scholarly journals An overview of machine learning techniques in constraint solving

2021 ◽  
Author(s):  
Andrei Popescu ◽  
Seda Polat-Erdeniz ◽  
Alexander Felfernig ◽  
Mathias Uta ◽  
Müslüm Atas ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Constraint Solving ◽  
Advantages And Disadvantages ◽  
Online Sales ◽  
Search Heuristics ◽  
Learning Techniques ◽  
Search Processes ◽  
Future Work

AbstractConstraint solving is applied in different application contexts. Examples thereof are the configuration of complex products and services, the determination of production schedules, and the determination of recommendations in online sales scenarios. Constraint solvers apply, for example, search heuristics to assure adequate runtime performance and prediction quality. Several approaches have already been developed showing that machine learning (ML) can be used to optimize search processes in constraint solving. In this article, we provide an overview of the state of the art in applying ML approaches to constraint solving problems including constraint satisfaction, SAT solving, answer set programming (ASP) and applications thereof such as configuration, constraint-based recommendation, and model-based diagnosis. We compare and discuss the advantages and disadvantages of these approaches and point out relevant directions for future work.

Improving Automated Planning with Machine Learning

2010 ◽  
pp. 599-620
Author(s):  
Susana Fernández Arregui ◽  
Sergio Jiménez Celorrio ◽  
Tomás de la Rosa Turbides
Keyword(s):  
Machine Learning ◽  
Automated Planning ◽  
Machine Learning Techniques ◽  
Advantages And Disadvantages ◽  
Learning Techniques ◽  
Depth Analysis ◽  
Search Processes ◽  
Action Models ◽  
New Challenges ◽  
Definition Of

This chapter reports the last machine learning techniques for the assistance of automated planning. Recent discoveries in automated planning have opened the scope of planners, from toy problems to real-world applications, making new challenges come into focus. The planning community believes that machine learning can assist to address these new challenges. The chapter collects the last machine learning techniques for assisting automated planners classified in: techniques for the improvement of the planning search processes and techniques for the automatic definition of planning action models. For each technique, the chapter provides an in-depth analysis of their domain, advantages and disadvantages. Finally, the chapter draws the outline of the new promising avenues for research in learning for planning systems.

Improving Automated Planning with Machine Learning

2012 ◽  
pp. 1355-1373
Author(s):  
Susana Fernández Arregui ◽  
Sergio Jiménez Celorrio ◽  
Tomás de la Rosa Turbides
Keyword(s):  
Machine Learning ◽  
Automated Planning ◽  
Machine Learning Techniques ◽  
Advantages And Disadvantages ◽  
Learning Techniques ◽  
Depth Analysis ◽  
Search Processes ◽  
Action Models ◽  
New Challenges ◽  
Definition Of

This chapter reports the last machine learning techniques for the assistance of automated planning. Recent discoveries in automated planning have opened the scope of planners, from toy problems to real-world applications, making new challenges come into focus. The planning community believes that machine learning can assist to address these new challenges. The chapter collects the last machine learning techniques for assisting automated planners classified in: techniques for the improvement of the planning search processes and techniques for the automatic definition of planning action models. For each technique, the chapter provides an in-depth analysis of their domain, advantages and disadvantages. Finally, the chapter draws the outline of the new promising avenues for research in learning for planning systems.

scholarly journals Using Argument Mining for Legal Text Summarization

2020 ◽  
Author(s):  
Huihui Xu ◽  
Jaromír Šavelka ◽  
Kevin D. Ashley
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
Text Summarization ◽  
Machine Learning Techniques ◽  
Legal Argument ◽  
Legal Text ◽  
Argumentative Text ◽  
Advantages And Disadvantages ◽  
Learning Techniques

Argument mining, a subfield of natural language processing and text mining, is a process of extracting argumentative text portions and identifying the role the selected texts play. Legal argument mining targets the argumentative parts of a legal text. In order to better understand how to apply legal argument mining as a step toward improving case summarization, we have assembled a sizeable set of cases and human-expert-prepared summaries annotated in terms of legal argument triples that capture the most important skeletal argument structures in a case. We report the results of applying multiple machine learning techniques to demonstrate and analyze the advantages and disadvantages of different methods to identify sentence components of these legal argument triples.

scholarly journals Air Temperature Forecasting Using Machine Learning Techniques: A Review

Energies ◽  
2020 ◽  
Vol 13 (16) ◽  
pp. 4215 ◽  
Author(s):  
Jenny Cifuentes ◽  
Geovanny Marulanda ◽  
Antonio Bello ◽  
Javier Reneses
Keyword(s):  
Machine Learning ◽  
Learning Strategies ◽  
Regional Scale ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Advantages And Disadvantages ◽  
Industrial Sectors ◽  
Learning Techniques ◽  
Temperature Forecasting ◽  
The Government

Efforts to understand the influence of historical climate change, at global and regional levels, have been increasing over the past decade. In particular, the estimates of air temperatures have been considered as a key factor in climate impact studies on agricultural, ecological, environmental, and industrial sectors. Accurate temperature prediction helps to safeguard life and property, playing an important role in planning activities for the government, industry, and the public. The primary aim of this study is to review the different machine learning strategies for temperature forecasting, available in the literature, presenting their advantages and disadvantages and identifying research gaps. This survey shows that Machine Learning techniques can help to accurately predict temperatures based on a set of input features, which can include the previous values of temperature, relative humidity, solar radiation, rain and wind speed measurements, among others. The review reveals that Deep Learning strategies report smaller errors (Mean Square Error = 0.0017 °K) compared with traditional Artificial Neural Networks architectures, for 1 step-ahead at regional scale. At the global scale, Support Vector Machines are preferred based on their good compromise between simplicity and accuracy. In addition, the accuracy of the methods described in this work is found to be dependent on inputs combination, architecture, and learning algorithms. Finally, further research areas in temperature forecasting are outlined.

A Drug Decision Support System for Developing a Successful Drug Candidate Using Machine Learning Techniques

2020 ◽  
Vol 16 (4) ◽  
pp. 407-419
Author(s):  
Aytun Onay ◽  
Melih Onay
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Decision Support ◽  
Support System ◽  
Molecular Descriptors ◽  
Machine Learning Techniques ◽  
Drug Candidate ◽  
Drug Molecules ◽  
Learning Techniques

Background: Virtual screening of candidate drug molecules using machine learning techniques plays a key role in pharmaceutical industry to design and discovery of new drugs. Computational classification methods can determine drug types according to the disease groups and distinguish approved drugs from withdrawn ones. Introduction: Classification models developed in this study can be used as a simple filter in drug modelling to eliminate potentially inappropriate molecules in the early stages. In this work, we developed a Drug Decision Support System (DDSS) to classify each drug candidate molecule as potentially drug or non-drug and to predict its disease group. Methods: Molecular descriptors were identified for the determination of a number of rules in drug molecules. They were derived using ADRIANA.Code program and Lipinski's rule of five. We used Artificial Neural Network (ANN) to classify drug molecules correctly according to the types of diseases. Closed frequent molecular structures in the form of subgraph fragments were also obtained with Gaston algorithm included in ParMol Package to find common molecular fragments for withdrawn drugs. Results: We observed that TPSA, XlogP Natoms, HDon_O and TPSA are the most distinctive features in the pool of the molecular descriptors and evaluated the performances of classifiers on all datasets and found that classification accuracies are very high on all the datasets. Neural network models achieved 84.6% and 83.3% accuracies on test sets including cardiac therapy, anti-epileptics and anti-parkinson drugs with approved and withdrawn drugs for drug classification problems. Conclusion: The experimental evaluation shows that the system is promising at determination of potential drug molecules to classify drug molecules correctly according to the types of diseases.

Impacto de las emociones vertidas por diarios digitales en Twitter

2020 ◽  
Author(s):  
Sergio Arce-García ◽  
Natalia Orviz-Martínez ◽  
Tatiana Cuervo-Carabel
Keyword(s):  
Machine Learning ◽  
General Information ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
The Social ◽  
General Elections ◽  
Statistical Studies ◽  
Twitter Users ◽  
La Red

The use of Twitter by newspapers is widespread and is a way to keep readers informed in real time. In this article, we analyze the discourse of the messages released by the ten main general information newspapers in Spain and the reactions they provoked on the social network. The objective is to analyze whether the emotional discourse of the news in each newspaper caused greater dissemination among and attention from users, as well as to determine the emotions and feelings expressed by them. To do so, news about important events such as court judgements, street riots, and general elections was followed between October and November 2019. A total of 124,897 tweets collected using machine-learning techniques were analyzed by the application of algorithms which allowed the determination of emotions and valences of feelings. We carried out statistical studies and produced graphs showing the dependence between emotional variables and positive or negative sentimental valence. The results showed that, in general, newspapers do not use an excessive amount of emotional speech with the aim of impacting their public. However, differences were found among the newspapers in terms of trying to encourage reader loyalty. The reaction of the users was more linked to the informative facts themselves and the emotions they provoked than to the type of emotional and/or polarized discourse. The day-to-day information determines to a large extent what is consumed by Twitter users, in which changing modes of speech are observed depending on the editorial line of each newspaper. Resumen El uso de Twitter por parte de los diarios de información está muy extendido y es una forma de tener a sus lectores informados casi en tiempo real. En este artículo analizamos el discurso de los mensajes vertidos por los diez principales diarios de información general en España y las reacciones que provocan en la red social. El objetivo de esta investigación es analizar si es el discurso emocional de las noticias de cada diario el que provoca mayor difusión y atención por parte de los usuarios, así como conocer las emociones y sentimientos vertidos temporalmente en los mismos. Para ello se hizo un seguimiento entre octubre y noviembre de 2019 de noticias que incluyen acontecimientos importantes como sentencias, altercados o la celebración de elecciones generales. Mediante el empleo de técnicas de machine learning se analizaron con la aplicación de algoritmos 124.897 tweets, lo que permitió determinar las emociones y valencias, así como desarrollar estudios estadísticos y gráficos de dependencia entre variables emocionales y de valencia sentimental positiva o negativa. Los resultados evidencian que en general, no se emplean excesivos discursos emocionales que busquen impactar. Sin embargo, sí que se aprecian diferencias de uso emocional y de sentimientos entre los diarios que pretenden la fidelización del lector. Por contra se encuentra que la reacción de los usuarios está más ligada al hecho informativo en sí y a las emociones que les provocan, que al tipo de discurso emocional y/o polarizado. El día a día informativo determina en gran medida qué se consume por parte de los usuarios de la red social, en la que se aprecian discursos cambiantes en función de la línea editorial de cada diario.

Sign in / Sign up

Export Citation Format

Share Document