Article Per Year (5 Year)
p-Index From 2020 - 2025
1.578
P-Index
This Author published in this journals
All Journal JURNAL SISTEM INFORMASI BISNIS JOIV : International Journal on Informatics Visualization Petra International journal of Business Studies (IJBS) INSIST (International Series on Interdisciplinary Research) Jurnal Teknologi Terpadu MULTINETICS Jurnal Abdi Insani BHAKTI PERSADA Jurnal Aplikasi IPTEKS (Journal of Applied Sciences and Technology) Jurnal Ilmu Kesehatan Immanuel
Maria Agustin
Fakultas Psikologi Universitas Merdeka Malang
Agriculture, Biological Sciences & Forestry Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Public Health Social Sciences Transportation Veterinary Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Penggunaan Jaringan Syaraf Tiruan Backpropagation Untuk Seleksi Penerimaan Mahasiswa Baru Pada Jurusan Teknik Komputer Di Politeknik Negeri Sriwijaya Agustin, Maria; Prahasto, Toni
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 2, No 2 (2012): Volume 2 Nomor 2 Tahun 2012
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (845.784 KB) | DOI: 10.21456/vol2iss2pp089-097

Abstract

Data availability of new studentsat the Polytechnic State Srivijaya high enough, so the need fora method to analyze the data. Artificial neuralnetwork  is  an  information  processing  system  that  has  characteristics  similar  to  biological  neural  networks,  neural  network  sare  used  topredict because ofthe ability of a good approach to ketidak linearan. This study  will design the software selection admission of new studentswith a  backpropagation  neural network  methods.    From the analysis of  backpropagation  neural networks  with  one  hidden layer  with  the number of neurons 50, 1000 iteration sand the activation functiont an sigproduce regression of 0.4822. Backpropagation neural network withtwo  hidden  layers  with  the  number  of  neurons  50,  4000  iterations  with  tansig  activation  function,  resulting  in  regression  of  0.7944. Backpropagation  neural networks  with 3  hidden layer  with  the number of neurons  35,  5000  iterations, resulting in  regression  of  0.8563. Based  on  the  results  of  this  analysis,  backpropagation  neural  networks  quite  effectively  used  for  selection  of  candidates  for  student admission.Keywords: Selection, Backpropagation, Regression
Do Value Added Intellectual Coefficient and Corporate Governance Contribute to Firm's Economic Value Added Hatane, Saarce Elsye; Agustin, Maria; Kana, Vera Radja; Dautrey, Jean Marc
Petra International Journal of Business Studies Vol 2 No 2 (2019): DECEMBER 2019
Publisher : Master of Management Study Program, Faculty of Business and Economics - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/ijbs.2.2.96-108

Abstract

This study is about examining the influence of Intellectual Capital and Corporate Governance to EVA. Data used in this study were collected from a sample of 121 consumer goods companies in Indonesia and Malaysia from 2010 to 2017. Panel data multiple regression was performed to examine the research framework. The intellectual capital was measured by VAIC value, while the corporate governance was explained by the audit committee, remuneration board, and auditor quality and tenure. This study found that HCE, SCE, audit committee gender, remuneration size and remuneration gender had no effect on EVA in both Malaysian and Indonesian companies. In contrast, the audit committee size was found to affect the EVA of the companies in both countries. The CEE affected the company value of Malaysian companies while it had no effect on Indonesian companies. Audit quality and audit tenure had a positive effect only on Malaysian companies and none on Indonesian companies. This study used limited variables and a narrow business sector, thus the future research may expand the research model for other types of industries and apply the model in other countries.
Sistem Pengenalan Benih Padi menggunakan Metode Light Convolutional Neural Network pada Raspberry PI 4 B Hermawan, Indra; Arnaldy , Defiana; Agustin, Maria; Widyono, M. Farishanif; Nathanael, David; Mulyani, Meutia Tri
Jurnal Teknologi Terpadu Vol. 7 No. 2: December, 2021
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v7i2.443

Abstract

Recently, Deep learning methods with Convolutional Neural Networks (CNNs) have been widely used for image classification tasks. CNN has an unrivaled advantage in extracting discriminatory image features. However, many existing CNN-based methods are designed to go deeper and more significant with more complex layers that make them challenging to implement on mobile devices or real-time devices that use microcontrollers like raspberry pi, Arduino, and immediately. This is overcome by using a Light Convolutional Neural Network (LCNN), so it needs to experiment to test the difference in LCNN performance on a personal computer and a raspberry pi four microcontrollers with a Raspbian operating system. Experiments will be carried out using several performance measures: accuracy, F-1 score, recall, precision, and time to get performance results from deep learning. As such, the results and model architecture will confirm performance differences across individual devices and show how the model performs on resource-constrained or real-time devices. Tests show that the performance of the raspberry pi, which is a tool with limited resources, does not affect the quality of image recognition but affects the recognition processing time because the raspberry pi requires a longer processing time to perform one data or photo recognition process. This will accumulate the time required for processing many data, so it can conclude that the raspberry pi and tools with limited resources are not very practical for conducting recognition training and carrying out a recognition process that contains a lot of data or photos in one process.
Sistem Pengenalan Benih Padi menggunakan Metode Light Convolutional Neural Network pada Raspberry PI 4 B Hermawan, Indra; Arnaldy , Defiana; Agustin, Maria; Widyono, M. Farishanif; Nathanael, David; Mulyani, Meutia Tri
Jurnal Teknologi Terpadu Vol 7 No 2: Desember, 2021
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v7i2.443

Abstract

Recently, Deep learning methods with Convolutional Neural Networks (CNNs) have been widely used for image classification tasks. CNN has an unrivaled advantage in extracting discriminatory image features. However, many existing CNN-based methods are designed to go deeper and more significant with more complex layers that make them challenging to implement on mobile devices or real-time devices that use microcontrollers like raspberry pi, Arduino, and immediately. This is overcome by using a Light Convolutional Neural Network (LCNN), so it needs to experiment to test the difference in LCNN performance on a personal computer and a raspberry pi four microcontrollers with a Raspbian operating system. Experiments will be carried out using several performance measures: accuracy, F-1 score, recall, precision, and time to get performance results from deep learning. As such, the results and model architecture will confirm performance differences across individual devices and show how the model performs on resource-constrained or real-time devices. Tests show that the performance of the raspberry pi, which is a tool with limited resources, does not affect the quality of image recognition but affects the recognition processing time because the raspberry pi requires a longer processing time to perform one data or photo recognition process. This will accumulate the time required for processing many data, so it can conclude that the raspberry pi and tools with limited resources are not very practical for conducting recognition training and carrying out a recognition process that contains a lot of data or photos in one process.
Flood Early Warning System with Informational Technology for Reducing Risk of Loss in Sustainability of City Supani, Ahyar; Agustin, Maria; Andriani, Yuli
International Series on Interdisciplinary Science and Technology Vol. 4 No. 2 (2019)
Publisher : Universitas Lampung

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

Abstract

Palembang is divided by Musi-river consisting of two parts of city called Hulu and Hilir. it has a height of Musi tide surface about 0.7 m to 2.2 m and average high rainfall 101.48 mm/hrs in a year so that it always happen flood every year. In tackling flood, Palembang goverment has did rehabilition of canals, river dredging, creation of retention ponds, demolition of illegal building on the banks of river and the extension services provided to the public about the cleanliness of the river. In addition in this study, it has been also applied infomational technology to tackle the flood in Palembang as early warning system. The flood early warning system that was built for measuring rainfall and water level, predicting flood condition using fuzzy logic and conveying data containing rainfall, water level and flood condition via short message service to people. In test, it was succesfull measuring water level up to 5 metres and rainfall  up to 380 ml/minutes and more, forecasting the flood conditions namely standby 2, standby 1 and flood. Hence, it was also successfull sending short message service containing rainfall, water level and flood conditions automatically. In addition, the increase of rainfall caused the increase of water level and change of flood condition. Meanwhile, it was based on study that the flood early warning system was the key element of disaster risk reduction. From the results, it can be concluded that flood early warning system resulted on flood for 5.0 m, 320.31-418.33 ml/minutes, S1 for 4.0-5.0 m, 243.33-647.5 ml/minutes, S2 for less than 3.6 m, 414.17 ml/minutes. It succeeded in sending data of rainfall, water level and flood as much as 15 times to community's cellulerphone automatically so that it is reducing risk of loss againts flood and maintaining sustainability of city.
Hubungan Pola Asuh Orang Tua dengan Perkembangan Anak PAUD di Kecamatan Samalantan Herlina, Herlina; Agustin, Maria
Jurnal Ilmu Kesehatan Immanuel Vol. 15 No. 1 (2021): Jurnal Ilmu Kesehatan Immanuel
Publisher : Institut Kesehatan Immanuel

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36051/jiki.v15i1.152

Abstract

Perkembangan secara optimal bagi anak jika anak mendapatkan pola asuh yang baik. Factor lingkungan dan interaksi antara anak dengan orang tua dapat mempengaruhi perkembangan anak yang sesuai dengan kebutuhan serta usianya. Desain korelasi, dilakukan terhadap 35 orang tua dan anak PAUD serta teknik pengambilan sampel dilakukan secara total sampling. Pengumpulan data dilakukan dengan menyebarkan kuesioner KPSP (Kuesioner Pra Skrining Perkembangan) untuk mengukur kemapuan perkembangan anak, sedangkan kuisioner pola asuh orang tua merupakan kuisioner dari penelitian sebelumnya yang telah dilakukan uji validitas dan realibilitas. Analiasis univariat dan bivariat dilakukan pada penelitian ini serta menggunakan uji pearson untuk melihat hububungan atau korelasinya. Penelitian dilakukan pada bulan November sampai Desember Tahun 2019 di Wilayah Kerja Puskesmas Samalantan. Terdapat hubungan bermakna antara pola asuh orang tua dengan perkembangan anak usia PAUD dengan nilai p value 0,003. Saran dari penelitian ini terkait perkembangan anak di wilayah kerja Puskesmas dapat menjadi informasi khusus bagi petugas Kesehatan, yang dapat menjadi informasi bagi petugas Kesehatan
Pemanfaatan Aplikasi Augmented Reality dan Teknologi Mobile sebagai Media Edukasi untuk Sekolah Dasar di Kelurahan Kebon Pedes Bogor Liliana, Dewi Yanti; Nalawati, Rizki Elisa; Marcheta, Noorlela; Agustin, Maria; Huzaifa, Malisa
Bhakti Persada Jurnal Aplikasi IPTEKS Vol. 9 No. 1 (2023): Bhakti Persada Jurnal Aplikasi IPTEKS
Publisher : Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31940/bp.v9i1.1-9

Abstract

Augmented Reality (AR) merupakan aplikasi penggabungan dunia nyata dengan dunia maya dalam bentuk tiga dimensi yang diproyeksikan dalam sebuah lingkungan nyata dalam waktu yang bersamaan atau dapat juga disebut sebagai realitas tertambah dan sering diterapkan dalam sebuah game. Dengan menggunakan AR sebagai salah satu alternatif media pembelajaran, diharapkan dalam sebuah kegiatan pembelajaran dapat lebih menarik bagi siswa. Manfaat lain yang diperoleh adalah media pembelajaran yang lebih maju dan memanfaatkan perkembangan teknologi mobile melalui smart phone. Melalui AR, maka dapat menjadi salah satu solusi untuk mengatasi modul ataupun trainer yang cukup mahal dan tidak mampu dibeli oleh sekolah. Selain itu, siswa juga tetap dapat melakukan praktikum dengan melihat barang seperti aslinya dalam bentuk virtual. Pengembangan AR sebagai media edukasi dapat diterapkan pada SD di Kelurahan Kebon Pedes, Bogor dimana dapat dijadikan motivasi dalam peningkatan minat belajar siswa. SDN Pondok Rumput dan SDN Kebon Pedes 7 merupakan sekolah dasar negeri yang ada di Kota Bogor yang sudah terakreditasi dan menerapkan IPTEK sebagai salah satu media yang mendukung proses pembelajarannnya, namun terbatas pada pemberian materi berbentuk teks dan video-video tutorial yang didapat dari youtube atau sumber lainnya. Hal tersebut menjadikan para guru harus menyesuaikan materi pembelajaran dengan ketersediaan materi yang ada di internet. Padahal seharusnya media pembelajaran sejalan dengan silabus pembelajaran di sekolah. Selain itu, minat peserta didik di masa pandemi ini semakin menurun karena antusiasme terhadap materi-materi yang umumnya berbentuk teks dirasa membosankan. Oleh karena itu, dibutuhkan teknologi yang dapat menjadi solusi masalah tersebut, salah satunya adalah penerapan konsep AR.
Pemantauan Dan Pengendalian Pintu Air Berbasis Komunikasi Radio Full Duplex Dengan Algoritma Decision Tree Kurniawan, Asep; Hermawan, Indra; Agustin, Maria
MULTINETICS Vol. 9 No. 1 (2023): MULTINETICS Mei (2023)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v9i1.5156

Abstract

Provision, management and distribution of water on agricultural land is one of the important factors that affect the quantity and quality of agricultural products. An irrigation canal technology is needed that is able to flow through all agricultural land according to the water needs of each land. Smart irrigation systems can be a solution to this problem. The smart irrigation technology that was previously developed has several limitations such as the length of time data transmission takes to reach the client, sensor devices in the field must take turns sending data and receiving data resulting in data not being sent or not being read properly, besides that the system that has been developed previously depends on to one factor, namely the water level to determine the degree of openness of the floodgates. In this research a fast sensor to cloud communication system is designed using websocket technology. This system is also designed to send and receive data simultaneously using full duplect communication technology. As well as using artificial intelligence with the decision tree algorithm to regulate the openness of the floodgates based on the water requirement for the rice fields, the water level in the irrigation canals and the speed of the water flow. This research produced a prototype of an intelligent irrigation system that can send data to clients with an average time of 417ms, the system is also able to handle 500 clients that are connected directly to the server. The system can also send and receive data simultaneously with a difference in time when data is received at the sensor node or at the central node which can reach 0ms. This prototype also succeeded in making an artificial intelligence system that is accurate, fast and real-life. This artificial intelligence can handle 500 requests simultaneously with an execution time of 544ms.
IMPLEMENTASI ALGORITMA DECISION TREE DENGAN FITUR SELEKSI WEIGHT BY INFORMATION GAIN Ali, Euis Oktavianti; Agustin, Maria; Sari, Risna
MULTINETICS Vol. 9 No. 2 (2023): MULTINETICS Nopember (2023)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v9i2.5715

Abstract

This paper aims to apply the weight selection feature by considering the Gain Ratio value in the decision tree algorithm in classifying student academic scores. We determine the feature selection from the gain ratio based on the split value information to reduce the feature's (attribute) bias value. The highest Gain Ratio' value will be the root of the branching in the tree in which becomes a determining feature (attribute) of student graduation. We use 82 data which are divide into two classes called a pass and a not pass. From the data, we know that the attribute ip smt 7 got the highest gain ratio value with 0.581. On the other hand, the multimedia introduction attribute got the lowest gain ratio value with 0.070. The calculation model using cross-validation with a value of k = 5 resulted in optimal performance. The resulting accuracy is 79.19% and AUC 0.778 using the decision tree algorithm. The threshold value of the gain ratio used is 1.00 so that four attributes are not used in this paper. feature selection using weights with information gain ratio will select the attribute selection process to be built in the model.
PEMANFAATAN TEKNOLOGI INFORMASI DI BANK SAMPAH KAMPUNG RAMAH LINGKUNGAN KAMPOENG BERSERI, KECAMATAN CILEUNGSI, KABUPATEN BOGOR Matin, Iik Muhamad Malik; Iswara, Ratna Widya; Kadarwati, Dinda; Oktivasari, Prihatin; Zain, Ayu Rosyida; Agustin, Maria; Arnaldy, Defiana; Hermawan, Indra
Jurnal Abdi Insani Vol 11 No 2 (2024): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v11i2.1285

Abstract

Program bank sampah di KRL Kampoeng Berseri merupakan upaya pemanfaatan sampah sebagai nilai ekonomi. Namun pengelolaan tabungan yang masih dilakukan secara manual sehingga petugas dirasa sulit ketika warga tidak membawa catatan. Akibatnya, tabungan yang terkumpul diambil saat itu juga sehingga warga disekitar kurang mendapatkan manfaat. Hal ini menyebabkan antusias nasabah bank sampah di Kampoeng Berseri menurun sehingga program bank sampah tidak berjalan secara optimal. sehingga perlu diterapkan teknologi informasi. Untuk itu, diterapkan teknologi informasi untuk pengelolaan tabungan sampah dan memberikan pelatihan teknologi informasi pengelolaan tabungan sampah pada pengurus bank sampah sebagai pengelola dan warga lingkungan KRL Kampoeng Berseri. Kegiatan Pengabdian ini dimulai dari persiapan dengan identifikasi masalah, menentukan solusi dan pengembangan aplikasi. Kemudian pelaksanaan yang teridri dari hibah dan pelatihan pada mengurus bank Sampah dan warga sekitar desa Limus Nunggal. Terakhir, evaluasi untuk mengukur hasil kegiatan pengabdian masyakarat. Berdasarkan hasil survei menunjukan pelaksanaan pengabdian dapat menigkatkan ketertarikan warga dalam menggunakan aplikasi. Selain itu warga juga menyatakan kegiatan pengabdian kepada masyarakat ini memiliki manfaat yang baik dan dapat diterapkan dalam kehidupan sehari-hari dan setuju untuk melanjutkan program pengabdian ini dimasa yang akan dating. Program pengabdian masyarakat berhasil memperbaiki pengelolaan tabungan sampah dengan teknologi informasi dan meningkatkan partisipasi serta dukungan warga untuk program tersebut.
Co-Authors Ali, Euis Oktavianti Aprilia, Puput Dwi Asep Kurniawan Asep Taufik Muharram Dautrey, Jean Marc Defiana Arnaldy Dewi Yanti Liliana Herlina Herlina Hermayanti, Elva HR, Des Fitria Putri Huzaifa, Malisa INDRA HERMAWAN Kadarwati, Dinda Kana, Vera Radja Marcheta, Noorlela Matin, Iik Muhamad Malik Mulyani, Meutia Tri Munawaroh Munawaroh Nalawati, Rizki Elisa Nathanael, David Prihatin Oktivasari Putri, Dini Marsela Ratna Widya Iswara, Ratna Widya Saarce Elsye Hatane Sari, Risna Sukma, Yunila Supani, Ahyar Susanti Susanti Toni Prahasto Warsuta, Bambang Widyono, M. Farishanif Yuli Andriani Zain, Ayu Rosyida