Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks

Teknik ◽  
2021 ◽  
Vol 42 (2) ◽  
pp. 169-177
Author(s):  
Faqih Rofii ◽  
Gigih Priyandoko ◽  
Muhammad Ifan Fanani ◽  
Aji Suraji
Keyword(s):  
Confusion Matrix ◽  
Model Performance ◽  
Vehicle Detection ◽  
Traffic Density ◽  
Total Recall ◽  
System Input ◽  
Camera Position ◽  
Bounding Boxes ◽  
Total Accuracy ◽  
Counting Model

Models for vehicle detection, classification, and counting based on computer vision and artificial intelligence are constantly evolving. In this study, we present the Yolov4-based vehicle detection, classification, and counting model approach. The number of vehicles was calculated by generating the serial number of the identity of each vehicle. The object is detected and classified, marked by the display of bounding boxes, classes, and confidence scores. The system input is a video dataset that considers the camera position, light intensity, and vehicle traffic density. The method has counted the number of vehicles: cars, motorcycles, buses, and trucks. Evaluation of model performance is based on accuracy, precision, and total recall of the confusion matrix. The results of the dataset test and the calculation of the model performance parameters had obtained the best accuracy, precision. Total recall values when the model testing was carried out during the day where the camera position was at the height of 6 m and the loss of 500 was 83%, 93%, and 94%. Meanwhile, the lowest total accuracy, precision, and recall were obtained when the model was tested at night. The camera position was at the height of 1.5 m, and 900 losses were 68%, 77%, and 78%.

scholarly journals IDENTIFYING KEY FACTORS OF COMMUTER TRAIN SERVICE QUALITY:AN EMPIRICAL ANALYSIS FOR DHAKA CITY

2019 ◽  
Vol 31 (2) ◽  
Author(s):  
Anika Nowshin Mowrin ◽  
Md. Hadiuzzaman ◽  
Saurav Barua ◽  
Md. Mizanur Rahman
Keyword(s):  
Traffic Congestion ◽  
Fuzzy Inference ◽  
Confusion Matrix ◽  
Model Development ◽  
Model Performance ◽  
Total Sample ◽  
Dhaka City ◽  
Anfis Model ◽  
Regular User ◽  
Inference System

Commuter train is a viable alternative to road transport to ease the traffic congestion which requires appropriate planning by concerned authorities. The research is aimed to assess passengers’ perception about commuter train service running in areas near Dhaka city. An Adaptive Neuro Fuzzy Inference System (ANFIS) model has been developed to evaluate service quality (SQ) of commuter train. Field survey data has been conducted among 802 respondents who were the regular user of commuter train and 12 attributes have been selected for model development. ANFIS was developed by the training and then tested by 80% and 20% of the total sample respectively. After that, model performance has been evaluated by (i) Confusion Matrix (ii) Root Mean Square Error (RMSE) and attributes are ranked based on their relative importance. The proposed ANFIS model has 61.50% accuracy in training and 47.80% accuracy in testing.  From the results, it is found that 'Bogie condition', 'Cleanliness', ‘Female harassment’, 'Behavior of staff' and 'Toilet facility' are the most significant attributes. This indicates that some necessary measures should be taken immediately to recover the effects of these attributes to improve the SQ of commuter train. 

scholarly journals Model Assessment with ROC Curves

2011 ◽  
pp. 1316-1323 ◽  
Author(s):  
Lutz Hamel
Keyword(s):  
Performance Metrics ◽  
Confusion Matrix ◽  
Model Performance ◽  
Roc Curves ◽  
Parametric Models ◽  
Classification Model ◽  
Model Assessment ◽  
Classification Models ◽  
The Difference ◽  
Class Skew

Classification models and in particular binary classification models are ubiquitous in many branches of science and business. Consider, for example, classification models in bioinformatics that classify catalytic protein structures as being in an active or inactive conformation. As an example from the field of medical informatics we might consider a classification model that, given the parameters of a tumor, will classify it as malignant or benign. Finally, a classification model in a bank might be used to tell the difference between a legal and a fraudulent transaction. Central to constructing, deploying, and using classification models is the question of model performance assessment (Hastie, Tibshirani, & Friedman, 2001). Traditionally this is accomplished by using metrics derived from the confusion matrix or contingency table. However, it has been recognized that (a) a scalar is a poor summary for the performance of a model in particular when deploying non-parametric models such as artificial neural networks or decision trees (Provost, Fawcett, & Kohavi, 1998) and (b) some performance metrics derived from the confusion matrix are sensitive to data anomalies such as class skew (Fawcett & Flach, 2005). Recently it has been observed that Receiver Operating Characteristic (ROC) curves visually convey the same information as the confusion matrix in a much more intuitive and robust fashion (Swets, Dawes, & Monahan, 2000). Here we take a look at model performance metrics derived from the confusion matrix. We highlight their shortcomings and illustrate how ROC curves can be deployed for model assessment in order to provide a much deeper and perhaps more intuitive analysis of the models. We also briefly address the problem of model selection.

scholarly journals ORIENTED VEHICLE DETECTION IN HIGH-RESOLUTION REMOTE SENSING IMAGES BASED ON FEATURE AMPLIFICATION AND CATEGORY BALANCE BY OVERSAMPLING DATA AUGMENTATION

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 153-159
Author(s):  
N. Mo ◽  
L. Yan
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Vehicle Detection ◽  
Training Dataset ◽  
Remote Sensing Images ◽  
Feature Maps ◽  
Fine Grained ◽  
Bounding Boxes ◽  
The Impact ◽  
Oriented Bounding Boxes

Abstract. Vehicles usually lack detailed information and are difficult to be trained on the high-resolution remote sensing images because of small size. In addition, vehicles contain multiple fine-grained categories that are slightly different, randomly located and oriented. Therefore, it is difficult to locate and identify these fine categories of vehicles. Considering the above problems in high-resolution remote sensing images, this paper proposes an oriented vehicle detection approach. First of all, we propose an oversampling and stitching method to augment the training dataset by increasing the frequency of objects with fewer training samples in order to balance the number of objects in each fine-grained vehicle category. Then considering the effect of the pooling operations on representing small objects, we propose to improve the resolution of feature maps so that detailed information hidden in feature maps can be enriched and they can better distinguish the fine-grained vehicle categories. Finally, we design a joint training loss function for horizontal and oriented bounding boxes with center loss, to decrease the impact of small between-class diversity on vehicle detection. Experimental verification is performed on the VEDAI dataset consisting of 9 fine-grained vehicle categories so as to evaluate the proposed framework. The experimental results show that the proposed framework performs better than most of competitive approaches in terms of a mean average precision of 60.7% and 60.4% in detecting horizontal and oriented bounding boxes respectively.

scholarly journals Detection of child depression using machine learning methods

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0261131
Author(s):  
Umme Marzia Haque ◽  
Enamul Kabir ◽  
Rasheda Khanam
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Mental Illness ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
Confusion Matrix ◽  
Model Performance ◽  
Child And Adolescent ◽  
Target Variable ◽  
Depression Detection

Background Mental health problems, such as depression in children have far-reaching negative effects on child, family and society as whole. It is necessary to identify the reasons that contribute to this mental illness. Detecting the appropriate signs to anticipate mental illness as depression in children and adolescents is vital in making an early and accurate diagnosis to avoid severe consequences in the future. There has been no research employing machine learning (ML) approaches for depression detection among children and adolescents aged 4–17 years in a precisely constructed high prediction dataset, such as Young Minds Matter (YMM). As a result, our objective is to 1) create a model that can predict depression in children and adolescents aged 4–17 years old, 2) evaluate the results of ML algorithms to determine which one outperforms the others and 3) associate with the related issues of family activities and socioeconomic difficulties that contribute to depression. Methods The YMM, the second Australian Child and Adolescent Survey of Mental Health and Wellbeing 2013–14 has been used as data source in this research. The variables of yes/no value of low correlation with the target variable (depression status) have been eliminated. The Boruta algorithm has been utilized in association with a Random Forest (RF) classifier to extract the most important features for depression detection among the high correlated variables with target variable. The Tree-based Pipeline Optimization Tool (TPOTclassifier) has been used to choose suitable supervised learning models. In the depression detection step, RF, XGBoost (XGB), Decision Tree (DT), and Gaussian Naive Bayes (GaussianNB) have been used. Results Unhappy, nothing fun, irritable mood, diminished interest, weight loss/gain, insomnia or hypersomnia, psychomotor agitation or retardation, fatigue, thinking or concentration problems or indecisiveness, suicide attempt or plan, presence of any of these five symptoms have been identified as 11 important features to detect depression among children and adolescents. Although model performance varied somewhat, RF outperformed all other algorithms in predicting depressed classes by 99% with 95% accuracy rate and 99% precision rate in 315 milliseconds (ms). Conclusion This RF-based prediction model is more accurate and informative in predicting child and adolescent depression that outperforms in all four confusion matrix performance measures as well as execution duration.

scholarly journals On the safety effects of spatially aggregated traffic flow parameters at macro-levels

2019 ◽  
Vol 11 (1) ◽  
pp. 168781401881940
Author(s):  
Chen Wang ◽  
Lin Liu ◽  
Zhenbo Lu
Keyword(s):  
Traffic Flow ◽  
Management Strategies ◽  
Central Area ◽  
Model Performance ◽  
Graph Cut ◽  
Crash Risk ◽  
Traffic Density ◽  
Minimization Method ◽  
Flow Parameters ◽  
Regional Management

Traffic flow parameters have been found to significantly affect crash risk at micro-levels. If such effects do exist at macro-levels, at least two benefits could be expected: (1) the performance and estimates of planning-based crash models could be improved and (2) useful safety knowledge could be provided for regional traffic management. In this article, a flow-based spatial unit was developed by a graph-cut minimization method, based on which regional management strategies are often applied. The graph-cut method partitioned the central area of Kunshan, China, into multiple sub-regions (i.e. graph-cut unit), considering traffic density homogeneity. Bayesian Poisson lognormal models with conditional autoregressive priors were utilized to examine the safety effects of traffic flow parameters, based on the traditional planning-based units and the flow-based graph-cut units. According to the results, no significant traffic flow effect was found for the traffic analysis zone–based model. Traffic flow parameters resulted in a decreased model performance and potential endogeneity issues for the census tract–based model. However, traffic flow effects were found significant for the graph-cut-based model, with an improved model performance. In general, the safety effects of macro-level traffic flow need to be considered for flow-based units developed for regional management.

scholarly journals Improved Faster RCNN Based on Feature Amplification and Oversampling Data Augmentation for Oriented Vehicle Detection in Aerial Images

2020 ◽  
Vol 12 (16) ◽  
pp. 2558 ◽  
Author(s):  
Nan Mo ◽  
Li Yan
Keyword(s):  
Data Augmentation ◽  
Vehicle Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Discriminative Ability ◽  
Feature Map ◽  
Negative Effect ◽  
Bounding Boxes ◽  
The Impact ◽  
Oriented Bounding Boxes

Vehicles in aerial images are generally with small sizes and unbalanced number of samples, which leads to the poor performances of the existing vehicle detection algorithms. Therefore, an oriented vehicle detection framework based on improved Faster RCNN is proposed for aerial images. First of all, we propose an oversampling and stitching data augmentation method to decrease the negative effect of category imbalance in the training dataset and construct a new dataset with balanced number of samples. Then considering that the pooling operation may loss the discriminative ability of features for small objects, we propose to amplify the feature map so that detailed information hidden in the last feature map can be enriched. Finally, we design a joint training loss function including center loss for both horizontal and oriented bounding boxes, and reduce the impact of small inter-class diversity on vehicle detection. The proposed framework is evaluated on the VEDAI dataset that consists of 9 vehicle categories. The experimental results show that the proposed framework outperforms previous approaches with a mean average precision of 60.4% and 60.1% in detecting horizontal and oriented bounding boxes respectively, which is about 8% better than Faster RCNN.

scholarly journals Identifying Cotton Fields from Remote Sensing Images Using Multiple Deep Learning Networks

Agronomy ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 174
Author(s):  
Haolu Li ◽  
Guojie Wang ◽  
Zhen Dong ◽  
Xikun Wei ◽  
Mengjuan Wu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Precision Agriculture ◽  
Agronomic Traits ◽  
Accuracy Assessment ◽  
Confusion Matrix ◽  
Model Performance ◽  
Accurate Identification ◽  
Cotton Crop ◽  
Cotton Fields

Remote sensing imageries processed through empirical and deterministic approaches help predict multiple agronomic traits throughout the growing season. Accurate identification of cotton crop from remotely sensed imageries is a significant task in precision agriculture. This study aims to utilize a deep learning-based framework for cotton crop field identification with Gaofen-1 (GF-1) high-resolution (16 m) imageries in Wei-Ku region, China. An optimized model for the pixel-wise multidimensional densely connected convolutional neural network (DenseNet) was used. Four widely-used classic convolutional neural networks (CNNs), including ResNet, VGG, SegNet, and DeepLab v3+, were also used for accuracy assessment. The results infer that DenseNet can identify cotton crop features within a relatively shorter time about 5 h for training convergence. The model performance was examined by multiple indicators (P, F1, R, and mIou) produced through the confusion matrix, and the derived cotton fields were then visualized. The DenseNet model has illustrated considerable improvements in comparison with the preceding mainstream models. The results showed that the retrieval precision was 0.948, F1 score was 0.953, and mIou was 0.911. Furthermore, its performance is relatively better in discriminating cotton crop fields’ fine structures when clouds, mountain shadows, and urban built up.

scholarly journals Machine Learning to Calculate Heparin Dose in COVID-19 Patients with Active Cancer

2021 ◽  
Vol 11 (1) ◽  
pp. 219
Author(s):  
Egidio Imbalzano ◽  
Luana Orlando ◽  
Angela Sciacqua ◽  
Giuseppe Nato ◽  
Francesco Dentali ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Confusion Matrix ◽  
Model Performance ◽  
Support Vector ◽  
Low Weight ◽  
Testing Data ◽  
High Risk Populations ◽  
Thromboembolism Events ◽  
Active Cancer

To realize a machine learning (ML) model to estimate the dose of low molecular weight heparin to be administered, preventing thromboembolism events in COVID-19 patients with active cancer. Methods: We used a dataset comprising 131 patients with active cancer and COVID-19. We considered five ML models: logistic regression, decision tree, random forest, support vector machine and Gaussian naive Bayes. We decided to implement the logistic regression model for our study. A model with 19 variables was analyzed. Data were randomly split into training (70%) and testing (30%) sets. Model performance was assessed by confusion matrix metrics on the testing data for each model as positive predictive value, sensitivity and F1-score. Results: We showed that the five selected models outperformed classical statistical methods of predictive validity and logistic regression was the most effective, being able to classify with an accuracy of 81%. The most relevant result was finding a patient-proof where python function was able to obtain the exact dose of low weight molecular heparin to be administered and thereby to prevent the occurrence of VTE. Conclusions: The world of machine learning and artificial intelligence is constantly developing. The identification of a specific LMWH dose for preventing VTE in very high-risk populations, such as the COVID-19 and active cancer population, might improve with the use of new training ML-based algorithms. Larger studies are needed to confirm our exploratory results.

Beyond Bounding Boxes: Using Bounding Shapes for Real-Time 3D Vehicle Detection from Monocular RGB Images

2019 ◽  
Author(s):  
Nils Gahlert ◽  
Jun-Jun Wan ◽  
Michael Weber ◽  
J. Marius Zollner ◽  
Uwe Franke ◽  
...  
Keyword(s):  
Real Time ◽  
Vehicle Detection ◽  
Rgb Images ◽  
Bounding Boxes
Sign in / Sign up

Export Citation Format

Share Document