DYAH ERNY HERWINDIATI Ir., M.Si, Dr., Prof.
Jurnal
Buku
-
-
Tahun : -
ISBN: 978-613-9-58609-7
Penerbit : Lambert Academic Publishing
Halaman : 90
HKI
Makalah
-
-
-
Tahun: 2019
Nama forum : International Conference on Signals and Systems
Penyelenggara : -
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/335395758_Object_and_Human_Action_Recognition_From_Video_Using_Deep_Learning_Models
-
-
-
Tahun: 2018
Nama forum : SSRN Electronic Journal
Penyelenggara : SSRN Electronic Journal
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/327852370_Batik_Image_Retrieval_System_Using_Self_Organizing_Map
-
-
-
Tahun: 2018
Nama forum : SSRN Electronic Journal
Penyelenggara : SSRN Electronic Journal
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/328060831_Classification_of_Batik_Motifs_Using_Convolutional_Neural_Networks
-
-
-
Tahun: 2017
Nama forum : European Journal of Sustainable Development
Penyelenggara : -
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/322757231_Impervious_Surface_Mapping_Using_Robust_Depth_Minimum_Vector_Variance_Regression
-
-
-
Tahun: 2016
Nama forum : International Conference on Information Technology and Digital Applications
Penyelenggara : The International Conference on Information Technology and Digital Applications
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/314796838_Sugarcane_Land_Classification_with_Satellite_Imagery_using_Logistic_Regression_Model
-
-
-
Tahun: 2016
Nama forum : International Congress on Engineering and Information (ICEAI)
Penyelenggara : Conference Proceeding, Osaka Japan
Status : Pemakalah Biasa
Url :
-
Cloud Removal Menggunakan Metode Interpolasi Pada Citra LandSat 8
Cloud Removal Menggunakan Metode Interpolasi Pada Citra LandSat 8
Tahun: 2016
Nama forum : Seminar Nasional Teknologi Informasi (SNTI) 2016
Penyelenggara : Fakultas Teknologi Informasi Universitas Tarumanagara
Status : Pemakalah Biasa
Url :
-
DETEKSI PERUBAHAN LAHAN RUANG TERBUKA HIJAU DENGAN ROBUST ESTIMATOR PADA CITRA LANDSAT 8
DETEKSI PERUBAHAN LAHAN RUANG TERBUKA HIJAU DENGAN ROBUST ESTIMATOR PADA CITRA LANDSAT 8
Tahun: 2016
Nama forum : SESINDO 2016
Penyelenggara : Jurusan Sistem Informasi ITS & Association for Information Systems Indonesia Chapter (AISINDO)
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/322790193_DETEKSI_PERUBAHAN_LAHAN_RUANG_TERBUKA_HIJAU_DENGAN_ROBUST_ESTIMATOR_PADA_CITRA_LANDSAT_8
-
KLASIFIKASI LAHAN MANGROVE MENGGUNAKAN METODE SINGULAR VALUE DECOMPOSITION
KLASIFIKASI LAHAN MANGROVE MENGGUNAKAN METODE SINGULAR VALUE DECOMPOSITION
Tahun: 2016
Nama forum : SESINDO 2016
Penyelenggara : Jurusan Sistem Informasi ITS & Association for Information Systems Indonesia Chapter (AISINDO)
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/322790358_KLASIFIKASI_LAHAN_MANGROVE_MENGGUNAKAN_METODE_SINGULAR_VALUE_DECOMPOSITION
-
-
-
Tahun: 2015
Nama forum : 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS)
Penyelenggara : IEEE Indonesia, Universitas Indonesia (UI)
Status : Pemakalah Biasa
Url : http://ieeexplore.ieee.org/abstract/document/7415151/
-
-
-
Tahun: 2014
Nama forum : 2014 International Conference on Advanced Computer Science and Information Systems (ICACSIS)
Penyelenggara : IEEE Indonesia, Universitas Indonesia (UI)
Status : Invited / Keynote Speaker
Url : http://ieeexplore.ieee.org/abstract/document/7065892/
-
Performance of Robot Two-Dimensional Pricipal Component For Classification
Performance of Robot Two-Dimensional Pricipal Component For Classification
Tahun: 2014
Nama forum : International Conference on Advanced Computer Science and Information System (ICACSIS 2014).
Penyelenggara : Universitas Indonesia
Status : Pemakalah Biasa
Url :
-
Minimum Vector Variance for Robust Classifacition of Remote Sensing Data
Minimum Vector Variance for Robust Classifacition of Remote Sensing Data
Tahun: 2014
Nama forum : International Conference on Advanced Computer Science and Information System (ICACSIS 2014)
Penyelenggara : Universitas Indonesia
Status : Pemakalah Biasa
Url :
-
Robust Discriminant Analysis for Classifacition of Remote Sensing Data
Robust Discriminant Analysis for Classifacition of Remote Sensing Data
Tahun: 2014
Nama forum : International Conference on Advanced Computer Science and Information System (ICACSIS 2014)
Penyelenggara : Universitas Indonesia
Status : Pemakalah Biasa
Url :
-
-
-
Tahun: 2014
Nama forum : 2014 International Conference on Advanced Computer Science and Information Systems (ICACSIS)
Penyelenggara : IEEE Indonesia, Universitas Indonesia (UI)
Status : Pemakalah Biasa
Url : http://ieeexplore.ieee.org/abstract/document/7065889/
-
Klasifikasi Fase Pertumbuhan Padi dengan Bee Algorithm dan K-Nearest Neighbour
Klasifikasi Fase Pertumbuhan Padi dengan Bee Algorithm dan K-Nearest Neighbour
Tahun: 2014
Nama forum : Seminar Nasional Teknologi Informasi (SNTI)
Penyelenggara : Fakultas Teknologi Informasi UNTAR
Status : Pemakalah Biasa
Url :
-
AN EFFICIENT AND EFFECTIVE ROBUST ALGORITHM FOR CLASSIFICATION OF JAKARTA VEGETATION AREA
AN EFFICIENT AND EFFECTIVE ROBUST ALGORITHM FOR CLASSIFICATION OF JAKARTA VEGETATION AREA
Tahun: 2013
Nama forum : Seminar International Conference On Advance Computer Science And Information System (ICACSIS)
Penyelenggara : Bali
Status : Pemakalah Biasa
Url :
-
MULTI-CRITERIA VARIABLE SELECTION FOR PROCESS MONITORING
MULTI-CRITERIA VARIABLE SELECTION FOR PROCESS MONITORING
Tahun: 2013
Nama forum : Seminar Internasional World Statistics Congress
Penyelenggara : Hongkong-China
Status : Pemakalah Biasa
Url :
-
ROBUST REDUCTION DIMENSION FOR MAPPING OF RICE FIELD
ROBUST REDUCTION DIMENSION FOR MAPPING OF RICE FIELD
Tahun: 2013
Nama forum : The World Congress on Engineering 2013 (WCE 2013)
Penyelenggara : INTERNATIONAL ASSOCIATION OF ENGINEERS
Status : Pemakalah Biasa
Url :
-
SHORT RUN MULTIVARIATE CONTROL CHART FOR PROCESS MEN AND VARIABILITY
SHORT RUN MULTIVARIATE CONTROL CHART FOR PROCESS MEN AND VARIABILITY
Tahun: 2013
Nama forum : WORLD CONGRESS ON ENGINEERING 2013
Penyelenggara : INTERNATIONAL ASSOCIATION OF ENGINEERS
Status : Pemakalah Biasa
Url :
-
-
-
Tahun: 2013
Nama forum : World Congress on Engineering
Penyelenggara : International Association of Engineers (IAENG)
Status : Pemakalah Biasa
Url : http://www.iaeng.org/publication/WCE2013/WCE2013_pp1531-1536.pdf
-
-
-
Tahun: 2013
Nama forum : The World Congress on Engineering 2013
Penyelenggara : IAENG
Status : Pemakalah Biasa
Url : http://www.iaeng.org/publication/WCE2013/WCE2013_pp670-674.pdf
-
-
-
Tahun: 2013
Nama forum : 2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)
Penyelenggara : IEEE Indonesia, Universitas Indonesia (UI)
Status : Pemakalah Biasa
Url : http://ieeexplore.ieee.org/abstract/document/6761602/?reload=true
-
APLIKASI CLUSTERING DATA BERUKURAN BESAR DAN BERDIMENSI TINGGI BERDASARKAN JARAK
APLIKASI CLUSTERING DATA BERUKURAN BESAR DAN BERDIMENSI TINGGI BERDASARKAN JARAK
Tahun: 2013
Nama forum : Seminar Nasional Teknologi Informasi (SNTI) 2013
Penyelenggara : Fakultas Teknologi Informasi Universitas Tarumanagara
Status : Pemakalah Biasa
Url :
-
-
-
Tahun: 2012
Nama forum : 20th International Conference on COMPUTATIONAL STATISTICS (COMPSTAT 2012)
Penyelenggara : The European Regional Section of the IASC; Cyprus University of Technology
Status : Invited / Keynote Speaker
Url : https://scholar.google.com/citations?view_op=view_citation&hl=en&user=9w1rY-AAAAAJ&cstart=20&citation_for_view=9w1rY-AAAAAJ:_FxGoFyzp5QC
-
-
-
Tahun: 2012
Nama forum : Advanced Computer Science and Information Systems (ICACSIS), 2012 - Proceedings
Penyelenggara : Fasilkom UI
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/261491293_Land_classifier_using_parallel_minimum_vector_variance_method
-
-
-
Tahun: 2011
Nama forum : World Congress on Engineering
Penyelenggara : International Association of Engineers (IAENG)
Status : Pemakalah Biasa
Url : https://scholar.google.com/citations?view_op=view_citation&hl=en&user=9w1rY-AAAAAJ&cstart=20&citation_for_view=9w1rY-AAAAAJ:Zph67rFs4hoC
-
-
-
Tahun: 2010
Nama forum : The Seventh International Conference on Engineering Computational Technology
Penyelenggara : Universidad Polit?cnica de Valencia & ICITECH
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/269085715_A_Robust_Two-Dimensional_Principal_Component_Analysis_for_Classification
-
-
-
Tahun: 2009
Nama forum : World Congress on Engineering
Penyelenggara : International Association of Engineers (IAENG)
Status : Pemakalah Biasa
Url : http://iaeng.org/publication/WCE2009/WCE2009_pp1297-1302.pdf Tahun: 2009
-
-
-
Tahun: 2009
Nama forum : World Congress on Engineering
Penyelenggara : International Association of Engineers (IAENG)
Status : Pemakalah Biasa
Url : http://iaeng.org/publication/WCE2009/WCE2009_pp1297-1302.pdf
-
-
-
Tahun: 2008
Nama forum : Proceedings of The 2008 International Conference on Data Mining
Penyelenggara : -
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/220705022_Data_Mining_For_Outlier_With_Minimum_Vector_Variance
-
-
-
Tahun: 2008
Nama forum : Proceedings of the 2008 International Conference on Information Theory and Statistical Learning
Penyelenggara : -
Status : Pemakalah Biasa
Url : Outliers are some observations deviate from postulated pattern. The masking effect is a serious problem often found in the classic outlier detection.
-
-
-
Tahun: 2007
Nama forum : 56Th Session of The International Statistics Institute
Penyelenggara : -
Status : Pemakalah Biasa
Url : https://www.researchgate.net/publication/322790407_The_Method_for_Detecting_Outlying_Observations
Luaran Lain
-
-
Tahun: 2019
Jenis : Teknologi Tepat Guna (TTG)
Deskripsi : Mangroves are coastal vegetations that grow at the interface between land and sea. It can be found in tropical and subtropical tidal areas. Mangrove ecosystems have many ecological roles spans from forestry, fisheries, environmental conservation. The Indonesian archipelago is home to a large mangrove population which has enormous ecological value. This paper discusses mangrove land detection in the North Jakarta from Landsat 8 satellite imagery. One of the special characteristics of mangroves that are distinguishing them from another vegetation is their growing location. This characteristic makes mangrove classification using satellite imagery non trivial task. We need an advanced method that can confidently detect the mangrove ecosystem from the satellite images. The objective of this paper is to propose the robust algorithm using projection kurtosis and minimizing vector variance for mangrove land classification. The evaluation classification provides that the proposed algorithm has a good performance.
-
-
Tahun: 2018
Jenis : Model
Deskripsi : Mangroves are coastal vegetations that grow at the interface between land and sea. It can be found in tropical and subtropical tidal areas. Mangrove ecosystems have many ecological roles spans from forestry, fisheries, environmental conservation. The Indonesian archipelago is home to a large mangrove population which has enormous ecological value. This paper discusses mangrove land detection in the North Jakarta from Landsat 8 satellite imagery. One of the special characteristics of mangroves that are distinguishing them from another vegetation is their growing location. This characteristic makes mangrove classification using satellite imagery non trivial task. We need an advanced method that can confidently detect the mangrove ecosystem from the satellite images. The objective of this paper is to propose the robust algorithm using projection kurtosis and minimizing vector variance for mangrove land classification. The evaluation classification provides that the proposed algorithm has a good performance.
-
-
Tahun: 2018
Jenis : Model
Deskripsi : -
-
-
Tahun: 2018
Jenis : Model
Deskripsi : -
-
-
Tahun: 2017
Jenis : Model
Deskripsi : This paper proposes a reliable minimum vector variance regression algorithm for robust supervised impervious mapping. The mapping is done with a conventional two phase process; training and mapping process. The outcome of training process is the robust regression models useful for the knowledge base of mapping land cover. The robust regression model is built from the existing
-
Deteksi Penyakit Diabetes dengan Metode Fuzzy C-means Clustering dan K-means Clustering
Tahun: 2017
Jenis : Model
Deskripsi : Means dan Fuzzy C-Means. Pengelompokan terdiri dari kelompok diabetes dan non-diabetes. Pengujian untuk masing-masing metode dilakukan terhadap 9 data. Hasil pengujian terbaik metode K-Means adalah 73,438% dan untuk metode Fuzzy C-Means adalah 82,812%.
-
-
Tahun: 2017
Jenis : Model
Deskripsi : -
-
-
Tahun: 2016
Jenis : Model
Deskripsi : This paper compares two robust algorithms using kurtosis and singular value decomposition projection for mining outliers. We define the mining outliers as the labeling and testing outliers. Both robust projection algorithms work in two stages. In the first stage, the projection approaches are used for reducing the dimensionality of a dataset consisting of a large number of interrelated variables. In the next stage (the second stage), a robust covariance matrix minimizing vector variance (MVV) is used for estimation on the lower dimensional data space. The performances of both algorithms are almost similar; they have a. good performance for mining outliers.
-
-
Tahun: 2016
Jenis : Teknologi Tepat Guna (TTG)
Deskripsi : This paper discusses the classification of sugarcane plantation area from Landsat-8 satellite imagery. The classification process uses binary logistic regression method with time series data of normalized difference vegetation index as input. The process is divided into two steps: training and classification. The purpose of training step is to identify the best parameter of the regression model using gradient descent algorithm. The best fit of the model can be utilized to classify sugarcane and non-sugarcane area.
-
DETEKSI PERUBAHAN LAHAN RUANG TERBUKA HIJAU DENGAN ROBUST ESTIMATOR PADA CITRA LANDSAT 8
Tahun: 2016
Jenis : Teknologi Tepat Guna (TTG)
Deskripsi : Ruang Terbuka Hijau (sebidang tanah yang di tanami oleh rumput, pohon, semak belukar atau vegetasi lainnya). Ruang terbuka hijau melingkupi taman, kebun, dan makam. Dalam sebuah kota, ruang terbuka hijau sangat berguna untuk membantu kota dari banyak hal, seperti masalah banjir, pemanasan global dan lainnya. Luas lahan ruang terbuka hijau pada suatu kota paling sedikit adalah 30%. Pada penilitian ini, kita menggunakan satelit landsat 8 untuk mengklasifikasikan ruang terbuka hijau pada provinsi Jakarta. Penginderaan jauh adalah sebuah teknologi untuk mendapatkan informasi tanpa menyentuh objek tersebut dengan menggunakan bantuan satelit. Area akan dibagi menjadi 4 macam, yaitu taman, air, resapan dan non-RTH (bangunan, jalanan dan lainnya). Modified fast minimum covariance determinant (FMCD) akan digunakan untuk mengklasifikasikan wilayah tersebut. Proses pada penelitian ini melewati 3 tahap yaitu, pelatihan , evaluasi model dan pengujian. Berdasrkan hasil percobaan yang ada, modified FMCD memberikan hasil yang cukup efektif untuk mengklasifikasi.
-
KLASIFIKASI LAHAN MANGROVE MENGGUNAKAN METODE SINGULAR VALUE DECOMPOSITION
Tahun: 2016
Jenis : Model
Deskripsi : Hutan mangrove merupakan tipe ekosistem hutan yang tumbuh di daerah batas pasang-surutnya air, tepatnya daerah pantai dan sekitar muara sungai. Kondisi lahan hutan mangrove di Indonesia saat ini diketahui terus menurun dari tahun ke tahun. Penelitian ini bertujuan untuk melakukan klasifikasi lahan mangrove dengan menggunakan metode Singular Value Decomposition Regression dan Spectral Angle Mapper serta menghitung luas dari lahan mangrove yang terdeteksi. Data yang digunakan adalah data citra satelit Landsat-8 pada tahun 2013, 2014 dan 2015. Dengan studi kasus untuk wilayah pesisir Jakarta, Bekasi, Tangerang. Dari proses klasifikasi yang sudah dilakukan pada daerah pesisir Jakarta, Bekasi dan Tangerang memberikan hasil yang baik sehingga dapat dilihat perubahan luas dari lahan mangrove yang ada pada daerah tersebut.
-
PERUBAHAN LAHAN IMPERVIOUS DAN BUKAN IMPERVIOUS DENGAN METODE ADABOOST DISKRIMINAN (STUDI KASUS: JABODETABEK)
Tahun: 2016
Jenis : Rekayasa Sosial
Deskripsi : "Perubahan lahan impervious dan bukan impervious
dengan metode adaboost diskriminan bertujuan untuk
melakukan klasifikasi lahan ke dalam suatu kelompok
impervious atau bukan impervious dengan melakukan
analisa terhadap citra satelit Landsat 7 band 1, 2, 3, 4, 5,
dan 7. Metode adaboost dapat digunakan dalam
gabungan dengan berbagai algoritma pembelajaran
lainnya untuk meningkatkan performanya, salah satunya
dengan analisis diskriminan."
-
"KLASIFIKASI LAHAN IMPERVIOUS, AIR, DAN LAHAN
TERBUKA DENGAN METODE BOOSTRAP PRINCIPAL
COMPONENT ANALYSIS (STUDI KASUS: JABODETABEK)"
Tahun: 2016
Jenis : Rekayasa Sosial
Deskripsi : "Klasifikasi lahan
impervious, air, dan lahan terbuka ini menggunakan data
citra Landasat-7 tahun 2006, 2008, 2010, 2011, dan 2012
dengan menggunakan band 1, 2, 3, 4, 5, dan 7 dengan
tujuan untuk melakukan klasifikasi dari tahun ke tahun.
Metode yang digunakan adalah Bootstrap Principal
Component Analysis yang merupakan resampling PCA."
-
-
Tahun: 2014
Jenis : Model
Deskripsi : The robust dimension reduction for classification of two dimensional data is discussed in this paper. The classification process is done with reference of original data. The classifying of class membership is not easy when more than one variable are loaded with the same information, and they can be written as a near linear combination of other variables. The standard approach to overcome this problem is dimension reduction. One of the most common forms of dimensionality reduction is the principal component analysis (PCA). The two-dimensional principal component (2DPCA) is often called a variant of principal component. The image matrices were directly treated as 2D matrices; the covariance matrix of image can be constructed directly using the original image matrices. The presence of outliers in the data has been proved to pose a serious problem in dimension reduction. The first component consisting of the greatest variation is often pushed toward the anomalous observations. The robust minimizing vector variance (MW) combined with two dimensional projection approach is used for solving the problem. The computation experiment shows the robust method has the good performances for matrix data classification.
-
-
Tahun: 2014
Jenis : Model
Deskripsi : This paper discusses the classic and robust discriminant
-
-
Tahun: 2013
Jenis : Model
Deskripsi : This paper discusses an efficient and effective robust algorithm applied to the classification of vegetation areas in the Jakarta Province. The input data is remote sensing data from the Landsat 7 Satellite. The classification process is guided over two steps, training and classification. The purpose of the training step is to determine the reference spectra of the vegetation area, and the purpose of the classification step is to classify Jakarta areas as either vegetation or nonvegetation. An efficient robust approach is used to classify the Jakarta area using the anomolous digital number resulting from a failed instrument. This paper discusses the application of an efficient and effective robust method to classify the remote sensing data with anomolous or inconsistent observations. The aim is to propose a new efficient subset robust approach - the subset minimum vector variance - to classify the vegetation area of Jakarta. The minimum vector variance (MVV) is a robust method having a minimum of the square of the length of a parallelotope diagonal.
-
-
Tahun: 2013
Jenis : Model
Deskripsi : Variable selection methods for process monitoring have focused mainly on the explained variance performance criteria. However, explained variance efficiency is a minimal notion of optimality and does not necessarily result in an economically desirable selected subset, as it makes no statement about the measurement cost or other engineering criteria. For many applications, it may be useful for external information to influence the selection process. For example, some variables may be easier and cheaper to carry out then others or they might be very important according to some engineering
-
-
Tahun: 2013
Jenis : Model
Deskripsi : Variable selection methods for process monitoring have focused mainly on the explained variance performance criteria. However, explained variance efficiency is a minimal notion of optimality and does not necessarily result in an economically desirable selected subset, as it makes no statement about the measurement cost or other engineering criteria. For many applications, it may be useful for external information to influence the selection process. For example, some variables may be easier and cheaper to carry out then others or they might be very important according to some engineering criteria. Neglecting this information in statistical process control, would be counterproductive. In this article, we propose a statistical methodology to select a reduced number of relevant variables for multivariate statistical process control that makes use of engineering and variability evaluation criteria. A double reduction of dimensionality is applied in conjunction with economic and variability selection criteria. The subset of relevant variables is selected in a manner that retains, to some extent, the structure and information carried by the full set of original variables. A real application from automotive industry will be used to illustrate the method.
-
-
Tahun: 2013
Jenis : Model
Deskripsi : Mapping of rice field is done with a conventional two step process: training process and classification.The results of mapping process are highly influenced by accuracy of spectral reference obtained in training process. Robust reduction dimension improvements are proposed for computing estimators. The first improvement consists in a modification of robust subset with preliminary data inspection. The inspection is useful for screening and removing the potential outliers. As a second improvement the replacement of process inversion of covariance matrix with a new depth function is proposed. The case study of research is rice fields located in Karawang, West Java. Data from MODIS (Moderate Resolution Imaging Spectroradiometer) satellite are used for rice field mapping.
-
-
Tahun: 2013
Jenis : Model
Deskripsi : Statistical process control methods for monitoring short-run processes with multivariate measurements are considered and new multivariate short-run control charts to monitor process mean and variability are proposed. To monitor the process mean the influence function of mean is proposed and to investigate process variability control charts based on the influence function of eigenvalues are suggested. The proposed techniques are general, and the influence functions may be used to build up short-run multivariate control charts relative to either nominal values or estimates. The method is further illustrated with real datasets, from a flexible job shop manufacturing system producing spare parts for classical cars.
-
-
Tahun: 2013
Jenis : Model
Deskripsi : All of the Landsat 7 data collected after 2003 contains missing pixels in the form of unsightly stripes across the images. To recover missing data of a Landsat image, different methods may be used. However, the gap filling process creates inconsistencies on pixel intensity values. The incongruous pixel numbers are anomolous observations and their classification in the reference specter is challenging. In an effort to contribute to this need, we propose a reliable robust approach to classify inconsistent pixels after the gap filling process. To estimate multivariate location-scale parameters a new robust DMVV (depth minimum vector variance estimator) is presented. The DMVV algorithm does not require any matrix inversion for its calculation, consequently its computational time is highly reduced. The results show that it has a high breakdown point and is very efficient for large data set. Landsat remote sensing data of Jakarta Province across years 2002 and 2010 are used as case study.
-
-
Tahun: 2011
Jenis : Model
Deskripsi : This paper discusses the robust classification for large data, in case classification of vegetation area at Jakarta with remote sensing. Remote Sensing is the process involving an interaction between incident radiation and the targets of interest. The classification process is guided in two steps; training and classification steps. The training step is done to know the reference spectral of vegetation area, and the classification step is carried out to clasify the Jakarta area into the vegetation and the non vegetation area. The hole process of classification is not simple. The main problem is noise. The claud covering area is considered as noise. The classification of large data with noise needs the efficient and effective approach. The aim of the paper is to propose a new robust approach, the Modified MVV, to classify the vegetation area of Jakarta. The Modified MVV is the modified data subset having minimum of a square of length of a parallelotope diagonal. The good properties of Modified MVV are the consistent estimator and the more efficient computational time than is of MVV.
-
-
Tahun: 2011
Jenis : Model
Deskripsi : In Computer Security area, Intrusion Detection System (IDS) plays important role in detecting any kinds of network attacks. Denial of Service (DoS) and Probing attacks are common detectable intrusions that are frightened by most network users since the final result of these attacks is collapsing the network. Our previous research has proposed a robust statistical method, the BACON-MVV method, that provides 100% accuracy in detecting patterns of DoS and Probing attacks, inspite of the training sets used contains suspicious packet traffic called outliers. One problem not yet being addressed by previous research was the processing time taken as the packet traffics to be analysed for detecting any intrusion grows bigger. In this paper, we propose a Parallel BACON-MVV method based on Data Decomposition to be implemented in IDS. Experiment using our own generated simulation datasets shows that this proposed method runs significantly faster than its serial version.
-
-
Tahun: 2010
Jenis : Model
Deskripsi : This paper proposes a new notion distance on the CBIR process which is derived from the measure of multivariate dispersion called vector variance (VV).The minimum vector variance (MVV) estimator is robust estimator having the highbreakdown point. The CBIR is a retrieval technique using the visual information by retrieving collections of digital images.
-
-
Tahun: 2010
Jenis : Model
Deskripsi : Principal Component Analysis (PCA) is a technique to transform the original set of variables into a smaller set of linear combinations that account for most of the original set variance. The data reduction based on the classical PCA is fruitless if outlier is present in the data. The decomposed classical covariance matrix is very sensitive to outlying observations. ROBPCA is an effective PCA method combining two advantages of both projection pursuit and robust covariance estimation. The estimation is computed with the idea of minimum covariance determinant (MCD) of covariance matrix. The limitation of MCD is when covariance determinant almost equal zero. This paper proposes PCA using the minimum vector variance (MVV) as new measure of robust PCA to enhance the result. MVV is defined as a minimization of sum of square length of the diagonal of a parallelotope to determine the location estimator and covariance matrix. The usefulness of MVV is not limited to small or low dimension data set and to non-singular or singular covariance matrix. The MVV algorithm, compared with FMCD algorithm, has a lower computational complexity; the complexity of VV is of order O(p 2).
-
-
Tahun: 2009
Jenis : Model
Deskripsi : Content based image retrieval (CBIR) is a retrieval technique which uses the visual information by retrieving collections of digital images. The process of retrieval is carried out by measuring the similarity between query image and the image in the database through similarity measure.
-
-
Tahun: 2009
Jenis : Model
Deskripsi : Principal Component Analysis (PCA) is a technique to transform the original set of variables into a smaller set of linear combinations that account for most of the original set variance. The data reduction based on the classical PCA is fruitless if outlier is present in the data. The decomposed classical covariance matrix is very sensitive to outlying observations. ROBPCA is an effective PCA method combining two advantages of both projection pursuit and robust covariance estimation. The estimation is computed with the idea of minimum covariance determinant (MCD) of covariance matrix. The limitation of MCD is when covariance determinant almost equal zero. This paper discusses PCA using the minimum vector variance (MVV) to enhance the result. The usefulness of MVV is not limited to small or low dimension data set and to non-singular or singular covariance matrix. The MVV algorithm, compared with FMCD algorithm, has a lower computational complexity; the complexity of VV is of order 0(p 2).
-
-
Tahun: 2008
Jenis : Model
Deskripsi : Understanding multivariate variability is a difficult task because there is no single measure that can be properly used. This article presents a new measure that features good properties. If this measure is simultaneously used with generalized variance, it will give a better understanding of multivariate variability. It can also efficiently be used for large data sets with high dimensions. Furthermore, when it is used for constructing a Shewhart-type chart to monitor multivariate variability, the resulting chart has a much better out-of-control ARL than the generalized variance chart. An example illustrates its advantage.
-
-
Tahun: 2007
Jenis : Model
Deskripsi : A criterion for robust estimation of location and the covariance matrix is considered, and its application in outlier labeling is discussed. This method, unlike the methods based on the minimum volume ellipsoid (MVE) and minimum covariance determinant (MCD), is applicable to large and high-dimensional data sets. The method proposed here is also robust and has the same breakdown point as the MVE- and MCD-based methods. Furthermore, the computational complexity of the proposed method is significantly smaller than that of other methods.