Claim Missing Document
Check
Articles

Found 24 Documents
Search

Classification of neovascularization using convolutional neural network model Wahyudi Setiawan; Moh. Imam Utoyo; Riries Rulaningtyas
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 1: February 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i1.11604

Abstract

Neovascularization is a new vessel in the retina beside the artery-venous. Neovascularization can appear on the optic disk and the entire surface of the retina. The retina categorized in Proliferative Diabetic Retinopathy (PDR) if it has neovascularization. PDR is a severe Diabetic Retinopathy (DR). An image classification system between normal and neovascularization is here presented. The classification using Convolutional Neural Network (CNN) model and classification method such as Support Vector Machine, k-Nearest Neighbor, Naïve Bayes classifier, Discriminant Analysis, and Decision Tree. By far, there are no data patches of neovascularization for the process of classification. Data consist of normal, New Vessel on the Disc (NVD) and New Vessel Elsewhere (NVE). Images are taken from 2 databases, MESSIDOR and Retina Image Bank. The patches are made from a manual crop on the image that has been marked by experts as neovascularization. The dataset consists of 100 data patches. The test results using three scenarios obtained a classification accuracy of 90%-100% with linear loss cross validation 0%-26.67%. The test performs using a single Graphical Processing Unit (GPU).
An improvement of Gram-negative bacteria identification using convolutional neural network with fine tuning Budi Dwi Satoto; Imam Utoyo; Riries Rulaningtyas; Eko Budi Khoendori
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.v18i3.14890

Abstract

This paper proposes an image processing approach to identify Gram-negative bacteria. Gram-negative bacteria are one of the bacteria that cause lung lobe damage-bacterial samples obtained through smears of the patient's sputum. The first step bacterium should pass the pathogen test process. After that, it bred using Mc Conkey's media. The problem faced is that the process of identifying bacterial objects is still done manually under a fluorescence microscope. The contributions offered from this research are focused on observing bacterial morphology for the operation of selecting shape features. The proposed method is a convolutional neural network with fine-tuning. In the stages of the process, a convolutional neural network of the VGG-16 architecture used dropout, data augmentation, and fine-tuning stages. The main goal of the current research was to determine the method selection is to get a high degree of accuracy. This research uses a total sample of 2520 images from 2 different classes. The amount of data used at each stage of training, testing, and validation is 840 images with dimensions of 256x256 pixels, a resolution of 96 points per inch, and a depth of 24 bits. The accuracy of the results obtained at the training stage is 99.20%.
Transfer learning with multiple pre-trained network for fundus classification Wahyudi Setiawan; Moh. Imam Utoyo; Riries Rulaningtyas
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.v18i3.14868

Abstract

Transfer learning (TL) is a technique of reuse and modify a pre-trained network. It reuses feature extraction layer at a pre-trained network. A target domain in TL obtains the features knowledge from the source domain. TL modified classification layer at a pre-trained network. The target domain can do new tasks according to a purpose. In this article, the target domain is fundus image classification includes normal and neovascularization. Data consist of 100 patches. The comparison of training and validation data was 70:30. The selection of training and validation data is done randomly. Steps of TL i.e load pre-trained networks, replace final layers, train the network, and assess network accuracy. First, the pre-trained network is a layer configuration of the convolutional neural network architecture. Pre-trained network used are AlexNet, VGG16, VGG19, ResNet50, ResNet101, GoogLeNet, Inception-V3, InceptionResNetV2, and squeezenet. Second, replace the final layer is to replace the last three layers. They are fully connected layer, softmax, and output layer. The layer is replaced with a fully connected layer that classifies according to number of classes. Furthermore, it's followed by a softmax and output layer that matches with the target domain. Third, we trained the network. Networks were trained to produce optimal accuracy. In this section, we use gradient descent algorithm optimization. Fourth, assess network accuracy. The experiment results show a testing accuracy between 80% and 100%.
Reconfiguration layers of convolutional neural network for fundus patches classification Wahyudi Setiawan; Moh. Imam Utoyo; Riries Rulaningtyas
Bulletin of Electrical Engineering and Informatics Vol 10, No 1: February 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i1.1974

Abstract

Convolutional neural network (CNN) is a method of supervised deep learning. The architectures including AlexNet, VGG16, VGG19, ResNet 50, ResNet101, GoogleNet, Inception-V3, Inception ResNet-V2, and Squeezenet that have 25 to 825 layers. This study aims to simplify layers of CNN architectures and increased accuracy for fundus patches classification. Fundus patches classify two categories: normal and neovascularization. Data used for classification is MESSIDOR and Retina Image Bank that have 2,080 patches. Results show the best accuracy of 93.17% for original data and 99,33% for augmentation data using CNN 31 layers. It consists input layer, 7 convolutional layers, 7 batch normalization, 7 rectified linear unit, 6 max-pooling, fully connected layer, softmax, and output layer.
Pengaplikasian Optimasi Neural Network oleh Algoritma Genetika pada Pendeteksian Kelainan Otak Stroke Iskemik sebagai Media Pembelajaran Dokter Muda Riries Rulaningtyas
Jurnal Fisika dan Aplikasinya Vol 3, No 1 (2007)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (311.977 KB) | DOI: 10.12962/j24604682.v3i1.969

Abstract

Pengidentikasian dan pendiagnosaan kelainan otak hasil rekaman MRI dilakukan oleh dokter spesialis. Pendiagnosaan citra MRI memerlukan ketelitian agar tidak terjadi kesalahan deteksi. Para dokter muda yang mengambil spesialis syaraf tentunya memerlukan banyak latihan untuk mendiagnosa citra MRI agar dapat memberikan hasil diagnosa yang tepat. Untuk membantu para dokter muda dalam mengidentikasi penyakit stroke iskemik, maka pada penelitian ini telah dibuat computer aided diagnose dengan menggunakan metode neural network yang dapat menggantikan peran dokter spesialis sehingga para dokter muda tersebut dapat berlatih mendiagnosa kelainan otak stroke iskemik secara mandiri. neural network yang digunakan menerima inputcitra MRI yang mengalami pengolahan citra terlebih dahulu yang meliputi proses scanning, proses grayscale, high pass lter, segmentasi, dan normalisasi level grayscale tiap segmen citra. Untuk meningkatkan kinerja neural network dilakukan optimasi jumlah node dan beban yang digunakan yaitu dengan menggunakan optimasi algoritma genetika. Hasilnya neural network mampu mendeteksi 100% data baru, error neural 0,000089 dan fungsi tness algoritma genetika 0,000076.
IMPLEMENTATION OF ICT BASED PEDIATRIC TELEHEALTH CARE POSYANDU AS AUTOMATIC MONITOR AND IDENTIFICATION OF INFANT’S GROWTH AND DEVELOPMENT Riries Rulaningtyas; Abidah Alfi Maritsa; Weni Endahing Warni; Soegianto Soelistiono; Khusnul Ain; Amirul Amalia; Aji Sapta Pramulen; Yusrinourdi Muhammad Zuchruf; Hanif Assyarify; Miranda Syafira Widyananda; Muhammad Fadhel Maulama
Darmabakti Cendekia: Journal of Community Service and Engagements Vol. 2 No. 1 (2020): JUNE 2020
Publisher : Faculty of Vocational Studies, Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1178.987 KB) | DOI: 10.20473/dc.V2.I1.2020.38-45

Abstract

Background: Posyandu is one of the Indonesian government’s attempt in order to monitor and improve the health and life quality of the community, especially infant. However, the implementation of Posyandu is facing some issues such as low effectiveness and low accuracy during the data collecting process of the infant’s growth and development. Purpose: This study aims to develop an automatic telehealth care product in order to help to increase the effectivity and accuracy in the implementation of Posyandu. Methods: (1) Development of the Telehealth Care Posyandu Application, (2) Implementation of the application in the form of social service program. Result: (1) “Toddler” Telehealth Care Application based in Android and ICT was buith with artificial intelligence of Decision Tree and Random Forest method. Program testing was done with 97.89% accuration score from total 85 infant’s growth data. While from 47 questionnaire data of infant’s development, accuracy score of 83.33% was obtained. (2) Target’s respond on the Telehealth Care Posyandu Application shown the status of “Very Satistified” based on the score of 81% from  the satisfaction survey. The satisfaction survey covered three aspects which are: System, User, and Interaction. Conclusion:   “Toddler” Telehealth Care Posyandu Application was proven to has high accuracy, sensitivity, and sensitivity score and also resulted in “Very Satisfied” user respond.
Pelatihan Rancang Bangun Alat Deteksi Kelelahan Berbasis Audiovisual untuk Meningkatkan Kualitas Kerja Dan Kesehatan di SMK 3 Pancasila Kecamatan Ambulu Kabupaten Jember Provinsi Jawa Timur Khusnul Ain; Riries Rulaningtyas; Alfian Pramudita Putra
Jurnal Pengabdian Magister Pendidikan IPA Vol 4 No 1 (2021)
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (213.173 KB) | DOI: 10.29303/jpmpi.v4i1.594

Abstract

Kelelahan adalah salah satu permasalahan serius yang sering dialami pekerja sehingga bisa mengancam nyawa jika kurang mendapat perhatian. Organisasi Buruh Dunia melaporkan sebanyak 2 juta/tahun pekerja melayang nyawanya akibat kecelakaan kerja yang disebabkan oleh kelelahan.  Di Indonesia jumlah kecelakaan kerja mengalami peningkatan tiap tahunnya hingga 5%. Data dari BPJS ketenagakerjaan menunjukkan bahwa pada tahun 2016 terjadi 116.850 kasus kecelakaan kerja sedangkan pada tahun 2017 jumlah kasus meningkat menjadi 123.000 kasus. Banyak penelitian menunjukkan bahwa kelelahan adalah salah satu faktor yang berkontribusi sebagai penyebab kecelakaan. Salah satu cara untuk mengurangi resiko tersebut adalah mengukur kelelahan yang dialami pekerja. Kelelahan dapat dideteksi dengan mengukur waktu respon terhadap rangsangan yang diberikan. Waktu respon umpan balik sebagai tanggapan dari rangsangan yang diberikan merupakan parameter utama yang digunakan untuk menentukan tingkat kelelahan seseorang. Berdasarkan analisis situasi tersebut, maka melalui kegiatan pengabdian masyarakat Program Kemitraan Masyarakat ini, dapat diberikan bekal keahlian kepada siswa Sekolah Menengah Kejuruan (SMK) yang sudah memiliki bekal keilmuan elektronika dasar dan mikrokontroller untuk diberikan pelatihan pembuatan alat kesehatan dengan mempelajari dan mengembangkan instrumentasi medis sederhana berbasis elektronika dan mikrokontroller sederhana yaitu alat ukur tingkat kelelahan pekerja. Para siswa SMK diharapkan setelah lulus mampu mengembangkan produksi dan pengadaan alat kesehatan secara mandiri di Indonesia. Hasil kegiatan pengabdian masyarakat terlihat bahwa peserta pelatihan sangat antusias terhadap pelaksanaan kegiatan karena mendapatkan pengetahuan baru terkait dasar elektronika dan mikrokontroler
Pelatihan Rancang Bangun Sistem Monitoring Kondisi Air Tambak Berbasis Internet of Things (IoT) di SMK Perikanan dan Kelautan Kecamatan Puger Kabupaten Jember Alfian Pramudita Putra; Riries Rulaningtyas; Franky Chandra Satria Arisgraha
Jurnal Pengabdian Magister Pendidikan IPA Vol 4 No 4 (2021)
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (425.918 KB) | DOI: 10.29303/jpmpi.v4i4.1007

Abstract

Kualitas air tambak atau kolam budidaya ikan atau udang merupakan aspek eksternal yang harus diperhatikan. Permasalahan utama dalam kegagalan produksi ikan atau udang adalah buruknya kualitas air selama masa pemeliharaan, terutama pada tambak intensif. Sebagian besar pekerjaan monitoring telah dibantu teknologi informasi untuk memudahkan dalam pelaksanaan pemantauan. Salah satunya adalah dengan penggunaan Internet of Things (IoT). Sistem IoT ini dapat digunakan para petambak untuk memantau kondisi perarian tambak sehingga produksi mereka bisa meningkat. Melalui kegiatan pengabdian masyarakat Program Kemitraan Masyarakat ini, sistem yang dapat memantau suhu dan pH dari perariran secara kontinu telah dibuat dengan memanfaatkan IoT. Hal ini bermanfaat untuk para siswa SMK sehinga mereka dapat meningkatkan kemampuan di bidang teknologi yang tetap berkaitan dengan perikanan dan kelautan. Peserta pelatihan sangat antusias terhadap pelaksanaan kegiatan karena mendapatkan pengetahuan baru terkait mikrokontroler dan IoT. Selain itu, Siswa SMK dapat memiliki tambahan kemampuan dan pengetahuan yang berguna untuk bersaing di dunia kerja, khususnya pada era revolusi industri 4.0.
RANCANG BANGUN PROTOTIPE 3 DIMENSI ORGAN MANDIBULA MENGGUNAKAN CITRA MEDIS RADIOLOGI Amillia Kartika Sari; Riries Rulaningtyas; Khusnul Ain; Suryani Dyah Astuti; Soegianto Soelistiono; David Buntoro Kamandjaja
Medika Respati : Jurnal Ilmiah Kesehatan Vol 17, No 4 (2022)
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/mr.v17i4.762

Abstract

Latar belakang: Tumor pada mandibula dapat menyebabkan kecacatan tulang. hal ini memberikan dampak negatif pada kehidupan sosial penderita. Solusi pada kasus ini adalah operasi rekonstruksi mandibula. Untuk mengoptimalkan operasi tersebut salah satunya dapat digunakan prototipe 3D sebagai perencanaan pra-bedah. Tujuan: Penelitian ini berfokus pada proses pembuatan prototipe 3D yang menggunakan pencitraan dari modalitas CT-Scan. Hasil: Pembuatan prototipe 3D diawali dari akuisisi data citra CT-Scan yang selanjutnya dilakukan proses segmentasi citra dan visualisasi 3 dimensi, pada proses terakhir dilakukan pencetakan 3 dimensi. Prototipe 3D yang telah jadi dilakukan analisa kualitatif melalui pengukuran dimensi panjang di daerah ramus, angulus, dan body of mandible dan dibandingkan dengan hasil pengukuran organ mandibula cadaver. Didapatkan hasil rerata panjang ramus pada mandibula cadaver adalah 33,62±0,34 mm, sedangkan panjang ramus pada mandibula prototipe 3D adalah 32,98±0,44 mm. Nilai rerata pengukuran pada daerah angulus adalah 31,26±0,25 mm pada mandibula cadaver, dan nilai 31,23±0,22 mm pada mandibula protptipe 3D. Dan pengukuran pada daerah body of mandible  mandibula cadaver adalah 32,05±0,98mm, sedangkan apada mandibula prootipe adalah 32,06±1,03 mm, secara keseluruhan akurasi pada prototipe 3D sebesar 99,317%.  Kesimpulan: Penggunaan citra radiologi sebagai data awal untuk membuat prototipe 3 dimensi mandibula dapat dilakukan, pengukuran akurasi prototipe 3D harus dievaluasi untuk masing-masing tahap fabrikasi.
Detection of lung disease using relative reconstruction method in electrical impedance tomography system Lina Choridah; Riries Rulaningtyas; Lailatul Muqmiroh; Suprayitno Suprayitno; Khusnul Ain
Bulletin of Electrical Engineering and Informatics Vol 12, No 4: August 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v12i4.4940

Abstract

Lung disease can be diagnosed with the image-based medical devices, including radiography, computed tomography, and magnetic resonance imaging. The devices are very expensive and have negative effects. An alternative device is electrical impedance tomography (EIT). The advantages of EIT arelow cost, fast, real-time, and free radiation, so it is very appropriate to be used as a monitoring device. The relative reconstruction method has succeeded in producing functional images of lung anomalies by simulation. In this study, the relative reconstruction method was used to obtain functional images of four lungs conditions, namely a healthy person, patient with left lung tumor with organized left pleural effusion, one with pulmonary tuberculosis with right pneumothorax and one with pulmonary tuberculosis with left pleural effusion. The relative reconstruction method can be used to obtain functional images of an individual’s lung conditions by using expiratory-respiratory potential data with results that can distinguish between the lungs of a healthy person and a diseased patient, but the position of the lung disease may have less details. The potential data from comparison between the data of a patient and a healthy person can be used as a reference to obtain more accurate functional image information of lung disease.