scholarly journals Vehicle Interaction Behavior Prediction with Self-Attention

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 429
Author(s):  
Linhui Li ◽  
Xin Sui ◽  
Jing Lian ◽  
Fengning Yu ◽  
Yafu Zhou
Keyword(s):  
Cluster Structure ◽  
Class Imbalance ◽  
Behavior Prediction ◽  
Time To Event ◽  
Future Behavior ◽  
Interaction Behavior ◽  
Proposed Model ◽  
High Interaction ◽  
Fully Connected ◽  
High Uncertainty

The structured road is a scene with high interaction between vehicles, but due to the high uncertainty of behavior, the prediction of vehicle interaction behavior is still a challenge. This prediction is significant for controlling the ego-vehicle. We propose an interaction behavior prediction model based on vehicle cluster (VC) by self-attention (VC-Attention) to improve the prediction performance. Firstly, a five-vehicle based cluster structure is designed to extract the interactive features between ego-vehicle and target vehicle, such as Deceleration Rate to Avoid a Crash (DRAC) and the lane gap. In addition, the proposed model utilizes the sliding window algorithm to extract VC behavior information. Then the temporal characteristics of the three interactive features mentioned above will be caught by two layers of self-attention encoder with six heads respectively. Finally, target vehicle’s future behavior will be predicted by a sub-network consists of a fully connected layer and SoftMax module. The experimental results show that this method has achieved accuracy, precision, recall, and F1 score of more than 92% and time to event of 2.9 s on a Next Generation Simulation (NGSIM) dataset. It accurately predicts the interactive behaviors in class-imbalance prediction and adapts to various driving scenarios.

Attention-based Graph ResNet with focal loss for epileptic seizure detection

2021 ◽  
pp. 1-13
Author(s):  
Changxu Dong ◽  
Yanna Zhao ◽  
Gaobo Zhang ◽  
Mingrui Xue ◽  
Dengyu Chu ◽  
...  
Keyword(s):  
Class Imbalance ◽  
Seizure Detection ◽  
Brain Regions ◽  
Class Imbalance Problem ◽  
Imbalance Problem ◽  
Topological Relationships ◽  
Average Accuracy ◽  
Proposed Model ◽  
Eeg Data ◽  
The Central Nervous System

Epilepsy is a chronic brain disease resulted from the central nervous system lesion, which leads to repeated seizure occurs for the patients. Automatic seizure detection with Electroencephalogram (EEG) has witnessed great progress. However, existing methods paid little attention to the topological relationships of different EEG electrodes. Latest neuroscience researches have demonstrated the connectivity between different brain regions. Besides, class-imbalance is a common problem in EEG based seizure detection. The duration of epileptic EEG signals is much shorter than that of normal signals. In order to deal with the above mentioned two challenges, we propose to model the multi-channel EEG data using the Attention-based Graph ResNet (AGRN). In particular, each channel of the EEG signal represents a node of the graph and the inter-channel relations are modeled via the adjacency matrix in the graph. The loss function of the ARGN model is re-designed using focal loss to cope with the class-imbalance problem. The proposed ARGN with focal model could learn discriminative features from the raw EEG data. Experiments are carried out on the CHB-MIT dataset. The proposed model achieves an average accuracy of 98.70%, a sensitivity of 97.94%, a specificity of 98.66% and a precision of 98.62%. The Area Under the ROC Curve (AUC) is 98.69%.

An Effective Video Surveillance System by using CNN for COVID-19

2022 ◽  
pp. 88-102
Author(s):  
Basetty Mallikarjuna ◽  
Anusha D. J. ◽  
Sethu Ram M. ◽  
Munish Sabharwal
Keyword(s):  
Deep Learning ◽  
Video Surveillance ◽  
Surveillance System ◽  
Video Surveillance System ◽  
Learning Technology ◽  
Proposed Model ◽  
The Social ◽  
Scripting Language ◽  
Python Programming ◽  
Fully Connected

An effective video surveillance system is a challenging task in the COVID-19 pandemic. Building a model proper way of wearing a mask and maintaining the social distance minimum six feet or one or two meters by using CNN approach in the COVID-19 pandemic, the video surveillance system works with the help of TensorFlow, Keras, Pandas, which are libraries used in Python programming scripting language used in the concepts of deep learning technology. The proposed model improved the CNN approach in the area of deep learning and named as the Ram-Laxman algorithm. The proposed model proved to build the optimized approach, the convolutional layers grouped as ‘Ram', and fully connected layers grouped as ‘Laxman'. The proposed system results convey that the Ram-Laxman model is easy to implement in the CCTV footage.

A Framework for Homogeneous Cross-Project Defect Prediction

2021 ◽  
Vol 9 (1) ◽  
pp. 52-68
Author(s):  
Lipika Goel ◽  
Mayank Sharma ◽  
Sunil Kumar Khatri ◽  
D. Damodaran
Keyword(s):  
Class Imbalance ◽  
The Other ◽  
Training Data ◽  
Defect Prediction ◽  
Rank Test ◽  
Ensemble Model ◽  
Class Imbalance Problem ◽  
Imbalance Problem ◽  
Proposed Model ◽  
Cross Project

Often, the prior defect data of the same project is unavailable; researchers thought whether the defect data of the other projects can be used for prediction. This made cross project defect prediction an open research issue. In this approach, the training data often suffers from class imbalance problem. Here, the work is directed on homogeneous cross-project defect prediction. A novel ensemble model that will perform in dual fold is proposed. Firstly, it will handle the class imbalance problem of the dataset. Secondly, it will perform the prediction of the target class. For handling the imbalance problem, the training dataset is divided into data frames. Each data frame will be balanced. An ensemble model using the maximum voting of all random forest classifiers is implemented. The proposed model shows better performance in comparison to the other baseline models. Wilcoxon signed rank test is performed for validation of the proposed model.

scholarly journals A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study

Algorithms ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 273
Author(s):  
Ioannis E. Livieris ◽  
Spiros D. Dafnis ◽  
George K. Papadopoulos ◽  
Dionissios P. Kalivas
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Computational Cost ◽  
Economic Benefits ◽  
Mixed Data ◽  
Cotton Production ◽  
Proposed Model ◽  
Multiple Input ◽  
Fully Connected

Cotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network model for the prediction of cotton’s production. The proposed model utilizes as inputs three different kinds of data (soil data, cultivation management data, and yield management data) which are treated and handled independently. The significant advantages of the selected architecture are that it is able to efficiently exploit mixed data, which usually requires being processed separately, reduces overfitting, and provides more flexibility and adaptivity for low computational cost compared to a classical fully-connected neural network. An empirical study was performed utilizing data from three consecutive years from cotton farms in Central Greece (Thessaly) in which the prediction performance of the proposed model was evaluated against that of traditional neural network-based and state-of-the-art models. The numerical experiments revealed the superiority of the proposed approach.

scholarly journals Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

2020 ◽  
Vol 16 (1) ◽  
pp. 37-45 ◽  
Author(s):  
Ensaf H. Mohamed ◽  
Wessam H. El-Behaidy ◽  
Ghada Khoriba ◽  
Jie Li
Keyword(s):  
Machine Learning ◽  
Blood Cells ◽  
White Blood Cells ◽  
Evaluation Process ◽  
Cell Detection ◽  
Learning Classifier ◽  
Proposed Model ◽  
Higher Rank ◽  
Fully Connected ◽  
Automated Methods

Leukocytes, or white blood cells (WBCs), are microscopic organisms that fight against infectious disease, bacteria, viruses, and others. The manual method to classify and count WBCs is tedious, time-consuming and may has inaccurate results, whereas the automated methods are costly. The objective of this work is to automatically identify and classify WBCs in a microscopic image into four types with higher accuracy. BCCD is the used dataset in this study, which is a scaled down blood cell detection dataset. BCCD is firstly pre-processed by passing through several processes such as segmentation and augmentation,then it is passed to the proposed model. Our model combines the privilege of deep models in automatically extracting features with the higher classification accuracy of traditional machine learning classifiers.The proposed model consists of two main layers; a shallow tuning pre-trained model and a traditional machine learning classifier on top of it. Here, ten different pretrained models with six different machine learning are used in this study. Moreover, the fully connected network (FCN) of pretrained models is used as a baseline classifier for comparison. The evaluation process shows that the hybrid between MobileNet-224 as feature extractor with logistic regression as classifier has a higher rank-1 accuracy with 97.03%. Besides, the proposed hybrid model outperformed the baseline FCN with 25.78% on average.

Challenging the Recognition of Facial Expression via Deep Learning

2014 ◽  
Vol 571-572 ◽  
pp. 717-720
Author(s):  
De Kun Hu ◽  
Yong Hong Liu ◽  
Li Zhang ◽  
Gui Duo Duan
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Back Propagation ◽  
Stochastic Gradient Descent ◽  
Excellent Performance ◽  
Proposed Model ◽  
Input Layer ◽  
Fully Connected

A deep Neural Network model was trained to classify the facial expression in unconstrained images, which comprises nine layers, including input layer, convolutional layer, pooling layer, fully connected layers and output layer. In order to optimize the model, rectified linear units for the nonlinear transformation, weights sharing for reducing the complexity, “mean” and “max” pooling for subsample, “dropout” for sparsity are applied in the forward processing. With large amounts of hard training faces, the model was trained via back propagation method with stochastic gradient descent. The results of shows the proposed model achieves excellent performance.

scholarly journals Personalized Behavior Prediction: An Idiographic Person-Situation Test

2021 ◽  
Author(s):  
Emorie D Beck ◽  
Joshua James Jackson
Keyword(s):  
Prediction Accuracy ◽  
Time Of Day ◽  
Learning Approaches ◽  
Behavior Prediction ◽  
Affective States ◽  
Intensive Longitudinal Data ◽  
Psychological Phenomena ◽  
Diurnal Cycles ◽  
Future Behavior ◽  
Day Of The Week

A longstanding goal of psychology is to predict the things people do, but tools to accurately predict future behaviors remain elusive. In the present study, we used intensive longitudinal data (N = 104; total assessments = 5,971) and three machine learning approaches to investigate the degree to which two behaviors – loneliness and procrastination – could be predicted from past psychological (i.e. personality and affective states), situational (i.e. objective situations and psychological situation cues), and time (i.e. trends, diurnal cycles, time of day, and day of the week) phenomena from an idiographic, person-specific perspective. Rather than pitting persons against situations, such an approach allows psychological phenomena, situations, and time to jointly predict future behavior. We find (1) a striking degree of prediction accuracy across participants, (2) that a majority of participants’ future behaviors are predicted by both person and situation features, and (3) that the most important features vary greatly across people.

scholarly journals COVID-19 County Level Severity Classification with Cl Imbalanced Class: A NearMiss Under-sampling Approach

2021 ◽  
Author(s):  
Timothy Oladunni ◽  
Sourou Tossou ◽  
Yayehyrad Haile ◽  
Adonias Kidane
Keyword(s):  
Class Imbalance ◽  
County Level ◽  
Policy Makers ◽  
Ensemble Models ◽  
Class A ◽  
Proposed Model ◽  
Under Sampling ◽  
Imbalanced Class ◽  
Severity Of The Disease ◽  
Sampling Approach

COVID-19 pandemic that broke out in the late 2019 has spread across the globe. The disease has infected millions of people. Thousands of lives have been lost. The momentum of the disease has been slowed by the introduction of vaccine. However, some countries are still recording high number of casualties. The focus of this work is to design, develop and evaluate a machine learning county level COVID-19 severity classifier. The proposed model will predict severity of the disease in a county into low, moderate, or high. Policy makers will find the work useful in the distribution of vaccines. Four learning algorithms (two ensembles and two non-ensembles) were trained and evaluated. Class imbalance was addressed using NearMiss under-sampling of the majority classes. The result of our experiment shows that the ensemble models outperformed the non-ensemble models by a considerable margin.

scholarly journals Remote Sensing Image Scene Classification Based on Global Self-Attention Module

2021 ◽  
Vol 13 (22) ◽  
pp. 4542
Author(s):  
Qingwen Li ◽  
Dongmei Yan ◽  
Wanrong Wu
Keyword(s):  
Remote Sensing ◽  
Semantic Information ◽  
Remote Sensing Image ◽  
Global Information ◽  
Classification Methods ◽  
Scene Classification ◽  
Local Perception ◽  
Proposed Model ◽  
Public Datasets ◽  
Fully Connected

The complexity of scene images makes the research on remote-sensing image scene classification challenging. With the wide application of deep learning in recent years, many remote-sensing scene classification methods using a convolutional neural network (CNN) have emerged. Current CNN usually output global information by integrating the depth features extricated from the convolutional layer through the fully connected layer; however, the global information extracted is not comprehensive. This paper proposes an improved remote-sensing image scene classification method based on a global self-attention module to address this problem. The global information is derived from the depth characteristics extracted by the CNN. In order to better express the semantic information of the remote-sensing image, the multi-head self-attention module is introduced for global information augmentation. Meanwhile, the local perception unit is utilized to improve the self-attention module’s representation capabilities for local objects. The proposed method’s effectiveness is validated through comparative experiments with various training ratios and different scales on public datasets (UC Merced, AID, and NWPU-NESISC45). The precision of our proposed model is significantly improved compared to other methods for remote-sensing image scene classification.

scholarly journals Deep Learning Models for Pneumonia Identification and Classification Based on X-Ray Images

2021 ◽  
Vol 38 (3) ◽  
pp. 903-909
Author(s):  
Veeranjaneyulu Naralasetti ◽  
Reshmi Khadherbhi Shaik ◽  
Gayatri Katepalli ◽  
Jyostna Devi Bodapati
Keyword(s):  
Experimental Studies ◽  
Cross Entropy ◽  
X Rays ◽  
Weight Decay ◽  
X Ray ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Multi Class Classification ◽  
Fully Connected

Diagnosis based on chest X-rays is widely used and approved for the diagnosis of various diseases such as Pneumonia. Manually screening of theses X-ray images technician or radiologist involves expertise and time consuming. Addressing this, we propose an automated approach for the diagnosis of pneumonia by assisting doctors in spotting infected areas in the X-ray images. We propose a deep Convolutional Neural Network (CNN) model for efficiently detecting the presence of pneumonia in the X-ray images. The proposed CNN is designed with 5 convolution blocks followed by 4 fully connected layers. In order to boost the performance of the model, we incorporate batch normalization, dynamic dropout, learning rate decay, L2 regularization weight decay along with Adam optimizer and binary Cross-Entropy loss function while training the model using back propagating algorithm. The proposed model is validated on two publicly accessible benchmark datasets, and the experimental studies conducted on these datasets indicate that the proposed model is efficient. The suggested CNN architecture with specified hyper parameters allows the model to outperform several existing models by achieving accuracy of 97.73% and 91.17% respectively for binary and multi-class classification tasks of pneumonia disease.

Sign in / Sign up

Export Citation Format

Share Document