Claim Missing Document
Check
Articles

Found 12 Documents
Search

Cursive Handwriting Segmentation using Ideal Distance Approach Fitrianingsih Fitrianingsih; Sarifuddin Madenda; Ernastuti Ernastuti; Suryarini Widodo; Rodiah Rodiah
International Journal of Electrical and Computer Engineering (IJECE) Vol 7, No 5: October 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (686.775 KB) | DOI: 10.11591/ijece.v7i5.pp2863-2872

Abstract

Offline cursive handwriting becomes a major challenge due to the huge amount of handwriting varieties such as slant handwriting, space between words, the size and direction of the letter, the style of writing the letter and handwriting with contour similarity on some letters. There are some steps for recursive handwriting recognition. The steps are preprocessing, morphology, segmentation, features of letter extraction and recognition. Segmentation is a crucial process in handwriting recognition since the success of segmentation step will determine the success level of recognition. This paper proposes a segmentation algorithm that segment recursive handwriting into letters. These letters will form words using a method that determine the intersection cutting point of image recursive handwriting with an ideal image distance. The ideal distance of recursive handwriting image is an ideal distance segmentation point in order to avoid the cutting of other letter’s section. The width and height of images are used to determine the accurate segmentation point. There were 999 recursive handwriting input images taken from 25 researchers used for this study. The images used are the images obtained from preprocessing step. Those are the images with slope correction. This study used Support Vector Machine (SVM) to recognize recursive handwriting. The experiments show the proposed segmentation algorithm able to segment the image precisely and have 97% success recognizing the recursive handwriting.
PENERAPAN FILTER GABOR UNTUK ANALISIS TEKSTUR CITRA MAMMOGRAM Lussiana ETP Lussiana ETP; Suryarini Widodo; Di Ajeng Pambayun
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2011
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract

Mammography merupakan kegiatan pemeriksaan yang telah banyak dilakukan melalui teknik radiologi seperti foto sinar-X untuk memperoleh gambaran jaringan payudara (citra mammogram). Adanya kelainan padajaringan dapat diketahui dengan pemeriksaan lebih lanjut menggunakan proses analisis tertentu. Tujuan dari penelitian ini adalah melakukan analisis tekstur terhadap citra mammogram dengan menggunakan filter Gabor. Hasil penelitian menyatakan bahwa output tekstur yang tampak sangat dipengaruhi oleh besarnya nilai parameter frekuensi serta derajat orientasi citra. Semakin rendah nilai frekuensi yang diberikan, maka hasilpengujianpun akan terlihat semakin terang dan blur. Begitupula sebaliknya, semakin tinggi nilai frekuensi, maka citrapun akan sulit didefinisi karena tingkat terang citra sangat terbatas. Oleh sebab itu, nilai frekuensi pada skala pertengahan (f = 0.176) dianggap paling sesuai untuk melakukan analisis tekstur. Selain frekuensi, parameter orientasi juga mampu memperlihatkan suatu kecenderungan tekstur yang tinggi pada arah tertentu. Dari tampilan tekstur berarah inilah wilayah yang dicurigai adanya kelainan pada jaringan payudara dapat lebih mudah terdeteksi
Perancangan Cloud Computing Dalam Pengelolaan Infrastruktur Teknologi Informasi Berbasis Roadmap Cloud Computing Adoption (Rocca) Mudiyono Mudiyono; Suryarini Widodo
Syntax Idea Vol 2 No 10 (2020): Syntax Idea
Publisher : Ridwan Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46799/syntax-idea.v2i10.517

Abstract

Cloud computing menjadi suatu trend teknologi virtualisasi yang banyak digunakan saat ini pada era revolusi industri 4.0. Pada instansi pemerintah teknologi ini menjadi sesuatu yang dibutuhkan untuk mengatasi masalah ketersediaan sumber daya server serta dapat meningkatkan efisiensi, efektifitas dan kerahasian data serta mendukung proses bisnis, hingga dapat memperkuat infrastruktur. Dengan alasan tersebut penelitian ini merancang arsitektur cloud computing menggunakan model implementasi Private Cloud dan layanan Infrastruktur as a Service (IaaS) dengan teknik adopsi model Roadmap Cloud Computing Adoption (ROCCA) menggunakan analisis SWOT untuk memetakan kebutuhan dalam rangka pengelolaan infrastruktur. Metode adopsi cloud computing melalui tahapan analisis, perancangan, adopsi, migrasi serta pengelolaan yang akan dirancang sesuai dengan model ROCCA. untuk perencanaan tidak menyebutkan biaya yang dibutuhkan. Penelitian melakukan pengujian dengan metode analisis deskriptif kualitatif melalui pendekatan studi kasus pada instansi BKKBN. Hasil dari penelitian dapat dijadikan sebagai referensi cetak biru STIK BKKBN 2020-2024. Sebagai pengembangan sistem ke depannya, hasil rancangan di desain memiliki sistem layanan private cloud pada Disaster Recovery Center (DRC) di lokasi yang berbeda dengan data center utama dengan tujuan untuk pemulihan data center jika terjadi bencana.
Advanced content-based retrieval for digital correspondence documents with ontology classification Rifiana Arief; Suryarini Widodo; Ary Bima Kurniawan; Hustinawaty Hustinawaty; Faisal Arkan
Bulletin of Electrical Engineering and Informatics Vol 11, No 3: June 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v11i3.3376

Abstract

The growth of digital correspondence documents with various types, different naming rules, and no sufficient search system complicates the search process with certain content, especially if there are unclassified documents, the search becomes inaccurate and takes a long time. This research proposed archiving method with automatic hierarchical classification and the content-based search method which displays ontology classification information as the solution to the content-based search problems. The method consists of preprocessing (creation of automatic hierarchical classification model using a combination of convolutional neural network (CNN) and regular expression method), archiving (document archiving with automatic classification), and retrieval (content-based search by displaying ontology relationships from the document classification). The archiving of 100 documents using the automatic hierarchical classification was found to be 79% accurate as indicated by the 99% accuracy for CNN and 80% for Regex. Moreover, the search results for classified content-based documents through the display of ontology relationships were discovered to be 100% accurate. This research succeeded in improving the quality of search results for digital correspondence documents as indicated by its higher specificity, accuracy, and speed compared to conventional methods based on file names, annotations, and unclassified content.
ALGORITMA NEURAL NETWORK BACKPROPAGATION UNTUK PREDIKSI HARGA SAHAM PADA TIGA GOLONGAN PERUSAHAAN BERDASARKAN KAPITALISASINYA Nopri Santi; Suryarini Widodo
Faktor Exacta Vol 14, No 3 (2021)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v14i3.9365

Abstract

Stock is one type of investment where investors can gain profits in the form of capital gains and dividends. Types of shares based on the level of capitalization are divided into 3 types, namely the first layer (blue chips), the second layer, and the third layer. One of the techniques that investors use in order to make a profit is technical analysis, which is using data of past stock prices and volumes based on the assumption that trends can recur following historical data patterns. Based on the assumptions of technical analysis, it is possible to use data mining to predict stock prices. In this study, stock price predictions will be carried out by comparing three types of companies based on their capitalization, for first layer stocks using PT. Bank Central Asia Tbk (BBCA), the second layer using PT. XL Axiata Tbk (EXCL), and third layer using PT Pembangunan Graha Lestari Indah Tbk. The data mining algorithm that will be used is the Neural Network Backpropagation method. The attributes used as predictors are open, high, low, and volume, while the objective attribute is close. This study aims to determine whether daily stock historical data can be used to predict stock prices using the Neural Network Backpropagation method and how to compare the results of predictions between 3 companies with different capitalization levels. The result of RMSE for BBCA by using the most optimal combination of parameters and 3 hidden layer is 123.84. The result of RMSE for EXCL by using the most optimal combination of parameters and hidden layer 2 is 37.36. The result of RMSE for PGLI by using the most optimal combination of parameters and hidden layer 6 is 6.16. So that the backpropagation neural network algorithm is most optimally applied to third layer companies, PT. Pembangunan Graha Lestari Indah Tbk because the RMSE value is the smallest.
Representasi Kode IRMA pada Basis Data Mammografi MIAS Karmilasari Karmilasari; Suryarini Widodo; Lussiana ETP
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2012: SNTIKI 4
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (278.977 KB)

Abstract

Limitations of mammography database with image coding and the identification of a variety ofcharacteristics, such as pathology, and abnormal breast tissue types, is an issue in the development ofcomputer systems for the diagnosis of breast cancer. IRMA coding system was developed to facilitatecontent-based image retrieval identify (CBIR) as a prototype application in medical diagnostic radiologyimagery. IRMA Code was developed following the network code American College of Radiology (ACR)and data system (BI-RAD). Through IRMA code, obtained standardized code for the type of tissue, thelevel of tumor and lesion description. The results of the code in the form of a character string of no morethan 13 characters (IRMA: YYYY - DDD - AAA - BBB). The code can be extended by introducingcharacters in certain positions code if there is a new modality is introduced. IRMA coding system can beapplied to mammographic Digital Mammogram Image Analysis Society (MIAS). Complete initialinformation from mammography is the basis for the study of medical image breast cancer, while the finalinformation obtained from IRMA coding system can be input for clinicians in decision-making for patientaction.Keywords : Mammography, IRMA coding system, MIAS database
PENERAPAN DATA MINING PADA PENERIMAAN MAHASISWA BARU DENGAN ALGORITMA K-MEANS CLUSTERING Septian Isnanto; Suryarini Widodo
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 4 No 2 (2021)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v4i2.367

Abstract

This paper aims to grouping data using Clustering method with k-means algorithm to find potential majors and type of schools that produce feature students who have a good GPA score in semester 1 and semester 2 at Politeknik STMI Jakarta. Dataset from academic data for 2017-2020 has been processed with Rapid Miner showing that in Automotive Business Administration study program there are 3 clusters of students where cluster 0 marked as best cluster is dominated by high school students majoring in Science and Social Sciences. Automotive Industry Information System study program produces 2 clusters of students where cluster 0 marked as best cluster is dominated by high school students majoring in science and vocational high school majoring in mechanical engineering. Automotive Industrial Engineering study program produces 2 clusters of students where cluster 1 marked as best cluster is dominated by high school students majoring in science. Polymer Chemical Engineering study program produces 6 student clusters where cluster 4 marked as best cluster which all come from high school students majoring in science.
PLANNING AND IMPLEMENTATION OF ODOO ERP HUMAN RESOURCE APPLICATION MODULE USING ACCELERATED SAP (ASAP) METHOD IN HEAVY EQUIPMENT RENTAL COMPANY Affandy Affandy; Suryarini Widodo; Syti Sarah
Indonesian Journal of Multidisciplinary Science Vol. 1 No. 11 (2022): IJOMS: Indonesian Journal of Multidisciplinary Science
Publisher : International Journal Labs

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1827.784 KB) | DOI: 10.55324/ijoms.v1i11.216

Abstract

An integrated information system in the Human Resources Department (HRD) is needed for good HR management to improve employee performance. The Importance of Odoo ERP Implementation Human Resource Application Module to replace a system that uses excel sheets into an automation process in the employee payroll process according to the company's business processes. Based on these problems, research was conducted to plan and implement this module using the Accelerated SAP (ASAP) method. The ASAP method is a framework method that is applied to project management to improve efficiency in the implementation of Odoo ERP. The results of this study are the renewal of the business process for employee payroll with changes in the division of labor between actors in HRD and the Accounting & Finance Department. In addition, customization and configuration of the Human Resource Application module was carried out according to the payroll process business blueprint. The process of testing this application uses the Black Box Testing method which is focused on functional specifications.
Implementation of Docker Swarm on A Mariadb Database Clustered with Galera Clusters on More than One Host (Multi Host) Rifqy Adli Damhuri*; Suryarini Widodo
JIM: Jurnal Ilmiah Mahasiswa Pendidikan Sejarah Vol 8, No 4 (2023): Agustus, Social Religious, History of low, Social Econmic and Humanities
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jimps.v8i4.26482

Abstract

The Covid-19 pandemic in Indonesia, which began in 2019, has had an impact on all levels of society. With this pandemic occurring, the Indonesian government made several policies with the aim of stopping the spread of the Covid-19 virus. One form of policy that is carried out is by imposing a system of Imposing Restrictions on Community Activities (PPKM), to prevent the spread of the virus through physical contact. The existence of this PPKM is one of the drivers of digitization in almost all sectors. This transformation in the digital world must be facilitated with qualified infrastructure. One example of important infrastructure needed to support digital transformation is a server and to be specific is a database server. To improve and optimize the performance of the server, system development is carried out using docker swarm on a mariadb database clustered with galera clusters on more than one host (multi host) that can be done by installing ubuntu and docker, swarm initialization, create overlay network, pull galera image, create cluster service, Prometheus and grafana installation and configuration, test integeration on database, and monitoring server. All cpu usage percentage from monitoring results show the percentage not reach 100% which means there are no overload and overworked.
Analysis of Speed and Connection When Accessing Information in Database Muhammad Guruh Ajinugroho; Tubagus Maulana Kusuma; Suryarini Widodo
J I M P - Jurnal Informatika Merdeka Pasuruan Vol 8, No 1 (2023): MARET 2023
Publisher : Fakultas Teknologi Informasi Universitas Merdeka Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51213/jimp.v8i1.783

Abstract

Animality Vetama is a pet store and clinic that has implemented an integrated management system which consist of several interconnected applications and a database across branches. Several branches complained about performances. Several factors was analyzed by the developer, resulting in a hypothesized that the problem was caused by connectivity issues on specific internet provider dubbed “provider X”. Said problem is suspected to lies within the TCP port because it only occurs when accessing the system but not when doing other things like browsing. Client application connects to the database using MySQL direct connection. To prove this case, a study using purposive sampling quota approach was proposed to determine what makes a problematic provider. This approach was then followed by a simulation for each criteria by doing a test connection to the database using the existing method and a proposed method using webservice. The simulation were focused on average connection durations as well as success and failed ratio. The result shown that in general, connecting to the database using webservice is a lot time faster than connecting client directly regardless of the provider. The success ratio is also increased significantly