Garuda - Garba Rujukan Digital

SELEKSI FITUR MENGGUNAKAN EKSTRAKSI FITUR BENTUK, WARNA, DAN TEKSTUR DALAM SISTEM TEMU KEMBALI CITRA DAUN Sari, Yuita Arum; Dewi, Ratih Kartika; Fatichah, Chastine
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 12, No 1, Januari 2014
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Fitur yang digunakan untuk mengenali jenis daun meliputi bentuk, warna, dan tekstur. Tidak semua jenis fitur perlu digunakan untuk melakukan komputasi hasil ektra ksi, namun perlu diseleksi beberapa fitur yang paling berpengarauh dalam sistem temu kembali citra daun. Teknik seleksi fitur Correlation based Featured Selection (CFS) digunakan untuk melakukan pemilihan fitur berdasarkan korelasi antar fitur, sehingga dapat meningkatkan performa dari sistem temu kembali citra daun. Jenis seleksi fitur yang digunakan diantaranya menggunaka CFS, CFS dengan Genetic Search (GS), dan chi square. Analisis keterkaitan korelasi antar fitur melalui seleksi fitur juga dikombinasikan dengan penggunaan kedekatan dalam menghitung similaritas pada sistem temu kembali. Penggunaan kedekatan dengan Lp norm, ma nhattan, euclidean, cosine, dan mahalanobis. Hasil penelitian ini menunjukkan nilai temu kembali paling tinggi ketika menggunakan seleksi fitur CFS dengan pengukuran kedekatan mahalanobis.

Deteksi Kanker Kulit Melanoma dengan Linear Discriminant Analysis-Fuzzy k-Nearest Neigbhour Lp-Norm Mentari, Mustika; Sari, Yuita Arum; Dewi, Ratih Kartika
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 2, No 1 (2016): Januari-Juni
Publisher : Prodi Sistem Informasi - Universitas Pesantren Tinggi Darul Ulum

Seiring perkembangan teknologi dilakukan otomatisasi deteksi kanker kulit melalui citra dermoscopy. Pengambilan informasi fitur citra dermoscopy terganggu dengan outlier dan overfitting, karena faktor jenis kulit, penyebaran kanker yang tidak merata atau kesalahan sampling. Penelitian ini mengusulkan deteksi kanker kulit melanoma dengan mengintegrasikan metode fuzzy K-Nearest Neighbour (FuzzykNN), Lp-norm dan Linear Discriminant Analysis (LDA) untuk mengurangi outlier dan overfitting. Masukan berupa citra warna RGB yang dinormalisasi menjadi RGBr. Reduksi dimensi dengan LDA menghasilkan fitur dengan nilai eigen paling menonjol. LDA pada penelitian ini menghasilkan dua fitur paling menonjol dari 141 jenis fitur, yaitu wilayah tumor dan minimum wilayah tumor channel R. Kemudian dilakukan klasifikasi FuzzykNN dan metode pengukur jarak Lp-norm. Penggunaan metode LDA dan Lp-norm dalam proses klasifikasi ini mengatasi terjadinya overfitting. Akurasi yang dihasilkan metode LDA-fuzzykNN Lp Norm, yaitu 72% saat masing-masing nilai p dan k = 25. Metode gabungan ini terbukti cukup baik dari pada metode yang dijalankan terpisah. Kata kunci: melanoma, fuzzy, KNN, Lp-norm, LDA.Â As the advancement of technology skin cancer detection need to be automated with the use of dermoscopy image. Outlier and overfitting are the problem in feature extraction of dermoscopy image, this can be caused by skin type, uneven cancer distribution or sampling error. This study proposed melanoma skin cancer detection by fuzzy K-Nearest Neighbour (FuzzykNN) with Lp-norm integrated with Linear Discriminant Analysis (LDA) to reduce the problem of outlier and overfitting. Input used in this study are images with RGB channel, then it adapted to RGBr. Dimensional reduction with LDA result in features with highest eigen value. LDA in this research select 2 discriminant, they are tumor area and minimum tumor area in R channel. This features then classified by fuzzykNN with Lp-Norm. Integration of LDA and Lp-norm in classification can reduce the problem of overfitting. This study results in 72% accuracy when the value of p and k are 25. Integration of LDA and fuzzykNN with Lp-norm has better result than unintegrated method. Keywords: melanoma, fuzzy, KNN, Lp-norm, LDA.

Regresi linier berbasis clustering untuk deteksi dan estimasi halangan pada smart wheelchair Adikara, Putra Pandu; Wihandika, Randy Cahya; Utaminingrum, Fitri; Sari, Yuita Arum; Fauzi, M Ali; Syauqy, Dahnial; Maulana, Rizal
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 3, No 1 (2017): Januari-Juni (3/7)
Publisher : Prodi Sistem Informasi - Universitas Pesantren Tinggi Darul Ulum

Â Penelitian ini bertujuan untuk mengusulkan sebuah pendekatan dalam mendeteksi halangan dan memperkirakan jarak halangan untuk diterapkan pada kursi roda pintar (smart wheelchair) yang dilengkapi kamera dan line laser. Kamera menangkap sinar line laser yang jatuh di depan kursi roda untuk mengenali adanya halangan pada lintasan berdasarkan bentuk citra line laser tersebut. Estimasi jarak halangan dihitung dari hasil Regresi Linier. Metode Regresi Linier yang digunakan dalam penelitian ini adalah model bertingkat dengan k-Means clustering. Metode Regresi Linier model bertingkat digunakan untuk merepresentasikan korelasi antara jarak line laser pada citra dan jarak halangan secara aktual. Hasil metode Regresi Linier model bertingkat dengan k-Means clustering yang diujicobakan memberikan hasil yang lebih baik dengan RMSE sebesar 3.541 cm dibanding dengan Regresi Liner sederhana dengan RMSE sebesar 5.367 cm.Â Â Â This research aim to propose a new approach to detect obstacles and to estimate the distance of the obstacle which is in this case applied to smart wheelchair equipped with camera and line laser. The camera capture the image of line laser reflected in front of the wheelchair to detect any existing obstacle on the wheelchairâs pathway based on the line shape of reflected line laser. Obstacleâs distance is estimated using Linier Regression. Linier Regression method used in this research is stepwise model using k-Means clustering. Linear Regression method with stepwise model will be used to represent the correlation between the distance of the line laser in the image and the actual distance of the obstacle in real world. The result of Linear Regression with stepwise model using k-Means clustering gave better result with RMSE of 3.541 cm than simple Linear Regression with RMSE of 5.367 cm.

Pengelompokan Dokumen Berita Berbahasa Indonesia Menggunakan Reduksi FiturInformation Gain dan Singular Value Decomposition dalam Fuzzy C-MeansClustering Sari, Yuita Arum; Putri, Tesa Eranti; Hapsani, Anggi Gustiningsih
Jurnal Informatika dan Multimedia Vol 10 No 1 (2018): Jurnal Volume 10, No.1 (2018)
Publisher : Teknik Informatika Politeknik Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar

Koran dan berita online merupakan media informasi digital saat ini yang proses pembaruan informasinya sangat mudah dan fleksibel. Kemudahan ini memungkinkan penulis berita untuk mengunggah informasi baru di waktu kapanpun dan dimanapun. Hal ini menyebabkan data dokumen berita sangat banyak dan tidak teratur sehingga perlu dilakukan pengelompokan berita sesuai dengan kontennya. Pengelompokanberita sesuai content dapat membantu pembaca untuk membaca berita dengan topiktertentu sesuai dengan minatnya. Proses pengelompokan informasi berita diimplementasikan denganbeberapa tahap, yaitu preprocessing dan pengelompokan dokumen. Preprocessing dilakukan dengan mengimplementasikan metode kombinasi reduksi fitur Document Frequency (DF) dan Information Gain (IG) Thresholding dalamSingular Value Decomposition (SVD). Algoritme SVD dipilih karena memiliki kemampuan untuk melakukan dekomposisi pada matriks dokumen-term, sehingga diperoleh matriks yang masih menyimpan informasi penting dengan ukuran dimensi yang lebih kecil.Pada tahap pengelompokan dokumen berita dilakukandengan algoritme Fuzzy C-Means. Hasil uji coba akurasipengelompokan dokumen berita menunjukkan bahwa pengelompokan yang dilakukan memberikan hasil pengkategorian yang cukup akurat dengan tingkat akurasi rata-rata 74,5 % (IG threshold 0.5, k = 5). Hal tersebut menunjukkan bahwa pengelompokan dokumen menggunakan IG dan SVD dengan FUZZY C-MEANS adalah sesuai dengan kebutuhan.

Color space and color channel selection on image segmentation of food images Maulana, Luthfi; Bihanda, Yusuf Gladiensyah; Sari, Yuita Arum
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 6, No 2 (2020): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v6i2.2061

Image segmentation is a predefined process of image processing to determine a specific object. One of the problems in food recognition and food estimation is the lack of quality of the result of image segmentation. This paper presents a comparative study of different color space and color channel selection in image segmentation of food images. Based on previous research regarding image segmentation used in food leftover estimation, this paper proposed a different approach to selecting color space and color channel based on the score of Intersection Over Union (IOU) and Dice from the whole dataset. The color transformation is required, and five color spaces were used: CIELAB, HSV, YUV, YCbCr, and HLS. The result shows that A in LAB and H in HLS are better to produce segmentation than other color channels, with the Dice score of both is 5 (the highest score). It concludes that this color channel selection is applicable to be embedded in the Automatic Food Leftover Estimation (AFLE) algorithm.

Regresi linier berbasis clustering untuk deteksi dan estimasi halangan pada smart wheelchair Adikara, Putra Pandu; Wihandika, Randy Cahya; Utaminingrum, Fitri; Sari, Yuita Arum; Fauzi, M Ali; Syauqy, Dahnial; Maulana, Rizal
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 3, No 1 (2017): January
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v3i1.587

Â Penelitian ini bertujuan untuk mengusulkan sebuah pendekatan dalam mendeteksi halangan dan memperkirakan jarak halangan untuk diterapkan pada kursi roda pintar (smart wheelchair) yang dilengkapi kamera dan line laser. Kamera menangkap sinar line laser yang jatuh di depan kursi roda untuk mengenali adanya halangan pada lintasan berdasarkan bentuk citra line laser tersebut. Estimasi jarak halangan dihitung dari hasil Regresi Linier. Metode Regresi Linier yang digunakan dalam penelitian ini adalah model bertingkat dengan k-Means clustering. Metode Regresi Linier model bertingkat digunakan untuk merepresentasikan korelasi antara jarak line laser pada citra dan jarak halangan secara aktual. Hasil metode Regresi Linier model bertingkat dengan k-Means clustering yang diujicobakan memberikan hasil yang lebih baik dengan RMSE sebesar 3.541 cm dibanding dengan Regresi Liner sederhana dengan RMSE sebesar 5.367 cm.Â Â Â This research aim to propose a new approach to detect obstacles and to estimate the distance of the obstacle which is in this case applied to smart wheelchair equipped with camera and line laser. The camera capture the image of line laser reflected in front of the wheelchair to detect any existing obstacle on the wheelchairâ€™s pathway based on the line shape of reflected line laser. Obstacleâ€™s distance is estimated using Linier Regression. Linier Regression method used in this research is stepwise model using k-Means clustering. Linear Regression method with stepwise model will be used to represent the correlation between the distance of the line laser in the image and the actual distance of the obstacle in real world. The result of Linear Regression with stepwise model using k-Means clustering gave better result with RMSE of 3.541 cm than simple Linear Regression with RMSE of 5.367 cm.

Deteksi Kanker Kulit Melanoma dengan Linear Discriminant Analysis-Fuzzy k-Nearest Neigbhour Lp-Norm Mentari, Mustika; Sari, Yuita Arum; Dewi, Ratih Kartika
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 2, No 1 (2016): January
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v2i1.443

Seiring perkembangan teknologi dilakukan otomatisasi deteksi kanker kulit melalui citra dermoscopy. Pengambilan informasi fitur citra dermoscopy terganggu dengan outlier dan overfitting, karena faktor jenis kulit, penyebaran kanker yang tidak merata atau kesalahan sampling. Penelitian ini mengusulkan deteksi kanker kulit melanoma dengan mengintegrasikan metode fuzzy K-Nearest Neighbour (FuzzykNN), Lp-norm dan Linear Discriminant Analysis (LDA) untuk mengurangi outlier dan overfitting. Masukan berupa citra warna RGB yang dinormalisasi menjadi RGBr. Reduksi dimensi dengan LDA menghasilkan fitur dengan nilai eigen paling menonjol. LDA pada penelitian ini menghasilkan dua fitur paling menonjol dari 141 jenis fitur, yaitu wilayah tumor dan minimum wilayah tumor channel R. Kemudian dilakukan klasifikasi FuzzykNN dan metode pengukur jarak Lp-norm. Penggunaan metode LDA dan Lp-norm dalam proses klasifikasi ini mengatasi terjadinya overfitting. Akurasi yang dihasilkan metode LDA-fuzzykNN Lp Norm, yaitu 72% saat masing-masing nilai p dan k = 25. Metode gabungan ini terbukti cukup baik dari pada metode yang dijalankan terpisah. Kata kunci: melanoma, fuzzy, KNN, Lp-norm, LDA.Â As the advancement of technology skin cancer detection need to be automated with the use of dermoscopy image. Outlier and overfitting are the problem in feature extraction of dermoscopy image, this can be caused by skin type, uneven cancer distribution or sampling error. This study proposed melanoma skin cancer detection by fuzzy K-Nearest Neighbour (FuzzykNN) with Lp-norm integrated with Linear Discriminant Analysis (LDA) to reduce the problem of outlier and overfitting. Input used in this study are images with RGB channel, then it adapted to RGBr. Dimensional reduction with LDA result in features with highest eigen value. LDA in this research select 2 discriminant, they are tumor area and minimum tumor area in R channel. This features then classified by fuzzykNN with Lp-Norm. Integration of LDA and Lp-norm in classification can reduce the problem of overfitting. This study results in 72% accuracy when the value of p and k are 25. Integration of LDA and fuzzykNN with Lp-norm has better result than unintegrated method. Keywords: melanoma, fuzzy, KNN, Lp-norm, LDA.

Movie recommender systems using hybrid model based on graphs with co-rated, genre, and closed caption features Adikara, Putra Pandu; Sari, Yuita Arum; Adinugroho, Sigit; Setiawan, Budi Darma
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 7, No 1 (2021): January
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v7i1.2081

A movie recommendation is a long-standing challenge. Figuring out the viewerâ€™s interest in movies is still a problem since a huge number of movies are released in no time. In the meantime, people cannot enjoy all available new releases or unseen movies due to their limited time. They also still need to choose which movies to watch when they have spare time. This situation is not good for the movie business too. In order to satisfy people in choosing what movies to watch and to boost movie sales, a system that can recommend suitable movies is required, either unseen in the past or new releases. This paper focuses on the hybrid approach, a combination of content-based and collaborative filtering, using a graph-based model. This hybrid approach is proposed to overcome the drawbacks of combination in the content-based and collaborative filtering. The graph database, Neo4j is used to store the collaborative features, such as movies with its genres, and ratings. Since the movieâ€™s closed caption is rarely considered to be used in a recommendation, the proposed method evaluates the impact of using this syntactic feature. From the early test, the combination of collaborative filtering and content-based using closed caption gives a slightly better result than without closed caption, especially in finding similar movies such as sequel or prequel.

Image Processing for Rapidly Eye Detection based on Robust Haar Sliding Window Fitri Utaminingrum; Renaldi Primaswara Praetya; Yuita Arum Sari
International Journal of Electrical and Computer Engineering (IJECE) Vol 7, No 2: April 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v7i2.pp823-830

Object Detection using Haar Cascade Clasifier widely applied in several devices and applications as a medium of interaction between human and computer such as a tool control that utilizes the detection of eye movements. Obviously speed and precision in the detection process such as eyes, has an effect if implemented on a device. If the eye could not detect accurately, controlling device systems could reach bad detection as well. The proposed method can be used as an approach to detect the eye region of eye based on haar classifier method by means of modifying the direction of sliding window. In which, it was initially placed in the middle position of image on facial area by assuming the location of eyes area in the central region of the image. While the window region of conventional haar cascade scan the whole of image start from the left top corner. From the experiment by using our proposed method, it can speed up the the computation time and improve accuracy significantly reach to 92,4%.

Batik Classification Using Convolutional Neural Network with Data Improvements Dewa Gede Trika Meranggi; Novanto Yudistira; Yuita Arum Sari
JOIV : International Journal on Informatics Visualization Vol 6, No 1 (2022)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.1.716

Batik is one of the Indonesian cultures that UNESCO has recognized.Â Batik has a variety of unique and distinctive patterns that reflect the area of origin of the batik motif. Batik motifs usually have aÂ 'core motif' printedÂ repeatedly on the fabric. The entry of digitization makes batik motif designs more diverse and unique.Â However, withÂ so many batik motifs spread on the internet, it is difficult for ordinary people to recognize the types of batik motifs. This makes an automatic classification of batik motifs must continue to be developed. Automation of batik motif classification can be assisted with artificial intelligence. Machine learning and deep learning have producedÂ muchÂ good performance in image recognition. In this study, we use deep learning based onÂ a ConvolutionalÂ Neural Network (CNN) to automate the classification of batik motifs. There are two datasets used in this study. The old dataset comes from a public repositoryÂ with 598Â data withÂ fiveÂ types of motifs. Meanwhile, the newÂ datasetÂ updatesÂ the old dataset by replacing the anomalous data in the old datasetÂ with 621 dataÂ with five types of motifs. TheÂ lereng motif is changed to pisanbali due to the difficulty of obtainingÂ the lerengÂ motif. Each dataset was divided intoÂ threeÂ ways: original, balance patch, and patch. We used ResNet-18 architecture, whichÂ used a pre-trained model to shorten the training time. The best test results were obtained in the new dataset with the patch way of 88.88 % Â±0.88, andÂ in the old dataset, the best accuracy was found in the patch way on the test data of 66.14 % Â±3.7. The dataÂ augmentationÂ in this study did not significantly affect the accuracy because theÂ most significantÂ increase in accuracy is only up to 1.22%.

Title

Found 31 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 31 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 31 Documents
Search