Claim Missing Document
Check
Articles

Gender Classification on Social Media Messages Using fastText Feature Extraction and Long Short-Term Memory Sa’diah, Halimatus; Faisal, Mohammad Reza; Farmadi, Andi; Abadi, Friska; Indriani, Fatma; Alkaff, Muhammad; Abdullayev, Vugar
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.407

Abstract

Currently, social media is used as a platform for interacting with many people and has also become a source of information for social media researchers or analysts. Twitter is one of the platforms commonly used for research purposes, especially for data from tweets written by individuals. However, on Twitter, user information such as gender is not explicitly displayed in the account profile, yet there is a plethora of unstructured information containing such data, often unnoticed. This research aims to classify gender based on tweet data and account description data and determine the accuracy of gender classification using machine learning methods. The method used involves FastText as a feature extraction method and LSTM as a classification method based on the extracted data, while to achieve the most accurate results, classification is performed on tweet data, account description data, and a combination of both. This research shows that LSTM classification on account description data and combined data obtained an accuracy of 70%, while tweet data classification achieved 69%. This research concludes that FastText feature extraction with LSTM classification can be implemented for gender classification. However, there is no significant difference in accuracy results for each dataset. However, this research demonstrates that both methods can work well together and yield optimal results.
Sistem Informasi Jadwal Siaran Studio 5 Universitas Muhammadiyah Banjarmasin Ansari, Rudy; Alkaff, Muhammad
Jurnal Teknologi Berkelanjutan Vol 12 No 2 (2023): Vol 12 No. 02
Publisher : Lambung Mangkurat University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtb.v12i2.253

Abstract

Studio 5 Muhammadiyah University Banjarmasin, there are 2 (two) employees, the scheduling process at studio 5 is carried out by sending a letter to the resource person concerned. Scheduling is also done by taking notes on the whiteboard in the studio5. Then when the filming process, video editing has been carried out, then the video has been uploaded to the YouTube channel, the notes on the whiteboard are deleted or cleaned. The aim of making this schedule is so that all schedules are recorded well and can be displayed visually. In this system, an application is created that can be displayed on the television screen at the Muhammadiyah University of Banjarmasin, where before this application was created, it was still written on a blackboard for the schedule and implementation of events. This information system was created based on the Software Development Life Cycle (SDLC) method, where the stages of the method include system analysis by directly conducting interviews with related parties, system design using Unified Modeling Language (UML) design for the diagram stages, namely Usecase Diagram, Sequence Diagram, Activity Diagram, then for the database using MySql Workbench, implementation, testing and maintenance for implementation using Laravel tools. So that with these stages it is possible to clearly build an information system for broadcast schedules for Studio 5 of Muhammadiyah University, Banjarmasin. The Studio 5 broadcast schedule information system has several features, starting from the broadcast proposal feature from users and the broadcast proposal feature from admin, the master data feature which includes section data, editor data, cameraman data, and moderator data which can be managed by the admin, a validation feature where broadcast suggestions from users can be scheduled because they have been validated by the admin, and a print or report feature where in this feature the data contained in the broadcast data is printed in excel format.
Rancang Bangun Sistem Identifikasi Arus Lalu Lintas pada Simpang Tiga Menggunakan Database NoSQL Muhammad Alkaff; Iphan Fitrian Radam; Sugiantoro Sugiantoro
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 2 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i2.2567

Abstract

T-junction is one of the types of intersections that often results in congestion, and long queues. Therefore, it is necessary to identify the traffic flow to determine vehicles per hour, Passenger Car Unit (PCU) per hour, traffic fluctuations, vehicle composition, trip composition and traffic flow at peak hours at T-junction. The process of identifying traffic flow is complex and involves many variables. The process is currently still using Microsoft Excel which requires a lot of time and energy and allows for human error. Therefore, the purpose of this research is to design and build a traffic flow identification system at T-junction using NoSQL database. NoSQL is useful for complex data because NoSQL eliminates repetitive data. The results of this research are the traffic flow identification system at T-junction using NoSQL database which consists of vehicles per hour, PCU per hour, traffic fluctuations, vehicle composition, trip composition, and traffic flow during peak hours.
PENINGKATAN MINAT BERWIRAUSAHA MAHASISWA UNIVERSITAS ISLAM INTERNASIONAL DARULLUGHAH WADDA'WAH Alkaff, Muhammad
Nidhomiyyah: Jurnal Manajemen Pendidikan Islam Vol. 4 No. 2 (2023): July
Publisher : Program Pascasarjana Institut Agama Islam Darullughah Wadda'wah Bangil Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38073/nidhomiyyah.v4i2.1025

Abstract

The problem of the growth of young enterpreneurs in Indonesia is still a polemic that has not been clearly defined. Therefore, it is necessary to prepare potential next generation in the field pf entrepreneurship. In this preparatory agenda, entrepreneurship education in tertiary institutions will play a crucial role, apart from the influence of classmates in fostering student interest in entrepreneurship. This research method uses a quantitative approach with a casual perspective. The population in this study were all student of Darullughah Wadda’wah International Islamic University class of 2020/2021, totaling 951 students from 8 study programs. While the sampling technique in this study used the simple random sampling method, the number of wich was calculated using the slovin formula so that the number of samples was 100 respondents. The analysis technique used is structural equation modeling with AMOS program tools. The research results obtained in this study are (1) entrepreneurship education has a significant effect on the interest in entrepreneurship; (2) entrepreneurship education has a significant effect on social media influence of classmate; (3) social influence of classmate influences interest in entrepreneurship.
Multimodal Biometric Recognition Based on Fusion of Electrocardiogram and Fingerprint Using CNN, LSTM, CNN-LSTM, and DNN Models Agustina, Winda; Nugrahadi, Dodon Turianto; Faisal, Mohammad Reza; Saragih, Triando Hamonangan; Farmadi, Andi; Budiman, Irwan; Parenreng, Jumadi Mabe; Alkaff, Muhammad
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.5098

Abstract

Biometric authentication offers a promising solution for enhancing the security of digital systems by leveraging individuals' unique physiological characteristics. This study proposes a multimodal authentication system using deep learning approaches to integrate fingerprint images and electrocardiogram (ECG) signals. The datasets employed include FVC2004 for fingerprint data and ECG-ID for ECG signals. Four deep learning architectures—Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), CNN-LSTM, and Deep Neural Network (DNN)—are evaluated to compare their effectiveness in recognizing individual identity based on fused multimodal features. Feature extraction techniques include grayscale conversion, binarization, edge detection, minutiae extraction for fingerprint images, and R-peak–based segmentation for ECG signals. The extracted features are combined using a feature-level fusion strategy to form a unified representation. Experimental results indicate that the CNN model achieves the highest classification accuracy at 96.25%, followed by LSTM and DNN at 93.75%, while CNN-LSTM performs the lowest at 11.25%. Minutiae-based features consistently yield superior results across different models, highlighting the importance of local feature descriptors in fingerprint-based identification tasks. This research advances biometric authentication by demonstrating the effectiveness of feature-level fusion and CNN architecture for accurate and robust identity recognition. The proposed system shows strong potential for secure and adaptive biometric authentication in modern digital applications.
Analisa Pengaruh Mobilitas Node Terhadap Kualitas Layanan Voice Call Pada Jaringan UMTS Alkaff, Muhammad; Djanali, Supeno; Ciptaningtyas, Henning Titi
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 1 No 1: April 2014
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (552.898 KB) | DOI: 10.25126/jtiik.201411103

Abstract

Abstrak IMS (IP Multimedia Subsystem) adalah bagian dari spesifikasi UMTS (Universal Mobile Telecomunication System) sesuai dengan release 5 dan 6. Telah banyak dilakukan penelitian tentang kinerja IMS namun umumnya dilakukan pada node UE (User Equipment) yang stationary. Penelitian ini bertujuan untuk meneliti pengaruh mobilitas UE terhadap kualitas layanan pada jaringan UMTS Release 5/6. Selain itu, juga akan dilakukan perbandingan pada kecepatan yang berbeda-beda untuk meneliti pengaruh perbedaan kecepatan tersebut terhadap kualitas layanan pada jaringan UMTS. Hasil uji coba menunjukkan, seiring dengan meningkatnya kondisi traffic, UE dengan kecepatan yang rendah mendapatkan hasil yang lebih baik jika dibandingkan dengan UE dengan kecepatan yang tinggi. Selain itu, pengaruh mobilitas UE menjadi semakin besar dengan bertambahnya kecepatan yang digunakan oleh UE. Secara umum, skenario dengan callee mobile mendapatkan hasil yang lebih baik seiring dengan bertambahnya kecepatan dan meningkatnya kondisi trafik. Kata kunci: IMS, Kecepatan, Mobilitas, UMTS Abstract IMS (IP Multimedia Subsystem) is a part of the specification of UMTS (Universal Mobile Telecommunications System) according to the release 5 and 6. Has done a lot of research on the performance of IMS but is generally performed on the UE node (User Equipment) that stationary. This study aimed to investigate the effect of mobility on the quality of service in the EU UMTS Release 5/6. In addition, comparisons will also be performed at different speeds to examine the effect of the speed difference to the quality of service in UMTS networks. Experimental results show, along with the increasing traffic conditions, the EU with a low speed get better results when compared to the EU with a high speed . In addition, the influence of EU mobility becomes larger with increasing speed used by the EU. In general, the scenario with mobile callee get better results with increasing speed and increasing traffic conditions. Keywords: IMS, Speed​​, Mobility, UMTS
Optimasi Penjadwalan Mata Kuliah Menggunakan Metode Algoritma Genetika dengan Teknik Tournament Selection Sari, Yuslena; Alkaff, Muhammad; Wijaya, Eka Setya; Soraya, Syarifah; Kartikasari, Dany Primanita
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 1: Februari 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3621.855 KB) | DOI: 10.25126/jtiik.2019611262

Abstract

AbstrakBagi sebuah perguruan tinggi, penjadwalan perkuliahan merupakan suatu kegiatan yang sangat penting   untuk   dapat   terlaksananya   proses belajar mengajar   yang   baik.  Dimana   dalam   proses  belajar mengajar dapat dilakukan oleh semua pihak yang terkait, bukan hanya bagi dosen yang mengajar, tetapi juga bagi mahasiswa yang mengambil mata kuliah. Dalam penyusunan jadwal, ada beberapa variabel yang mempengaruhi yaitu: ruangan yang tersedia, jumlah mata kuliah yang diselenggarakan, waktu yang ada dan ketersediaan dosen yang mengajar. Oleh karena itu tujuan dari penelitian ini adalah merancang suatu sistem yang dapat membuat atau menyusun   jadwal    perkulihaan    secara  teroptimasi. Metode dalam proses pembuatan jadwal perkuliahan secara otomatis pada penelitian ini menggunakan metode algoritma genetika dengan teknik seleksi turnamen. hasil pengujian sistem dapat memberikan kemudahan dan kecepatan kepada user atau Program Studi Teknologi Informasi dalam proses pembuatan atau penyusunan jadwal untuk    perkuliahan,    yaitu hanya diperlukan waktu sekitar 14,7 menit dibandingkan dengan proses manual yang memerlukan waktu sekitar 2 (dua) hari.AbstractFor a college, the university course timetabling is is an activity that’s very important for the implementation of good teaching and learning process. In  teaching  and  learning  process  can be done    by    all    related    parties,   not    only    for Lecturers who teach, but also for students who take the course. In the preparation of the schedule, there are several variables that affect the: the available space, the number of courses held, the time available and the availability of lecturers  who  teach. Therefore, the  purpose  of this research is to design a system that can create or arrange optimization schedule optimally. Methods in the process of making university course   timetabling   automatically   in   this study using genetic algorithm method with tournament selection.
Sistem Pakar Berbasis Android untuk Mendeteksi Jenis Perilaku ADHD pada Anak Alkaff, Muhammad; Khatimi, Husnul; Sari, Yuslena; Darmawan, Puja; Primananda, Rakhmadhany
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 2: April 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2464.534 KB) | DOI: 10.25126/jtiik.2019621265

Abstract

ADHD (Attention Deficit Hyperactivity Disorder) adalah gangguan perkembangan otak pada anak yang mengakibatkan meningkatnya aktifitas motorik sehingga menyebabkan penderitanya menjadi hiperaktif, impulsif dan inatentif. Kondisi ini sering memperlihatkan tingkah laku yang tidak wajar seperti selalu bergerak tanpa tujuan, selalu gelisah, atau tidak bisa duduk dengan tenang. Gangguan ADHD terbagi menjadi tiga jenis yaitu Hiperaktif, Inatentif dan Impulsif. Salah satu cara untuk mendiagnosa jenis ADHD yang diderita oleh anak adalah dengan konseling. Tujuan dari penelitian ini adalah membangun sebuah sistem pakar yang dapat membantu memberikan kesimpulan tentang jenis penyakit ADHD yang diderita oleh anak serta tingkat keyakinan diagnosisnya. Penelitian ini menggunakan metode Dempster-Shafer untuk melakukan perhitungan terhadap nilai keyakinan suatu diagnosa. Hal ini dilakukan dengan cara membandingkan setiap nilai keyakinan dari 2 gejala awal yang terjadi pada anak untuk selanjutnya dibandingkan lagi dengan nilai keyakinan dari gejala-gejala lainnya. Sehingga mengerucut pada suatu gejala yang mengacu kepada suatu jenis dari ADHD disertai dengan nilai keyakinannya seperti layaknya diagnosa seorang pakar psikologi anak. Dalam penelitian ini dibangun sistem pakar berbasis Android dengan basis pengetahuan dari 3 orang pakar untuk memudahkan orang tua anak dalam mendiagnosa gejala-gelaja yang mungkin diderita oleh anaknya. Hasil pengujian sistem terhadap pakar dengan persentase rata-rata sebesar 93,3% dari 3 orang pakar, menunjukan bahwa sistem pakar yang telah dibuat mampu mendiagnosa jenis perilaku ADHD yang diderita oleh anak-anak disertai dengan nilai tingkat keyakinan diagnosisnya.Abstract ADHD (Attention Deficit Hyperactivity Disorder) is a brain development disorder in children resulting in increased motor activity causing the sufferer to become hyperactive, impulsive and inattentive. This condition often shows unnatural behavior like always moving aimlessly, always restless, or unable to sit quietly. ADHD disorders divided into three types, namely Hyperactive, Inattentive and Impulsif. One way to diagnose the type of ADHD suffered by children is by counseling. The purpose of this study is to build an expert sistem that can help provide conclusions about the kind of ADHD that the children had and the diagnosis level of confidence. This research uses Dempster-Shafer method to perform the calculation of confidence value of diagnosis. This is done by comparing each of the confidence values of the two early symptoms that occur in the child to furthermore compare with the belief value of the other symptoms. Therefore, conical to a symptom that refers to a type of ADHD accompanied by the value of the diagnosis beliefs, just like the diagnosis of a child psychologist. In this study, an Android-based expert system with a knowledge base from three experts is built to facilitate the child's parents in diagnosing symptoms that may be suffered by his son. The experimental test of the system with the mean percentage of 90% from 3 experts, indicates that the expert system that has been made can diagnose the type of ADHD behavior suffered by the children accompanied by the value of the diagnosis confidence level.
Klasifikasi Laporan Keluhan Pelayanan Publik Berdasarkan Instansi Menggunakan Metode LDA-SVM Alkaff, Muhammad; Baskara, Andreyan Rizky; Maulani, Irham
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8 No 6: Desember 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2021863768

Abstract

Sebuah sistem layanan untuk menyampaikan aspirasi dan keluhan masyarakat terhadap layanan pemerintah Indonesia, bernama Lapor! Pemerintah sudah lama memanfaatkan sistem tersebut untuk menjawab permasalahan masyarakat Indonesia terkait permasalahan birokrasi. Namun, peningkatan volume laporan dan pemilahan laporan yang dilakukan oleh operator dengan membaca setiap keluhan yang masuk melalui sistem menyebabkan sering terjadi kesalahan dimana operator meneruskan laporan tersebut ke instansi yang salah. Oleh karena itu, diperlukan suatu solusi yang dapat menentukan konteks laporan secara otomatis dengan menggunakan teknik Natural Language Processing. Penelitian ini bertujuan untuk membangun klasifikasi laporan secara otomatis berdasarkan topik laporan yang ditujukan kepada instansi yang berwenang dengan menggabungkan metode Latent Dirichlet Allocation (LDA) dan Support Vector Machine (SVM). Proses pemodelan topik untuk setiap laporan dilakukan dengan menggunakan metode LDA. Metode ini mengekstrak laporan untuk menemukan pola tertentu dalam dokumen yang akan menghasilkan keluaran dalam nilai distribusi topik. Selanjutnya, proses klasifikasi untuk menentukan laporan agensi tujuan dilakukan dengan menggunakan SVM berdasarkan nilai topik yang diekstraksi dengan metode LDA. Performa model LDA-SVM diukur dengan menggunakan confusion matrix dengan menghitung nilai akurasi, presisi, recall, dan F1 Score. Hasil pengujian menggunakan teknik split train-test dengan skor 70:30 menunjukkan bahwa model menghasilkan kinerja yang baik dengan akurasi 79,85%, presisi 79,98%, recall 72,37%, dan Skor F1 74,67%. AbstractA service system to convey aspirations and complaints from the public against Indonesia's government services, named Lapor! The Government has used the Government for a long time to answer the problems of the Indonesian people related to bureaucratic problems. However, the increasing volume of reports and the sorting of reports carried out by operators by reading every complaint that comes through the system cause frequent errors where operators forward the reports to the wrong agencies. Therefore, we need a solution that can automatically determine the report's context using Natural Language Processing techniques. This study aims to build automatic report classifications based on report topics addressed to authorized agencies by combining Latent Dirichlet Allocation (LDA) and Support Vector Machine (SVM). The topic-modeling process for each report was carried out using the LDA method. This method extracts reports to find specific patterns in documents that will produce output in topic distribution values. Furthermore, the classification process to determine the report's destination agency carried out using the SVM based on the value of the topics extracted by the LDA method. The LDA-SVM model's performance is measured using a confusion matrix by calculating the value of accuracy, precision, recall, and F1 Score. The test results using the train-test split technique with a 70:30 show that the model produces good performance with 79.85% accuracy, 79.98% precision, 72.37% recall, and 74.67% F1 Score
Variations of Business Process Reengineering: The Conceptual Framework for Teak Production Sustainability Alkaff, Muhammad
Dalwa Islamic Economic Studies: Jurnal Ekonomi Syariah Vol. 2 No. 1 (2023): Dalwa Islamic Economic Studies
Publisher : Program Studi Ekonomi Syariah Institut Agama Islam Darullughah Wadda'wah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38073/dies.v2i1.1197

Abstract

For agroforestry industry, in this case teak production, the most challenge that are faced is the balance of teak production optimization and environmental problem. Because, when the production of timber is increased, and then the environment will be affected. Hence, it is required to be found the better solution in balancing the teak production optimization and environment conservation. By searching any literatures, either empirically or theoretically, this article reveals that business process re-engineering that can be implemented by agroforestry industry in teak production may be consist of five stages, they are identifying, model map, analyzing, improvement the process, and re-engineering. All those process must be completed by the principles in the business process they are clarity (understandable), correctness, relevance, economic efficiency, comparability, systematic design. In which must understood and completed in the business process re-engineering may include process mapping, fail-saving, teamwork, and communication. Hence, when it is implemented in the teak production process, it can deliver the positive outcomes that supported the business sustainability in teak production.
Co-Authors Abdullayev, Vugar Agus Dwi Susanto Ahmad Zainul Abidin Ainiyyah, Ainiyyah Akhmad Rojali Aldy Heriwardito Alfando, Muhammad Alvin Andi Eriadi Andi Farmadi Andreyan Rizky Baskara ARIF RAHMAN, MUHAMMAD Arina Ihda Rahmah Syarifah Ariska Deffy Anggarany, Ariska Deffy Baskara, Andreyan Budhi Antariksa Ceva W. Pitoyo Dany Primanita Kartikasari Darmawan, Puja Dewi Rizqia Najipah Dewi Yennita Sari Dodon Turianto Nugrahadi Erlina Burhan Fajar Zulkarnain, Andry Fatma Indriani Friska Abadi Gusti Nizar Syafi'i Halimah Halimah Hayatun Nufus Henning Titi Ciptaningtyas Hera Afidjati Herry Purnomo Husnul Khatimi Ibrahim Nur Insan Putra Darmawan Iftihatul Aulia Rahmah Iphan Fitrian Radam Iphan Fitrian Radam Iqbal Rizqi, Muhammad Irwan Budiman Jumadi Mabe Parenreng Marimin Marimin Maulani, Irham Maulidiya, Erika Maya Amalia Mohamad Fahmi Alatas Muhammad Afrizal Miqdad Muhammad Fachrurrazi Muhammad Nur Abdi Muhammad Reza Faisal, Muhammad Reza Muhammad Ridho A.G.D. Muhammad Ziki Elfirman Muliadi Muti'a Maulida Mutia Maulida Nandang Eko Yulianto Nurul Fathanah Mustamin Nurul Qamaria Paramita, Diana Putra, Andika Chandra Putri Ridha Amalia Raisa Amalia Rakhmadhany Primananda, Rakhmadhany Rani Sauriasari, Rani Reza Karimi Rita Rogayah Rudy Ansari, Rudy Rudy Herteno Ryan Ramel Samoedro, Erlang Saragih, Triando Hamonangan Sa’diah, Halimatus siti sheilawati Soehardiman, Dicky Sugiantoro Sugiantoro Sugiantoro Sugiantoro Sukamto Koesnoe Sukardi Sukardi Supeno Djanali Syarifah Soraya Takhwifa, Famila Taufik, Feni Fitriani Wenny Puspita Wijaya, Eka Setya Winarto Chandra Winda Agustina Windarsyah Windarsyah Yandra Arkeman Yulianto, Nandang Eko Yuslena Sari, Yuslena