Articles
<![CDATA[Pemanfaatan Optical Character Recognition Dan Text Feature Extraction Untuk Membangun Basisdata Pengaduan Tenaga Kerja ]]>
<![CDATA[Yan Puspitarani]]>;
<![CDATA[Yenie Syukriyah]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 4 (2020): Agustus 2020 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (242.186 KB)
|
DOI: 10.29207/resti.v4i4.2107
<![CDATA[The examination of complaints of labor violations is part of the main activity of the labor inspection section within the Department of Manpower. Monitors will examine companies that are considered to have violated labor laws based on a letter of complaint sent by the relevant union organization or legal aid agency. The easy way to communicate at this time, making the submission of complaint letters can be directly sent in the form of images through electronic media such as whatsapp or email. This makes it difficult for administrative staff to recapitulate incoming complaints because they have to read and enter data manually into the system. Therefore, this research was conducted to create a system that utilizes OCR technology and text feature extraction to be able to input complaints data automatically. This research resulted in a prototype of letter input and a database of letter storage that can be further utilized for Data Mining and Business Intelligent. OCR implementation is done by using the Tesseract library while the text feature selection utilizes the Natural Language Toolkit (NLTK) library. The results of testing of the prototype showed an accuracy of 66.7% of the OCR results and 91.67% of the manually typed letters.]]>
<![CDATA[ESTIMASI RESIKO PENGEMBANGAN SISTEM INFORMASI MENGGUNAKAN PENDEKATAN EXPECTED MONETARY VALUE (EVM) ]]>
<![CDATA[Yenie Syukriyah]]>;
<![CDATA[Falahah Suprapto]]>
<![CDATA[ Jurnal Ilmiah Teknologi Infomasi Terapan Vol. 3 No. 3 (2017) ]]>
Publisher : <![CDATA[Universitas Widyatama ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (228.676 KB)
|
DOI: 10.33197/jitter.vol3.iss3.2017.143
<![CDATA[[Id]Manajemen resiko merupakan bidang penting pada manajemen proyek secara keseluruhan, dan manajemen proyek sistem informasi secara khusus. Melalui manajemen resiko yang baik, pimpinan dan stakeholder proyek berharap bahwa resiko terhadap kegagalan proyek dapat diminimalisir dengan usaha yang rasional. Manajemen resiko sendiri meliputi banyak kegiatan, salah satunya adalah analisis dan perencanaan mitigasi resiko. Aspek penting pada analisis dan perencanaan mitigasi resiko yaitu melakukan penilaian atau estimasi atas resiko untuk menentukan prioritas serta dampak setiap mitigasi yang diambil. Pada umumnya, hal yang paling mudah diterima stakeholder dalam menyajikan resiko adalah menghitung biaya akibat resiko tersebut. Untuk melakukan perhitungan biaya untuk memitigasi resiko, dapat digunakan salah satu pendekatan yaitu Expected Monetary Value (EVM). Melalui pendekatan EVM, dapat ditentukan pilihan tindakan mitigasi yang paling optimal, dengan estimasi biaya paling minimal[En] Risk management is an important area of overall project management, and information systems project management in particular. Through good risk management, project leaders and stakeholders expect that the risks to project failure can be minimized by rational efforts. Risk management itself includes many activities, one of which is risk mitigation analysis and planning. An important aspect of risk mitigation analysis and planning is to assess or estimate the risks to determine the priorities and impacts of each mitigation. In general, the easiest thing a stakeholder receives in presenting risk is to calculate the cost of the risk. To perform cost calculation to mitigate risk, one of the approaches is Expected Monetary Value (EVM). Through the EVM approach, the most optimal mitigation options can be determined, with the least cost estimate]]>
<![CDATA[Model Sistem Monitoring URL Menggunakan Plugin Browser dengan Pendekatan NLP dan SDMIL untuk Perlindungan Anak ]]>
<![CDATA[Esa Fauzi]]>;
<![CDATA[Feri Sulianta]]>;
<![CDATA[Yenie Syukriyah]]>;
<![CDATA[Sy Yuliani]]>
<![CDATA[ SITEKIN: Jurnal Sains, Teknologi dan Industri Vol 20, No 1 (2022): Desember 2022 ]]>
Publisher : <![CDATA[Fakultas Sains dan Teknologi Universitas Islam Negeri Sultan Syarif Kasim Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24014/sitekin.v20i1.19889
<![CDATA[Internet adalah salah satu kemajuan teknologi yang berdampak ke banyak orang termasuk anak-anak. Dengan internet anak-anak dapat mengakses halaman web yang memiliki banyak informasi termasuk untuk mendukung pendidikan anak. Namun di internet banyak pula halaman web yang berisikan konten tidak pantas untuk dilihat anak-anak seperti pornografi. Bebasnya anak dalam mengakses konten halaman web ini menyulitkan orang tua untuk memantau perilaku anak di internet. Oleh karena itu pada penelitian ini diajukan sebuah model sistem monitoring untuk perlindungan anak dari konten negatif internet. Model sistem ini dikembangkan dengan arsitektur microservice dengan masing-masing service memiliki fungsi untuk mendeteksi konten negatif. Service pertama didukung dengan google API content filtering untuk menyaring konten website untuk orang dewasa. Service kedua dibuat dengan pendekatan NLP (Natural Language Processing) untuk menyaring tulisan-tulisan negatif. Service ketiga dibuat dengan pendekatan SDMIL atau Strongly Supervised Deep MIL (Multiple Instant Learning) untuk mendeteksi gambar dan video yang tidak cocok untuk anak-anak. Service keempat menyediakan layanan untuk kustomisasi URL negatif yang bisa diatur sendiri. Terakhir service kelima untuk log yang dapat membantu developer memantau kesalahan sistem. Model ini juga diintegrasikan dengan perangkat mobile sehingga orang tua dapat menerima laporan pengaksesan internet anak secara real-time.]]>
<![CDATA[Model of NFT Implementation on Web SSO over OpenID Connect and Oauth 2.0 protocols ]]>
<![CDATA[Esa Fauzi]]>;
<![CDATA[Sy Yuliani]]>;
<![CDATA[Yenie Syukriyah]]>;
<![CDATA[Azizah Zakiah]]>
<![CDATA[ INTECOMS: Journal of Information Technology and Computer Science Vol 6 No 2 (2023): INTECOMS: Journal of Information Technology and Computer Science ]]>
Publisher : <![CDATA[Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31539/intecoms.v6i2.6972
<![CDATA[Single Sign-On (SSO) is a mechanism that allows users to access various services using a single set of login credentials. However, in SSO implementations, there are still challenges related to security and authentication management, particularly attacks targeting the Identity Provider (IDP). To address this, the use of Non-Fungible Tokens (NFTs) as proof of IDP ownership has been proposed as a solution to enhance security in the authentication mechanism. The utilization of NFTs in SSO with OpenID Connect and OAuth 2.0 has the potential to improve security and convenience in the authentication process due to the unique and non-duplicable nature of NFTs. The results of this research present a model and design of SSO with NFTs on OpenID Connect and OAuth 2.0. An SSO application with login, register, and password recovery features was also developed to provide convenience to users during the login process. The findings conclude that the utilization of NFTs in SSO with OpenID Connect and OAuth 2.0 has the potential to enhance security and convenience in the authentication mechanism. Further research is needed to explore aspects such as scalability, in-depth security analysis, testing in real-world scenarios, improvement of integration and interoperability, as well as comparative analysis with other SSO technologies.]]>
<![CDATA[Integrated Learning Model: A Blend of Project-Based Approach and SDLC Concepts for Software Engineering Courses, Evaluated through EUCS ]]>
<![CDATA[Esa Fauzi]]>;
<![CDATA[Azizah Zakiah]]>;
<![CDATA[Yenie Syukriyah]]>;
<![CDATA[Sy Yuliani]]>
<![CDATA[ INTECOMS: Journal of Information Technology and Computer Science Vol 6 No 2 (2023): INTECOMS: Journal of Information Technology and Computer Science ]]>
Publisher : <![CDATA[Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31539/intecoms.v6i2.8171
<![CDATA[Online learning and face-to-face learning are two examples of current learning models. Online learning has the advantage of time and place flexibility as it can be conducted remotely. Meanwhile, face-to-face learning excels in the teacher-student relationship as they can meet in person. However, particularly in online learning, not all subjects can be taught optimally, such as practical courses. Blended learning is one solution for a combined learning model that can leverage both online and face-to-face learning. One of the most challenging subjects in online learning is software engineering, which requires practical exercises to write application code. There are various types of blended learning models, but we propose a blended learning model specifically based on the Software Development Lifecycle (SDLC) pattern in software engineering course materials. We do this to maximize the learning process. We also integrate blended learning with a project-based concept, as this course is well-suited for project-based learning. In evaluating this model, we analyze the satisfaction level using the end-user computing satisfaction method. The sample consists of 60 students from the Computer Science program, selected using accidental sampling. The data analysis and processing methods employed in this study include t-tests, F-tests, and multiple linear regression. The research yields a satisfaction level of 71%. The results of hypothesis testing also show that the variables Ease of Use and Timeliness have a significant positive partial impact on student satisfaction.]]>
<![CDATA[INTERNET SEHAT ON CHILD ONLINE PROTECTION DI SMP AL BURUNI CERDAS MULIA ]]>
<![CDATA[yakub, sy yuliani yuliani]]>;
<![CDATA[Syukriyah, Yenie]]>;
<![CDATA[Sulianta, Feri]]>;
<![CDATA[Fauzi, Esa]]>
<![CDATA[ Prosiding Konferensi Nasional Pengabdian Kepada Masyarakat dan Corporate Social Responsibility (PKM-CSR) Vol 7 (2024): PKMCSR2024: Kolaborasi Hexahelix dalam Optimalisasi Potensi Pariwisata di Indonesia: A ]]>
Publisher : <![CDATA[Asosiasi Sinergi Pengabdi dan Pemberdaya Indonesia (ASPPI) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37695/pkmcsr.v7i0.2403
<![CDATA[Internet memiliki dampak positif dalam meningkatkan konektivitas, Berkembangnya teknologi komunikasi dan informasi juga mempengaruhi anak. Anak tidak lagi canggung menggunakan internet dan khususnya media sosial. Berdasarkan data yang dikumpulkan oleh UNICEF pada tahun 2023, ada 175.000 anak menggunakan internet di dunia dan sebanyak 30 juta anak di Indonesia diantaranya. Internet digunakan untuk belajar secara online, mengerjakan tugas sekolah, media sosial, namun penyalahgunaan internet juga dapat menimbulkan dampak negatif. Pengguna internet dapat menjadi korban penjahat di dunia maya, bahkan pelaku dari cybercrime, dengan sangat mudah pada saat mengakses internet. Permasalahan dari kondisi saat ini banyak anak anak yang belum memliki keilmuan yang terkait dengan keamanan ber internet, etika dalam menggunakan internet, kejahatan yang ada pada dunia internet, bagaimana mengantisipasi jika sudah menjadi korban kejahatan dalam dunia internet, hukum yang berlaku jika kita melanggar dalam menggunakan internet. Diperlukan kesadaran menggunakan internet dengan sehat, baik dan aman (cyber safety awareness) Tujuan dari PKM ini adalah untuk Meningkatkan Kesadaran interenet yang aman dan sehat atau dikenal dengan Internet safety awareness untuk anak SMA dan SMP Al biruni Cerdas Mulia. Hasil PKM ini menghasilkan peningkatan awareness sebanyak 78% merasakan manfaat dari seminar yang dilaksanakan]]>
<![CDATA[Modelling Time Series Data for Stock Prices Prediction Using Bidirectional Long Short-Term Memory ]]>
<![CDATA[Syukriyah, Yenie]]>;
<![CDATA[Purnama, Adi]]>
<![CDATA[ Knowbase : International Journal of Knowledge in Database Vol. 4 No. 2 (2024): December 2024 ]]>
Publisher : <![CDATA[Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30983/knowbase.v4i2.8759
<![CDATA[The dynamic nature of stock markets, characterized by intricate patterns and sudden fluctuations, poses significant challenges to accurate price prediction. Traditional analytical methods are often unable to capture this complexity. This requires the use of advanced techniques capable of modelling non-linear dependencies. This study aims to build a model using recurrent neural network and predict the Indonesian stock prices. PT Gudang Garam Tbk.'s (GGRM.JK) stock was selected due to its significant role in the Indonesian stock market and its contribution to national revenue through excise tax. The method used in this research involves training the BiLSTM (Bidirectional Long Short-Term Memory) model using historical stock price data with training and test data ratios of 90:10, 80:20 and 70:30 to determine the optimal configuration. The evaluation results showed that the 90:10 data ratio gave the best performance with a MAPE of 1.51%, MAE of 343.55 IDR and RMSE of 522.30 IDR. These results indicate that the BiLSTM model has high accuracy and minimal prediction errors. Further analysis showed that the model performed optimally with a batch size of 32 and higher epochs, such as 200 and 250, providing greater stability and prediction accuracy. These results demonstrate the potential of the BiLSTM model as an effective predictive tool to support strategic investment decisions, particularly for high volatility stocks. Future research is recommended to test this model on other stock data and to consider external factors to improve its generalizability.]]>
<![CDATA[The Use of Attention-RNN and Dense Layer Combinations and The Performance Metrics Achieved in Palm Vein Recognition ]]>
<![CDATA[Indriani, Indriani]]>;
<![CDATA[Syukriyah, Yenie]]>
<![CDATA[ Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 1 (2025): March ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/jiteki.v11i1.30517
<![CDATA[The utilization of palm veins in vascular biometrics is widely recognized, offering significant potential and challenges for advancing individual recognition technology. Deep learning has played a crucial role in enhancing the accuracy of these recognition systems. In this study, we proposed combining Attention-RNN and Dense Layer. To validate this proposed method, three deep learning model scenarios were implemented: (1) a combined Dense Layer with RNN, (2) an Attention-RNN model, and (3) a combined Attention-RNN with a Dense Layer for palm vein recognition. Experimental results demonstrated that the Attention-RNN combined with the Dense Layer achieved the highest accuracy, outperforming the other two models. The model’s performance was evaluated on two datasets, achieving 95% accuracy on the Kaggle dataset and 83% on the CASIA dataset, confirming its effectiveness in palm vein recognition.]]>
<![CDATA[Image Segmentation for Sweet Potato Leaf Disease Detection using U-Net ]]>
<![CDATA[Syukriyah, Yenie]]>;
<![CDATA[Purnama, Adi]]>
<![CDATA[ International Journal of Multidisciplinary Approach Research and Science Том 3 № 03 (2025): International Journal of Multidisciplinary Approach Research and Science ]]>
Publisher : <![CDATA[PT. Riset Press International ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.59653/ijmars.v3i03.1848
<![CDATA[The detection and management of sweet potato leaf diseases play a vital role in ensuring sustainable crop yields and reducing agricultural losses. This study proposes an automated segmentation approach using the U-Net convolutional neural network to detect disease regions on sweet potato leaves. The dataset, consisting of leaf images and corresponding masks, underwent a structured preprocessing pipeline including resizing, normalization, and reshaping. The U-Net architecture, comprising an encoder-decoder structure with skip connections, was trained on 70% of the dataset and evaluated using accuracy, Intersection over Union (IoU), and Dice coefficient. Experimental results show that the model achieved an accuracy of 94.6%, IoU of 0.88, and a Dice coefficient of 0.92, indicating strong segmentation performance. Visual comparison between predictions and ground truth masks further confirms the model’s effectiveness in isolating disease regions. This research demonstrates the potential of U-Net as a reliable deep learning framework for plant disease detection and contributes to the development of intelligent agricultural monitoring systems.]]>
<![CDATA[Modelling Time Series Data for Stock Prices Prediction Using Bidirectional Long Short-Term Memory ]]>
<![CDATA[Syukriyah, Yenie]]>;
<![CDATA[Purnama, Adi]]>
<![CDATA[ Knowbase : International Journal of Knowledge in Database Vol. 4 No. 2 (2024): December 2024 ]]>
Publisher : <![CDATA[Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30983/knowbase.v4i2.8759
<![CDATA[The dynamic nature of stock markets, characterized by intricate patterns and sudden fluctuations, poses significant challenges to accurate price prediction. Traditional analytical methods are often unable to capture this complexity. This requires the use of advanced techniques capable of modelling non-linear dependencies. This study aims to build a model using recurrent neural network and predict the Indonesian stock prices. PT Gudang Garam Tbk.'s (GGRM.JK) stock was selected due to its significant role in the Indonesian stock market and its contribution to national revenue through excise tax. The method used in this research involves training the BiLSTM (Bidirectional Long Short-Term Memory) model using historical stock price data with training and test data ratios of 90:10, 80:20 and 70:30 to determine the optimal configuration. The evaluation results showed that the 90:10 data ratio gave the best performance with a MAPE of 1.51%, MAE of 343.55 IDR and RMSE of 522.30 IDR. These results indicate that the BiLSTM model has high accuracy and minimal prediction errors. Further analysis showed that the model performed optimally with a batch size of 32 and higher epochs, such as 200 and 250, providing greater stability and prediction accuracy. These results demonstrate the potential of the BiLSTM model as an effective predictive tool to support strategic investment decisions, particularly for high volatility stocks. Future research is recommended to test this model on other stock data and to consider external factors to improve its generalizability.]]>
