Claim Missing Document
Check
Articles

Found 19 Documents
Search

Color Space to Detect Skin Image: The Procedure and Implication Endah, Sukmawati Nur; Kusumaningrum, Retno; Wibawa, Helmie Arif
Scientific Journal of Informatics Vol 4, No 2 (2017): November 2017
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v4i2.12013

Abstract

Skin detection is one of the processes to detect the presence of pornographic elements in an image. The most suitable feature for skin detection is the color feature. To be able to represent the skin color properly, it is needed to be processed in the appropriate color space. This study examines some color spaces to determine the most appropriate color space in detecting skin color. The color spaces in this case are RGB, HSV, HSL, YIQ, YUV, YCbCr, YPbPr, YDbDr, CIE XYZ, CIE L*a*b*, CIE L*u* v*, and CIE L*ch. Based on the test results using 400 image data consisting of 200 skin images and 200 non-skin images, it is obtained that the most appropriate color space to detect the color is CIE L*u*v*.
SISTEM INFORMASI VEGETASI MANGROVE (SIVM) BERBASIS WEB DI TAMAN NASIONAL KARIMUNJAWA, JEPARA, JAWA TENGAH Endah, sukmawati Nur; Kusumaningrum, Retno
Jurnal Masyarakat Informatika Vol 1, No 1 (2010): Jurnal Masyarakat Informatika
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (305.313 KB)

Abstract

Mangrove forest at Karimunjawa National Park that has been used for research, education source, and tourism, needs an information system accessible for global community. The information covers the species, morphology, and taxonomy of mangrove vegetations in Karimunjawa National Park. Human need for up to date and accurate information supported with modern technology motivates the researcher to construct mangrove vegetations information system web based. It is hoped that the information can be accessed by interest group. Methods to be used refers to the stage of system development method. Its name is FAST system. SIVM can be used for all social stratum because this output is easy to understand interesting and user friendly.   Keywords: information system web based, mangrove vegetations
PERANCANGAN MODEL PENDUKUNG KEPUTUSAN UNTUK PENENTUAN LOKASI INDUSTRI BERDASARKAN PROSES HIERARKI ANALITIK Kusumaningrum, Retno
MATEMATIKA Vol 9, No 1 (2006): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (52.811 KB)

Abstract

The Analytic Hierarchy Process (AHP), a decision-making method based upon division of problem spaces into hierarchies. This paper looks at AHP as a tool used in determination of industrial location. Solution of AHP method finished with the iteration process of through at scheme of  Pascal computer program to assist the calculation process. From result of program device which have been made to be obtained the highest total priority value (TPV) was potential distribution and promotion track
CIELab Color Moments: Alternative Descriptors for LANDSAT Images Classification System Kusumaningrum, Retno; Manurung, Hisar Maruli; Arymurthy, Aniati Murni
INKOM Journal Vol 8, No 2 (2014)
Publisher : Pusat Penelitian Informatika - LIPI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (251.469 KB) | DOI: 10.14203/j.inkom.409

Abstract

This study compares the image classification system based on normalized difference vegetation index (NDVI) and Latent Dirichlet Allocation (LDA) using CIELab color moments as image descriptors.  It was implemented for LANDSAT images classification by evaluating the accuracy values of classification systems. The aim of this study is to evaluate whether the CIELab color moments can be used as an alternatif descriptor replacing NDVI when it is implemented using LDA-based classification model.  The result shows that the LDA-based image classification system using CIELab color moments provides better performance accuracy than the NDVI-based image classification system, i.e 87.43% and 86.25% for LDA-based and NDVI-based respectively.  Therefore, we conclude that the CIELab color moments which are implemented under the LDA-based image classification system can be assigned as alternative image descriptors for the remote sensing image classification systems with the limited data availability, especially when the data only available in true color composite images.
Studi Perbandingan Algoritma Pencarian String dalam Metode Approximate String Matching untuk Identifikasi Kesalahan Pengetikan Teks Rochmawati, Yeny; Kusumaningrum, Retno
Jurnal Buana Informatika Vol 7, No 2 (2016): Jurnal Buana Informatika Volume 7 Nomor 2 April 2016
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (430.747 KB) | DOI: 10.24002/jbi.v7i2.491

Abstract

Abstract. Error typing resulting in the change of standard words into non-standard words are often caused by misspelling. This can be addressed by developing a system to identify errors in typing. Approximate string matching is one method that is widely implemented to identify error typing by using several string search algorithms, i.e. Levenshtein Distance, Hamming Distance, Damerau Levenshtein Distance and Jaro Winkler Distance. However, there is no study that compares the performance of the four algorithms.  Therefore, this research aims to compare the performance between the four algorithms in order to identify which algorithm is the most accurate and precise in the search string based on various errors typing. Evaluation is performed by using users’ relevance judgments which produce the mean average precision (MAP) to determine the best algorithm. The result shows that Jaro Winkler Distance algorithm is the best in word-checking with 0.87 of MAP value when identifying the typing error of 50 incorrect words.Keywords: Errors typing, Levenshtein, Hamming, Damerau Levenshtein, Jaro WinklerAbstrak. Kesalahan pengetikan mengakibatkan kata baku berubah menjadi kata tidak baku karena ejaan yang digunakan tidak sesuai. Hal tersebut dapat ditangani dengan mengembangkan sistem untuk mengidentifikasi kesalahan pengetikan. Metode approximate string matching merupakan salah satu metode yang banyak diterapkan untuk mengidentifikasi kesalahan pengetikan dengan berbagai jenis algoritma pencarian string yaitu Levenshtein Distance, Hamming Distance, Damerau Levenshtein Distance dan Jaro Winkler Distance. Akan tetapi studi perbandingan kinerja dari keempat algoritma tersebut untuk Bahasa Indonesia belum pernah dilakukan. Oleh karena itu penelitian ini bertujuan untuk melakukan studi perbandingan kinerja dari keempat algoritma tersebut sehingga dapat diketahui algoritma mana yang lebih akurat dan tepat dalam pencarian string berdasarkan kesalahan penulisan yang bervariasi. Evaluasi yang dilakukan menggunakan user relevance judgement yang menghasilkan nilai mean average precision (MAP) untuk menentukan algoritma yang terbaik. Hasil penelitian terhadap 50 kata salah menunjukkan bahwa algoritma Jaro Winkler Distance terbaik dalam melakukan pengecekan kata dengan nilai MAP sebesar 0,87.Kata Kunci: Kesalahan pengetikan, Levenshtein, Hamming, Damerau Levenshtein, Jaro Winkler
HOAX DETECTION IN INDONESIA LANGUAGE USING LONG SHORT-TERM MEMORY MODEL Apriliyanto, Andi; Kusumaningrum, Retno
SINERGI Vol 24, No 3 (2020)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2020.3.003

Abstract

Nowadays, the internet and social media grow fast. This condition has positive and negative effects on society. They become media to communicate and share information without limitation. However, many people use that easiness to broadcast news or information which do not accurate with the facts and gather people's opinions to get benefits or we called a hoax. Therefore, we need to develop a system that can detect hoax. This research uses the neural network method with Long Short-Term Memory (LSTM) model. The process of the LSTM model to identify hoax has several steps, including dataset collection, pre-processing data, word embedding using pre-trained Word2Vec, built the LSTM model. Detection model performance measurement using precision, recall, and f1-measure matrix. This research results the highest average score of precision is 0.819, recall is 0.809, and f1-measure is 0.807.  These results obtained from the combination of the following parameters, i.e., Skip-gram Word2Vec Model Architecture, Hierarchical Softmax, 100 as vector dimension, max pooling, 0.5 as dropout value, and 0.001 of learning rate.
Sistem Informasi Perencanaan dan Pengukuran Kinerja Unit dengan Metode Analytical Hierarchy Process Widiyanto, Widiyanto; Suryono, Suryono; Kusumaningrum, Retno
Rekayasa : Jurnal Penerapan Teknologi dan Pembelajaran Vol 17, No 2 (2019): December
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/rekayasa.v17i2.18777

Abstract

Penilaian kegiatan untuk pengukuran kinerja menggunakan Analytical Hierarchy Process. Proses kegiatan unit kerja dimulai dari pengajuan proposal, pelaksanaan, dan laporan kegiatan. Input data proposal dilakukan oleh operator unit yang menghasilkan perencanaan kegiatan dan keuangan. Input data pelaksanaan kegiatan ini menghasilkan data arsip kegiatan. Input laporan kegiatan dan keuangan menghasilkan data capaian, serapan anggaran, serta lama proses laporan kegiatan. Nilai kegiatan didapatkan dari total nilai capaian semua kegiatan yang dikalikan dengan bobot masing-masing indikator. Bobot indikator didapatkan dengan metode Analytical Hierarchy Process. Nilai kinerja dari unit didapatkan dari rata-rata nilai kegiatannya. Dengan adanya sistem informasi manajemen dapat membantu dan mempermudah penilaian kinerja unit menggunakan metode Analytical Hierarchy Process sehingga perencanaan dapat direalisasikan dengan baik dan terukur pada unit pengembang jurnal secara terintegrasi. Evaluasi kinerja dengan menilai kualitas suatu unit sistem menghasilkan nilai 60% dengan kriteria baik, dan informasi yang dihasilkan sebesar 80% dengan kriteria baik, serta kegunaan sistem dalam pemenuhan kebutuhan unit sebesar 80% dengan kriteria baik.
Optimisation towards Latent Dirichlet Allocation: Its Topic Number and Collapsed Gibbs Sampling Inference Process Bambang Subeno; Retno Kusumaningrum; Farikhin Farikhin
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 5: October 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.186 KB) | DOI: 10.11591/ijece.v8i5.pp3204-3213

Abstract

Latent Dirichlet Allocation (LDA) is a probability model for grouping hidden topics in documents by the number of predefined topics. If conducted incorrectly, determining the amount of K topics will result in limited word correlation with topics. Too large or too small number of K topics causes inaccuracies in grouping topics in the formation of training models. This study aims to determine the optimal number of corpus topics in the LDA method using the maximum likelihood and Minimum Description Length (MDL) approach. The experimental process uses Indonesian news articles with the number of documents at 25, 50, 90, and 600; in each document, the numbers of words are 3898, 7760, 13005, and 4365. The results show that the maximum likelihood and MDL approach result in the same number of optimal topics. The optimal number of topics is influenced by alpha and beta parameters. In addition, the number of documents does not affect the computation times but the number of words does. Computational times for each of those datasets are 2.9721, 6.49637, 13.2967, and 3.7152 seconds. The optimisation model has resulted in many LDA topics as a classification model. This experiment shows that the highest average accuracy is 61% with alpha 0.1 and beta 0.001.
Pengembangan Sistem Manajemen Naskah Soal dengan Keamanan Pre-Hash Coding Prajanto Wahyu Adi; Retno Kusumaningrum
Techno.Com Vol 20, No 4 (2021): November 2021
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v20i4.5271

Abstract

Sistem pengelolahan dokumen secara elektronik sudah menjadi salah satu kebutuhan penting dalam institusi pendidikan khususnya dalam pengelolaan naskah soal. Masalah utama dalam pengelolaan naskah elektronik adalah adanya berbagai format yang digunakan serta kekhawatiran terhadap tingkat keamanan akun. Sistem keamanan akun dengan menggunakan password yang sederhana akan mudah diretas sedangkan penggunaan sistem yang kompleks akan mempersulit pengguna. Departemen Informatika Universitas Diponegoro mengembangkan sistem manajemen naskah soal yang mampu menghasilkan format naskah soal sesuai dengan standar tunggal serta memiliki sistem keamanan yang sederhana namun kuat melalui sistem pre-hash coding dengan nilai unik pengguna melalui dua skema. Pengujian pertama yang dilakukan berhasil membuktikan kemampuan sistem dalam menghasilkan naskah soal sesuai dengan standar tunggal. Percobaan kedua dilakukan untuk menguji tingkat keamanan terhadap nilai hash dari sampel password melalui uji brute-force menggunakan sistem Hashcat. Sistem yang diusulkan mampu menggagalkan peretasan sebesar 40% pada karakter alfanumerik pada skema pertama dengan operator bitwise xor sedangkan pada skema kedua dengan operator penjumlahan mampu menggagalkan seluruh peretasan yang dilakukan. Sistem yang diusulkan mampu memenuhi kebutuhan pengguna terhadap password yang sederhana namun kuat.
WCLOUDVIZ: Word Cloud Visualization of Indonesian News Articles Classification Based on Latent Dirichlet Allocation Retno Kusumaningrum; Satriyo Adhy; Suryono Suryono
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 4: August 2018
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v16i4.8194

Abstract

Latent Dirichlet Allocation (LDA) is a widely implemented approach for extracting hidden topics in documents generated by soft clustering of a word based on document co-occurrence as a multinomial probability distribution over terms. Therefore, several visualizations have been developed, such as matrices design, text-based design, tree design, parallel coordinates, and force-directed graphs. Furthermore, based on a set of documents representing a class (category), we can implement classification task by comparing topic proportion for each class and topic proportion for the testing document by using Kullback-Leibler Divergence (KLD). Therefore, the purpose of this study is to develop a system for visualizing the output of LDA as a classification task. The visualization system consists of two parts: bar chart and dependent word cloud. The first visualization aims to show the trend of each category, while the second visualization aims to show the words that represent each selected category in a word cloud. This visualization is subsequently called WCloudViz. It provides clear, understandable and preferably shared the result.