cite-check

Cite-Abgleich Bericht 2026-08-17

Cites gesamt: 84, davon 84 mit Primärquellen-Bezug

BFOS84 (27 Cites, 27 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	60		(bibliograph.)	–	–	–
02_Grundlagen.tex	70	S.~28,f.	28	9	✓	The four elements needed in the initial tree growing procedu
02_Grundlagen.tex	297		(bibliograph.)	–	–	–
03_Funktionsprinzipien.tex	23	S.~23	23	4	✓	The first problem in tree construction is how to use £ to de
03_Funktionsprinzipien.tex	28	S.~26, M2	26	7	✓	To terminate the tree growing, a heuristic rule was designed
03_Funktionsprinzipien.tex	30	S.~228	228	39	✓	A tree structured predictor is similar to a tree structured
03_Funktionsprinzipien.tex	34	S.~30	30	11	✓	When fixed-dimensional data have only ordered variables, an-
03_Funktionsprinzipien.tex	105	S.~25	25	6	✓	Then the goodness of the split is defined to be the decrease
03_Funktionsprinzipien.tex	112	S.~26, M1	26	7	✓	To terminate the tree growing, a heuristic rule was designed
03_Funktionsprinzipien.tex	132	S.~228	228	39	✓	A tree structured predictor is similar to a tree structured
03_Funktionsprinzipien.tex	139	S.~222	222	33	✓	But for reasons having to do with ease of computations, the
03_Funktionsprinzipien.tex	141	S.~230	230	41	✓	PROPOSITION 8.10. The value of y(t) that minimizes R(d) is
03_Funktionsprinzipien.tex	145	S.~231	231	42	✓	DEFINITION 8.13. The best split 4* of t is that split in S
03_Funktionsprinzipien.tex	162	S.~103, M1	103	20	✓	In later work the Gini diversity index was adopted. This has
03_Funktionsprinzipien.tex	175	S.~103, M3	103	20	✓	In later work the Gini diversity index was adopted. This has
03_Funktionsprinzipien.tex	189	S.~104, M1	104	21	✓	The second approach to the multiclass problem adopts a diffe
03_Funktionsprinzipien.tex	195	S.~103, M2	103	20	✓	In later work the Gini diversity index was adopted. This has
03_Funktionsprinzipien.tex	246	S.~104,f., M2	104	21	✓	The second approach to the multiclass problem adopts a diffe
03_Funktionsprinzipien.tex	262	S.~60	60	16	✓	In fact, stepwise regression simulations have shown that pas
03_Funktionsprinzipien.tex	264	S.~61, M1	61	17	✓	Notice two important features in Table 3.1: 1. The estimate
03_Funktionsprinzipien.tex	269	S.~61, M2	61	17	✓	Notice two important features in Table 3.1: 1. The estimate
03_Funktionsprinzipien.tex	275	S.~62, M1	62	18	✓	1. Prune instead of stopping. Grow a tree that is much too
03_Funktionsprinzipien.tex	282	S.~63	63	19	✓	The first step is to grow a very large tree T ax by letting
03_Funktionsprinzipien.tex	298	S.~62, M2	62	18	✓	1. Prune instead of stopping. Grow a tree that is much too
05_Anwendung.tex	9	Kap.~6, S.~174	174	23	✓	6 MEDICAL DIAGNOSIS AND PROGNOSIS
05_Anwendung.tex	9	Kap.~7, S.~203	203	25	✓	7 MASS SPECTRA CLASSIFICATION
06_Zusammenfassung.tex	56	S.~39	39	13	✓	In problems where linear structure is suspected, the set of

Bre01 (10 Cites, 5 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	64		(bibliograph.)	–	–	–
02_Grundlagen.tex	315		(bibliograph.)	–	–	–
04_Ensembleverfahren.tex	113	S.~6	6	2	✓	After a large number of trees is generated, they vote for th
04_Ensembleverfahren.tex	118	S.~10	10	6	✓	To improve accuracy, the randomness injected has to minimize
04_Ensembleverfahren.tex	120	S.~11, M1	11	7	✓	In my experiments with random forests, bagging is used in ta
04_Ensembleverfahren.tex	127	S.~10	10	6	✓	To improve accuracy, the randomness injected has to minimize
04_Ensembleverfahren.tex	166	S.~11, M2	11	7	✓	In my experiments with random forests, bagging is used in ta
04_Ensembleverfahren.tex	171	S.~11, M1	11	7	✓	In my experiments with random forests, bagging is used in ta
04_Ensembleverfahren.tex	174	S.~11, M2	11	7	✓	In my experiments with random forests, bagging is used in ta
05_Anwendung.tex	12	S.~12, Tab.~1	12	8	✓	Table 1. Data set summary. Data set Train size Test size Inp

Bre96a (7 Cites, 3 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	62		(bibliograph.)	–	–	–
02_Grundlagen.tex	310		(bibliograph.)	–	–	–
04_Ensembleverfahren.tex	48	S.~123	123	1	✓	Still, an imitation of the process leading to ~#A can be don
04_Ensembleverfahren.tex	56	S.~124	124	2	✓	For unstable procedures bagging works well. In Section 2 we
04_Ensembleverfahren.tex	62	S.~124	124	2	✓	For unstable procedures bagging works well. In Section 2 we
04_Ensembleverfahren.tex	64	S.~137	137	15	✓	What one loses, with the trees, is a simple and interpretabl
06_Zusammenfassung.tex	65	S.~137	137	15	✓	What one loses, with the trees, is a simple and interpretabl

Bre96b (5 Cites, 3 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	63		(bibliograph.)	–	–	–
02_Grundlagen.tex	303		(bibliograph.)	–	–	–
04_Ensembleverfahren.tex	13	S.~2354	2354	5	✓	Heuristic definition. A regularization procedure is unstable
04_Ensembleverfahren.tex	27	S.~2355	2355	6	✓	Given that instability has undesirable consequences, what ca
04_Ensembleverfahren.tex	31	S.~2374	2374	25	✓	When using nonlinear predictors there are usually no simple

CBHK02 (6 Cites, 4 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	66		(bibliograph.)	–	–	–
02_Grundlagen.tex	322		(bibliograph.)	–	–	–
04_Ensembleverfahren.tex	190	S.~328, M1	328	8	✓	We propose an over-sampling approach in which the minority c
04_Ensembleverfahren.tex	195	S.~328, M2	328	8	✓	We propose an over-sampling approach in which the minority c
04_Ensembleverfahren.tex	198	S.~331	331	11	✓	The majority class is under-sampled by randomly removing sam
04_Ensembleverfahren.tex	200	S.~352	352	32	✓	The results show that the SMOTE approach can improve the acc

PNRB15 (29 Cites, 24 Highlights)

Kap-Datei	Zeile	Cite-Spec	Article-S.	PDF-S.	Highlight?	Highlight-Text (Auszug)
01_Einleitung.tex	68		(bibliograph.)	–	–	–
02_Grundlagen.tex	329		(bibliograph.)	–	–	–
05_Anwendung.tex	32	S.~142, M4	142	4	✓	The usual RUL approach is to estimate f ðxtjYtÞ or the expec
05_Anwendung.tex	38	S.~139, M1	139	1	✓	We present a data-driven approach that combines pattern reco
05_Anwendung.tex	49	S.~139,f., M2	139	1	✓	We present a data-driven approach that combines pattern reco
05_Anwendung.tex	62	S.~142, M1	142	4	✓	The usual RUL approach is to estimate f ðxtjYtÞ or the expec
05_Anwendung.tex	65	S.~143, M2	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	72	S.~142, M2	142	4	✓	The usual RUL approach is to estimate f ðxtjYtÞ or the expec
05_Anwendung.tex	78	S.~143, M3	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	85	S.~143, M4	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	92	S.~143, M5	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	102	S.~143, M5	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	107	S.~143, M5	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	110	S.~144, M2	144	6	✓	Machine learning methods usually assume a fairly balanced da
05_Anwendung.tex	114	S.~145, M1	145	7	✓	We use the Synthetic Minority Over-sampling TEchnique (SMOTE
05_Anwendung.tex	142	S.~139,ff.	139	1	✓	We present a data-driven approach that combines pattern reco
05_Anwendung.tex	156	S.~142, M3	142	4	✓	The usual RUL approach is to estimate f ðxtjYtÞ or the expec
05_Anwendung.tex	161	S.~147,f.	147	9	✓	Interestingly, from this point of view, the system performan
05_Anwendung.tex	166	S.~145, M2	145	7	✓	We use the Synthetic Minority Over-sampling TEchnique (SMOTE
05_Anwendung.tex	167	S.~143, M1	143	5	✓	Ultimately, the criterion for evaluation of the model perfor
05_Anwendung.tex	181	S.~146, M1	146	8	✓	The different feature selection approaches, and the age norm
05_Anwendung.tex	184	S.~144, M1	144	6	✓	Machine learning methods usually assume a fairly balanced da
05_Anwendung.tex	240	S.~148, Tab.~1	148	10	✓	will be false negatives. Large number of them will lower acc
05_Anwendung.tex	251	S.~148	148	10	✓	will be false negatives. Large number of them will lower acc
05_Anwendung.tex	251	S.~149, M1	149	11	✓	The best features are the Beam search 1 and the Usage sets,
05_Anwendung.tex	255	S.~148	148	10	✓	will be false negatives. Large number of them will lower acc
05_Anwendung.tex	259	S.~149, M1	149	11	✓	The best features are the Beam search 1 and the Usage sets,
05_Anwendung.tex	269	S.~149,f., M2	149	11	✓	The best features are the Beam search 1 and the Usage sets,
05_Anwendung.tex	302	S.~149, M1	149	11	✓	The best features are the Beam search 1 and the Usage sets,