Article Per Year (5 Year)
p-Index From 2021 - 2026
12.762
P-Index
This Author published in this journals
All Journal JURNAL SISTEM INFORMASI BISNIS Techno.Com: Jurnal Teknologi Informasi Scientific Journal of Informatics CESS (Journal of Computer Engineering, System and Science) Sinkron : Jurnal dan Penelitian Teknik Informatika JISTech (Journal of Islamic Science and Technology) JURNAL TEKNOLOGI DAN OPEN SOURCE JURNAL PENDIDIKAN TAMBUSAI Jurnal Nasional Komputasi dan Teknologi Informasi IJISTECH (International Journal Of Information System & Technology) JOURNAL OF SCIENCE AND SOCIAL RESEARCH Jurnal Mantik JISKa (Jurnal Informatika Sunan Kalijaga) Technologia: Jurnal Ilmiah Jurnal Ilmu Komputer dan Bisnis Health Information : Jurnal Penelitian Journal of Applied Engineering and Technological Science (JAETS) JSR : Jaringan Sistem Informasi Robotik Jatilima : Jurnal Multimedia Dan Teknologi Informasi Journal of Computer System and Informatics (JoSYC) JIKA (Jurnal Informatika) INFOKUM Community Development Journal: Jurnal Pengabdian Masyarakat Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) El-Qist : Journal of Islamic Economics and Business (JIEB) Journal of Computer Networks, Architecture and High Performance Computing Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Teknik Informatika (JUTIF) IJISTECH Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Walisongo Journal of Information Technology Syntax: Journal of Software Engineering, Computer Science and Information Technology Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Instal : Jurnal Komputer Jurnal Teknisi J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Mandiri IT Jurnal Pustaka Data : Pusat Akses Kajian Database, Analisa Teknologi, dan Arsitektur Komputer Jurnal Sains dan Teknologi JOMLAI: Journal of Machine Learning and Artificial Intelligence Data Sciences Indonesia (DSI) Internet of Things and Artificial Intelligence Journal Jurnal Ilmiah Teknik Informatika dan Komunikasi Jurnal Ilmu Komputer dan Sistem Informasi Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Jurnal Nasional Komputasi dan Teknologi Informasi
Mhd Furqan
Universitas Islam Negeri Sumatera Utara
Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Other

Published : 110 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 110 Documents
Search

 7   8   9   10   11 
Optimized KNN Performance with PCA and K-Fold Cross-Validation for Colorectal Cancer Survival Prediction Manza, Yuke; Rosnelly, Rika; Furqan, Mhd; Riza, Bob Subhan
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 1 (2026): JUTIF Volume 7, Number 1, February 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.1.5422

Abstract

Colorectal cancer remains a leading cause of global mortality, necessitating effective predictive tools for patient survival. While Machine Learning algorithms like K-Nearest Neighbors (KNN) utilize patient data for prediction, standard KNN implementations often suffer from the curse of dimensionality and overfitting, leading to unreliable performance on complex medical datasets. This study aims to evaluate and optimize the performance of the KNN algorithm by integrating Principal Component Analysis (PCA) for dimensionality reduction and K-Fold Cross-Validation (KFCV) to enhance model stability. The research utilized a quantitative approach on a global colorectal cancer dataset, processing demographic and clinical features through a rigorous pipeline of imputation, encoding, and normalization. Three model configurations were systematically compared: Standard KNN, KNN combined with PCA, and an optimized KNN model utilizing both PCA and KFCV across various neighbor values. The results demonstrate a distinct trade-off between predictive sensitivity and model stability. While the Standard KNN and PCA-enhanced models achieved higher recall, indicating a strong ability to identify survivors in a single data split, the fully optimized KNN+PCA+KFCV model provided the most stable and generalized accuracy with minimal deviation. These findings indicate that while PCA effectively reduces computational complexity without information loss, the integration of cross-validation is crucial for obtaining an honest assessment of model performance. This research contributes to clinical informatics by highlighting the necessity of prioritization between high sensitivity and generalization stability when developing survival prediction models for complex, inseparable medical data.
APPLICATION OF WEIGHTED AVERAGE ALGORITHM IN RECREATIONAL PARK TOURIST DESTINATION RECOMMENDATION SYSTEM BASED ON GOOGLE MAPS USER RATINGS Nayla Faiza; Hervilla Amanda R. Siregar; Nur Shafwa Aulia Sitorus; Agung Nugroho; Muhammad Fathir Aulia; Mhd Furqan
JURNAL TEKNISI Vol. 5 No. 2 (2025): Agustus 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/teknisi.v5i2.3790

Abstract

Abstract: The development of digital technology has changed the behavior patterns of tourists in choosing travel destinations. Google Maps is now not only used to find restaurant locations but has also become the main source for searching nearby tourist destinations based on user ratings and reviews. This research aims to build a recommendation system for recreational park tourist destinations in Medan City by applying the Weighted Average algorithm using Google Maps user rating data. The data used comes from reviews by five users of five popular recreational parks in Medan City during the period from January 1, 2025, to April 30, 2025. The Weighted Average algorithm was chosen because it can provide a more objective and fair assessment by taking into account the weight of each rating given by users. As a result, this system can recommend the best recreational parks based on user experiences related to cleanliness, parking facilities, toilets, security, running paths, and accessibility. It is hoped that this system can help tourists choose destinations that meet their needs and preferences, as well as provide a more enjoyable and satisfying travel experience.Keywords : digital technology; google maps; recommendation system; weighted average algorithmAbstrak: Perkembangan teknologi digital telah mengubah pola perilaku wisatawan dalam memilih destinasi wisata. Google Maps kini tidak hanya digunakan untuk mencari lokasi restoran, tetapi juga menjadi sumber utama dalam mencari destinasi wisata terdekat berdasarkan rating dan ulasan pengguna. Penelitian ini bertujuan untuk membangun sistem rekomendasi destinasi wisata taman rekreasi di Kota Medan dengan menerapkan algoritma Weighted Average menggunakan data rating pengguna Google Maps. Data yang digunakan berasal dari lima ulasan pengguna terhadap lima taman rekreasi populer di Kota Medan selama periode 1 Januari 2025 hingga 30 April 2025. Algoritma Weighted Average dipilih karena mampu memberikan penilaian yang lebih objektif dan adil dengan memperhatikan bobot setiap rating yang diberikan pengguna. Hasilnya, sistem ini dapat merekomendasikan taman rekreasi terbaik berdasarkan pengalaman pengguna terkait aspek kebersihan, fasilitas parkir, toilet, keamanan, lintasan lari, dan aksesibilitas. Diharapkan sistem ini dapat membantu wisatawan dalam memilih destinasi yang sesuai dengan kebutuhan, preferensi, dan memberikan pengalaman wisata yang lebih menyenangkan dan memuaskan. Kata Kunci: google maps; sistem rekomendasi; teknologi digital; weighted average algorithm
DYNAMIC VISUALIZATION OF THE SPREAD OF COVID-19 IN MEDAN CITY USING HEATMAP WITH PYTHON Mhd Fikri Hasrul Hasibuan; Fredy Kusuma Ramadhani; Lailatul Badria; Laila Nurzannah; Fikri Haikal; Mhd Furqan
JURNAL TEKNISI Vol. 5 No. 2 (2025): Agustus 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/teknisi.v5i2.3791

Abstract

Abstract: The rapid and widespread transmission of COVID-19 has posed significant challenges for public health management, particularly in densely populated urban areas like Medan. Manual data reporting often fails to convey the dynamic nature of the virus's spread in a clear and actionable manner. This study aims to address this gap by developing dynamic visualizations of COVID-19 distribution using heat maps created with Python programming. The study utilized official COVID-19 datasets sourced from platforms like Kaggle, which include district- and municipal-level data across North Sumatra. Methodological steps included data collection, preprocessing, and visualization using Python libraries like Pandas and Matplotlib. These tools enable the transformation of static tabular data into interactive heat maps that highlight spatial and temporal trends in infections, recoveries, and mortality. The visualizations reveal that Medan City recorded the highest number of confirmed and recovered cases, while Deli Serdang had the highest number of deaths. Conversely, North Nias and South Nias showed the lowest mortality rates. The resulting spreadsheets provide a practical solution for monitoring the pandemic's development and serve as decision-support tools for policymakers and health authorities. In conclusion, dynamic data visualization improves understanding of COVID-19 patterns and supports effective pandemic response strategies.Keywords: dynamic visualization; COVID-19; python; heatmap. Abstrak: Penularan COVID-19 yang cepat dan meluas telah menimbulkan tantangan yang signifikan bagi manajemen kesehatan masyarakat, terutama di daerah perkotaan yang padat penduduk seperti Kota Medan. Laporan data manual sering kali gagal menyampaikan sifat dinamis penyebaran virus dengan cara yang jelas dan dapat ditindaklanjuti. Penelitian ini bertujuan untuk mengatasi kesenjangan ini dengan mengembangkan visualisasi dinamis distribusi COVID-19 menggunakan peta panas yang dibuat dengan pemrograman Python. Penelitian ini menggunakan kumpulan data resmi COVID-19 yang bersumber dari platform seperti Kaggle, yang mencakup data tingkat kabupaten dan kotamadya di seluruh Sumatera Utara. Langkah-langkah metodologis meliputi pengumpulan data, prapemrosesan, dan visualisasi menggunakan pustaka Python seperti Pandas dan Matplotlib. Alat-alat ini memungkinkan transformasi data tabular statis menjadi peta panas interaktif yang menyoroti tren infeksi, pemulihan, dan mortalitas secara spasial dan temporal. Visualisasi tersebut mengungkapkan bahwa Kota Medan mencatat jumlah kasus terkonfirmasi dan sembuh tertinggi, sementara Deli Serdang memiliki jumlah kematian tertinggi. Sebaliknya, Nias Utara dan Nias Selatan menunjukkan tingkat mortalitas terendah. Heatmap yang dihasilkan memberikan solusi praktis untuk memantau perkembangan pandemi dan berfungsi sebagai alat pendukung keputusan bagi para pembuat kebijakan dan otoritas kesehatan. Kesimpulannya, visualisasi data dinamis meningkatkan pemahaman pola COVID-19 dan mendukung strategi respons pandemi yang efektif.Kata Kunci: visualisasi dinamis; COVID-19; python; peta panas.
Klasifikasi Algoritma K-Nearest Neighbor (KNN) untuk Pengenalan Angka Tulisan Tangan Berbasis Citra Digital Andita Utami; Dewi Aulia Tanjung; Muhammad Fadil Ramadhana; Farhan Sadli Siregar; Hapisfatly Sir; Mhd Furqan

Publisher :

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v9i1.10366

Abstract

Abstrak - Klasifikasi angka tulisan tangan merupakan salah satu topik penting dalam analisis citra digital dan membutuhkan metode yang akurat serta efisien. Penelitian ini menerapkan algoritma K-Nearest Neighbor (KNN) untuk mengenali angka tulisan tangan pada dataset MNIST, yang dipadukan dengan teknik ekstraksi fitur zoning untuk memperoleh 16 fitur utama dari setiap citra. Beberapa nilai k diuji untuk menentukan konfigurasi yang paling optimal. Hasil pengujian menunjukkan bahwa nilai k = 7 memberikan akurasi terbaik sebesar 83.54%. Evaluasi menggunakan confusion matrix dan classification report mengonfirmasi bahwa model mampu mengklasifikasikan sebagian besar digit dengan baik, meskipun masih terdapat sebagian kecil kesalahan pada digit yang memiliki bentuk serupa. Temuan ini menunjukkan bahwa kombinasi metode zoning dan algoritma KNN tetap efektif digunakan untuk pengenalan angka tulisan tangan pada sistem yang membutuhkan komputasi ringan dan cepat.Kata kunci: Algoritma; Citra; K-Nearest Neighbors; MNIST; Abstract - Handwritten digit classification is an important topic in digital image analysis and requires accurate and efficient methods. This study applies the K-Nearest Neighbor (KNN) algorithm to recognize handwritten digits in the MNIST dataset, combined with the zoning feature extraction technique to obtain 16 main features from each image. Several values of k were tested to determine the most optimal configuration. The test results show that k = 7 provides the best accuracy of 83.54%. Evaluation using a confusion matrix and classification report confirms that the model is able to classify most digits well, although there are still some errors with digits that have similar shapes. These findings indicate that the combination of the zoning method and the KNN algorithm remains effective for handwritten digit recognition in systems that require light and fast computation.Keywords: Algorithm; Image; K-Nearest Neighbors; MNIST;
Perbandingan Kinerja SVM, Random Forest, dan XGBoost dengan Pendekatan Feature Engineering dalam Prediksi Produk Terlaris Bintang Kurniawan Herman; Mhd. Furqan; M. Fakhriza
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 4 (2026): Agustus, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/prf0k336

Abstract

Abstrak - Penelitian ini membandingkan kinerja Support Vector Machine, Random Forest, dan XGBoost dengan pendekatan rekayasa fitur untuk mengklasifikasikan produk terlaris pada platform Tokopedia. Data diperoleh melalui web scraping terhadap produk elektronik dari enam merek, yaitu Baseus, Fantech, Logitech, Sony, Ugreen, dan Xiaomi, dengan total awal 1.147 baris. Tahap prapemrosesan mencakup validasi tipe data, penanganan nilai hilang dan duplikasi, pembentukan label, penghapusan zona ambigu, transformasi logaritmik, pengodean merek, serta pencegahan kebocoran target. Produk dengan jumlah terjual sekurang-kurangnya 500 diberi label Terlaris, produk dengan jumlah terjual kurang dari 100 diberi label Tidak Terlaris, sedangkan data dengan penjualan 100-499 dikeluarkan. Dataset akhir berjumlah 884 data, terdiri atas 587 produk Terlaris dan 297 produk Tidak Terlaris. Data dibagi secara stratifikasi dengan rasio 70:30 menjadi 618 data latih dan 266 data uji. Rekayasa fitur menghasilkan 24 fitur yang mencakup harga, diskon, rating, kualitas, posisi harga terhadap merek, segmentasi harga, dan interaksi antarfitur. Hasil pengujian menunjukkan bahwa Random Forest dengan fitur dasar dan rekayasa fitur pada ambang keputusan 0,53 memberikan kinerja terbaik, yaitu akurasi 86,84%, precision tertimbang 0,8675, recall tertimbang 0,8684, F1-score tertimbang 0,8656, dan F1-score makro 0,8463. Model tersebut mengungguli XGBoost dan Support Vector Machine. Fitur yang paling dominan adalah rating_kuadrat, Rating, nilai_produk_score, kompetitif_score, rating_x_harga_rel, dan brand_encoded. Temuan ini menunjukkan bahwa rekayasa fitur memberi peningkatan paling besar pada Random Forest dan membantu model menangkap hubungan nonlinier antara kualitas, harga, diskon, dan karakteristik merek. Kata kunci : Rekayasa Fitur; Pembelajaran Mesin; Produk Terlaris; Abstract - This study compares the performance of Support Vector Machine, Random Forest, and XGBoost using a feature engineering approach to classify best-selling products on Tokopedia. The data were collected through web scraping from electronic products of six brands, namely Baseus, Fantech, Logitech, Sony, Ugreen, and Xiaomi, producing 1,147 initial records. Preprocessing included data-type validation, missing value and duplicate handling, label construction, ambiguous-zone exclusion, logarithmic transformation, brand encoding, and target-leakage prevention. Products with at least 500 units sold were labelled Best Selling, products with fewer than 100 units sold were labelled Non-Best Selling, while records with 100-499 units sold were excluded. The final dataset contained 884 records, consisting of 587 Best-Selling and 297 Non-Best-Selling products. A stratified 70:30 split produced 618 training and 266 testing records. Feature engineering generated 24 predictors representing prices, discounts, ratings, quality, brand-relative prices, price tiers, and feature interactions. The results show that Random Forest with basic and engineered features at a decision threshold of 0.53 achieved the best performance, with 86.84% accuracy, 0.8675 weighted precision, 0.8684 weighted recall, 0.8656 weighted F1-score, and 0.8463 macro F1-score. It outperformed XGBoost and Support Vector Machine. The most influential features were rating_squared, Rating, product_value_score, competitiveness_score, rating_by_relative_price, and brand_encoded. These findings demonstrate that feature engineering provides the largest improvement for Random Forest and helps capture nonlinear relationships among product quality, price, discount, and brand characteristics. Keywords: Feature Engineering; Machine Learning; Best-Selling Products;
PENGAMANAN DATA TEKS MENGGUNAKAN METODE DIGITAL SIGNATURE ALGORITHM (DSA) DAN ADVANCED ENCRYPTION STANDARD (AES) Mhd Reza Alfani; Mhd Furqan; Yusuf Ramadhan Nasution
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 7 No. 1 (2024): February 2024
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v7i1.1686

Abstract

Abstract: The issue of data security and confidentiality are two important aspects of an information system. This is closely related to how important the information is sent and received by interested people. Cryptography is a field of science that aims to maintain the confidentiality of messages from unauthorized parties. The cryptographic algorithm that will be used is the Digital Signature Algorithm (DSA) asymmetric cryptography algorithm and combined with the Advanced Encryption Standard (AES) symmetric algorithm. DSA as authentication using a hash function cannot perform encryption and decryption, with a combination of Advanced Encryption Standard (AES) cryptography to enable encryption and decryption. Advanced Encryption Standard (AES) is a block cipher algorithm and has a symmetrical nature that uses a symmetric key during the encryption and decryption process. The text file type to be used is in the format (*.xlsx). Files that have been encrypted still use the same extension as the previous file but cannot be opened. Encrypted files have a size change of 30%. The decrypted file is exactly the same as the initial file before the encryption process is carried out. Keywords: cryptography, digital signature algorithm, advanced encryption standard,                   text data Abstrak: Masalah keamanan dan kerahasiaan data merupakan dua aspek penting dalam sistem informasi. Hal ini erat kaitannya dengan pentingnya informasi yang dikirimkan dan diterima oleh masyarakat yang berkepentingan. Kriptografi merupakan bidang ilmu yang menjaga kerahasiaan pesan dari pihak yang tidak berkepentingan. Algoritma kriptografi yang akan digunakan adalah algoritma kriptografi asimetris Digital Signature Algorithm (DSA) dan dikombinasikan dengan algoritma simetris Advanced Encryption Standard (AES). DSA sebagai autentikasi menggunakan fungsi hash tidak dapat melakukan enkripsi dan dekripsi, dengan kombinasi kriptografi Advanced Encryption Standard (AES) agar dapat melakukan enkripsi dan dekripsi. Advanced Encryption Standard (AES) merupakan algoritma enkripsi blok dan memiliki sifat simetris yang menggunakan kunci simetris selama enkripsi dan dekripsi. Jenis file teks yang akan digunakan berformat (*.xlsx). File yang telah dienkripsi masih memakai ekstensi seperti file sebelumnya namun tidak dapat dibuka. File hasil enkripsi memiliki perubahan ukuran sebesar 30%. File hasil dekripsi sama persis seperti file awal sebelum dilakukan proses enkripsi. Kata kunci: kriptografi, digital signature algorithm, advanced encryption standard, data teks
RECOGNITION OF CALLIGRAPHY WRITING PATTERNS USING THE ZERNIKE MOMENT METHOD AND SUPPORT VECTOR MACHINE Mhd. Furqan; Sriani Sriani; Riswanda Ichsan Himawan Hasibuan
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 7 No. 4 (2024): November 2024
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v7i4.2362

Abstract

Abstract: One of the great arts of Islam that is very attached to Muslims is the art of calligraphy. The art of writing in calligraphy is of many types because the art of calligraphy is generally handwritten by someone called khatat and each khatat has its own technique for writing calligraphy. There fore there are many variations of calligraphy writing, even with the same type of writing. With so many variations of the type of calligraphy writing, technological innovation is needed to recognize variations of each type of calligraphy. Types of calligraphy diwani, diwaji jali, naskhi and tsuluts are the objects of this study. The Zernike Moment method is a feature extraction method that has the advantage of being invariant to rotate (resistant to rotation) and can help identify calligraphy types well based on their features. And the Support Vector Machine method is a good method for identifying calligraphy types by finding the best hyperplane. The combination of the Zernike Moment method and the Support Vector Machine is proven to produce good accuracy in recognizing calligraphy types based on their features, the accuracy obtained in identifying calligraphy types is 95%. Keywords: Pattern Recognition, Zernike Moment, Support Vector Machine, Calligraphy Abstrak: Salah satu seni besar Islam yang sangat melekat di kalangan umat Islam adalah seni kaligrafi. Seni menulis kaligrafi banyak macamnya karena seni kaligrafi umumnya ditulis tangan oleh seseorang yang disebut khatat dan setiap khatat mempunyai teknik penulisan kaligrafi tersendiri. Oleh karena itu terdapat banyak variasi penulisan kaligrafi, bahkan dengan jenis tulisan yang sama. Dengan banyaknya variasi jenis tulisan kaligrafi, diperlukan inovasi teknologi untuk mengenali variasi setiap jenis kaligrafi. Jenis kaligrafi diwani, diwaji jali, naskhi dan tsuluts menjadi objek penelitian ini. Metode Zernike Moment merupakan salah satu metode ekstraksi ciri yang mempunyai kelebihan yaitu bersifat invarian terhadap rotasi (tahan terhadap rotasi) dan dapat membantu mengidentifikasi jenis-jenis kaligrafi dengan baik berdasarkan ciri-cirinya. Dan metode Support Vector Machine merupakan metode yang baik untuk mengidentifikasi jenis kaligrafi dengan mencari hyperplane terbaik. Kombinasi metode Zernike Moment dan Support Vector Machine terbukti menghasilkan akurasi yang baik dalam mengenali jenis kaligrafi berdasarkan ciri-cirinya, akurasi yang didapat dalam mengidentifikasi jenis kaligrafi adalah 95%. Kata kunci: Pengenalan Pola, Momen Zernike, Mesin Vektor Pendukung, Kaligrafi
Klasifikasi Algoritma K-Nearest Neighbor (KNN) untuk Pengenalan Angka Tulisan Tangan Berbasis Citra Digital Andita Utami; Dewi Aulia Tanjung; Mhd Fadil Ramadhana; Farhan Sadly Siregar; Hapisfatly Sir; Mhd Furqan
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 1 (2026): Februari, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v9i1.209

Abstract

Abstrak - Dalam pemrosesan citra digital, mengklasifikasikan angka tulisan tangan masih merupakan tantangan. Penyebab utamanya adalah variasi bentuk yang sangat besar akibat gaya penulisan yang berbeda-beda antar individu. Klasifikasi angka tulisan tangan merupakan salah satu topik penting dalam analisis citra digital dan membutuhkan metode yang akurat serta efisien. Penelitian ini menerapkan algoritma K-Nearest Neighbor (KNN) untuk mengenali angka tulisan tangan pada dataset MNIST, yang dipadukan dengan teknik ekstraksi fitur zoning untuk memperoleh 16 fitur utama dari setiap citra. Beberapa nilai k diuji untuk menentukan konfigurasi yang paling optimal. Hasil pengujian menunjukkan bahwa nilai k = 7 memberikan akurasi terbaik sebesar 83.54%. Evaluasi menggunakan confusion matrix dan classification report mengonfirmasi bahwa model mampu mengklasifikasikan sebagian besar digit dengan baik, meskipun masih terdapat sebagian kecil kesalahan pada digit yang memiliki bentuk serupa. Temuan ini menunjukkan bahwa kombinasi metode zoning dan algoritma KNN tetap efektif digunakan untuk pengenalan angka tulisan tangan pada sistem yang membutuhkan komputasi ringan dan cepat. Kata kunci: Algoritma, Citra, K-Nearest Neighbors, MNIST Abstract - Handwritten digit classification is an important topic in digital image analysis and requires accurate and efficient methods. This study applies the K-Nearest Neighbor (KNN) algorithm to recognize handwritten digits in the MNIST dataset, combined with the zoning feature extraction technique to obtain 16 main features from each image. Several values of k were tested to determine the most optimal configuration. The test results show that k = 7 provides the best accuracy of 83.54%. Evaluation using a confusion matrix and classification report confirms that the model is able to classify most digits well, although there are still some errors with digits that have similar shapes. These findings indicate that the combination of the zoning method and the KNN algorithm remains effective for handwritten digit recognition in systems that require light and fast computation. Keywords: Algorithm, Image, K-Nearest Neighbors, MNIST
Analisis Sentimen Debat Capres dan Cawapres Indonesia 2024 Menggunakan Metode Bert Zaki Musyaffa; Mhd. Furqan; Aidil Halim Lubis
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v5i3.703

Abstract

The 2024 Indonesian Presidential and Vice Presidential Candidate Debate, broadcast on the YouTube channel of the Indonesian General Elections Commission (KPU), generated thousands of public comments reflecting societal sentiment toward the candidates, yet these opinions have not been systematically examined. This study aims to analyze the sentiment of YouTube comments on the debate using the Bidirectional Encoder Representations from Transformers (BERT) method. A total of 2,500 comments were collected via the YouTube Data API from five debate sessions, then cleaned through a pre-processing stage and automatically labeled using the InSetLexicon dictionary into three categories: positive, negative, and neutral. After removing duplicate data, 2,362 clean records were obtained and divided into training and testing data with an 80:20 ratio. The IndoBERT model was then fine-tuned to classify comment sentiment. The results show that the sentiment distribution was dominated by positive comments (1,107), followed by negative (660) and neutral (595) comments. Model evaluation using a confusion matrix yielded an accuracy of 76.5%, with the highest precision, recall, and F1-score values in the positive class at 87.78%, 85.39%, and 86.57%, respectively. These findings indicate that the BERT method is fairly effective in analyzing the sentiment of Indonesian-language comments in the context of political debates on YouTube, while also contributing a mapping of public opinion toward candidates and debate issues that can serve as a reference for future Indonesian-language political sentiment analysis research.
PENERAPAN SISTEM PAKAR DIAGNOSIS PERADANGAN PULPA GIGI DENGAN METODE CERTAINTY FACTOR Mhd Furqan; Yusuf Ramadhan Nasution; Aisyah Nurrahmah Siregar
Technologia : Jurnal Ilmiah Vol 14 No 2 (2023): Technologia (April)
Publisher : Fakultas Teknologi Informasi, Universitas Islam Kalimantan Muhammad Arsyad Al Banjari, di bawah koordinasi UPT Publikasi dan Pengelolaan Jurnal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v14i2.10448

Abstract

 Bagian dari mulut yang punya peran penting dalam proses pencernaan untuk memecah makanan dengan bantuan lidah dan air liur adalah gigi. Gigi juga dapat membantu orang berbicara dengan jelas. Sehingga ketika gigi mengalami masalah maka si penderita akan merasa kesulitan bahkan kesakitan. Peradangan pulpa gigi atau yang lebih dikenal dengan pulpitis adalah salah satu dari beberapa penyakit gigi dan mulut yang lazim diderita masyarakat saat ini. Oleh sebab itu penulis berpendapat bahwa sistem pakar bisa dijadikan  sebagai jalan keluar untuk mendeskripsikan dan menjelaskan jenis penyakit yang ada pada gigi sehingga jenis penyakit pada gigi dapat lebih mudah diketahui oleh si penderita tanpa harus langsung menemui dokter. Metode Certainty Factor menjadi salah satu metode yang cocok digunakan  untuk mendiagnosis penyakit gigi  pulpitis. Kemudian pada penelitian ini dikembangkan sebuah aplikasi sistem pakar diagnosis pulpitis dengan metode Certainty Factor berbasis mobile dengan maksud memudahkan penderita dalam mendiagnosis pulpitis pada gigi yang terindikasi serta memungkinkan deteksi dan perawatan pulpitis. Pada penelitian ini ditemukan hasil bahwa gejala pulpitis dirangkum menjadi 12 gejala, pilihan tingkat kepercayaan untuk setiap gejala adalah antara 0 dan 1, dan yang terakhir adalah pulpitis diklasifikasikan menjadi lima jenis.
Co-Authors ., Zulpadli Abdul Halim Hasugian Adha, Rifki Mahsyaf Agpina, Pipi Agung Nugroho Ahmad Fakhri Ab. Nasir Ahmad Fauzi Aidil Halim Lubis Aisyah Nurrahmah Siregar Akmal, Muhammad Haikal Andita Utami Anggraini, Delia Anwar, Mufti Husain Apriansyah, Yuda Ardyanti, Tiwy Armansyah Armansyah Armansyah Armansyah Armansyah Armansyah Armansyah, A Aulia, Atiqah Aulia, Muhammad Arief Aulia, Muhammad Fathir Aulia, Rafif Risdi Badria, Lailatul Bagus Ageng Alfahri Basyir, Muhammad Khalidin Bintang Kurniawan Herman Bob Subhan Riza, Bob Subhan Br Rambe, Indri Gusmita Cahyadi, Bhagaskara Dalimunthe, Ayu Sahriani Daulay, Ikhsan Agus Martua Dea Alya Dewi Aulia Tanjung Diah Putri Kartikasari Dodyk Fahlome Elce, Furkan Fadil, Ulfi Muzayyanah Fadillah, Rini Fadlan, Aulia Fahrul Azis Nasution Faiza, Nayla fandi, Fandi Ahmad Farhan Amar Pramudya Farhan Sadli Siregar Farhan Sadly Siregar FIKRI HAIKAL Fikri Haikal Fredy Kusuma Ramadhani Gunawan, Irwan Hapisfatly Sir Harahap, Khaila Mukti Harahap, Raihan Rizieq Harahap, Rosa Linda Hasrul Hasibuan, Mhd Fikri Heri Santoso Hervilla Amanda R. Siregar Himawan Hasibuan, Riswanda Ichsan HP, Kiki Iranda Hsb, Dinda Umami Hsb, Munawir Siddik Hutagalung, Muhammad Wandisyah R Ilham Fuadi Nasution Imam Zaki Husein Nst Iskandar, Rozai Ismail Pulungan Januar, Bagus Jundi Haqqoni K Khairunnisa Khairi, Nouval Khairunnisa Khairunnisa Khairunnisa, K Kurniawan, Riski Askia Laila Nurzannah Lailatul Badria Lely Sahrani Lubis, Akbar Maulana M. Alfatoni Muarrip M. Fakhriza Mahendra, Rifandi Manza, Yuke Matondang, Toibatur Rahma Maulana Ihsan, Maulana Mey Hendra Putra Sirait Mhd Fadil Ramadhana Mhd Fikri Hasrul Hasibuan Mhd Galih Khairi Mhd Ikhsan Rifki Mhd Reza Alfani Miftahul Rizky Pulungan Muhammad Akbar Ramadhan Tanjung Muhammad Fadil Ramadhana Muhammad Farhan Muhammad Fathir Aulia Muhammad Ikhsan Muhammad Irfan Gurning Muhammad Luthfi Muhammad Naufal Shidqi Muhammad Ridzki Hasibuan Muhammad Rizki Munadi Munadi Nabawy, Putri Nabila, Siti Fadiyah Naina Nazwa Hasibuan Nasution, Afri Yunda Nasution, Irma Yunita Nasution, Romaito Nasution, Zulia Lestari Nayla Faiza Nazwa Aliya Muthmainnah Hasibuan Ningsih, Siti Alus Nur Bainatun Nisa Nur Shafwa Aulia Sitorus Nurhasanah Nurhasanah Nurul Hadi Muliani Hariadi Saputra Nurzannah, Laila Pane, Putri Pratiwi Pangestu, Dimas Panggabean, Alwi Andika Pratama, Haris Prayoga Elfanda Fachmi Hasibuan Putra, Suan Ekie Nanda Putri Salsa Nabila Putri, Alma Irawanti Radhifan Mardhi Raissa Amanda Putri Rakhmat Kurniawan R Ramadani, Wily Supi Ramadhan Nasution, Yusuf Ramadhani, Fredy Kusuma Razzaq H. Nur Wijaya Reza Muhammad Rifnandy, Muhammad Fauzan Rika Rosnelly, Rika Riswanda Ichsan Himawan Hasibuan Rivaldi Prima Nanda Rizka Rizki Ananda Rizki Siregar, Awal Rizqi Hidayat Tanjung RR. Ella Evrita Hestiandari Said Arrahman Salsabila Mahfuza Saparuddin Siregar Sembiring, Yogasurya Pranantha Shafa, Dafa Ikhwanu Sigit Muslim Anggoro Pratono Sinaga, Meri Siregar, Dzilhulaifa Siregar, Hervilla Amanda R. Siregar, Kalfida Eka Wati Sitepu, Anggi Jelita Siti Saniah Siti Sarah Harahap Siti Sumita Harahap Sitorus, Nur Shafwa Aulia Solly Aryza Sri Rahmadani Sri Wahyuni Sriani Sriani Sriani Sriani Sriani, S Suci Syahputri Suci Wulandari Suhardi, S Suhardi, Suhardi Susan Mayang Sari Syamia, Nanda Tambak, Tiara Ayu Triarta Tanjung, Tegar Haryahya Tiara Bela Harahap Tria Elisa Wahyudin, Rahmat Wan Fadilla Rischa Wati, Putri Kurni Wicaksana, Agum Widiya Yuli Kartika Siregar Yusuf Ramadhan Nasution Yusuf Ramadhan Nasution Yusuf Ramadhan Nasution, Yusuf Ramadhan Zabni, Nur Hera Zahra Humaira Kudadiri Zaki Musyaffa Ziqra Addilah Zulnun, M. Ridho Azmuddin