cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota bandung,
Jawa barat
INDONESIA
MIND (Multimedia Artificial Intelligent Networking Database) Journal
Published by Institut Teknologi Nasional Bandung
ISSN : 25280015     EISSN : 25280902     DOI : -
Core Subject : Science,
Computer Science & IT
Arjuna Subject : -
Articles 219 Documents
 18   19   20   21   22 
Sistem Estimasi Tingkat Kematangan Buah Melon Menggunakan Machine Learning BAHARUDIN HASAN; SETIAWARDHANA SETIAWARDHANA; AGUS INDRA GUNAWAN; ARNA FARIZA
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.15-29

Abstract

ABSTRAKPenentuan tingkat kematangan buah melon sangat penting untuk menjaga kualitas dan daya simpan. Metode tradisional yang bergantung pada penilaian visual, penciuman, dan mengetuk buah bersifat subjektif dan tidak konsisten. Penelitian ini mengusulkan sistem estimasi usia dan tingkat kematangan buah melon berbasis citra dengan metode Faster R-CNN menggunakan backbone ResNet-50. Dataset sebanyak 1.683 citra melon dikumpulkan dari kebun hidroponik, kemudian melalui proses anotasi, preprocessing, dan augmentasi sebelum digunakan untuk pelatihan model. Evaluasi kinerja dilakukan menggunakan mean Average Precision (mAP), precision, recall, F1-score, dan accuracy. Hasil pengujian menunjukkan akurasi 92,42%, F1-score 0,890, dan mAP (0.5:0.95) sebesar 0,828. Sistem ini mampu mendeteksi objek melon serta mengklasifikasikan tingkat kematangan menjadi tiga kategori dengan lebih objektif dibandingkan metode tradisional.Kata kunci: Machine Learning, Faster R-CNN, Kematangan Buah Melon, Pengolahan Citra, Deteksi ObjekABSTRACTThe determination of melon fruit maturity is crucial for maintaining quality and shelf life. Traditional methods that rely on visual assessment, smell, and tapping the fruit are subjective and inconsistent. This study proposes an image-based system for estimating the age and maturity level of melons using the Faster R-CNN method with a ResNet-50 backbone. A dataset of 1,683 melon images was collected from a hydroponic farm and subsequently processed through annotation, preprocessing, and augmentation before being used for model training. Performance evaluation was conducted using mean Average Precision (mAP), precision, recall, F1-score, and accuracy. The experimental results demonstrated an accuracy of 92.42%, an F1-score of 0.890, and an mAP (0.5:0.95) of 0.828. The proposed system is capable of detecting melon objects and classifying maturity levels into three categories more objectively than traditional methods.Keywords: Machine Learning, Faster R-CNN, Melon Ripeness, Image Processing, Object Detection
The Impact of Chunking Granularity on Hybrid GraphRAG Architecture Performance in Mitigating Hallucinations YUSUP MIFTAHUDDIN; AFIN MAULANA; DIASH FIRDAUS
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.88-101

Abstract

AbstrakPesatnya pertumbuhan literatur herbal memicu information overload yang menghambat ekstraksi data manual. Meskipun Large Language Models (LLMs) membantu otomasi, risiko halusinasi faktual pada domain medis tetap tinggi, sementara Retrieval-Augmented Generation (RAG) konvensional sering gagal menangkap hubungan relasional antar-entitas. Penelitian ini menerapkan Hybrid GraphRAG, menggabungkan pencarian vektor dan Knowledge Graph, untuk mengatasi kelemahan tersebut. Fokus utamanya adalah menguji dampak granularitas chunking (karakter, kata, kalimat) terhadap representasi pengetahuan, mengingat fragmentasi teks berisiko memutus konteks semantik. Hasil eksperimen menunjukkan bahwa chunking berbasis kalimat memberikan performa terbaik, menggandakan skor Correctness dan Recall dari 0,28 ke 0,56. Temuan ini menegaskan pentingnya menjaga keutuhan kalimat demi akurasi dan keterhubungan data dalam sistem informasi medis.  Kata kunci: Hybrid GraphRAG, Knowledge Graph, Chunking, Tanaman HerbalAbstractThe rapid growth of herbal medicine literature triggers an information overload that hinders manual data extraction. Although Large Language Models (LLMs) assist in automation, the risk of factual hallucination within the medical domain remains high, while conventional Retrieval-Augmented Generation (RAG) frequently fails to capture relational connections between entities. To address these limitations, this study implements a Hybrid GraphRAG architecture that integrates vector search and Knowledge Graphs. The primary focus is to evaluate the impact of chunking granularity (character, word, and sentence-level) on knowledge representation, considering that text fragmentation risks disrupting semantic context. Experimental results demonstrate that sentence-based chunking yields the best performance, doubling the Correctness and Recall scores from 0.28 to 0.56. These findings emphasize the importance of preserving sentence integrity for data accuracy and interconnectivity within medical information systems.Keywords:Hybrid GraphRAG, Knowledge Graph, Chunking, Herbal Plants
Prediksi Curah Hujan di Kabupaten Sumenep Menggunakan Metode Extreme Gradient Boosting (XGBoost) dan Algoritma Grid Search M THUFAIL ALWANNABIL SAMAS; NURISSAIDAH ULINNUHA; MOH HAFIYUSHOLEH
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.30-43

Abstract

AbstrakCurah hujan di Kabupaten Sumenep merupakan variabel meteorologis penting karena memengaruhi kegiatan pertanian dan produksi garam. Penelitian ini bertujuan memprediksi curah hujan harian menggunakan metode Extreme Gradient Boosting (XGBoost) yang dioptimalkan dengan Grid Search. Variabel yang digunakan meliputi suhu udara, durasi sinar matahari, tekanan udara, kelembapan udara, kecepatan angin, dan penguapan. Data yang digunakan berupa data cuaca harian dari BMKG periode 1 Juli 2020 hingga 30 Juni 2024. Proses pemodelan meliputi preprocessing data, pembentukan fitur lag, pembagian data menggunakan Time Series Cross Validation dengan pendekatan expanding window, serta optimasi hyperparameter menggunakan Grid Search. Model dengan kombinasi hyperparameter terbaik menghasilkan MAAPE sebesar 0.9152 dan RMSE sebesar 11.9566. Kata kunci: Curah Hujan, Grid Search, Kabupaten Sumenep, Prediksi, XGBoostAbstractRainfall in Sumenep Regency is an important meteorological variable because it affects agricultural activities and salt production. This study aims to predict daily rainfall using the Extreme Gradient Boosting (XGBoost) method optimized with Grid Search. The variables used include air temperature, sunshine duration, air pressure, air humidity, wind speed, and evaporation. The data used is daily weather data from BMKG for the period July 1, 2020, to June 30, 2024. The modeling process includes data preprocessing, lag feature formation, data division using Time Series Cross Validation with an expanding window approach, and hyperparameter optimization using Grid Search. The model with the best hyperparameter combination produced an MAAPE of 0.9152 and an RMSE of 11.9566.Keywords: Rainfall, Grid Search, Sumenep Regency, Prediction, XGBoost
Evaluasi Kinerja dan Keamanan Jaringan Menggunakan IDS Snort pada Disdukcapil Tasikmalaya HEGIRA MUSYAFA KARTIWAN; FATCKU ROCHMAN; HELMY DZULFIKAR
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.102-114

Abstract

AbstrakPenelitian ini mengevaluasi kinerja dan keamanan jaringan di Disdukcapil Kabupaten Tasikmalaya yang rentan karena belum memiliki sistem keamanan memadai. Menggunakan metode Network Development Life Cycle (NDLC) dan simulasi Graphical Network Simulator-3 (GNS3), diimplementasikan Intrusion Detection System (IDS) berbasis Snort yang diintegrasikan dengan iptables sebagai IPS. Hasil menunjukkan serangan SYN Flood menurunkan throughput hingga 99,99% dan meningkatkan latency 95 kali lipat. Snort berhasil mendeteksi seluruh serangan dengan detection rate 100%, sementara mekanisme IPS auto-block memulihkan performa jaringan mendekati kondisi normal. Penelitian ini merekomendasikan solusi keamanan open-source yang efektif dan ekonomis bagi instansi pemerintah.Kata kunci: Snort, keamanan jaringan, quality of service, NDLC, GNS3, IPSAbstractThis study evaluates the network performance and security of Disdukcapil Tasikmalaya Regency, which is vulnerable due to the lack of security systems. Using the Network Development Life Cycle (NDLC) method and Graphical Network Simulator-3 (GNS3) simulation, a Snort-based Intrusion Detection System (IDS) integrated with iptables as an IPS was implemented. Results show that SYN Flood attacks reduce throughput by 99.99% and increase latency 95-fold. Snort successfully detected all attacks with a 100% detection rate, while the IPS auto-block mechanism restored network performance close to normal. This research recommends an effective and economical open-source security solution for government agencies.Keywords: Snort, network security, quality of service, NDLC, GNS3, IPS
Klasifikasi Daun Herbal Berbasis Integrasi Fitur LBP dan Bentuk Menggunakan Random Forest AMALIA PUTRI UTAMI; DOLLY INDRA; FITRIYANI UMAR
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.44-59

Abstract

Abstrak Identifikasi daun herbal secara manual sering mengalami kendala akibat kemiripan visual antarspesies yang berpotensi menimbulkan kesalahan pemanfaatan. Penelitian ini bertujuan mengklasifikasikan sepuluh jenis daun herbal menggunakan kombinasi fitur tekstur Local Binary Pattern (LBP) dan fitur bentuk, yaitu aspect ratio, eccentricity, circularity, dan convexity. Dataset terdiri dari 500 citra yang dibagi menjadi 400 data latih dan 100 data uji dengan rasio 80:20. Tahap pre-processing meliputi resize, konversi ke grayscale, dan Gaussian Blur untuk mengurangi noise. Segmentasi dilakukan menggunakan Otsu thresholding untuk memperoleh objek daun dan Canny Edge Detection untuk menonjolkan struktur tekstur. Proses klasifikasi menerapkan algoritma Random Forest dengan pengujian beberapa kombinasi parameter guna memperoleh model optimal. Hasil terbaik diperoleh pada model dengan n_estimators=200, max_features=2, max_depth=none, dan min_samples_leaf=2, yang menghasilkan akurasi 92%, precision 92%, recall 92%, dan F1-score 92%. Kata kunci: Daun Tanaman Herbal; Fitur Bentuk; Fitur Tekstur; Klasifikasi Citra; Local Binary Pattern; Random Forest AbstractManual identification of herbal leaves often encounters challenges due to visual similarities among species, which can potentially lead to errors in their utilization. This study aims to classify ten types of herbal leaves using a combination of Local Binary Pattern (LBP) texture features and shape features, namely aspect ratio, eccentricity, circularity, and convexity. The dataset consists of 500 images divided into 400 training data and 100 testing data with an 80:20 ratio. The preprocessing stage includes resizing, grayscale conversion, and Gaussian Blur to reduce noise. Segmentation was performed using Otsu thresholding to extract the leaf object and Canny Edge Detection to enhance texture structures. The classification process applies the Random Forest algorithm with testing of several parameter combinations to obtain the optimal model. The best results were achieved with a model using n_estimators=200, max_features=2, max_depth=none, and min_samples_leaf=2, yielding an accuracy of 92%, precision of 92%, recall of 92%, and F1-score of 92%. Keywords: Herbal Plant Leaves, Texture Features, Shape Features, Image Classification, Local Binary Pattern; Random Forest
Prediksi Retensi Mahasiswa Menggunakan Algoritma Random Forest dengan Optimasi Algoritma Genetika PUDY PRIMA; AHMAD RIO ADRIANSYAH; ALFIAN NUR USYAID
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.115-126

Abstract

AbstrakKetidakseimbangan kelas (imbalanced data) memicu bias mayoritas pada model konvensional dalam memprediksi retensi mahasiswa. Penelitian ini mengusulkan model peringatan dini (early warning system) dengan mengintegrasikan teknik penyeimbangan data Synthetic Minority Over-sampling Technique (SMOTE) dan pengklasifikasi Random Forest (RF). Untuk menghindari inefisiensi pencarian hyperparameter manual, Algoritma Genetika (GA) diaplikasikan guna melakukan optimasi secara global. Pengujian terhadap dataset historis mahasiswa STT Terpadu Nurul Fikri angkatan 2021 membuktikan bahwa kombinasi SMOTE dan GA-RF sangat efektif. Model hibrida ini mencapai akurasi global 99%, dengan nilai Precision 1,00 dan Recall 0,67 pada deteksi kelas minoritas (dropout). Analisis ekstraksi fitur (Feature Importance) mengungkap bahwa ketahanan studi mahasiswa didominasi oleh performa Indeks Prestasi Semester (IPS) di tahun pertama serta faktor administratif berupa jalur pendaftaran seleksi mandiri.Kata kunci: prediksi Dropout, Ketidakseimbangan Data, SMOTE, Random Forest, Algoritma GenetikaAbstractClass imbalance triggers majority bias in conventional models for predicting student retention. This study proposes an early warning model integrating the Synthetic Minority Over-sampling Technique (SMOTE) for data balancing and a Random Forest (RF) classifier. To avoid manual hyperparameter tuning inefficiencies, a Genetic Algorithm (GA) is applied for global optimization. Testing on the 2021 historical student dataset of STT Terpadu Nurul Fikri proves the effectiveness of combining SMOTE and GA-RF. The hybrid model achieved 99% global accuracy, with 1.00 Precision and 0.67 Recall in minority class (dropout) detection. Feature Importance analysis reveals that student study retention is predominantly driven by first-year Grade Point Average (GPA) performance and administrative factors, specifically the independent selection admission path.Keywords:  Dropout Prediction, Imbalanced Data, SMOTE, Random Forest, Genetic Algorithm
Klasifikasi Tulisan Tangan Aksara Sunda dengan Menggunakan Arsitektur Model Inception-V3 YOULLIA INDRAWATY NURHASANAH; TOTO HARYANTO
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.60-76

Abstract

Abstrak Penelitian ini bertujuan mengembangkan model klasifikasi aksara Sunda dari citra tulisan tangan menggunakan arsitektur Inception-V3. Dataset diperoleh dari Kaggle dan melalui tahap preprocessing sebelum pelatihan model. Hasil eksperimen menunjukkan bahwa model mencapai nilai terbaik sebesar 88,3% pada konfigurasi batch-size 16 dan epoch 30. Namun, performa menurun signifikan pada data riil dengan akurasi 68,7%, yang mengindikasikan keterbatasan generalisasi model terhadap data riil. Penurunan ini disebabkan oleh kemiripan visual antar karakter, keterbatasan jumlah data, serta variasi kualitas citra. Kontribusi utama penelitian ini adalah pengembangan baseline model klasifikasi aksara Sunda berbasis deep learning menggunakan arsitektur Inception-V3, analisis komprehensif terhadap gap performa antara data dataset publik dan data riil, serta identifikasi faktor-faktor kritis yang mempengaruhi akurasi klasifikasi, seperti kemiripan visual karakter dan kualitas dataset. Kata kunci: Aksara sunda, Inception-V3, klasifikasi Abstract This study aims to develop a classification model for Sundanese script from handwritten images using the Inception-V3 architecture. The dataset was obtained from Kaggle and underwent preprocessing prior to model training. Experimental results show that the model achieved the best accuracy of 88.3% with a batch size of 16 and 30 epochs. However, performance decreased significantly on primary (real-world) data, with an accuracy of 68.7%, indicating limited model generalization. This decline is attributed to visual similarity among characters, limited data availability, and variations in image quality. The main contributions of this study include the development of a baseline deep learning model for Sundanese script classification using Inception-V3, a comprehensive analysis of the performance gap between public datasets and real-world data, and the identification of critical factors affecting classification accuracy, such as character similarity and dataset quality. Keywords: Aksara sundanese, classification, Inception-V3
Perbandingan Efektivitas Pengujian Manual dan Otomatis Menggunakan System Testing dengan Pendekatan AHP KURNIA RAMADHAN PUTRA; MOCHAMAD FAQIH FAIZAL; SOFIA UMAROH
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.127-143

Abstract

AbstrakPemilihan strategi pengujian seringkali subjektif tanpa mempertimbangkan karakteristik sistem. Penelitian ini mengevaluasi efektivitas pengujian manual dan otomatis menggunakan Analytic Hierarchy Process (AHP) pada studi kasus SIM SKK dan RPL untuk mengatasi subjektivitas pemilihan metode uji dan menentukan prioritas kriteria yang digunakan untuk membandingkan pengujian manual dan otomatis tersebut. Evaluasi diukur secara objektif melalui teknik Checklist-based Testing berdasarkan empat kriteria utama: waktu pengujian, cakupan pengujian, biaya pengujian berbasis Time-Driven Activity-Based Costing (TDABC), dan kuantitas penemuan bug. Pengujian otomatis menggunakan Katalon Studio terbukti menjadi strategi paling optimal pada kedua studi kasus karena mendominasi kriteria penemuan bug (33 pada SIM SKK dan 40 pada RPL) serta efisiensi waktu, sehingga menghasilkan Skor Global yang mengungguli metode manual baik pada SIM SKK (0,9697 berbanding 0,8986) maupun Sistem RPL (0,9379 berbanding 0,9002). Pengujian otomatis unggul karena dominasi mutlak pada aspek penemuan bug dan kecepatan eksekusi yang memiliki bobot kepentingan tertinggi dalam model keputusan AHP.Kata kunci: Software Quality, Automated Testing, Manual Testing, TDABC, AHPAbstractThe selection of testing strategies is often subjective and may overlook system characteristics. This study evaluates manual and automated testing using the Analytic Hierarchy Process (AHP) on SIM SKK and RPL systems. Evaluation was conducted through Checklist-based Testing based on four criteria: testing time, test coverage, testing cost, and bug detection. Automated testing using Katalon Studio proved to be the most effective approach due to better bug detection and higher time efficiency. As a result, automated testing achieved higher Global Scores than manual testing in both SIM SKK (0.9697 vs. 0.8986) and RPL (0.9379 vs. 0.9002). Its superiority is mainly attributed to bug detection capability and execution speed, which received the highest weights in the AHP model.Keywords: Software Quality, Automated Testing, Manual Testing, TDABC, AHP
Penerapan Algoritma Clarke and Wright Saving dalam Capacitated Vehicle Routing Problem dengan Optimasi Nearest Neighbor untuk Rute Terpendek FARREL ADI IBRAHIM; YUSUP MIFTAHUDDIN; MUHAMMAD ICHWAN; SURYA REZA PUTRA; WIRAWAN HADIWIBOWO
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 11, No 1 (2026): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v11i1.1-14

Abstract

Abstrak Distribusi merupakan komponen krusial dalam aktivitas logistik karena berperan dalam kelancaran proses pengiriman. Penelitian ini bertujuan menyusun rute distribusi dengan jarak terpendek berdasarkan kapasitas kendaraan, menggunakan algoritma Clarke and Wright Saving untuk membentuk rute awal serta algoritma Nearest Neighbor untuk mengatur urutan kunjungan. Pendekatan penelitian dilakukan secara kuantitatif melalui perhitungan algoritmik dengan memanfaatkan data lokasi pelanggan dan jumlah permintaan. Temuan penelitian menunjukkan bahwa rute usulan memiliki total jarak tempuh 151.69 km untuk mendistribusikan 300 ekor ayam beku, atau 18.97 km (11.12%) lebih pendek dibandingkan rute aktual perusahaan yang mencapai 170.66 km. Dengan demikian, penerapan kedua algoritma tersebut mampu menghasilkan rancangan rute yang lebih ringkas sekaligus mempertimbangkan jarak tempuh dan keterbatasan kapasitas kendaraan.Kata kunci: Clarke and Wright Saving, Capacitated Vehicle Routing Problem, Nearest NeighborAbstract Distribution is a crucial component in logistics activities because it plays a role in the smooth delivery process. This study aims to develop the shortest distribution route based on vehicle capacity, using the Clarke and Wright Saving algorithm to form the initial route and the Nearest Neighbor algorithm to arrange the order of visits. The research approach was conducted quantitatively through algorithmic calculations using customer location data and number of requests. The findings show that the proposed route has a total distance of 151.69 km to distribute 300 frozen chickens, which is 18.97 km (11.12%) shorter than the company's actual route of 170.66 km. Thus, the application of these two algorithms is able to produce a more concise route design while considering travel distance and vehicle capacity limitations.Keywords: Clarke and Wright Saving, Capacitated Vehicle Routing Problem, Nearest Neighbor

Page 22 of 22 | Total Record : 219

 18   19   20   21   22 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol 11, No 1 (2026): MIND Journal Vol 10, No 2 (2025): MIND Journal Vol 10, No 1 (2025): MIND Journal Vol 9, No 2 (2024): MIND Journal Vol 9, No 1 (2024): MIND Journal Vol 8, No 2 (2023): MIND Journal Vol 8, No 1 (2023): MIND Journal Vol 7, No 2 (2022): MIND Journal Vol 7, No 1 (2022): MIND Journal Vol 6, No 2 (2021): MIND Journal Vol 6, No 1 (2021): MIND Journal Vol 5, No 2 (2020): MIND Journal Vol 5, No 1 (2020): MIND Journal Vol 4, No 2 (2019): MIND Journal Vol 4, No 1 (2019): MIND Journal Vol 3, No 2 (2018): MIND Journal Vol 3, No 2 (2018): MIND Journal Vol 3, No 1 (2018): MIND Journal Vol 3, No 1 (2018): MIND Journal Vol 2, No 2 (2017): MIND Journal Vol 2, No 2 (2017): MIND Journal Vol 2, No 1 (2017): MIND Journal Vol 2, No 1 (2017): MIND Journal Vol 1, No 2 (2016): MIND Journal Vol 1, No 2 (2016): MIND Journal Vol 1, No 1 (2016): MIND Journal Vol 1, No 1 (2016): MIND Journal More Issue