Structured Data-Driven Operating Policies for Commodity Storage

2019 ◽  
Author(s):  
Christian Mandl ◽  
Selvaprabu Nadarajah ◽  
Stefan Minner ◽  
Srinagesh Gavirneni
JAMIA Open ◽  
2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Fuchiang R Tsui ◽  
Lingyun Shi ◽  
Victor Ruiz ◽  
Neal D Ryan ◽  
Candice Biernesser ◽  
...  

Abstract Objective Limited research exists in predicting first-time suicide attempts that account for two-thirds of suicide decedents. We aimed to predict first-time suicide attempts using a large data-driven approach that applies natural language processing (NLP) and machine learning (ML) to unstructured (narrative) clinical notes and structured electronic health record (EHR) data. Methods This case-control study included patients aged 10–75 years who were seen between 2007 and 2016 from emergency departments and inpatient units. Cases were first-time suicide attempts from coded diagnosis; controls were randomly selected without suicide attempts regardless of demographics, following a ratio of nine controls per case. Four data-driven ML models were evaluated using 2-year historical EHR data prior to suicide attempt or control index visits, with prediction windows from 7 to 730 days. Patients without any historical notes were excluded. Model evaluation on accuracy and robustness was performed on a blind dataset (30% cohort). Results The study cohort included 45 238 patients (5099 cases, 40 139 controls) comprising 54 651 variables from 5.7 million structured records and 798 665 notes. Using both unstructured and structured data resulted in significantly greater accuracy compared to structured data alone (area-under-the-curve [AUC]: 0.932 vs. 0.901 P < .001). The best-predicting model utilized 1726 variables with AUC = 0.932 (95% CI, 0.922–0.941). The model was robust across multiple prediction windows and subgroups by demographics, points of historical most recent clinical contact, and depression diagnosis history. Conclusions Our large data-driven approach using both structured and unstructured EHR data demonstrated accurate and robust first-time suicide attempt prediction, and has the potential to be deployed across various populations and clinical settings.


Author(s):  
Elena Cabrio ◽  
Serena Villata

Argument mining is the research area aiming at extracting natural language arguments and their relations from text, with the final goal of providing machine-processable structured data for computational models of argument. This research topic has started to attract the attention of a small community of researchers around 2014, and it is nowadays counted as one of the most promising research areas in Artificial Intelligence in terms of growing of the community, funded projects, and involvement of companies. In this paper, we present the argument mining tasks, and we discuss the obtained results in the area from a data-driven perspective. An open discussion highlights the main weaknesses suffered by the existing work in the literature, and proposes open challenges to be faced in the future.


Designs ◽  
2019 ◽  
Vol 3 (3) ◽  
pp. 44 ◽  
Author(s):  
Md Ashikul Alam Khan ◽  
Javaid Butt ◽  
Habtom Mebrahtu ◽  
Hassan Shirvani ◽  
Alireza Sanaei ◽  
...  

Process re-engineering and optimization in manufacturing industries is a big challenge because of process interdependencies characterized by a high failure rate. Research has shown that over 70% of approaches fail because of complexity as a result of process interdependencies during the implementation phase. This paper investigates data from a manufacturing operation and designs a filtration algorithm to analyze process interdependencies as a new approach for process optimization. The algorithm examines the data from a manufacturing process to identify limitations through cause and effect relationships and implements changes to achieve an optimized result. The proposed cause and effect approach of re-engineering is termed the Khan-Hassan-Butt (KHB) methodology, and it can filter the process interdependencies and use those as key decision-making tools. It provides an improved process optimization framework that incorporates data analysis along with a cause and effect algorithm to filter out the process interdependencies as an approach to increase output and reduce failure factors simultaneously. It also provides a framework for filtering the manufacturing data into smart structured data. Based on the proposed KHB methodology, the study investigated a production line process using the WITNESS Horizon 22 simulation package and analyzed the efficiency of the proposed approach for production optimization. A case study is provided that integrated the KHB methodology with data-driven process re-engineering to analyze the process interdependencies to use them as decision-making tools for production optimization.


2018 ◽  
Vol 17 (02) ◽  
pp. 583-620 ◽  
Author(s):  
Thierno M. L. Diallo ◽  
Sébastien Henry ◽  
Yacine Ouzrout ◽  
Abdelaziz Bouras

This paper provides a comprehensive data-driven diagnosis approach applicable to complex manufacturing industries. The proposed approach is based on the Bayesian network paradigm. Both the implementation of the Bayesian model (the structure and parameters of the network) and the use of the resulting model for diagnosis are presented. The construction of the structure taking into account the issue related to the explosion in the number of variables and the determination of the network’s parameters are addressed. A diagnosis procedure using the developed Bayesian framework is proposed. In order to provide the structured data required for the construction and the usage of the diagnosis model, a unitary traceability data model is proposed and its use for forward and backward traceability is explained. Finally, an industrial benchmark — the Tennessee Eastman process — is utilized to show the ability of the developed framework to make an accurate diagnosis.


2020 ◽  
Vol 12 (4) ◽  
pp. 3443-3452
Author(s):  
Hong-He Xu ◽  
Zhi-Bin Niu ◽  
Yan-Sen Chen

Abstract. Big data are significant for quantitative analysis and contribute to data-driven scientific research and discoveries. Here a brief introduction is given to the Geobiodiversity Database (GBDB), a comprehensive stratigraphic and palaeontological database, and its data. The GBDB includes abundant geological records from China and has supported a series of scientific studies on the Paleozoic palaeogeography and tectonic and biodiversity evolution of China. The data that the GBDB has including those that are newly collected are described in detail; the statistical results and structure of the data are given. A comparison between the GBDB; the largest palaeobiological database, the Paleobiology Database (PBDB); and the geological rock database Macrostrat is drawn. The GBDB and other databases are complementary in palaeontological and stratigraphic research. The GBDB will continually provide users access to detailed palaeontological and stratigraphic data based on publications. Non-structured data of palaeontology and stratigraphy will also be included in the GBDB, and they will be organically correlated with the existing data of the GBDB, making the GBDB more widely used for both researchers and anyone who is interested in fossils and strata. The GBDB fossil and stratum dataset (Xu, 2020) is freely downloadable from https://doi.org/10.5281/zenodo.4245604.


Sign in / Sign up

Export Citation Format

Share Document