Claim Missing Document
Check
Articles

Found 32 Documents
Search

Tinjauan Supervised Reinforcement Learning pada Tindakan Medis Penyakit Diabetes Melitus: Review of Supervised Reinforcement Learning on Medical Actions for Diabetes Mellitus Putri, Indah Pratiwi; Marcelina, Dona; Yulianti, Evi
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 3 (2024): MALCOM July 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i3.1363

Abstract

Diabetes Melitus (DM) merupakan penyakit kronis yang memerlukan pengelolaan medis yang berkelanjutan. Pengelolaan pengendalian penyakit diabetes bergantung pada kadar glukosa  dalam darah guna mengambil tindakan yang tepat agar dapat mencegah kadar glukosa darah menjadi terlalu rendah atau tinggi. Dalam konteks perawatan medis DM, penggunaan teknologi pembelajaran mesin, khususnya Supervised Reinforcement Learning (SRL) telah mengahadirkan pendekatan yang inovatif. Penelitian ini bertujuan untuk menyelidiki dan merangkum beberapa karya ilmiah yang membahas tentang penerapan SRL dalam konteks tindakan medis untuk penyakit DM. Beberapa percobaan dilakukan oleh para peneliti dengan menggunakan data dari pasien diabetes untuk menentukan parameter model yang optimal, melakukan simulasi dan studi validasi secara real-time sehinga dapat memberikan wawasan lebih lanjut tentang penerapan praktis model pembelajaran penguatan dalam pengaturan klinis. Melalui SRL, agen pembelajaran dapat menggabungkan umpan balik lingkungan dengan informasi eksplisit dari supervisor untuk menghasilkan keputusan yang optimal dalam pengelolaan DM. Dalam makalah ini, penulis menganalisis kajian literatur terkait penerapan SRL pada pengelolaan medis DM, serta mengeksplorasi potensi dan tantangan yang terkait dengan penggunaan pendekatan ini dalam praktik klinis
Adjusted TextRank for keyword extraction in petrochemical project correspondence documents Atmoko, Indri; Yulianti, Evi; Jiwanggi, Meganingrum Arista
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 2: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i2.pp1171-1180

Abstract

A large petrochemical construction project is typically executed by multiple parties, all bound by contract agreement. During the execution phase, issues and problems may arise because the work details are not clearly specified in the contractual agreement. These issues are formally communicated and documented through written correspondence letters. By identifying important keywords within these formal letters, a comprehensive narrative of the project, including its associated issues, can be identified and analyzed. In this research, we introduce an adjusted TextRank algorithm that integrates external features from the Indonesian FastText language model and term frequency-inverse document frequency (TF-IDF) scores to identify important keywords within a dataset of correspondence letters of petrochemical projects. This enhancement involves refining phrase detection, semantic relationship estimation between words, and part-of-speech (POS) identification for words or phrases. Our results show that the proposed adjustments result in improved evaluation scores compared to the baseline standard TextRank and standard TF-IDF, respectively by 24.1% and 25% in terms of F-1 scores.
Penerapan Artificial Intelligence Dalam Meningkatkan Produktivitas Guru Sekolah Dasar 13 Palembang Yulianti, Evi; Pratiwi, Indah Putri; Suryati; Saluza, Imelda; Marcelina, Dona; Permatasari, Indah
Jurnal Abdimas Mandiri Vol. 8 No. 2
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jam.v8i2.4271

Abstract

Penerapan artificial intelligence (AI) telah menjadi fokus eksplorasi dalam upaya meningkatkan efisiensi dan produktivitas di lingkungan pendidikan, terutama di Sekolah Dasar Negeri 13 Palembang. Sekolah ini dihadapkan pada sejumlah tantangan, termasuk waktu yang terbatas untuk mengelola tugas administratif, kesulitan dalam personalisasi pembelajaran sesuai dengan kebutuhan siswa, serta pengelolaan data siswa yang optimal untuk meningkatkan pengambilan keputusan pendidikan. Kegiatan pengabdian masyarakat ini dipilih untuk mengatasi permasalahan tersebut dengan mengimplementasikan teknologi AI. Tujuan utama pengabdian ini adalah memperkenalkan dan mengintegrasikan AI dalam sistem penilaian otomatis, personalisasi pembelajaran adaptif berbasis AI, analisis data yang komprehensif dapat mendukung pengambilan keputusan yang lebih baik di tingkat sekolah dasar. Metode pelaksanaan pengabdian mencakup analisis kebutuhan awal melalui survei dan wawancara dengan guru-guru, pengembangan modul pelatihan AI yang terfokus, workshop intensif dengan pendampingan langsung, dan hasil evaluasi pre-test dan post-test menunjukkan peningkatan yang signifikan dalam pemahaman dan penerapan konsep AI di antara para peserta, meskipun beberapa tantangan dalam adopsi teknologi AI masih perlu diatasi. Kesimpulannya, pemanfaatan AI dalam pendidikan menjanjikan solusi inovatif dalam mengatasi permasalahan yang dihadapi para guru dan meningkatkan kualitas pembelajaran yang lebih adaptif serta efisien. Hasil pengabdian ini menegaskan pentingnya terus mendorong pengembangan teknologi AI dalam konteks pendidikan sebagai langkah strategis untuk meningkatkan standar pendidikan di masa depan.
The Synthesized-Hydroxyapatite Powder from Anadara Granosa Shells using Deposition Time Method for Biomedical Applications Sunardi, Sunardi; A’yun, Nidha Aulia Qurrata; Dari, Qorinah Wulan; Aminuddin, Jamrud; Bilalodin, Bilalodin; Praktino, Budi; Yulianti, Evi; Utomo, Agung Bambang Setio; Sari, Kartika
Jurnal Ilmu Fisika Vol 16 No 1 (2024): March 2024
Publisher : Jurusan Fisika FMIPA Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jif.16.1.88-96.2024

Abstract

Hydroxyapatite (HAp) powder, one of the biomaterials derived from natural sources, could be used in biomedical applications. In this research, the synthesized-HAp powder from Anadara Granosa shells as raw materials had a high calcium carbonate content with variations in deposition time using the precipitation method. Variations of deposition time used were 0 (S0), 24 (S24), and 48 (S48) hours. Fourier Transform Infrared (FTIR), X-Ray Diffractions (XRD), and Scanning Electron Microscopy (SEM) were used to investigate the chemical structure, phase analysis, and morphology of the synthesized HAp powder. FTIR results of the S0, S24, and S48 showed that the functional groups ,  and were formed at variations in the deposition time. The XRD results showed that the smallest of crystallite size of S48 was 26.03 nm, and the crystallinity degree of S24 was 38.74%. The grain dispersity of the synthesized-hydroxyapatite powder from SEM results were uniform, agglomeration, and spherical, irregular shape. The Ca, P, Mg, and Si compositions were shown in the synthesized-hydroxyapatite powder. The deposition time affects the synthesized-Hydroxyapatite (HAp) powder from the Anadara Granosa shell, and it is a potential raw material for biomedical applications.
Molecular Vibration and Physicochemical Performance of Proton-Conducting Solid Polymer Electrolyte Membrane based on CMC/PVA/CH3COONH4 Ndruru, Sun Theo Constan Lotebulo; Rachmadhanti, Elvira Nur; Fridarima, Shanny; Berghuis, Nila Tanyela; Prasetyo, Ridho; Yulianti, Evi; Hayati, Atika Trisna; Adriana, Risda; Siregar, Rabiyatul Adawiyah; Sofyan, Muhammad Ihsan; Sampora, Yulianti; Annas, Dicky; Madiabu, Muhammad Jihad
Molekul Vol 19 No 3 (2024)
Publisher : Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jm.2024.19.3.11001

Abstract

This work studied examined the influence of ammonium acetate (CH3COONH4) on CMC/PVA-based solid polymer electrolyte (SPE) membranes, focusing on molecular vibration, proton conductivity, and physicochemical properties. SPE membranes were prepared via the casting solution method with varying CH3COONH4 concentrations to determine the optimal proton conductivity. Various characterizations, including FTIR, EIS, XRD, and TGA, were performed. The optimal membrane condition was achieved with 10 wt-% CH3COONH4 in the CMC/PVA (80/20) blend, yielding proton conductivity of 3.93×10⁻⁴ S/cm and favorable mechanical, thermal, and crystallinity properties, making it suitable for proton-conducting polymer applications. Keywords: ammonium acetate, carboxymethyl cellulose, ionic conductivity, poly(vinyl alcohol), proton battery, solid electrolyte membrane
Sistem Closed Domain Question Answering Metadata Statistik Berbasis Metode Transfer Learning Rachmawati, Nur; Yulianti, Evi
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2225

Abstract

Statistical metadata plays an important role in society. Statistical metadata allows us to know all information about statistical activities that have been carried out. In this study, we built a Closed Domain Question Answering system related to statistical metadata (CDQA-Metadata Statistik). The absence of a large benchmark regarding QA datasets on statistical metadata caused us to choose the transfer learning method. This study uses a retriever (BM25)-reader (IndoBERT) architecture based on transfer learning with three experiments. The results of the first experiment showed that statistically the performance of the transfer learning model significantly outperformed the non-transfer learning model on human question data and automatic question data. The results of the second experiment showed that statistically the performance of the CDQAStatistical Metadata system based on transfer learning on automatic question data was significantly better than on human question data. The results of the third experiment showed that for human question data, adding automatic question data during fine-tuning did not improve system performance. Then on automatic question data, adding human question data during fine-tuning did not seem to be able to improve system performance.
Modification of Chitosan/PEG4000 dispersed with Lithium Triflate (LiCF\(_3\)SO\(_3\)) as a solid polymer electrolyte for the secondary battery Sari, Kartika; Haryadi, Arifin Nur Muhammad; Khusaenah, Nur; Sudaryanto; Yulianti, Evi; Utomo, Agung Bambang Setio
Communications in Science and Technology Vol 9 No 2 (2024)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.9.2.2024.1496

Abstract

Secondary battery solid electrolytes attract researchers' attention for being one of the components of the anode and cathode separation in batteries. Currently, battery electrolytes on the market are liquid-based, which have weaknesses in their safety and are not environmentally friendly. Solid-based electrolytes can be a good choice since they excel in the safety and stability of mechanical and electrical properties; however, they still have the disadvantage of low conductivity values (~10-4 - 10-6 S/cm), thus requiring modification. The solid electrolytes modification using chitosan can be done by adding other polymers and salts as fillers and Li+ ion-making agents. This scientific paper offers an overview of the development of chitosan-based secondary battery solid electrolytes with the addition of PEG4000 polymer and LiCF3SO3. The study was conducted using the solution casting method producing solid electrolytes in the form of membranes. The addition of PEG4000 and LiCF3SO3 affected the microstructure and electrical permittivity of the polymer solid electrolyte membrane. PEG4000 as a plasticizer had no significant effect on inter- and intra-molecular bonds due to poor membrane homogeneity; meanwhile, LiCF3SO3 could increase the permittivity and ionic conductivity of the chitosan polymer solid electrolyte membrane to 3.199 x 10-7 S/cm. The chitosan polymer solid electrolyte membrane with the addition of PEG4000 and 30% LiCF3SO3 salt has an optimal value compared to other salt concentration variations. The results of this research concluded that LiCF3SO3 is evenly dispersed in the chitosan/PEG4000 solid polymer electrolyte membrane enabling it to be used as a secondary battery solid electrolyte.
Workshop Pengembangan Kompetensi Guru Melalui Pembuatan Media Pembelajaran Interaktif Menggunakan Augmented Reality Saluza, Imelda; Putri, Indah Pratiwi; Yulianti, Evi; Marcelina, Dona; Permatasari, Indah
Reswara: Jurnal Pengabdian Kepada Masyarakat Vol 6, No 1 (2025)
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/rjpkm.v6i1.5318

Abstract

Makalah ini membahas pelaksanaan workshop pengembangan kompetensi guru melalui pembuatan media pembelajaran interaktif menggunakan Augmented Reality (AR) di SMA Negeri 1 Banyuasin I. Kebijakan merdeka belajar memberikan kebebasan dalam pendidikan baik bagi guru maupun peserta didik. Artiannya guru diberi kebebasan dalam mengembangkan diri sehingga memiliki kompetensi untuk menjadi guru profesional. Workshop ini bertujuan untuk meningkatkan pengetahuan dan keterampilan guru dalam memanfaatkan teknologi digital untuk menciptakan pengalaman belajar yang lebih menarik dan interaktif bagi siswa. Metode yang digunakan adalah Participatory Action Research (PAR), yang meliputi langkah-langkah perencanaan, implementasi, pengamatan, dan refleksi. Hasil evaluasi menunjukkan bahwa 93,80% peserta memberikan respon positif terhadap kegiatan ini, dengan 98,08% guru merasa bahwa workshop ini meningkatkan kompetensi mereka. Meskipun terdapat tantangan dalam penerapan AR, terutama di kalangan guru senior, antusiasme untuk belajar dan mengembangkan media pembelajaran berbasis teknologi tetap tinggi. Kesimpulannya, kegiatan ini berhasil meningkatkan kompetensi guru dan diharapkan dapat dilanjutkan untuk mendukung profesionalisme guru dalam menghadapi perkembangan teknologi di pendidikan.
Implementasi Soft Skill dan Hard Skill Dalam Pendidikan Islam Yulianti, Evi; Saputra, Muklas Ade; Busral, Busral; Hakim, Lukman
Al-Ashri: Ilmu-Ilmu Keislaman Vol 8 No 1 (2023): April
Publisher : LP2M STAI Balaiselasa YPPTI Pesisir Selatan Sumatera Barat

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

Abstract

Social competence is the teacher's ability to communicate and interact effectively and efficiently with students, fellow teachers, parents/guardians of students, and the surrounding community. Social competence interpersonal skills, namely the ability to build relationships with other people, effectively in the form of; communication skills, motivation skills, collaboration skills, and leadership skills. Hard skills are several skills possessed by a teacher whose concrete form can be captured through the senses or observed directly because the procedures are technical or administrative. This research uses the literature study method. Literature studies are carried out by reading library sources to obtain the necessary data. The data sources used come from secondary data, the data was collected through textbooks, scientific journals, periodicals, ebooks, websites, statutory regulations, and other sources relevant to the research problem. Hard skills are divided into two parts, namely; Pedagogical competency is the ability to manage student learning which includes understanding students; and Professional competency is the ability to master subject matter broadly and in depth. A professional educator in the Islamic view is an educator who has expertise. Development efforts in Islamic education can be done in several ways, namely taking part in teacher upgrading, taking part in teacher deliberations in the field of study, taking courses, increasing knowledge through mass or electronic media, and improving the profession through self-study.
Classification of Economic Activities in Indonesia Using IndoBERT Language Model Syazali, Muhammad Rizki; Yulianti, Evi
Jurnal Ilmu Komputer dan Informasi Vol. 18 No. 2 (2025): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v18i2.1446

Abstract

Classification of economic activities plays a vital role in understanding, analyzing, and managing complex economic processes in a society or country. It facilitates economic analysis, data collection, policy formulation, and informed decision-making. In Indonesia, economic activities are classified according to the Indonesian Standard Industrial Classification (KBLI). This classification process requires in-depth knowledge about KBLI, and this process is still performed manually, which is therefore time-consuming. To address this challenge, this paper proposes to use a transformer-based language model that was pretrained using a large Indonesian corpus, i.e., IndoBERT, to better understand the contextual meanings of text in order to improve the accuracy of automatic economic activity classification. Our results show that the finetuned IndoBERTLARGE model achieves superior results, with an F1 score of 96.82% and a balanced accuracy of 96.10%, outperforming other recent methods used for similar task, i.e., CatBoost and DistilBERT models.