Garuda - Garba Rujukan Digital

Analisis Perbandingan KNN dengan SVM untuk Klasifikasi Penyakit Diabetes Retinopati berdasarkan Citra Eksudat dan Mikroaneurisma AULIA, SUCI; HADIYOSO, SUGONDO; RAMADAN, DADAN NUR
Jurnal Elkomika Vol 3, No 1 (2015): Jurnal Elkomika
Publisher : Jurnal Elkomika

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

ABSTRAK Penelitian mengenai pengklasifikasian tingkat keparahan penyakit Diabetes Retinopati berbasis image processing masih hangat dibicarakan, citra yang biasa digunakan untuk mendeteksi jenis penyakit ini adalah citra optik disk, mikroaneurisma, eksudat, dan hemorrhages yang berasal dari citra fundus. Pada penelitian ini telah dilakukan perbandingan algoritma SVM dengan KNN untuk klasifikasi penyakit diabetes retinopati (mild, moderate, severe) berdasarkan citra eksudat dan microaneurisma. Untuk proses ekstraksi ciri digunakan metode waveletÂ pada masing-masing kedua metode tersebut. Pada penelitian ini digunakan 160 data uji, masing-masing 40 citra untuk kelas normal, kelas mild, kelas moderate, kelas saviere. Tingkat akurasi yang diperoleh dengan menggunakan metode KNN lebih tinggi dibandingkan SVM, yaitu 65 % dan 62%. Klasifikasi dengan algoritma KNN diperoleh hasil terbaik dengan parameter K=9 cityblock. Sedangkan klasifikasi dengan metode SVM diperoleh hasil terbaik dengan parameter One Agains All. Â Kata Kunci : Diabetic Retinopathy, KNN , SVM, Wavelet. ABSTRACT Research based on severity classification of the disease diabetic retinopathy by using image processing method is still hotly debated, the image is used to detect the type of this disease is an optical image of the disk, microaneurysm, exudates, and bleeding of the image of the fundus. This study was performed to compare SVM method with KNN method for classification of diabetic retinopathy disease (mild, moderate, severe) based on exudate and microaneurysm image. For feature extraction uses wavelet method, and each of the two methods. This study made use of 160 test data, each of 40 images for normal class, mild class, moderate class, severe class. The accuracy obtained by KNN higher than SVM, with 65% and 62%. KNN classification method achieved the best results with the parameters K = 9, cityblock. While the classification with SVM method obtained the best results with parameters One agains all . Keywords : Diabetic Retinopathy, KNN, SVM, Wavelet.

Purwarupa Radar sebagai Pendeteksi Benda Diam menggunakan Ultrasonik RENALDI, LUKY; HADIYOSO, SUGONDO; RAMADAN, DADAN NUR
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 6, No 3 (2018): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v6i3.317

ABSTRAKDeteksi keberadaan objek secara otomatis pada ruangan diperlukan ketika terdapat keterbatasan dalam melakukan penginderaan. Pemanfaatan sistem radar menjadi saah satu solusi untuk penginderaan objek. Pada paper ini, diimplementasikan prototipe radar menggunakan sensor ultrasonik, mikrokontroller Arduino UNO R3 dan motor servo. Sistem ini dirancang dengan tiga buah sensor ultrasonik dengan motor sebagai penggerak horizontal dan vertikal dalam sistem pemindainya. Sensor yang berjumlah tiga buah, diletakkan pada titik yang berbeda sehingga dapat membaca jarak, sudut dan ketinggian objek dari arah titik tersebut, hasil dari pengukuran objek ditampilkan pada PC melalui aplikasi pemograman GUI. Dari hasil pengujian, radar mampu mendeteksi objek antara 5 cm dari depan radar dengan jarak maksimum 30 cm dan diperoleh tingkat kesalahan pengukuran jarak dan ketinggian sebesar 1 - 2 cm sedangkan untuk sudut 1˚- 3˚.Kata kunci: Deteksi, Radar, Ultrasonik, Jarak, SudutABSTRACTAutomatic detection of objects in the room is required when there are limitations in the sensing. Utilization of radar system becomes one solution for sensing object. In this paper, we implemented a prototype radar using ultrasonic sensor, Arduino UNO R3 microcontroller and servo motor. The system is designed with three ultrasonic sensors with motors as horizontal and vertical drive in the scanning system. Three sensors are placed at different points so that they can read the distance, angle and height of the object from that point, the result of measuring the object displayed on the PC through the GUI programming application. From the test results, the radar is able to detect objects between 5 cm from the front of the radar with a maximum distance of 30 cm and obtained the error rate measurement of distance and altitude of 1 - 2 cm while for the angle of 1˚ - 3˚.Keywords: Detection, Radar, Ultrasonic, Distance, Angle

Analisis Perbandingan KNN dengan SVM untuk Klasifikasi Penyakit Diabetes Retinopati berdasarkan Citra Eksudat dan Mikroaneurisma AULIA, SUCI; HADIYOSO, SUGONDO; RAMADAN, DADAN NUR
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 3, No 1 (2015): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v3i1.75

ABSTRAKPenelitian mengenai pengklasifikasian tingkat keparahan penyakit Diabetes Retinopati berbasis image processing masih hangat dibicarakan, citra yang biasa digunakan untuk mendeteksi jenis penyakit ini adalah citra optik disk, mikroaneurisma, eksudat, dan hemorrhages yang berasal dari citra fundus. Pada penelitian ini telah dilakukan perbandingan algoritma SVM dengan KNN untuk klasifikasi penyakit diabetes retinopati (mild, moderate, severe) berdasarkan citra eksudat dan microaneurisma. Untuk proses ekstraksi ciri digunakan metode wavelet pada masing-masing kedua metode tersebut. Pada penelitian ini digunakan 160 data uji, masing-masing 40 citra untuk kelas normal, kelas mild, kelas moderate, kelas saviere. Tingkat akurasi yang diperoleh dengan menggunakan metode KNN lebih tinggi dibandingkan SVM, yaitu 65 % dan 62%. Klasifikasi dengan algoritma KNN diperoleh hasil terbaik dengan parameter K=9 cityblock. Sedangkan klasifikasi dengan metode SVM diperoleh hasil terbaik dengan parameter One Agains All.Kata kunci: Diabetic Retinopathy, KNN , SVM, Wavelet. ABSTRACT Research based on severity classification of the disease diabetic retinopathy by using image processing method is still hotly debated, the image is used to detect the type of this disease is an optical image of the disk, microaneurysm, exudates, and bleeding of the image of the fundus. This study was performed to compare SVM method with KNN method for classification of diabetic retinopathy disease (mild, moderate, severe) based on exudate and microaneurysm image. For feature extraction uses wavelet method, and each of the two methods. This study made use of 160 test data, each of 40 images for normal class, mild class, moderate class, severe class. The accuracy obtained by KNN higher than SVM, with 65% and 62%. KNN classification method achieved the best results with the parameters K = 9, cityblock. While the classification with SVM method obtained the best results with parameters One agains all .Keywords: Diabetic Retinopathy, KNN, SVM, Wavelet.

Smart parking management system using SSGA MQTT and real-time database Putri Sandika Juwita; Radya Fadhil; Tri Nopiani Damayanti; Dadan Nur Ramadan
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 3: June 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i3.14869

Smart parking system as a part of smart city development has been widely proposed with several research. In this research, proposed a system of parking management application that functions to monitor and control the location of parking slot that can be used by the parking management and parking users. The web application connected to ultrasonic sensor and GPS using MQTT protocol and real-time database. The research used modify algorithm of the SSGA, to optimize the allocation of empty parking slot and MQTT protocol to obtain the faster response time of the system when many users are accessing the website application. The results obtain a variation of sending delays from the client publish to firebase at 4 seconds. Meanwhile, for the sending delay from the broker to firebase the variation was at 2 seconds for each time of data sending.

IoT: smart garbage monitoring using android and real time database Riyan Hadi Putra; Feri Teja Kusuma; Tri Nopiani Damayanti; Dadan Nur Ramadan
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 3: June 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i3.10121

Every single day, garbage is always produced and sometimes, due to the unbalance between high volume produced and the garbage volume transported to the landfill; it then leads to the buildup. To prevent any negative impact on environment, a system is needed to support the waste management process. Smart Garbage Monitoring System consists of two parts: portable garbage can and monitoring application using android smartphone. The use of ultrasonic sensor, GPS and GSM Module on the garbage can aims to provide the data on the garbage and send it to the real time database, in which the data will be processed by the monitoring application on smartphone to determine the time of garbage transport purposely to prevent any buildup. The system doesn't need a server to process, because the entire process of will be run by android application on a smartphone. Test results showed the capability of the system in monitoring the garbage can with the minimum distance between the wastes by three meters. The information on the height level of garbage can be synchronized in real time to smartphone, with an average delay on the EDGE network of 4.57 seconds, HSPA+ of 4.52 seconds and LTE of 3.85 seconds.

Implementation of electronic stethoscope for online remote monitoring with mobile application Sugondo Hadiyoso; Dieny Rofiatul Mardiyah; Dadan Nur Ramadan; Asril Ibrahim
Bulletin of Electrical Engineering and Informatics Vol 9, No 4: August 2020
Publisher : Institute of Advanced Engineering and Science

The stethoscope is a piece of medical standard equipment that isused by a physician for an initial examination of the patient. Generally, the stethoscopeis used for auscultating sounds which are generated by the workings of organ systems such as cardiac, lung or digestive. In the present condition with the growing number of the patient population, it has an impact on the burden of hospitals and medical practitioners. So that treatment is not optimal, especially patients who need continuous monitoring. Thus it needs a system that can work dynamically, flexibly and remotely based. This paper focuses on the implementation of the electronic stethoscope which is integrated with a mobile phone as the modality of online data transmission through the internet network. The prototype of an electronic stethoscope uses condenser mic, pre-amplifier, wide bandpass filter (20 Hz-1 KHz) and audio amplifier. The maximum gain is 28.63 dB in the 20 Hz-690 Hz frequency range. The signal output can be connected to the android mobile through the jacked phone to be stored in MP3 format and then sent to the cloud server for further monitoring and analysis. The application called “Steder” supports realtime communication between patient and physician for medical check-up, consultation, and discussion activities.

Sistem Monitoring Ketersediaan Air pada Perangkat Cuci Tangan Portable berbasis IoT DADAN NUR RAMADAN; SUGONDO HADIYOSO; INDRARINI DYAH IRAWATI
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 9, No 2 (2021): ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektro
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v9i2.455

ABSTRAKPada studi ini diimplementasikan sebuah sistem untuk memantau ketinggian air di dalam drum secara online real-time menggunakan platform Internet of Things (IoT). Sistem ini terdiri dari sensor ultrasonik untuk estimasi ketinggian air, kemudian data tersebut dikirim ke firebase cloud database, untuk diakses oleh perangkat monitoring atau mengakses halaman website. Level air yang tersisa direpresentasikan dalam nilai persen (%). Rata-rata kesalahan pembacaan sensor adalah tidak lebih dari 2%. Delay pengiriman yang digenerate adalah 39,06 ms, sesuai dengan rekomendasi ITU-T untuk komunikasi real-time. Sistem informasi web dapat menampilkan data ketinggian air dalam bentuk numerik dan grafik. Sistem ini telah diterapkan di sekolah menengah pertama Al-Azhar kota Bandung dan diharapkan dapat diperluas penerapannya.Kata kunci: drum, ketinggian air, real-time, IoT ABSTRACTIn this study, a real-time online monitoring of the water level in the drum was implemented using the internet of things (IoT) platform. This system consists of ultrasonic sensors to estimate the water level, then the data is sent to the Firebase cloud database, to be accessed by monitoring devices or accessing a website page. Water level is represented as a percent (%). The average sensor reading error is not more than 2%. The generated delivery delay is 39.06 ms, according to ITU-T recommendations for real-time communication. The web information system can display water level data in numerical and graphic form. This system has been implemented in Al-Azhar junior high school in Bandung and it is hoped that its application can be expanded.Keywords: drums, water level, real-time, IoT

Sistem Pemantauan dan Pendeteksi Kebakaran berbasis Logika Fuzzy dan Real-time Database EVA AISAH HW; ROHMAT TULLOH; SUGONDO HADIYOSO; DADAN NUR RAMADAN
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 9, No 3 (2021): ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektro
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v9i3.577

ABSTRAKKebakaran rumah seringkali disebabkan oleh kelalaian manusia. Oleh karena itu diperlukan sebuah sistem yang dapat mendeteksi kebakaran secara online realtime. Pada studi ini, dirancang dan diimplementasikan sebuah sistem pendeteksi kebakaran dengan sejumlah sensor untuk mengukur beberapa parameter lingkungan. Sistem ini dilengkapi dengan pengambil keputusan menggunakan metode fuzzy logic. Parameter lingkungan yang diukur mencakup suhu ruangan, asap dan api yang kemudian dapat dimonitor secara real-time melalui web interface menggunakan Internet of Things platform. Pengujian menunjukkan bahwa detektor dapat mendeteksi api dengan jarak hingga 100 cm dengan akurasi mencapai 100%. Pengujian sensor suhu menunjukkan akurasi 98.79%, sementara itu detektor asap memperoleh akurasi 77.81%. Sistem ini mampu mengirimkan data dengan rata-rata delay transmisi 0.62 detik. Sistem usulan ini diharapkan dapat menyediakan pemantauan kondisi suatu ruangan secara real-time.Kata kunci: Kebakaran, Real-Time, Deteksi, Fuzzy, Internet Of Things ABSTRACTHouse fires are often caused by human error. Therefore, we need a system that can detect fires online real-time. In this study, a fire detection system with a number of sensors is designed and implemented to measure several environmental parameters. This system is equipped with a decision maker using the fuzzy logic method. The environmental parameters measured include room temperature, smoke and fire which can then be monitored in real time via a web interface using the Internet of Things platform. Tests show that the detector can detect fires with a distance of up to 100 cm with an accuracy of up to 100%. The temperature sensor test shows an accuracy of 98.79%, while the smoke detector generates an accuracy of 77.81%. This system is capable of sending data with an average transmission delay of 0.62 seconds. This proposed system is expected to provide realtime monitoring of the condition of a room.Keywords: Fire, Real-time, detection, Fuzzy, internet of things

Analisis Perbandingan KNN dengan SVM untuk Klasifikasi Penyakit Diabetes Retinopati berdasarkan Citra Eksudat dan Mikroaneurisma SUCI AULIA; SUGONDO HADIYOSO; DADAN NUR RAMADAN
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 3, No 1 (2015): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v3i1.75

ABSTRAKPenelitian mengenai pengklasifikasian tingkat keparahan penyakit Diabetes Retinopati berbasis image processing masih hangat dibicarakan, citra yang biasa digunakan untuk mendeteksi jenis penyakit ini adalah citra optik disk, mikroaneurisma, eksudat, dan hemorrhages yang berasal dari citra fundus. Pada penelitian ini telah dilakukan perbandingan algoritma SVM dengan KNN untuk klasifikasi penyakit diabetes retinopati (mild, moderate, severe) berdasarkan citra eksudat dan microaneurisma. Untuk proses ekstraksi ciri digunakan metode wavelet pada masing-masing kedua metode tersebut. Pada penelitian ini digunakan 160 data uji, masing-masing 40 citra untuk kelas normal, kelas mild, kelas moderate, kelas saviere. Tingkat akurasi yang diperoleh dengan menggunakan metode KNN lebih tinggi dibandingkan SVM, yaitu 65 % dan 62%. Klasifikasi dengan algoritma KNN diperoleh hasil terbaik dengan parameter K=9 cityblock. Sedangkan klasifikasi dengan metode SVM diperoleh hasil terbaik dengan parameter One Agains All.Kata kunci: Diabetic Retinopathy, KNN , SVM, Wavelet. ABSTRACT Research based on severity classification of the disease diabetic retinopathy by using image processing method is still hotly debated, the image is used to detect the type of this disease is an optical image of the disk, microaneurysm, exudates, and bleeding of the image of the fundus. This study was performed to compare SVM method with KNN method for classification of diabetic retinopathy disease (mild, moderate, severe) based on exudate and microaneurysm image. For feature extraction uses wavelet method, and each of the two methods. This study made use of 160 test data, each of 40 images for normal class, mild class, moderate class, severe class. The accuracy obtained by KNN higher than SVM, with 65% and 62%. KNN classification method achieved the best results with the parameters K = 9, cityblock. While the classification with SVM method obtained the best results with parameters One agains all .Keywords: Diabetic Retinopathy, KNN, SVM, Wavelet.

Purwarupa Radar sebagai Pendeteksi Benda Diam menggunakan Ultrasonik LUKY RENALDI; SUGONDO HADIYOSO; DADAN NUR RAMADAN
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 6, No 3 (2018): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v6i3.317

ABSTRAKDeteksi keberadaan objek secara otomatis pada ruangan diperlukan ketika terdapat keterbatasan dalam melakukan penginderaan. Pemanfaatan sistem radar menjadi saah satu solusi untuk penginderaan objek. Pada paper ini, diimplementasikan prototipe radar menggunakan sensor ultrasonik, mikrokontroller Arduino UNO R3 dan motor servo. Sistem ini dirancang dengan tiga buah sensor ultrasonik dengan motor sebagai penggerak horizontal dan vertikal dalam sistem pemindainya. Sensor yang berjumlah tiga buah, diletakkan pada titik yang berbeda sehingga dapat membaca jarak, sudut dan ketinggian objek dari arah titik tersebut, hasil dari pengukuran objek ditampilkan pada PC melalui aplikasi pemograman GUI. Dari hasil pengujian, radar mampu mendeteksi objek antara 5 cm dari depan radar dengan jarak maksimum 30 cm dan diperoleh tingkat kesalahan pengukuran jarak dan ketinggian sebesar 1 - 2 cm sedangkan untuk sudut 1˚- 3˚.Kata kunci: Deteksi, Radar, Ultrasonik, Jarak, SudutABSTRACTAutomatic detection of objects in the room is required when there are limitations in the sensing. Utilization of radar system becomes one solution for sensing object. In this paper, we implemented a prototype radar using ultrasonic sensor, Arduino UNO R3 microcontroller and servo motor. The system is designed with three ultrasonic sensors with motors as horizontal and vertical drive in the scanning system. Three sensors are placed at different points so that they can read the distance, angle and height of the object from that point, the result of measuring the object displayed on the PC through the GUI programming application. From the test results, the radar is able to detect objects between 5 cm from the front of the radar with a maximum distance of 30 cm and obtained the error rate measurement of distance and altitude of 1 - 2 cm while for the angle of 1˚ - 3˚.Keywords: Detection, Radar, Ultrasonic, Distance, Angle

Title

Found 42 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 42 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 42 Documents
Search