Claim Missing Document
Check
Articles

VEHICLE VOLUME FORECASTING SYSTEM ON TOLL ROADS USING DOUBLE MOVING AVERAGE AND DOUBLE EXPONENTIAL SMOOTHING METHODS: CASE STUDY AT JASAMARGA PANDAAN TOLL ROAD Mesach Habel Wiyono Pranataningtyas; Yosep Agus Pranoto; Deddy Rudhistiar
International Journal of Computer Science and Information Technology Vol. 1 No. 1 (2024): IJCOMIT Vol 1 No 1
Publisher : Computer Science Department, Malang National Institute of Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/ijcomit.v1i1.6722

Abstract

Forecasting or forecasting has been used as one of the considerations, especially in the field of business and economics. This is done so that company losses can be minimized and company profits can be maximized. Therefore we need a system that can make it easier to get accurate forecasting results. However, in real cases procurement of IT consultants requires quite expensive costs. So the research provides a solution to design a website-based vehicle volume forecasting system on toll roads conducted at PT. Jasamarga Pandaan Tol. This system is expected to facilitate the Traffic Collection team in projecting the volume of vehicles on toll roads in the future. The method used in forecasting vehicle volume is the Double Moving Average and Double Exponential Smoothing methods. The Double Moving Average method is a time series method where the results of this method are influenced by the order or time period. The Exponential Smoothing method is a time series method where the results of this method are influenced by the alpha parameter. The results of these two methods will be compared based on the accuracy of the data so that the user can easily see the results of forecasting vehicle volume in the future. Mean Absolute Percentage Error (MAPE) is the absolute (absolute) average percentage error. Definition of Mean Absolute Percentage Error is a statistical measurement of the accuracy of estimates (predictions) in forecasting methods. The results of the accuracy of applying the Double Moving Average method give an average MAPE value of 30,124% and the Double Exponential Smoothing method gives an average MAPE value of 5,368%.
STOCK PRICE PREDICTION FOR BANK SYARIAH INDONESIA USING BIDIRECTIONAL LONG SHORT-TERM MEMORY (BI-LSTM) Deddy Rudhistiar; Muhammad Hasan Wahyudi; Widhy Wahyani; Thesa Adi Saputra Yusri
International Journal of Computer Science and Information Technology Vol. 1 No. 2 (2024): IJCOMIT Vol 1 No 2
Publisher : Computer Science Department, Malang National Institute of Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/ijcomit.v1i2.12320

Abstract

The evolution of global financial markets has heightened the demand for accurate stock price prediction methods, particularly in the Islamic banking sector, which operates under unique principles of Sharia compliance. This study aims to predict the stock prices of Bank Syariah Indonesia (BSI) using a Bidirectional Long Short-Term Memory (Bi-LSTM) model. The dataset comprises daily closing prices from January 2022 to June 2024. The model is optimized through systematic hyperparameter tuning, including configurations for the number of layers, neurons, batch size, learning rate, and optimizers. Evaluation using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) identifies the Adam optimizer with a learning rate of 0.001 and batch size of 16 as the optimal configuration. The results highlight that while increasing the number of neurons or layers reduces minimum error, it increases model instability. This research provides novel insights into the application of Bi-LSTM for predicting Islamic banking stock prices, supporting data-driven decision-making in the Islamic financial sector.
DEVELOPMENT OF A WEB-BASED REGISTRATION SYSTEM AT THE TUNJUNGSEKAR SUBDISTRICT OFFICE Deddy Rudhistiar; Muhammad Hasan Wahyudi; Cornelia Luba Tara Boro; Siti Mutiara; Thesa Adi Saputra Yusri
International Journal of Computer Science and Information Technology Vol. 2 No. 1 (2025): IJCOMIT Vol 2 No 1
Publisher : Computer Science Department, Malang National Institute of Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/ijcomit.v2i1.14171

Abstract

The Tunjungsekar subdistrict office regularly organizes various activities involving local participants. Currently, the registration process is conducted using Google Forms, which, while facilitating data collection, presents challenges such as duplicate registrations and difficulties in managing participant quotas. Additionally, participant data processing and activity summaries are still handled manually, reducing administrative efficiency. To address these issues, a web-based registration system was developed using PHP with the Laravel framework and a MySQL database. This system enables automatic validation to prevent duplicate registrations and allows for more effective participant quota management. Blackbox taesting shows that the system works, the system functions properly without significant bugs or errors. With this system, activity data management becomes more structured, participant records are more accurate, and administrative processes are more efficient. The implementation of this system is expected to support the digitalization of community services and enhance the community’s experience in accessing information and services more practically and systematically
Designing an Android-Based Teacher Attendance System to Improve The Quality of Learning in Vocational High Schools Mochammad Ibrahim Ashari; Deddy Rudhistiar; Ni Putu Agustini; Reiny Ditta Myrtanti; Sujianto
TAAWUN Vol. 5 No. 01 (2025): TA'AWUN FEBRUARY 2025
Publisher : Pusat Penelitian Pengabdian Pada Masyarakat Sekolah Tinggi Ilmu Tarbiyah Al-Fattah Siman Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37850/taawun.v5i01.794

Abstract

This service aims to overcome problems in attendance management at SMK PGRI Sumber Pucung, which is currently still using a manual system, so it can potentially cause recording errors, time inefficiencies, and the risk of data loss during the archiving process. Therefore, as a solution to the existing problem, an Android-based attendance system was developed, where the method applied is the waterfall method, with the implementation carried out in stages starting from problem identification to system evaluation. The results of the service show that the system has succeeded in increasing the efficiency of daily attendance recording time by 66.67% and increasing the recording accuracy by up to 80%, so that this android-based attendance system can overcome problems in manual attendance management at SMK PGRI Sumber Pucung, and can be implemented as a solution to help the school administration process. Attendance system testing shows effective performance and runs well across various platforms. In the admin dashboard test, the test on the student attendance application from 3 test scenarios was successfully carried out as expected, then the test on the student attendance application consisting of 6 scenarios was also successfully carried out according to expectations. Functional testing on the web browser, admin dashboard, and functional testing on the teacher attendance application which has the same scenario, totaling 14, was successfully carried out according to expectations. Testing on the student attendance application that has 4 scenarios was successfully carried out according to expectations.
Classification of Palm Fruit Ripeness Level Using Learning Vector Quantization (LVQ) Method Rudhistiar, Deddy; Wahyani, Widhy; Yusri, Thesa Adi Saputra
Journal of INISTA Vol 6 No 1 (2023): November 2023
Publisher : LPPM Institut Teknologi Telkom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/inista.v6i1.1273

Abstract

The implementation of Learning Vector Quantization (LVQ) to classify the ripeness of oil palm fruits is investigated in this study. In addition, this study provides a comprehensive set of procedures ranging from data collection and pre-processing to training and testing of the LVQ model, and finally, the proposed method has been validated by testing it on previously unseen data. Three feature extraction methods, specifically Gray-Level Co-occurrence Matrix (GLCM), Hue, Saturation, and Value (HSV), and t-Distributed Stochastic Neighbor Embedding (t-SNE), were assessed for their performance. The results show that the chosen feature extraction method strongly influences the classification performance. The accuracy of the model employing t-SNE features is notably the highest at 50%, indicating its efficacy in identifying the ripeness level of palm fruits by extracting pertinent features. On the other hand, the GLCM feature has a 40% accuracy in the test data, suggesting that although it captures information on texture, it may not comprehensively encapsulate ripeness characteristics. Additionally, the HSV feature achieves an accuracy of 45%, which is less precise than that of t-SNE. To conclude, this study elucidates the appropriateness of various feature extraction techniques in categorizing the degree of ripeness in palm fruits. The t-SNE feature extraction model stands out as the most efficient option, exhibiting greater precision in comparison to other methodologies.
Implementasi Game Tebak Gambar Binatang Berbasis Android Sebagai Media Pembelajaran Anak Usia Dini Prasetya, Renaldi Primaswara; Wahyuni, Febriana Santi; Rudhistiar, Deddy
Journal Of Computer Science Contributions (JUCOSCO) Vol. 4 No. 1 (2024): Januari 2024
Publisher : Lembaga Penelitian, Pengabdian kepada Masyarakat dan Publikasi Universitas Bhayangkara Jakarta Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31599/w7pdmm55

Abstract

The increasingly rapid development of technology, especially mobile phone devices has targeted all groups, including young children aged 3 to 5 years, so like it or not,parents have to supervise their children. But in reality, technology cannot be avoided. As a parent, the most important thing right now is how to ensure that the mobile devices playing with children can be handled well and have a positive impact on their children, although supervision is still needed. Supervision of children who are already at school cannot be carried out continuously. At school, parents can only expect for the teachers as their second parents. Teachers as educators must be able to provide understanding to Kindergarten children, thus the use of cellphones can be used for positive things, one of which is by providing mobile game-based learning media. The problem is that there are only a few mobile applications in the form of games that provide simple learning media for Kindergarten children. Through this service, an Android-based educational game of animal picture guessing will be designed and developed as a learning medium for children aged 3-5 years. To determine the impact of implementing the application, implementation and testing were carried out, where the average System Usability Scale (SUS) score from 15 respondents was 88.33, and when referring to the usability scale value range it can be concluded that the animal picture guessing game that has been developed falls into the category acceptable or well accepted with a fairly significant impact category. Meanwhile the functionality also meets the needs of its users.
DIGITALISASI PEMASARAN BAKPIA PADA USAHA MIKRO KECIL MENENGAH (UMKM) BIMA BAKERY Wahyani, Widhy; Rudhistiar, Deddy; Asmoro, Wahyu Panji; Basuki, Diah Wilis Lestarining
Community Development Journal : Jurnal Pengabdian Masyarakat Vol. 5 No. 4 (2024): Volume 5 No. 4 Tahun 2024
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/cdj.v5i4.31142

Abstract

Kegiatan pengabdian masyarakat ini bertujuan untuk meningkatkan strategi pemasaran produk Bakpia pada Usaha Mikro Kecil Menengah (UMKM) Bima Bakery dengan menerapkan sistem e-commerce. Pandemi COVID-19 telah berdampak signifikan terhadap penjualan bakery, yang mengakibatkan penurunan drastis dan memerlukan strategi pemasaran yang inovatif. Pengembangan dan implementasi platform e-commerce diharapkan dapat meningkatkan penjualan dan meningkatkan keterlibatan pelanggan. Metode yang digunakan dalam pengabdian masyarakat ini adalah pendekatan kualitatif deskriptif, yang melibatkan pengumpulan data melalui observasi langsung, wawancara, dan dokumentasi. Kegiatan ini berlangsung selama tiga minggu di UMKM Bima Bakery di Pasuruan, Jawa Timur. Hasilnya menunjukkan bahwa implementasi e-commerce telah berhasil meningkatkan penjualan dan memperluas jangkauan pasar UMKM Bima Bakery. Selain itu, kegiatan ini mengidentifikasi beberapa tantangan, termasuk menjaga kualitas produk dan mengelola transaksi online secara efektif. Kesimpulan yang diambil dari pengabdian masyarakat ini adalah bahwa digitalisasi strategi pemasaran melalui e-commerce memiliki dampak positif yang signifikan terhadap penjualan dan kepuasan pelanggan. Namun, perbaikan lebih lanjut diperlukan dalam mengelola transaksi online dan menjaga kualitas produk untuk memastikan pertumbuhan yang berkelanjutan. Inisiatif ini menyoroti pentingnya mengadopsi strategi pemasaran modern dalam bisnis kecil untuk beradaptasi dengan kondisi pasar yang berubah dan perilaku konsumen, terutama dalam konteks pandemi yang sedang berlangsung. Dengan memanfaatkan e-commerce, UMKM Bima Bakery dapat lebih baik memenuhi kebutuhan pelanggan dan tetap kompetitif di pasar yang berkembang pesat.
OPTIMALISASI STRATEGI PEMASARAN PRODUK BAKPIA PADA UMKM BIMA BAKERY MELALUI IMPLEMENTASI SISTEM E-COMMERCE Wahyani , Widhy; Rudhistiar, Deddy; B, Diah Wilis L.
Jurnal Review Pendidikan dan Pengajaran Vol. 7 No. 3 (2024): Vol. 7 No. 3 (2024): Volume 7 No 3 Tahun 2024 (Special Issue)
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jrpp.v7i3.32044

Abstract

Penelitian ini berfokus pada pengoptimalan strategi pemasaran produk Bakpia di UMKM Bima Bakery melalui penerapan sistem e-commerce. Penelitian ini menggunakan metode kualitatif deskriptif dengan teknik pengumpulan data yang mencakup observasi, wawancara, dan dokumentasi. Temuan penelitian menunjukkan bahwa penggunaan e-commerce dapat meningkatkan produktivitas penjualan Bakpia di UMKM Bima Bakery serta mempermudah konsumen dalam proses pembelian dan pembayaran. Implementasi strategi e-commerce ini tidak hanya meningkatkan efisiensi operasional tetapi juga memperluas jangkauan pasar secara signifikan, memungkinkan UMKM Bima Bakery untuk mencapai konsumen di luar wilayah lokal. Penelitian ini juga mengungkapkan bahwa penggunaan platform e-commerce dapat meningkatkan kepuasan dan loyalitas pelanggan, karena konsumen dapat dengan mudah mengakses informasi produk, melakukan pemesanan, dan memilih metode pembayaran yang diinginkan. Dengan demikian, sistem e-commerce menjadi solusi yang efektif dan efisien untuk mengatasi tantangan pemasaran di era digital, membantu UMKM Bima Bakery tetap bersaing di pasar yang semakin kompetitif.
IMPLEMENTASI WEBSITE PPDB DALAM MENDUKUNG DIGITALISASI LAYANAN ADMINISTRASI SEKOLAH DI SMK PGRI SUMBERPUCUNG MALANG Dwi Agustina, Fransisca; Edwin Tjahjadi, Martinus; Purwanto, Hery; Rudhistiar, Deddy; Himawan Subiyanto, Krishna
Jurnal Pengabdian Masyarakat FKIP UTP Vol 7 No 1 (2026): PROFICIO : Jurnal Abdimas FKIP UTP
Publisher : FKIP UNIVERSITAS TUNAS PEMBANGUNAN SURAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36728/jpf.v7i1.6004

Abstract

Proses penerimaan peserta didik baru di sekolah menengah kejuruan (SMK) masih banyak dilakukan secara manual, sehingga berpotensi menimbulkan keterlambatan layanan, kesalahan pencatatan data, serta keterbatasan akses informasi bagi masyarakat. Kondisi tersebut mendorong perlunya penerapan teknologi informasi untuk meningkatkan efektivitas dan transparansi layanan administrasi sekolah. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk merancang dan mengimplementasikan website penerimaan peserta didik baru sebagai sarana digitalisasi layanan administrasi di sekolah. Metode pelaksanaan dilakukan melalui tahapan analisis kebutuhan, perancangan sistem, pengembangan website, uji coba, pelatihan pengguna, serta pendampingan selama implementasi. Hasil kegiatan menunjukkan bahwa website yang dikembangkan mampu memfasilitasi proses pendaftaran secara daring, pengelolaan data calon peserta didik, unggah dokumen persyaratan, serta penyampaian informasi hasil seleksi secara lebih cepat dan terstruktur. Sistem ini meningkatkan efisiensi kerja panitia penerimaan siswa dan memudahkan akses layanan bagi calon peserta didik dan orang tua. Simpulan dari kegiatan ini menunjukkan bahwa implementasi website penerimaan peserta didik baru menjadi solusi efektif dalam mendukung digitalisasi layanan administrasi sekolah dan berpotensi diterapkan secara berkelanjutan.
Comparative Study of Lightweight Deep Learning Architectures for Potato Plant Disease Detection Faisol, Ahmad; Rudhistiar, Deddy; Puspasari, Betty Dewi
PYTHAGORAS Jurnal Matematika dan Pendidikan Matematika Vol. 20 No. 2 (2025)
Publisher : Department of Mathematics Education, Faculty of Mathematics and Natural Sciences, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/pythagoras.v20i2.90854

Abstract

Potato leaf diseases pose a significant threat to crop productivity and global food security, necessitating accurate and reliable diagnostic systems for early detection. Although deep learning based image classification has shown promising results in plant disease recognition, many existing studies rely on simple train test splits, insufficient handling of class imbalance, and limited statistical analysis. This study presents a comprehensive evaluation of multiple pretrained convolutional neural network architectures for multi class potato leaf condition classification, including disease categories and a healthy class. DenseNet121, EfficientNetV2 S, InceptionV3, MobileNetV3 Small, ResNet50, and Xception were evaluated using a stratified K fold cross validation framework. Class imbalance was addressed through class weighted loss functions, and model performance was assessed using accuracy, macro averaged F1 score, and weighted F1 score reported as mean values with 95% confidence intervals. The experimental results indicate that ResNet50 achieved the best overall performance with a mean accuracy of 99.07% ± 0.38% and a macro F1 score of 98.24% ± 0.80%, demonstrating strong and consistent classification across all classes. Lightweight architectures such as MobileNetV3 Small also delivered competitive results with an accuracy of 97.77% ± 0.59%, highlighting their suitability for deployment in resource constrained agricultural environments. These findings emphasize the importance of statistically robust evaluation and imbalance aware training strategies for developing reliable deep learning based systems in precision agriculture.
Co-Authors Adzdziqri, Tareh Rozzaq Agung Panji Sasmito Agung Prasetyo, Yudha Ahmad Fahrudi Setiawan AHMAD FAISOL Alfin Ardiansyah Alfino Raditya Amanullah Amar Rizqi Afdholy Amar Rizqi Afdholy Anang Ansyori Annisa Yuniar Ardian Arya Putra, Rio Aria Pramudia Eka Sakti Arya Wardhana, Rama Asmoro, Wahyu Panji B, Diah Wilis L. Bangko, Yohanes Yudha Saputra Betty Dewi Puspasari Bhakti Widiatama, Manggala Bintang Aqil Mahendra Boro, Cornelia Luba Tara Cornelia Luba Tara Boro Danar Pratiyksa, I Made Dedy Irawan, Josep Deviany Kartika Diah Wilis Lestarining Basuki Dwi Agustina, Fransisca Dwi Fathur Rohman, Agung Dwi Yulianto, Afri Edwin Tjahjadi, Martinus Eka Budiani, Renata Enusjaya Putra, Arga Erlangga Prasetya, Imam Erwinda, Gesha Warilotte F.X Ari Wibisono Fatchurrozi, Muhammad Fauzan Nashir, Muhamad Febriana Santi Wahyuni Firmansyah, Syafril Fransisca Dwi Agustina Garinanto, Budi Ghifari, Moch Azhar Al Gunawan, Rakhmat Dedi Habib Asiddiqie, Prananda Hadi Surya Wibawanto Sunarwadi Halizah, Nurul Hani Zulfia Zahro Hery Purwanto Himawan Subiyanto, Krishna Ida Bagus Suardika Imelda Febrianti Irma Sari, Ramandani Izmi Apriosa, Silvia Joseph Dedy Irawan Karina Auliasari Kartiko Ardi Widodo Khanan Alqutbhi, Latief Kurniawan, William Lalo Nusa, Faustino Listyani Kartika, Angelina M. Ibrahim Ashari Martinus Edwin Tjahjadi Mesach Habel Wiyono Pranataningtyas Mira Orisa Mizaell Manusiwa Mochammad Ibrahim Ashari monika putri, hemanulisa Muhammad Fajar Fazriyana Muhammad Hasan Wahyudi Muhammad Rizky Firdaus Nanang Utomo, Mochammad Ni Putu Agustini Nisyasalsabila Putri, Khoyru Nugi Ferdiyanto, Elan Nurlaily Vendyansyah Nurul Alifia, Anisa Paryanto, Lukas Patricia Evericho Mountaines Peniel Immanuel Gultom Peterson Tho, Sandhy Pitriya Rizki, Ani Pranata, Krish Prasetyo Nugroho, Bagas Prayoga, Andrian Prio Utomo, Yandi Putri Kartikasari, Yolanda Aprilia Putu Agustini, Ni Ramadhan, Zulfaiz RAMADHANI, RONI Rangga Saputra, Aulya Ratnasari, Andika Putri Reiny Ditta Myrtanti Reiny Ditta Myrtanti Reiny Myrtanti Renaldi Primaswara Prasetya Reynaldi Prayoga, Thomas Rezky Ramadhan, Bayu Rian Setya Budi Riska Amalia Praptiwi Rizky Prayudhi, Bimo Rohibun Rahman Ryo Cahyo Prakoso Salsabil Haq, Mustaqdimin Satrio, Imam Sentot Achmadi Shiva Divanti Natasya Siti Mutiara suaidah suaidah Sujianto Suliati Suliati Suryo Adi Wibowo Thesa Adi Saputra Thesa Adi Saputra Yusri Wahyani , Widhy Widhy Wahyani Widhy Wahyani Willyam Saputra, Leonardo Wiradi Surya, Rachmat Xavier Ariwibisono, Fransiscus Yohanes Oraplean, Cavin Yosep Agus Pranoto Yosep Agus Pranoto Yusran Bin Acho Yusri, Thesa Adi Saputra Zakaria Rifqi Azib, Muhammad Zulfia Zahro’, Hani