Claim Missing Document
Check
Articles

Found 24 Documents
Search

A comparison between Super Vector Regression, Random Forest Regressor, LSTM, and GRU in Forecasting Bitcoin Price Rifando Panggabean; Yohana Dewi Lulu Widyasari
International ABEC Vol. 2 (2022): Proceeding International Applied Business and Engineering Conference 2022
Publisher : International ABEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1170.719 KB)

Abstract

High bitcoin user volume results in high market volatility, and indicators commonly used in stock and forex transactions have low accuracy in handling bitcoin's highly volatile market. The present study aims to find out the most optimal machine learning algorithm for Bitcoin transactions by examining four algorithms: Super vector regression(SVR),Random Forest Regressor(RF),Long short-term memory(LSTM), and Gated Recurrent Unit (GRU), examined using four tests, namely Root Mean Square Error (RMSE), Mean Square Error (MSE) , Mean Absolute Error (MAE) and R-Squared(R2). The test was performed using Bitcoin data between 2014 and 2022. The test result showed that LSTM+GRU algorithm exhibited the highest accuracy, indicated by a R-squared of 94%.
The Coaching of Dunia Coding Program to Improve Computational Thinking Ability at As Shofa Junior High School Pekanbaru : Pembinaan Program Dunia Coding untuk Meningkatkan Kemampuan Computational Thinking Pada SMP As Shofa Pekanbaru Indah Lestari; Satria Perdana Arifin; Yohana Dewi Lulu Widyasari; Muhammad Mahrus Zain; Heni Rachmawati
Dinamisia : Jurnal Pengabdian Kepada Masyarakat Vol. 7 No. 1 (2023): Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/dinamisia.v7i1.12455

Abstract

Computational thinking (CT) is basic competency that must be provided to Indonesia's young generation, through integration into curriculum or extracurriculars to face the information, industrial era 4.0 or society 5.0. SMP As Shofa Pekanbaru has computer extracurriculars, but the material is only Office. This school needs programming extracurricular coaching which can be mediafor training students' CT. Therefore, in this community service program, extracurricular programming training was carried out at SMP As Shofa, namedDunia Coding. This activity produced 2 textbooks. The implementation method is an offline workshop in 12 meetings 1x/week. The results obtained were that 73.9% of students agreed that the material provided was very appropriate to their needs, 82.6% of students agreed that the program was very useful, 80.4% of students agreed that the delivery of the material was very clear, interesting, and easy to understand, and 56.5% of students agreed that the implementation time was sufficient
Sistem Monitoring Pengadaan Bahan Baku Menggunakan Metode Extreme Programming Pada Ayam Geprek Family Fitrianti; Yohana Dewi Lulu Widyasari
ABEC Indonesia Vol. 10 (2022): 10th Applied Business and Engineering Conference
Publisher : Politeknik Caltex Riau

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

Abstract

Ayam Geprek Family is one of the fast-food businesses. This business was founded in 2019 and is in Tanah Putih Tanjung Melawan. Ayam Geprek Family uses a make-to-stock business strategy, i.e., production will still be carried out without an order. Inventory of raw materials is important and very influential in the smooth production process. The condition of the high production volume has not been supported by the calculation of the optimal use of raw materials, resulting in several impacts. The main impact of the excess is the high cost of storage. On the other hand, the capital allocation for other investments cannot be done optimally. As well as the reduced quality of raw materials that are stored for too long. Therefore, handling and control are needed that can assist in monitoring the procurement of raw materials. The development of this procurement monitoring system uses material requirements planning (MRP) and forecasting techniques. System development using extreme programming (XP) approach. This research produces a system that can display information on planning and ordering raw materials in schedules and notifications to make monitoring easier. The time for system development using extreme programming becomes more effective and efficient, which is approximately 3 months. In black box testing, the system can run 100% of all features. In white box testing, the results of the Cyclomatic Complexity calculation are 18 regions for the MRP program algorithm.
Pelatihan Pengelolaan Blog dalam Peningkatan Literasi Bidang Informatika untuk Santri SMAIT Imam Syafii 2 Pekanbaru Satria Perdana Arifin; Dadang Syarif Sihabudin Sahid; Yohana Dewi Lulu Widyasari; nina fadilah najwa; Khairul Umam Syaliman
JITER-PM (Jurnal Inovasi Terapan - Pengabdian Masyarakat) Vol. 1 No. 1 (2023): JITER-PM
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (343.078 KB) | DOI: 10.35143/jiterpm.v1i1.5892

Abstract

Salah satu kompetensi dan profil lulusan Program Studi Sistem Informasi Politeknik Caltex Riau adalah pengelolaan teknologi. Perlu rasanya untuk memperkenalkan kepada masyarakat, khususnya kepada pelajar sekolah menengah atas untuk lebih mengetahui salah satu kompetensi tersebut yang ada di program studi sistem informasi. Salah satunya adalah dengan melakukan pelatihan kepada siswa-siswa SMAIT Imam Syafii 2 Pekanbaru. Ruang lingkup pelatihan adalah teknik dasar pengelolaan blog yang mana materi yang akan disampaikan meliputi teknik pembuatan artikel menggunakan media digital wordpress, menggunakan SEO dan mempublikasikan hasil tulisan yang telah dibuat. Hasil akhir dari pelatihan ini adalah siswa SMAIT Imam Syafii 2 bisa membuat blog dan mampu mengembangkan literasi di bidang informatika oleh siswa dan mengenal dengan baik mengenai salah satu kurikulum yang ada di Program Studi Sistem Informasi.
Implementasi SEM-Multiple Linear Regression dalam Prediksi Jumlah Pendaftaran Mahasiswa Baru di Perguruan Tinggi XYZ Amelia Rahmadhani; Dadang Syarif Sihabudin Sahid; Yohana Dewi Lulu Widyasari
Jurnal Nasional Teknologi dan Sistem Informasi Vol 9, No 2 (2023): Agustus 2023
Publisher : Jurusan Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v9i2.2023.150-162

Abstract

Bagi perguruan tinggi swasta (PTS), tidak menutup kemungkinan semakin banyak mahasiswa baru yang diterima, maka PTS tersebut akan terus eksis. Sebaliknya, jika PTS gagal menambah atau bahkan menurunkan jumlah mahasiswa baru setiap tahunnya, hal itu bisa berubah dengan tidak mampu beroperasi lagi bagi PTS dikarenakan pendapatan mereka satu-satunya hanya dari biaya kuliah mahasiswa. Tujuan penelitian ini diantaranya penentuan faktor-faktor yang mendukung prediksi pendaftaran mahasiswa di perguruan tinggi berdasarkan data sebelumnya, mengimplementasikan Multiple Linear Regression terhadap pendaftaran mahasiswa di perguruan tinggi, dan menganalisis tingkat akurasi hasil prediksi pendaftaran mahasiswa di perguruan tinggi. Penelitian ini menggunakan algoritma Multiple Linear Regression. Sebelum melakukan tahap prediksi, terlebih dahulu menentukan faktor-faktor yang mempengaruhi jumlah penerimaan mahasiswa baru menggunakan Structural Equation Modeling (SEM) dengan faktor promosi, biaya Pendidikan, tingkat kelulusan, informasi pendafataran, jenis kelamin dan nilai akreditasi. Berdasarkan hasil SEM didapat faktor promosi, biaya Pendidikan, tingkat kelulusan, informasi pendafataran, dan nilai akreditasi, dapat dilanjutkan ke tahap berikutnya karena faktor tersebut berpengaruh signifikan terhadap mahasiswa baru, sedangkan hasil prediksi menggunakan Multiple Linear Regression didapat bahwa nilai prediksi untuk tahun berikutnya adalah 486 orang calon mahasiswa baru, dengan hasil perhitungan MSE adalah 2657,79 dan MAE adalah 42.29, dimana semakin kecil hasil nilai MSE dan MAE yang diperoleh maka kesalahan pada sistem juga semakin sedikit serta R2 adalah 0.9280 (92,80%) menandakan bahwa pengaruh semua struktur eksogen pada struktur endogen kuat.
Manajemen Pengetahuan Melalui Web 2.0 (Wikipedia) pada Organisasi Delfi Angela; Wawan Yunanto; Yohana Dewi Lulu Widyasari
JURNAL INFOTEL Vol 9 No 3 (2017): August 2017
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v9i3.245

Abstract

Himpunan mahasiswa merupakan wadah bagi setiap mahasiswa program studi tertentu yang bertujuan untuk menampung aspirasi setiap anggotanya. Proses berbagi pengetahuan biasanya dilakukan melalui pertemuan langsung yang dilakukan di dalam kelas, diskusi, dan rapat. Sistem manajemen pengetahuan dapat mengelola dan mendokumentasikan semua pengetahuan setiap anggotanya agar proses berbagi pengetahuan tidak terhambat. Penelitian ini mengembangkan sebuah sistem manajemen pengetahuan web 2.0 dengan konsep Wikipedia. Konsep Wikipedia diterapkan untuk memungkinkan setiap anggota organisasi dalam menambah, menghapus, dan memperbaiki isi dari website. Informasi dan pengetahuan yang ada dapat dimanfaatkan dan diperbaharui secara terus menerus oleh sesama anggota organisasi. Proses manajemen pengetahuan yang digunakan pada sistem ini adalah knowledge discovery, knowledge capture dan knowledge sharing. Hasil dari pengujian User Acceptance Test yang telah dilakukan bahwa sistem manajemen pengetahuan telah dapat diterima oleh organisasi dalam membantu anggota organisasi mengembangkan pengetahuan serta mendapatkan pengetahuan yang baru.
Sistem Dashboard Segmentasi Pasar menggunakan Metode Customer Portfolio Management nina fadilah najwa; mutia sari zulvi; Yohana Dewi Lulu
Jurnal Sosioteknologi Vol. 22 No. 3 (2023): NOVEMBER 2023
Publisher : Fakultas Seni Rupa dan Desain ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/sostek.itbj.2023.22.3.9

Abstract

Business competition is getting tighter, so MSMEs use influencer marketing as a marketing strategy for their products or services. The BrandQ application is an idea designed as an influencer marketing platform to connect MSMEs and influencers. BrandQ has a solution that can make it easier for MSMEs to find the right influencer based on product or service category, target market, and demographics. In developing the BrandQ application, a customer relationship management strategy is needed using the Customer Portfolio Management (CPM) method to analyze the right target market to obtain business opportunities and anticipate the risk of business failure. The output of the CPM analysis results is the system developer’s intuitive analysis and the data analysis in the form of a market segmentation dashboard system. The system was built using data mining and the K-Means algorithm to segment the market. Based on the black box testing results, the results show that the system has been 100% successful.
Clustering Analysis of Internal and External Factors Affecting Post-Pandemic Study Duration in XYZ Educational Institution Using the Orange Application: Prediction of The Influence of Internal and External Factors on Study Duration Muluk, Imelda; Widyasari, Yohana Dewi Lulu; Amelia, Riska
Jurnal Teknologi Informasi dan Pendidikan Vol. 16 No. 2 (2023): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v16i2.804

Abstract

The COVID-19 pandemic has had a significant impact on various economic sectors in Indonesia, including the education system. Consequently, the educational landscape has undergone substantial changes, such as the shift from traditional classroom instruction to online learning. All students, regardless of their academic or non-academic backgrounds, have benefited from this transition in numerous ways. We are interested in identifying the most crucial factors that determine long-term learning outcomes and how academic and non-academic factors influence students' academic performance. The study will be conducted in October 2022 at SMK Negeri 6 Pekanbaru, and 529 out of 1400 participants will be randomly selected. We will use a Google Form with 22 questions to collect quantitative data.
Integrated production facilities clustering and time-series forecasting derived from large dataset of multiple hydrocarbon flow measurement Rangga, Adityapati; Widyasari, Yohana Dewi Lulu; Sahid, Dadang Syarif Sihabudin
Science, Technology and Communication Journal Vol. 2 No. 2 (2022): SINTECHCOM Journal (February 2022)
Publisher : Lembaga Studi Pendidikan and Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v2i2.207

Abstract

In the complex, mature, and large oilfields, there is a need for Integrated solution in order to have a helicopter view of entire facilities throughput. The real time metering information provides an on-demand daily data and trend. However, it is rarely being connected to analytics solution for business intelligence such as, prediction, optimization, decision support and forecast. This paper cover about exploratory data analysis of large dataset of multiple hydrocarbon facilities metering within integrated network, performing multi-feature data clustering and making a time-series forecasting techniques. K-means and PCA are combined to make cluster of production facilities which resulted with gas processing cluster, high oil producer, high water processing station, and the lowest performer in term in hydrocarbon processing. Furthermore, VAR and LSTM are compared as forecasting tools for day-to-day fluid prediction, to maintain normal operational scenario.
PRISMA-Guided Systematic Review on Machine Learning for University Student Dropout Prediction Elza, Sari Fauzia; Widyasari, Yohana Dewi Lulu
ABEC Indonesia Vol. 12 (2024): 12th Applied Business and Engineering Conference
Publisher : Politeknik Negeri Bengkalis

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

Abstract

This systematic review examines the application of machine learning techniques to predict students dropout.The prisma 2020 guidelines were followed to ensure a comprehensive and transparent review process. As the behaviour ofstudents who drop out becomes increasingly complex due to factors such as academic performance, personal characteristicsand socio-economic conditions, machine learning offers promising solutions for the early identification of students at risk.This review summarises findings from peer-reviewed studies published between 2014 and 2024 and indexed in the scopusdatabase. The focus is on the performance, strengths and limitations of different machine learning models such as decisiontrees, support vector machines and neural networks. The selection of the 2014-2024 timeframe reflects the significantadvances in machine learning technologies, the improved quality and availability of educational data, and the evolvingresearch trends in education. This timeframe also coincides with changes in education policy and ensures that the studycaptures current and relevant findings. The report concludes with recommendations for future research, including theintegration of complex data characteristics and the development of universal models that can be adapted to different studentpopulations.