Claim Missing Document
Check
Articles

An Approach of Brain-Computer Interface Electroencephalography for Measuring Visual Height Intolerance Moch Yusuf Asyhari; Dhomas Hatta Fudholi; Fery Luvita Sari
JUITA : Jurnal Informatika JUITA Vol. 9 No. 1, May 2021
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1163.818 KB) | DOI: 10.30595/juita.v9i1.8314

Abstract

The environment is one factor that influences the quality of life, including a high environment for people with the fear of height (Visual Height Intolerance, VHI). Currently, VHI is measured by using the Visual Height Intolerance Severity Scale (VHISS). The lack of evidence-based testing makes these measurements feel weak and less meaningful. The use of Virtual Reality (VR) and Electroencephalography (EEG) based on the Brain-Computer Interface (BCI) deserves to be tested. The test is done by reading the human brain's electrical activity using a BCI-based EEG when given VR exposure. The analysis process uses a simple wave concept. Furthermore, the correlation study was carried out using the Spearman-rho method with a consideration of the normality test, which produced non-parametric data. The correlation test results show that the BCI-based EEG biometric data in the form of the amount of waves per time and magnitude has a strong relationship with the VHISS scale. The higher the number of waves per time, the higher the amplitude, the higher the VHISS scale. The evaluation was carried out by examining the correlation based on the demographics of age and gender. Finally, EEG based on BCI and VR can be an alternative and concrete evidence to review the level of visual height intolerance other than VHISS.
Analisis Penerapan Model Business Intelligence pada Aplikasi Payment Point Online Banking dalam Meningkatkan Strategi Pemasaran (Studi Kasus: Aplikasi ApotikKuota) Altesa Yunistira; Dhomas Hatta Fudholi
Jurnal Ilmu Komputer & Agri-Informatika Vol. 7 No. 1 (2020)
Publisher : Departemen Ilmu Komputer - IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (647.731 KB) | DOI: 10.29244/jika.7.1.1-10

Abstract

Perkembangan bisnis era digital saat ini membuat stakeholder aplikasi ApotikKuota menyadari besarnya tantangan dalam dunia bisnis. Saat ini, data merupakan hal yang berharga dan memiliki nilai penting sehingga membuat stakeholder ApotikKuota memiliki fokus pada penanganan data yang baik. Data tersebut antara lain berupa transaksi penjualan, pelanggan, serta data lainnya yang akan berguna dalam pengambilan keputusan dalam penerapan strategi pemasaran. Selama ini, penanganan pemasaran didasarkan pada intuisi stakeholder tanpa melihat manfaat dari proses analisis data yang ada. Business intelligence menjadi solusi bagi perusahaan atau organisasi untuk menganalisis dan menyediakan akses ke data guna membantu mengambil keputusan secara lebih baik. Dalam penelitian ini, peneliti merancang dan membangun model business intelligence untuk mendukung strategi pemasaran pada bisnis payment point online bank. Penelitian ini dilakukan untuk mengkaji penerapan business intelligence dengan membuat dashboard pelaporan dan online analytical processing untuk membantu stakeholder mengambil keputusan. Hasil penelitian ini berupa penyajian informasi yang dibutuhkan oleh stakeholder dalam proses pengambilan keputusan dengan mengacu pada penerapan strategi bauran pemasaran (marketing mix) yang memiliki komponen 4P, yaitu price, product, place, dan promotion. Kata Kunci: business intelligence, dashboard, payment point online bank, strategi pemasaran, pengambilan keputusan
Analisis Topik Penelitian Kesehatan di Indonesia Menggunakan Metode Topic Modeling LDA (Latent Dirichlet Allocation) Yoga Sahria; Dhomas Hatta Fudholi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 2 (2020): April 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (842.85 KB) | DOI: 10.29207/resti.v4i2.1821

Abstract

In this time, the need of research, the development and the implementation of the result of research in health is increasing both from the researchers, the government, the academic even of from the public general. One of the ways to find out the health research trend is by topic modeling. The method that used in this research is topic modeling LDA (Latent Dirichlet Allocation) method. The purpose of this research is to identify how modeling topic method LDA analyze modeling topic to some health research in Indonesia by Sinta Journal and to know how the coherence value in each topic of the model that has been made. Besides, hopefully it can be used as a reference to do heath research in Indonesia based the topic that has been modeled. The development of this research uses Anaconda3 Python Programming Language Tools and utilizes the LDA library that provided to get the topic model. To examine the result of this research the respondent are medical worker, health researcher and academics. The result of this research the topic modeling that used 94,1% respondent say very good and 5,9% say good.
Pengembangan Aplikasi Virtual Reality dengan Model ADDIE untuk Calon Tenaga Pendidik Anak dengan Autisme Dhomas Hatta Fudholi; Rahadian Kurniawan; Dimas Panji Eka Jalaputra; Izzati Muhimmah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 4 (2020): Agustus 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (782.079 KB) | DOI: 10.29207/resti.v4i4.2092

Abstract

Knowledge is needed for children with special needs to support their quality of life. This is a challenge for prospective educators / prospective teachers. A deeper knowledge is needed to really understand children with special needs. This research is carried out to develop a skill simulator application for autistic child’s prospective educator using Virtual Reality technology. This application will be used as a teaching medium which incorporates motion sensor tools. The sensors will make the virtual application looks realistic. The application was developed using the ADDIE method (Analysis, Design, Development, Implementation and Evaluation). The application development begins with discovering the characteristic of autistic children. This is done to formulate the learning materials. The knowledge base of the autistic children was obtained from the Sekolah Luar Biasa (SLB). By using the obtained knowledge, storyboard was designed and implemented. The developed application has been evaluated by 16 prospective child educators with autism and two professional experts. In general, the application can help prospective educators understand the characteristics of children with autism. Moreover, it provides a safe and pleasant teaching skill practice for the prospective educators.
Realtime Object Detection Masa Siap Panen Tanaman Sayuran Berbasis Mobile Android Dengan Deep Learning Andri Heru Saputra; Dhomas Hatta Fudholi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 4 (2021): Agustus 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (591.055 KB) | DOI: 10.29207/resti.v5i4.3190

Abstract

Determining the harvesting period can be done visually, physically, computationally, and chemically. Since the harvesting process is crucial, late harvesting will affect post-harvest and production quality. Leafy vegetables have a relatively short ready-to-harvest period. Visual recognition of the harvesting period combined with image processing can recognize harvesting vegetables' visual characteristics. This study aims to build a deep learning-based mobile model to detect real-time vegetable plant objects such as bok choy, spinach, kale, and curly kale to determine whether these vegetables are ready for harvest. Mobile-based architecture is chosen due to latency, privacy, connectivity, and power consumption reason since there is no round-trip communication to the server. In this research, we use MobileNetV3 as the base architecture. To find the best model, we experiment using different image input size. We have obtained a maximum MAP score of 0. 705510 using a 36,000 image dataset. Furthermore, after implementing the model into the Android mobile application, we analyze the best practice in using the application to capture distance. In real-time detection usage, the detection can be done with an ideal distance of 5 cm and 10 cm.
Prediksi Harga Saham Menggunakan BiLSTM dengan Faktor Sentimen Publik Nurdi Afrianto; Dhomas Hatta Fudholi; Septia Rani
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 1 (2022): Februari 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (441.866 KB) | DOI: 10.29207/resti.v6i1.3676

Abstract

Stock market is one economic driver. It has roles in growth and development of a country. Stock is an attractive investment due to the huge profit. Many people buy and sell their stock. Stock investors try to choose the good investment company to get profits with small risk. Therefore, stock investors need to be careful and must evaluate a company. With machine learning technology, stock prediction problems can be solved. Deep learning is a subset of machine learning with own network. Deep learning has good performance in managing large amounts of data. This study used stock price history data and public sentiment data on a company. The method used in this research is Bidirectional Long-Short Term Memory (BiLSTM). The features used were closing price and compound score value of the public sentiment. Four scenarios were used in finding the best predictive model. The four scenarios use the same test data with different lengths of training data window. From the modelling, predictions with the model built using BiLSTM resulted in the smallest MSE value of 0.094 and the smallest RMSE value of 0.306.
ANALISIS SPASIAL PERSEBARAN REKLAME Gunanto Gunanto; Dhomas Hatta Fudholi; Lizda Iswari
JITU : Journal Informatic Technology And Communication Vol 3 No 1 (2019)
Publisher : Universitas Boyolali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36596/jitu.v3i1.56

Abstract

Regional autonomy is the surrender of authority from the center to the regions to regulate and manage the interests of the local community according to their own initiatives based on the aspirations of the people, as stated in Law No. 32 of 2004 concerning Regional Government. With the existence of regional autonomy, the regional government is expected to be better to explore the potential of local revenue sources in financing all regional development activities through increasing Original Local Government Revenue (OLGR). One component of OLGL that has a contribution in Pekalongan Regency is Regional Tax. Regional tax, one of which is advertisement tax, is one component of the OLGL that contributes to regional development. Clustering algorithm, one of which is k-means clustering can be applied to advertisement tax data so that it can be known that ad grouping is based on distance from the market, distance to traffic light and vehicle volume. From each of these groupings can also be seen each of the characteristics so that it is known which groups have the largest amount of tax and the number of tax donations. From this research, a web-based system has been successfully developed that is able to process the spatial analysis of the distribution of billboards with the clustering method in Pekalongan Regency. From the results of clustering analysis, it can be seen that the Subdistrict passed by the coastline has a correlation with the high amount of advertisement tax in Pekalongan Regency, this can be seen in the results of clustering using the k-means algorithm, where advertisements are in clusters that have average quantities the highest taxes are all in the sub-district that is crossed by north coast way. The closeness to the market and traffic light has a correlation with the high amount of billboard bill advertising tax in Pekalongan Regency, wherein the clusters that have the highest volume of vehicles the average size of the billboard tax is high.
Perbandingan Penggunaan Algoritma Machine Learning pada Prediksi Tren Harga Saham Netflix Harry Akbar Al Hakim; Dhomas Hatta Fudholi
AUTOMATA Vol. 2 No. 2 (2021)
Publisher : AUTOMATA

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

Abstract

Salah satu instrumen finansial yang cukup dikenal dan digandrungi oleh masyarakat adalah saham, karena mampu memberikan keuntungan yang besar. Selama pandemi Covid-19 pertumbuhan investor saham di Indonesia mencapai 27% dalam waktu satu tahun. Namun untuk bisa mendapatkan keuntungan investor harus mampu melihat tren harga saham yang sedang terjadi untuk dapat memaksimalkan keuntungan. Penelitian ini bertujuan mencoba memprediksi tren pergerakan harga saham menggunakan pendekatan algoritma deep learning. Algoritma yang digunakan akan dibandingkan satu sama lain untuk  mengetahui algoritma mana yang efektif untuk memproses data saham. Algoritma yang akan dibandingkan adalah Linear Regression, Decision Tree Regression serta Long Short Term Memory (LSTM). Data yang akan digunakan adalah data saham Netflix, Inc (NFLX) yang merupakan saham dari bursa saham NASDAQ. Didapatkan hasil bahwa model LSTM mempunyai nilai RMSE 10.834, Linear Regression dengan nilai RMSE 11.906 dan Decision Tree Regression dengan nilai RMSE 36.679. Kesimpulan yang dapat diambil adalah performa algoritma LSTM yang khusus dikembangkan untuk memproses data time series dapat mengungguli kedua algoritma lainnya.
Implementasi Arsitektur Transformer pada Image Captioning dengan Bahasa Indonesia Umar Abdul Aziz Al-Faruq; Dhomas Hatta Fudholi
AUTOMATA Vol. 2 No. 2 (2021)
Publisher : AUTOMATA

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

Abstract

Abstract—Penelitian image captioning untuk menghasilkan deskripsi yang baik pada gambar dalam Bahasa Inggris banyak dilakukan. Sedikit penelitian yang ditemukan mengenai image captioning untuk menghasilkan deskripsi gambar dalam Bahasa Indonesia. Penelitian ini akan berfokus dalam mengembangkan model generative yang menggabungkan natural language preprocessing dan computer vision untuk menghasilkan deskripsi gambar dalam Bahasa Indonesia. Model yang digunakan dalam penelitian ini adalah attention mechanism dengan arsitektur transformer. Model penelitian ini menggunakan dataset MS COCO captions 2014 yang sudah diterjemahkan dan memperoleh skor rata-rata BLEU-1, BLEU-2, BLEU-3, BLEU-4 masing-masing adalah 31.12, 32.31, 42.39, 46.16.
Segmentasi Karakteristik Pelanggan menggunakan Teknik Clustering pada Bisnis On Demand Service Sigit Nugroho; Dhomas Hatta Fudholi; Lizda Iswari
Jurnal Pendidikan Teknologi Informatika dan Sains Vol 1 No 2 (2019): Journal of Education Informatic Technology and Science (JeITS)
Publisher : Faculty of Teacher Training and Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (351.056 KB)

Abstract

Dalam sebuah bisnis, pengetahuan terkait karakteristik pelanggan adalah menjadi mutlak untuk diketahui, untuk mengetahui hal itu dibutuhkan sebuah metode yaitu marketing mix for big data management framework. Sumber data dalam penelitian ini diambil dari perusahaan start up di Yogyakarta yang memiliki model bisnis on demand service berbasis aplikasi, fungsi utama aplikasi ini untuk mempertemukan antara Partner dan Customer terkait kendala aktifitas rutin rumah. Terdapat 5 variabel yang digunakan, yaitu rata – rata rating Partner (skala 1-5), rata- rata selisih jarak order dan workshop, rata – rata selisih waktu order dan pengerjaan, jumlah order, dan rata – rata biaya transaksi. Data diambil dari rentan waktu mei 2017 sampai dengan juli 2019, terdapat 1697 jumlah customer, 302 jumlah partner, dan 1483 jumlah traksaksi, pengolahan data menggunakan k-means, membentuk 4 kluster untuk setiap jenis pelanggan (Partner dan Customer), dimana hasil dari analisis data tersebut memberikan rujukan kepada pihak marketing perusahaan dalam pembuatan model pelanggan potensial.
Co-Authors Abdullah Aziz Sembada Abdullah Aziz Sembada ABDURRAHIM Abyan Fadilla Noor Aditya Perwira Joan Dwitama Affan Taufiqur Afrianto, Nurdi Ahmad Fathan Hidayatullah, Ahmad Fathan Ahmad Luthfi Ahmad Rafie Pratama Altesa Yunistira Andi Wafda Andri Heru Saputra Annisa Zahra Ari Farhan Nurihsan Ari Sujarwo Arief Rahman Arrie Kurniawardhan Arrie Kurniawardhani Arrie Kurniawardhani Chandra Kusuma Dewa Dendy Surya Darmawan Deny Rahmalianto Dimas Adi Wibowo Dimas Danu Budi Pratikto Dimas Pamilih Epin Andrian Dimas Panji Eka Jalaputra Dirgahayu, Raden Teduh Dziky ridhwanulah Eko Prasetio Widhi Eko Setiawan Erin Eka Citra Fahmi Adi Nugraha Ferdian Nursulistio Fery Luvita Sari Gilang Persada Bhagawadita Gunanto Gunanto Harry Akbar Al Hakim Ibnu Fajar Arrochman Insanur Hanifuddin Iqbal Syauqi Mubarak Izzan Yattaqi Nugraha Izzati Muhimmah Jaka Nugraha LAILA KUSUMA WARDANI Lizda Iswari M. Ulil Albab Surya Negara Malik Abdul Aziz Mawar Hardiyanti Meilita . Moch Bagoes Pakarti Moch Yusuf Asyhari Muhammad Abyanda Tamaza Muhammad Habib Izdhihar Muhammad Rizhan Ridha Muhammad Sulthon Alif Novian Mahardika Putra Prastyo Eko Susanto Purwoko, Agus Raden Teduh Dirgahayu Rahadian Kurniawan Rakhmat Syarifudin Rendy Ressa Sutrisno Ridho Iman Tiyar Ridho Rahmadi Risca Naquitasia Royan Abida N. Nayoan Sabar Aritonang Rajagukguk Safira Yuniar Putri Buana Salma Aufa Azaliarahma Salsabila Zahirah Pranida Septia Rani Septia Rani Sigit Nugroho Siti Mutmainah Siwi Cahyaningtyas Sri Mulyati Teduh Dirgahayu Tri Handayani Umar Abdul Aziz Al-Faruq Wahyu Fajrin Mustafa Wahyuzi, Zikri windi astriningsih Yasmin Aulia Ramadhini Yoga Sahria Yudi prayudi Yurio Windiatmoko