Desain Sistem Pengatur Lampu Lalu Lintas dengan Identifikasi Kepadatan Kendaraan Menggunakan Metode Subtraction

Djavendra, Geminiesty Lathifasari; Aisyah, Siti; Jamzuri, Eko Rudiawan

doi:10.25077/jnte.v7n2.541.2018

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Subsequently, all RGB MRIs are converted to greyscale, and noise is removed using the Gaussian blur technique. Threshold processing then converts the greyedout employee image into a binary format [36]. The next step is to locate contours in the threshold picture by choosing the biggest contour that is present.…”

Section: Image Preprocessingmentioning

confidence: 99%

A Transfer Learning-Based Model for Brain Tumor Detection in MRI Images

Faiz Rofi Hencya,

Satria Mandala,

Tong Boon Tang

et al. 2023

JNTE

View full text Add to dashboard Cite

Brain tumors are life-threatening medical conditions characterized by abnormal cell proliferation in or near the brain. Early detection is crucial for successful treatment. However, the scarcity of labelled brain tumor datasets and the tendency of convolutional neural networks (CNNs) to overfit on small datasets have made it challenging to train accurate deep learning models for brain tumor detection. Transfer learning is a machine learning technique that allows a model trained on one task to be reused for a different task. This approach is effective in brain tumor detection as it allows CNNs to be trained on larger datasets and generalize better to new data. In this research, we propose a transfer learning approach using the Xception model to detect four types of brain tumors: meningioma, pituitary, glioma, and no tumor (healthy brain). The performance of our model was evaluated on two datasets, demonstrating a sensitivity of 98.07%, specificity of 97.83%, accuracy of 98.15%, precision of 98.07%, and f1-score of 98.07%. Additionally, we developed a user-friendly prototype application for easy access to the Xception model for brain tumor detection. The prototype was evaluated on a separate dataset, and the results showed a sensitivity of 95.30%, specificity of 96.07%, accuracy of 95.30%, precision of 95.31%, and f1-score of 95.27%. These results suggest that the Xception model is a promising approach for brain tumor detection. The prototype application provides a convenient and easy-to-use way for clinical practitioners and radiologists to access the model. We believe the model and prototype generated from this research will be valuable tools for diagnosing, quantifying, and monitoring brain tumors.

show abstract

Section: Image Preprocessingmentioning

confidence: 99%

A Transfer Learning-Based Model for Brain Tumor Detection in MRI Images

Faiz Rofi Hencya,

Satria Mandala,

Tong Boon Tang

et al. 2023

JNTE

View full text Add to dashboard Cite

show abstract

“…The study developed a method for estimating the queue length. Finally, Djavendra et al [21] designed a traffic light control system for vehicle density identification. The research proposes an automatic traffic light control system to predict vehicle density using pixel image processing techniques.…”

Section: Introductionmentioning

confidence: 99%

Traffic lights time strategy for T-junctions of toll road gate

Tristono,

Cahyono,

Aji

et al. 2023

IJRA

View full text Add to dashboard Cite

Vehicles wishing to pass on the toll road must diverge from the traffic flow on public roads. The toll road movement consists of low vehicles (LV) and heavy vehicles (HV). The public road movement is a mixed traffic flow consisting of LV, HV, motorcycles, and unmotorized vehicles. Traffic lights are used at the T-junction of the toll road gate for travel safety management. The traffic lights that implement a fixed-time strategy should be optimized for efficiency. This study aims to review the safety of travel management at T-junctions for the toll road gate when adaptive traffic lights are used. The structural complexity of mathematical modeling with Petri net is used to analyze and measure the feasibility study. Results illustrate that the structural complexity of the traffic lights that implement a fixed time strategy equals 0.387. It is equal to 0.489 for the adaptive traffic lights. The structural complexity of adaptive traffic lights is 25% higher than conventional systems that implement a fixed-time strategy. The adaptive traffic lights time strategy is feasible for travel safety for road users. The travel time is efficient and comfortable because the delay is low. Furthermore, traffic lights can adjust to the demand of vehicles queuing.

show abstract

“…Pengambilan gambar dalam pengolahan citra ini dapat dilakukan dengan menggunakan gambar dari berkas yang sudah ada, ataupun dengan menggunakan kamera. [6] Segmentasi citra yang merupakan bagian dari pengolahan citra digital merupakan suatu proses untuk memisahkan antara objek yang ingin diamati dengan latar belakang atau objek lain yang tidak diinginkan. Dengan menerapkan proses segmentasi pada citra retina, maka pembuluh darah dari retina mata dapat dipisahkan dari latar belakang atau objek lain yang tidak diinginkan sehingga bisa mempermudah dalam mendeteksi kelainan yang ada pada pembuluh darah retina tersebut.…”

unclassified

Analisis Performa Algoritma Segmentasi Pembuluh Darah pada Citra Fundus Retina

Asril

Maison

Yudertha

2019

JEPIN

View full text Add to dashboard Cite

Ada banyak penyakit yang bisa di deteksi melalui pembuluh darah, seperti hipertensi, jantung, dan retinopati diabetes. Namun, pendeteksian penyakit melalui retina tidak mudah. Dokter harus mengamati struktur pembuluh darah pada citra fundus retina. Pengamatan secara langsung pada citra fundus membutuhkan waktu yang lama dan juga beresiko terjadi kesalahan. Dalam mengatasi hal ini, maka pengolahan citra digital diperlukan sebagai upaya untuk mempermudah pendeteksian kelainan pada retina mata. Penelitian ini bertujuan untuk melakukan analisis terhadap algoritma yang digunakan pada proses segmentasi citra fundus retina, karena hasil segmentasi dari citra akan berpengaruh besar dalam proses klasifikasi jenis penyakit pada retina. Kesalahan dalam pengklasifikasian jenis kelainan pada retina bisa menyebabkan kesalahan diagnosis dan kesalahan pemberian terapi yang tepat bagi pasien. Pengolahan citra dilakukan mulai tahap pra-pengolahan hingga segmentasi. Pengujian algoritma dilakukan pada tahap segmentasi. Hasil pengujian terhadap tiga algoritma menunjukkan bahwa metode pertama yaitu Morfologi Rekonstruksi memiliki rata-rata akurasi sebesar 94,46% dengan standard deviasi 2,94, Coye Filter memiliki rata-rata akurasi sebesar 94,97% dengan standard deviasi 4,99 dan Kirsch and Fuzzy C-Means dengan rata-rata akurasi 88,73% dan standar deviasi 2,74. Performa algoritma yang paling baik tidak hanya ditentukan dari tingkat akurasi tetapi juga dari aspek lain yaitu standar deviasi.

show abstract

Desain Sistem Pengatur Lampu Lalu Lintas dengan Identifikasi Kepadatan Kendaraan Menggunakan Metode Subtraction

Cited by 3 publications

References 0 publications

A Transfer Learning-Based Model for Brain Tumor Detection in MRI Images

A Transfer Learning-Based Model for Brain Tumor Detection in MRI Images

Traffic lights time strategy for T-junctions of toll road gate

Analisis Performa Algoritma Segmentasi Pembuluh Darah pada Citra Fundus Retina

Contact Info

Product

Resources

About