Integrated “Generate, Make, and Test” for Formulated Products using Knowledge Graphs

Abstract In the multi-billion dollar formulated product industry, state of the art continues to rely heavily on experts during the generate, make and test steps of formulation design. We propose automation aids to each of these steps with a knowledge graph of relevant information as the central artefact. The generate step usually focuses on coming up with new recipes for intended formulation. We propose to aid the experts who generally carry out this step manually, by providing a recommendation system and a templating system on top of the knowledge graph. Using the former, the expert can create a recipe from scratch using historical formulations and related data. With the latter, the expert starts with a recipe template created by our system and substitutes the requisite constituents to form a recipe. In the current state of practice, the three steps mentioned above operate in a fragmented manner wherein observations from one step do not aid other steps in a streamlined manner. Instead of manually operated labs for the make and test steps, we assume the use of automated or robotic labs and in-silico testing respectively. Using two formulations namely, face cream and an exterior coating, we show how the knowledge graph may help integrate and streamline the communication between the generate, the make, and the test steps. Our initial exploration shows considerable promise.

Download Full-text

Computational Analysis of Storylines

10.1017/9781108854221 ◽

2021 ◽

Keyword(s):

Computational Linguistics ◽

Language Processing ◽

Computational Analysis ◽

State Of The Art ◽

Relevant Information ◽

Event Extraction ◽

Multidisciplinary Research ◽

Narrative Structures ◽

Current State ◽

Event Representations

Event structures are central in Linguistics and Artificial Intelligence research: people can easily refer to changes in the world, identify their participants, distinguish relevant information, and have expectations of what can happen next. Part of this process is based on mechanisms similar to narratives, which are at the heart of information sharing. But it remains difficult to automatically detect events or automatically construct stories from such event representations. This book explores how to handle today's massive news streams and provides multidimensional, multimodal, and distributed approaches, like automated deep learning, to capture events and narrative structures involved in a 'story'. This overview of the current state-of-the-art on event extraction, temporal and casual relations, and storyline extraction aims to establish a new multidisciplinary research community with a common terminology and research agenda. Graduate students and researchers in natural language processing, computational linguistics, and media studies will benefit from this book.

Download Full-text

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6476 ◽

2020 ◽

Vol 34 (05) ◽

pp. 9354-9361

Author(s):

Kun Xu ◽

Linfeng Song ◽

Yansong Feng ◽

Yan Song ◽

Dong Yu

Keyword(s):

State Of The Art ◽

The Other ◽

Knowledge Graph ◽

Alignment Algorithm ◽

Graph Alignment ◽

Current State ◽

Alignment Model ◽

The Many ◽

The One ◽

Cross Lingual

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity. This decoding method may not only cause the “many-to-one” problem but also neglect the coordinated nature of this task, that is, each alignment decision may highly correlate to the other decisions. In this paper, we introduce two coordinated reasoning methods, i.e., the Easy-to-Hard decoding strategy and joint entity alignment algorithm. Specifically, the Easy-to-Hard strategy first retrieves the model-confident alignments from the predicted results and then incorporates them as additional knowledge to resolve the remaining model-uncertain alignments. To achieve this, we further propose an enhanced alignment model that is built on the current state-of-the-art baseline. In addition, to address the many-to-one problem, we propose to jointly predict entity alignments so that the one-to-one constraint can be naturally incorporated into the alignment prediction. Experimental results show that our model achieves the state-of-the-art performance and our reasoning methods can also significantly improve existing baselines.

Download Full-text

The total costs of seismic retrofits: State of the art

Earthquake Spectra ◽

10.1177/87552930211009522 ◽

2021 ◽

pp. 875529302110095

Author(s):

Juan F Fung ◽

Siamak Sattar ◽

David T Butry ◽

Steven L McCabe

Keyword(s):

State Of The Art ◽

Risk Mitigation ◽

Indirect Costs ◽

Structural Elements ◽

Existing Building ◽

Total Cost ◽

Current State ◽

Seismic Risk Mitigation ◽

State Of Practice ◽

Cost Components

This article presents the current state-of-practice with respect to quantifying the total cost to retrofit an existing building. In particular, we combine quantitative, qualitative, and heuristic data to provide a taxonomy for understanding the direct and indirect costs associated with seismic risk mitigation. Much of the literature to date has focused on estimating structural retrofit costs, the costs of retrofitting the structural elements of a building. In contrast, there is very little research or data on the remaining cost components of the total cost. We propose using structural cost as the foundation for approximating the remaining cost components and the total cost itself. To validate our findings, we compare the proposed approximations with actual cost estimates developed by engineering professionals.

Download Full-text

DisBot: A Portuguese Disaster Support Dynamic Knowledge Chatbot

Applied Sciences ◽

10.3390/app10249082 ◽

2020 ◽

Vol 10 (24) ◽

pp. 9082

Author(s):

João Boné ◽

João C. Ferreira ◽

Ricardo Ribeiro ◽

Gonçalo Cadete

Keyword(s):

Decision Making ◽

Social Media ◽

State Of The Art ◽

Design Science ◽

Science Research ◽

Design Science Research ◽

Relevant Information ◽

Knowledge Graph ◽

Design Science Research Methodology ◽

Safety Knowledge

This paper presents DisBot, the first Portuguese speaking chatbot that uses social media retrieved knowledge to support citizens and first-responders in disaster scenarios, in order to improve community resilience and decision-making. It was developed and tested using Design Science Research Methodology (DSRM), being progressively matured with field specialists through several design and development iterations. DisBot uses a state-of-the-art Dual Intent Entity Transformer (DIET) architecture to classify user intents, and makes use of several dialogue policies for managing user conversations, as well as storing relevant information to be used in further dialogue turns. To generate responses, it uses real-world safety knowledge, and infers a dynamic knowledge graph that is dynamically updated in real-time by a disaster-related knowledge extraction tool, presented in previous works. Through its development iterations, DisBot has been validated by field specialists, who have considered it to be a valuable asset in disaster management.

Download Full-text

The Geranium Platform: A KG-Based System for Academic Publications

Information ◽

10.3390/info12090366 ◽

2021 ◽

Vol 12 (9) ◽

pp. 366

Author(s):

Giovanni Garifo ◽

Giuseppe Futia ◽

Antonio Vetrò ◽

Juan Carlos De Martin

Keyword(s):

Recommendation System ◽

State Of The Art ◽

Synthetic Data ◽

Knowledge Graph ◽

Human Knowledge ◽

Core Technology ◽

Academic Publications ◽

Knowledge Graphs ◽

Graph Neural Networks ◽

Semantic Properties

Knowledge Graphs (KGs) have emerged as a core technology for incorporating human knowledge because of their capability to capture the relational dimension of information and of its semantic properties. The nature of KGs meets one of the vocational pursuits of academic institutions, which is sharing their intellectual output, especially publications. In this paper, we describe and make available the Polito Knowledge Graph (PKG) –which semantically connects information on more than 23,000 publications and 34,000 authors– and Geranium, a semantic platform that leverages the properties of the PKG to offer advanced services for search and exploration. In particular, we describe the Geranium recommendation system, which exploits Graph Neural Networks (GNNs) to suggest collaboration opportunities between researchers of different disciplines. This work integrates the state of the art because we use data from a real application in the scholarly domain, while the current literature still explores the combination of KGs and GNNs in a prototypal context using synthetic data. The results shows that the fusion of these technologies represents a promising approach for recommendation and metadata inference in the scholarly domain.

Download Full-text

MNI: An enhanced multi-task neighborhood interaction model for recommendation on knowledge graph

PLoS ONE ◽

10.1371/journal.pone.0258410 ◽

2021 ◽

Vol 16 (10) ◽

pp. e0258410

Author(s):

Xintao Ma ◽

Liyan Dong ◽

Yuequn Wang ◽

Yongli Li ◽

Hao Zhang

Keyword(s):

Local Structure ◽

Recommendation System ◽

State Of The Art ◽

Side Information ◽

Interaction Model ◽

Knowledge Graph ◽

Graph Structure ◽

Latent Features ◽

Real World Datasets ◽

Neighborhood Interaction

To alleviate the data sparsity and cold start problems for collaborative filtering in recommendation systems, side information is usually leveraged by researchers to improve the recommendation performance. The utility of knowledge graph regards the side information as part of the graph structure and gives an explanation for recommendation results. In this paper, we propose an enhanced multi-task neighborhood interaction (MNI) model for recommendation on knowledge graphs. MNI explores not only the user-item interaction but also the neighbor-neighbor interactions, capturing a more sophisticated local structure. Besides, the entities and relations are also semantically embedded. And with the cross&compress unit, items in the recommendation system and entities in the knowledge graph can share latent features, and thus high-order interactions can be investigated. Through extensive experiments on real-world datasets, we demonstrate that MNI outperforms some of the state-of-the-art baselines both for CTR prediction and top-N recommendation.

Download Full-text

Recommendation Systems: Algorithms, Challenges, Metrics, and Business Opportunities

Applied Sciences ◽

10.3390/app10217748 ◽

2020 ◽

Vol 10 (21) ◽

pp. 7748

Author(s):

Zeshan Fayyaz ◽

Mahsa Ebrahimian ◽

Dina Nawara ◽

Ahmed Ibrahim ◽

Rasha Kashef

Keyword(s):

Recommender Systems ◽

Recommendation System ◽

Information Overload ◽

State Of The Art ◽

Recommendation Systems ◽

Qualitative Evaluation ◽

Potential Influence ◽

Systems Research ◽

Current State

Recommender systems are widely used to provide users with recommendations based on their preferences. With the ever-growing volume of information online, recommender systems have been a useful tool to overcome information overload. The utilization of recommender systems cannot be overstated, given its potential influence to ameliorate many over-choice challenges. There are many types of recommendation systems with different methodologies and concepts. Various applications have adopted recommendation systems, including e-commerce, healthcare, transportation, agriculture, and media. This paper provides the current landscape of recommender systems research and identifies directions in the field in various applications. This article provides an overview of the current state of the art in recommendation systems, their types, challenges, limitations, and business adoptions. To assess the quality of a recommendation system, qualitative evaluation metrics are discussed in the paper.

Download Full-text

The History of the Development of Melt Blowing Technology

International Nonwovens Journal ◽

10.1177/1558925099os-800123 ◽

1999 ◽

Vol os-8 (1) ◽

pp. 1558925099OS-80 ◽

Cited By ~ 8

Author(s):

John G. McCulloch

Keyword(s):

Melt Spinning ◽

State Of The Art ◽

Nonwoven Fabric ◽

Naval Research ◽

Melt Blowing ◽

Current State ◽

Spinning Process ◽

History Of ◽

One Step ◽

Oil Company

Almost a half century ago development efforts were initiated by very different entities, in widely different locations, to demonstrate one step processes to convert polymer to web: • Major fiber producers (DuPont, Freudenberg, Monsanto) began work on converting polymer (PE, PET, Nylon) into continuous “cold drawn” filaments and integrating the conversion of these filaments into a random-laid bonded nonwoven fabric. • An oil company (Exxon), building on the earlier work (1950's) of the Naval Research Labs to produce fine fibers, began work on converting their recently commercialized PP polymer into discontinuous, or continuous, “hot drawn” filaments and integrating these filaments into a random-laid self bonded nonwoven web having average fiber sizes 2–5 microns (fine fibered webs) to 100+ fibers (coarse fibered webs). As a result of these early development efforts, three different, but related melt spinning nonwoven processes have achieved significant commercial importance, with tremendous benefits to consumers worldwide: • Spunbond process • Melt blowing process • Flash spinning process This presentation will summarize the development of the melt blowing process from conceptualization to current state-of-the-art. Important product, process and equipment developments are detailed in the 50 year growth of the melt blowing process from a laboratory concept to a 125 million pound a year U.S. and Canadian commercial business and substantial additional worldwide consumption. Today, spunbond and melt blown processes are used for approximately 54% of the total 18.6 million square yards U.S. nonwoven market.

Download Full-text

Modelling Processes and Products in the Cereal Chain

Foods ◽

10.3390/foods10010082 ◽

2021 ◽

Vol 10 (1) ◽

pp. 82

Author(s):

Otilia Carvalho ◽

Maria N. Charalambides ◽

Ilija Djekić ◽

Christos Athanassiou ◽

Serafim Bakalis ◽

...

Keyword(s):

Supply Chain ◽

Predictive Models ◽

Food Processing ◽

State Of The Art ◽

Current State ◽

The World ◽

Modelling Techniques ◽

One Step ◽

High Level ◽

Different Parts

In recent years, modelling techniques have become more frequently adopted in the field of food processing, especially for cereal-based products, which are among the most consumed foods in the world. Predictive models and simulations make it possible to explore new approaches and optimize proceedings, potentially helping companies reduce costs and limit carbon emissions. Nevertheless, as the different phases of the food processing chain are highly specialized, advances in modelling are often unknown outside of a single domain, and models rarely take into account more than one step. This paper introduces the first high-level overview of modelling techniques employed in different parts of the cereal supply chain, from farming to storage, from drying to milling, from processing to consumption. This review, issued from a networking project including researchers from over 30 different countries, aims at presenting the current state of the art in each domain, showing common trends and synergies, to finally suggest promising future venues for research.

Download Full-text

Multitask Healthcare Management Recommendation System Leveraging Knowledge Graph

Journal of Healthcare Engineering ◽

10.1155/2021/1233483 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Wanheng Liu ◽

Ling Yin ◽

Cong Wang ◽

Fulin Liu ◽

Zhiyu Ni

Keyword(s):

Deep Neural Network ◽

Recommendation System ◽

State Of The Art ◽

Healthcare Management ◽

Treatment Programs ◽

Treatment Recommendation ◽

Knowledge Graph ◽

Disease Prediction ◽

Smart Healthcare ◽

5G Network

In this paper, a novel multitask healthcare management recommendation system leveraging the knowledge graph is proposed, which is based on deep neural network and 5G network, and it can be applied in mobile and terminal device to free up medical resources and provide treatment programs. The technique we applied is referred to as KG-based recommendation system. When several experiments have been carried out, it is demonstrated that it is more intelligent and precise in disease prediction and treatment recommendation, similar to the state of the art. Also, it works well in the accuracy and comprehension, which is much higher and highly consistent with the predictions of the theoretical model. The fact that our work involves studies of multitask healthcare management recommendation system, which can contribute to the smart healthcare development, proves to be promising and encouraging.

Download Full-text