The Experts below are selected from a list of 1305 Experts worldwide ranked by ideXlab platform
Axel Legay - One of the best experts on this subject based on the ideXlab platform.
-
beyond boolean product line model checking dealing with feature Attributes and multi features
International Conference on Software Engineering, 2013Co-Authors: Maxime Cordy, Pierreyves Schobbens, Patrick Heymans, Axel LegayAbstract:Model checking techniques for software product lines (SPL) are actively researched. A major limitation they currently have is the inability to deal efficiently with non-Boolean features and multi-features. An example of a non-Boolean feature is a Numeric Attribute such as maximum number of users which can take different Numeric values across the range of SPL products. Multi-features are features that can appear several times in the same product, such as processing units which number is variable from one product to another and which can be configured independently. Both constructs are extensively used in practice but currently not supported by existing SPL model checking techniques. To overcome this limitation, we formally define a language that integrates these constructs with SPL behavioural specifications. We generalize SPL model checking algorithms correspondingly and evaluate their applicability. Our results show that the algorithms remain efficient despite the generalization.
Santosa R. Gunawan - One of the best experts on this subject based on the ideXlab platform.
-
Perbandingan Algoritma C4.5 dan CART dalam Memprediksi Kategori Indeks Prestasi Mahasiswa
'Institute of Research and Community Services Diponegoro University (LPPM UNDIP)', 2018Co-Authors: Alverina Dea, Chrismanto, Antonius Rachmat, Santosa R. GunawanAbstract:This research compared the accuracy of prediction of Grade Point Average (GPA) of the first semester students using C4.5 and CART algorithms in Faculty of Information Technology (FTI), Universitas Kristen Duta Wacana (UKDW). This research also explored various parameters such as Numeric Attribute categorization, data balance, GPA categories number, and different Attributes availability due to the difference of data availability between Achievement Admission (AA) and Regular Admission (RA). The training data used to create decision tree were FTI students, 2008-2015 batch, while the testing data were FTI students, 2016 batch. The accuracy of prediction was measured by using crosstab table. In AA, the accuracy of both algorithms can be achieved about 86.86%. Meanwhile, in RA the accuracy of C4.5 is about 61.54% and CART is about 63.16%. From these accuracy result, both algorithms are better to predict AA rather than RA.Penelitian ini membandingkan akurasi prediksi kategori Indeks Prestasi (IP) semester pertama mahasiswa Fakultas Teknologi Informasi (FTI) Universitas Kristen Duta Wacana (UKDW) menggunakan algoritma C4.5 dan CART. Penelitian ini juga mengeksplorasi berbagai parameter seperti kategorisasi atribut numerik, keseimbangan data, jumlah kategori IP, dan ketersediaan atribut yang berbeda karena perbedaan ketersediaan data antara jalur prestasi dan jalur non-prestasi. Data mahasiswa FTI tahun 2008-2015 digunakan sebagai data latih sedangkan data uji menggunakan data tahun 2016. Akurasi kedua algoritma dalam memprediksi tersebut diukur dengan menggunakan tabel crosstab. Pada jalur prestasi, akurasi kedua algoritma mampu mencapai 86,86%. Pada jalur non-prestasi, akurasi algoritma C4.5 sebesar 61,54% dan algoritma CART sebesar 63,16%. Dilihat dari segi akurasinya, algoritma C4.5 dan CART lebih baik digunakan untuk memprediksi jalur prestasi daripada jalur non-prestasi
Gunawan R. Santosa - One of the best experts on this subject based on the ideXlab platform.
-
Perbandingan Akurasi Algoritma C4.5 dan CART dalam Memprediksi Kategori Indeks Prestasi Mahasiswa
Diponegoro University, 2018Co-Authors: Dea Alverina, Antonius Rachmat Chrismanto, Gunawan R. SantosaAbstract:This research compared the accuracy of prediction of Grade Point Average (GPA) of the first semester students using C4.5 and CART algorithms in Faculty of Information Technology (FTI), Universitas Kristen Duta Wacana (UKDW). This research also explored various parameters such as Numeric Attribute categorization, data balance, GPA categories number, and different Attributes availability due to the difference of data availability between Achievement Admission (AA) and Regular Admission (RA). The training data used to create decision tree were FTI students, 2008-2015 batch, while the testing data were FTI students, 2016 batch. The accuracy of prediction was measured by using crosstab table. In AA, the accuracy of both algorithms can be achieved about 86.86%. Meanwhile, in RA the accuracy of C4.5 is about 61.54% and CART is about 63.16%. From these accuracy result, both algorithms are better to predict AA rather than RA. Penelitian ini membandingkan akurasi prediksi kategori Indeks Prestasi (IP) semester pertama mahasiswa Fakultas Teknologi Informasi (FTI) Universitas Kristen Duta Wacana (UKDW) menggunakan algoritma C4.5 dan CART. Penelitian ini juga mengeksplorasi berbagai parameter seperti kategorisasi atribut numerik, keseimbangan data, jumlah kategori IP, dan ketersediaan atribut yang berbeda karena perbedaan ketersediaan data antara jalur prestasi dan jalur non-prestasi. Data mahasiswa FTI tahun 2008-2015 digunakan sebagai data latih sedangkan data uji menggunakan data tahun 2016. Akurasi kedua algoritma dalam memprediksi tersebut diukur dengan menggunakan tabel crosstab. Pada jalur prestasi, akurasi kedua algoritma mampu mencapai 86,86%. Pada jalur non-prestasi, akurasi algoritma C4.5 sebesar 61,54% dan algoritma CART sebesar 63,16%. Dilihat dari segi akurasinya, algoritma C4.5 dan CART lebih baik digunakan untuk memprediksi jalur prestasi daripada jalur non-prestasi
Maxime Cordy - One of the best experts on this subject based on the ideXlab platform.
-
beyond boolean product line model checking dealing with feature Attributes and multi features
International Conference on Software Engineering, 2013Co-Authors: Maxime Cordy, Pierreyves Schobbens, Patrick Heymans, Axel LegayAbstract:Model checking techniques for software product lines (SPL) are actively researched. A major limitation they currently have is the inability to deal efficiently with non-Boolean features and multi-features. An example of a non-Boolean feature is a Numeric Attribute such as maximum number of users which can take different Numeric values across the range of SPL products. Multi-features are features that can appear several times in the same product, such as processing units which number is variable from one product to another and which can be configured independently. Both constructs are extensively used in practice but currently not supported by existing SPL model checking techniques. To overcome this limitation, we formally define a language that integrates these constructs with SPL behavioural specifications. We generalize SPL model checking algorithms correspondingly and evaluate their applicability. Our results show that the algorithms remain efficient despite the generalization.
Kazuo Hashimoto - One of the best experts on this subject based on the ideXlab platform.
-
decision tree induction from Numeric data stream
Australasian Joint Conference on Artificial Intelligence, 2008Co-Authors: Satoru Nishimura, Masahiro Terabe, Kazuo HashimotoAbstract:Hoeffding Tree Algorithm is known as a method to induce decision trees from a data stream. Treatment of Numeric Attribute on Hoeffding Tree Algorithm has been discussed for stationary input. It has not yet investigated, however, for non-stationary input where the effect of concept drift is apparent. This paper identifies three major approaches to handle Numeric values, Exhaustive Method, Gaussian Approximation, and Discretizaion Method, and through experiment shows the best suited modeling of Numeric Attributes for Hoeffding Tree Algorithm. This paper also experimentaly compares the performance of two known methods for concept drift detection, Hoeffding Bound Based Method and Accuracy Based Method.