Garuda - Garba Rujukan Digital

Penerapan Metode Simple Additive Weighting (SAW) Dalam Mengelompokkan Kualitas Kacang Kedelai Di Rumah Tempe A-Zaki Padang Nissa, Ika Ima; Yuhandri, Y; Nurcahyo, Gunadi Widi
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.737

Soybeans are a legume that has quite high protein levels. This Decision Support System uses the Simple Additive Weighting (SAW) method. This method has seven stages, namely determining the criteria and criteria weight values, determining the suitability rating of each alternative for each criterion, determining the normalization value and weight attribute, determining the decision matrix, determining the normalized matrix value, calculating the matrix by adding up the respective criteria matrices, alternatively do Ranking. The data processed in this research comes from Rumah Tempe A-Zaki Padang. The data consists of 4 alternatives, namely green soybeans, yellow soybeans, black soybeans, brown soybeans with 5 assessment criteria, namely color, texture, cost, aroma, taste which are used to apply the Simple Additive Weighting (SAW) method. The results of this research are that green soybeans have the highest value with a yield of 0.8525, yellow soybeans with a yield of 0.755, brown soybeans with a yield of 0.6345 and the lowest value with a yield of 0.6275. Therefore, the Decision Support System designed can help increase accuracy in determining the quality of soybeans using the Simple Additive Weighting (SAW) method and provide information for Rumah Tempe A-Zaki Padang in making decisions regarding the best quality of soybeans.

Audit Web E-Government Dengan Acunetix Web Vulnerability Guna Menganalisis Dan Perbaikan Celah Keamanan Website Khairani, Maisan Dewi Puspa; Yuhandri, Y; Sumijan, S
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.751

The use of the internet in government to encourage the realization of e-Government can provide benefits in increasing the power of society by increasing access to information, improving government services to the community, strengthening interaction between government and the private sector in related industries, and increasing the ease and openness of government management. One tool used to identify vulnerabilities in web applications is Acunetix Web Vulnerability. This tool is a security scanner that can automatically detect common vulnerabilities in web applications, including SQL injection attacks, Cross-Site Scripting (XSS), and others. The purpose of this research is to conduct an e-Government web audit, steps for e-Government security analysis and provide recommendations for improvements from the results of security analysis using Acunetix web vulnerabilities on the Padang City DPMPTSP website. Data was obtained using the Acunetix web Vulnerability tool to obtain a report from the penetration test process which contains information about security vulnerabilities found on the SINOPEN website https://nonperizinan.web.dpmptsp.padang.go.id/sinopen. The vulnerability findings of 148 data were at a high level, 107 data were at a medium level, 16 data were at a low level. Some of the attacks found were 11 attacks, namely Blind SQL injection, Cross site scripting (XSS), SQL injection, Application error message, HTML form without CSRF protection, Clickjacking: X-Frame-Option Header Missing, Cookie Without Secure Flag Set, File Upload, Login Page Password Guessing Attack, Broken Link, Password Type Input With AutoComplete Enabled. The Acunetix web vulnerability tool is used as a basis for analyzing improvements made after scanning the website. The results after an e-gov security audit was carried out to analyze and improve the level of vulnerabilities found on the SINOPEN website were at a low level, thereby increasing the level of security from attacks and the status of the website can be said to be safe from attack vulnerabilities.

Optimalisasi Analisis Keamanan Menggunakan Acunetix Vulnerability Pada Rekam Medis Elektronik Tamin, Zulfiqar; Yuhandri, Y; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.494

The use of the internet and web applications has significantly increased across various sectors, including education, healthcare, finance, and entertainment. However, web applications are highly vulnerable to various types of cyberattacks, such as SQL Injection, Cross-Site Scripting (XSS), and code injection, which can threaten the confidentiality, availability, and integrity of data. In line with technological advancements, the 2022 Ministry of Health regulation mandates that all healthcare facilities in Indonesia implement Electronic Medical Records (EMR). Universitas Andalas Hospital (RS UNAND) has adhered to this policy by developing a web-based EMR system. This study aims to evaluate and analyze the security of the EMR application used at RS UNAND. The Vulnerability Assessment process in this study was conducted using the Acunetix Web Vulnerability Scanner tool, which is designed to identify and assess vulnerabilities in web applications. The results of the first scan revealed that the RS UNAND EMR application had significant vulnerabilities, with a threat level of 3 (high). This scan identified 573 alerts, including 1 high-level, 253 medium-level, 2 low-level, and 317 informational alerts. These issues were followed by a thorough recap and further analysis to determine optimization steps. Several major vulnerabilities identified included HTML Form Without CSRF Protection, User Credentials Sent in Clear Text, Directory Listing, Source Code Disclosure, Git Repository Found, Multiple Vulnerabilities Fixed in PHP Versions, and Slow HTTP Denial of Service Attack. Optimization measures were then taken through a comprehensive review of the source code and enhancements to the security features of the EMR application. After the optimization, the second scan showed a significant reduction in the threat level, with the RS UNAND EMR application dropping to threat level 1 (low), with 12 alerts, consisting of 0 high and medium-level alerts, 9 low-level alerts, and 3 informational alerts. This study underscores the importance of regular security assessments and the optimization of security features to protect sensitive data in electronic medical record systems.

Enhancing Real Time Crowd Counting Using YOLOv8 Integrated with Microservices Architecture for Dynamic Object Detection in High Density Environments Prihandoko, P; Zufari, Faisal; Yuhandri, Y; Irawan, Yuda
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.575

This study presents the implementation of the YOLOv8 algorithm to enhance real-time crowd counting on the ngedatedotid application, which aims to provide accurate crowd density information at various locations. The proposed model leverages the advanced capabilities of YOLOv8 in detecting and localizing head-people objects within crowded environments, even in complex visual conditions. The model achieved a mAP of 85%, outperforming previous models such as YOLO V8'S (78.3%) and YOLO V7 (81.9%), demonstrating significant improvements in detection accuracy and localization capabilities. The custom-trained model further exhibited a detection accuracy of up to 95% in specific scenarios, ensuring reliable and real-time feedback to users regarding crowd conditions at various locations. By implementing a microservices architecture integrated with RESTful API communication, the system facilitates efficient data processing and supports a modular approach in system development, enabling seamless updates and scalability. This architecture allows for independent deployment of services, thereby minimizing system downtime and optimizing performance. The integration of YOLOv8 and the custom-trained model has proven to be effective in enhancing real-time monitoring and detection of crowd density, making it a suitable solution for diverse applications that require dynamic and accurate crowd information. The results indicate that the proposed model and system architecture can provide a robust framework for real-time crowd management, which is crucial for business owners, event organizers, and public safety monitoring. Future research should consider exploring newer versions of YOLO, such as YOLO V9-S, and expanding the dataset to address challenges related to varying lighting conditions, occlusions, and object orientations. Optimizing these factors will further improve the model’s accuracy and reliability, setting a new standard for crowd detection systems in public spaces and enhancing the overall user experience.

Technology Readiness Index untuk Menganalisis Kesiapan Adopsi Teknologi Kecerdasan Buatan Mahasiswa Komputer Wirahmadayanti, Isna; Yuhandri, Y; Sumijan, S
Jurnal KomtekInfo Vol. 12 No. 1 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i1.584

The education sector combined with the branch of artificial intelligence has great potential to change the way information is accessed and managed to improve the learning experience and support decision making in the educational process. It is important to understand the level of readiness for the adoption of artificial intelligence among students as the main stakeholders in the educational environment. The purpose of this study was to determine the readiness for adoption of technology, and what factors influence the readiness for adoption of artificial intelligence in Computer Science Students at Universitas Putra Indonesia "YPTK" Padang. This study uses the Technology Readiness Index (TRI) method which consists of four variables, including the variables of optimism, innovativeness, discomfort, and insecurity. The Technology Readiness Index (TRI) measures a person's tendency to accept and use technology to complete goals in their home life or at work. This study was conducted by distributing questionnaires to 348 students consisting of students of information systems and informatics engineering study programs. Data were obtained from a total population of 2689 students, 348 samples were obtained based on the Slovin formula with an error margin of 5%. Determination of the sample to determine the number of samples of each stratum in the population with proportionate stratified random sampling in the Information Systems study program of as many as 250 students and the Informatics Engineering study program of 98 students. Manual calculations and using applications show that computer students at Universitas Putra Indonesia “YPTK” Padang are very ready to adopt artificial intelligence technology with variable values of optimism 93.27%, innovative 92.64%, discomfort 91.66%, and insecurity 88.73%. These results can be stated that the factors that influence the readiness to adopt artificial intelligence technology include optimism, innovative, discomfort, and insecurity with a median index value of all variables of 92.15%

Prediksi Jumlah Kunjungan Pasien pada Bidan Praktik Mandiri dengan Jaringan Syaraf Tiruan Backpropagation Rifky, Muhammad; Yuhandri, Y; Sumijan, S
Jurnal KomtekInfo Vol. 12 No. 1 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i1.628

Independent Midwives (BPM) are important in providing health services for mothers and children. One of the main challenges in managing BPM is the uncertain fluctuation in patient visits, making it difficult to plan resources, such as medical personnel, drug supplies, and other supporting facilities. If the number of patient visits cannot be predicted properly, the risk of shortages or excess resources becomes higher, which can impact operational efficiency and the quality of health services. Uncertainty in the number of patients can also affect financial planning and readiness to face a surge in visits. Based on this, this study aims to develop a prediction model for the number of patient visits using Artificial Neural Networks (ANN) with the Backpropagation method. The dataset uses data on the number of Antenatal Care (ANC) patient visits over the past three years. The results of the model evaluation were carried out based on the Mean Squared Error (MSE) value and the prediction accuracy level presented more than 94% accuracy level. The evaluation results also obtained an MSE value of 0.0023, and MAPE of 5.62% so that the results can be stated that the model prediction error is within acceptable limits. This predictive model can contribute to assisting BPM in resource planning, improving service efficiency, and strategic decision-making in managing health facilities

Penerapan Deep Learning Menggunakan Metode Convolutional Neural Network dan K-Means dalam Klasterisasi Citra Butiran Pasir Olivia, Ladyka Febby; Yuhandri, Y; Arlis, Syafri
Jurnal KomtekInfo Vol. 12 No. 1 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i1.629

Agregat halus (pasir) merupakan bahan bangunan yang paling banyak digunakan dalam dunia konstruksi, sehingga kebutuhan pasir setiap harinya sangat banyak terutama di daerah perkotaan yang pembangunannya sangat pesat. Pasir berbentuk butiran - butiran yang memiliki tekstur berbeda untuk setiap jenisnya. Karakteristik pasir yang baik apat ditentukan melalui beberapa parameter, seperti segi kadar lumpur pasir, pemeriksaan kadar air nyata dan SSD, pemeriksaan gradasi, kadar air, zat organik, berat isi kondisi padat/gembur, daya serap, modulus kehalusan. faktor-faktor ini menjadi acuan dalam memilih pasir yang sesuai untuk berbagai kebutuhan konstruksi, termasuk plesteran dinding dan lantai. Parameter-parameter ini menjadi acuan dalam memilih pasir yang tepat untuk digunakan dalam berbagai kebutuhan konstruksi, termasuk plesteran dinding dan lantai. penelitian ini bertujuan untuk mengelompokkan kesesuaian antara butiran pasir untuk plesteran dinding atau lantai. Gambar dari citra butiran pasir memiliki nilai piksel yang banyak kerena terdiri dari tiga komponen warna yang mana red, green, blue. Sehingga membutuhkan teknik yang baik dalam menganalisa gambar ini. Metode yang digunakan dalam penelitian ini adalah Convulutional neural network (CNN) sebagai untuk mendeteksi dan mengekstraksi fitur butiran pasir, Convolutional Neural Network yang digunakan dalam penelitian ini adalah arsitektur resNet 50 sebagai memiliki kinerja tinggi dalam analisis citra.. Convolutional Neural Network memiliki arsitektur yang terinspirasi oleh struktur visual sistem manusia dan sangat efektif untuk tugas-tugas dalam ekstraksi gambar dan Metode K-means Clustering untuk menentukan pengelompokkan data ke dalam beberapa kelompok (klaster) sehingga data dalam satu klaster memiliki kemiripan tinggi sementara data antar klaster berbeda secara signifikan butiran pasir. Dataset yang diolah dalam penelitian ini bersumber di CV. Sumber Rezeki. Dataset terdiri 94 citra butiran pasir. Hasil penelitian menunjukkan bahwa pasir dapat diklasifikasikan ke dalam beberapa kategori mengelompokan seperti butiran bulat, butiran tajam, butiran tumpul, butiran tidak beraturan, butiran sub angular. Penelitian ini dapat menjadi acuan dalam menentukan kesesuaian butiran citra pasir yang cocok untuk lantai atau plesteran dinding dan membantu kontraktor memilih jenis pasir.

Penerapan Artificial Neural Network untuk Memprediksi Persediaan Obat Esensial Alfallah, Fadhly; Yuhandri, Y; Sumijan, S
Jurnal KomtekInfo Vol. 12 No. 1 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i1.630

The availability of essential medicines is a fundamental factor in ensuring high-quality healthcare services, especially in primary healthcare facilities such as Puskesmas. Inefficient drug inventory management can lead to various issues, including drug shortages that disrupt medical services and overstocking that may result in waste due to expiration. An accurate prediction system is essential to support more effective and efficient drug inventory planning. This study aims to analyze historical drug usage patterns to generate more accurate predictions. The research methodology includes problem identification, data collection, preprocessing, ANN architecture design, implementation, and system evaluation. Historical drug usage data from previous years is used for training and testing, with a division of 70% for training and 30% for testing. The backpropagation algorithm is applied to optimize the model by adjusting parameters such as the number of neurons in the hidden layer, learning rate, and activation function. The study results show that the ANN model with a 12-12-1 architecture achieves a high prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 2.13% for paracetamol stock. The developed MATLAB application provides an interactive platform for users to input historical data and obtain dynamic stock predictions. This system implementation is expected to help Puskesmas manage drug inventory more effectively, reduce the risks of shortages and overstocking, and improve efficiency in essential drug distribution. This study contributes to the field of health informatics by demonstrating the effectiveness of ANN in drug inventory prediction. Future research may explore hybrid machine learning models or integrate external factors, such as seasonal disease patterns and community demand levels, to enhance predictive accuracy and adaptability.

Hybrid CNN Approach for Post-Disaster Building Damage Classification Using Satellite Imagery Sonang, Sahat; Yuhandri, Y; Tajuddin, Muhammad
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.931

Accurate post-disaster building damage assessment is critical for timely response and effective reconstruction planning. This study proposes a hybrid deep learning architecture that integrates Inception-ResNet-v2 and EfficientNetV2B0, designed to enhance post-disaster damage classification from high-resolution satellite imagery. The model leverages dual-stream feature extraction, followed by concatenated fully connected layers optimized with dropout and batch normalization to improve generalization and reduce overfitting. The objective is to outperform standard Convolutional Neural Network (CNN) models in terms of classification and segmentation performance across multiple damage categories: no damage, minor damage, major damage, destroyed, and unclassified. The model was trained and validated on the publicly available xView dataset, covering over 12,000 annotated images from various natural disasters. Comparative evaluation against ResNet, GoogleNet, DenseNet, and EfficientNet demonstrates that the proposed model achieves the highest accuracy (86%), precision (85%), recall (86%), and F1-score (84%). Furthermore, it outperforms all baseline models in segmentation metrics, achieving an Intersection over Union (IoU) score of 0.7749 and a Dice Similarity Coefficient (DSC) of 0.8726. The model also significantly reduces misclassification rates in critical categories such as “major damage” and “destroyed.” A Wilcoxon signed-rank test confirmed that these improvements are statistically significant (p 0.05) across all major performance indicators. The novelty of this study lies in the fusion of two state-of-the-art CNN backbones with tailored architectural modifications, yielding a robust and generalizable model suitable for automated disaster damage assessment. This research contributes a scalable deep learning approach that can be integrated into real-time or semi-automated disaster response systems, offering improved decision-making support in emergency contexts. The results affirm the model’s potential as a reliable tool in post-disaster scenarios and set a foundation for future work in multi-modal and real-time AI-based disaster management.

Prediction of Extreme Poverty Levels Using the Performance of the Multiple Linear Regression Method Borianto, B; Yuhandri, Y; Sovia, Rini
Jurnal KomtekInfo Vol. 12 No. 3 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i3.655

Extreme poverty is a type of poverty that is defined as a condition that cannot meet basic human needs. The Government of Indonesia through Presidential Instruction No. 4 of 2022 sets a target for the elimination of extreme poverty, but this effort requires an accurate and comprehensive data-driven approach. This study aims to build a model for predicting extreme poverty levels. The method used in this study is Multiple Linear Regression (MLR), which is able to measure the contribution of each predictor variable to the phenomenon of extreme poverty. The dataset processed in this study was sourced from the Dumai City Social and Community Empowerment Office. The dataset consisted of 2,007 extreme poverty data with predictor variables in the form of residence ownership (X1), employment (X2), income (X3), education (X4), and health insurance (X5). The results of this study show that the Multiple Linear Regression method is able to provide accurate predictions of the extreme poverty level in Dumai City with an accuracy rate of 87%. The model evaluation was carried out using three metrics based on the results of the test obtained R = 0.674 and R² = 0.454, which means that 45.4% of the variation in poverty status can be explained by the variables of home ownership, type of occupation, amount of income, education level, and health insurance. The ANOVA test showed a value of F = 332.777 with a significance of < 0.001, so the model was simultaneously significant. The regression coefficient showed that all variables had a negative and significant influence (p < 0.05) on poverty status, with the greatest influence coming from the type of job (β = -0.304) and amount of income (β = -0.291), followed by home ownership, health insurance, and education level. Thus, the Multiple Linear Regression method has proven to be effective in building an extreme poverty prediction system. This model can be a basic reference in supporting more targeted, measurable, and data-based socio-economic policy decision-making, especially in efforts to combat extreme poverty in a sustainable and systematic manner.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search