• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.85-90
• /
• 2021

In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models' validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.290-306
• /
• 2024

To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transferlearning methodology and a multilabel convolutional neural network for COVID (MLCNN-COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer-learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN-COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three-dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN-COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer-learning model's performance. It shows that three-dimensional conformers adequately identify negative COVID medicine responses.

• Journal of Cadastre & Land InformatiX
• /
• v.48 no.2
• /
• pp.213-225
• /
• 2018

For constructing three-dimensional (3D) spatial information occlusion region problem arises in the process of taking the texture of the building. In order to solve this problem, it is necessary to investigate the automation method to automatically recognize the occlusion region, issue it, and automatically complement the texture. In fact there are occasions when it is possible to generate a very large number of structures and occlusion, so alternatives to overcome are being considered. In this study, we attempt to apply an approach to automatically create an occlusion region based on learning by patterning the blocked region using the recently emerging deep learning algorithm. Experiment to see the performance automatic detection of people, banners, vehicles, and traffic lights that cause occlusion in building walls using two advanced algorithms of Convolutional Neural Network (CNN) technique, Faster Region-based Convolutional Neural Network (R-CNN) and Mask R-CNN. And the results of the automatic detection by learning the banners in the pre-learned model of the Mask R-CNN method were found to be excellent.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.420-437
• /
• 2024

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.