the proceedings contain 29 papers. the special focus in this conference is on Health Information Science. the topics include: Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning ...
ISBN:
(纸本)9783031206269
the proceedings contain 29 papers. the special focus in this conference is on Health Information Science. the topics include: Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space;MHDML: construction of a Medical Lakehouse for Multi-source Heterogeneous Data;a Hybrid Medical Causal Inference Platform Based on Data Lake;data Exploration Optimization for Medical Big Data;improving Data Analytic Performance in Health Information System with Big Data Technology;holoCleanX: A Multi-source Heterogeneous Data Cleaning Solution Based on Lakehouse;the construction and Validation of an Automatic Crisis Balance analysis Model;Assessing the Utilisation of TELedentistry from Perspectives of Early Career Dental Practitioners - Development of the UTEL Questionnaire;genetic Algorithm for Patient Assignment Optimization in Cloud Healthcare System;detection of Obsessive-Compulsive Disorder in Australian Children and Adolescents Using Machine Learning Methods;research on the construction of Psychological Crisis Intervention Strategy Service System;towards a Perspective to Analyze Emergent systems in Health Domain;food Recommendation for Mental Health by Using Knowledge Graph Approach;medical Knowledge Graph construction Based on Traceable Conversion;automated Knowledge Graph construction for Healthcare Domain;Alcoholic EEG Data Classification Using Weighted Graph-Based Technique;Optical Coherence Tomography Classification Based on Transfer Learning and RA-Attention;intelligent Interpretation and Classification of Multivariate Medical Time Series Based on Convolutional Neural Networks;ECG Signals Classification Model Based on Frequency Domain Features Coupled with Least Square Support Vector Machine (LS-SVM);cluster analysis of Low-Dimensional Medical Concept Representations from Electronic Health Records;an Anomaly Detection Framework Based on Data Lake for Medical Multivariate Time Series;anomaly Detection on Health Data;an Intellig
As the global community increasingly recognizes the importance of transitioning towards sustainable and environmentally conscious energy solutions, the quest for efficient and reliable on-grid systems becomes ever mor...
详细信息
Blockchain is an emerging technology that is being studied more and more in academia and applied in industry. Some of these characteristics are immutability, traceability, and security. Several areas can be benefiting...
详细信息
this paper presents an efficient procedure for multi-objective model checking of long-run average reward (aka: mean pay-off) and total reward objectives as well as their combination. We consider this for Markov automa...
详细信息
ISBN:
(数字)9783030720162
ISBN:
(纸本)9783030720155;9783030720162
this paper presents an efficient procedure for multi-objective model checking of long-run average reward (aka: mean pay-off) and total reward objectives as well as their combination. We consider this for Markov automata, a compositional model that captures both traditional Markov decision processes (MDPs) as well as a continuous-time variant thereof. the crux of our procedure is a generalization of Forejt et al.'s approach for total rewards on MDPs to arbitrary combinations of long-run and total reward objectives on Markov automata. Experiments with a prototypical implementation on top of the Storm model checker show encouraging results for both model types and indicate a substantial improved performance over existing multi-objective long-run MDP model checking based on linear programming.
Numerous tasks in program analysis and synthesis reduce to deciding reachability in possibly infinite graphs such as those induced by Petri nets. However, the Petri net reachability problem has recently been shown to ...
详细信息
ISBN:
(纸本)9783030720124;9783030720131
Numerous tasks in program analysis and synthesis reduce to deciding reachability in possibly infinite graphs such as those induced by Petri nets. However, the Petri net reachability problem has recently been shown to require non-elementary time, which raises questions about the practical applicability of Petri nets as target models. In this paper, we introduce a novel approach for efficiently semi-deciding the reachability problem for Petri nets in practice. Our key insight is that computationally lightweight over-approximations of Petri nets can be used as distance oracles in classical graph exploration algorithms such as A* and greedy best-first search. We provide and evaluate a prototype implementation of our approach that outperforms existing state-of-the-art tools, sometimes by orders of magnitude, and which is also competitive with domain-specific tools on benchmarks coming from program synthesis and concurrent program analysis.
In order to develop reliable software and systems, we depend on practical techniques for the construction and analysis of such software and systems. this special issue of Software tools for Technology Transfer present...
详细信息
In order to develop reliable software and systems, we depend on practical techniques for the construction and analysis of such software and systems. this special issue of Software tools for Technology Transfer presents various tool-supported techniques that can help withthe construction and analysis of such reliable software and systems. the papers in this special issue are extended versions of selected conference papers from the proceedings of the 24thinternationalconference on tools and algorithms for the construction and analysis of systems (TACAS 2018).
For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to use...
详细信息
ISBN:
(纸本)9781954085527
For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities, or domains. In pursuit of these goals, we introduce the RADDLE(1) benchmark 2, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Adversarial training is also proposed to improve model robustness against noisy inputs. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.
Our submission to SV-COMP'21 is based on the software verification framework CPAchecker and implements the extension to the thread-modular approach. It considers every thread separately, but in a special environme...
详细信息
ISBN:
(纸本)9783030720124;9783030720131
Our submission to SV-COMP'21 is based on the software verification framework CPAchecker and implements the extension to the thread-modular approach. It considers every thread separately, but in a special environment which models thread interactions. the environment is expressed by projections of normal transitions in each thread. A projection contains a description of possible effects over shared data and synchronization primitives, as well as conditions of its application. Adjusting the precision of the projections, one can find a balance between the speed and the precision of the whole analysis. Implementation on the top of the CPAchecker framework allows combining our approach with existing algorithms and analyses. Evaluation on the sv-benchmarks confirms the scalability and soundness of the approach.
One of the main obstacles faced by students initiating their academic life in the courses of the computing field is the difficulty to comprehend the concepts related to the construction of algorithms. To promote inter...
详细信息
ISBN:
(纸本)9783030779429;9783030779436
One of the main obstacles faced by students initiating their academic life in the courses of the computing field is the difficulty to comprehend the concepts related to the construction of algorithms. To promote interaction of students withthese concepts, their peers and withthe teacher, one of the methodological resources used is gamification. To investigate the potential use of this resource, specifically in relation to quiz tools and their contributions to the teaching and learning process in this scenario, the following methodological steps were taken: (a) analysis of gamified quiz tools in relation to principles of educational gamification design;(b) selection of one of the analyzed tools;(c) use of the selected tool in class;and (d) discussion about its potential and questions related to the design of this kind of tool for use in this context. For the analysis of the potential use of gamification and the chosen tool, a practice of exploratory nature was made, in a classroom environment with a total of 31 students, in the first semester of a course of Computer Science. Highlighting only the question of potential use in the scenario in question, gamification motivated the class and constituted challenges for boththe professor and the students, insofar as establishing flexibility, creativity and partnership among professor and students.
this paper presents a virtualization environment that is composed of a transmission network simulator, a distribution network simulator, and an Electric Vehicles (EV) ecosystem emulator. the coupling and synchronizati...
this paper presents a virtualization environment that is composed of a transmission network simulator, a distribution network simulator, and an Electric Vehicles (EV) ecosystem emulator. the coupling and synchronization of these three components are ensured so that the environment can simulate different applications in a context of an energy transition of the grid characterized by transportation electrification. the performance of this environment will be evaluated through some tests that highlight its advantages and show its importance in improving the grid modeling. Potential applications of our virtualisation tools include the simulation and study of cyberattacks that impact the transmission and/or the distribution systemsthrough compromising, for instance, the operations of the EV charging infrastructure, third party systems in the EV ecosystem, or other power grid components.
暂无评论