Claim Missing Document
Check
Articles

Found 23 Documents
Search

MULTICLASS CLASSIFICATION FOR STUNTING PREDICTION USING DEEP NEURAL NETWORKS Wulan Sri Lestari; Yuni Marlina Saragih; Caroline Caroline
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 2 (2024): JITK Issue November 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i2.5636

Abstract

Stunting is a chronic nutritional issue that hinders child growth and leads to serious long-term health and developmental impacts, particularly in developing countries. Therefore, early and accurate prediction of stunting is crucial for implementing effective interventions. This research aims to develop a multiclass classification model based on Deep Neural Networks (DNNs) to predict stunting status. The model is trained using a comprehensive dataset that encompasses various health variables related to stunting. The research process includes data collection, data preprocessing, dataset splitting, and training and evaluation of the DNNs model. The model can classify stunting status into four categories: stunted, severely stunted, normal, and tall. Further analysis is conducted to evaluate the influence of various parameters on the model's performance, including dataset splitting ratios (80:20 and 70:30) and learning rates (0.001, 0.0001, and 0.00001). The results show that a learning rate of 0.0001 yields the highest prediction accuracy, at 93.64% and 93.83% for the two data-splitting schemes. This indicates that this learning rate has achieved an optimal balance between convergence speed and the model's generalization capability. Additionally, the developed DNNs model can identify complex patterns hidden within the data without being affected by noise. These findings confirm that appropriate parameter selection, particularly the dataset splitting ratio and learning rate, can significantly enhance the DNNs model's ability to identify complex data patterns.
Migrasi server on-premise ke exchange online pada Badan Pelaksana Otoritas Danau Toba Hanes Hanes; Wulan Sri Lestari; Paulus Paulus; William William
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 8, No 3 (2024): September
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v8i3.25270

Abstract

AbstrakBadan Pelaksana Otorita Danau Toba (BPODT) merupakan Satuan Kerja dibawah Kementrian Pariwisata dan Ekonomi Kreatif yang bertujuan untuk mengembangkan Kawasan Pariwisata Danau Toba sebagai Kawasan Strategis Pariwisata Nasional. Untuk meningkatkan efisiensi komunikasi, BPODT berencana melakukan migrasi dari server email on-premise ke Exchange Online, layanan email berbasis cloud yang disediakan oleh Microsoft. Tim Pengabdian kepada Masyarakat (PkM) dari Universitas Mikroskil berkolaborasi dengan BPODT dalam kegiatan transfer teknologi untuk proses migrasi dan implementasi server email on-premise ke Exchange Online. Tahapan transfer teknologi melibatkan analisis kebutuhan, pembelian lisensi, verifikasi domain, pembuatan akun pengguna, migrasi data email, konfigurasi DNS, komunikasi dan dukungan pengguna serta penyusunan buku panduan untuk dokumentasi proses migrasi. Hasilnya, seluruh proses berjalan lancar  dibuktikan dengan analisis kebutuhan yang efektif dan efisien, pembelian lisensi Exchange Online yang tepat sasaran, dan implementasi migrasi Exchange Online yang sukses dan diharapkan dapat meningkatkan efisiensi komunikasi internal dan eksternal BPODT. Buku panduan yang disusun juga menjadi sumber referensi yang berguna bagi BPODT dalam mengelola Exchange Online. Kata kunci: BPODT; transfer teknologi; exchange online; migrasi; email on-premise. AbstractBadan Pelaksana Otorita Danau Toba (BPODT) is an organizational unit under the Ministry of Tourism and Creative Economy that aims to develop the Lake Toba tourism area as a national strategic tourism area. To improve communication efficiency, BPODT plans to migrate from on-premises email servers to Exchange Online, a cloud-based email service from Microsoft. Mikroskil University's Community Service Team (PkM) collaborate with BPODT in the technology transfer process for the migration and implementation of on-premises email servers to Exchange Online. The technology transfer phases include needs assessment, license procurement, domain verification, user account creation, email data migration, DNS configuration, user communication and support, and the creation of a migration process documentation guide. The results indicate that the entire process went smoothly, demonstrated by an effective and efficient needs analysis, targeted procurement of Exchange Online licenses, and successful implementation of the Exchange Online migration, which is expected to enhance both internal and external communication efficiency at BPODT. The resulting guide serves as a useful reference for BPODT in managing Exchange Online. Keywords: BPODT; technology transfer; exchange online; migration; email on-premise.
Forecasting Climate Change Patterns to Improving Rice Harvest Using SVR for Achieving Green Economy Juliandy, Carles; Kelvin, Kelvin; Halim, Apriyanto; Pipin, Sio Jurnalis; Sinaga, Frans Mikael; Lestari, Wulan Sri
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.32393

Abstract

The consistently declining rice harvest will cause several economic and environmental problems. The unstable and unpredictable climate change was believed as the main problem of the declining rice harvest. We proposed a method for forecasting climate change to help the farmer in their rice cultivation. We used Support Vector Regression (SVR) to improve algorithm steps such as normalizing the data and applying an Adaptive Linear Combiner (ALC) to optimize the dataset before we processed it with the algorithm. Our model gets 95% accuracy as measured with the confusion matrix. We believe our model will help the farmers in their rice cultivation with good climate forecasting. A further benefit of this research we belief that with the well-forecasted climate, the usage of pesticides will decrease and will help the vision of the Indonesian government with a green economy
Comparison of Deep Neural Networks and Random Forest Algorithms for Multiclass Stunting Prediction in Toddlers Lestari, Wulan Sri; Saragih, Yuni Marlina; Caroline
Teknika Vol. 13 No. 3 (2024): November 2024
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v13i3.1063

Abstract

Stunting in toddlers is a serious global health issue, with long-term impacts on physical growth and cognitive development. To address this problem more effectively, it is crucial not only to identify whether a child is stunted but also to predict the severity of the condition. Multiclass stunting prediction offers deeper insights into a child’s condition, enabling more precise and targeted interventions. This study aims to compare the performance of multiclass stunting prediction models using two machine learning algorithms: Deep Neural Networks and Random Forest. The research process involved data collection, preprocessing, as well as model development and testing. The results show that the Random Forest model achieved 100% accuracy in training and 99.92% accuracy in testing, while the Deep Neural Networks model achieved 93.49% accuracy in training and 93.21% in testing. Both models demonstrated strong performance in multiclass stunting prediction, with Random Forest proving superior in terms of accuracy compared to Deep Neural Networks.
Optimization of Sentiment Analysis Classification of ChatGPT on Big Data Twitter in Indonesia using BERT Sinaga, Frans Mikael; Purba, Ronsen; Pipin, Sio Jurnalis; Lestari, Wulan Sri; Winardi, Sunaryo
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7861

Abstract

This research is grounded in the emergence of ChatGPT technology, supported by prior and similar studies. The urgency of the issue is highlighted by previous research indicating non-convergent classification outcomes in LSTM (Long Short-Term Memory) methods due to suboptimal hyperparameter settings and limitations in understanding text data within Big Data. The presence of ChatGPT technology brings both benefits and potential misuse, such as copyright infringement, unauthorized news extraction, and violations of accountability principles. Understanding public sentiment towards the presence of ChatGPT technology is crucial. The research aims to implement the BERT (Bidirectional Encoder Representations from Transformers) method to achieve accurate and convergent sentiment analysis classification. This study involves data preprocessing stages using Natural Language Processing (NLP) techniques. Text data, already vectorized, is classified using BERT to determine public sentiment (positive, negative, neutral) towards ChatGPT technology, ensuring greater accuracy, convergence, and contextual relevance. Performance testing of the BERT model is conducted using a Confusion Matrix. With parameters set to Max Sequence Length = 128 and Batch Size = 16, the highest classification accuracy achieved is 93.4%.
Innovarte Learning: Media Pembelajaran Berbasis Augmented Reality Bagi Mahasiswa Penyandang Disabilitas Lestari, Wulan Sri; Ulina, Mustika; Gunawan, Gunawan; Gaol, Manto Lumban
Jurnal Riset dan Inovasi Pembelajaran Vol. 4 No. 3 (2024): September-December 2024
Publisher : Education and Talent Development Center Indonesia (ETDC Indonesia)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51574/jrip.v4i3.2426

Abstract

Kesenjangan akses pendidikan bagi mahasiswa penyandang disabilitas masih menjadi tantangan serius. Penelitian ini bertujuan untuk mengembangkan dan mengevaluasi efektivitas modul pembelajaran interaktif berbasis Augmented Reality (AR) yang selanjutnya disebut dengan InnovARte Learning untuk meningkatkan pemahaman dan keterlibatan mahasiswa, khususnya mahasiswa penyandang disabilitas. Proses analisis dilakukan melalui serangkaian tahapan, dimulai dengan analisis kebutuhan menggunakan Focus Group Discussion (FGD) Bersama psikolog, yang memberikan wawasan untuk desain modul. Modul yang dikembangkan mengintegrasikan teknologi AR, video pembelajaran, dan kuis berbasis permainan. Selanjutnya, implementasi modul dilakukan, disertai evaluasi melalui metode pra-eksperimen, yang melibatkan pengukuran dengan pretest, posttest, ujian, dan kuesioner. Penelitian ini dilakukan di Program Studi Teknologi Informasi Universitas Mikroskil dengan melibatkan mahasiswa reguler serta mahasiswa penyandang disabilitas, termasuk Autism Spectrum Disorder, Disabilitas Intelektual, dan Kesulitan Belajar. Hasil analisis data menunjukkan adanya peningkatan rata-rata nilai posttest dibandingkan pretest, meskipun mahasiswa dengan Disabilitas Intelektual memerlukan pendekatan tambahan untuk memahami materi. Data kuesioner menunjukkan 64,87% responden merasa modul ini efektif, mudah digunakan, dan mendukung pembelajaran fleksibel, sementara 35,12% bersikap netral. Hasil evaluasi ini menunjukkan bahwa modul InnovARte Learning merupakan inovasi yang relevan dalam mendukung pendidikan inklusif, menyediakan akses pembelajaran yang lebih mudah dan menyenangkan bagi mahasiswa penyandang disabilitas.
Peningkatan pemanfaatan sistem automasi perkantoran pada perkumpulan pemuda Theravada Indonesia Paulus, Paulus; Hanes, Hanes; Lestari, Wulan Sri; William, William
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 9, No 4 (2025): Juli
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v9i4.31982

Abstract

AbstrakPemuda Theravada Indonesia adalah perkumpulan sosial keagamaan berskala nasional dengan kepengurusan  yang tersebar di 23 provinsi di seluruh Indonesia. Organisasi ini telah memanfaatkan sistem automasi perkantoran berupa Microsoft 365 dan Google Workspace untuk organisasi nirlaba. Akan tetapi, tingkat pemanfaatan kedua sistem tersebut masih sangat rendah. Kegiatan Pengabdian pada Masyarakat ini bertujuan untuk mengeksplorasi dan mengimplementasikan solusi agar sistem automasi perkantoran dapat dimanfaatkan lebih efektif untuk mendukung kegiatan Perkumpulan. Tahapan yang dilakukan tim pelaksana mencakup analisis kondisi, merumuskan solusi, implementasi sistem, dan memberikan dukungan / pendampingan. Hasil wawancara, diskusi, observasi sistem, dan studi dokumen Perkumpulan memperlihatkan bahwa rendahnya pemanfaatan sistem automasi perkantoran disebabkan beberapa kendala. Kendala yang dimaksud yaitu belum ada pengurus Perkumpulan yang bertugas sebagai pengelola sistem / teknologi, kurangnya pelatihan sistem dan sosialisasi, dan belum ada program kerja sehubungan peningkatan sistem automasi perkantoran. Tim Pengabdian kepada Masyarakat membantu merumuskan solusi agar Perkumpulan membuat kebijakan internal tentang pemanfaatan sistem automasi perkantoran. Berdasarkan kebijakan tersebut, tim pelaksana melakukan implementasi dan kemudian memberikan dukungan / pendampingan selama implementasi. Pendampingan dilakukan dalam bentuk sosialisasi dan pelatihan yang diikuti oleh 90 anggota Perkumpulan dan dilakukan secara daring. Upaya ini membuahkan dampak positif terhadap efisiensi kegiatan, kolaborasi dan pengelolaan data Perkumpulan. Kata kunci: organisasi nirlaba; digitalisasi; automasi perkantoran; efisiensi proses; Microsoft 365. AbstractPemuda Theravada Indonesia, a national socio-religious association with branches in 23 provinces across Indonesia. This organization has utilized office automation systems such as Microsoft 365 and Google Workspace for nonprofit organizations. However, the level of utilization of both systems is still very low. This Community Service aims to explore and implement solutions to enhance the effective use of office automation systems in the Association’s activities. The Community Service Team conducted condition analysis, formulated solutions, implemented the systems, and provided support / assistance. Interviews, discussions, system observations, and document studies revealed that the low utilization of office automation systems is due to several obstacles. These obstacles include the absence of system / technology managers, lack of system training and socialization, and the absence of work programs related to the enhancement of office automation systems. The Community Service Team assisted in formulating solutions for the Association to establish internal policies on the utilization of office automation systems. Based on these policies, the implementation team carried out the implementation and subsequently provided support and assistance for the Association during the implementation. Mentoring was carried out in the form of socialization and training attended by 90 members of the Association and was carried out online. This effort has had a positive impact on the efficiency of activities, collaboration and data management of the Association. Keywords: nonprofit organization; digitalization; office automation; process efficiency; Microsoft 365.
Pelatihan Pemanfaatan Microsoft Teams Untuk Mendukung Perkuliahan Online Siagian, Hanny; Lestari, Wulan Sri; Saragih, Yuni Marlina
Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming Vol 6, No 2 (2023): Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstormin
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/japhb.v6i2.3542

Abstract

Covid-19 yang telah melanda dunia termasuk Indonesia, memberikan dampak yang terlihat nyata dalam berbagai bidang, salah satunya yaitu dalam bidang pendidikan.  Pelaksanaan pendidikan di Indonesia dalam masa pandemi Covid-19 mengalami perubahan, dimana masyarakat dituntut untuk melaksanakan pembelajaran secara online (tanpa tatap muka secara langsung) atau istilah lainnya yaitu daring (dalam jaringan/sistem pembelajaran jarak jauh). Salah satu sarana pembelajaran daring yang dapat dimanfaatkan yaitu Microsoft Teams. Namun belum semua peserta didik memahami cara penggunaan dari Microsoft Teams tersebut, sehingga dibutuhkan pelatihan pemanfaatan Microsoft Teams tersebut. Pelatihan ini berlangsung melalui video conference di Microsoft Teams bersama 40 orang mahasiswa baru. Melalui pelatihan ini diharapkan mahasiswa baru dapat mengenal dan memahami cara pembelajaran online di Mikroskil dan mengetahui cara penggunaan Microsoft Teams supaya dapat mendukung perkuliahan online nantinya. Sebelum kegiatan pelatihan, dilakukan kegiatan pre-test dan di akhir pelatihan dilakukan kegiatan post-test untuk mengukur pemahaman mahasiswa/i baru Mikroskil sebelum dan sesudah mengikuti pelatihan. Hasil penilaian pre-test memperoleh nilai rata-rata 16,91 sedangkan nilai rata-rata post-test 20,06. Hal ini menunjukkan bahwa mahasiswa/i baru memiliki gambaran mengenai pelaksanaan perkuliahan online dan mampu menggunakan tools perkuliahan online yaitu Microsoft Teams.
Penggunaan Aplikasi Microsoft Office 365 Sebagai Alat Pembelajaran Daring Wulan Sri Lestari; Hernawati Gohzali; Naca Perangin-Angin
Jurnal Mitra Pengabdian Farmasi Vol. 1 No. 3 (2022): Juni 2022
Publisher : Akademi Farmasi YPPM Mandiri

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

Abstract

Online learning is a distance learning process through the use of technology that must be done during a pandemic. The ability and skills to use information and communication technology applications are important things that must be possessed by students to be able to follow the learning process well. One of the applications in the field of information and communication technology that has features to support the online learning process is Microsoft Office 365. This application can make it easy for students to collaborate, communicate, share learning documents and view the learning outcomes that have been done. Based on the results of the questionnaire, it was found that the participants had never used Microsoft Office 365 as an online learning medium so they did not have the ability and good skills to utilize the application. To overcome this problem, in this service activity, training on the use of Microsoft Office 365 applications will be carried out in the form of workshops for 2 times and followed by task assignment activities and asynchronous task monitoring on the Microsoft Teams channel that has been determined. Then an evaluation process was carried out by giving pre-test and post-test questions when the training activities were carried out. Based on the results of the pre-test and post-test, it was found that after the training was completed there was an increase in participants' understanding of the use of Microsoft Office 365 applications such as Microsoft Teams, Outlook, OneDrive, Microsoft Forms, Microsoft Stream, Microsoft Office online.
PELATIHAN PEMROGRAMAN DASAR MENGGUNAKAN BAHASA PYTHON PADA SMK METHODIST TANJUNG MORAWA Megawan, Sunario; Lestari, Wulan Sri; Tanti, Tanti
Reswara: Jurnal Pengabdian Kepada Masyarakat Vol 5, No 1 (2024)
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/rjpkm.v5i1.3648

Abstract

SMK Swasta Methodist Tanjung Morawa merupakan salah satu sekolah swasta di bawah naungan Yayasan Methodist Kasih Imanuel Indonesia yang berdiri sejak tahun 2008. Salah satu jurusan yang ada di SMK Swasta Methodist Tanjung Morawa adalah Teknik Komputer dan Jaringan (TKJ). Sesuai dengan kurikulum yang digunakan di jurusan TKJ, pemrograman merupakan salah satu pelajaran yang harus diberikan kepada para siswa untuk mencapai dasar bidang keahlian dan dasar program keahlian. Namun, saat ini bahasa pemrograman yang sudah diberikan masih terbatas pada HTML dan Javascript saja dimana keduanya merupakan mata pelajaran pemrograman web yang hanya mencapai dasar program keahlian saja. Sedangkan untuk mencapai dasar bidang keahlian dibutuhkan pemahaman tentang pemrograman dasar lainnya, sehingga para siswa memiliki kompetensi yang lebih baik. Oleh karena itu, Fakultas Informatika Universitas Mikroskil menawarkan solusi berupa pelatihan pemrograman dasar menggunakan bahasa Python yang bertujuan untuk membantu para siswa meningkatkan kemampuan pemrograman mereka. Kegiatan pelatihan ini berlangsung selama 2 hari dan dilaksanakan di Laboratorium komputer Universitas Mikroskil dengan metode workshop/praktek langsung. Berdasarkan hasil evaluasi kegiatan pelatihan, diperoleh 86,3% siswa merasa Python mudah dipahami dan 95,5% merasa materi pelatihan yang diberikan ini bermanfaat. Selain itu, berdasarkan hasil pre-test dan post-test diketahui bahwa pengetahuan para siswa secara umum meningkat setelah mengikuti pelatihan