Claim Missing Document
Check
Articles

Found 40 Documents
Search

STUDI KOMPARASI ALGORITMA RANDOM FOREST CLASSIFIER DAN SUPPORT VECTOR MACHINE DALAM PREDIKSI PENYAKIT JANTUNG Alfajr, Nur Halizah; Garno, Garno; Yusup, Dadang
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3.6569

Abstract

Heart disease is a non-communicable disease with a high mortality rate both globally and in Indonesia. According to WHO, around 17.9 million deaths occur each year due to cardiovascular diseases. Early prediction is crucial to reducing mortality and improving life expectancy. This study compares the performance of machine learning algorithms Random Forest Classifier and Support Vector Machine in predicting heart disease. The dataset consists of 5432 medical records from cardiac outpatients at RSUD Kabupaten Bekasi in 2024, with two classes (labeled 1 (heart disease) = 3068 and labeled 0 (non-heart disease) = 2364). Models were developed using the Knowledge Discovery in Databases (KDD) approach. Evaluation results show that the Support Vector Machine model achieved the best performance compared to Random Forest Classifier with 65% accuracy, 70% precision, 68% recall, and 64% f-measure. Cross-validation and ROC analysis also indicated that Support Vector Machine obtained the highest AUC score, ranging from 0.67 to 0.68, which is categorized as poor classification.
PERANCANGAN SISTEM PEMANTAU DETAK JANTUNG PASIEN MENGGUNAKAN SERVER WEB BERBASIS INTERNET OF THINGS (IoT) PADA KLINIK BIDAN NINING Setiawan, Fikri Maulana; Purwantoro, Purwantoro; Garno, Garno
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3.6677

Abstract

Dalam konteks pelayanan kesehatan di Indonesia, khususnya pada fasilitas kesehatan tingkat pertama seperti klinik bidan, keterbatasan peralatan medis modern sering menjadi hambatan dalam memberikan layanan kesehatan optimal. Penelitian ini dilatarbelakangi oleh tantangan spesifik di Klinik Bidan Nining yang meliputi ketiadaan alat pemantauan detak jantung, tingginya angka rujukan ke rumah sakit, serta beban ekonomi dan waktu yang ditanggung pasien untuk mendapatkan pemeriksaan lanjutan. Solusi yang diusulkan adalah sistem terintegrasi yang menggabungkan sensor detak jantung MAX30102 dengan mikrokontroler NodeMCU ESP8266 yang terhubung ke web server, memungkinkan pemantauan dan analisis data kesehatan secara real-time.
Prototype Kendali Otomatis Peralatan Listrik dalam Ruangan Menggunakan Arduino Garno, Garno; Purwantoro, Purwantoro; Hidayat, Ibnu Nur
Jurnal Ilmu Teknik dan Komputer Vol 9, No 2 (2025)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian bergerak dalam bidang penggunaan perangkat keras yang digunakan sebagai teknik otomatisasi. Perangkat dibangun berbentuk prototype sebagai sarana eksperimen dalam pengujian sistem kendali. Penelitian mengangkat penyelesaian masalah pemborosan listrik. Faktor pemborosan listrik diantaranya tidak dimatikannya daya listrik setelah selesai digunakan dapat berupa kelalaian pengguna, ketidakdisiplinan pengguna, kurang praktisnya peralatan karena masih bermetode manual sehingga pengguna malas. Metode yang diajukan untuk mengatasi masalah dengan membuat prototype sistem kendali otomatis sebelum implementasi sebenarnya. Prototype yang dibangun menggunakan Arduino uno sebagai kontrol utama sistem kendali terhubung Sensor PIR, sensor DHT11, sensor LDR dan LCD. Hasil penelitian dari pengujian prototype yang dibangun dan perbandingan tingkat efisiensi jika kendali otomatis diterapkan yaitu pengujia sensor gerak mencapai tingkat sensitif maksimal sejauh 6 meter dalam ruangan, sensor suhu sangat sensitif dan proses tercapainya nillai suhu pada temperatur aktual harus menunggu selama ± 12 menit sebab DHT11 sangat sensitive dengan keadaan sekitar, serta deteksi cahaya memiliki ketepatan 399-200 bit/scond tergolong sedikit gelap dan lampu sudah menyala. Hasil eksperimen selama 2 bulan terakhir dengan melakukan penerapan prototype ke dalam kondisi sebenarnya diruangan kerja ditempat studi kasus memberikan informasi mengalami penurunan pemakaian daya dari kebiasaan bulan sebelumnya yaitu mencapai 28.22%.
Implementasi Design Thinking Dalam Meningkatkan User Experience Pada Website Bemitory Milik Bem Fasilkom Unsika Irna Purnahasanah; Garno, Garno; Betha Nurina Sari
Innovative: Journal Of Social Science Research Vol. 5 No. 4 (2025): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v5i4.20492

Abstract

The development of information technology demands improved user experience (UX) in web-based applications. This study aims to recommend a redesigned user interface (UI) for the Bemitory website owned by BEM Fasilkom Unsika and evaluate its usability based on three ISO 9241-11 aspects: effectiveness, efficiency, and satisfaction. The research method used is Design Thinking, consisting of five stages: empathize, define, ideate, prototype, and testing. This approach explores the needs and expectations of users, particularly students of Fasilkom. The results show an increase in the average System Usability Scale (SUS) score from 45 to 94,5 after redesign. This score is categorized as “Best Imaginable” in adjective rating, grade “A”, and “Acceptable” in acceptability. Task completion effectiveness reached 100%, and time-based efficiency reached 0.16 goals per second. These findings indicate that implementing Design Thinking in website development effectively improves user satisfaction, efficiency, and effectiveness, and is suitable for creating more user-centered UI designs. Keywords: Design Thinking, System Usability Scale, UI, UX, Website
Socialization of Digital Literacy and Artificial Intelligence to Improve Knowledge and Skills in Rangdumulya Village Voutama, Apriade; Maulana, Iqbal; Yusup, Dadang; Garno, Garno; Novalia, Elfina
Society : Jurnal Pengabdian Masyarakat Vol. 4 No. 3 (2025): Mei
Publisher : Edumedia Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55824/jpm.v4i3.524

Abstract

The socialization of Digital Literacy and Artificial Intelligence was carried out in Randumulya Village, Karawang Regency, which focused on increasing the community's insight into skills so that they can train and create creative ideas and opportunities. The socialization was carried out by two targets, namely to village officials and the community and students at elementary schools in the village. This activity was carried out in the Village Hall with resource persons who were expert lecturers in their fields and activities with students were carried out at the school and accompanied by students to be more interactive. The results of the satisfaction of 55 respondents who were carried out by distributing questionnaires reached 85% who stated that they were satisfied. With this training, it can help the village community to know and get benefits from digital literacy and technological intelligence so that it has a positive impact and standard of living in the village.
ANALISIS SENTIMEN TERHADAP PELAYANAN DISDUKCAPIL KARAWANG MENGGUNAKAN NAIVE BAYES CLASSIFIER Nurian, Andriani; Padilah, Tesa Nur; Garno, Garno
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 2 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i2.4178

Abstract

Pengelolaan Administrasi Kependudukan penting dalam kehidupan di Indonesia karena terkait dengan banyak aktivitas seperti pemilihan umum, pengurusan dokumen kendaraan dan surat tanah, perbankan, dan lain-lain. Dinas Kependudukan dan pencatatan sipil Kabupaten Karawang melayani administrasi kependudukan kabupaten karawang dan memastikan setiap masyarakat di Kabupaten Karawang tercatat dan terdata oleh Pemerintah Republik Indonesia melalui daerah dan melimpahkan sebagian wewenangnya kepada Dinas penduduk dan pencatatan sipil Kabupaten Karawang. Analisis sentimen terhadap pelayanan Disdukcapil Karawang digunakan untuk memberikan gambaran tentang opini publik terhadap pelayanan Disdukcapil Karawang. Hasil pengolahan opini atau sentimen dari penerapan algoritma Naïve bayes menggunakan metodologi KDD kedalam tiga kelas yaitu Positif, Netral dan Negatif melalui media sosial Twitter  menggunakan penerapan algoritma Naïve bayes diperoleh hasil yaitu 146 label positif, 189 label negatif, dan 961 label netral. Nilai accuracy tertinggi terdapat pada  model 90:10 dengan 69%, precision 82%, dan recall 48%. Selain menggunakan confusion matrix model diuji dengan grafik ROC yang menghasilkan nilai AUC tertinggi pada model 90:10 dengan nilai 0.79 yang dapat diartikan model ini kualitasnya good classification.
ANALISIS SENTIMEN PERFORMA “VIDEO ASSISTANT REFEREE” MENGGUNAKAN ALGORITMA NAÏVE BAYES Athariq, Fajar; Garno, Garno; Maulana, Iqbal
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4912

Abstract

Video Assistant Referee (VAR) adalah teknologi yang diterapkan dalam sepak bola untuk membantu wasit membuat keputusan yang lebih akurat. Meskipun bertujuan untuk meningkatkan keadilan dalam permainan, penerapan VAR sering kali memicu kontroversi dan perdebatan di kalangan penggemar serta pemain sepak bola. Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap VAR melalui data yang dikumpulkan dari Twitter. Masalah utama yang dihadapi adalah adanya perbedaan pandangan terhadap efektivitas dan dampak VAR, yang mempengaruhi persepsi publik. Metode yang digunakan dalam penelitian ini adalah Naïve Bayes dengan fitur TF-IDF dan teknik oversampling SMOTE. Beberapa skenario pembagian data latih dan uji diterapkan, yaitu 90:10, 80:20, 70:30, dan 60:40. Hasil penelitian menunjukkan bahwa penggunaan SMOTE menghasilkan akurasi tertinggi sebesar 77% pada skenario 80:20 dan 60:40. Sementara itu, nilai precision tertinggi dicapai pada skenario 90:10 dan 80:20 dengan 68%, recall tertinggi pada skenario 90:10 dengan 82%, dan F1-score tertinggi pada skenario 90:10 dengan 85%. Analisis word cloud dari tweet menunjukkan bahwa sentimen negatif terhadap VAR terkait dengan kata-kata seperti "abolish," "rugi," "lama," "kualitas wasit," "problem," dan "kontroversi." Sentimen netral berfokus pada kata-kata seperti "petition," "sign petition," "technology," "league," "football," dan "match official," sementara sentimen positif mencakup kata-kata seperti "langsung," "jelas," "guna," "adil," "bantu," dan "cepat.".
IMPLEMENTASI ALGORITMA K-MEANS UNTUK KLASTERISASI DALAM PENGELOLAAN PERSEDIAAN OBAT (STUDI KASUS : APOTEK NAZA) Fitriyani, Dede; Jajuli, Mohamad; Garno, Garno
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4921

Abstract

Apotek Naza plays an important role in providing medicines to the community. This study utilizes sales data from Apotek Naza for the period of July to December 2023. The K-Means algorithm is used to cluster the medicine data into clusters representing different sales patterns. The Elbow Method is employed to determine the optimal number of clusters (K) based on the Sum of Square Error (SSE). Evaluation is conducted using the Silhouette Coefficient (SC) to measure the quality of the resulting clusters. The analysis results show that the distribution of medicines in each cluster is as follows: 13.7% or 70 items are classified in the high-usage cluster (Cluster 0 - High), 57.5% or 294 items are classified in the medium-usage cluster (Cluster 1 - Medium), and 28.8% or 147 items are classified in the low-usage cluster (Cluster 2 - Low). This indicates a dominance of medium-usage medicines in the Apotek Naza dataset. The obtained Silhouette Score is 0.520, indicating that the clustering is well performed. According to Table 2.1 on the criteria for measuring clustering based on the Silhouette Coefficient (SC), this score indicates that the resulting clusters are fairly compact and well-separated from each other. Keywords: Medicine Inventory, Data Mining, K-Means, KDD, Elbow Method, Silhouette Coefficient
APLIKASI SISTEM MONITORING DAN KONTROL SUHU CAIRAN NOX-RUST (STUDI KASUS: PT ASTRA DAIHATSU MOTOR) Raharjo, Yudi; Garno, Garno; Primajaya, Aji
JTIK (Jurnal Teknik Informatika Kaputama) Vol. 5 No. 2 (2021): Volume 5, Nomor 2, Juli 2021
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jtik.v5i2.576

Abstract

Sistem monitoring dan kontrol suhu nox-rust secara realtime berbasis arduino uno melalui konektifitas bluetooth ini merupakan perpaduan antara alat dan aplikasi yang dirancang berbasis smartphone android dengan modul arduino. Aplikasi ini digunakan pada smartphone android untuk melakukan monitoring dan control suhu cairan nox-rust pada mesin wax applicator. Dengan aplikasi tersebut user dapat memonitoring detail suhu, dan juga dapat mengontrol relay untuk menormalisasi suhu ketika suhu kurang dari batas yang ditentukan. Dalam pembuatan sistem monitoring suhu terdiri dari modul arduino uno, sensor suhu DS18B20, bluetooth HC-05, Led Indikator, Relay SRC-05VDC-S1-C. Pembuatan aplikasi ini menggunakan MIT App Inventor. Metodologi yang digunakan dalam merancang sistem ini menggunakan metode RUP (Rational Unified Process).
Android-Based Claim System for Electricity Network Customers of PLN Padang Branch Voutama, Apriade; Novalia, Elfina; Garno, Garno
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 6 No 2 (2022): August 2022
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/intensif.v6i2.17433

Abstract

The Padang branch of the State Electricity Company (PLN) is a BUMN responsible for the electricity aspect. Complaints about various electricity problems are difficult for customers, so it is necessary to have a system that can be used as a place for protests and increase PLN's loyalty to customers. The Android-based Claim System is a new application developed to be used by customers as a forum for complaints about electrical problems to the Padang branch of PLN. The Claim System is made into two parts: a Website-based System for PLN and an Android-based Claim Application for customers. Application development using the OOP concept uses UML (Unified Modeling Language) diagrams with the PHP MySql and Android programming languages. The test results were carried out using black box testing with the relevant results. The data of 35 respondents from the assessment questionnaire on the claims system obtained results with an Excellent rating of 78%, a Good rating of 21%, and a Bad rating of 2%. From the analysis results, the Claim System supported by this Android-based Client application can help customers complain about electrical problems quickly and easily.