Claim Missing Document
Check
Articles

Found 31 Documents
Search

Implementasi Algoritma Support Vector Machine (SVM) Untuk Diagnosis Kesehatan Manusia Berbasis Web Application Ramadhani, Mifta Aulia; Khumaidi, Agus
Jurnal Ners Vol. 9 No. 1 (2025): JANUARI 2025
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jn.v9i1.31481

Abstract

Rumah sakit mempunyai peranan penting dalam kesehatan masyarakat. Namun, rumah sakit mempunyai banyak kekurangan salah satunya adalah dari segi pelayanan. Oleh karena itu, untuk meningkatkan efisiensi pelayanan rumah sakit dilakukan perancangan sistem diagnosis kesehatan manusia melalui aplikasi web berbasis kecerdasan buatan yaitu support vector machine. Support Vector Machine (SVM) merupakan algoritma supervised learning yang bekerja dengan cara mencari hyperplane antara dua kelas data hingga mendapatkan margin terbesar. SVM mempunyai beberapa keunggulan serta performa yang baik, seperti kemampuan generalisasi yang tinggi dan mempunyai fungsi kernel untuk digunakan pada dataset yang berdimensi tinggi sehingga sering digunakan di berbagai penelitian. Pengumpulan data dilakukan dengan penyebaran kuisioner kepada masyarakat umum dengan jumlah responden sebanyak 1.164 orang serta wawancara dengan expert judgement untuk menentukan 10 penyakit dan 40 gejala penyakit. Hasil penelitian menunjukkan tingkat akurasi pengujian diagnosis penyakit pasien mencapai 99%. Inovasi ini memungkinkan diagnosis gejala penyakit manusia dilakukan dengan lebih tepat dan cepat, sehingga diharapkan dapat meningkatkan produktivitas rumah sakit dan derajat kesehatan masyarakat Indonesia secara keseluruhan. Kata Kunci: Diagnosis Penyakit, Support Vector Machine (SVM), Rumah Sakit.
Design of a Marine Weather Monitoring System Based on an Arduino System Rahmat, M. Basuki; Widodo, Hendro Agus; Khumaidi, Agus; Budiawati, Ratna; Mudjanarko, Sri Wiwoho
THE SPIRIT OF SOCIETY JOURNAL : International Journal of Society Development and Engagement Vol 8 No 1: September 2024
Publisher : LPPM of NAROTAMA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29138/scj.v8i1.2949

Abstract

The need for information about weather conditions in a particular environment is very necessary for the community, so that they can plan activities for the future. A forecaster cannot process data to predict weather or climate conditions if it is not accompanied by historical data within a predetermined time period. Data is a very important savings for future generations, because data will make the nation's generation smart. Without data, all previous information would not be known to be studied. The current condition of the earth is very worrying and not easy to predict. Therefore, it is very important to have integrated observations and services in coastal and marine areas to support resilience to climate change and other marine hazards.Sustainable marine observations and services are very important and relevant to reduce potential problems and threats arising from climate change.In this paper we will discuss the creation of a tool for monitoring weather, where this tool will take data on humidity, temperature and rainfall. so that from this data we can predict weather conditions in the area. By using the fuzzy method, the combination of these three data can be used by fishermen to make decisions about whether it is still safe to go to sea.The system is built based on Arduino using muoring buoy media. where this tool will be placed in the sea. The power supply system uses solar cells, so that it can independently meet the power needs of the equipment. From the test results the system can work normally and well.
Development of PCB Defect Detection System Using Image Processing With YOLO CNN Method Santoso, Agus Dwi; Cahyono, Ferry Budi; Prahasta, Brendi; Sutrisno, Imam; Khumaidi, Agus
International Journal of Artificial Intelligence Research Vol 6, No 1.1 (2022)
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (212.907 KB) | DOI: 10.29099/ijair.v6i1.343

Abstract

Inside the equipment there are many electronic components such as resistors, transistors, capacitors and so on. When used in the production of electronic equipment, PCBs are very influential in the manufacture of these electronic devices, for example, when there are only a few broken or damaged PCB paths, the electronic device cannot be operated properly. So it is very important in the PCB Quality Check process to check whether there is damage to the PCB or not. Usually in PCB inspection only direct checking is used in the conventional way. Therefore, in this study, the author tries to create and analyze a PCB flaw checking tool with the help of a camera that has a high revolution to replace human vision to make it easier and save costs. The application of this PCB checking tool uses a technology called a laptop and a camera. With these two technologies, Image Processing can be used to detect objects using the OpenCv and Tensorflow libraries. PCB flaw detection tool with the help of Image Processing with the YOLO Convolutional Neural Network method to help determine broken paths and drill holes on the PCB
Pemberdayaan Masyarakat Melalui Pelatihan Penggunaan Perangkat GPS untuk Meningkatkan Keamanan dan Keselamatan Nelayan Kecil di Kenjeran Surabaya Arumsari, Nurvita; Praharsi, Yugowati; Khumaidi, Agus; Aju, Irma Rustini; Widiana, Dika Rahayu; Indriawati, Melta Anindya
Jurnal Cakrawala Maritim Vol. 8 No. 1 (2025): Jurnal Cakrawala Maritim
Publisher : P3M Politeknik Perkapalan Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35991/jcm.v8i1.34

Abstract

Ketergantungan para nelayan kecil di kawasan Kenjeran terhadap iklim dan cuaca berdampak pada panjangnya durasi melaut dimana sekali berangkat bisa sampai seharian di laut. Saat terjadi kondisi bahaya nelayan sulit untuk meminta bantuan karena perangkat keselamatan yang dimiliki terbatas akibat mahalnya harga pasaran perangkat yang disertai dengan teknologi. Jika tiba-tiba terjadi cuaca ekstrem nelayan hanya menunggu di kapal sampai kabut itu hilang, sebelum melanjutkan perjalanan melaut. Untuk meminimalisir terjadinya risiko kecelakaan, maka dalam kegiatan pengabdian ini diaplikasikan suatu perangkat berbasis GPS, jaringan seluler, dan Internet of things (IOT) dinamakan HORORS. Petugas dapat mengetahui posisi kapal nelayan dengan presisi melalui interface ground sector yang telah dibuat secara realtime, dan akan menerima notifikasi apabila terjadi kecelakaan atau kondisi bahaya. Dari hasil penilaian oleh 15 nelayan pada saat In Depth Interview demonstrasi, dimensi kinerja dan ketahanan perangkat dinilai kurang baik. Hal ini juga dibuktikan melalui uji coba koneksi telah menunjukkan hasil bahwa alat ini hanya mampu menerima koneksi dengan jarak Ground Sector (GS) maksimum 1300 km. Sedangkan penilaian terhadap dimensi ketahanan perangkat diuji dengan memasukkan perangkat ke dalam air. Hasilnya dianggap masih belum memadai dikarenakan sampling waktu uji hanya sekali dengan durasi kurang dari 20 menit. Sementara itu rata-rata jarak melaut nelayan per hari sekitar 10 – 20 km dengan durasi rata-rata 6 – 8 jam. Dengan demikian, program pengembangan ke depan agar berkelanjutan untuk perangkat ini adalah penyempurnaan kinerja dan inovasi perangkat. Inovasi perangkat diperlukan dengan menambahkan menu prediksi cuaca, angin dan curah hujan yang lebih akurat pada hari yang sama
Implementation of integrated temperature, humidity, and dust monitoring system on building electrical panel Khumaidi, Agus; Hasin, Muhammad Khoirul; Pujiputra, Anggarjuna Puncak; Irsyad, Sholahuddin Muhammad; Rinanto, Noorman; Rachman, Isa; Budi, Perdinan Setia; Malik, Alfianto Taufiqul; Bayu, Nurissabiqoh Binta
Journal of Soft Computing Exploration Vol. 5 No. 4 (2024): December 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v5i4.483

Abstract

This research aims to develop and implement an electrical power monitoring system at the Sub Sub Distribution Panel (SSDP) in the Building. The system is designed to monitor power usage in real-time, provide accurate information on energy consumption, and detect potential energy waste. The methodology used includes hardware and software design. The hardware consists of current and voltage sensors connected to a microcontroller. The data collected by the sensors is then transmitted via Wi-Fi network to the server for analysis. The software uses an Internet of Things (IoT) platform that displays the data in the form of graphs and tables. The implementation shows that the system is capable of monitoring power usage with a high degree of accuracy. The sensors used, namely PM2100 for voltage, SHT20 for temperature and humidity, and GP2Y101AU0F for dust concentration, proved effective in generating accurate real-time data. Based on the test results, the voltage measurement error with the PM2100 was only 0.035%, while the current measurement resulted in an error of 0.48%. The SHT20 sensor recorded an error of 2.4% for temperature and 1.0% for humidity. Dust measurements with the GP2Y101AU0F sensor had a very small error of 0.02%. These results indicate that the tested device has a sufficient level of precision for electrical power and environmental monitoring applications.
PEMETAAN POSISI ROBOT SOCCER MENGGUNAKAN GYRODOMETRY DAN TRIGONOMETRY UNTUK MEMPREDIKSI SUDUT TENDANGAN Agus Khumaidi
Jurnal Poli-Teknologi Vol. 19 No. 3 (2020)
Publisher : Politeknik Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/pt.v19i3.2864

Abstract

The main robot that robots must have in wheeled balls is the ability to find balls, position in the goal, kick the ball and between robots with base station in the wheeled Indonesian Soccer Robot Contest (KRSBI). Wheeled type. KRSBI is one of the activities that are part of the Indonesian Robot Contest (KRI) as a venue for engineering and design competition in the field of robotics. One obstacle to the robot In the detection of the goal is still applying the Robust Algorithms method using only a camera, so that the search process is still relatively slow and kicking the ball is still often deviated from the opponent's goal. In this research, applying the Gyrodometry method in mapping the position of the robot in the field based on reading the sensor data of Rotary encoder and Gyroscope. Then the data will be sent from the microcontroller to the base station via PC and Router to be mapped. Whereas to detect the goal using Trigonometry calculation with the search of the goal based on the position of the robot's data on the Field with the opponent's goal point. The advantage of applying the Gyrodometry method in mapping the position of the robot in the field and Trigonometry calculations for goal detection can improve the efficiency of the robot to detect the goal with average speed (2.1s) and with an accuracy of 91.7%.
Identifikasi Penyebab Cacat Pada Hasil Pengelasan Dengan Image Processing Menggunakan Metode Yolo Khumaidi, Agus; Pradana, Rizal Lucky
Jurnal Teknik Elektro dan Komputer TRIAC Vol 9, No 2 (2022): Special Edition
Publisher : Jurusan Teknik Elektro Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/triac.v9i3.15997

Abstract

In everyday life, of course, we often see iron or metal objects that are connected to each other. The joining of these two metals is known as welding. Incomplete welding can cause defects in the welding results, the occurrence of electrode buildup, excessive spatter, and porosity that occurs in the metal plate. Visual Inspection is one of the Non Distructive Test (NDT) methods for the process of testing the welding results. This process is still using the manual method, namely with human eyesight, so the test results are still subjective. The author has an innovation to detect the cause of welding defects using image processing using the YOLO method. Based on testing using the YOLO method, a success value of 92% was obtained.
Identifikasi Warna Buoy Menggunakan Metode You Only Look Once Pada Unmanned Surface Vehicle Romadloni, Faiz; Endrasmono, Joko; Putra, Zindhu Maulana Ahmad; Khumaidi, Agus; Rachman, Isa; Adhitya, Ryan Yudha
Jurnal Teknik Elektro dan Komputer TRIAC Vol 10, No 1 (2023): Mei 2023
Publisher : Jurusan Teknik Elektro Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/triac.v10i1.19650

Abstract

Abstract— Unmanned Surface Vehicle merupakan kapal permukaan tanpa awak yang dapat beroperasi secara otomatis maupun manual dengan kontrol dari manusia. Unmannned Surface Vehicle dilengkapi oleh berbagai sistem seperti sistem komunikasi, sistem propulsi, dan sistem deteksi yang memungkinkannya untuk dapat berlayar dan bernavigasi dengan baik. Salah satu sarana navigasi yang penting dalam dunia pelayaran adalah buoy (pelampung suar). Buoy memiliki kode warna tertentu yang digunakan sebagai tanda peringatan, larangan, atau perintah bagi kapal yang memasuki area tersebut. Oleh karena itu, identifikasi warna buoy secara cepat, tepat, dan real-time sangat dibutuhkan untuk mengurangi potensi kecelakaan di wilayah laut, terutama pada Unmanned Surface Vehicle yang tidak memiliki awak kapal. Pada penelitian ini digunakan metode You Only Look Once untuk mengidentifikasi warna buoy. Metode You Only Look Once dipilih karena dapat mendeteksi objek secara real-time dengan kecepatan yang tinggi. Dari hasil penelitian didapatkan nilai Mean Average Precision sebesar 99,3% dan nilai average loss sebesar 0,2383. Algoritma ini juga telah diuji pada intensitas cahaya yang berbeda beda. dimana semua pengujian menghasilkan rata rata nilai deteksi sebesar 98,8% untuk buoy merah dan 100% untuk buoy hijau. Sehingga dapat disimpulkan bahwa metode ini memiliki nilai yang baik dalam deteksi maupun akurasi.Kata Kunci— Unmanned Surface Vehicle, Buoy, You Only Look Once, Warna, Real-Time
Sistem Tracking Posisi Kamera Menggunakan Pengolahan Citra Untuk Pemusatan Posisi Pengambilan Video di Automation Academy Khumaidi, Agus; Priyonggo, Projek; Kusumah, Adam; Rahmat, M. Basuki; Endrasmono, Joko
Jurnal Teknik Elektro dan Komputer TRIAC Vol 9, No 2 (2022): Special Edition
Publisher : Jurusan Teknik Elektro Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/triac.v9i2.16021

Abstract

Kamera merupakan komponen yang sangat penting pada Automation Academy, dimana pada aktivitas yang dilakukan dalam perusahaan ini adalah berhubungan dengan video dan isi dari video adalah materi yang di unggah pada website automationacademy.com, sehingga kamera sangat mengambil peranan yang tidak kalah besarnya dengan peranan lain. Dalam pengambilan video biasanya harus ada paling sedikit 2 orang untuk menjadi cameraman, ini menjadi masalah karena melihat keterbatasan sumber daya manusia yang ada di Automation Academy. Penelitian ini bertujuan untuk meminimalisir masalah tersebut dengan membuat Sistem Tracking Posisi Kamera Menggunakan Pengolahan Citra Untuk Pemusatan Posisi Pengambilan Video di Automation Academy, pada penelitian ini, framework MediaPipe  digunakan sebagai pengolahan citra untuk pengenalan posisi pemateri yang akan direkam menggunakan kamera DSLR. Mekanik dari Sistem Tracking Posisi Kamera Menggunakan Pengolahan Citra Untuk Pemusatan Posisi Pengambilan Video di Aautomation Academy bekerja sesuai dengan sistem yang telah direncanakan. Akurasi dari pendeteksian menggunakan framework MediaPipe sangat bagus, dapat terdeteksi dengan jarak antara 1,5 meter hingga 8 meter. Kemudian intensitas cahaya yang ideal adalah antara 125 lux hingga 190 lux. Lalu agar posisi kamera dapat mengikuti manusia dengan cara mengubah nilai pixels menjadi pulse dari motor stepper
Coating Inspection on Sea Transportation Equipment (Ship) Using Image Processing Dianita Wardani; Agus Khumaidi; Rizal Fahmi; Imah Luluk Kusminah; Basuki Rahmat
Indonesian Journal of Innovation Multidisipliner Research Vol. 2 No. 2 (2024): April - June
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/ijim.v2i2.133

Abstract

Research in the last decade, particularly in this research there are methods and steps for completion, namely 4 process steps, including: First of all, take samples and image data from the parts of the ship that are being repaired and maintained, Then, in making the prototype tool resulting from the coating, it is assembled using several tools, mini PC is installed with a web camera, next the image for the observation further processes and processed using the edge method contours detection with the help of cany to obtain the contrast and contour from the ship's hull. For next process, uses Neural Network for image creation processes taken from prototype plating or plating on observed ship parts. Some mixed results from the process. The images taken areand thenthe data obtained is processed and its form is observedfor shape, pattern,corrosion, contour and so on layers formed. There are two classifications of RGB and GLCM results, the rejected results can match the corrosion spot found on the hull, and the accepted results mean no corrosion spot found.
Co-Authors Abdul Hafizh Abyan Faruq Achmad, Vandy Adhitya, Ryan Yudha Adi Rahmad Ramadhan Adi Wisnu Sahputera Adianto Adianto Afianto, Afif Zuhri Am Maisarah Disrinama Anggarjuna Puncak Pujiputra Ardiana, Mirza Arfianto, Afif Zuhri Arief Subekti Arninputranto, Wibowo Arumsari, Nurvita Astutik, Rina Puji Aulia Rahma Annisa Bagus Setiawan, Danis Basuki Rahmat Basuki Rahmat Masdi Siduppa Basuki Rahmat, Mohammad Bayu, Nurissabiqoh Binta Bhakti Bhakti Budi, Perdinan Setia Budiawati, Ratna Budiyanto, Ekky Nur C. I. Sutrisno Cahyono, Ferry Budi Danis Bagus Setiawan Darmawan, Wahyu Dewi Kurniasih Dianita Wardani Dianita Wardani Dika Rahayu Widiana Endrasmono, Joko Fadlol, Muhammad Thoriq Faturrahman, Bima Fitri Hardiyanti Hafid, Mohammad Arigo Al. Hananta A Hasin, M. Khoirul Hasin, Muhammad Khoirul Hendro Agus Widodo, Hendro Agus Ihsania, Tsabita Ii Munadhif Imah Luluk Kusminah Imam Sutrisno Imam Sutrisno Imam Sutrisno Indriawati, Melta Anindya Irfan Marzuqi Irma Rustini Aju Jami’in, Mohammad Abu Joesianto Eko Poetro Joko Endrasmono Joko Endrasmono Khoirun Nasikhin Kusminah, Imah Luluk Kusumah, Adam Lilik Subiyanto M. Basuki Rahmat Mades Darul Khairansyah Malik, Alfianto Taufiqul Mat Syai’in Mochamad Yusuf Santoso Mohammad Basuki Rahmat Mustika Kurnia Mayangsari Nasikhin, Khoirun Noorman Rinanto Oktavia, Shelly Pradana, Rizal Lucky Prahasta, Brendi Pristovani Riananda, Dimas Pristovani, Dimas Projek Priyonggo Sumangun Lukitadi Pujiputra, Anggarjuna Puncak Putra, Zindhu Maulana Ahmad Rafsanjani, Zainu Rahmat, M. Basuki Rahmawati, Nanda Putri Ramadhani, Mifta Aulia Riananda, Dimas Pristovani Rinanto, Noorman Rizal Fahmi Rizal Fahmi Rizky, Sofi Berliana Romadloni, Faiz Ryan Yudha Adhitya Santoso, Agus Dwi Setiani, Vivin Setyawati, Emeralda Eka Putri Sholahuddin Muhammad Irsyad Sholihah, Mar'atus Sri Wiwoho Mudjanarko, Sri Wiwoho Sryang T Sarena Suwandi, Donny Aryo Seno Syai’in, Mat Syai’in Wahyudi, Mohammad Thoriq Wibowo, Sekarsari Wisnu Sahputera, Adi Yudha Adhitya, Ryan Yugowati Praharsi Yuning Widiarti, Yuning Zazila, Mujtaba Fa'akuli Zindhu Maulana Ahmad Putra