Classification of Traffic Vehicle Density Using Deep Learning

Kholik, Abdul; Harjoko, Agus; Wahyono, Wahyono

doi:10.22146/ijccs.50376

Cited by 7 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traffic management especially dealing with traffic jams depends on several influencing factors. In this study, 4 indicators are categorized in determining the level of traffic density which is divided into 6 types of density levels (Kholik et al, 2020) which are presented in table 1.…”

Section: Methodsmentioning

confidence: 99%

Indicator of Highway Conditions on Traffic Density Levels

Rosita

Akbar²,

Kurniawan³

2023

ijeeit

View full text Add to dashboard Cite

Traffic problems, especially congestion which is the impact of high levels of traffic density, are problems that have not been properly resolved, especially in big cities in Indonesia. In this article, 7 features of road conditions are proposed on the level of traffic density. These features include the number of vehicles, the average speed of the vehicle, the area of the main road, the length of traffic that has been determined, the duration of traffic congestion, and the time of traffic congestion. Determining the level of traffic density can be determined by utilizing the MCDM hybrid technique to produce information that can be used to support decision-making in traffic management or other policies such as formulating policies on the buying and selling of private vehicles. The number of indicators related to computer vision for presenting information on the level of traffic density requires a large amount of time and memory. Besides that, the perception of a decision maker in determining priority weights also influences the results of the information on the level of traffic density.

show abstract

Section: Methodsmentioning

confidence: 99%

Indicator of Highway Conditions on Traffic Density Levels

Rosita

Akbar²,

Kurniawan³

2023

ijeeit

View full text Add to dashboard Cite

show abstract

“…Additionally, its output formed a vector comprising probabilities for all potential outcomes. The probabilities in this vector are collectively summed up to one for all classes or outcomes [22]. Softmax was commonly deployed in the final layer of classification-oriented neural networks.…”

Section: B Softmaxmentioning

confidence: 99%

Robust Convolutional Neural Network for Image Classification with Gaussian Noise

Surono,

Arofah,

Thobirin

2023

Fuzzy Systems and Data Mining IX

View full text Add to dashboard Cite

A Convolutional Neural Network (CNN) is one branch of Deep Learning widely used for image classification. CNN have complex architectures and capable of achieving high accuracy and producing good results. However, CNN have limitations, especially when dealing with noisy images. Image noise can decrease classification performance and increase network training time. This research was tested the robustness of two CNN methods, namely VGG16 and ResNet50, in processing images with added Gaussian noise at various levels, without any preprocessing. The dataset used is the Rice Image Dataset, which consists of images of 5 different types of rice. The data is divided into three parts: 70% for training, 20% for testing, and 10% for validation. The results of this study show that as the variability in generating Gaussian noise in the images increases, the loss function value consistently increases, and the accuracy decreases. However, the increase in the loss function value and the decrease in accuracy are not significantly different among the different levels of noise variability.

show abstract

“…Berikut merupakan alur dari penelitian ini: Setelah pelatihan selesai, model CNN akan dievaluasi menggunakan data uji yang terpisah dari data latih dan data validasi [9], [10] [11]. Performa model diukur dengan menggunakan metrik-metrik seperti akurasi, presisi, dan recall.…”

Section: Metode Penelitianunclassified

DeepSun: Klasifikasi Fase Cahaya Matahari Berdasarkan Warna Menggunakan CNN

Nengsih,

Juni Nurma Sari,

Angresta

et al. 2023

JKT

View full text Add to dashboard Cite

Penelitian ini berbasis metode DeepSun, sebuah sistem yang menggunakan Jaringan Syaraf Tiruan Konvolusi (CNN) untuk mengklasifikasikan fase cahaya matahari berdasarkan warna. Fase cahaya seperti Golden Hour, Blue Hour, dan Pink Hour memiliki karakteristik visual yang khas, dan mengidentifikasi fase cahaya ini secara otomatis dapat memberikan pemahaman yang lebih baik tentang suasana dan estetika suatu gambar. Pendekatan yang diusulkan menggunakan dataset yang terdiri dari gambar-gambar yang dikumpulkan selama berbagai kondisi cahaya matahari. Data tersebut dianotasi dengan label fase cahaya yang sesuai. CNN digunakan untuk mengekstraksi fitur-fitur penting dari gambar-gambar ini. Kemudian, fitur-fitur tersebut digunakan sebagai input untuk pengklasifikasi yang dilatih menggunakan algoritma pembelajaran mesin. Eksperimen dilakukan untuk mengevaluasi kinerja sistem DeepSun. Hasil-hasil yang diperoleh menunjukkan bahwa sistem ini mampu mengklasifikasikan fase cahaya matahari dengan tingkat akurasi yang tinggi. Kesalahan klasifikasi terutama terjadi saat kondisi cahaya yang sangat mirip antara fase-fase tertentu. Namun, dengan meningkatkan jumlah data latih dan peningkatan arsitektur CNN, tingkat akurasi dapat ditingkatkan lebih lanjut. Dengan kemampuan untuk mengklasifikasikan fase cahaya matahari secara otomatis, DeepSun dapat membantu pengguna untuk memilih waktu yang tepat dalam mengambil gambar yang berkualitas. Selain itu, sistem ini juga dapat digunakan untuk meningkatkan pemrosesan gambar otomatis dan pengeditan yang berbasis pada fase cahaya yang diinginkan.

show abstract

Classification of Traffic Vehicle Density Using Deep Learning

Cited by 7 publications

References 5 publications

Indicator of Highway Conditions on Traffic Density Levels

Indicator of Highway Conditions on Traffic Density Levels

Robust Convolutional Neural Network for Image Classification with Gaussian Noise

DeepSun: Klasifikasi Fase Cahaya Matahari Berdasarkan Warna Menggunakan CNN

Contact Info

Product

Resources

About