Claim Missing Document
Check
Articles

Found 24 Documents
Search

Logika Fuzzy Untuk Uji Kelayakan Lahan Singkong Sebagai Bahan Baku Bioetanol Purwanti, Endah
Prosiding SNATIKA Vol 01 (2011) Vol 1
Publisher : Prosiding SNATIKA Vol 01 (2011)

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

Abstract

Bioetanol merupakan salah satu solusi pemerintah dalam mengganti BBM untuk menghadapi keterbatasan minyak dunia. Bioetanol dapat dengan mudah diproduksi dari bahan bergula dan berserat seperti singkong. Namun, untuk membudidayakan singkong sebagai bahan baku bioetanol diperlukan lahan yang berkualitas dan tentunya dapat digunakan dalam jangka panjang karena itu perlu adanya syarat tumbuh untuk menentukan kelayakan lahan. Logika fuzzy digunakan untuk membantu menentukan kelayakan lahan dengan segala ketidakpastian yang ada. Dalam sistem ini dilakukan survei lahan singkong didaerah Jawa Tengah. Dimana hasil pertanian singkong disana dijadikan sebagai bahan baku bioetanol oleh salah satu perusahaan kimia. Penentuan kelayakan lahan menggunakan 5(lima) parameter yaitu, ketersediaan air, kondisi tanah, sejarah lahan, nilai ekonomis dan naungan. Basis pengetahuan berupa aturan dari kombinasi himpunan fuzzy semua parameter, sebagai pendukung pengambilan keputusan layak tidaknya suatu lahan singkong sebagai bahan baku bioetanol. Sistem ini mampu memutuskan apakah suatu lahan dapat dikatakan sangat layak, layak, kurang layak atau tidak layak untuk ditanami singkong sebagai bahan baku bioetanol. 46% lahan dinyatakan layak, 2% tidak layak, dan sisanya kurang layak. Parameter yang perlu dikaji ulang untuk penelitian lebih lanjut adalah parameter nilai ekonomis, dan naungan lahan. Karena dua parameter ini umumnya bernilai kecil. Keywords/Kata kunci:logika fuzzy, kelayakan lahan, bioetanol, sistem pendukung keputusan
Perencanaan Arsitektur Perusahaan untuk Pengelolaan Aset di PT. Musdalifah Group menggunakan Kerangka Kerja Zachman Safarina, Indah; Raharjana, Indra Kharisma; Purwanti, Endah
Journal of Information Systems Engineering and Business Intelligence Vol 1, No 2 (2015): October
Publisher : Program Studi Sistem Informasi, Fakultas Sains dan Teknologi, Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1411.567 KB)

Abstract

Abstrak— Aset adalah hal penting yang dimiliki oleh setiap perusahaan atau organisasi. Proses manajemen aset yang dilakukan dengan tepat akan membuat aset yang dimiliki oleh perusahaan atau organisasi lebih optimal. Karena proses manajemen aset belum terlaksana dengan maksimal, maka pada penelitian ini direncanakan sebuah arsitektur enterprise untuk proses manajemen aset untuk kelompok perusahaan PT. Musdalifah Group dengan kerangka kerja Zachman melalui tujuh tahap. Tahap pertama adalah pengumpulan data terkait manajemen aset perusahaan yang digunakan sebagai acuan perencanaan. Tahap kedua adalah inisialisasi perencanaan yang menghasilkan rencana kerja arsitektur perusahaan sesuai ruang lingkup dan kondisi perusahaan. Tahap ketiga, meninjau kondisi enterprise saat ini perusahaan, dengan hasil tinjauan model proses bisnis dan katalog sumber daya perusahaan terkait manajemen aset. Tahap keempat adalah analisis hasil tinjauan enterprise dengan analisis SWOT, sehingga dapat dihasilkan 5 rencana proses bisnis serta usulan sistem dan teknologi terintegrasi. Tahap kelima melakukan perencanaan arsitektur enterprise yaitu arsitektur data dengan hasil 34 kandidat entitas data, arsitektur aplikasi yang menghasilkan 9 kandidat aplikasi, dan arsitektur teknologi dengan hasil 3 kandidat perangkat keras dan platform aplikasi yang terintegrasi. Sedangkan tahap terakhir, perencanaan implementasi hasil penelitian yaitu, rencana pemenuhan komponen, rencana migrasi, dan evaluasi dampak arsitektur. Evaluasi dari hasil penelitian menyatakan bahwa cetak biru arsitektur dapat diterima oleh perusahaan dan dipertimbangkan untuk diimplementasikan beberapa tahun kedepan.Kata Kunci—Perencanaan Arsitektur Perusahaan, Kerangka Kerja Zachman, Manajemen Aset.Abstract— Asset is an important thing that owned by any company or organization. Asset management process aims to manage an organization’s assets optimally. Because of the asset management process has not been implemented maximally, so in this study planned an enterprise architecture for the process of asset management for the group of companies PT. Musdalifah Group using Zachman framework through seven phases. The first phase, data collection, and the results is relevant information of company’s asset management as a design reference. The second phase, planning initialization, generates enterprise architecture work plan according to the scope and conditions of the company. The third phase, reviewing the companys current enterprise conditions, the results of the review are models of business processes and enterprise resource catalog of related asset management. The fourth phase, results review analysis of enterprise with SWOT analysis, so it can produce 5 plan and proposed business processes and technology systems terintegrasi. The fifth phase, enterprise architecture planning of data architecture with the results are 37 data entities candidates, application architecture which produces 9 applications candidate, and technology architecture with the results are 3 hardware and application platform candidates. The last phase, planning the implementation of the research’s result, plan fulfillment component, the migration plan, and evaluating the impact of architecture. Evaluation of the result of research is describing that the architectural blueprints can be received by the company and considered to be implemented next few years.Keywords— Enterprise Architecture Planning, Zachman Framework, Asset Management.
USING LEARNING VECTOR QUANTIZATION METHOD FOR AUTOMATED IDENTIFICATION OF MYCOBACTERIUM TUBERCULOSIS Purwanti, Endah; Widiyanti, Prihartini
Indonesian Journal of Tropical and Infectious Disease Vol 3, No 1 (2012)
Publisher : Institute of Topical Disease

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (177.655 KB)

Abstract

In this paper, we are developing an automated method for the detection of tubercle bacilli in clinical specimens, principally the sputum. This investigation is the first attempt to automatically identify TB bacilli in sputum using image processing and learning vector quantization (LVQ) techniques. The evaluation of the learning vector quantization (LVQ) was carried out on Tuberculosis dataset show that average of accuracy is 91,33%.
HEART ABNORMALITY CLASSIFICATIONS USING FOURIER TRANSFORMS METHOD AND NEURAL NETWORKS Purwanti, Endah; Nastiti, Amadea Kurnia; Supardi, Adri
Indonesian Journal of Tropical and Infectious Disease Vol 5, No 2 (2014)
Publisher : Institute of Topical Disease

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

Abstract

Health problems with cardiovascular system disorder are still ranked high globally. One way to detect abnormalities in the cardiovascular system especially in the heart is through the electrocardiogram (ECG) reading. However, reading ECG recording needs experience and expertise, software-based neural networks has designed to help identify any abnormalities of the heart through electrocardiogram digital image. This image is processed using image processing methods to obtain ordinate chart which representing the heart’s electrical potential. Feature extraction using Fourier transforms which are divided into several numbers of coefficients. As the software input, Fourier transforms coefficient have been normalized. Output of this software is divided into three classes, namely heart with atrial fibrillation, coronary heart disease and normal. Maximum accuracy rate of this software is 95.45%, with the distribution of the Fourier transform coefficients 1/8 and number of nodes 5, while minimum accuracy rate of this software at least 68.18% by distribution of the Fourier transform coefficients 1/32 and the number of nodes 32. Overall result accuracy rate of this software has an average of 86.05% and standard deviation of 7.82.
Information Retrieval Document Classified with K-Nearest Neighbor Zaman, Badruz; Purwanti, Endah; Sukma, Alifian
Record and Library Journal Vol 1, No 2 (2015): Juli-Desember
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (26.491 KB) | DOI: 10.20473/rlj.v1i2.1177

Abstract

Along with the rapid advancement of technology development led to the amount of information available is also increasingly abundant. The aim of this study was to determine how the implementation of information retrieval system in the classification of the journal by using the cosine similarity and K-Nearest Neighbor (KNN). The data used as many as 160 documents with categories such as Physical Sciences and Engineering, Life Science, Health Science, and Social Sciences and Humanities. Construction stage begins with the use of text mining processing, the weighting of each token by using the term frequency-inverse document frequency (TF-IDF), calculate the degree of similarity of each document by using the cosine similarity and classification using k-Nearest Neighbor.Evaluation is done by using the testing documents as much as 20 documents, with a value of k = {37, 41, 43}. Evaluation system shows the level of success in classifying documents on the value of k = 43 with a value precision of 0501. System test results showed that 20 document testing used can be classified according to the actual category.
Information Retrieval Document Classified with K-Nearest Neighbor Zaman, Badruz; Purwanti, Endah; Sukma, Alifian
Record and Library Journal Vol 1, No 2 (2015): Juli-Desember
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (26.491 KB) | DOI: 10.20473/rlj.v1i2.1177

Abstract

Along with the rapid advancement of technology development led to the amount of information available is also increasingly abundant. The aim of this study was to determine how the implementation of information retrieval system in the classification of the journal by using the cosine similarity and K-Nearest Neighbor (KNN). The data used as many as 160 documents with categories such as Physical Sciences and Engineering, Life Science, Health Science, and Social Sciences and Humanities. Construction stage begins with the use of text mining processing, the weighting of each token by using the term frequency-inverse document frequency (TF-IDF), calculate the degree of similarity of each document by using the cosine similarity and classification using k-Nearest Neighbor.Evaluation is done by using the testing documents as much as 20 documents, with a value of k = {37, 41, 43}. Evaluation system shows the level of success in classifying documents on the value of k = 43 with a value precision of 0501. System test results showed that 20 document testing used can be classified according to the actual category.
DESIGN OF EXPERT SYSTEM AS A SUPPORT TOOL FOR EARLY DIAGNOSIS OF PRIMARY HEADACHE Azzahra, Zahwa Arsy; Purwanti, Endah; Hidayati, Hanik Badriyah
Malang Neurology Journal Vol 3, No 2 (2017): July
Publisher : Malang Neurology Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (708.76 KB) | DOI: 10.21776/ub.mnj.2017.003.02.5

Abstract

Background. Headache is the top ranked with 42% percentage of all complaints neurology’s patients. Focused and systematic approach is needed in making a diagnosis of primary headache type because management of headache is different for each type.Objective. Enabling users to identify the type of headache.Methods. The experiment was conducted using Naïve Bayes classifier method which is the principle is multiplying the percentage likelihood of each variable for each parameter for each class.Results. The percentage value of each parameter obtained from the data of headache patients at neurology polyclinic poly of Dr. Soetomo Hospital within 1 year from the year 2014 to 2015. The percentage value of each class likelihood sought highest value which is the output or decision-diagnosis program. Analysis of each of the input parameters, gender, age, location of head pain, headache characteristics, appeared least autonomous signs, and scale of headache may indicate that each of the options selected by the user influence the decision of the diagnosis program.Conclusion. The design of early detection of primary headaches with the input parameters as mentioned before derived from the raw data as electronic medical records to be analyzed based on methods Naïve Bayes classifier resulted in the decision diagnosis of migraine, cluster and TTH have accuracy values by 92 %.
Information Retrieval Document Classification with K-Nearest Neighbor Sukma, Alifian; Zaman, Badruz; Purwanti, Endah
Record and Library Journal Vol 1, No 2 (2015)
Publisher : D3 Teknisi Perpustakaan Fakultas Vokasi Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (511.443 KB) | DOI: 10.20473/rlj.V1-I2.2015.129-138

Abstract

Along with the rapid advancement of technology development led to the amount of information available is also increasingly abundant. The aim of this study was to determine how the implementation of information retrieval system in the classification of the journal by using the cosine similarity and K-Nearest Neighbor (KNN).The data used as many as 160 documents with categories such as Physical Sciences and Engineering, Life Science, Health Science, and Social Sciences and Humanities. Construction stage begins with the use of text mining processing, the weighting of each token by using the term frequency-inverse document frequency (TF-IDF), calculate the degree of similarity of each document by using the cosine similarity and classification using k-Nearest Neighbor.Evaluation is done by using the testing documents as much as 20 documents, with a value of k = {37, 41, 43}. Evaluation system shows the level of success in classifying documents on the value of k = 43 with a value precision of 0501. System test results showed that 20 document testing used can be classified according to the actual category
Identifikasi Kebutuhan Operasional CRM untuk Monitoring Tugas Akhir Purwanti, Endah; Zaman, Badrus
MULTINETICS Vol 2, No 2 (2016): MULTINETICS Nopember (2016)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.Vol2.No.2.2016.pp.75-79

Abstract

Customer Relationship Management (CRM) telah berkembang menjadi sebuah strategi, proses, dan teknologi untuk memperkuat hubungan perusahaan dengan pelanggannya, melalui customer life-cycle. Tren pada e-bisnis menunjukkan perubahan dari product-centric menjadi customer-centric. Universitas atau perguruan tinggi dapat mengambil keuntungan dari CRM melalui peningkatan proses student-facing. Pada penelitian ini dilakukan identifikasi kebutuhan operasional CRM untuk monitoring Tugas Akhir, dengan mengambil studi kasus di program studi D3 Sistem Informasi Fakultas Vokasi Unair. Identifikasi dilakukan dengan menggunakan model IDIC (Identify, Differentiate, Interact and Customize). Identifikasi kebutuhan merujuk pada konsumen yang ada. Aktor yang diidentifikasi sebagai konsumen sistem monitoring tugas akhir adalah mahasiswa, dosen pembimbing dan koordinator program studi.  Tahap diferensiasi dilakukan pada masing-masing aktor untuk mendapatkan kepentingan dan kebutuhan terhadap informasi yang dihasilkan oleh sistem. Identifikasi kebutuhan fungsional digambarkan dalam sebuah use case diagram. Secara umum kepentingan tiap aktor adalah akses informasi secara langsung ke dalam sistem. Kemudahan dalam mendapatkan informasi akan meningkatkan kepuasan konsumen dalam mendapatkan informasi dan memutuskan strategi yang dipilih untuk memperlancar pengerjaan tugas akhir
Sistem Deteksi Bahasa pada Dokumen menggunakan N-Gram Zaman, Badrus; Hariyanti, Eva; Purwanti, Endah
MULTINETICS Vol 1, No 2 (2015): MULTINETICS Nopember (2015)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.Vol1.No.2.2015.pp.21-26

Abstract

Language detection on a very large collection of documents can be done to increasing performance of information retrieval system. One of popular method on language detection is N-Grams, based on pieces of n-characters taken from a string. This research is developed language detection system based on N-Gram that performs by Indonesian or English language. In general, the steps being taken there were 3 phases, namely creating profile of each language, system testing, and system evaluation. Fifty documents were used to creating profile of each language, i.e. 25 Indonesian and 25 English. Sixty documents were used for system testing. System performance was evaluated using F-measures. Based on the test, obtained F-measures for unigram, bigram, and unigram respectively 0.933, 0.917, and 0.933.