• International Journal of Computer Science & Network Security
• /
• 제22권12호
• /
• pp.98-106
• /
• 2022

A condition of the retina known as hypertensive retinopathy (HR) is connected to high blood pressure. The severity and persistence of hypertension are directly correlated with the incidence of HR. To avoid blindness, it is essential to recognize and assess HR as soon as possible. Few computer-aided systems are currently available that can diagnose HR issues. On the other hand, those systems focused on gathering characteristics from a variety of retinopathy-related HR lesions and categorizing them using conventional machine-learning algorithms. Consequently, for limited applications, significant and complicated image processing methods are necessary. As seen in recent similar systems, the preciseness of classification is likewise lacking. To address these issues, a new CAD HR-diagnosis system employing the advanced Deep Dense CNN Learning (DD-CNN) technology is being developed to early identify HR. The HR-diagnosis system utilized a convolutional neural network that was previously trained as a feature extractor. The statistical investigation of more than 1400 retinography images is undertaken to assess the accuracy of the implemented system using several performance metrics such as specificity (SP), sensitivity (SE), area under the receiver operating curve (AUC), and accuracy (ACC). On average, we achieved a SE of 97%, ACC of 98%, SP of 99%, and AUC of 0.98. These results indicate that the proposed DD-CNN classifier is used to diagnose hypertensive retinopathy.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.143-148
• /
• 2022

In this paper, we employ deep neural network (DNN) to discern Android user interaction data distribution from artificial data distribution. We utilize real Android user interaction trace dataset collected from [1] to evaluate our DNN design. In particular, we use sequential model with 4 dense hidden layers and 1 dense output layer in TensorFlow and Keras. We also deploy sigmoid activation function for a dense output layer with 1 neuron and ReLU activation function for each dense hidden layer with 32 neurons. Our evaluation shows that our DNN design fulfills high test accuracy of at least 0.9955 and low test loss of at most 0.0116 in all cases of artificial data distributions.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• 한국컴퓨터정보학회논문지
• /
• 제25권5호
• /
• pp.11-18
• /
• 2020

본 연구는 컨베이어 시스템에서 딥러닝을 이용한 배출구 막힘 판단 기술에 대하여 제안한다. 제안 방법은 산업 현장의 CCTV에서 수집한 영상을 이용하여 배출구 막힘 판단을 위한 다양한 CNN 모델들을 학습시키고, 성능이 가장 좋은 모델을 사용하여 실제 공정에 적용하는 것을 목적으로 한다. CNN 모델로는 잘 알려진 VGGNet, ResNet, DenseNet, 그리고 NASNet을 사용하였으며, 모델 학습과 성능 테스트를 위하여 CCTV에서 수집한 18,000장의 영상을 이용하였다. 다양한 모델에 대한 실험 결과, VGGNet은 99.89%의 정확도와 29.05ms의 처리 시간으로 가장 좋은 성능을 보였으며, 이로부터 배출구 막힘 판단 문제에 VGGNet이 가장 적합함을 확인하였다.

• 전자공학회논문지A
• /
• 제29A권11호
• /
• pp.70-77
• /
• 1992

Generally, the conventional tracking algorithms are very limited in the practical applications because of that the computation load is exponentially increased as the number of targets being tracked is increase. Recently, to overcome this kind of limitation, some new tracking methods based on neural network algorithms which have learning and parallel processing capabilities are introduced. By application of neural networks to multi-target tracking problems, the tracking system can be made computationally independent of the number of objects being tracked, through their characteristics of massive parallelism and dense interconnectivity. In this paper, a new neural network tracking algorithm, which has capability of adaptive target tracking with little increase of the amount of calculation under the clutter and noisy environments, is suggested and the possibility of real-time multi-target tracking system based on neural networks is also demonstrated through some good computer simulation results.

• 한국차세대컴퓨팅학회논문지
• /
• 제14권6호
• /
• pp.66-74
• /
• 2018

최근 가상환경에서 몰입감을 늘리고 자유로운 상호작용을 제공하기 위한 손 제스처 인식에 대한 연구가 활발히 진행되고 있다. 그러나 기존의 연구는 특화된 센서나 장비를 요구하거나, 낮은 인식률을 보이고 있다. 본 논문은 정적 손 제스처와 동적 손 제스처 인식을 위해 카메라 이외의 별도의 센서나 장비 없이 딥러닝 기술을 사용한 손 제스처 인식 방법을 제안한다. 일련의 손 제스처 영상을 고주파 영상으로 변환한 후 손 제스처 RGB 영상들과 이에 대한 고주파 영상들 각각에 대해 덴스넷 3차원 합성곱 신경망을 통해 학습한다. 6개의 정적 손 제스처와 9개의 동적 손 제스처 인터페이스에 대해 실험한 결과 기존 덴스넷에 비해 4.6%의 성능이 향상된 평균 92.6%의 인식률을 보였다. 본 연구결과를 검증하기 위하여 3D 디펜스 게임을 구현한 결과 평균 34ms로 제스처 인식이 가능하여 가상현실 응용의 실시간 사용자 인터페이스로 사용가능함을 알 수 있었다.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.58-67
• /
• 2020

In this paper, we propose a data-driven-based beam selection scheme for massive multiple-input and multiple-output (MIMO) systems in ultra-dense networks (UDN), which is capable of addressing the problem of high computational cost of conventional coordinated beamforming approaches. We consider highly dense small-cell scenarios with more small cells than mobile stations, in the millimetre-wave band. The analog beam selection for hybrid beamforming is a key issue in realizing millimetre-wave UDN MIMO systems. To reduce the computation complexity for the analog beam selection, in this paper, two deep neural network models are used. The channel samples, channel gains, and radio frequency beamforming vectors between the access points and mobile stations are collected at the central/cloud unit that is connected to all the small-cell access points, and are used to train the networks. The proposed machine-learning-based scheme provides an approach for the effective implementation of massive MIMO system in UDN environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.498-500
• /
• 2019

Point cloud is a flexible set of points that can provide a scalable geometric representation which can be applied in different computer graphic task. We propose a method based on EdgeConv and densely connected layers to aggregate the features for better classification. Our proposed approach shows significant performance improvement compared to the state-of-the-art deep neural network-based approaches.