@article{Meyer1985,
abstract = {A critique of a natural-language specification, followed by presentation of a mathematical alternative, demonstrates the weakness of natural language and the strength of formalism in requirements specifications. {\textcopyright} 1985, American Medical Association. All rights reserved.},
author = {Meyer, Bertrand},
doi = {10.1109/MS.1985.229776},
issn = {0740-7459},
journal = {IEEE Software},
month = {jan},
number = {1},
pages = {6--26},
title = {{On Formalism in Specifications}},
url = {http://ieeexplore.ieee.org/document/1695257/},
volume = {2},
year = {1985}
}
@article{Purnomo2017,
abstract = {Pengembangan perangkat lunak diawali dengan proses yang sangat penting yaitu memahami dan menentukan seperti apa perangkat lunak yang nantinya akan dibangun yang ditulis ke dalam sebuah dokumen Spesifikasi Kebutuhan Perangkat Lunak (SKPL). Meyer's “The Seven Sins of Specifier” menjelaskan hal-hal yang harus dihindari dalam menyusun SKPL. Salah satunya adalah overspecification. Overspecification terjadi ketika dalam dokumen spesifikasi terdapat elemen yang tidak terkait pada fitur permasalahan melainkan terkait pada kemungkinan solusi permasalahan. Penelitian ini mengajukan sebuah metode untuk mendeteksi adanya overspecification pada dokumen SKPL dengan membangun sebuah text classifier berbasis decision tree memanfaatkan kakas bantu pengolahan bahasa alami. Dari hasil pengujian dan evaluasi didapatkan nilai Kappa 0,8872 pada threshold 0,0. Ini berarti bahwa solusi yang diajukan bekerja dengan baik dan dapat digunakan untuk mendeteksi adanya overspecification pada dokumen spesifikasi kebutuhan perangkat lunak dengan nilai Kappa 0,8872 atau proporsi kesepakatan antara solusi yang diajukan dengan anotator adalah almost perfect agreement.},
author = {Purnomo, Welly and Siahaan, Daniel Oranova},
doi = {10.35585/inspir.v7i1.2431},
issn = {20886705},
journal = {Inspiration : Jurnal Teknologi Informasi dan Komunikasi},
month = {jun},
number = {1},
pages = {1--9},
title = {{Pendeteksian Overspesification Pada Dokumen Spesifikasi Kebutuhan Perangkat Lunak}},
url = {https://jurnal.akba.ac.id/index.php/inspiration/article/view/2431},
volume = {7},
year = {2017}
}
@article{Enda2018,
abstract = {Tahap awal dalam pengembangan perangkat lunak ialah menelusuri, mengumpulkan dan menyajikan segala kebutuhan pengguna ke dalam sebuah dokumen spesifikasi kebutuhan perangkat lunak (SKPL). Latar belakang akademik yang beragam, pengalaman yang berbeda, dan keterbatasan pengetahuan yang dimiliki oleh perekayasa kebutuhan memungkinkan adanya kesalahan dalam pembuatan dokumen SKPL. Salah satu kesalahan yang sering muncul pada sebuah dokumen SKPL ialah terdapatnya penggunaan kata-kata yang rancu. Hal ini tentunya dapat menyebabkan kesalahan penafsiran dan kesulitan dalam memahami kebutuhan perangkat lunak yang hendak dibangun bagi pemangku kepentingan dalam proses pengembangan perangkat lunak. Penelitian ini bertujuan mengusulkan sebuah pendekatan untuk memberikan rekomendasi perbaikan pernyataan kebutuhan perangkat lunak yang rancu. Adapun metode yang diusulkan adalah teknik berbasis aturan dengan menggunakan model bahasa n-gram. Realibilitas metode usulan di-evaluasi menggunakan indeks statistik Gwet's AC1. Hasil analisis metode rekomendasi yang diusulkan memiliki tingkat proporsi kesepakatan yang lebih baik dibandingkan dengan metode rekomendasi menggunakan teknik statistik berbasis frekuensi n-gram. Metode rekomendasi yang diusulkan memiliki nilai indeks statistik Gwet's AC1 tertinggi sebesar 0.5263 dengan tingkat proporsi kesepakatan sedang. Abstract The first stage in software development is to investigate, collect and provide all user requirements into a software requirements specification document (SRS's). Diverse academic background, different experiences, and the limitations of knowledge possessed by the requirement engineer make possible mistakes in the creation of SRS's documents. One of the most common mistakes in SRS's document is the use of ambiguous words. This can certainly lead to misinterpretation and difficulties in understanding the software requirement that stakeholders to built in the software development process. The purpose of this research is to build an approach that gives recommendation improvement of ambiguous software requirement statement. The proposed method is a rule-based technique using n-gram language model. The reliability of the proposed method is evaluated using Gwet's AC1 statistical index. The analysis results of the proposed recommendation method have a better level of agreement proportion than the recommendation method using the n-gram frequency-based statistical technique. The proposed recommendation method has the highest Gwet's AC1 statistic value of 0.5263 with a moderate agreement proportion rate.},
author = {Enda, Depandi and Siahaan, Daniel},
doi = {10.25126/jtiik.201852627},
issn = {2528-6579},
journal = {Jurnal Teknologi Informasi dan Ilmu Komputer},
month = {may},
number = {2},
pages = {207},
title = {{Rekomendasi Perbaikan Pernyataan Kebutuhan yang Rancu dalam Spesifikasi Kebutuhan Perangkat Lunak Menggunakan Teknik Berbasis Aturan}},
url = {http://jtiik.ub.ac.id/index.php/jtiik/article/view/627},
volume = {5},
year = {2018}
}
@article{SariSahadi2015,
abstract = {Abstrak.   Dalam membuat dan menganalisa suatu dokumen SKPL diperlukan ketelitian dalam penyusunan SKPL. Dokumen SKPL harus jelas, lengkap, dan tidak ambigu. Istilah berbeda merupakan varian dari noise dalam suatu dokumen SKPL. Penelitian ini berfokus mengenai istilah berbeda yang dikenali sebagai sinonim pada pasangan kalimat dalam dokumen SKPL. Sinonim merupakan kata yang memiliki istilah yang berbeda dan bermakna sama. Perancangan metode terdiri dari proses pelatihan dan pengujian, yaitu prapemrosesan, menghitung kemiripan semantik dari pasangan kalimat dan menentukan nilai threshold. Sedangkan nilai Kappa untuk mengetahui perancangan metode dapat diandalkan dan digunakan untuk mendeteksi ketidakkonsisten istilah pada dokumen SKPL. Hasilnya adalah pasangan kalimat yang terdeteksi sebagai istilah berbeda.          Kata Kunci: dokumen SKPL, fakta, istilah berbeda, kemiripan semantic},
author = {{Sari Sahadi}, Fitria Vera and Siahaan, Daniel Oranova and Yuhana, Umi Laili},
file = {:C$\backslash$:/Users/animf/AppData/Local/Temp/619-2074-1-PB.pdf:pdf},
issn = {1978-0087},
journal = {SCAN - Jurnal Teknologi Informasi dan Komunikasi},
number = {3},
pages = {9--16},
title = {{Pendeteksian Istilah Berbeda Pada Dokumen Spesifikasi Kebutuhan Perangkat Lunak (Skpl)}},
url = {http://www.ejournal.upnjatim.ac.id/index.php/scan/article/view/619},
volume = {10},
year = {2015}
}
@article{Siahaan2012,
author = {Siahaan, Daniel and Umami, Izzatul},
doi = {10.12962/j20882033.v23i4.99},
issn = {2088-2033},
journal = {IPTEK The Journal for Technology and Science},
month = {nov},
number = {4},
title = {{Natural Language Processing for Detecting Forward Reference in a Document}},
url = {https://iptek.its.ac.id/index.php/jts/article/view/99},
volume = {23},
year = {2012}
}
@article{Yang2011,
author = {Yang, Hui and de Roeck, Anne and Gervasi, Vincenzo and Willis, Alistair and Nuseibeh, Bashar},
doi = {10.1007/s00766-011-0119-y},
issn = {0947-3602},
journal = {Requirements Engineering},
month = {sep},
number = {3},
pages = {163--189},
title = {{Analysing anaphoric ambiguity in natural language requirements}},
url = {http://link.springer.com/10.1007/s00766-011-0119-y},
volume = {16},
year = {2011}
}
@article{Manek2019,
abstract = {Requirements engineering phase in software development resulting in a SRS (Software Requirements Specification) document. The use of natural language approach in generating such document has some drawbacks that caused 7 common mistakes among the engineer which had been formulated by Meyer as "The 7 sins of specifier". One of the 7 common mistakes is noise. This study attempted to detect noise in software requirements with spectral clustering. The clustering algorithm working on fewer dimensions compared to others. The resulting kappa coefficient is 0.4426 . The result showed that the consistency between noise prediction and noise assessment made by three annotators is still low.},
author = {Manek, Patricia Gertrudis and Siahaan, Daniel},
doi = {10.12962/j24068535.v17i1.a771},
file = {:C$\backslash$:/Users/animf/OneDrive/Kuliah/thesis/771-1710-1-PB.pdf:pdf},
issn = {2406-8535},
journal = {JUTI: Jurnal Ilmiah Teknologi Informasi},
keywords = {natural language processing,noise detection,software requirements,spectral clustering},
month = {mar},
number = {1},
pages = {30},
title = {{NOISE DETECTION IN SOFTWARE REQUIREMENTS SPECIFICATION DOCUMENT USING SPECTRAL CLUSTERING}},
url = {http://juti.if.its.ac.id/index.php/juti/article/view/771},
volume = {17},
year = {2019}
}
@article{Cai2011,
author = {Cai, Xiaoyan and Zhang, Renxian and Gao, Dehong and Li, Wenjie},
journal = {Proceedings of 5th International Joint Conference on Natural Language Processing},
pages = {491--499},
title = {{Simultaneous Clustering and Noise Detection for Theme-based Summarization}},
url = {http://aclweb.org/anthology/I11-1055},
year = {2011}
}
@article{Gan2017,
author = {Gan, Guojun and Ng, Michael Kwok-Po},
doi = {10.1016/j.patrec.2017.03.008},
issn = {01678655},
journal = {Pattern Recognition Letters},
month = {apr},
pages = {8--14},
title = {k -means clustering with outlier removal},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0167865517300740},
volume = {90},
year = {2017}
}
@article{Mahapatra2012,
author = {Mahapatra, Amogh and Srivastava, Nisheeth and Srivastava, Jaideep},
doi = {10.3390/a5040469},
issn = {1999-4893},
journal = {Algorithms},
month = {oct},
number = {4},
pages = {469--489},
title = {{Contextual Anomaly Detection in Text Data}},
url = {http://www.mdpi.com/1999-4893/5/4/469},
volume = {5},
year = {2012}
}
@article{Kamaruddin2012,
author = {Kamaruddin, Siti Sakira and Hamdan, Abdul Razak and Bakar, Azuraliza Abu and {Mat Nor}, Fauzias},
doi = {10.3233/IDA-2012-0535},
issn = {15714128},
journal = {Intelligent Data Analysis},
mendeley-groups = {Jurnal},
month = {may},
number = {3},
pages = {487--511},
title = {{Deviation detection in text using conceptual graph interchange format and error tolerance dissimilarity function}},
url = {https://www.medra.org/servlet/aliasResolver?alias=iospress{\&}doi=10.3233/IDA-2012-0535},
volume = {16},
year = {2012}
}
@article{Colditz2015,
abstract = {Land cover mapping for large regions often employs satellite images of medium to coarse spatial resolution, which complicates mapping of discrete classes. Class memberships, which estimate the proportion of each class for every pixel, have been suggested as an alternative. This paper compares different strategies of training data allocation for discrete and continuous land cover mapping using classification and regression tree algorithms. In addition to measures of discrete and continuous map accuracy the correct estimation of the area is another important criteria. A subset of the 30 m national land cover dataset of 2006 (NLCD2006) of the United States was used as reference set to classify NADIR BRDF-adjusted surface reflectance time series of MODIS at 900 m spatial resolution. Results show that sampling of heterogeneous pixels and sample allocation according to the expected area of each class is best for classification trees. Regression trees for continuous land cover mapping should be trained with random allocation, and predictions should be normalized with a linear scaling function to correctly estimate the total area. From the tested algorithms random forest classification yields lower errors than boosted trees of C5.0, and Cubist shows higher accuracies than random forest regression.},
author = {Colditz, Ren{\'{e}} Roland},
doi = {10.3390/rs70809655},
file = {:C$\backslash$:/Users/animf/OneDrive/Kuliah/thesis/refparent/remotesensing-07-09655-v2.pdf:pdf},
issn = {20724292},
journal = {Remote Sensing},
keywords = {Class membership estimation,Classification tree,Discrete classification,MODIS,National land cover dataset of the united states 2,Regression tree,Sample allocation schemes,Training data},
number = {8},
pages = {9655--9681},
title = {{An evaluation of different training sample allocation schemes for discrete and continuous land cover classification using decision tree-based algorithms}},
volume = {7},
year = {2015}
}
@article{siahaan2012analisa,
abstract = {Tugas utama dari seorang programmer adalah tentunya menyusun sebuah kode-kode bahasa pemrograman agar nantinya bisa disusun untuk menjadi sebuah program komputer yang handal. Namun sebelum menyusun kode-kode tersebut tentunya seorang programmer harus mengetahui kira-kira program seperti apa yang diinginkan oleh klien. Untuk itu seorang programmer handal hendaknya mengetahui konsep yang dinamakan dengan Rekayasa Perangkat Lunak. Karena dengan konsep rekayasa perangkat lunak ini merupakan dasar teori untuk bagaimana menyusun dan membuat sebuah software agar sesuai dengan spesifikasi kebutuhan sistem. Buku ini ditujukan bagi para mahasiswa strata-1 maupun strata-2 yang menekuni bidang rekayasa perangkat lunak, khususnya rekayasa kebutuhan perangkat lunak. Akan tetapi buku ini juga dapat menjadi bahan pengayaan bagi setiap perekayasa sistem yang hendak memahami dan menguasai metode, teknologi, kerangka kerja, ataupun aplikasi yang terkait dengan spesifikasi kebutuhan. Buku ini ditulis ke dalam sembilan bagian. Bagian pertama dari buku ini memberikan gambaran dasar mengenai rekayasa kebutuhan. Bagian kedua memberikan perspektif tentang pihak-pihak yang mungkin berkepentingan terhadap proses spesifikasi kebutuhan yang baik. Bagian ketiga menjelaskan tentang teknis skenario sebagai salah satu teknik yang banyak dipakai dalam proses pengumpulan kebutuhan. Bagian empat, lima, enam dan delapan menjelaskan sub-sub proses di dalam rekayasa kebutuhan. Bagian ketujuh mengulas mengenai kebutuhan yang baik berdasarkan kepada acuan SMART Requirements. Bagian yang terakhir ditutup dengan penjelasan dan ulasan terkait dengan manajemen kebutuhan.},
author = {Siahaan, Daniel},
isbn = {978-979-29-3195-2},
journal = {Yogyakarta: Andi Offset},
keywords = {rekayasa kebutuhan,requirements engineering},
pages = {287},
title = {{Analisa Kebutuhan dalam Rekayasa Perangkat Lunak}},
year = {2012}
}
@article{Immitzer2012,
abstract = {Tree species diversity is a key parameter to describe forest ecosystems. It is, for example, important for issues such as wildlife habitat modeling and close-to-nature forest management. We examined the suitability of 8-band WorldView-2 satellite data for the identification of 10 tree species in a temperate forest in Austria. We performed a Random Forest (RF) classification (object-based and pixel-based) using spectra of manually delineated sunlit regions of tree crowns. The overall accuracy for classifying 10 tree species was around 82{\%} (8 bands, object-based). The class-specific producer's accuracies ranged between 33{\%} (European hornbeam) and 94{\%} (European beech) and the user's accuracies between 57{\%} (European hornbeam) and 92{\%} (Lawson's cypress). The object-bas approach outperformed the pixel-based approach. We could show that the 4 new WorldView-2 bands (Coastal, Yellow, Red Edge, and Near Infrared 2) have only limited impact on classification accuracy if only the 4 main tree species (Norway spruce, Scots pine, European beech, and English oak) are to be separated. However, classification accuracy increased significantly using the full spectral resolution if further tree species were included. Beside the impact on overall classification accuracy, the importance of the spectral bands was evaluated with two measures provided by RF. An in-depth analysis of the RF output was carried out to evaluate the impact of reference data quality and the resulting reliability of final class assignments. Finally, an extensive literature review on tree species classification comprising about 20 studies is presented. {\textcopyright} 2012 by the authors.},
author = {Immitzer, Markus and Atzberger, Clement and Koukal, Tatjana},
doi = {10.3390/rs4092661},
file = {:C$\backslash$:/Users/animf/OneDrive/Kuliah/thesis/refparent/remotesensing-04-02661-v2.pdf:pdf},
issn = {20724292},
journal = {Remote Sensing},
keywords = {Classification reliability,Linear discriminant analysis,Random forest,Temperate forest,Tree species classification,Variable importance measures,WorldView-2},
number = {9},
pages = {2661--2693},
title = {{Tree species classification with Random forest using very high spatial resolution 8-band worldView-2 satellite data}},
volume = {4},
year = {2012}
}
@article{Rebentrost2014,
author = {Rebentrost, Patrick and Mohseni, Masoud and Lloyd, Seth},
doi = {10.1103/PhysRevLett.113.130503},
issn = {0031-9007},
journal = {Physical Review Letters},
mendeley-groups = {Jurnal},
month = {sep},
number = {13},
pages = {130503},
title = {{Quantum Support Vector Machine for Big Data Classification}},
url = {https://link.aps.org/doi/10.1103/PhysRevLett.113.130503},
volume = {113},
year = {2014}
}
@article{Patil2013,
author = {Patil, Tina R and Sherekar, S S},
file = {:C$\backslash$:/Users/animf/Downloads/189.pdf:pdf},
keywords = {bayes,databases,databases such as spatial,false positive rate,j48 decision tree,multimedia,na{\"{i}}ve,time-series databases and textual,true positive rate},
mendeley-groups = {Jurnal},
number = {2},
title = {{Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification}},
volume = {6},
year = {2013}
}
@article{Winter2016,
author = {Winter, Joost C F De and Gosling, Samuel D and Potter, Jeff},
doi = {10.1037/met0000079},
file = {:C$\backslash$:/Users/animf/Downloads/2016-dewinter.pdf:pdf},
keywords = {10,1037,1896,and the spearman rank,correlation,correlation coefficient,doi,dx,http,met0000079,moment correlation coefficient,nonparametric versus parametric,org,outlier,pear-,r p,r s,rank transformation,son,supp,supplemental materials,the pearson product},
mendeley-groups = {Jurnal},
number = {3},
pages = {273--290},
title = {{Comparing the Pearson and Spearman Correlation Coefficients Across Distributions and Sample Sizes : A Tutorial Using Simulations and Empirical Data}},
volume = {21},
year = {2016}
}
@article{Amancio2014,
author = {Amancio, Diego Raphael and Comin, Cesar Henrique and Casanova, Dalcimar and Travieso, Gonzalo and Bruno, Martinez and Rodrigues, Francisco Aparecido and Costa, Fontoura},
doi = {10.1371/journal.pone.0094137},
file = {:C$\backslash$:/Users/animf/OneDrive/Kuliah/thesis/refparent/A Systematic Comparison of Supervised Classifiers.PDF:PDF},
number = {4},
title = {{A Systematic Comparison of Supervised Classifiers}},
volume = {9},
year = {2014}
}
@inproceedings{Umber2011,
author = {Umber, Ashfa and Bajwa, Imran Sarwar},
booktitle = {2011 Sixth International Conference on Digital Information Management},
doi = {10.1109/ICDIM.2011.6093363},
isbn = {978-1-4577-1539-6},
mendeley-groups = {Jurnal},
month = {sep},
pages = {102--107},
publisher = {IEEE},
title = {{Minimizing ambiguity in natural language software requirements specification}},
url = {http://ieeexplore.ieee.org/document/6093363/},
year = {2011}
}
@inproceedings{Romano2018,
address = {New York, NY, USA},
author = {Romano, Simone and Scanniello, Giuseppe and Fucci, Davide and Juristo, Natalia and Turhan, Burak},
booktitle = {Proceedings of the 12th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement},
doi = {10.1145/3239235.3240496},
isbn = {9781450358231},
month = {oct},
pages = {1--10},
publisher = {ACM},
title = {{The effect of noise on software engineers' performance}},
url = {https://dl.acm.org/doi/10.1145/3239235.3240496},
year = {2018}
}
@inproceedings{Jiang2008,
author = {Jiang, Sheng-yi and An, Qing-bo},
booktitle = {2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery},
doi = {10.1109/FSKD.2008.244},
isbn = {978-0-7695-3305-6},
month = {oct},
pages = {429--433},
publisher = {IEEE},
title = {{Clustering-Based Outlier Detection Method}},
url = {http://ieeexplore.ieee.org/document/4666153/},
year = {2008}
}
@inproceedings{Pamula2011,
author = {Pamula, Rajendra and Deka, Jatindra Kumar and Nandi, Sukumar},
booktitle = {2011 Second International Conference on Emerging Applications of Information Technology},
doi = {10.1109/EAIT.2011.25},
isbn = {978-1-4244-9683-9},
month = {feb},
pages = {253--256},
publisher = {IEEE},
title = {{An Outlier Detection Method Based on Clustering}},
url = {http://ieeexplore.ieee.org/document/5734938/},
year = {2011}
}
@inproceedings{Liu2010,
abstract = {Based on the text information processing, we have made a study on the application of support vector machine in text categorization. Through introducing the basic principle of SVM, we described the process of text classification and further proposed a SVM-based classification model. Finally, experimental data show that F1 value of SVM classifier has reached more than 86.26{\%}, and the classification results comparing to other classification methods have greatly improved, and it also proves that SVM is an effective machine learning method. {\textcopyright} 2010 IEEE.},
author = {Liu, Zhijie and Lv, Xueqiang and Liu, Kun and Shi, Shuicai},
booktitle = {2010 Second International Workshop on Education Technology and Computer Science},
doi = {10.1109/ETCS.2010.248},
file = {:C$\backslash$:/Users/animf/OneDrive/Kuliah/thesis/maybe/classStudy on SVM Compared with the other Text.pdf:pdf},
isbn = {978-1-4244-6388-6},
keywords = {Machine learning,SVM,Text classification},
pages = {219--222},
publisher = {IEEE},
title = {{Study on SVM Compared with the other Text Classification Methods}},
url = {http://ieeexplore.ieee.org/document/5459006/},
volume = {1},
year = {2010}
}