Automatically Identifying Eviction Cases and Outcomes Within Case Law of Dutch Courts of First Instance

In this paper we attempt to identify eviction judgements within all case law published by Dutch courts in order to automate data collection, previously conducted manually. To do so we performed two experiments. The first focused on identifying judgements related to eviction, while the second focused on identifying the outcome of the cases in the judgements (eviction vs. dismissal of the landlord’s claim). In the process of conducting the experiments for this study, we have created a manually annotated dataset with eviction-related judgements and their outcomes.

Identification of Low Population States in Cryo-EM Using Deep Learning

Cryo-EM has made extraordinary headway towards becoming a semi-automated, high-throughput structure determination technique. In the general workflow, high-to-medium population states are grouped into two- and three-dimensional classes, from which structures can be obtained with near-atomic resolution and subsequently analyzed to interpret function. However, low population states, which are also functionally important, are often discarded. Here, we describe a technique whereby low population states can be efficiently identified with minimal human effort via a deep convolutional neural network classifier. We use this deep learning classifier to describe a transient, low population state of bacteriophage A511 in the midst of infecting its bacterial host. This method can be used to further automate data collection and identify other functionally important low population states.

Artificial Intelligence in Metrology Data Collection

Many companies have tried to automate data collection for handheld Digital Multimeters (DMM) using Optical Character Recognition (OCR). Only recently have companies tried to perform this task using Artificial Intelligence (AI) technology, Cal Lab Solutions being one of them in 2020. But when we developed our first prototype application, we discovered the difficulties of getting a good value with every measurement and test point.A year later, lessons learned and equipped with better software, this paper is a continuation of that AI project. In Beta-,1 we learned the difficulties of AI reading segmented displays. There are no pre-trained models for this type of display, so we needed to train a model. This required the testing of thousands of images, so we changed the scope of the project to a continual learning AI project. This paper will cover how we built our continuous learning AI model to show how any lab with a webcam can start automating those handheld DMMS with software that gets smarter over time.

Graph Visualization of the Characteristics of Complex Objects on the Example of the Analysis of Politicians

The paper considers the task of analyzing complex interconnected objects using graph construction. There is no unified tool for constructing graphs. Some solutions can build graphs limited by the number of nodes, while others do not visually display data. The Gephi application was used to construct graphs for the research. Gephi has great functionality for building and analyzing graphs. The subject of research is a politician with a certain set of characteristics. In the paper an algorithm that enables to automate data collection on politicians was developed. One of the main methods of data collecting on the Internet is web scraping. Web scraping software may access the World Wide Web directly using the HTTP, or through a web browser. While web scraping can be done manually by a software user, the term typically refers to automated processes implemented using a software agent. The data was necessary for constructing graphs and their analysis. The use of graphs enables to see various types of relationships, including mediate. This methodology enables to change the attitude towards the analysis of multidi-mensional objects.

A guide to using the Internet to monitor and quantify the wildlife trade

The unrivalled growth in e-commerce of animals and plants presents an unprecedented opportunity to monitor wildlife trade to inform conservation, biosecurity, and law enforcement. Using the Internet to quantify the scale of the wildlife trade (volume, frequency) is a relatively recent and rapidly developing approach, which currently lacks an accessible framework for locating relevant websites and collecting data. Here, we present an accessible guide for Internet-based wildlife trade surveillance, which uses a repeatable and systematic method to automate data collection from relevant websites. Our guide is adaptable to the multitude of trade-based contexts including different focal taxa or derived parts, and locations of interest. We provide information for working with the diversity of websites that trade wildlife, including social media platforms. Finally, we discuss the advantages and limitations of web data, including the challenges presented by trade occurring on clandestine sections of the Internet (e.g., deep and dark web).

First year outcomes of an initiative to increase BRCA testing among NCCN guideline-eligible breast cancer patients within a large community OCM practice.

1540 Background: Pathogenic variants in BRCA1/BRCA2 can affect a breast CA pts care: preventative interventions, surgical decisions, medical treatments, screening, and family counseling. National data suggests significant non-adherence to NCCN testing guidelines, with only 1/3 of eligible pts referred for genetic services. In 2018, OHC (Cincinnati) launched an APP-centric genetics program. Specially trained APPs carry out genetic counseling and order NCCN-compliant testing. Early data suggested a significant deficit in physician-driven referrals. From 1/01/18 - 07/31/18, 138 new breast pts were estimated to be NCCN guideline-eligible. Only 28 (20%) pts received genetic services. Methods: In 2019, the OHC genetics team implemented a standardized screening process for every new breast CA pt. An EMR template (iKnowMed G2) that included NCCN guidelines was created for initial breast CA consultation and Oncology Care Model (OCM) treatment planning. All pts, not just OCM pts, are subject to OCM treatment planning. This automated screening method ensured all breast CA pts were screened, drastically increasing compliance. Through integration of genetics screening into the templates, pts meeting NCCN criteria for testing are reflexively referred for genetic counseling. With USON/McKesson, integrated data fields were developed in the EMR to automate data collection. Results: From 01/01/19 – 12/31/19, 717 new breast CA pts were seen at OHC. 676/717 (94%) were screened. Of those screened, 279 new breast CA pts met NCCN criteria for BRCA testing. 140 (50%) eligible new pts had appts with the genetics team. Another 50 (18%) had confirmed testing outside of OHC. 57 (20%) refused appts and/or testing. 32 (11%) did not have appts, representing screen fails. Referrals in non-breast CA pts also increased by 127%; 604 (2019) vs 264 (2018) suggesting a halo effect. Analyses suggest the program to be economically viable, with a financial growth rate of 127%. Conclusions: EMR templates embedded with the NCCN guidelines for reflex genetics referral can appropriately increase the utilization of genetic services. Breast genetics screening and resultant appt/testing rates increased significantly 2019 vs 2018. Success in BRCA testing in breast CA will lead to expansion to other cancers and genes. Implementation of structured EMR genetics data fields can automate data collection and measure compliance. Integration of genetics screening into universal OCM treatment planning is feasible, economically viable and scalable.

Assessment of Complex Performances in Digital Environments

Digital technologies hold the potential to transform educational assessment. Recent advances reveal that digital environments will support the development of learning and assessment activities in ways that will both increase the inferential fidelity of assessments and change the form of assessments altogether. Digital technologies can also automate data collection and the production of assessment inferences on a massive scale. Here, we discuss the wide variation in digital learning experiences and explain how they are transforming traditional language for discussing assessment. We argue that the predigital constraints on assessment have skewed our thinking about assessment and give examples of new and novel approaches. Second, we discuss how digital environments can allow us to capture and make inferences from simple or complex learning activities in new ways. Third, we point to advances in machine learning and AI that have the potential to change current and future assessment practices. Finally, we argue for balancing enthusiasm for digital environments against the challenges of making appropriate assessment inferences.

From Principles to Practice

The College of Business Administration (CBA) is part of a mid-sized urban university with a primary focus on teaching. It had recently decided to develop a process for defining student learning objectives and outcomes, measuring success in achieving these, and using the results of those measures for continuously improving the quality of student learning. Its aim was to design and develop a system which could automate data collection and streamline the processes of course effectiveness evaluation and course/curriculum enhancement. Even though many challenges still existed for the college, it nevertheless launched into a logical design of the Student Learning Outcome Assessment System (SLOAS). Alexis, the college’s IT Manager, was assigned the responsibility for managing this project. She determined this system would be used for data collection and reporting in order to provide evidence that student learning outcomes were being achieved at the course, college, and potentially university levels. Amid the lack of internal development resources, insufficient IT support, constantly changing standards and policies, budget issues, and so forth. Alexis knew that she was faced with a challenging project.