p-Index From 2020 - 2025
7.804
P-Index
Claim Missing Document
Check
Articles

PENENTUAN DOMAIN DENGAN TEKNIK VARIOGRAM Aji Hamim Wigena; Utami Dyah Syafitri; Yuan Millafanti
FORUM STATISTIKA DAN KOMPUTASI Vol. 12 No. 2 (2007)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

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

Abstract

Dalam banyak kesempatan, penyusunan model skoring untuk memprediksi klasifikasi calon nasabah dilakukan menggunakan model regresi logistik dan beberapa model lain.  Proses pengklasifikasian dapat juga dilakukan dengan menerapkan simple naive Bayesian classifier.  Meskipun menggunakan asumsi yang secara umum dilanggar oleh data dan proses komputasi yang jauh lebih sederhana, teknik ini mampu menghasilkan akurasi dugaan yang tidak mengecewakan.  Paper ini memberikan ilustrasi penggunaan simple naive bayesian classifier pada kasus prediksi klasifikasi status kolektibilitas calon nasabah dan membandingkannya dengan model regresi logistik dan generalized additive model.   Kata kunci: simple naive Bayesian classifier
KONSISTENSI RESPONDEN DALAM MENGEVALUASI PROFIL PRODUK PADA ANALISIS KONJOIN Utami Dyah Syafitri; Hari Wijayanto; Yuni Suci Kurniawati
FORUM STATISTIKA DAN KOMPUTASI Vol. 12 No. 2 (2007)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

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

Abstract

Salah satu non sampling error dalam suatu survey adalah ketidakkonsistenan jawaban yang diberikan oleh responden terutama jika diminta untuk memberikan prioritas terhadap profil suatu produk. Hal tersebut berkaitan dengan alat ukur (kuesioner) yang digunakan. Dalam analisis konjoint, evaluasi preferensi terhadap suatu produk dilakukan dengan memberikan penilaian (rating) dan mengurutkan (ranking) profil-profil suatu produk. Responden dikatakan konsisten apabila hasil analisis konjoin per individu dari data rating dan ranking menunjukkan urutan tingkat kepentingan atribut yang sama dari dua metode pengukuran tersebut. Sebagai bahan evaluasi terhadap ketidakkonsistenan jawaban responden, dalam penelitian ini digunakan studi kasus preferensi mahasiswa IPB dalam memilih mata kuliah pilihan. Pengambilan sampel dilakukan secara purposive. Dari hasil survey, secara umum dapat dikatakan responden konsisten dalam mengevaluasi stimuli dengan metode rating dan ranking. Sedangkan apabila ditinjau dari sisi masing-masing individu diperoleh sekitar 43% responden yang dapat mengevaluasi stimuli dengan metode rating dan ranking secara konsisten. Kekonsistenan jawaban responden dipengaruhi oleh lamanya waktu yang diperlukan untuk evaluasi produk, sikap dan kesungguhan dalam menjawab, serta pribadi yang serius (ditunjukkan oleh prilaku yang tidak gemar bermain games). Kata kunci : konjoint, rating, ranking, kekonsistenan
L-Histidine-Modified Silica from Rice Husk and Optimization of Adsorption Condition for Extractive Concentration of Pb(II) Nurhajawarsi Nurhajawarsi; Mohamad Rafi; Utami Dyah Syafitri; Eti Rohaeti
The Journal of Pure and Applied Chemistry Research Vol 7, No 2 (2018): Edition May-August 2018
Publisher : Chemistry Department, The University of Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1035.086 KB) | DOI: 10.21776/ub.jpacr.2018.007.02.402

Abstract

A new chelating agent, L-histidine-modified silica from rice husk (LHSRH), was prepared to increase the adsorption capacity and selectivity for Pb(II). LHSRH was synthesized by immobilizing L-histidine on silica from rice husk (RH) modified with 3-aminopropyltrimethoxysilane (APTMS). Silica from rice husk (SRH) was synthesized via precipitation process by adding hydrochloric acid solution to rice husk ash (RHA). The RHA was subsequently destructed with sodium hydroxide and heated to obtain sodium silicate (Na2SiO3). SRH was characterized by Fourier transform infrared spectroscopy and x-ray diffraction. The LHSRH was used further to adsorp Pb(II) metal ion. The pH range, amount of adsorbent, and adsorption time were optimized by response surface methodology. The optimum condition for the adsorption of Pb(II) was pH 5, an amount of adsorbent 0.1 g; and adsorption time 15 minutes. The adsorption capacity for Pb(II) ion was found to be 62.5 mg/g. The adsorption behavior of the matrix followed the Langmuir’s model.
Data Fusion of UV-Vis and FTIR Spectra Combined with Principal Component Analysis for Distinguishing of Andrographis paniculata Extracts Based on Cultivation Ages and Solvent Extraction Antonio Kautsar; Wulan Tri Wahyuni; Utami Dyah Syafitri; Syifa Muflihah; Nursifa Mawadah; Eti Rohaeti; Zulhan Arif; Bambang Prajogo; Muhammad Bachri Amran; Abdul Rohman; Mohamad Rafi
Indonesian Journal of Chemistry Vol 21, No 3 (2021)
Publisher : Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijc.60321

Abstract

Andrographis paniculata is one of the medicinal plants used for the treatment of antidiabetic. Cultivation ages and solvent extraction affected metabolites' composition and concentration that directly cause the plant's efficacies. This research aimed to distinguish A. paniculata based on cultivation ages and solvent extraction using data fusion of UV-Vis and FTIR spectra combined with principal component analysis (PCA). A. paniculata with 2, 3, and 4 months post-planting were extracted by water, 50% ethanol, 70% ethanol, and ethanol. In each extract, we measured UV-Vis and FTIR spectra. Then, we used the data fusion from both spectra. We used UV-Vis and FTIR absorbance from 200–400 nm and 1800–400 cm–1, respectively. Each extract gives a similar pattern of UV-Vis and FTIR spectra, only differ in their intensities. PCA score plot in two and three-dimensional showed A. paniculata extracts could be distinguished based on cultivation ages and solvent extraction with a total variance of 86 and 92%, respectively. Furthermore, this study confirms the data fusion of UV-Vis and FTIR spectra could distinguished A. paniculata extracts combined with chemometrics based on cultivation ages and solvent extraction.
Discrimination of cassava, taro, and wheat flour using near-infrared spectroscopy and chemometrics Mohamad Rafi; Sifa Awalul Fikriah; Rifki Husnul Khuluk; Utami Dyah Syafitri
Jurnal Kimia Sains dan Aplikasi Vol 23, No 10 (2020): Volume 23 Issue 10 Year 2020
Publisher : Chemistry Department, Faculty of Sciences and Mathematics, Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1886.409 KB) | DOI: 10.14710/jksa.23.10.360-364

Abstract

There is a difference in the selling price for cassava, taro, and wheat flour, with taro flour having a higher price. It could be a reason for adulterating the taro flour from the other two flours and reducing quality. This study aims to distinguish the three types of flour using the near-infrared (NIR) spectra combined with chemometrics. The NIR spectra of all samples were measured at a wavelength of 1000-2500 nm. The multivariate analysis used was principal component analysis (PCA), and PCA followed with discriminant analysis (DA). The preliminary process of the signal using area normalization was carried out before the multivariate analysis. The PCA results showed that most of the samples were grouped in their respective groups except for two samples, namely 1 sample of taro flour and 1 sample of cassava flour. Meanwhile, the PCA-DA results using seven main components showed that the three samples were grouped well. DA validation was carried out using the cross-validation method, showing that the samples could be identified into their respective groups. Therefore, a combination of NIR spectrum and chemometric analysis can be used to differentiate cassava, taro, and wheat flour
Karakteristik Daging Tiruan (Meat Analog) dengan Optimasi Formulasi Substitusi Rumput Laut menggunakan Mixture Design: Characteristics of Meat Analog with Formula Optimization of Seaweed Substitution using Mixture Design Bambang Riyanto; Utami Dyah Syafitri; Joko Santoso; Endina Fatihah Yasmin
Jurnal Pengolahan Hasil Perikanan Indonesia Vol 25 No 2 (2022): Jurnal Pengolahan Hasil Perikanan Indonesia 25(2)
Publisher : Masyarakat Pengolahan Hasil Perikanan Indonesia (MPHPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17844/jphpi.v25i2.39942

Abstract

Meat analog atau daging alternatif berbasis protein nabati telah memberikan preferensi konsumen akan pentingnya kesehatan. Potensi alami dengan karakteristik fungsional rumput laut menawarkan perspektif baru meat analog. Konsep rancangan serta strategi formulasi menjadi awal yang sangat penting. Penelitian bertujuan menentukan karakteristik daging tiruan (meat analog) dengan optimasi formulasi substitusi rumput laut menggunakan mixture design. Penelitian meliputi karakterisasi bahan penyusun, rancangan formulasi dan pembuatan daging tiruan, optimasi formulasi substitusi rumput laut menggunakan mixture design serta perbandingan karakteristik daging tiruan substitusi rumput laut dan meat analog komersial. Formula optimal daging tiruan menggunakan mixture design menghasilkan substitusi tepung rumput laut 45%, dengan proporsi tepung kedelai 40% dan tepung jagung 15%. Daging tiruan substitusi rumput laut memiliki bentuk burger ukuran diameter 5 cm, tebal 2 cm dan berat 50 g, sensori ketampakan berserat, berwarna cokelat kekuningan dan rasa khas daging. Karakteristik tekstur dengan nilai hardness 2.385,90±0,02 gf, springiness 0,83±0,01, chewiness 1,52±0,02 dan water holding capacity 6,19±0,04 serta kadar protein 10,16%±0,01, karbohidrat 46,79%±0,03 dan abu 2,50%±0,02, yang menyerupai meat analog komersial dan kepatuhan dengan SNI 8503-2018 mengenai burger.
Identifying Characteristics of Households Recipient of the Government’s Social Protection Program Nofrida Elly Zendrato; Bagus Sartono; Utami Dyah Syafitri
Indonesian Journal of Artificial Intelligence and Data Mining Vol 5, No 1 (2022): March 2022
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v5i1.18579

Abstract

According to Statistics Indonesia, the number of poor people increased by 1,12 million people in March 2020. In March 2021, the percentage of poor people increased by 0,36 points compared to March 2020. The percentage of poor people in Banten Province has increased in the last three years (2019-2021). One way to reduce poverty by the government is to increase social protection programs. The characteristics of households receiving social protection programs were identified by modeling the classification of households using the random forest technique, obtaining important variables using the permutation feature importance and Shapley additive explanations interpretation techniques, and analyzing the most important variables from the two interpretations methods. Handling the imbalance data on the response variables using SMOTE technique and evaluating the classification model obtained an AUC value of 0,718. The important variables were selected from the permutation feature importance and Shapley additive explanation methods based on a consistent ranking at the top. Shapley’s additive explanation was more consistent than permutation feature importance. Six important, namely capita expenditure, education of the head of household, age of head of household, source of drinking water, floor area, and the number of household members.
UHPLC-Q-Orbitrap HRMS-based Untargeted Metabolomics of Sida rhombifolia Leaves and Stem Extracts Alfi Hudatul Karomah; Mohamad Rafi; Dewi Anggraini Septaningsih; Auliya Ilmiawati; Utami Dyah Syafitri; Nanik Siti Aminah; Muhamad Insanu; Abdul Rohman
HAYATI Journal of Biosciences Vol. 30 No. 4 (2023): July 2023
Publisher : Bogor Agricultural University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.4308/hjb.30.4.770-778

Abstract

Sida rhombifolia, also known as sidaguri in Indonesia, is a medicinal plant commonly used as a herbal medicine because of its metabolite and biological activities. One of the several factors that affect plant metabolite composition and concentration is the use of plant parts. In this study, the experiment aimed to identify the metabolite profile in the leaves and stem extracts of S. rhombifolia using UHPLC-Q-Orbitrap HRMS-based untargeted metabolomics. The samples were distinguished by principal component analysis (PCA). Extraction of metabolites was conducted by sonication for approximately 30 min with 70% ethanol as the extraction solvent; 28 metabolites were identified. Seven metabolites were identified only in the leaves, three were identified only in the stems, and 18 other metabolites were identified in both the leaves and stems. These metabolites were categorized as flavonoids, triterpenoids, alkaloids, coumarins, phenolic aldehydes, phenolic acids, ecdysteroids, fatty acids, and monoterpene lactones. Based on the classification results, PCA grouped the leaves and stem extracts of S. rhombifolia using the peak area variables of the identified metabolites.
Segmentasi Mahasiswa S1 IPB terhadap Sistem Peminjaman Sepeda Tania Amalia Darsono; Utami Dyah Syafitri; Aam Alamudi
Xplore: Journal of Statistics Vol. 2 No. 1 (2018): 30 Juni 2018
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (270.104 KB) | DOI: 10.29244/xplore.v2i1.74

Abstract

IPB is the one campus that realize the Green Campus program. One of the elements in Green Campus is Green Transportation. In realizing this Green Transportation, IPB has several programs that include the Green Bike program. There are rules in implementation the Green Bike program related to the borrowing system. Because of the borrowing system, it is necessary to make the segmentation of S1 IPB students on bicycle borrowing system. Segmentation of respondent's characteristic used two step clustering method and the result is 3 optimal clusters. Then segmentation on respondent's preference to bicycle borrowing system used k-means method and the result is 2 optimal clusters. Segmentation of bicycle borrowing system based on respondent's characteristic and respondent's preference is 6 combinations of cluster using cross tabulation.
Segmentasi Mahasiswa S1 IPB terhadap Sistem Peminjaman Sepeda Tania Amalia Darsono; Utami Dyah Syafitri; Aam Alamudi
Xplore: Journal of Statistics Vol. 7 No. 3 (2018): 31 Desember 2018
Publisher : Department of Statistics, IPB

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

Abstract

Green Campus is one program of IPB. One element of Green Campus is Green Transportation. There are programs in Green Transportation, one of the programs is Green Bike. There are rules in Green Bike program which were related to the system of borrowing. Based on the rules, so it was required to make segmentation of undergraduate students IPB on bicycle borrowing system. This research used data of undergraduate students IPB on bicycle borrowing system’s preferences and characteristics of respondents. Segmentation on characteristics of respondents using two step cluster method. The distance that was used in two step cluster is log-likelihood and to determinate the optimal clusters using BIC. There are 3 optimal clusters formed and quality of clustering is fair (coefficient Silhouette = 0.3). Then segmentation on bicycle borrowing system’s preferences using kmeans method. The distance that was used in k-means is euclid and there are 2 optimal clusters formed (based on the Pseudo-F value). Based on segmentation on bicycle borrowing system by combining characteristics and preferences of respondents, there are 6 cluters formed.
Co-Authors Aam Alamudi Abdul Rohman Abdul Rohman Agus Mohamad Soleh Agustin Faradila Aidi, Muhammad Nur Aji Hamim Wigena Akbar Rizki Alfi Hudatul Karomah ALIU, MUFTIH ALWI Anang Kurnia Andreas Nicholas Gandaputra Simbolon Andrew Donda Munthe Anggrahini, Ervina Dwi Anggraini Sukmawati Anik Djuraidah Anissa Permatasari Antonio Kautsar ASEP SAEFUDDIN Auliya Ilmiawati Aziza, Vivin Nur Azkiya, Azka Al Baehera, Seta Bagus Sartono Bambang - Riyanto Bambang Prajogo Eko Wardoyo Bambang Riyanto Bartho Sihombing Bayu Pranata, Bayu Budi Susetyo Christin Halim Cici Suhaeni Dea Amelia, Dea Dwi Agustin Nuriani Sirodj Dwi Putri Kurniasari Eka Dewi Pertiwi Eka Winarni Sapitri Eminita, Viarti Endina Fatihah Yasmin Erfiani Erfiani Erfiani, Erfiani Erlinda Widya Widjanarko Ernawati, Fitrah Eti Rohaeti Evita Choiriyah Fadhila Hijryani FAHREZAL ZUBEDI Farit M Afendi Fatimah, Zahra Nurul Fitrianto, Anwar Gusti Tasya Meilania Hari Wijayanto I Made Sumertajaya Idqan Fahmi Immatul Ulya Indahwati Indonesian Journal of Statistics and Its Applications IJSA Intan Lukiswati Irmanida Batubara Irzaman, Irzaman Isti Rochayati Izzati, Mumpuni Nur Joko Santoso Jumansyah, L. M. Risman Dwi Khairil Anwar Notodiputro Kusman Sadik Laradea Marifni Lidiasari, Melisa Lismayani Usman M. Iqbal M. Rafi Meilania, Gusti Tasya Mohamad Rafi Mohamad Rafi Mohamad Rafi Mohammad Masjkur Muhamad Insanu Muhammad Bachri Amran Muhammad Nur Aidi Muhammad Nursid Mulianto Raharjo Muslim, Muhammad Irfai Muthahari, Wadudi Nanik Siti Aminah Nariswari Karina Dewi Ni Kadek Manik Dewantari Noer Endah Islami Nofrida Elly Zendrato Novia Yustika Tri Lestari. YR Nur Aidi, Muhammad Nurhajawarsi Nurhajawarsi Nursifa Mawadah R, Arifuddin Rifki Husnul Khuluk Ririn Fara Afriani Riswan Riswan Sanusi, Ratna Nur Mustika Sari, Mutia Dwi Permata Septaningsih, Dewi Anggraini Setyowati, Silfiana Lis Sifa Awalul Fikriah Siwi Haryu Pramesti Soleh, Agus M Soni Yadi Mulyadi Sony Hartono Wijaya Sri Sulastri Sri Wahyuningsih Syam, Ummul Auliyah Syifa Muflihah Tania Amalia Darsono Thasya Putri Topan . Ruspayandi Triyani Oktaria Vega, Iliana Patricia Vivin Nur Aziza Weisha, Ghea Wini - Trilaksani Wulan Tri Wahyuni Yenni Angraini Yuan Millafanti Yuni Suci Kurniawati Yuniar Istiqomah