Mining IPC-2011 Results
نویسندگان
چکیده
The International Planning Competition (IPC) offers a wonderful scope to evaluate and compare different planning approaches and specific planner implementations in benchmark domains. In IPC 2011, the software generated for the competition permits to obtain a lot of data about the execution of all the planners in the different tracks in a simple way, which permits its recovery and use. In this work, we propose to analyze such data from a Data Mining (DM) perspective, including additional features which can be useful for the analysis. In such a way, we are able to construct models of the results obtained, allowing us to make additional analysis to the ones performed by the organizers. In this work, we report some initial analysis after constructing classification and regression models for the sequential satisficing and optimal track.
منابع مشابه
Relevance Levels for Patent Mining
This paper presents a proposal for relaxed relevance for patent mining. The essential argument is that assignment of a complete international patent classification (IPC) to a document is a difficult task and that because the IPC code has several levels of hierarchy, relaxed relevance judgments as higher levels may provide better performance of the same classification algorithms.
متن کاملCLEF-IP 2011 Working Notes: Utilizing Prior Art Candidate Search Results for Refined IPC Classification
For the refined IPC classification in the CLEF-IP 2011 task, we constructed classification system with KNN classification which uses PAC (Prior Art Candidate) search results as neighbors. We also slightly modified the neighborhood evaluation. We also furnished a simple PAC search system. We produced some running results both in PAC search and classification, and evaluated our system. Our test s...
متن کاملLysine deacetylation in ischaemic preconditioning: the role of SIRT1.
AIMS Acute ischaemic preconditioning (IPC) induces protection against cardiac ischaemia-reperfusion (IR) via post-translational modification of key proteins. Lysine (Lys) acetylation is an important regulator of protein function, but this type of modification has not been studied in the context of IPC. We investigated Lys acetylation in IPC and its upstream regulation by SIRT1. METHODS AND RE...
متن کاملMulti-label Classification using Logistic Regression Models for NTCIR-7 Patent Mining Task
We design a multi-label classification system based on a machine learning approach for the NTCIR-7 Patent Mining Task. In our system, we employ a logistic regression model for each International Patent Classification (IPC) code that determines the IPC code assignment of research papers. The logistic regression models are trained by using patent documents provided by task organizers. To mitigate...
متن کامل