Claim Missing Document
Check
Articles

Pemodelan Alat Pencegah Micro-Sleep Sebagai Upaya Mitigasi Kecelakaan Transportasi Sugiharto, Wibowo Harry; Ghozali, Muhammad Imam; Murti, Alif Catur
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 3, No 1 (2019): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (647.546 KB) | DOI: 10.30645/j-sakti.v3i1.92

Abstract

Micro-sleep (MS) is a short sleep condition ranging from 1 to 30 seconds, where people who experience this condition fail to respond to motor sensors and become unconscious. Micro-sleep often occurs as a result of lack of sleep, but not always micro-sleep is caused by lack of sleep, some cases explain that micro-sleep sufferers are also experienced by those who do during monotonous work. Micro-sleep becomes very important when this condition involves dangerous conditions. Even though it's only a few seconds, of course this is very dangerous, and may be one of the main causes of accidents. By utilizing sensor technology, we can do realtime monitoring of the data of the owner, so that a tool that can detect the condition of the driver who has micro-sleep can be developed. With this information the micro-sleep detector will make a warning to the driver. This is expected to reduce the number of accidents caused by micro-sleep.
Pemodelan Alat Pencegah Micro-Sleep Sebagai Upaya Mitigasi Kecelakaan Transportasi Sugiharto, Wibowo Harry; Ghozali, Muhammad Imam; Murti, Alif Catur
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 3, No 1 (2019): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v3i1.92

Abstract

Micro-sleep (MS) is a short sleep condition ranging from 1 to 30 seconds, where people who experience this condition fail to respond to motor sensors and become unconscious. Micro-sleep often occurs as a result of lack of sleep, but not always micro-sleep is caused by lack of sleep, some cases explain that micro-sleep sufferers are also experienced by those who do during monotonous work. Micro-sleep becomes very important when this condition involves dangerous conditions. Even though it's only a few seconds, of course this is very dangerous, and may be one of the main causes of accidents. By utilizing sensor technology, we can do realtime monitoring of the data of the owner, so that a tool that can detect the condition of the driver who has micro-sleep can be developed. With this information the micro-sleep detector will make a warning to the driver. This is expected to reduce the number of accidents caused by micro-sleep.
Implementasi Sistem Perpustakaan Digital Untuk Mengelola Koleksi E-Book (Studi Kasus: SDN 1 Bulungcangkring) Novianti, Vina; Meimahari, Rizkysari; Ghozali, Muhammad Imam
Progresif: Jurnal Ilmiah Komputer Vol 21, No 1: Februari 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v21i1.2515

Abstract

 A digital library is a library that stores, processes and provides access to digital collections via the internet. SDN 1 Bulungcangkring has limited physical storage space, and users still have difficulty finding books. Implementing a digital library can save physical storage space and help in managing collections better. This research uses the waterfall method with stages of needs analysis, system design, implementation, testing and maintenance. The test results show that the digital library system developed can manage e-book collections more efficiently, increase user accessibility, and make it easier to search and borrow books.Keywords: Digital library; E-books; Library information system AbstrakPerpustakaan digital adalah perpustakaan yang menyimpan, memproses, dan menyediakan akses ke koleksi digital melalui internet. SDN 1 Bulungcangkring memiliki keterbatasan ruang penyimpanan fisik, dan pengguna masih kesulitan mencari buku. Implementasi perpustakaan digital dapat menghemat ruang penyimpanan fisik dan membantu dalam mengelola koleksi dengan lebih baik. Penelitian ini menggunakan metode Waterfall dengan tahapan analisis kebutuhan, desain sistem, implementasi, pengujian, dan pemeliharaan. Hasil pengujian menunjukkan bahwa sistem perpustakaan digital yang dikembangkan dapat mengelola koleksi e-book dengan lebih efisien, meningkatkan aksesibilitas pengguna, serta mempermudah pencarian dan peminjaman buku.Kata kunci: Perpustakaan digital; E-book; Sistem informasi perpustakaan
OTOMATISASI PEMUSATAN JARINGAN IPV4 dan IPV6 MENGGUNAKAN RIVERBED MODELER GHOZALI, MUHAMMAD IMAM
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 5 No 1 (2020): APRIL
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (296.481 KB) | DOI: 10.24252/instek.v5i1.13687

Abstract

Simulasi jaringan adalah teknik untuk menguji operasi teknologi atau protokol sebelum penyebaran aktualnya, atau bahkan selama penyebaran. Konsep-konsep ini terkait konsistensi Kualiatas Layanan dua protokol IPv4 dan IPv6 dalam jaringan skala besar seperti internet. Tidak ada yang dapat menyangkal bahwa sebagian besar Penyedia Layanan Internet (ISP) hanya menyediakan jaringan akses berbasis IPv4, namun, klien dapat menggunakan IPv6 secara lokal. Beberapa mekanisme transisi dan teknik penerjemahan alamat dapat digunakan untuk mengakomodir interkoneksi dua protokol yang berbeda. Dalam makalah ini, kami mengusulkan pendekatan baru untuk mengotomatisasi simulasi mekanisme transisi IPv6 dan IPv4 dalam jaringan skala besar. Pendekatan yang diusulkan dengan simulator Riverbed Modeler dan dapat dimodifikasi untuk memasukkan simulator jaringan lainnya. Hasil evaluasi pendekatan menunjukkan bahwa durasi pengaturan jaringan komputer dengan 100 node IPv6 yang saling berhubungan melalui jaringan IPv4 tidak melebihi total 30 detik. Kata Kunci : simulasi,otomatisasi,ipv4,ipv6, riverbed modeler, jaringan komputer
Comparative Analysis of Machine Learning Algorithms for Predicting Patient Admission in Emergency Departments Using EHR Data Chamid, Ahmad Abdul; Nindyasari, Ratih; Ghozali, Muhammad Imam
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 2 (2025): April 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i2.6188

Abstract

Every patient who is rushed to the Emergency Department needs fast treatment to determine whether the patient should be inpatient or outpatient. However, the existing fact is that deciding whether an inpatient or outpatient must wait for the diagnosis made by the existing doctor, so if there are many patients, it generally takes quite a long time. So, to predict patient admissions to the emergency unit, a machine learning model that can be fast and accurate is needed. Therefore, this study developed a machine learning and neural network model to determine patient care in Emergency Departments. This study uses publicly available electronic health record (EHR) data, which is 3,309. The model development process uses machine learning methods (SVM, Decision Tree, KNN, AdaBoost, MLPClassifier) and neural networks. The model that has been obtained is then evaluated for its performance using a confusion matrix and several matrices such as accuracy, precision, recall, and F1-Score. The results of the model performance evaluation were compared, and the best model was obtained, namely the MLPClassifier model with an accuracy value = 0.736 and an F1-Score value = 0.635, and the Neural Network model obtained an accuracy value = 0.724 and an F1-Score value = 0.640. The best models obtained in this study, namely the MLPClassifier and Neural Network models, were proven to be able to outperform other models.
ANALISIS SENTIMEN TERHADAP TAGAR #KABURAJADULU DI MEDIA SOSIAL X MENGGUNAKAN METODE NAÏVE BAYES Hamim Aftoni, Tsanil; Sugiharto, Wibowo Harry; Ghozali, Muhammad Imam
Jurnal Komputer dan Teknologi Vol 4 No 2 (2025): JUKOMTEK JULI 2025
Publisher : Yayasan Pendidikan Cahaya Budaya Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64626/jukomtek.v4i2.443

Abstract

Tingginya aktivitas masyarakat Indonesia di media sosial, khususnya platform X (dahulu Twitter), mencerminkan kuatnya opini publik terhadap berbagai isu sosial, termasuk kritik terhadap kebijakan pemerintah. Salah satu fenomena yang viral adalah tagar #kaburajadulu, yang merepresentasikan ekspresi kekecewaan terhadap kondisi sosial, ekonomi, dan politik. Penelitian ini bertujuan untuk mengklasifikasikan sentimen masyarakat terhadap tagar tersebut ke dalam tiga kategori: positif, negatif, dan netral, serta mengevaluasi performa metode Naïve Bayes Multinomial dalam klasifikasi sentimen. Data dikumpulkan melalui proses crawling dari platform X, kemudian diproses melalui tahap pra-pemrosesan teks, pelabelan menggunakan InSet Lexicon, dan pembobotan fitur menggunakan TF-IDF. Model Naïve Bayes dilatih dan diuji dengan pembagian data 80:20 serta dievaluasi menggunakan 10-Fold Cross Validation dengan metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkanbahwa model berhasil mengklasifikasikan sentimen negatif dengan baik (akurasi 75%), namun belum optimal dalam mengenali sentimen positif dan netral. Penelitian ini mengonfirmasi dominasi opini negatif terhadap tagar #kaburajadulu dan membuka peluang pengembangan metode klasifikasi yang lebih kompleks pada isu-isu sosial digital.
MEDIA PEMBELAJARAN TENTANG ANIMASI SHOLAT Aziz, Fitrian Abdul; Ghozali, Muhammad Imam; Sugiharto, Wibowo Harry
AKSELERASI: Jurnal Ilmiah Nasional Vol 7 No 1 (2025): AKSELERASI: JURNAL ILMIAH NASIONAL
Publisher : GoAcademica Research dan Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54783/jin.v7i1.1269

Abstract

Setiap muslim memiliki kewajiban untuk melaksanakan ibadah sholat fardhu, yaitu sholat 5 waktu dalam sehari semalam. Hukum sholat 5 waktu adalah fardhu‘ain. Sejak kecil kita harus menanamkan kebiasaan sholat, ketika beranjak baligh akan menjadi kewajiban. Tata cara praktek sholat melalui media buku yang merupakan media tradisional terkadang dinilai kurang efektif, hal ini mungkin disebabkan oleh kurang tertariknya para pembelajar untuk membaca dan bersifat monoton. Tujuan dari penelitian ini adalah membuat animasi 2D sebagai media pembelajaran alternatif.
Android-Based Studend Cooperative Application (Case Study of Kopma UMK) Agung Prasetyo; Ghozali, Muhammad Imam; Sugihartono, Wibowo Harry
Jurnal Teknologi Informasi dan Pendidikan Vol. 18 No. 2 (2025): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v18i2.1054

Abstract

Many cooperatives in Indonesia still rely on manual systems, resulting in slow processes, inefficiency, and data inconsistencies. To address this issue, an Android-based KOPMA application was developed using the Dart programming language and Flutter framework. The system facilitates management of member data, sales transactions, and savings in a more effective way. Implementation at KOPMA Universitas Muria Kudus demonstrated faster services, reduced data errors, and improved work effectiveness, while also contributing to student entrepreneurship through a modern and integrated system.
Analyzing Criteria Count Impact on SAW and TOPSIS Stability in Decision Support Systems Murti, Alif Catur; Ghozali, Muhammad Imam; Puta, Indra Lina; Ikhwan, Ali
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.25707

Abstract

This study investigates how increasing the number of decision criteria (5–30) affects the ranking stability and computational efficiency of Simple Additive Weighting (SAW) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Previous studies compared these methods in domains such as scholarship selection and food assistance but did not examine how rankings evolve under greater complexity. Using a synthetic dataset of five fixed alternatives with multiple random seeds, results show that SAW is more prone to ranking fluctuations, while TOPSIS demonstrates greater stability. Kendall’s Tau reveals variability across scenarios, and sensitivity tests confirm that agreement depends on data generation. Computationally, SAW exhibits quasi-linear growth in processing time (≈0.002–0.008 s), whereas TOPSIS remains efficient (≈0.002–0.004 s) with minimal variance. These findings highlight a context-dependent choice SAW offers simplicity in low-dimensional settings, while TOPSIS provides scalability and robustness for complex, high-stakes decision support.
Performance Comparison of WSN Topologies in IoT-Based Water Quality Monitoring Systems Ghozali, Muhammad Imam; Murti, Alif Catur; Sugiharto, Wibowo Harry; Roder, Klaus
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.25706

Abstract

This study, we quantify how WSN topology shapes QoS for IoT water-quality monitoring and derive deployment rules. Five topologies (Hybrid Star–Mesh, Cluster Tree, Full Mesh, Ring, ZigBee Star; 20 nodes) were simulated in NS-3 for 10 independent runs with random seeds. Our mathematical contribution is a compact QoS model set—latency LLL, packet-loss PlossP_{\text{loss}} Ploss, bandwidth usage UBU_BUB, and throughput TTT—used to compare topologies and compute relative/absolute improvements. Statistics report mean±SD with 95% confidence intervals from Student’s t-distribution; pairwise Mann–Whitney tests with Benjamini–Hochberg FDR control (α=0.05) yield compact-letter displays; Cliff’s δ quantifies effect sizes. Results: Hybrid Star–Mesh minimizes latency/loss while maximizing throughput; Ring is consistently inferior; Cluster Tree and ZigBee Star are mid-range; Full Mesh trades redundancy for delay and bandwidth. These models produce actionable guidance for aquaculture (real-time dissolved-oxygen) and urban drinking-water safety, and motivate multi-objective optimization (latency–throughput–energy) toward Pareto-optimal designs.