learning to detect complex events in sensor networks through knowledge injection

Neuroplex is a neural-symbolic framework that learns to perform complex reasoning on raw sensory data with the help of high-level, injected human knowledge and is capable of learning to efficiently and effectively detect complex events-which cannot be handled by state-of-the-art neural network models.

Neural probabilistic logic programming in DeepProbLog

CNN architectures for large-scale audio classification

This work uses various CNN architectures to classify the soundtracks of a dataset of 70M training videos with 30,871 video-level labels, and investigates varying the size of both training set and label vocabulary, finding that analogs of the CNNs used in image classification do well on the authors' audio classification task, and larger training and label sets help up to a point.

DeepProbLog: Neural Probabilistic Logic Programming

This work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples.

A Pilot Study on Detecting Violence in Videos Fusing Proxy Models

It is shown that there are specific, detectable, and measurable features of video feeds that correlate with—among other things—violence and, by fusing such features with semantic knowledge, this work can in principle provide estimates of sequences of videos that correlates with violence.

An Ingestion Based Analytics Framework for Complex Event Processing Engine in Internet of Things

The experimental results suggest the rich abilities of Deep Learning to predict events proactively with minimal error and allows to deal with uncertainties and steps for significant improvement can be made in advance.

The power of events - an introduction to complex event processing in distributed enterprise systems

Some possible long-term future roles of CEP in the Information Society are discussed along with the need to develop rule-based event hierarchies on a commercial basis to make those applications possible.

Stream reasoning and complex event processing in ETALIS

This paper describes ETALIS --a system which enables specification and monitoring of changes in near real time, and implements two languages for specification of event patterns: ETALis Language for Events, and Event Processing SPARQL.

Knowledge-based processing of complex stock market events

This paper describes a system for knowledge-based event detection of complex stock market events based on available background knowledge about stock market companies which profits from data fusion of live event stream and backgroundknowledge about companies which is stored in a knowledge base.