Deteksi Arteri Karotis pada Citra Ultrasound B-Mode Berbasis Convolution Neural Network Single Shot Multibox Detector

Detection of vascular areas (blood vessels) using B-Mode ultrasound images is needed for automatic applications such as registration and navigation in medical operations. This study developed the detection of the carotid artery area using Convolution Neural Network Single Shot Network Multibox Detector (SSD) to determine the bounding box ROI of the carotid artery area in B-mode ultrasound images. The data used are B-Mode ultrasound images on the neck that contain the carotid artery area (primary data). SSD method result is 95% of accuracy which is higher than the Hough transformation method, Ellipse method, and Faster RCNN in detecting carotid artery area in the B-Mode ultrasound image. The use of image enhancement with Gaussian filter, histogram equalization, and Median filters in this method can increase detection accuracy. The best process time of the proposed method is 2.09 seconds so that it can be applied in a real-time system.

Download Full-text

CXR-RefineDet: Single-Shot Refinement Neural Network for Chest X-Ray Radiograph Based on Multiple Lesions Detection

Journal of Healthcare Engineering ◽

10.1155/2022/4182191 ◽

2022 ◽

Vol 2022 ◽

pp. 1-11

Author(s):

Cong Lin ◽

Yongbin Zheng ◽

Xiuchun Xiao ◽

Jialun Lin

Keyword(s):

Neural Network ◽

Object Detection ◽

Disease Diagnosis ◽

Detection Algorithm ◽

Detection Accuracy ◽

Single Shot ◽

Detection Model ◽

Network Output ◽

Artificial Intelligence Technology ◽

Chest X Ray

The workload of radiologists has dramatically increased in the context of the COVID-19 pandemic, causing misdiagnosis and missed diagnosis of diseases. The use of artificial intelligence technology can assist doctors in locating and identifying lesions in medical images. In order to improve the accuracy of disease diagnosis in medical imaging, we propose a lung disease detection neural network that is superior to the current mainstream object detection model in this paper. By combining the advantages of RepVGG block and Resblock in information fusion and information extraction, we design a backbone RRNet with few parameters and strong feature extraction capabilities. After that, we propose a structure called Information Reuse, which can solve the problem of low utilization of the original network output features by connecting the normalized features back to the network. Combining the network of RRNet and the improved RefineDet, we propose the overall network which was called CXR-RefineDet. Through a large number of experiments on the largest public lung chest radiograph detection dataset VinDr-CXR, it is found that the detection accuracy and inference speed of CXR-RefineDet have reached 0.1686 mAP and 6.8 fps, respectively, which is better than the two-stage object detection algorithm using a strong backbone like ResNet-50 and ResNet-101. In addition, the fast reasoning speed of CXR-RefineDet also provides the possibility for the actual implementation of the computer-aided diagnosis system.

Download Full-text

Detection, Classification and Boundary Regularization of Buildings in Satellite Imagery Using Faster Edge Region Convolutional Neural Networks

Remote Sensing ◽

10.3390/rs12142240 ◽

2020 ◽

Vol 12 (14) ◽

pp. 2240

Author(s):

Kinga Reda ◽

Michal Kedzierski

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Urban Areas ◽

Future Research ◽

Detection Accuracy ◽

Single Shot ◽

Building Detection ◽

Edge Region ◽

Additional Advantage

With the development of effective deep learning algorithms, it became possible to achieve high accuracy when conducting remote sensing analyses on very high-resolution images (VHRS), especially in the context of building detection and classification. In this article, in order to improve the accuracy of building detection and classification, we propose a Faster Edge Region Convolutional Neural Networks (FER-CNN) algorithm. This proposed algorithm is trained and evaluated on different datasets. In addition, we propose a new method to improve the detection of the boundaries of detected buildings. The results of our algorithm are compared with those of other methods, such as classical Faster Region Convolution Neural Network (Faster R-CNN) with the original VGG16 and the Single-Shot Multibox Detector (SSD). The experimental results show that our methods make it possible to obtain an average detection accuracy of 97.5% with a false positive classification rate of 8.4%. An additional advantage of our method is better resistance to shadows, which is a very common issue for satellite images of urban areas. Future research will include designing and training the neural network to detect small buildings, as well as irregularly shaped buildings that are partially obscured by shadows or other occlusions.

Download Full-text

Optimal Feature Selection for Carotid Artery Image Segmentation Using Evolutionary Computation

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.626.79 ◽

2014 ◽

Vol 626 ◽

pp. 79-86 ◽

Cited By ~ 1

Author(s):

I. Mohammed Farook ◽

S. Dhanalakshmi ◽

V. Manikandan ◽

C. Venkatesh

Keyword(s):

Neural Network ◽

Carotid Artery ◽

Ultrasound Image ◽

Intima Media Thickness ◽

Ultrasound Images ◽

Gray Level ◽

Genetic Search ◽

Heart Attacks ◽

Hilbert Huang Transform ◽

Occurrence Matrix

Atherosclerosis is hardening of arteries due to high blood pressure and high cholesterol. It causes heart attacks, stroke and peripheral vascular disease and is the major cause of death. In this paper we have attempted a method to identify the presence of plaque in carotid artery from ultrasound images. The ultrasound image is segmented using improved spatial Fuzzy c means algorithm to identify the presence of plaque in carotid artery. Spatial wavelet, Hilbert Huang Transform (HHT), Moment of Gray Level Histogram (MGLH) and Gray Level Co-occurrence Matrix (GLCM) features are extracted from ultrasound images and the feature set is reduced using genetic search process. The intima media thickness is measured using the proposed method. The IMT values are measured from the segmented image and trained using MLBPNN neural network. The neural network classifies the images into normal and abnormal.

Download Full-text

Design of Secure Blockchain Convolution Neural Network Architecture for Detection Malware Attacks

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.f8094.038620 ◽

2020 ◽

Vol 8 (6) ◽

pp. 3055-3060

Keyword(s):

Neural Network ◽

Deep Learning ◽

Network Architecture ◽

Information Privacy ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Neural Network Architecture ◽

Network Method ◽

Advance Method ◽

Learning Concept

Nowadays, Cyberattack continues to target the applications and networks more than past with different and advance ways like programming complex format of malware that it executes unauthorized action on the targeted system, so it is needed to develop and deploy advance method to these kind of attacks for detecting correctly with a trusted and a better accuracy. Therefore, the recent solutions to detect malware attacks focuses on new advance technologies like Deep learning and Machine learning concepts. In this paper we have developed secure blockchain convolution (SBC) Algorithm that provides a better way of analyzing malware data with effectiveness and accuracy. The deep learning concept does not involve in a method to identify the trust while the process is led to extraction of the features as it can be infected by the intervention of human or a trained system. Therefore, According to research which is done towards blockchain, it features as authentication function, immutable property, information privacy and safety helps in deployment of Convolution Neural Network method with better detection. Blockchain has a decentralized structure which is able to record the data between various parties and it helps in preventing the manipulation when the deep learning concept is applied and the higher detection accuracy is received in the limited time.

Download Full-text

Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

Remote Sensing ◽

10.3390/rs11212483 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2483 ◽

Cited By ~ 15

Author(s):

Zhang ◽

Shi ◽

Wei

Keyword(s):

Neural Network ◽

Real Time ◽

Network Architecture ◽

High Speed ◽

Fishery Management ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Ship Detection ◽

Military Planning ◽

Detection Speed

As an active microwave imaging sensor for the high-resolution earth observation, synthetic aperture radar (SAR) has been extensively applied in military, agriculture, geology, ecology, oceanography, etc., due to its prominent advantages of all-weather and all-time working capacity. Especially, in the marine field, SAR can provide numerous high-quality services for fishery management, traffic control, sea-ice monitoring, marine environmental protection, etc. Among them, ship detection in SAR images has attracted more and more attention on account of the urgent requirements of maritime rescue and military strategy formulation. Nowadays, most researches are focusing on improving the ship detection accuracy, while the detection speed is frequently neglected, regardless of traditional feature extraction methods or modern deep learning (DL) methods. However, the high-speed SAR ship detection is of great practical value, because it can provide real-time maritime disaster rescue and emergency military planning. Therefore, in order to address this problem, we proposed a novel high-speed SAR ship detection approach by mainly using depthwise separable convolution neural network (DS-CNN). In this approach, we integrated multi-scale detection mechanism, concatenation mechanism and anchor box mechanism to establish a brand-new light-weight network architecture for the high-speed SAR ship detection. We used DS-CNN, which consists of a depthwise convolution (D-Conv2D) and a pointwise convolution (P-Conv2D), to substitute for the conventional convolution neural network (C-CNN). In this way, the number of network parameters gets obviously decreased, and the ship detection speed gets dramatically improved. We experimented on an open SAR ship detection dataset (SSDD) to validate the correctness and feasibility of the proposed method. To verify the strong migration capacity of our method, we also carried out actual ship detection on a wide-region large-size Sentinel-1 SAR image. Ultimately, under the same hardware platform with NVIDIA RTX2080Ti GPU, the experimental results indicated that the ship detection speed of our proposed method is faster than other methods, meanwhile the detection accuracy is only lightly sacrificed compared with the state-of-art object detectors. Our method has great application value in real-time maritime disaster rescue and emergency military planning.

Download Full-text

Fault Detection Method of Power Insulator Based on Deep Convolution Neural Network

Distributed Generation & Alternative Energy Journal ◽

10.13052/dgaej2156-3306.3621 ◽

2021 ◽

Author(s):

Yan Wang ◽

Weijie Zhang

Keyword(s):

Neural Network ◽

Fault Detection ◽

Detection Method ◽

Convolution Neural Network ◽

Detection Methods ◽

Detection Accuracy ◽

Region Selection ◽

Function Design ◽

Deep Convolution Neural Network ◽

Anchor Design

Aiming at the problem of low detection accuracy of traditional power insulator fault detection methods, a power insulator fault detection method based on deep convolution neural network is designed. For the training of deep convolution neural network, the fault detection of power insulator based on deep convolution neural network is realized by anchor design, loss function design, candidate region selection mechanism establishment and sharing convolution features. The experimental results show that the fault detection method of power insulator based on deep convolution neural network is more accurate than the traditional method, and the detection time is less.

Download Full-text

IoT-based intrusion detection system using convolution neural networks

PeerJ Computer Science ◽

10.7717/peerj-cs.721 ◽

2021 ◽

Vol 7 ◽

pp. e721

Author(s):

Abdullah Aljumah

Keyword(s):

Neural Network ◽

Deep Learning ◽

Intrusion Detection ◽

Intrusion Detection System ◽

Detection System ◽

Machine Learning Algorithms ◽

Convolution Neural Network ◽

Data Repository ◽

Detection Accuracy ◽

Data Traffic

In the Information and Communication Technology age, connected objects generate massive amounts of data traffic, which enables data analysis to uncover previously hidden trends and detect unusual network-load. We identify five core design principles to consider when designing a deep learning-empowered intrusion detection system (IDS). We proposed the Temporal Convolution Neural Network (TCNN), an intelligent model for IoT-IDS that aggregates convolution neural network (CNN) and generic convolution, based on these concepts. To handle unbalanced datasets, TCNN is accumulated with synthetic minority oversampling technique with nominal continuity. It is also used in conjunction with effective feature engineering techniques like attribute transformation and reduction. The presented model is compared to two traditional machine learning algorithms, random forest (RF) and logistic regression (LR), as well as LSTM and CNN deep learning techniques, using the Bot-IoT data repository. The outcomes of the experiments depicts that TCNN maintains a strong balance of efficacy and performance. It is better as compared to other deep learning IDSs, with a multi-class traffic detection accuracy of 99.9986 percent and a training period that is very close to CNN.

Download Full-text

Lane marking detection and classification with combined deep neural network for driver assistance

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering ◽

10.1177/0954407018768659 ◽

2018 ◽

Vol 233 (5) ◽

pp. 1259-1268 ◽

Cited By ~ 2

Author(s):

Weiwei Zhang ◽

Hui Liu ◽

Xuncheng Wu ◽

Lingyun Xiao ◽

Yubin Qian ◽

...

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Lane Detection ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Lane Marking ◽

Fitting Method ◽

Boundary Fitting ◽

The Time Domain ◽

Continuous Frames

An efficient approach for lane marking detection and classification by the combination of convolution neural network and recurrent neural network is proposed in this paper. First, convolution neural network is trained for lane marking features extraction, and then these convolution neural network features of continuous frames are transferred to recurrent neural network model for lane boundary detection and classification in the time domain. At last, a lane boundary fitting method based on dynamic programming is proposed to improve the lane detection accuracy and robustness. The method presented generates satisfactory results of lane detection and type classification under various traffic conditions according to the experimental results, which show that the approach provided in this paper outperforms traditional methods and the total lane markings classification reached 95.21% accuracy.

Download Full-text

Application of Spatio-Temporal Context and Convolution Neural Network (CNN) in Grooming Behavior of Bactrocera minax (Diptera: Trypetidae) Detection and Statistics

Insects ◽

10.3390/insects11090565 ◽

2020 ◽

Vol 11 (9) ◽

pp. 565

Author(s):

Zhiliang Zhang ◽

Wei Zhan ◽

Zhangzhang He ◽

Yafeng Zou

Keyword(s):

Neural Network ◽

Insect Behavior ◽

Convolution Neural Network ◽

Temporal Context ◽

Detection Accuracy ◽

Grooming Behavior ◽

Behavior Detection ◽

Detection Model ◽

Spatio Temporal ◽

The Difference

Statistical analysis and research on insect grooming behavior can find more effective methods for pest control. Traditional manual insect grooming behavior statistical methods are time-consuming, labor-intensive, and error-prone. Based on computer vision technology, this paper uses spatio-temporal context to extract video features, uses self-built Convolution Neural Network (CNN) to train the detection model, and proposes a simple and effective Bactrocera minax grooming behavior detection method, which automatically detects the grooming behaviors of the flies and analysis results by a computer program. Applying the method training detection model proposed in this paper, the videos of 22 adult flies with a total of 1320 min of grooming behavior were detected and analyzed, and the total detection accuracy was over 95%, the standard error of the accuracy of the behavior detection of each adult flies was less than 3%, and the difference was less than 15% when compared with the results of manual observation. The experimental results show that the method in this paper greatly reduces the time of manual observation and at the same time ensures the accuracy of insect behavior detection and analysis, which proposes a new informatization analysis method for the behavior statistics of Bactrocera minax and also provides a new idea for related insect behavior identification research.

Download Full-text

Exploring Underwater Target Detection Algorithm Based on Improved SSD

Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University ◽

10.1051/jnwpu/20203840747 ◽

2020 ◽

Vol 38 (4) ◽

pp. 747-754

Author(s):

Wei Qiang ◽

Yuyao He ◽

Yujin Guo ◽

Baoqi Li ◽

Lingjiao He

Keyword(s):

Neural Network ◽

Target Detection ◽

Detection Algorithm ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Detection Model ◽

Underwater Environment ◽

Underwater Target Detection ◽

Basic Network ◽

Underwater Target

As the in-depth exploration of oceans continues, the accurate and rapid detection of fish, bionics and other intelligent bodies in an underwater environment is more and more important for improving an underwater defense system. Because of the low accuracy and poor real-time performance of target detection in the complex underwater environment, we propose a target detection algorithm based on the improved SSD. We use the ResNet convolution neural network instead of the VGG convolution neural network of the SSD as the basic network for target detection. In the basic network, the depthwise-separated deformable convolution module proposed in this paper is used to extract the features of an underwater target so as to improve the target detection accuracy and speed in the complex underwater environment. It mainly fuses the depthwise separable convolution when the deformable convolution acquires the offset of a convolution core, thus reducing the number of parameters and achieving the purposes of increasing the speed of the convolution neural network and enhancing its robustness through sparse representation. The experimental results show that, compared with the SSD detection model that uses the ResNet convolution neural network as the basic network, the improved SSD detection model that uses the depthwise-separated deformable convolution module improves the accuracy of underwater target detection by 11 percentage points and reduces the detection time by 3 ms, thus validating the effectiveness of the algorithm proposed in the paper.

Download Full-text