Claim Missing Document
Check
Articles

Found 20 Documents
Search

PENGELOMPOKAN PERMINTAAN DARAH BERDASARKAN GOLONGAN DAN WAKTU DI KABUPATEN GROBOGAN DENGAN ALGORITMA K-MEANS triyono, andri; Santoso, Kartika Imam; Arum, Dhika Malita Puspita; Supriyadi, Eko; Nugroho, Agus Susilo
TRANSFORMASI Vol 21, No 1 (2025): TRANSFORMASI
Publisher : STMIK BINA PATRIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56357/jt.v21i1.418

Abstract

The availability of adequate blood supplies continues to pose a significant challenge for blood transfusion services such as the Indonesian Red Cross (PMI), particularly due to the fluctuating and uneven nature of demand across various blood groups. Incorrectly estimating blood demand can result in either critical shortages that jeopardize patient safety or an excess of supplies that are wasted due to the limited shelf life of blood. The objective of this research is to examine historical blood demand data in Grobogan Regency by applying the K-Means clustering algorithm to identify trends related to time intervals and blood group classifications. The study draws on secondary data involving blood requests across multiple blood groups over a span of several years. By implementing the K-Means method, the research identifies unique trends in demand, highlighting critical periods between 2013–2016 and 2022–2024, during which nearly all blood types showed elevated levels of demand. These insights are crucial for improving blood stock management, refining donor mobilization strategies, and enhancing distribution planning based on empirical patterns. The K-Means algorithm proves effective in handling extensive and continuous numerical data, offering valuable guidance for strategic decision-making in healthcare logistics.
PREDIKSI TINGKAT KELULUSAN PESERTA DIDIK SMK FATHUL ULUM GABUS DENGAN METODE NAIVE BAYES Wahyudi; Eko Supriyadi; Andri Triyono
Julia: Jurnal Ilmu Komputer An Nuur Vol 5 No 1 (2025): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v5i1.3

Abstract

The graduation of students refers to those who are able to complete and meet the graduation requirements set through a graduation meeting based on the decision letter signed by the school principal. Graduation rate data can be used to help make policies and strategies for the school to improve graduation rates in the following year. This study utilizes classification or prediction methods to analyze the graduation rates of students at SMK Fathul Ulum Gabus. The method used in this study is Naive Bayes, using variables such as practical exam scores, school exam scores, competency test scores, student attendance, and student behavior. The purpose of this study is to test the accuracy of the Naive Bayes method in predicting graduation rates based on data collected from 2019 to 2024. The research process includes data collection, data integration, and model training using Naive Bayes, which produces fairly accurate predictions with an accuracy of 94.64%. Based on this accuracy, it can be concluded that the Naive Bayes method can be used to predict graduation rates at SMK Fathul Ulum Gabus.
Image Cluster Features Shape and Texture Determinants of Rice Quality Using the K Means Algorithm Eko Supriyadi
Julia: Jurnal Ilmu Komputer An Nuur Vol 2 No 01 (2022): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/pm208j29

Abstract

There is a lot of fraud case in the forgery of ricequality by mixing good quality rice with low quality rice for increasing price. To protect the community from counterfeiting, we conduct research to detect the quality of rice which can later help the community to be able to distinguish good and bad quality. This paper presents a low-costimage processing system for assessing the quality of rice. Many factors affect the quality of rice such as grain fragments, non-uniform color, odor and other factors. This study uses procentage of broken rice grains and color uniformity to determine the quality of rice. We propose texture feature with Otsu segementation for determining the number of broken grains and color distribution for specifying the color uniform. The classification results usingK Fold validation on the original data show the results of K-Nearest Neighbor have 99.70% accuracy.
STRATEGIC PLANNING OF MONTHLY DONATION PAYMENT INFORMATION SYSTEM AT SMK AT-THOAT TOROH Agus Susilo Nugroho; Eko Supriyadi
Julia: Jurnal Ilmu Komputer An Nuur Vol 1 No 01 (2021): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v1i01.12

Abstract

The development of a school, has an impact on the development of various services in the school. If school doesn’t improve the services, schools can lose competition, especially for private schools. The same thing happened at SMK At-Thoat Toroh. This Vocational High School, located in Grobogan Regency, Central Java, experiences significant development every year. One of the indicators is the increasing number of new students enrolling to the school. Even though the number of new students is increasing, At-Thoat Toroh Vocational School must still be able to serve the needs of all its students well. One form of this service is the payment of monthly donations. So far, students who will pay monthly contributions have to come to the teacher's office to meet the administration department. This often creates a crowd at the teacher's office door. Apart from being uncomfortable, it's certainly not a good thing in the midst of the current Covid-19 outbreak. In addition, the recording of monthly contributions by the administrative division is still done manually. This often causes disorder and confusion in recording student monthly contributions. Even though this record is very sensitive, because it relates to school finances. To overcome this problem, it is necessary to have a strategic planning of a monthly donation payment information system. This strategic planning uses the waterfall method and SWOT analysis. It aims to facilitate the analysis and process of making a monthly donation payment information system. The result of this research is the formulation of a monthly donation payment information system business strategy.
OPTIMIZATION OF PARTICLE SWARM OPTIMIZATION IN NAÏVE BAYES FOR CAESAREAN BIRTH PREDICTION Dhika Malita Puspita Arum; Andri Triyono; Eko Supriyadi; Rahmawan Bagus Trianto
Julia: Jurnal Ilmu Komputer An Nuur Vol 2 No 01 (2022): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v2i01.17

Abstract

The Maternal Mortality Rate (MMR) in 2017 according to the World Health Organization (WHO) is estimated to reach 296,000 women who die during and after pregnancy or childbirth. Caesarean birth is the last alternative in labor if the mother cannot give birth normally due to certain indications with a high risk, both for the mother and the baby. factors of a mother giving birth by caesarean section, such as placenta previa, hypertension, breech baby, fetal distress, narrow hips, and can also experience bleeding in the mother before the delivery stage. It is hoped that delivery by caesarean method can minimize problems for the baby and mother. Accurate prediction of the condition of the mother's pregnancy can enable d octors, health care providers and mothers to make more informed decisions regarding the management of childbirth. To predict caesarean births, data mining techniques using the Naive Bayes algorithm can be used. Naive Bayes is very simple and efficient but very sensitive to features, therefore the selection of appropriate features is very necessary because irrelevant features can reduce the level of accuracy. Naive Bayes will work more effectively when combined with several attribute selection procedures such as Particle Swarm Optimization. In this study, the researcher proposes a Particle Swarm Optimization algorithm for attribute weighting in Naive Bayes so as to increase the accuracy of Caesarean birth prediction results 
ANALYSIS OF SENTIMENT ON TEACHER MARKETPLACE ISSUES USING THE LEXICON AND K-NEAREST NEIGHBOR ALGORITHMS Addien Anaba; Rahmawan Bagus Trianto; Eko Supriyadi
Julia: Jurnal Ilmu Komputer An Nuur Vol 4 No 1 (2024): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v4i1.19

Abstract

The advancement of social media makes it easier for users to express opinions. Twitter has become one of the media that is loved by internet users, users can freely express their thoughts or opinions, apart from that they can also express everything that is being experienced. The busy issue of the Teacher Marketplace initiated by the Minister of Education, Nadiem Makarim, has invited many comments from internet users. Twitter users' tendencies in posting content can be determined by analyzing sentiment. In this research, the Lexicon and K-Nearest Neighbor (KNN) methods are proposed to analyze sentiment towards the education minister's discourse on Twitter social media on the topic of Teacher Marketplace Issue Sentiment by classifying it into positive, neutral and negative. The results of this research show that the accuracy value obtained was 91.70%, precision 90.51%, recall 71.95%. By carrying out this sentiment analysis, it is hoped that the problems contained in the Marketplace Guru topic controversy can be identified, used as input and consideration for further research.
Sistem Informasi Pembuatan Aplikasi Berbasis Web  Pada Konveksi ‘Sania Komveksi’ Erika Dwi Saputra; Muhammad Muzammil; Rheimanda Devin Emmanuel; Agus Susilo Nugroho; Eko Supriyadi
Julia: Jurnal Ilmu Komputer An Nuur Vol 5 No 1 (2025): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v5i1.21

Abstract

Perkembangan teknologi informasi yang pesat telah mempengaruhi berbagai sektor bisnis, termasuk industri konveksi. Sistem informasi berbasis web kini menjadi solusi efektif untuk meningkatkan efisiensi operasional dan manajemen data. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sebuah aplikasi berbasis web pada konveksi ‘Sania Konveksi’ yang dapat membantu dalam pengelolaan data produksi, pemesanan, inventaris, serta pelaporan secara lebih terstruktur dan real-time. Aplikasi ini dibangun dengan menggunakan metode pengembangan perangkat lunak Waterfall, dimulai dari tahap analisis kebutuhan, desain sistem, implementasi, sampai dengan pengujian. Hasil penelitian ini adalah sebuah aplikasi berbasis web yang mampu mengintegrasikan berbagai proses bisnis pada konveksi, memudahkan pihak manajemen dalam memonitor kinerja operasional, serta meningkatkan efisiensi dalam pengelolaan data dan proses produksi. Berdasarkan hasil pengujian, sistem ini terbukti dapat memberikan kemudahan dan efisiensi dalam pengelolaan operasional konveksi ‘Sania Konveksi’
AI-BAHSI: Metode Hibrid Artificial Intelligence-Behavioral Analysis dan Hybrid Security Intelligence untuk Deteksi dan Mitigasi Ancaman Real-time pada Wireless Access Point Emmanuel, Rheimanda Devin Emmanuel; Emmanuel, Rheimanda Devin; Anggraini, Ani; Condro Wibowo, Agus; Imam Santoso, Kartika; Supriyadi, Eko
Julia: Jurnal Ilmu Komputer An Nuur Vol 5 No 2 (2025): julia.ejournal.unan.ac.id
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v5i2.30

Abstract

Wireless access point (AP) security faces significant challenges with the emergence of sophisticated attacks such as SSID Confusion (CVE-2023-52424), KRACK attacks, and advanced persistent threats. This research develops a hybrid AI-BAHSI (Artificial Intelligence-Behavioral Analysis and Hybrid Security Intelligence) method that integrates deep learning, ensemble machine learning, and federated learning for real-time threat detection and mitigation on wireless access points. The proposed method combines Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) for pattern recognition, Random Forest-Support Vector Machine ensemble for threat classification, and federated learning for privacy-preserving security intelligence. Evaluation was conducted on a synthetic dataset that includes 15,000 normal traffic samples and 8,500 attack samples of various types. The results show that AI-BAHSI achieves a detection accuracy of 98.7%, a precision of 97.3%, a recall of 98.1%, and an F1-score of 97.7% with a false positive rate of only 1.2%. This method successfully detected zero-day attacks with a 94.6% confidence level and was able to automatically mitigate them in an average of 0.8 seconds. The main contribution of this research is the development of an adaptive security framework that can learn from new attack patterns in real time while preserving privacy through a federated learning architecture.
SMART-GUARD: Self-adaptive Multi-Agent Reinforcement learning Threat Guard dengan Game Theory dan Consensus Mechanisms untuk Enhanced Wireless Access Point Security  Aprilianto, Dwi Kurniawan; Yusuf Mufarihin, Ahmad; Najhan Atifa, Akhie; Supriyadi, Eko; Imam Santoso, Kartika
Julia: Jurnal Ilmu Komputer An Nuur Vol 5 No 2 (2025): julia.ejournal.unan.ac.id
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v5i2.32

Abstract

Kompleksitas serangan cyber terhadap wireless access point semakin meningkat dengan munculnya adversarial AI dan coordinated attack scenarios. Penelitian ini mengembangkan framework SMART-GUARD (Self-adaptive Multi-Agent Reinforcement learning Threat Guard) yang mengintegrasikan multi-agent reinforcement learning (MARL), game theory, dan consensus mechanisms untuk membangun sistem pertahanan adaptif dan kolaboratif. Framework yang diusulkan menggabungkan Deep Q-Networks (DQN) dengan hierarchical multi-agent architecture, Stackelberg game untuk strategic defense planning, Self-Organizing Maps (SOM) untuk threat clustering, dan Byzantine-fault tolerant consensus untuk koordinasi terdistribusi. Evaluasi dilakukan pada testbed yang mensimulasikan 20 access points dengan 500 client devices dan 15 jenis serangan berbeda. Hasil eksperimen menunjukkan SMART-GUARD mencapai defense success rate 97.4%, mean response time 1.2 detik, dan resource utilization efficiency 89.3%. Framework ini mampu beradaptasi dengan 12 jenis zero-day attacks dengan confidence level 92.8% dan menunjukkan scalability yang superior hingga 1000+ access points. Kontribusi utama penelitian ini adalah pengembangan self-adaptive defense ecosystem yang dapat melakukan strategic decision making secara autonomous melalui game-theoretic analysis dan koordinasi multi-agent yang fault-tolerant.
Expert System For Corn Plant Disease Diagnosis Using Hybrid Fuzzy Tsukamoto And Naive Bayes Method Kartika Imam Santoso; Eko Supriyadi; Andri Triyono; Dhika Malita Puspita
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p141-155

Abstract

Corn is a strategic food commodity in Indonesia, with production of 22.44 million tons in 2023. However, disease attacks can cause productivity declines of up to 30-80%, mainly from downy mildew, leaf rust, and leaf spot. The limited number of pathology experts in the field leads to delayed diagnosis, resulting in significant economic losses for farmers. This research aims to develop an expert system for diagnosing corn plant diseases using a hybrid Fuzzy Tsukamoto and Naive Bayes method to enhance diagnosis accuracy, taking into account uncertainty in symptom severity levels. The system was developed using Durkin's Expert System Development Life Cycle (ESDLC), which consists of six phases. A knowledge base was built from SINTA and Scopus-indexed literature, identifying five diseases and 17 symptoms. The fuzzy Tsukamoto method was employed for the fuzzification of symptom severity, utilizing three membership functions (intensity, coverage, and severity), after which Naive Bayes calculated the posterior probability. The hybrid score was calculated with 40% Fuzzy and 60% Bayes weights. The system was successfully developed with an interactive web interface. Accuracy testing using 30 validation cases yielded an accuracy of 86.67%, with 85% sensitivity and 88% specificity. Expert testing by three plant pathology experts gave excellent ratings (average 4.6/5.0) for diagnosis accuracy, knowledge base completeness, and usability aspects. The hybrid Fuzzy Tsukamoto and Naive Bayes method is effective for diagnosing corn plant diseases, achieving 86.67% accuracy, which is 6.67% higher than the Certainty Factor method and 11.67% higher than the single Naive Bayes method. This system can help farmers perform early diagnosis and reduce dependence on experts.