The use of an Explainable Artificial Intelligence Tool for Decision-making Support in Virtual Learning Environments

Jun 6, 20191 like429 views

A joint work of Jose Maria Alonso (Universidade de Santiago de Compostela, Spain) and Gabriella Casalino (University of Bari Aldo Moro, Italy) Presented at HELMeTO 2019 - International Workshop on Higher Education Learning Methodologies and Technologies Online, June 6-7, 2019, Novedrate (CO), Italy full text: https://link.springer.com/chapter/10.1007/978-3-030-31284-8_10

The use of an Explainable Arti?cial Intelligence Tool
for Decision-making Support
in Virtual Learning Environments
Jose Maria Alonso
Universidade de Santiago de
Compostela, Spain
Gabriella Casalino
University of Bari Aldo Moro, Italy,
HELMeTO 2019
International Workshop on
Higher Education Learning Methodologies and Technologies Online
June 6-7, 2019, Novedrate (CO), Italy

Distance Learning
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy

Educational Data Mining
and Learning Analytics
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy

Educational Data Mining
and Learning Analytics
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy
Experts
?

Explainable Arti?cial
Intelligence - XAI
There is a gap between data and human users
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy
Explainable AI refers to techniques
in AI which can be trusted and
easily understood by humans.

ExpliClas
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy
https://demos.citius.usc.es/ExpliClas/
https://demos.citius.usc.es/ExpliClasAPI/
Jose M. Alonso, A. Bugarín, “ExpliClas:
Automatic Generation of Explanations in Natural
Language for Weka Classi?ers”, IEEE
International Conference on Fuzzy Systems
(FUZZ-IEEE), New Orleans, USA, 1-6, 2019

OULAD Dataset
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy
https://analyse.kmi.open.ac.uk/open_dataset

Furia
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy

J48
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy

Conclusions and Future
Work
? ExpliClas XAI tool to analyze educational data
? Multimodal explanations: graphs + text.
? Global explanation
? Local explanation
? Online survey about the goodness of the
explanations
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy

Thanks
Gabriella Casalino
gabriella.casalino@uniba.it
HELMeTO 2019 - June 6-7, 2019, Novedrate (CO), Italy
Jose Maria Alonso
josemaria.alonso.moral@usc.es

The document describes a data management and visualization platform for smart cities and IoT called Snap4City. It uses a lambda architecture to process streaming and batch data using tools like HDFS, Elasticsearch, Kibana and Node-RED. The platform was tested using SolrCloud and Elasticsearch to index 30 million documents totaling 7GB. Elasticsearch had better performance, scaling to 4500 parallel requests while SolrCloud broke down after 1500 requests. CPU usage increased linearly as requests grew.

Smart Networks: Blockchain, Deep Learning, and Quantum ComputingMelanie Swan

Head-on collision of two spherical grains with 2-d internal structureSparisoma Viridi

AFOLAYAN CURRICULUM VITAEAbimbola Afolayan

This curriculum vitae outlines the educational and professional background of Afolayan A.H. It includes her personal details, educational history, qualifications, publications, memberships, grants, and conferences attended. She holds a B.Tech in Computer Science from Federal University of Technology Akure, an M.Tech also from FUTA, and a Ph.D in Computer Science from the same institution. She has published papers in various journals and conferences and received grants to attend international conferences.

Incremental rebalancing learning on evolving data streamsAlessio Bernardo

Nowadays, every device connected to the Internet generates an ever-growing stream of data (formally, unbounded). Machine Learning on unbounded data streams is a grand challenge due to its resource constraints. In fact, standard machine learning techniques are not able to deal with data whose statistics is subject to gradual or sudden changes without any warning. Massive Online Analysis (MOA) is the collective name, as well as a software library, for new learners that are able to manage data streams. We present a research study on streaming rebalancing. Indeed, data streams can be imbalanced as static data, but there is not a method to rebalance them incrementally, one element at a time. For this reason we propose a new streaming approach able to rebalance data streams online. Our new methodology is evaluated against some synthetically generated datasets using prequential evaluation in order to demonstrate that it outperforms the existing approaches.

20210224_Kirkby_EMinar.pdfMavia4

MTPy is an open-source Python toolbox for processing, analyzing, modeling, and visualizing magnetotelluric (MT) data. It was initiated in 2013 and is currently maintained by Geoscience Australia in collaboration with other groups. MTPy provides modules for reading and writing MT data files, dimensionality analysis, strike analysis, phase tensor calculations, penetration depth calculations, data plotting, and generating inputs and visualizing outputs for 1D, 2D, and 3D MT inversion codes. The documentation provides guidance on installing MTPy and example Jupyter notebooks demonstrate its practical applications using real MT datasets.

Myrror: una piattaforma per Holistic User Modeling e Quantified SelfCataldo Musto

EU Brasil Cloud ForumWalton Institute

This document summarizes the discussions from a working group session on future scenarios and research challenges for cloud computing collaboration between the EU and Brazil. The working group identified five potential future scenarios for sustainable living enabled by cloud computing: 1) environmental monitoring, 2) smart water and energy management, 3) assisted health and well-being, 4) heterogeneous cloud radio access networks, and 5) base station virtualization in cloud-radio access networks. They also identified three main drivers that present challenges for developing cloud computing technologies to achieve these scenarios: technologies being global and pervasive, socio-economic factors affecting cloud markets, and technological innovation creating new issues. Based on this analysis, the working group proposed seven potential research opportunities for EU-Brazil collaboration

Video, AI and News: video analysis and verification technologies for supporti...VasileiosMezaris

The document discusses how AI technologies can support journalism by verifying third-party video content, understanding video content through annotation and discovery, and adapting content for different platforms and audiences through summarization. It describes tools that utilize video fragmentation, deep learning models, and generative adversarial networks to verify video authenticity, annotate video concepts and captions, enable video search, and create customized video summaries. The document argues that AI tools can help journalists efficiently manage and repurpose video content while avoiding distribution of false information.

Herramientas 2.0 para el desarrollo de competencias profesionalizadorasIsmael Pe?a-López

Pedro Fonseca - Work 4 0 Pedro Fonseca

EUBrasilCloudFORUM Working Group on future scenarios and research challengesEUBrasilCloudFORUM .

Congresso Sociedade Brasileira de Computa??o CSBC2016 Porto Alegre (Brazil) Workshop on Cloud Networks & Cloudscape Brazil - James Clarke, Waterford Institute of Technology, Ireland - Moacyr Martucci, Department of Engineering and Digital Systems of Polytechnic School of University of S?o Paulo, EUBrasilCloudFORUM member and Brazilian National Contact Point Coordinator for the Horizon 2020 and for ERC, Brazil EUBrasilCloudFORUM Working Group on future scenarios and research challenges

Humans, AI & WorkGeorge Tilesch

Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Amélie Gyrard

CV_academicAniello De Santo

This document is a curriculum vitae for Aniello De Santo, who is currently a PhD student in Linguistics at Stony Brook University. He has received degrees in Computer Science and Engineering from Università degli Studi di Pavia. His research focuses on natural language processing, social network analysis, and computational linguistics. He has published papers in peer-reviewed conferences and served as a teaching assistant and research assistant at various universities.

AGINFRA+ on EOSCHubWeekAGINFRA

The AGINFRA PLUS project received funding from the European Union's Horizon 2020 research program to accelerate user-driven innovation in e-infrastructure for food and agriculture. The three year project involves seven partners across Europe led by AGRO-KNOW IKE. It aims to develop innovative applications and workflows powered by open e-infrastructures to strengthen the AGINFRA virtual research environment for the agriculture and food domains. Three initial pilot applications will focus on agro-climatic and economic modeling, food safety risk assessment, and food security issues.

AGINFRA+ project (Agriculture and food)EOSC-hub project

Deep Learning Explained: The future of Artificial Intelligence and Smart Netw...Melanie Swan

This talk provides an overview of an important emerging artificial intelligence technology, deep learning neural networks. Deep learning is a branch of computer science focused on machine learning algorithms that model and make predictions about data. A key distinction is that deep learning is not merely a software program, but a new class of information technology that is changing the concept of the modern technology project by replacing hard-coded software with a capacity to learn and execute tasks. In the future, deep learning smart networks might comprise a global computational infrastructure tackling real-time data science problems such as global health monitoring, energy storage and transmission, and financial risk assessment.

Explanation Strategies - Advances in Content-based Recommender SystemCataldo Musto

This document summarizes a talk on content-based explanation strategies for recommender systems. It discusses using linked open data to provide explanations based on descriptive properties of recommended items and the user's preferences. It also discusses using sentiment analysis and text summarization of user reviews to justify recommendations. The talk presents the ExpLOD framework for generating explanations from linked open data and evaluates it in a user study comparing it to popularity-based and non-personalized baselines.

8th International Conference on Natural Language Processing (NLP 2019)aciijournal

On-line training and monitoring of robot tasks through virtual reality FAST-Lab. Factory Automation Systems and Technologies Laboratory, Tampere University of Technology

International conference on Advanced Natural Language Processing (AdNLP 2020)ijcsa

EDAIM 110 juni 08butest

This document provides a summary of upcoming artificial intelligence (AI) conferences and events in June and July 2008. It lists 32 upcoming conferences, workshops, and competitions covering a wide range of AI topics such as automated planning, machine learning, swarm intelligence, and more. Many have submission deadlines in June 2008. It also provides details on the ECCAI Bulletin, an electronic newsletter about European AI activities, and notifications regarding access to AI journals and membership in related organizations.

EDAIM 110 juni 08butest

This document provides a summary of upcoming artificial intelligence conferences and events. It announces deadlines for AAAI-08/IAAI-08 on May 16th for early registration. It also announces deadlines of May 6th for demo submissions to AIIDE-08 and June 15th for paper/poster submissions to AI-2008 in Cambridge, UK. The document provides links and details on each event for topics, dates, and calls for participation.

Upcoming Academic Conferences In Italy in December, 2019All Conference Alert

Finding upcoming academic conferences in Italy has never been this easy. Leading global conference listing & promotion platform- AllConferenceAlert brings you complete details of recent & upcoming conferences across 140 academic fields of study. We segregate all conferences and scientific events in Italy on basis of areas of research and location to make it easier for our users to find information & be notified about upcoming conferences in their niche.

IRJET- Detecting Fake NewsIRJET Journal

This document discusses an approach to detecting fake news statements made by public figures using artificial intelligence. Three classification algorithms (Naive Bayes, Support Vector Machines, Random Forrest Classifier) were tested on a dataset of statements labeled as true or false. The Random Forrest Classifier achieved the best results, correctly classifying statements 86% of the time. The paper concludes the results could be improved by using more data and advanced deep learning models in future work.

Wandering Robots in Hungarian Primary Schools: a Case StudyIKT Masterminds Research Group

IJCCI2023.pdfGabriella Casalino

Semi-Supervised Fuzzy C-Means for Regression We propose a method to perform regression on partially labeled data, which is based on SSFCM (Semi-Supervised Fuzzy C-Means), an algorithm for semi-supervised classification based on fuzzy clustering. The proposed method, called SSFCM-R, precedes the application of SSFCM with a relabeling module based on target discretization. After the application of SSFCM, regression is carried out according to one out of two possible schemes: (i) the output corresponds to the label of the closest cluster; (ii) the output is a linear combination of the cluster labels weighted by the membership degree of the input. Some experiments on synthetic data are reported to compare both approaches. IJCCI 15th International joint Conference on Computational Intelligence, 13-15 November, 2023, Rome, Italy full paper: https://www.researchgate.net/publication/375671573_Semi-Supervised_Fuzzy_C-Means_for_Regression

On the use of the Dynamic Incremental Semi-Supervised Fuzzy Clustering Algori...Gabriella Casalino

More Related Content

Similar to The use of an Explainable Artificial Intelligence Tool for Decision-making Support in Virtual Learning Environments (20)

EU Brasil Cloud ForumWalton Institute

Video, AI and News: video analysis and verification technologies for supporti...VasileiosMezaris

Herramientas 2.0 para el desarrollo de competencias profesionalizadorasIsmael Pe?a-López

Pedro Fonseca - Work 4 0 Pedro Fonseca

EUBrasilCloudFORUM Working Group on future scenarios and research challengesEUBrasilCloudFORUM .

Humans, AI & WorkGeorge Tilesch

Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Amélie Gyrard

CV_academicAniello De Santo

AGINFRA+ on EOSCHubWeekAGINFRA

AGINFRA+ project (Agriculture and food)EOSC-hub project

Deep Learning Explained: The future of Artificial Intelligence and Smart Netw...Melanie Swan

Explanation Strategies - Advances in Content-based Recommender SystemCataldo Musto

8th International Conference on Natural Language Processing (NLP 2019)aciijournal

On-line training and monitoring of robot tasks through virtual reality FAST-Lab. Factory Automation Systems and Technologies Laboratory, Tampere University of Technology

International conference on Advanced Natural Language Processing (AdNLP 2020)ijcsa

EDAIM 110 juni 08butest

Upcoming Academic Conferences In Italy in December, 2019All Conference Alert

IRJET- Detecting Fake NewsIRJET Journal

Wandering Robots in Hungarian Primary Schools: a Case StudyIKT Masterminds Research Group

EU Brasil Cloud ForumWalton Institute

Video, AI and News: video analysis and verification technologies for supporti...VasileiosMezaris

Herramientas 2.0 para el desarrollo de competencias profesionalizadorasIsmael Pe?a-López

Pedro Fonseca - Work 4 0 Pedro Fonseca

EUBrasilCloudFORUM Working Group on future scenarios and research challengesEUBrasilCloudFORUM .

Humans, AI & WorkGeorge Tilesch

Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Amélie Gyrard

CV_academicAniello De Santo

AGINFRA+ on EOSCHubWeekAGINFRA

AGINFRA+ project (Agriculture and food)EOSC-hub project

Deep Learning Explained: The future of Artificial Intelligence and Smart Netw...Melanie Swan

Explanation Strategies - Advances in Content-based Recommender SystemCataldo Musto

8th International Conference on Natural Language Processing (NLP 2019)aciijournal

On-line training and monitoring of robot tasks through virtual reality FAST-Lab. Factory Automation Systems and Technologies Laboratory, Tampere University of Technology

International conference on Advanced Natural Language Processing (AdNLP 2020)ijcsa

EDAIM 110 juni 08butest

Upcoming Academic Conferences In Italy in December, 2019All Conference Alert

IRJET- Detecting Fake NewsIRJET Journal

Wandering Robots in Hungarian Primary Schools: a Case StudyIKT Masterminds Research Group

More from Gabriella Casalino (15)

IJCCI2023.pdfGabriella Casalino

On the use of the Dynamic Incremental Semi-Supervised Fuzzy Clustering Algori...Gabriella Casalino

A mHealth solution for contact-less self-monitoring of vital sign parametersGabriella Casalino

Text mining through Non Negative Matrix FactorizationsGabriella Casalino

The 2nd International Conference on Machine Learning and Intelligent Systems (MLIS2020) October 25-28, 2020, Online Conference References: G. Casalino, C. Castiello, N. Del Buono, C. Mencar, (2018) A framework for intelligent Twitter data analysis with non-negative matrix factorization, International Journal of Web Information Systems, Vol. 14 Issue: 3, pp.334-356, https://doi.org/10.1108/IJWIS-11-2017-0081 Casalino G., Castiello C., Del Buono N., Mencar C. (2017) Intelligent Twitter Data Analysis Based on Nonnegative Matrix Factorizations. In: Gervasi O. et al. (eds) Computational Science and Its Applications – ICCSA 2017. ICCSA 2017. Lecture Notes in Computer Science, vol 10404, pages 188--202. Springer G.Casalino, N.Del Buono, C. Mencar, (2016), Non Negative Matrix Factorisations for Intelligent Data Analysis, in G.R. Naik (ed.), Nonnegative Matrix Factorization Techniques, Signals and Communication Technology, ISBN: 978-3-662-48330-5, http://dx.doi.org/10.1007/978-3-662-48331-2_2.

Dynamic Incremental Semi-supervised Fuzzy Clustering for Bipolar Disorder Epi...Gabriella Casalino

A mHealth solution for contact-less self-monitoring of vital signs parametersGabriella Casalino

This document describes a contactless mHealth solution for self-monitoring vital signs using a webcam. The solution extracts photoplethysmography signals from video of a person's face to estimate blood oxygen saturation levels. It uses face detection, tracking of regions of interest, and signal processing techniques. The estimated vital signs are then used in a fuzzy inference system to predict cardiovascular risk levels. The goal is to provide an affordable, easy to use method for remote patient monitoring.

Dynamic Incremental Semi-Supervised Fuzzy Clustering for Data Stream Classifi...Gabriella Casalino

Incremental and Adaptive fuzzy clustering for Virtual Learning Environments D...Gabriella Casalino

Data stream classification by incremental semi-supervised fuzzy clusteringGabriella Casalino

Incremental adaptive semi-supervised fuzzy clustering for data stream classif...Gabriella Casalino

Intelligent data analysis through Nonnegative matrix factorization (NMF): app...Gabriella Casalino

Non-negative factorization methods for extracting semantically relevant featu...Gabriella Casalino

This document discusses non-negative matrix factorization methods for dimensionality reduction and feature extraction in intelligent data analysis. It begins with an outline of non-negative matrix factorization background and applications. Next, it describes how non-negative matrix factorization can be used for tasks like document clustering by discovering semantic features in text while preserving data non-negativity. Finally, it proposes using subtractive clustering to provide the initial matrices for non-negative matrix factorization, which helps guide the number of clusters.

ICCSA2014 - slidesGabriella Casalino

Didamatica2012 - slidesGabriella Casalino

WILF2011 - slidesGabriella Casalino