HOG Feature Extraction and KNN Classification for Detecting Vehicle in The Highway

Putra, Firnanda Al Islama Achyunda; Utaminingrum, Fitri; Mahmudy, Wayan Firdaus

doi:10.22146/ijccs.54050

Cited by 23 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…K Nearest Neighbors (KNN) is a supervised learningbased classification algorithm [1]- [3], KNN has been used in a wide range of research fields [4]- [7], Some research fields that apply KNN as a classification algorithm include the health sector [6], e-commerce [8], Detecting Vehicle [9]. Although KNN has been widely used in various fields, it has some limitations, including the difficulty of determining the appropriate hyperparameter K. This difficulty arises because an incorrect value of K can lead to overfitting or underfitting problems.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Hyperparameter K in K-Nearest Neighbor Using Particle Swarm Optimization

Rizki,

Hermawan,

Avianto

2024

JUITA

View full text Add to dashboard Cite

This study aims to enhance the performance of the K-Nearest Neighbors (KNN) algorithm by optimizing the hyperparameter K using the Particle Swarm Optimization (PSO) algorithm. In contrast to prior research, which typically focuses on a single dataset, this study seeks to demonstrate that PSO can effectively optimize KNN hyperparameters across diverse datasets. Three datasets from different domains are utilized: Iris, Wine, and Breast Cancer, each featuring distinct classification types and classes. Furthermore, this research endeavors to establish that PSO can operate optimally with both Manhattan and Euclidean distance metrics. Prior to optimization, experiments with default K values (3, 5, and 7) were conducted to observe KNN behavior on each dataset. Initial results reveal stable accuracy in the iris dataset, while the wine and breast cancer datasets exhibit a decrease in accuracy at K=3, attributed to attribute complexity. The hyperparameter K optimization process with PSO yields a significant increase in accuracy, particularly in the wine dataset, where accuracy improves by 6.28% with the Manhattan matrix. The enhanced accuracy in the optimized KNN algorithm demonstrates the effectiveness of PSO in overcoming KNN constraints. Although the accuracy increase for the iris dataset is not as pronounced, this research provides insight that optimizing the hyperparameter K can yield positive results, even for datasets with initially good performance. A recommendation for future research is to conduct similar experiments with different algorithms, such as Support Vector Machine or Random Forest, to further evaluate PSO's ability to optimize the iris, wine, and breast cancer datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of Hyperparameter K in K-Nearest Neighbor Using Particle Swarm Optimization

Rizki,

Hermawan,

Avianto

2024

JUITA

View full text Add to dashboard Cite

show abstract

“…In research [21], HOG feature extraction is used to detect objects such as cars. With HOG feature extraction, testing data is created from 304 x 240 pixel images.…”

Section: Introductionmentioning

confidence: 99%

Compares the effectiveness of the bagging method in classifying spices using the histogram of oriented gradient feature extraction technique

Muhathir

2023

J. Teknik Informatika CIT Medicom,

View full text Add to dashboard Cite

Spice classification is a crucial task in the food industry to ensure food safety and quality. This study focuses on the classification of spices using the Histogram of Oriented Gradient (HoG) feature extraction method and bagging method. The objective of this research is to compare the performance of three different models of bagging method, including Bootstrap Aggregating (Bagging), Random Forests, and Extra Tree Classifier, in classifying spices. The evaluation metrics used in this research are Precision, Recall, F1-Score, F2-Score, Jaccard Score, and Accuracy. The results show that the Random Forest model achieved the best performance, with precision, recall, F1-score, F2-Score, Jaccard, and Accuracy values of 0.861, 0.8633, 0.8587, 0.8607, 0.7694, and 0.8733 respectively. On the other hand, the Extra Tree Classifier had the lowest performance with precision, recall, F1-score, F2-Score, Jaccard, and Accuracy values of 0.7034, 0.7958, 0.7037, 0.7047, 0.5635, and 0.72 respectively. Overall, the results indicate a fairly good success rate in classifying spices using the HoG feature extraction method and bagging method. However, further evaluation is needed to improve the accuracy of the classification results, such as increasing the number of training data or considering the use of other feature extraction methods. The findings of this research may have significant implications for the food industry in ensuring the quality and safety of food products.

show abstract

“…On the other hand, some other papers such as [19] have been conducted on image-base analysis using several algorithms to recognize cars and vehicles. Pattern recognition algorithms, such as histogram of gradient (HOG) [20], scale invariant feature transform (SIFT) [21], convolutional neural network (CNN) [22] and Harr-like [23], were used in this perspective. These methods make use of some predefined visual features like color, shape and texture to recognize cars.…”

Section: Introductionmentioning

confidence: 99%

Traffic flow measurement for smart traffic light system design

Al-Momin,

Alkhafaji,

Al-Musawi

2023

TELKOMNIKA

View full text Add to dashboard Cite

Determining congestions on intersection roads can significantly improve the performance of a traffic light system. One of the everyday problems on our roads nowadays is the unbalanced traffic on different roads. The blind view of roads and the dependency on the conventional timer-based traffic light systems can cause unnecessary delays on some arterial roads on expense of offering a needless extra pass time on some other secondary minor roads. In this paper, a foreground extraction model has been built in MATLAB platform to measure the congestions on the different roads constructing an intersection. Results show a satisfactory performance in terms of accuracy in counting cars and in consequence reducing the wait time on some major roads. System was tested under different weather and lighting conditions, and results were adequately promising.

show abstract

HOG Feature Extraction and KNN Classification for Detecting Vehicle in The Highway

Cited by 23 publications

References 19 publications

Optimization of Hyperparameter K in K-Nearest Neighbor Using Particle Swarm Optimization

Optimization of Hyperparameter K in K-Nearest Neighbor Using Particle Swarm Optimization

Compares the effectiveness of the bagging method in classifying spices using the histogram of oriented gradient feature extraction technique

Traffic flow measurement for smart traffic light system design

Contact Info

Product

Resources

About