scholarly journals Knowledge-infused Learning for Entity Prediction in Driving Scenes

2021 ◽  
Vol 4 ◽  
Author(s):  
Ruwan Wickramarachchi ◽  
Cory Henson ◽  
Amit Sheth
Keyword(s):  
Scene Understanding ◽  
Autonomous Driving ◽  
Semantic Knowledge ◽  
Quality Data ◽  
Knowledge Graph ◽  
Social Environments ◽  
High Quality Data ◽  
Knowledge Based ◽  
Standard Mapping ◽  
High Level

Scene understanding is a key technical challenge within the autonomous driving domain. It requires a deep semantic understanding of the entities and relations found within complex physical and social environments that is both accurate and complete. In practice, this can be accomplished by representing entities in a scene and their relations as a knowledge graph (KG). This scene knowledge graph may then be utilized for the task of entity prediction, leading to improved scene understanding. In this paper, we will define and formalize this problem as Knowledge-based Entity Prediction (KEP). KEP aims to improve scene understanding by predicting potentially unrecognized entities by leveraging heterogeneous, high-level semantic knowledge of driving scenes. An innovative neuro-symbolic solution for KEP is presented, based on knowledge-infused learning, which 1) introduces a dataset agnostic ontology to describe driving scenes, 2) uses an expressive, holistic representation of scenes with knowledge graphs, and 3) proposes an effective, non-standard mapping of the KEP problem to the problem of link prediction (LP) using knowledge-graph embeddings (KGE). Using real, complex and high-quality data from urban driving scenes, we demonstrate its effectiveness by showing that the missing entities may be predicted with high precision (0.87 Hits@1) while significantly outperforming the non-semantic/rule-based baselines.

What Can Digitization Do For Formulated Product Innovation and Development

2020 ◽  
Author(s):  
James McDonagh ◽  
William Swope ◽  
Richard L. Anderson ◽  
Michael Johnston ◽  
David J. Bray
Keyword(s):  
High Performance ◽  
Quality Data ◽  
High Quality Data ◽  
Base Level ◽  
Hybrid Approaches ◽  
Digital Ecosystem ◽  
Recent Developments ◽  
Chemical Simulation ◽  
High Level ◽  
Physical And Chemical

Digitization offers significant opportunities for the formulated product industry to transform the way it works and develop new methods of business. R&D is one area of operation that is challenging to take advantage of these technologies due to its high level of domain specialisation and creativity but the benefits could be significant. Recent developments of base level technologies such as artificial intelligence (AI)/machine learning (ML), robotics and high performance computing (HPC), to name a few, present disruptive and transformative technologies which could offer new insights, discovery methods and enhanced chemical control when combined in a digital ecosystem of connectivity, distributive services and decentralisation. At the fundamental level, research in these technologies has shown that new physical and chemical insights can be gained, which in turn can augment experimental R&D approaches through physics-based chemical simulation, data driven models and hybrid approaches. In all of these cases, high quality data is required to build and validate models in addition to the skills and expertise to exploit such methods. In this article we give an overview of some of the digital technology demonstrators we have developed for formulated product R&D. We discuss the challenges in building and deploying these demonstrators.<br>

scholarly journals Knowledge Graph Driven Approach to Represent Video Streams for Spatiotemporal Event Pattern Matching in Complex Event Processing

2020 ◽  
Vol 14 (03) ◽  
pp. 423-455
Author(s):  
Piyush Yadav ◽  
Dhaval Salwala ◽  
Dibya Prakash Das ◽  
Edward Curry
Keyword(s):  
Search Time ◽  
Semantic Knowledge ◽  
Complex Event Processing ◽  
Video Data ◽  
Streaming Data ◽  
Knowledge Graph ◽  
Event Processing ◽  
Video Streams ◽  
Video Event ◽  
High Level

Complex Event Processing (CEP) is an event processing paradigm to perform real-time analytics over streaming data and match high-level event patterns. Presently, CEP is limited to process structured data stream. Video streams are complicated due to their unstructured data model and limit CEP systems to perform matching over them. This work introduces a graph-based structure for continuous evolving video streams, which enables the CEP system to query complex video event patterns. We propose the Video Event Knowledge Graph (VEKG), a graph-driven representation of video data. VEKG models video objects as nodes and their relationship interaction as edges over time and space. It creates a semantic knowledge representation of video data derived from the detection of high-level semantic concepts from the video using an ensemble of deep learning models. A CEP-based state optimization — VEKG-Time Aggregated Graph (VEKG-TAG) — is proposed over VEKG representation for faster event detection. VEKG-TAG is a spatiotemporal graph aggregation method that provides a summarized view of the VEKG graph over a given time length. We defined a set of nine event pattern rules for two domains (Activity Recognition and Traffic Management), which act as a query and applied over VEKG graphs to discover complex event patterns. To show the efficacy of our approach, we performed extensive experiments over 801 video clips across 10 datasets. The proposed VEKG approach was compared with other state-of-the-art methods and was able to detect complex event patterns over videos with [Formula: see text]-Score ranging from 0.44 to 0.90. In the given experiments, the optimized VEKG-TAG was able to reduce 99% and 93% of VEKG nodes and edges, respectively, with 5.19[Formula: see text] faster search time, achieving sub-second median latency of 4–20[Formula: see text]ms.

scholarly journals Software for online reconstruction and filtering at the Belle II experiment

2020 ◽  
Vol 35 (33) ◽  
pp. 2043001 ◽  
Author(s):  
Nils Braun ◽  
Thomas Kuhr
Keyword(s):  
Quality Data ◽  
Software Components ◽  
Data Transport ◽  
High Quality Data ◽  
Processing Pipeline ◽  
Level Trigger ◽  
Belle Ii ◽  
High Level ◽  
Online Reconstruction ◽  
Monitoring Information

The Belle II experiment is designed to collect 50 times more data than its predecessor. For a smooth collection of high-quality data, a robust and automated data transport and processing pipeline has been established. We describe the basic software components employed by the high level trigger. It performs a reconstruction of all events using the same algorithms as offline, classifies the events according to physics criteria, and provides monitoring information. The improved system described in this paper has been deployed successfully since 2019.

scholarly journals KNOWLEDGE BASED EMPLOYMENT PROCESS – DATA DRIVEN RECRUITMENT

2020 ◽  
Author(s):  
Jelena Vemić Đurković ◽  
◽  
Ivica Nikolić ◽  
Slavica Siljanoska ◽  
◽  
...  
Keyword(s):  
Data Driven ◽  
Quality Data ◽  
Process Data ◽  
High Quality Data ◽  
Knowledge Based ◽  
Special Part ◽  
Using Data ◽  
Recruitment System ◽  
The One ◽  
Further Development

The purpose of this paper is to highlight the main benefits and challenges of using a data-driven recruiting system in enterprises. The trend of increasing digital presence in all fields requires new knowledge and skills of employees. Sustainable development of enterprise is increasingly based on human capital and investment in it. Precisely in these conditions of business, on the one hand, there is increasing pressure to attract and hire the highest quality employees more efficiently, which implies large investments in the recruitment processes and on the other hand to justify those investments. The high-quality data-driven recruitment system provides a way to measure the contribution of recruiting process to the success, to adequately manage existing recruitment programs, and to justify investments in their further development. A special part of this paper will be consecrated to the trends and challenges of using data-driven recruitment in the context of the global crisis of the coronavirus COVID - 19 pandemic.

scholarly journals What Can Digitization Do For Formulated Product Innovation and Development

2020 ◽  
Author(s):  
James McDonagh ◽  
William Swope ◽  
Richard L. Anderson ◽  
Michael Johnston ◽  
David J. Bray
Keyword(s):  
High Performance ◽  
Quality Data ◽  
High Quality Data ◽  
Base Level ◽  
Hybrid Approaches ◽  
Digital Ecosystem ◽  
Recent Developments ◽  
Chemical Simulation ◽  
High Level ◽  
Physical And Chemical

Digitization offers significant opportunities for the formulated product industry to transform the way it works and develop new methods of business. R&D is one area of operation that is challenging to take advantage of these technologies due to its high level of domain specialisation and creativity but the benefits could be significant. Recent developments of base level technologies such as artificial intelligence (AI)/machine learning (ML), robotics and high performance computing (HPC), to name a few, present disruptive and transformative technologies which could offer new insights, discovery methods and enhanced chemical control when combined in a digital ecosystem of connectivity, distributive services and decentralisation. At the fundamental level, research in these technologies has shown that new physical and chemical insights can be gained, which in turn can augment experimental R&D approaches through physics-based chemical simulation, data driven models and hybrid approaches. In all of these cases, high quality data is required to build and validate models in addition to the skills and expertise to exploit such methods. In this article we give an overview of some of the digital technology demonstrators we have developed for formulated product R&D. We discuss the challenges in building and deploying these demonstrators.<br>

scholarly journals What Can Digitization Do For Formulated Product Innovation and Development

2020 ◽  
Author(s):  
James McDonagh ◽  
William Swope ◽  
Richard L. Anderson ◽  
Michael Johnston ◽  
David J. Bray
Keyword(s):  
High Performance ◽  
Quality Data ◽  
High Quality Data ◽  
Base Level ◽  
Hybrid Approaches ◽  
Digital Ecosystem ◽  
Recent Developments ◽  
Chemical Simulation ◽  
High Level ◽  
Physical And Chemical

Digitization offers significant opportunities for the formulated product industry to transform the way it works and develop new methods of business. R&D is one area of operation that is challenging to take advantage of these technologies due to its high level of domain specialisation and creativity but the benefits could be significant. Recent developments of base level technologies such as artificial intelligence (AI)/machine learning (ML), robotics and high performance computing (HPC), to name a few, present disruptive and transformative technologies which could offer new insights, discovery methods and enhanced chemical control when combined in a digital ecosystem of connectivity, distributive services and decentralisation. At the fundamental level, research in these technologies has shown that new physical and chemical insights can be gained, which in turn can augment experimental R&D approaches through physics-based chemical simulation, data driven models and hybrid approaches. In all of these cases, high quality data is required to build and validate models in addition to the skills and expertise to exploit such methods. In this article we give an overview of some of the digital technology demonstrators we have developed for formulated product R&D. We discuss the challenges in building and deploying these demonstrators.<br>

Collecting High-Quality Data

2018 ◽  
Author(s):  
Mary Kay Gugerty ◽  
Dean Karlan
Keyword(s):  
Data Collection ◽  
Social Desirability ◽  
Measurement Errors ◽  
Monitoring And Evaluation ◽  
Quality Data ◽  
Social Desirability Bias ◽  
High Quality ◽  
High Quality Data ◽  
Evaluation Systems ◽  
Demand Effect

Without high-quality data, even the best-designed monitoring and evaluation systems will collapse. Chapter 7 introduces some the basics of collecting high-quality data and discusses how to address challenges that frequently arise. High-quality data must be clearly defined and have an indicator that validly and reliably measures the intended concept. The chapter then explains how to avoid common biases and measurement errors like anchoring, social desirability bias, the experimenter demand effect, unclear wording, long recall periods, and translation context. It then guides organizations on how to find indicators, test data collection instruments, manage surveys, and train staff appropriately for data collection and entry.

scholarly journals Semantic knowledge based reasoning framework for human robot collaboration

Procedia CIRP ◽  
2021 ◽  
Vol 97 ◽  
pp. 373-378
Author(s):  
Sharath Chandra Akkaladevi ◽  
Matthias Plasch ◽  
Michael Hofmann ◽  
Andreas Pichler
Keyword(s):  
Semantic Knowledge ◽  
Knowledge Based ◽  
Human Robot Collaboration

scholarly journals Velocity Analysis Using Separated Diffractions for Lunar Penetrating Radar Obtained by Yutu-2 Rover

2021 ◽  
Vol 13 (7) ◽  
pp. 1387
Author(s):  
Chao Li ◽  
Jinhai Zhang
Keyword(s):  
Dielectric Permittivity ◽  
Lunar Regolith ◽  
Velocity Model ◽  
Velocity Estimation ◽  
Quality Data ◽  
High Quality Data ◽  
Shallow Subsurface ◽  
Subsurface Structures ◽  
Ground Penetrating ◽  
Permittivity Model

The high-frequency channel of lunar penetrating radar (LPR) onboard Yutu-2 rover successfully collected high quality data on the far side of the Moon, which provide a chance for us to detect the shallow subsurface structures and thickness of lunar regolith. However, traditional methods cannot obtain reliable dielectric permittivity model, especially in the presence of high mix between diffractions and reflections, which is essential for understanding and interpreting the composition of lunar subsurface materials. In this paper, we introduce an effective method to construct a reliable velocity model by separating diffractions from reflections and perform focusing analysis using separated diffractions. We first used the plane-wave destruction method to extract weak-energy diffractions interfered by strong reflections, and the LPR data are separated into two parts: diffractions and reflections. Then, we construct a macro-velocity model of lunar subsurface by focusing analysis on separated diffractions. Both the synthetic ground penetrating radar (GPR) and LPR data shows that the migration results of separated reflections have much clearer subsurface structures, compared with the migration results of un-separated data. Our results produce accurate velocity estimation, which is vital for high-precision migration; additionally, the accurate velocity estimation directly provides solid constraints on the dielectric permittivity at different depth.

Sign in / Sign up

Export Citation Format

Share Document