Claim Missing Document
Check
Articles

Found 13 Documents
Search

Hand Gesture Recognition Sebagai Pengganti Mouse Komputer Menggunakan Kamera Yunita, Helda; Setyati, Endang
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol 3 No 2 (2019)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (985.475 KB) | DOI: 10.31961/eltikom.v3i2.114

Abstract

Akhir-akhir ini perkembangan teknologi semakin pesat, metode interaksi dan komunikasi antara pengguna dengan komputer adalah salah satu tuntutan perkembangan teknologi. Berbagai macam pembaharuan teknologi mengusahakan untuk meminimalisir berbagai macam perangkat menjadi satu agar lebih mudah digunakan. User lebih membutuhkan peralatan komunikasi yang bersifat alami karena tidak membutuhkan kontak langsung dengan peralatan input. Misalnya dengan gerakan dari tubuh manusia didepan kamera komputer sudah bisa menginterpretasikan. Untuk mengatasi masalah tersebut maka dilakukan suatu penelitian tentang deteksi isyarat tangan. Inputan berupa isyarat dan gerakan tangan didepan kamera dapat memberikan aksi pergerakan pada mouse yang diistilahkan dengan kamera mouse. Metode yang digunakan adalah convexhull algorithm. Melalui convexhull algorithm bisa didapatkan jumlah jari tangan yang kemudian dapat dijadikan acuan dalam pengerjaan aksi mouse. Sebenarnya sudah banyak penelitian tentang camera mouse, tetapi implementasinya masih banyak yang bergantung dengan peralatan tambahan. Penelitian ini mengembangkan penelitian yang sudah ada, yaitu hand gesture recognition dengan implemen-tasi pergerakan mouse dari video secara realtime. Dengan hand gesture recognition dan menggunakan metode convexhull algorithm pengenalan tangan akan lebih mudah hanya dengan menggunakan kamera, hanya dengan hitungan detik aksi mouse pada komputer dapat berjalan dengan baik yaitu dengan tingkat akurasi sebesar 68 % dari 75 kali percobaan
Pneumonia Classification of Thorax Images using Convolutional Neural Networks Suyuti, Mahmud; Setyati, Endang
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi Vol 5, No 2 (2020)
Publisher : Universitas Dr. Soetomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25139/inform.v0i1.2707

Abstract

The digital image processing technique is a product of computing technology development. Medical image data processing based on a computer is a product of computing technology development that can help a doctor to diagnose and observe a patient. This study aimed to perform classification on the image of the thorax by using Convolutional Neural Network (CNN).  The data used in this study is lung thorax images that have previously been diagnosed by a doctor with two classes, namely normal and pneumonia. The amount of data is 2.200, 1.760 for training, and 440 for testing. Three stages are used in image processing, namely scaling, gray scaling, and scratching. This study used Convolutional Neural Network (CNN) method with architecture ResNet-50. In the field of object recognition, CNN is the best method because it has the advantage of being able to find its features of the object image by conducting the convolution process during training. CNN has several models or architectures; one of them is ResNet-50 or Residual Network. The selection of ResNet-50 architecture in this study aimed to reduce the loss of gradients at certain network-level depths during training because the object is a chest image of X-Ray that has a high level of visual similarity between some pathology. Moreover, several visual factors also affect the image so that to produce good accuracy requires a certain level of depth on the CNN network. Optimization during training used Adaptive Momentum (Adam) because it had a bias correction technique that provided better approximations to improve accuracy. The results of this study indicated the thorax image classification with an accuracy of 97.73%.
Extraction of Eye and Mouth Features for Drowsiness Face Detection Using Neural Network Fitrianingsih, Elis; Setyati, Endang; Zaman, Luqman
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 2, May-2018
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (626.909 KB) | DOI: 10.22219/kinetik.v3i2.589

Abstract

Facial feature extraction is the process of searching for features of facial components such as eyes, nose, mouth and other parts of human facial features. Facial feature extraction is essential for initializing processing techniques such as face tracking, facial expression recognition or face shape recognition. Among all facial features, eye area detection is important because of the detection and localization of the eye. The location of all other facial features can be identified. This study describes automated algorithms for feature extraction of eyes and mouth. The data takes form of video, then converted into a sequence of images through frame extraction process. From the sequence of images, feature extraction is based on the morphology of the eyes and mouth using Neural Network Backpropagation method. After feature extraction of the eye and mouth is completed, the result of the feature extraction will later be used to detect a person’s drowsiness, being useful for other research.
Klasifikasi Topeng Pandawa dengan SVM Sanjaya, Andi; Setyati, Endang; Budianto, Herman
INTEGER: Journal of Information Technology Vol 5, No 1: April 2020
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (236.222 KB) | DOI: 10.31284/j.integer.2020.v5i1.910

Abstract

Klasifikasi merupakan tahapan tingkat lanjut dari sebuah keilmuan computer vision. Karena tujuan dari sebuah aplikasi rekognisi yaitu mengenali. Cara mengenali yaitu dengan cara klasifikasi. Banyak metode klasifikasi yang ada, namun pada penelitian ini menggunakan Support Vector Machine (SVM). SVM dipilih karena bisa mengatasi data dengan dimensi yang sangat besar tanpa mereduksi data, bekerja dengan data linier atau nonlinier dan membuat sebuah hyperplane yang memisahkan data antar kelas. Pada penelitian ini menggunakan data patung pandawa dengan lima kelas. Lima kelas terdiri dari kelas yudhistira, bima, arjuna, nakula dan sadewa. Kernel yang digunakan pada penelitian ini menggunakan  Radial Basis Function (RBF). Hasil ujicoba pada penelitian mempunya rata-rata akurasi sebesar 0,848.
Desain dan implementasi Wireless Sensor Network menggunakan LoRa untuk pemantauan tingkat pencemaran udara di Kota Surabaya Arafat, Yasir; Setyati, Endang
TEKNOLOGI: Jurnal Ilmiah Sistem Informasi Vol 10, No 2 (2020): July
Publisher : Universitas Pesantren Tinggi Darul 'Ulum (Unipdu) Jombang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/teknologi.v10i2.2070

Abstract

Pencemaran udara merupakan hal yang tidak dapat dihindarkan pada setiap daerah. Sumber pencemaran udara tersebut bermacam-macam, seperti gas kendaraan bermotor, limbah pabrik, dan sampah yang dibuang sembarangan. Penelitian ini mengusulkan pembuatan sebuah sistem pemantauan kualitas udara di kota Surabaya. Zat pencemar yang menjadi tolak ukur untuk menentukan tingkat pencemaran udara dalam penelitian ini adalah CO (Carbon monoxide), SO2 (Sulfur dioxide), O3 (Ozone), dan NO2 (Nitrogen dioxide). Sensor yang digunakan untuk mengetahui kadar zat pencemar tersebut adalah MQ-7 dan MQ-135. Penelitian ini memanfaatkan wireless sensor network (WSN) dan teknologi LoRa sebagai media pengiriman data. Empat titik pengujian dan dua papan ISPU (Indeks Standar Pencemar Udara) sebagai ground truth digunakan untuk mengetahui tingkat pencemaran udara di kota surabaya. Pengukuran dan perbandingan antara sensor dengan ground truth dilakukakan untuk mengetahui hasil penelitian ini. Hasil pemantauan tingkat pencemaran udara didapatkan dengan menggunakan sensor MQ-7 dan MQ-135 yang mampu membaca keadaan zat pencemar dengan tingkat error paling besar 5,77%. Sistem pengiriman data menggunakan teknologi LoRa pada jarak terjauh 2,97 km dapat mengirimkan data dengan baik dengan RSSI (Received Signal Strength Indication) -92 dBm pada ketinggian 12 mdpl dan frekuensi 433 Mhz. Data hasil pemantauan tersebut dapat dipantau melalui aplikasi ThingSpeak secara online. Everywhere, air pollution isn't avoidable. The source of pollution could be anything, such as gas emitted from vehicles, toxic waste, and garbages that are thrown not to their places. In this study, a system to monitor air quality will be built in Surabaya. The pollutants that will be the benchmark to measure the level of air pollution are CO (Carbon Dioxide), SO2 (Sulfur Dioxide), O3 (ozone), and NO2 (Nitrogen Dioxide). The sensor that will be used to detect the level of pollutants is called MQ-7 and MQ-135. This study takes Wireless Sensor Network (WSN) into use while LoRa technology is being used as a media to send data. To know the level of pollution in Surabaya, 4 test points are taken, and AQI (Air Pollution Index) are used as ground truth. After measuring and comparing the sensor and ground truth, the result that is taken using MQ-7 sensor and MQ-135 could read the status of pollutants with 5.77% as its highest sensor range. After that, the system that is sending the data using LoRa technology with 2.97 km as its highest distance could send the data well with RSSI -92dBm in 12m MSL height and 433 Mhz frequency. The result of this monitoring could be seen through thingspeak application online.
Desain dan implementasi wireless sensor network (WSN) menggunakan LoRa untuk pemantauan tingkat pencemaran udara di kota Surabaya Arafat, Yasir; Setyati, Endang
Teknologi: Jurnal Ilmiah Sistem Informasi 2020: Articles in press
Publisher : Universitas Pesantren Tinggi Darul 'Ulum (Unipdu) Jombang

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

Abstract

Pencemaran udara merupakan hal yang tidak dapat dihindarkan pada setiap daerah. Sumber pencemaran udara tersebut bermacam-macam, seperti gas kendaraan bermotor, limbah pabrik, dan sampah yang dibuang sembarangan. Penelitian ini mengusulkan pembuatan sebuah sistem pemantauan kualitas udara di kota Surabaya. Zat pencemar yang menjadi tolak ukur untuk menentukan tingkat pencemaran udara dalam penelitian ini adalah CO (Carbon monoxide), SO2 (Sulfur dioxide), O3 (Ozone), dan NO2 (Nitrogen dioxide). Sensor yang digunakan untuk mengetahui kadar zat pencemar tersebut adalah MQ-7 dan MQ-135. Penelitian ini memanfaatkan wireless sensor network (WSN) dan teknologi LoRa sebagai media pengiriman data. Empat titik pengujian dan dua papan ISPU (Indeks Standar Pencemar Udara) sebagai ground truth digunakan untuk mengetahui tingkat pencemaran udara di kota surabaya. Pengukuran dan perbandingan antara sensor dengan ground truth dilakukakan untuk mengetahui hasil penelitian ini. Hasil pemantauan tingkat pencemaran udara didapatkan dengan menggunakan sensor MQ-7 dan MQ-135 yang mampu membaca keadaan zat pencemar dengan tingkat error paling besar 5,77%. Sistem pengiriman data menggunakan teknologi LoRa pada jarak terjauh 2,97 km dapat mengirimkan data dengan baik dengan RSSI (Received Signal Strength Indication) -92 dBm pada ketinggian 12 mdpl dan frekuensi 433 Mhz. Data hasil pemantauan tersebut dapat dipantau melalui aplikasi ThingSpeak secara online. Everywhere, air pollution isn't avoidable. The source of pollution could be anything, such as gas emitted from vehicles, toxic waste, and garbages that are thrown not to their places. In this study, a system to monitor air quality will be built in Surabaya. The pollutants that will be the benchmark to measure the level of air pollution are CO (Carbon Dioxide), SO2 (Sulfur Dioxide), O3 (ozone), and NO2 (Nitrogen Dioxide). The sensor that will be used to detect the level of pollutants is called MQ-7 and MQ-135. This study takes Wireless Sensor Network (WSN) into use while LoRa technology is being used as a media to send data. To know the level of pollution in Surabaya, 4 test points are taken, and AQI (Air Pollution Index) are used as ground truth. After measuring and comparing the sensor and ground truth, the result that is taken using MQ-7 sensor and MQ-135 could read the status of pollutants with 5.77% as its highest sensor range. After that, the system that is sending the data using LoRa technology with 2.97 km as its highest distance could send the data well with RSSI -92dBm in 12m MSL height and 433 Mhz frequency. The result of this monitoring could be seen through thingspeak application online.
Model Architecture of CNN for Recognition the Pandava Mask Sanjaya, Andi; Setyati, Endang; Budianto, Herman
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi Vol 5, No 2 (2020)
Publisher : Universitas Dr. Soetomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25139/inform.v0i1.2740

Abstract

This research was conducted to observe the use of architectural model Convolutional Neural Networks (CNN) LeNEt, which was suitable to use for Pandava mask objects. The Data processing in the research was 200 data for each class or similar with 1000 trial data. Architectural model CNN LeNET used input layer 32x32, 64x64, 128x128, 224x224 and 256x256. The trial result with the input layer 32x32 succeeded, showing a faster time compared to the other layer. The result of accuracy value and validation was not under fitted or overfit. However, when the activation of the second dense process as changed from the relu to sigmoid, the result was better in sigmoid, in the tem of time, and the possibility of overfitting was less. The research result had a mean accuracy value of 0.96.
DROWSY DETECTION FROM VIDEO DRIVER FACE BASED ON EYE AND MOUTH FEATURES EXTRACTION USING THE CONVOLUTION NEURAL NETWORK METHOD Solikin, Akhmad; Setyati, Endang
BEST Vol 2 No 1 (2020): BEST
Publisher : Program Studi Teknik Elektro Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/best.vol2.no1.2584

Abstract

This research was conducted in an effort to minimize the occurrence of road traffic accidents. In this study detected the level of fatigue and sleepiness from the driver's face video based on the extraction of eye and mouth features using the CNN method. The dataset in this study is 300 data with 3 different classes namely drowsiness 100 data, sleepy 100 data and normal 100 data. The number of epochs used in research to achieve high accuracy is as much as 50. In the test results it is known that the validation of accuracy has increased in each of the input layer results.
MODEL CNN LENET DALAM PENGENALAN JENIS GOLONGAN KENDARAAN PADA JALAN TOL Pramana, Anggay Luri; Setyati, Endang; Kristian, Yosi
Jurnal Teknika Vol 12, No 2 (2020): Bersinergi untuk kemajuan dan perkembangan teknologi bangsa indonesia
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30736/jt.v13i2.469

Abstract

Research in the field of transportation, especially vehicle classification with various methods, is a widely developed field of study. Vehicles can be categorized by shape, dimension, logo, and  type. The vehicle dataset is also not difficult to find because it is general in nature. Based on the research that has been done, the introduction of group types based on the number of axles with CNN, the dataset is not yet available to the public. In this paper, we discuss the introduction of the types of groups using the Convolutional Neural Network method. The architecture used is the LeNet model. The trial scenario is carried out in 4 stages, namely 25 epochs, 50 epochs, 75 epochs and 100 epochs. Based on the test results, the accuracy obtained continues to increase at 50 epochs and 100 epochs iterations. Starting from an accuracy of 82%, 94% to the highest accuracy of 95%. Likewise in the prediction the data has increased from 80%, 85% to the highest accuracy that can be 86%. From 50 epochs to 75 epochs, the accuracy of both training and testing has decreased.
Utilization Of Augmented Reality In Automotive Subjects For Basic Competencies Of Four-Wheeled Vehicle Brake Systems Farkhan, Muhammad; Setyati, Endang; Haryanti Chandra, Francisca
BEST Vol 3 No 2 (2021): BEST
Publisher : Program Studi Teknik Elektro Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/best.vol3.no2.4243

Abstract

In automotive learning, teachers generally use books and teaching aids as learning media. Automotive learning outcomes show the low value of learning outcomes. Thus a learning media is needed that can help improve learning outcomes. One way to overcome this problem is to use learning media that utilize augmented reality technology. In this study, a learning media using augmented reality technology based on android was developed to simulate the brake system on four-wheeled vehicles in 3 dimensions. The Augmented Reality work system used is marker based tracking, and uses 3D Max software and the Vuforia plug-in. In terms of pedagogy, this learning system uses the Modality Principle. Participants are class XI students of SMK YPM 4 Taman. This research uses experimental research. The students involved were 44 students divided into 2 groups, with each group consisting of 22 students. Both groups received a pre-test and a post-test. The experimental group was given treatment with Augmented Reality-based learning media, while the control group did not use conventional learning media. After making comparisons, the results show less than optimal due to the pandemic period. The results showed that the pre-test result between the control group and the experimental group was 49.32, and the post-test result for the control group was 62.73, while for the experimental group it was 73.18. So that from the difference in the difference in post-test scores between the experimental group and the control group shows that the treatment factor by providing Augmented Reality-based learning media in the experimental group has an influence. From observations and interviews, students were more active in learning activities and students were eager to take part in learning. This proves that students are interested in this media which can generate motivation to learn.