RARia Arafiyah

Ria Arafiyah

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ria Arafiyah has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting Student Dropout Risk Using Long Short-Term Memory Based on Academic Performance Data

    by Ria Arafiyah

    Student dropout is a critical issue affecting academic quality and institutional performance in higher education. Dropout behavior usually emerges gradually through declining academic performance across semesters. Therefore, time-series modeling is essential to capture such temporal patterns. This study proposes a Long Short-Term Memory (LSTM) model to predict student dropout risk based on semester-wise academic data. The dataset consists of 385 undergraduate students from the Computer Science program, FMIPA, represented by Grade Point Average (GPA) and credit load (SKS) over eight semesters. Student status is converted into a binary label: dropout and non-dropout. To address class imbalance, Synthetic Minority Over-sampling Technique (SMOTE) is applied. Experimental results show that the proposed LSTM model achieves a recall of 1.00 for the dropout class, indicating that all dropout cases are successfully detected. Although the precision remains relatively low due to false positives, the model demonstrates strong potential as a basis for academic monitoring and early intervention systems.

  • Open Access

    Expert System for Laptop Damage Diagnosis Using Naïve Bayes-Certainty Factor Method Based on Website

    by Novitasari, Ria Arafiah, Mulyono

    Laptop damage is a condition where the laptop malfunctions caused by damaged components in the laptop. According to the ICT Survey and Its Implications for Socio-Cultural and Economic Aspects of Society in Indonesia, 41.55% of Indonesians are computer/laptop users. Seeing that this number is quite large and not everyone can diagnose damage and handle laptop damage, this research is here to build an expert system for diagnosing laptop damage. This study discusses the development of a laptop-based expert system for diagnosing damage website as an effort to provide laptop damage diagnostic services along with suggestions or solutions that can be repair the damage experienced by the user's laptop. This expert system was developed using the methodNaïve Bayes and Certainty factor. The input given to the system is in the form of symptoms of damage experienced, along with its intensity. Method naïve bayes used to find the highest probability of the diagnosis. The results of this diagnosis are then processed using certainty factor to determine the level of confidence in the results of the diagnosis. This expert system comes in the form website built using framework CodeIgniter and MySQL. Based on the results of system testing using 40 expert data, it shows that the expert system for diagnosing laptop damage uses the method Naïve Bayes-Certainty factor shows the suitability of the results of system diagnostics with expert diagnoses that is equal to 85%.

  • Open Access

    Perancangan Sistem Informasi Praktik Kerja Lapangan Berbasis Website

    by Agam Nufriansyah, Med Irzal, Ria Arafiah

    Praktik Kerja Lapangan (PKL) merupakan mata kuliah yang wajib diambil oleh mahasiswa Ilmu Komputer UNJ. Mata kuliah yang terdiri atas 2 sks ini bertujuan untuk memberi bekal kepada mahasiswa agar mengetahui permasalahan di dunia kerja yang berkaitan dengan mata kuliah yang pernah diambil sebelumnya dan dapat membuat deskripsi teoritis dan analisis dari sudut pandang bidang studi yang bersangkutan serta memberikan atau menjelaskan alternatif pemecahannya dalam bentuk laporan untuk diseminarkan. Skripsi ini bertujuan untuk membangun suatu sistem informasi praktik kerja lapangan berbasis website yang dapat membantu Program Studi Ilmu Komputer Universitas Negeri Jakarta dalam melaksanakan pemantauan dan administrasi terkait praktik kerja lapangan. Sistem Informasi ini dikembangankan menggunakan metode pengembangan perangkat lunak SDLC dengan Model Spiral, framework Code Igniter untuk back-end dan framework Bootstrap untuk front-end. Pada akhir pengembangan dilakukan pengujian sistem menggunakan Black Box secara fungsional dan skala likert untuk menguji tingkat kelayakan sistem, dapat dikatakan bahwa Perancangan Sistem Informasi Praktik Kerja Lapangan berbais website telah berjalan dengan baik dan sesuai yang diharapkan dengan tingkat kelayakan sebesar 87,1% pada keseluruhan sistem.


  • Open Access

    An Android-Based Expert System for Recognition of Cats Diseases Using Naïve Bayes Method

    by Angga Arian, Ria Arafiah, Muhammad Eka Suryana

    The animal that is currently being studied a lot is the cat, because there has been a lot of research related to this cat and it is easy to learn. This cat research also needs an expert or experts who can study this, especially cat diseases. This thesis research is aimed at the need for the public to know cat disease which is then applied in the form of an Android-based expert system application. Making this application of an expert system for recognizing cat diseases uses a method that is often used and studied by many people, namely the Naïve Bayes method. The purpose of making this cat disease recognition expert system is to help users, especially cat lovers, to get information about recognizing and treating their pets at an early stage when they have problems with their health so that they can recover faster from their illness. The results of the expert system research on the introduction of cat diseases, namely this application is used to determine the cat's disease suffered from the symptoms that have been described in the application and these symptoms are obtained directly from interviews from the two doctors (experts). The test also got good results, namely 100%.

  • Open Access

    Penentuan Tipe Attention Deficit Hyperactivity Disorder Menggunakan Metode Dempster Shafer

    by Saphira Maulidina Faturahman, Med Irzal, Ria Arafiah

    Attention Hypercativity Disorder terdiri dari tiga tipe, yaitu Inatensi, Hiperaktif-Impulsif, dan gabungan Inatensi Hiperaktif-Impulsif. Periode anak usia dini hanya berlangsung pada saat anak dalam kandungan hingga usia dini, yaitu 0-6 tahun. Tidak semua orangtua yang memiliki kemampuan finansial untuk mendatangi psikolog anak atau psikiater anak, karena untuk melakukan konsultasi membutuhkan biaya yang tidak sedikit. Selain faktor biaya, faktor waktu juga mempengaruhi orangtua tidak bisa konsultasi kepada pakar, hal itu disebabkan oleh terbatasnya waktu praktek atau jauhnya lokasi anak dengan lokasi konsultasi. Dalam hal ini, selaku orangtua yang memakai jasa, orangtua membutuhkan pakar yang bisa memudahkan dalam mendiagnosa gangguan lebih dini. Teori Dempster-Shafer adalah representasi, kombinasi dan propogasi ketidakpastian, dimana teori ini memiliki beberapa karakteristik yang secara instuitif sesuai dengan cara berfikir seorang pakar, namun dasar matematika yang kuat. Secara umum teori Dempster-Shafer ditulis dalam suatu interval. Interval tersebut digunakan untuk mengkombinasikan potongan informasi yang terpisah dan mengkalkulasikan kemungkinan dari suatu peristiwa. Proses pengujian dilakukan dengan menggunakan bahasa pemrograman PHP dan database mysql. Rangkaian penelitian ini berhasil mengakuisisi data dari pakar mulai gejala sampai tipe ADHD. Representasi pengetahuan pada sistem ini dalam menentukan tipe ADHD berdasarkan gejala dari setiap tipe ADHD yang ditampilkan dalam bentuk memilih gejala yang dirasakan. Penelitian ini telah menerapkan metode dempster shafer untuk menentukan tipe ADHD serta memberikan hasil berupa keterangan tipe ADHD.

  • Open Access

    Monitoring System Development of Milkfish Salinity on Aquaponic at Green House

    by Alimuddin Alimuddin, Masjudin, Venna Vanessha, Cakra Adipura Wicaksana, Ria Arafiyah, Irma Saraswati


  • Open Access

    Development and Performance Study of Temperature and Humidity Regulator in Baby Incubator Using Fuzzy-PID Hybrid Controller

    by Alimuddin Alimuddin, Ria Arafiyah, Irma Saraswati, Rocky Alfanz, Partogi Hasudungan, Taufik Taufik

    Technological developments in the health sector for the safety of neonates are essential. Such efforts are needed to curb the increase in premature infant mortality cases caused by bacteria, asphyxia, infections, and poor management of facility equipment. Furthermore, preterm and other at-risk babies have low ability to regulate temperature and produce body heat as characterized by their dry skin conditions; hence, the need for baby incubators. For their operation, these baby incubators provide strict regulated energy change that is influenced by heat transfer caused by the surrounding atmospheric temperature and humidity. This paper presents the design, construction, and performance study of a proposed Fuzzy-PID hybrid control system for regulating temperature and humidity in a baby incubator. To accomplish its goal, the proposed controller must be able to distribute heat and maintain humidity in the incubator under fluctuating atmospheric conditions to keep the baby’s body warm. Performance tests of the proposed hybrid controller were conducted by comparing temperature and humidity outputs in the baby incubator against predetermined expected values. Results show that the proposed controller is able to successfully achieve and maintain the temperature and humidity set points. Further examination also suggests that the proposed Fuzzy-PID hybrid control offers an improved overall system response performance compared to the PID controller.


  • Open Access

    Classification of Dengue Haemorrhagic Fever (DHF) using SVM, naive bayes and random forest

    by R Arafiyah, F Hermin, I R Kartika, A Alimuddin, I Saraswati

    Handling Dengue Hemorrhagic Fever (DHF) becomes Indonesia's national priority. DHF is an infectious disease whose treatment requires precision and speed of diagnosis. Data mining can be used to build prediction diagnosing DHF disease with supporting database. This paper aims to predict DHF using SVM, Naive Bayes, and Random Forest and then compare it with the accuracy of the result of third method. The accurate DHF prediction system can be used to avoid the error of diagnosing DHF and the treatment of the disorder can be done more quickly and precisely. The input systems are the patient's medical records (i.e. temperature, spotting, rumple leed, and bleeding) and the output system is suffering from DHF or not.


  • Open Access

    Data mining for dengue hemorrhagic fever (DHF) prediction with naive Bayes method

    by Ria Arafiyah, Fariani Hermin

    Handling of infectious diseases is determined by the accuracy and speed of diagnosis. Government through the Regulation of the Minister of Health of the Republic of Indonesia No. 82 of 2014 on the Control of Communicable Diseases establishes Dengue Hemorrhagic Fever (DHF) has made DHF prevention a national priority. Various attempts were made to overcome this misdiagnosis. The treatment and diagnosis of DHF using ANFIS has result an application program that can decide whether a patient has dengue fever or not [1]. An expert system of dengue prevention by using ANFIS has predict the weather and the number of sufferers [2]. The large number of data on DHF often cannot affect a person in making decisions. The use of data mining method, able to build data base support in decision makers diagnose DHF disease [3]. This study predicts DHF with the method of Naive Bayes. Parameter of The input variable is the patient's medical data (temperature, spotting, bleeding, and tornuine test) and the output variable suffers from DBD or not while the system output is diagnosis of the patient suffering from DHF or not. Result of model test by using tools of Orange 3.4.5 obtained level of precision model is 77,3%.