Article Per Year (5 Year)
p-Index From 2021 - 2026
4.006
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) International Journal of Public Health Science (IJPHS) Jurnal Pendidikan Vokasi Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Natural A Jurnal POINTER Jurnal Pendidikan: Teori, Penelitian, dan Pengembangan Jurnal Teknik Otomotif Kajian Keilmuan dan Pengajaran Jurnal Preventia Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Jurnal Informatika dan Multimedia Indonesian Journal of Electrical Engineering and Computer Science Jurnal Pengabdian, Pendidikan dan Teknologi Jurnal Graha Pengabdian Prosiding Seminar Nasional Pengabdian Kepada Masyarakat Abdimas Indonesian Journal Prosiding Seminar Kesehatan Nasional Sexophone National Journal of Occupational Health and Safety
Marji Marji
Fakultas Ilmu Komputer, Universitas Brawijaya
Religion Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Public Health Social Sciences Other

Published : 97 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 97 Documents
Search

 5   6   7   8   9 
Pelatihan Feedforward Neural Network dengan Particle Swarm Optimization dalam Memprediksi Pertumbuhan Penduduk Kota Malang Andini Agustina; Muhammad Tanzil Furqon; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 10 (2019): Oktober 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (605.038 KB)

Abstract

Indonesia is the fourth most populous country in the world. With a large population, Indonesia is not immune to population problems. This happens because the rate of population growth is not accompanied by the provision of clothing, food, and shelter. In other words, the amount of population growth is not balanced with the availability of natural resources, services, and existing facilities. Therefore, predicting population growth is expected to help the government to overcome population problems. This paper will be using Feedforward Neural Network trained by Particle Swarm Optimization (PSO). PSO algorithm is considered to be able to overcome the weaknesses of the Backpropagation algorithm in training networks. In this study, the predicted error rate is calculated using Mean Average Percentage Error (MAPE). The smallest MAPE results obtained were 0,1599% using 6 input neurons, 4 hidden neurons, 1 output neurons in the network architecture, and the dataset used is the population of Malang City from January 2009 to June 2019. The MAPE results showed that PSO is able to train Feedforward Neural Network to predict the population growth of Malang City.
Pemilihan Fitur dengan Information Gain untuk Klasifikasi Penyakit Gagal Ginjal menggunakan Metode Modified K-Nearest Neighbor (MKNN) Muhammad Ramanda Hasibuan; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 11 (2019): November 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (495.767 KB)

Abstract

Kidney has an important role in human body. Decreased kidney function can result in chronic kidney disease. Detection of chronic kidney disease using medical data that use features as factors of kidney failure, this data can be processed and build an intelligent system from it, that can help detect kidney failure. In the process of chronic kidney disease data classification method can be used. Modified K-Nearest Neighbor (MKNN) is one of classification method. But the weakness of the MKNN method is in the process using all available features, so it can cause an error detection because there are some features that are less relevant. Therefore in this research, a feature selection method is added, namely Information Gain, Information Gain method calculates the Gain value for each feature, features with large Gain values ​​will be better used for the classification process. On the results of testing variations numbers of features after selection and the effect of variations of K values, produces the highest accuracy value on 4 features with K values = 2 and 4 produces an accuracy value of 97,7% and on 6 features with K values = 2 and 4 produces an accuracy value of 97,7%. For the system testing using Information Gain produces an accuracy value of 96,8% and those not using Information Gain produce an accuracy value of 79,9%.
Seleksi Fitur dengan Information Gain pada Identifikasi Jenis Attention Deficit Hyperactivity Disorder Menggunakan Metode Modified K-Nearest Neighbor Muhammad Hafidzullah; Sutrisno Sutrisno; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 11 (2019): November 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (363.05 KB)

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) is a disorder that usually occurs in early childhood. In general there are three types of behavior associated with this disorder, namely: inattentiveness, impulsiveness, and hyperactivity. ADHD mental illness can only be recognized through changes in patient behavior. In this study, the data used using 45 features, where the number of features can affect the performance and accuracy of the classification method. Feature selection aims to reduce features that are of equal importance to make classification algorithms easier to operate more quickly and effectively so as to produce better accuracy. The method to be used for the selection of features is the Information Gain method. The use of the Information Gain method in this case is to select the best features that have relevance to the related data. These features are selected based on the magnitude of the gain value obtained, where the greater the gain value, the more relevant the feature is with the related data. The best average accuracy results obtained from this system are obtained in the second test scenario with the highest average accuracy value of 88% obtained at k = 37 and k = 42 and the number of features 36 and 41, and at k = 1 in testing without using Information Gain. These results indicate the use of the Information Gain feature selection method in this case has a fairly good accuracy value.
Pencarian Terjemahan Hadits Shahih Muslim menggunakan Metode BM-25 Bagus Abdan Aziz Fahriansyah; Indriati Indriati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 11 (2019): November 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (376.416 KB)

Abstract

Hadits is second reference to moslem people. Furthermore function of hadits is explanation from alquran . but many common people difficult to find some topic of hadits because its amount very much and not everyone can memorize it. Actually paper book or electronic book can't give feedback which relevant first. In computer science there's subject that study about extracting words become a new information that we need or to know similarity a phrase with certain document namely text mining. writer wants implement one of text mining technique namely BM-25 in searching of hadits shahih moeslem . and writer wants to know how effective BM-25 algorithm for handle problem that writer give. From research that using hadits shahih moeslem as its data. Writer wants testing with five different queries and made variate of value of k and b variable that can optimize the result of query dan k variable optimum at q1=0.75 ; q2=0.5 ; q3=0.75 ; q4=0.75 ; q5=0.5 and b variable optimum at q1=0.1.2 ; q2=1.2 ; q3=1.2; q4=1.2; q5=1.2 and precision @ k that gets average precision value p@10=70%,p@20=54%,p@30=42%.
Klasifikasi Emosi pada Komentar YouTube Menggunakan Metode Modified K-Nearest Neighbor (MKNN) dengan BM25 dan Seleksi Fitur Chi-Square Candra Ardiansyah; Indriati Indriati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 4 (2020): April 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (400.266 KB)

Abstract

YouTube is the world's largest online video social media that is used to display various videos created by users and companies in the field of media content. Every video contained in YouTube can be done by giving a text type comment in the comments column of the video that has been watched. The large number of comments causes the content creator (video maker) to spend enough time to understand every emotion in the existing comment. After consideration of the solution used to resolve the problem, the authors chose to use the Modified K-Nearest Neighbor (MKNN) classification method with BM25 and Chi-Square feature selection. The test used is 5-fold cross validation to find the best k value which is then used for testing the Chi-Square feature selection. In Chi-Square test the data used is the best fold data based on the highest f-measure value in the 5-fold cross validation test. The results obtained are the maximum accuracy, precision, recall, f-measure values ​​achieved when k is 30, 72,82%, 72,94%, 72,26%, and 72,59%. While the Chi-Square test on the 4th fold of data the best number of terms used is 40% and 50%, with the value of accuracy, precision, recall, f-measure is 80,56%, 80,37%, 81,61 % and 80,98%.
Analisis Sentimen Penggunaan Tol Trans Jawa Periode Mudik Lebaran 2019 dengan Metode K-Nearest Neighbor dan Seleksi Fitur Information Gain Ahmad Fauzan Rahman; Indriati Indriati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 6 (2020): Juni 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

One of the facilities provided by the government to speed up travel time is the toll road. Toll roads can also be referred to as highways that are connected from one city to another for four or more wheeled vehicles. In December 2018, the Trans Java Toll Road officially connected the two major cities in Indonesia, Jakarta and Surabaya. The new Trans Java Toll Road can be used in the period of eid 2019 will generate various opinions from its users. Many people in Indonesia use social media as one of the media to express their opinions. Thus this study tries to analyze public opinion on social media to be classified into two classes, namely positive and negative classes. The method used in this research is K-Nearest Neighbor with Information Gain Feature Selection. The classification process consists of preprocessing text including data cleansing, case folding, stop word removal, stemming and tokenization, term wighting with tf-idf, feature selection using Information Gain and classification using K-Nearest Neighbor. Tests in this study using confusion matrix produce accuracy of 85%, precision of 85%, recall of 100%, and f-measure of 91.89%.
Prediksi Pertumbuhan Jumlah Penduduk Kota Malang menggunakan Metode Average-based Fuzzy Time Series Pricielya Alviyonita; Muhammad Tanzil Furqon; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 7 (2020): Juli 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

The population growth in Indonesia continues to increase every year, making Indonesia as the 4th country with the largest population in the world. High population growth will greatly affect several aspects, such as the economy, the quality of people's lives, health and development planning. Prediction of population growth is needed to anticipate the negative affects of population growth which is expected to assist the government in making future urban planning plans. The Population and Civil Registry Office also needs these predictions to make a draft budget of needs such as e-KTP blanks, birth certificates, and others. Average-based fuzzy time series is one method of forecasting the results of the development of fuzzy time series. The fuzzy time series method based on average is able to determine the length of the effective interval so that it can produce predictions with a low error rate. By using time series data, the population of Malang City per month with a total of 123 data, this study implements the average-based fuzzy times series method to predict population growth. Based on testing in this study it can be concluded that the amount of training data has an influence on the value of MAPE produced, but the use of training data that is increasingly not always in line with the lower error value and the lowest Mean Absolute Percentage Error (MAPE) value of 0.02810%.
Pengembangan Sistem Informasi E-report dan Monitoring Laporan Bulanan(LB1) Penyakit Berbasis Web (Studi Kasus: Puskesmas Dinoyo) Muzdalifah Yully Ayu; Adam Hendra Brata; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 8 (2020): Agustus 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Monthly report (LB1) is disease data report containing ICD-10 data code, distribution of disease cases according to age group, and new cases or old cases. The report of disease data has done routine in every month, quarter, and annual report. The problem of Public Health Center Dinoyo in recording and reporting are still manual or conventional way to process, maintain, and deliver the report. The average amount of disease data at the Dinoyo Public Health Center was recorded 2000 - 3000 in every month by use manual system and it caused the record taking long time process, incomplete data so that it affected on the accuracy of LB1. Furthermore, late delivery of the report made the Health Office of Malang City could not monitoring, evaluating, and have difficulty to know the public health center's around Indonesia which not sent the report. Based on these problems is built the system based on website with waterfall model development, Codeigniter framework, and PHP programming language. The result is information system can be used for managing medical records, monthly report (LB1), and monitoring the monthly report (LB1). Based on the testing that has been done produce 100% valid value on unit testing, integration, and validation which shows that the system function already fulfilling the needs. The result of usability test is using usability scale system method obtained the score up to 77 which could be concluded the system has been acceptable and has provided user convinience.
Klasifikasi Pengaduan Pelayanan Dispendukcapil Kota Malang Menggunakan Metode Naive Bayes dan Seleksi Fitur Glasgow-II Choirul Anam; Indriati Indriati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 9 (2020): September 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

The service of each service will never escape from imperfections including the Population and Civil Registry Service (DISPENDUKCAPIL). Service improvement aims to create a sense of comfort and increase satisfaction and trust towards DISPENDUKCAPIL employees for the residents of Malang City. The categories or types of complaints that often go into DISPENDUKCAPIL are complaints on issues of Identity Card (KTP), Family Card (KK), deed (birth, death, and marriage), moving or coming letters. The categorization of various types of service complaints that have been sent to DISPENDUKCAPIL can be done using classification. Classification of service complaints is done using the Naive Bayes method and the Glasgow-II Feature Selection. The process starts from text preprocessing, term weighting, Feature Selection, Naive Bayes training, and Naive Bayes testing. Based on the results of tests conducted using the Naive Bayes method and the Glasgow-II Feature Selection, values ​​of accuracy, precision, recall were 87.5%, 85.1%, 88.075% and an average accuracy of 81.25%. Whereas by using the Naive Bayes method without the Glasgow-II Feature Selection the accuracy, precision, recall values ​​were 84.375%, 83.1%, 81.5625% and the average accuracy was 79.99%. So, that the use of the Naive Bayes method and the Glasgow-II Feature Selection are able to provide better results.
Klasifikasi Jenis Kelamin Pengguna Twitter dengan menggunakan Metode BM25 dan K-Nearest Neighbor (KNN) Annisa Selma Zakia; Indriati Indriati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 10 (2020): Oktober 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Twitter is a microblogging social network where one can write up to 280 characters in one tweet. Indonesia emerged as the fifth largest country in terms of Twitter users. Seeing how many Twitter users in Indonesia can certainly be used by companies in creating new business strategies to serve their customers, but some social account users objection if they have to reveal their identities. These problems can be solved by developing a system for classifying based on tweets from users, this system is certainly useful because it saves time. The system is designed using the BM25 method for calculating similarities between documents and KNN for classifying data. the system used 1000 documents, then the document is tested with K-Fold Cross Validation using K = 10 so that 900 training documents and 100 testing documents are obtained on each K. The next test is about neighbor values, neighbor values used are 1, 3, 5, 7, 10, 20, 30, 40 and 50, the test results show that the optimal neighbor value is k = 3. At k = 3 the value of accuracy, precision, recall and F-Measure of the average Cross Validation 10 fold are 68.6%, 67.63%, 71.52% and 69.34%.
Co-Authors Achmad Burhannudin Adam Hendra Brata Adhikari, Basanta Prasad Adhiyatma Mugiprakoso Afifah, Nadiyah Hanun Agi Putra Kharisma Agung Kurniawan Agustian, Moch. Alfredo Barta Ahmad Fauzan Rahman Ahmad, Baihaqi Aldy Satria Andika Harlan Andini Agustina Anita Sulistyorini Annisa Selma Zakia Ardhimas Ilham Bagus Pranata Arifin, Maulana Muhamad Asti Melani Astari Atika Anggraeni Audi Nuermey Hanafi Bagus Abdan Aziz Fahriansyah Bahruddin El Hayat Baihaq, Firda Barlian, Salwa Isna Bayu Rahayudi Bayu Septyo Adi Budi Darma Setiawan Budi Darma Stiawan Cahyo Adi Prasojo Candra Ardiansyah Choirul Anam Cindy Puspita Sari Cindy Rizki Amalya Dani Irawan Daud, Nathan Dea Widya Hutami Dewi Yanti Liliana Dian Eka R Dian Eka Ratnawati Djoko Kustono Dwi Yana Wijaya Dyva Agna Fauzan Edy Santoso Edy Santoso Edy Santoso Endang Wahyu Handamari Erwin Komara Mindarta Fanani, Erianto Fatih Kamala Nurika Gilang Ramadhan Gustian Ri'pi Hadi, Moch. Sholihul Handoyo, Samingun Hary Suswanto Hasan Ismail Ilham Romadhona Imam Cholisoddin Imam Cholissodin Imam Muda Nauri Imran Imran Indriati Indriati Indriati Indriati Issa Arwani Istiana Rachmi Istiqomah, Mutiara Titian Januar Dwi Amanda Jeffrey Simanjuntak Kenty Wantri A Kohei Arai Kurnianingtyas, Diva Lailatul Fitriah Lailil Muflikah Lailil Muflikhah Lailil Muflikkah Laily Putri Rizby Laksono Trisnantoro Leni Istikomah Liana Shanty Wato Wele Keaan Lilik Zuhriyah Lilis Damayanti Luthfi Faisal Rafiq M Chandra Cahyo Utomo M. Alfian Mizar Made Bela Pramesthi Putri Mahmudi, Wayan Firdaus Maududi, Affan Al Michael Adrian Halomoan Mochammad Pratama Viadi Mountaz, Lotu Muchammad Harly Muhamad Altof Muhamad Hilmi Hibatullah Muhammad Fakhri Mubarak Muhammad Hafidzullah Muhammad Indra Harjunada Muhammad Ramanda Hasibuan Muhammad Rizkan Arif Muhammad Robby Dharmawan Muhammad Tanzil Furqon Muhammad, Naufalsyah Falah Muzdalifah Yully Ayu Nonny Aji Sunaryo Nurul Hidaya Nurul Hidayat Nurul Hidayat Okvio Akbar Karuniawan P. P. S, Gladis Viona Pangestu, Wiyan Dwi Panji Prasuci Saputra Paryono Permadani , Anda Permatasari, Adelia Pratitha Vidya Sakta Prawidiastri, Firnadila Pricielya Alviyonita Rafely Chandra Rizkilillah Ratih Kartika Dewi Ratna Candra Ika Razaq, Hilal Nurfadhilah Retiana Fadma Pertiwi Sinaga Revinda Bertananda Riana Nurmalasari Ricky Irfandi Ricky Marten Sahalatua Tumangger Rizqi Addin Arfiansyah Rosalinda, Nadia Ryan Mahaputra Krishnanda Sabrina Hanifah Sari, Resti Novita Shinta Anggun Larasati Sri Wahyuni Sri Widyarti Sumarli Sumarli, Sumarli Supraptoa Supraptoa Supriyadi Supriyadi Sutrisno Sutrisno Swandy Raja Manaek Pakpahan Syarif Suhartadi Tahtri Nadia Utami Tawang Wulandari Tika Dwi Tama Usman Adi Nugroho Wayan Firdaus Mahmudy Wulandadi, Retno Yamlikho Karma Yayuk Wiwin Nur Fitriya Yuita Arum Sari Yusufrakadhinata, Muhammad Zulianur Khaqiqiyah