Garuda - Garba Rujukan Digital

Identifikasi Kadar Semen dan Pasir pada Campuran Kering Menggunakan Metode Backpropagation Gasim, Gasim; Sudiadi, Sudiadi
Khazanah Informatika Vol. 5 No. 1 Juni 2019
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v5i1.8014

Campuran perekat dan juga plesteran dinding pada bangunan biasanya terdiri dari semen dan pasir. Perbedaan kadar capuran semen dan pasir berdampak pada kekuatan hasil. Penelitian ini mengimplementasikan kecerdasan buatan untuk mengidentifikasi atau mengenali kadar campuran semen dan pasir melalui citra campuran semen dan pasir yang sudah kering. Penelitian ini menggunakan enam macam campuran semen dan pasir. Pengumpulan data citra dilakukan dengan cara pemotretan menggunakan kamera resolusi sensor sebesar 7 MP, jarak potret lebih kurang 8 cm, dilakukan pada siang hari, dan tidak menggunakan cahaya dari lampu kamera. Citra latih dan citra uji berukuran 500 x 500 piksel, dan banyaknya citra latih adalah 300 citra dan 150 citra sebagai data uji. Metode pengenalan menggunakan jaringan syaraf tiruan dengan algoritma propagasi balik (backpropagation) dan dengan input berupa nilai tekstur dari citra campuran semen dan pasir yang sudah kering. Tingkat akurasi keberhasilan identifikasi adalah 87.33%. Penelitian ini berhasil mengimplementasikan JST dan fitur tekstur analisis dari GLCM dengan jarak potret dan resolusi kamera tertentu, serta penelitian ini dapat menjadi referensi pada penelitian lanjutan.

Identifikasi Kadar Semen dan Pasir pada Campuran Kering Menggunakan Metode Backpropagation Gasim Gasim; Sudiadi Sudiadi
Khazanah Informatika Vol. 5 No. 1 June 2019
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v5i1.8014

Campuran perekat dan juga plesteran dinding pada bangunan biasanya terdiri dari semen dan pasir. Perbedaan kadar capuran semen dan pasir berdampak pada kekuatan hasil. Penelitian ini mengimplementasikan kecerdasan buatan untuk mengidentifikasi atau mengenali kadar campuran semen dan pasir melalui citra campuran semen dan pasir yang sudah kering. Penelitian ini menggunakan enam macam campuran semen dan pasir. Pengumpulan data citra dilakukan dengan cara pemotretan menggunakan kamera resolusi sensor sebesar 7 MP, jarak potret lebih kurang 8 cm, dilakukan pada siang hari, dan tidak menggunakan cahaya dari lampu kamera. Citra latih dan citra uji berukuran 500 x 500 piksel, dan banyaknya citra latih adalah 300 citra dan 150 citra sebagai data uji. Metode pengenalan menggunakan jaringan syaraf tiruan dengan algoritma propagasi balik (backpropagation) dan dengan input berupa nilai tekstur dari citra campuran semen dan pasir yang sudah kering. Tingkat akurasi keberhasilan identifikasi adalah 87.33%. Penelitian ini berhasil mengimplementasikan JST dan fitur tekstur analisis dari GLCM dengan jarak potret dan resolusi kamera tertentu, serta penelitian ini dapat menjadi referensi pada penelitian lanjutan.

Identifikasi Kadar Semen dan Pasir Melalui Citra Permukaan Menggunakan Teknik Blok Citra Gasim Gasim
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 7 No 2 (2020): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v7i2.371

This research raises the topic of identifying the types of cement and sand mixtures on dry material using artificial intelligence. This is done because the comparison of the mixture between cement and sand is very influential on the quality of the material produced. Several experimental models affect the level of recognition accuracy. In this study the experimental model used was the image block and LBP image techniques, with a mixture of cement and sand used was 1: 1, 1: 1.5, 1: 2, 1: 2.5, 1: 3, and 1: 3.5. The recognition method used is Artificial Neural Network (ANN) with back propagation algorithm. The number of ANN training samples is 600 samples, and 120 samples for testing. This research uses image block technique before feature extraction is carried out. The features used are the mean, standard deviation, entropy, skewness, and kurtosis of LBP images. ANN training results get a three-layer hidden architecture, with testing showing an accuracy rate of 80% recognition.

Perbandingan Akurasi Pengenalan Jenis Beras dengan Algoritma Propagasi Balik pada Beberapa Resolusi Kamera David Ricardo; Gasim gasim
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 3 No 2 (2019): Agustus 2019
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Rice is a staple that is cooked so that it becomes rice for daily consumption. The type of rice that is often used for daily consumption is white rice. There are several types of white rice circulating in the market that are consumed by the public. Each type of rice gives different scent, taste and price. This study compares the accuracy of white rice type recognition based on several camera resolutions. The types of rice used in this study are Jawa Barat rice, Jawa Timur rice, Pandan Wangi rice, Thailand rice and Vietnam rice. The camera resolution used is 5MP, 8 MP, 12 MP, 14 MP, and 16MP. The shooting distance used is ± 9 cm between the camera and the object of rice. The recognition method used is BackPropagation Artificial Neural Networks, while for feature extraction using the Gray Level Co-occurrence Matrix (GLCM) which consists of contrast, energy, homogeneity, and correlation. The highest results obtained at 12 MP camera resolution with the results of the recognition of 25 of 50 test data and the results of the calculation with confusion matrix obtained an average accuracy of 82%, precision of 55%, and recall of 50%. The results of this study can be used as a reference for research that uses objects of similar character, or further research with the same object in developing applications that are ready to use.

PERBANDINGAN JARAK POTRET DAN RESOLUSI KAMERA PADA TINGKAT AKURASI PENGENALAN ANGKA KWH METERMENGGUNAKAN SVM Dini Amputri; Siti Nadra; Gasim Gasim; M. Ezar Al Rivan
Jurnal Informatika Global Vol 8, No 1
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Electricity meter is a tool used to measure the electricity power consumption. Electricity meter has the numeral part known as electricity meter number which load the electricity power consumption.Usually, the recording is done once a month, by recording the number on the electric meter into the book, and then the recording officer take pictures the power meter. Electricity meter number can be analized through an image using the knowledge of pattern recognition in image processing. In analyzing picture of electicity meter number, we used Histogram Of Oriented Gradients (HOG) as the feature extraction and Supply Vector Machine (SVM) as the classification method. The result using 100 train-set and 30 test-set for each combination of category shows that the best resolution is 10 MP and 14 MP and the picture capturing distance is at 30 cm byand 10 cm by 73,33% accuracy for each image and 86,67% for each number and confusion matrix shows that presentation of all number is 75,48%. Key words:Number Recognition, Histogram Of Oriented Gradients (HOG) , Support Vector Machine (SVM)

Identifikasi Jenis Mangga Berdasarkan Bentuk Menggunakan Fitur HOG dan Jaringan Syaraf Tiruan Edgar Utama; Fikario Yapputra; Gasim Gasim
Jurnal Informatika Global Vol 9, No 1
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

AbstractMany searches have been done for object recognition based on shape using artificial intelligence with various feature extraction. also a lot of research has been done for the introduction of fruit types using various features of extraction and various methods of recognition. This research is identification of mango variant based on shape. Mango is one of the popular fruits and is often consumed by the community. Mango has many variants, each variant of mango usually has a different shape. Mango shape, among others, round with its variants and oval with its variants. the shape of mango is one of the differentiator of each type. Mango used is five variants of mango. The training data comprised 16 images for each variant (a total of 80 images for five mango variants). The test data consisted of 4 images for each variant (a total of 20 images for five mango variants). Train data and test data were obtained by photographing using optical camera, 5 MP secsor resolution, 20 cm photo spacing, and with white background. resize the image used size 50 x 50 pixels on the mango object only. This research uses feature from Histogram of Oriented Gradients (HOG) as training input and testing of recognition method. Recognition method using Artificial Neural Network with back propagation algorithm. Accuracy of recognition that can be achieved in this study is 90%.Keywords : Object recognition, Shape, HOG, Artificial Neural Network AbstrakBanyak penelian yang pernah dilakukan untuk objek recognition berdasarkan shape menggunakan kecerdasan buatan dengan berbagai ekstraksi ciri. juga banyak penelitian yang pernah dilakukan untuk pengenalan jenis buah menggunakan berbagai fitur ekstraksi dan berbagai metode recognition. Penelitian ini adalah identifikasi varian mangga berdasarkan shape. Mangga merupakan salah satu buah yang popular dan sering dikonsumsi oleh masyarakat. Mangga memiliki banyak varian, tiap varian dari mangga biasanya memiliki bentuk yang berbeda. Bentuk mangga antara lain bulat dengan variannya dan lonjong dengan variannya. the shape mangga merupakan salah satu pembeda dari masing-masing jenis. Mangga yang digunakan adalah lima varian mangga. Data latih terdiri 16 citra untuk tiap variannya (total 80 citra untuk lima varian mangga). Data uji terdiri dari 4 citra untuk tiap variannya (total 20 citra untuk lima varian mangga). Data latih dan data uji didapatkan dengan cara difoto menggunakan kamera optik, resolusi secsor 5 MP, jarak foto 20 cm, dan dengan latar putih. resize citra yang digunakan berukuran 50 x 50 piksel pada bagian objek mangga saja. Research ini menggunakan feature from Histogram of Oriented Gradients (HOG) sebagai input pelatihan dan pengujian metode recognition. Metode recognition menggunakan Jaringan Saraf Tiruan dengan algoritma propagasi balik. Akurasi pengenalan yang dapat dicapai dalam penelitian ini adalah sebesar 90%.Kata kunci : Pengenalan Objek, bentuk , HOG, Jaringan Saraf Tiruan

PERBANDINGAN TINGKAT AKURASI BENTUK FRAME MENGGUNAKAN TEMPLATE MATCHING PADA PENGENALAN WAJAH Fika Rusilawati; Hardianing Wahyu Kinasih; Gasim Gasim
Jurnal Informatika Global Vol 8, No 2
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Facial recognition research is usually done with a rectangular frame model. previously it is not known whether this model is the best model among other models in face recognition. This research conducted a comparison of face recognition accuracy with elliptical frame model, triangle, rectangle, and pentagon. RGB image is used for facial segmentation, and skin color is used as a feature. using 320 x 240 pixel image, face position is front view, shooting distance about 200 cm, and use one color for background. The method of recognition used is Template Matching. Test results on 40 test images is the highest recognition accuracy level is a rectangular frame that is 97%, and the lowest accuracy is the triangle frame that is equal to 68%.Keywords : Face recognition, Frame, Segmentation, Template Matching

PERBANDINGAN TINGKAT AKURASI JENIS CITRA KEABUAN , HSV, DAN L*a*b* PADA IDENTIFIKASI JENIS BUAH PIR Mulia Octavia; Jesslyn K; Gasim Gasim
Jurnal Informatika Global Vol 7, No 1
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Image processing has been commonly used in automatic object identification. These are some methods that can be used for automatic object identification, such as LVQ, K-NN, SVM, and Neural Network. This research specifically bring out the topic about the level accuracy comparison in identification of pear variety using grayscale, HSV, and L*a*b* images in aim to get the best image type for pear image identification using neural network. The feature are gray level co-occurrence matrix feature (energy, entropy, homogeneity, and contrast) from canny edge detection’s image and also color feature. Based on image examination result, grayscale reached its best accuracy for 90% on MSE 1e-10 with 10 hidden layer neurons, HSV reached its best accuracy for 100% on MSE 1e-5 with 20 hidden layer neurons, L*a*b* reached its best accuracy for 100% on MSE 1e-5 with 15 hidden layer neurons. HSV and L*a*b* give the better accuracy for pear variety image identification than grayscale.Keyword:Image Processing, Pear, Neural Network, Identification, Gray Level Co-occurrence Matrix, Canny, Color.

Identifikasi Kadar Campuran Material pada Beton Keras Melalui Citra Menggunakan Jaringan Saraf Tiruan Propagasi Balik dengan Fitur LBP Gasim Gasim; Rusbandi Rusbandi; Rizani Teguh
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 9 No 4 (2022): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v9i4.3198

Concrete can be found in permanent buildings, such as houses, buildings, bridges. Concrete is usually used for foundations, columns, beams, slabs. Concrete is a mixture of cement, fine aggregate, coarse aggregate and water. One of the determinants of the quality of concrete is the content of the concrete-forming mixture, so it is very important to know it. The problem arises about how to find out the mixture content in hardened concrete. Civil engineering discipline has a way to determine the content of the mixture forming the hardened concrete. However, it is possible to find out the level of this mixture using other disciplines, for example, from the discipline of computer science, in this case, artificial intelligence. Then, the problem is how to identify the mixture content in hardened concrete? This study uses the features of the Local Binary Pattern (LBP) image with the Artificial Neural Network (ANN) recognition method. There are 5 types of mixture used, each of which is represented by 5 samples of each type. Using a 14 MP camera, the shooting distance is approximately 27 cm. There are 1,000 training images from 3 samples of each type with 200 images each, and 500 test images from 2 samples from each type with 100 images each. The overall recognition accuracy rate is 67.6%. Keywords— Identification, Hardened Concrete, Local Binary Pattern, ANN

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search