Automated preprocessing of environmental data

Rönkkö, Mauno; Heikkinen, Jani; Kotovirta, Ville; Chandrasekar, V.

doi:10.1016/j.future.2014.10.011

Cited by 8 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development This work has been partially supported by EMELIOT national research project, which has been funded by the MUR under the PRIN 2020 program (Contract 2020W3A5FY) and by European Union -Horizon 2020 Program under the scheme "INFRAIA-01-2018-2019 -Integrating Activities for Advanced Communities", Grant Agreement n.871042, "SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics" (http://www.sobigdata.eu) of ML systems usually requires a good knowledge of the underlying ML approaches to choose the best techniques and models to solve the targeted problem. Many methods have been developed in the last years to automate some ML systems development phases and help non-technical users [61,31,34]. However, these techniques do not consider the quality properties essential for ML systems, such as dataset's Privacy, model's Interpretability, Explainability, and Fairness [50,46,12].…”

Section: Introductionmentioning

confidence: 99%

Democratizing Quality-Based Machine Learning Development through Extended Feature Models

d’Aloisio

Marco

Stilo

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

ML systems have become an essential tool for experts of many domains, data scientists and researchers, allowing them to find answers to many complex business questions starting from raw datasets. Nevertheless, the development of ML systems able to satisfy the stakeholders’ needs requires an appropriate amount of knowledge about the ML domain. Over the years, several solutions have been proposed to automate the development of ML systems. However, an approach taking into account the new quality concerns needed by ML systems (like fairness, interpretability, privacy, and others) is still missing.In this paper, we propose a new engineering approach for the quality-based development of ML systems by realizing a workflow formalized as a Software Product Line through Extended Feature Models to generate an ML System satisfying the required quality constraints. The proposed approach leverages an experimental environment that applies all the settings to enhance a given Quality Attribute, and selects the best one. The experimental environment is general and can be used for future quality methods’ evaluations. Finally, we demonstrate the usefulness of our approach in the context of multi-class classification problem and fairness quality attribute.

show abstract

Section: Introductionmentioning

confidence: 99%

Democratizing Quality-Based Machine Learning Development through Extended Feature Models

d’Aloisio

Marco

Stilo

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Therefore, we consider two aspects important for the research: improvement of monitoring system to forecast and managerial tasks to ensure environmental safety based on information technologies; professional development of specialists in the energy, environmental and related fields who are responsible for decisionmaking to reduce negative impact on environment. Was made systematization of scientific publications in the following areas directly related to this research based on analysis of the works of foreign and domestic scientists: -approaches to sustainable development [4,6,8,[10][11][12][13]; -development of indicators, indices to measure sustainable development [2,[14][15][16][17][18][19][20][21]; -construction of mathematical, software and hardware tools to assess impact of potentially dangerous enterprises on environment, taking into account economic indicators [22][23][24][25][26][27][28][29][30][31][32][33]; -training of specialists in the field of environmental safety and related industries [34][35][36][37][38][39][40][41][42][43][44][45][46].…”

Section: Introductionmentioning

confidence: 99%

Software tools for tasks of sustainable development of environmental problems: peculiarities of programming and implementation in the specialists’ preparation

et al. 2020

View full text Add to dashboard Cite

It is necessary to follow signed documents on development of renewable energy, modernization of fuel and energy sector enterprises and waste management in order to fulfil Ukraine's commitments to the global community on climate change prevention. Therefore, it is an urgent task to develop software that allows to solve problems of visual analysis of environmental status dynamics of territorial systems and to determine boundaries of individual territories stability. The authors propose new forms of monitoring data presentation of technogenic loadings and risks which reflect dynamics of environmental situation in the space of informative features. It is important to improve skills of professionals, particularly, stuff of the ministries, enterprises and organizations responsible for decision-making to reduce negative impact on environment and to train future professionals in this area. Curriculums of higher education institutions do not pay much attention on usage of software to support managerial decision-making to reduce negative impact on the environment. It is proposed to improve qualification of such specialists, responsible for management in the following areas: conducting training seminars at the ministries, institutions and departments interested in the implementation of developed systems; scientific and methodological support and advisory assistance in the process of implementation of the software; development and improvement of educational and methodological support for postgraduate students and trainees of advanced training, specialists responsible for decision -making in energy, environmental and related fields.

show abstract

“…For example, the approach presented in [19] performs data pre-processing in an automatic manner with the support of meta-learning, while an approach for pipelining methods to facilitate further automated data pre-processing in presented in [20]. Also, there are domain-oriented data preprocessing approaches for characterizing automated data pre-processing such us the approach presented in [21] for environmental data.…”

Section: Introductionmentioning

confidence: 99%

S3Mining: A model-driven engineering approach for supporting novice data miners in selecting suitable classifiers

Espinosa

García‐Saiz

Zorrilla

et al. 2019

Computer Standards & Interfaces

View full text Add to dashboard Cite

Data mining has proven to be very useful in order to extract information from data in many different contexts. However, due to the complexity of data mining techniques, it is required the know-how of an expert in this field to select and use them. Actually, adequately applying data mining is out of the reach of novice users which have expertise in their area of work, but lack skills to employ these techniques. In this paper, we use both model-driven engineering and scientific workflow standards and tools in order to develop named S3Mining framework, which supports novice users in the process of selecting the data mining classification algorithm that better fits with their data and goal. To this aim, this selection process uses the past experiences of expert data miners with the application of classification techniques over their own datasets. The contributions of our S3Mining framework are as follows: (i) an approach to create a knowledge base which stores the past experiences of experts users, (ii) a process that provides the expert users with utilities for the construction of classifiers' recommenders based on the existing knowledge base, (iii) a system that allows novice data miners to use these recommenders for discovering the classifiers that better fit for solving their problem at hand, and (iv) a public implementation of the framework's workflows. Finally, an experimental evaluation has been conducted to shown the feasibility of our framework.

show abstract

Automated preprocessing of environmental data

Cited by 8 publications

References 37 publications

Democratizing Quality-Based Machine Learning Development through Extended Feature Models

Democratizing Quality-Based Machine Learning Development through Extended Feature Models

Software tools for tasks of sustainable development of environmental problems: peculiarities of programming and implementation in the specialists’ preparation

S3Mining: A model-driven engineering approach for supporting novice data miners in selecting suitable classifiers

Contact Info

Product

Resources

About