https://reunir.unir.net/handle/123456789/12882 2024-11-03T14:10:33Z 2024-11-03T14:10:33Z Alonso-Betanzos, Amparo Cabalar, Pedro Dimuro, Gracaliz P. García, Marcos Hernández-Orallo, José Hervás, Raquel Manjarés, Ángeles Martínez-Plumed, Fernado Mora-Jiménez, Inmaculada Sànchez-Marrè, Miquel https://reunir.unir.net/handle/123456789/12920 2022-05-19T06:47:10Z

Editor's Note Alonso-Betanzos, Amparo; Cabalar, Pedro; Dimuro, Gracaliz P.; García, Marcos; Hernández-Orallo, José; Hervás, Raquel; Manjarés, Ángeles; Martínez-Plumed, Fernado; Mora-Jiménez, Inmaculada; Sànchez-Marrè, Miquel Artificial Intelligence has become nowadays one of the main relevant technologies that is driven us to a new revolution, a change in society, just as well as other human inventions, such as navigation, steam machines, or electricity did in our past. There are several ways in which AI might be developed, and the European Union has chosen a path, a way to transit through this revolution, in which Artificial Intelligence will be a tool at the service of Humanity. That was precisely the motto of the 2020 European Conference on Artificial Intelligence (“Paving the way towards Human-Centric AI”), of which these special issue is a selection of the best papers selected by the organizers of some of the Workshops in ECAI 2020. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T09:38:07Z No. of bitstreams: 1 ijimai_6_5_0.pdf: 497691 bytes, checksum: ed2c7b345639776423b1760faae18f47 (MD5); Made available in DSpace on 2022-04-25T09:38:07Z (GMT). No. of bitstreams: 1 ijimai_6_5_0.pdf: 497691 bytes, checksum: ed2c7b345639776423b1760faae18f47 (MD5)

Zhang, Sicui Genga, Laura Yan, Hui Nie, Hongchao Lu, Xudong Kaymak, Uzay https://reunir.unir.net/handle/123456789/12919 2022-04-25T09:29:59Z

Towards Multi-perspective Conformance Checking with Fuzzy Sets Zhang, Sicui; Genga, Laura; Yan, Hui; Nie, Hongchao; Lu, Xudong; Kaymak, Uzay Nowadays organizations often need to employ data-driven techniques to audit their business processes and ensure they comply with laws and internal/external regulations. Failing in complying with the expected process behavior can indeed pave the way to inefficiencies or, worse, to frauds or abuses. An increasingly popular approach to automatically assess the compliance of the executions of organization processes is represented by alignment-based conformance checking. These techniques are able to compare real process executions with models representing the expected behaviors, providing diagnostics able to pinpoint possible discrepancies. However, the diagnostics generated by state of the art techniques still suffer from some limitations. They perform a crisp evaluation of process compliance, marking process behavior either as compliant or deviant, without taking into account the severity of the identified deviation. This hampers the accuracy of the obtained diagnostics and can lead to misleading results, especially in contexts where there is some tolerance with respect to violations of the process guidelines. In the present work, we discuss the impact and the drawbacks of a crisp deviation assessment approach. Then, we propose a novel conformance checking approach aimed at representing actors’ tolerance with respect to process deviations, taking it into account when assessing the severity of the deviations. As a proof of concept, we performed a set of synthetic experiments to assess the approach. The obtained results point out the potential of the usage of a more flexible evaluation of process deviations, and its impact on the quality and the interpretation of the obtained diagnostics. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T09:29:59Z No. of bitstreams: 1 ijimai_6_5_13.pdf: 1071887 bytes, checksum: 32b33cd6018b9ff2afe672e989a3c615 (MD5); Made available in DSpace on 2022-04-25T09:29:59Z (GMT). No. of bitstreams: 1 ijimai_6_5_13.pdf: 1071887 bytes, checksum: 32b33cd6018b9ff2afe672e989a3c615 (MD5)

Hernàndez-Carnerero, Àlvar Sànchez-Marrè, Miquel Mora-Jiménez, Inmaculada Soguero-Ruiz, Cristina Martínez-Agüero, Sergio Álvarez-Rodríguez, Joaquín https://reunir.unir.net/handle/123456789/12918 2022-04-25T09:24:37Z

Antimicrobial Resistance Prediction in Intensive Care Unit for Pseudomonas Aeruginosa using Temporal Data-Driven Models Hernàndez-Carnerero, Àlvar; Sànchez-Marrè, Miquel; Mora-Jiménez, Inmaculada; Soguero-Ruiz, Cristina; Martínez-Agüero, Sergio; Álvarez-Rodríguez, Joaquín One threatening medical problem for human beings is the increasing antimicrobial resistance of some microorganisms. This problem is especially difficult in Intensive Care Units (ICUs) of hospitals due to the vulnerable state of patients. Knowing in advance whether a concrete bacterium is resistant or susceptible to an antibiotic is a crux step for clinicians to determine an effective antibiotic treatment. This usual clinical procedure takes approximately 48 hours and it is named antibiogram. It tests the bacterium resistance to one or more antimicrobial families (six of them considered in this work). This article focuses on cultures of the Pseudomonas Aeruginosa bacterium because is one of the most dangerous in the ICU. Several temporal data-driven models are proposed and analyzed to predict the resistance or susceptibility to a determined antibiotic family previously to know the antibiogram result and only using the available past information from a data set. This data set is formed by anonymized electronic health records data from more than 3300 ICU patients during 15 years. Several data-driven classifier methods are used in combination with several temporal modeling approaches. The results show that our predictions are reasonably accurate for some antimicrobial families, and could be used by clinicians to determine the best antibiotic therapy in advance. This early prediction can save valuable time to start the adequate treatment for an ICU patient. This study corroborates the results of a previous work pointing that the antimicrobial resistance of bacteria in the ICU is related to other recent resistance tests of ICU patients. This information is very valuable for making accurate antimicrobial resistance predictions. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T09:24:37Z No. of bitstreams: 1 ijimai_6_5_12_0.pdf: 1767884 bytes, checksum: 2e4cbefa7dbbdd510a6f3472de7e0bc5 (MD5); Made available in DSpace on 2022-04-25T09:24:37Z (GMT). No. of bitstreams: 1 ijimai_6_5_12_0.pdf: 1767884 bytes, checksum: 2e4cbefa7dbbdd510a6f3472de7e0bc5 (MD5)

Zoe Cremer, Carla Whittlestone, Jess https://reunir.unir.net/handle/123456789/12917 2022-04-25T09:18:24Z

Artificial Canaries: Early Warning Signs for Anticipatory and Democratic Governance of AI Zoe Cremer, Carla; Whittlestone, Jess We propose a method for identifying early warning signs of transformative progress in artificial intelligence (AI), and discuss how these can support the anticipatory and democratic governance of AI. We call these early warning signs ‘canaries’, based on the use of canaries to provide early warnings of unsafe air pollution in coal mines. Our method combines expert elicitation and collaborative causal graphs to identify key milestones and identify the relationships between them. We present two illustrations of how this method could be used: to identify early warnings of harmful impacts of language models; and of progress towards high-level machine intelligence. Identifying early warning signs of transformative applications can support more efficient monitoring and timely regulation of progress in AI: as AI advances, its impacts on society may be too great to be governed retrospectively. It is essential that those impacted by AI have a say in how it is governed. Early warnings can give the public time and focus to influence emerging technologies using democratic, participatory technology assessments. We discuss the challenges in identifying early warning signals and propose directions for future work. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T09:18:24Z No. of bitstreams: 1 ijimai_6_5_8.pdf: 811659 bytes, checksum: effdef00ca187bdcd3b848a656965925 (MD5); Made available in DSpace on 2022-04-25T09:18:24Z (GMT). No. of bitstreams: 1 ijimai_6_5_8.pdf: 811659 bytes, checksum: effdef00ca187bdcd3b848a656965925 (MD5)

Rao S B, Pooja Agnihotri, Manish Babu Jayagopi, Dinesh https://reunir.unir.net/handle/123456789/12916 2022-04-25T09:02:55Z

Improving Asynchronous Interview Interaction with Follow-up Question Generation Rao S B, Pooja; Agnihotri, Manish; Babu Jayagopi, Dinesh The user experience of an asynchronous video interview system, conventionally is not reciprocal or conversational. Interview applicants expect that, like a typical face-to-face interview, they are innate and coherent. We posit that the planned adoption of limited probing through follow-up questions is an important step towards improving the interaction. We propose a follow-up question generation model (followQG) capable of generating relevant and diverse follow-up questions based on the previously asked questions, and their answers. We implement a 3D virtual interviewing system, Maya, with capability of follow-up question generation. Existing asynchronous interviewing systems are not dynamic with scripted and repetitive questions. In comparison, Maya responds with relevant follow-up questions, a largely unexplored feature of irtual interview systems. We take advantage of the implicit knowledge from deep pre-trained language models to generate rich and varied natural language follow-up questions. Empirical results suggest that followQG generates questions that humans rate as high quality, achieving 77% relevance. A comparison with strong baselines of neural network and rule-based systems show that it produces better quality questions. The corpus used for fine-tuning is made publicly available. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T09:02:55Z No. of bitstreams: 1 ijimai_6_5_8.pdf: 811659 bytes, checksum: effdef00ca187bdcd3b848a656965925 (MD5); Made available in DSpace on 2022-04-25T09:02:55Z (GMT). No. of bitstreams: 1 ijimai_6_5_8.pdf: 811659 bytes, checksum: effdef00ca187bdcd3b848a656965925 (MD5)

Song, Hao Flach, Peter https://reunir.unir.net/handle/123456789/12915 2022-04-25T08:26:43Z

Efficient and Robust Model Benchmarks with Item Response Theory and Adaptive Testing Song, Hao; Flach, Peter Progress in predictive machine learning is typically measured on the basis of performance comparisons on benchmark datasets. Traditionally these kinds of empirical evaluation are carried out on large numbers of datasets, but this is becoming increasingly hard due to computational requirements and the often large number of alternative methods to compare against. In this paper we investigate adaptive approaches to achieve better efficiency on model benchmarking. For a large collection of datasets, rather than training and testing a given approach on every individual dataset, we seek methods that allow us to pick only a few representative datasets to quantify the model’s goodness, from which to extrapolate to performance on other datasets. To this end, we adapt existing approaches from psychometrics: specifically, Item Response Theory and Adaptive Testing. Both are well-founded frameworks designed for educational tests. We propose certain modifications following the requirements of machine learning experiments, and present experimental results to validate the approach. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T08:26:43Z No. of bitstreams: 1 ijimai_6_5_11_0.pdf: 1553782 bytes, checksum: 3902c228651abcbb54eedf8f00911863 (MD5); Made available in DSpace on 2022-04-25T08:26:43Z (GMT). No. of bitstreams: 1 ijimai_6_5_11_0.pdf: 1553782 bytes, checksum: 3902c228651abcbb54eedf8f00911863 (MD5)

Criado, Natalia Ferrer, Xavier Such, José M. https://reunir.unir.net/handle/123456789/12914 2022-04-25T08:22:14Z

Attesting Digital Discrimination Using Norms Criado, Natalia; Ferrer, Xavier; Such, José M. More and more decisions are delegated to Machine Learning (ML) and automatic decision systems recently. Despite initial misconceptions considering these systems unbiased and fair, recent cases such as racist algorithms being used to inform parole decisions in the US, low-income neighborhood's targeted with high-interest loans and low credit scores, and women being undervalued by online marketing, fueled public distrust in machine learning. This poses a significant challenge to the adoption of ML by companies or public sector organisations, despite ML having the potential to lead to significant reductions in cost and more efficient decisions, and is motivating research in the area of algorithmic fairness and fair ML. Much of that research is aimed at providing detailed statistics, metrics and algorithms which are difficult to interpret and use by someone without technical skills. This paper tries to bridge the gap between lay users and fairness metrics by using simpler notions and concepts to represent and reason about digital discrimination. In particular, we use norms as an abstraction to communicate situations that may lead to algorithms committing discrimination. In particular, we formalise non-discrimination norms in the context of ML systems and propose an algorithm to attest whether ML systems violate these norms. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-25T08:22:14Z No. of bitstreams: 1 ijimai_6_5_2_0.pdf: 1547136 bytes, checksum: ae3fea797aa35805462bbd0ce54b2d59 (MD5); Made available in DSpace on 2022-04-25T08:22:14Z (GMT). No. of bitstreams: 1 ijimai_6_5_2_0.pdf: 1547136 bytes, checksum: ae3fea797aa35805462bbd0ce54b2d59 (MD5)

Boeschoten, Laura van Kesteren, Erik-Jan Bagheri, Ayoub Oberski, Daniel L. https://reunir.unir.net/handle/123456789/12889 2022-04-21T09:51:33Z

Achieving Fair Inference Using Error-Prone Outcomes Boeschoten, Laura; van Kesteren, Erik-Jan; Bagheri, Ayoub; Oberski, Daniel L. Recently, an increasing amount of research has focused on methods to assess and account for fairness criteria when predicting ground truth targets in supervised learning. However, recent literature has shown that prediction unfairness can potentially arise due to measurement error when target labels are error prone. In this study we demonstrate that existing methods to assess and calibrate fairness criteria do not extend to the true target variable of interest, when an error-prone proxy target is used. As a solution to this problem, we suggest a framework that combines two existing fields of research: fair ML methods, such as those found in the counterfactual fairness literature and measurement models found in the statistical literature. Firstly, we discuss these approaches and how they can be combined to form our framework. We also show that, in a healthcare decision problem, a latent variable model to account for measurement error removes the unfairness detected previously. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T09:51:33Z No. of bitstreams: 1 ijimai_6_5_1_0.pdf: 1416724 bytes, checksum: 5967c9d0ef87c8fe583c0a5ce961bd2d (MD5); Made available in DSpace on 2022-04-21T09:51:33Z (GMT). No. of bitstreams: 1 ijimai_6_5_1_0.pdf: 1416724 bytes, checksum: 5967c9d0ef87c8fe583c0a5ce961bd2d (MD5)

Gonçalo Oliveira, Hugo Sousa, Tiago Alves, Ana https://reunir.unir.net/handle/123456789/12888 2022-04-21T09:40:33Z

Assessing Lexical-Semantic Regularities in Portuguese Word Embeddings Gonçalo Oliveira, Hugo; Sousa, Tiago; Alves, Ana Models of word embeddings are often assessed when solving syntactic and semantic analogies. Among the latter, we are interested in relations that one would find in lexical-semantic knowledge bases like WordNet, also covered by some analogy test sets for English. Briefly, this paper aims to study how well pretrained Portuguese word embeddings capture such relations. For this purpose, we created a new test, dubbed TALES, with an exclusive focus on Portuguese lexical-semantic relations, acquired from lexical resources. With TALES, we analyse the performance of methods previously used for solving analogies, on different models of Portuguese word embeddings. Accuracies were clearly below the state of the art in analogies of other kinds, which shows that TALES is a challenging test, mainly due to the nature of lexical-semantic relations, i.e., there are many instances sharing the same argument, thus allowing for several correct answers, sometimes too many to be all included in the dataset. We further inspect the results of the best performing combination of method and model to find that some acceptable answers had been considered incorrect. This was mainly due to the lack of coverage by the source lexical resources and suggests that word embeddings may be a useful source of information for enriching those resources, something we also discuss. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T09:40:33Z No. of bitstreams: 1 ijimai_6_5_4.pdf: 740435 bytes, checksum: 4dc5d11063ba9a0dead09ca7c9ec2f31 (MD5); Made available in DSpace on 2022-04-21T09:40:33Z (GMT). No. of bitstreams: 1 ijimai_6_5_4.pdf: 740435 bytes, checksum: 4dc5d11063ba9a0dead09ca7c9ec2f31 (MD5)

Pitt, Steph van Meelis Lacey, Marlína Scaife, Ed Pitt, Jeremy https://reunir.unir.net/handle/123456789/12887 2022-04-21T09:07:05Z

No App is an Island: Collective Action and Sustainable Development Goal-Sensitive Design Pitt, Steph; van Meelis Lacey, Marlína; Scaife, Ed; Pitt, Jeremy The transformation to the Digital Society presents a challenge to engineer ever more complex socio-technical systems in order to address wicked societal problems. Therefore, it is essential that these systems should be engineered with respect not just to conventional functional and non-functional requirements, but also with respect to satisfying qualitative human values, and assessing their impact on global challenges, such as those expressed by the UN sustainable development goals (SDGs). In this paper, we present a set of sets of design principles and an associated meta-platform, which focus design of socio-technical systems on the potential interaction of human and artificial intelligence with respect to three aspects: firstly, decision-support with respect to the codification of deep social knowledge; secondly, visualisation of community contribution to successful collective action; and thirdly, systemic improvement with respect to the SDGs through impact assessment and measurement. This methodology, of SDG-Sensitive Design, is illustrated through the design of two collective action apps, one for encouraging plastic re-use and reducing plastic waste, and the other for addressing redistribution of surplus food. However, as with the inter-connectedness of the SDGs, we conclude by arguing that the inter-connectedness of the Digital Society implies that system development cannot be undertaken in isolation from other systems. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T09:07:05Z No. of bitstreams: 1 ijimai_6_5_3.pdf: 1257169 bytes, checksum: 49b23252669790ab29a032be89e83f70 (MD5); Made available in DSpace on 2022-04-21T09:07:05Z (GMT). No. of bitstreams: 1 ijimai_6_5_3.pdf: 1257169 bytes, checksum: 49b23252669790ab29a032be89e83f70 (MD5)

Susaiyah, Allmin Härmä, Aki Reiter, Ehud Petković, Milan https://reunir.unir.net/handle/123456789/12886 2022-04-21T08:51:32Z

Neural Scoring of Logical Inferences from Data using Feedback Susaiyah, Allmin; Härmä, Aki; Reiter, Ehud; Petković, Milan Insights derived from wearable sensors in smartwatches or sleep trackers can help users in approaching their healthy lifestyle goals. These insights should indicate significant inferences from user behaviour and their generation should adapt automatically to the preferences and goals of the user. In this paper, we propose a neural network model that generates personalised lifestyle insights based on a model of their significance, and feedback from the user. Simulated analysis of our model shows its ability to assign high scores to a) insights with statistically significant behaviour patterns and b) topics related to simple or complex user preferences at any given time. We believe that the proposed neural networks model could be adapted for any application that needs user feedback to score logical inferences from data. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T08:51:32Z No. of bitstreams: 1 ijimai_6_5_9.pdf: 1542068 bytes, checksum: 0b7f144dee74038863f4319af98fcb00 (MD5); Made available in DSpace on 2022-04-21T08:51:32Z (GMT). No. of bitstreams: 1 ijimai_6_5_9.pdf: 1542068 bytes, checksum: 0b7f144dee74038863f4319af98fcb00 (MD5)

Philipp, Tobias Roland, Valentin Schweizer, Lukas https://reunir.unir.net/handle/123456789/12885 2022-04-21T08:44:55Z

Smoke Test Planning using Answer Set Programming Philipp, Tobias; Roland, Valentin; Schweizer, Lukas Smoke testing is an important method to increase stability and reliability of hardware- gramming, Testing depending systems. Due to concurrent access to the same physical resource and the impracticality of the use of virtualization, smoke testing requires some form of planning. In this paper, we propose to decompose test cases in terms of atomic actions consisting of preconditions and effects. We present a solution based on answer set programming with multi-shot solving that automatically generates short parallel test plans. Experiments suggest that the approach is feasible for non-inherently sequential test cases and scales up to thousands of test cases. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T08:44:55Z No. of bitstreams: 1 ijimai_6_5_6.pdf: 1421291 bytes, checksum: dd56f403e28117df1c8d95bf34057b55 (MD5); Made available in DSpace on 2022-04-21T08:44:55Z (GMT). No. of bitstreams: 1 ijimai_6_5_6.pdf: 1421291 bytes, checksum: dd56f403e28117df1c8d95bf34057b55 (MD5)

Costantini, Stefania De Gasperis, Giovanni De Lauretis, Lorenzo https://reunir.unir.net/handle/123456789/12884 2022-04-21T08:25:49Z

An Application of Declarative Languages in Distributed Architectures: ASP and DALI Microservices Costantini, Stefania; De Gasperis, Giovanni; De Lauretis, Lorenzo In this paper we introduce an approach to the possible adoption of Answer Set Programming (ASP) for the definition of microservices, which are a successful abstraction for designing distributed applications as suites of independently deployable interacting components. Such ASP-based components might be employed in distributed architectures related to Cloud Computing or to the Internet of Things (IoT), where the ASP microservices might be usefully coordinated with intelligent logic-based agents. We develop a case study where we consider ASP microservices in synergy with agents defined in DALI, a well-known logic-based agent-oriented programming language developed by our research group. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T08:25:49Z No. of bitstreams: 1 ijimai_6_5_7.pdf: 798062 bytes, checksum: abbe89b464aadcbe68089ed6649c2a0b (MD5); Made available in DSpace on 2022-04-21T08:25:49Z (GMT). No. of bitstreams: 1 ijimai_6_5_7.pdf: 798062 bytes, checksum: abbe89b464aadcbe68089ed6649c2a0b (MD5)

Travé Allepuz, Esther del Fresno Bernal, Pablo Mauri Martí, Alfred Medina Gordo, Sonia https://reunir.unir.net/handle/123456789/12883 2022-04-21T08:11:57Z

The Semantics of History. Interdisciplinary Categories and Methods for Digital Historical Research Travé Allepuz, Esther; del Fresno Bernal, Pablo; Mauri Martí, Alfred; Medina Gordo, Sonia This paper aims at introducing and discussing the data modelling and labelling methods for interdisciplinary and digital research in History developed and used by the authors. Our approach suggests the development of a conceptual framework for interdisciplinary research in history as a much-needed strategy to ensure that historians use all vestiges from the past regardless of their origin or support for the construction of historical discourse. By labelling Units of Topography and Actors in a wide range of historical sources and exploiting the obtained data, we use the Monastery of Sant Genís de Rocafort (Martorell, Spain) as a lab example of our method. This should lead researchers to the development of an integrated historical discourse maximizing the potential of interdisciplinary and fair research and minimizing the risks of bias. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-21T08:11:57Z No. of bitstreams: 1 ijimai_6_5_5_0.pdf: 2719671 bytes, checksum: 6892ed37b8ab2c895160236b59719993 (MD5); Made available in DSpace on 2022-04-21T08:11:57Z (GMT). No. of bitstreams: 1 ijimai_6_5_5_0.pdf: 2719671 bytes, checksum: 6892ed37b8ab2c895160236b59719993 (MD5)