Detection of Atrial Fibrillation Using 1D Convolutional Neural Network

The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which results in heavy training computation and high implementation cost. This paper proposes an AF detection method based on an end-to-end 1D convolutional neural network (CNN) architecture to raise the detection accuracy and reduce network complexity. By investigating the impact of major components of a convolutional block on detection accuracy and using grid search to obtain optimal hyperparameters of the CNN, we develop a simple, yet effective 1D CNN. Since the dataset provided by PhysioNet Challenge 2017 contains ECG recordings with different lengths, we also propose a length normalization algorithm to generate equal-length records to meet the requirement of CNN. Experimental results and analysis indicate that our method of 1D CNN achieves an average F1 score of 78.2%, which has better detection accuracy with lower network complexity, as compared with the existing deep learning-based methods.

Download Full-text

Convolutional Neural Network Using Kalman Filter for Human Detection and Tracking on RGB-D Video

CommIT (Communication and Information Technology) Journal ◽

10.21512/commit.v12i2.4890 ◽

2018 ◽

Vol 12 (2) ◽

pp. 105 ◽

Cited By ~ 1

Author(s):

Jovin Angelico ◽

Ken Ratri Retno Wardani

Keyword(s):

Neural Network ◽

Kalman Filter ◽

Convolutional Neural Network ◽

Human Detection ◽

Detection Accuracy ◽

Tracking Accuracy ◽

Lighting Condition ◽

Detection And Tracking ◽

Computation Efficiency ◽

The Impact

The computer ability to detect human being by computer vision is still being improved both in accuracy or computation time. In low-lighting condition, the detection accuracy is usually low. This research uses additional information, besides RGB channels, namely a depth map that shows objects’ distance relative to the camera. This research integrates Cascade Classifier (CC) to localize the potential object, the Convolutional Neural Network (CNN) technique to identify the human and nonhuman image, and the Kalman filter technique to track human movement. For training and testing purposes, there are two kinds of RGB-D datasets used with different points of view and lighting conditions. Both datasets have been selected to remove images which contain a lot of noises and occlusions so that during the training process it will be more directed. Using these integrated techniques, detection and tracking accuracy reach 77.7%. The impact of using Kalman filter increases computation efficiency by 41%.

Download Full-text

P-Wave Detection Using a Fully Convolutional Neural Network in Electrocardiogram Images

Applied Sciences ◽

10.3390/app10030976 ◽

2020 ◽

Vol 10 (3) ◽

pp. 976

Author(s):

Rana N. Costandy ◽

Safa M. Gasser ◽

Mohamed S. El-Mahallawy ◽

Mohamed W. Fakhr ◽

Samir Y. Marzouk

Keyword(s):

Neural Network ◽

Atrial Fibrillation ◽

Convolutional Neural Network ◽

P Wave ◽

Ecg Signal ◽

P Waves ◽

Ecg Signals ◽

Wave Detection ◽

Automated Algorithm ◽

Electrocardiogram Ecg

Electrocardiogram (ECG) signal analysis is a critical task in diagnosing the presence of any cardiac disorder. There are limited studies on detecting P-waves in various atrial arrhythmias, such as atrial fibrillation (AFIB), atrial flutter, junctional rhythm, and other arrhythmias due to P-wave variability and absence in various cases. Thus, there is a growing need to develop an efficient automated algorithm that annotates a 2D printed version of P-waves in the well-known ECG signal databases for validation purposes. To our knowledge, no one has annotated P-waves in the MIT-BIH atrial fibrillation database. Therefore, it is a challenge to manually annotate P-waves in the MIT-BIH AF database and to develop an automated algorithm to detect the absence and presence of different shapes of P-waves. In this paper, we present the manual annotation of P-waves in the well-known MIT-BIH AF database with the aid of a cardiologist. In addition, we provide an automatic P-wave segmentation for the same database using a fully convolutional neural network model (U-Net). This algorithm works on 2D imagery of printed ECG signals, as this type of imagery is the most commonly used in developing countries. The proposed automatic P-wave detection method obtained an accuracy and sensitivity of 98.56% and 98.78%, respectively, over the first 5 min of the second lead of the MIT-BIH AF database (a total of 8280 beats). Moreover, the proposed method is validated using the well-known automatically and manually annotated QT database (a total of 11,201 and 3194 automatically and manually annotated beats, respectively). This results in accuracies of 98.98 and 98.9%, and sensitivities of 98.97 and 97.24% for the automatically and manually annotated QT databases, respectively. Thus, these results indicate that the proposed automatic method can be used for analyzing long-printed ECG signals on mobile battery-driven devices using only images of the ECG signals, without the need for a cardiologist.

Download Full-text

Research on Flame Combustion Stability Based on Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.516-517.390 ◽

2012 ◽

Vol 516-517 ◽

pp. 390-394

Author(s):

Gui Zhi Bai ◽

Li Hong Zhang ◽

Shu Qian Chen

Keyword(s):

Neural Network ◽

Detection Method ◽

Combustion Stability ◽

Detection Methods ◽

Detection Accuracy ◽

Multiple Features ◽

Flame Combustion ◽

Flame Pulsation ◽

Neural Network Input ◽

The Impact

For the use of boiler flame image analysis to detect the boiler flame combustion stability, when the combustion affected by coal, peaking , improper operation or other effects, the flame appeared short pulsation. In general, the traditional detection methods based on gray scale variance can not avoid the impact of flame pulsation on account of the inaccuracy of the boiler combustion stability detection. This paper presents a flame combustion instability detection method based on neural network and selects multiple features which are directly related to the flame stability as neural network input vector. Experiments show that this method can fight off the tiny ripple influence caused by the impurities combustion or peak and simultaneously, greatly improve the detection accuracy and stability.

Download Full-text

Identifikasi Kemurnian Daging Berbasis Analisis Citra

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.0813307 ◽

2021 ◽

Vol 8 (4) ◽

pp. 643

Author(s):

Nila Susila Yulianti ◽

Kudang Boro Seminar ◽

Joko Hermanianto ◽

Sri Wahjuni

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Wild Boar ◽

Detection System ◽

Detection Methods ◽

Population Census ◽

Muslim Population ◽

Image Deformation ◽

Long Time ◽

Wild Boar Meat

Daging sapi merupakan salah satu sumber protein hewani yang diperlukan oleh tubuh. Pada tahun 2015 dan 2016 konsumsi daging sapi per kapita sebesar 0,417 kg dan terjadi kenaikan pada tahun 2017 yaitu 12,50 % sebesar 0,469 kg. Sementara harga rata-rata daging sapi di tahun 2015 sebesar Rp 104 747 per kg dan mengalami kenaikan pada tahun 2016 yaitu 8,41 % sebesar Rp 113 555 per kg. Di tahun 2017 kembali terjadi kenaikan yaitu 2,09 % sebesar 115 932 per kg. Berdasarkan sensus penduduk tahun 2010 mendata jumlah penduduk muslim sebesar 207176162 yaitu 87 % dari total penduduk di Indonesia. Kekhawatiran daging halal sangat penting di negara mayoritas muslim. Metode secara konvensional dengan uji laboratorium untuk mendeteksi daging celeng membutuhkan waktu yang relatif lama, tempat khusus, serta biaya yang relatif mahal. Sementara daging yang diwaspadai dicampur dengan daging babi hutan bisa terjadi di berbagai tempat seperti pasar, retailer serta distributor yang sepatutnya bisa dideteksi seketika di tempat tersebut secara cepat. Oleh karena itu, diperlukan sistem yang mudah, cepat, dan mudah dibawa untuk mendeteksi daging sapi murni (tanpa campuran daging lainnya) dalam penelitian ini adalah daging celeng.Paper ini membahas metode deteksi daging campuran berbasis citra menggunakan Convolutional Neural Network (CNN) yang dapat dioperasikan di android. Keunggulan metode ini dapat melakukan proses pembelajaran secara mandiri yaitu ekstraksi citra dan klasifikasi, adapun kemampuan lain yang dimiliki yaitu dapat menangani deformasi gambar seperti translasi, rotasi dan skala. Akurasi yang didapatkan dari metode ini yaitu 94 % untuk mendeteksi daging sapi murni, daging celeng murni, dan daging campuran sapi dan celeng. Sementara presisi untuk celeng, campuran dan sapi yaitu 100 %, 90 % dan 95 %. Selain itu, recall untuk celeng, campuran dan sapi yaitu 85 %, 95 %, dan 97,5 %. Prototipe sistem deteksi yang dikembangkan telah diimplementasikan pada platform android dan diuji pada situasi pencahayaan yang masih terkondisikan. Upaya penyempurnaan ke depan adalah menambah fitur sistem pencahayaan khusus/standar dengan kamera khusus yang memiliki cahaya tambahan yang mengatasi keragaman tingkat pencahayaan di tempat terbuka. AbstractBeef is one of animal protein source that important for human body. In 2015 and 2016 beef consumption per capita was 0.417 kg and it was increasing in 2017 by 12.50 % (i.e., 0.469 kg). While The average price of beef at Rp 104 747 per kg in 2015 and went up by 8,41 % at Rp 113 555 per kg in 2016. In 2017, there was an increase by 2,09 % at Rp 115 932 per kg. The increase of beef price average occurred in 2015 amounting to Rp 104 747 per kg and an increase in 2016 that was 8.41% amounting to Rp 113 555 per kg. Based on the population census in 2010 recorded a Muslim population of 207176162 which is 87% of the total population in Indonesia. The concern of halal (lawful) meat is very critical in the muslim majority country. The conventional method with laboratory testing to detect wild boar meat requires a relatively long time, a special place, and a relatively expensive cost. While meat that is mixed with wild boar can happen in various places such as markets, retailers and distributors which can be detected immediately in that place quickly.Therefore, a system that can be easily, quickly and portably used for detecting pure beef (without other mixed meat) in this study is wild boar. This paper discusses image-based mixed meat detection methods using the Convolutional Neural Network (CNN) that can be operated on android. so the proposed computationally method is Convolutional Neural Network (CNN). The advantages of this method can do the learning process independently, object extraction and classification, while the other capabilities that can handle image deformation such as translation, rotation, and scale. This method yields an overall accuracy of 94% for detecting pure beef, pure wild boar meat, and mixed beef and wild boar. The obtained precision values for wild boar, mixed meat and beef are by 100 %, 90 % and 95 % respectively. Moreover, the values recall for wild boar, mixed meat and beef are by 85 %, 95 % and 97,5 % respectively. The prototype detection system developed has been implemented on the Android platform and tested in a lighting situation that is still conditioned. A future effort to improve is providing special / standard lighting with a special camera that has additional light that can overcome the diversity of levels of exposure in the open areas.

Download Full-text

Deep convolutional neural networks for human movement detection using wireless signals

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189629 ◽

2021 ◽

pp. 1-10

Author(s):

Chien-Cheng Leea ◽

Zhongjian Gao ◽

Xiu-Chi Huanga

Keyword(s):

Neural Network ◽

Feature Extraction ◽

Convolutional Neural Network ◽

Detection System ◽

Deep Convolutional Neural Network ◽

Human Detection ◽

Two Dimensional ◽

Dimensional Matrix ◽

State Classification ◽

Propagation Paths

This paper proposes a Wi-Fi-based indoor human detection system using a deep convolutional neural network. The system detects different human states in various situations, including different environments and propagation paths. The main improvements proposed by the system is that there is no cameras overhead and no sensors are mounted. This system captures useful amplitude information from the channel state information and converts this information into an image-like two-dimensional matrix. Next, the two-dimensional matrix is used as an input to a deep convolutional neural network (CNN) to distinguish human states. In this work, a deep residual network (ResNet) architecture is used to perform human state classification with hierarchical topological feature extraction. Several combinations of datasets for different environments and propagation paths are used in this study. ResNet’s powerful inference simplifies feature extraction and improves the accuracy of human state classification. The experimental results show that the fine-tuned ResNet-18 model has good performance in indoor human detection, including people not present, people still, and people moving. Compared with traditional machine learning using handcrafted features, this method is simple and effective.

Download Full-text

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01571-1 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Bambang Tutuko ◽

Siti Nurmaini ◽

Alexander Edo Tondas ◽

Muhammad Naufal Rachmatullah ◽

Annisa Darmawahyuni ◽

...

Keyword(s):

Neural Network ◽

Atrial Fibrillation ◽

Convolutional Neural Network ◽

Learning System ◽

Single Frequency ◽

Feature Maps ◽

Normal Sinus ◽

Unseen Data ◽

Specific Device ◽

Model Formation

Abstract Background Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity. Result Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity. Conclusion These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment

Download Full-text

Anomaly Detection Using Deep Neural Network for IoT Architecture

Applied Sciences ◽

10.3390/app11157050 ◽

2021 ◽

Vol 11 (15) ◽

pp. 7050

Author(s):

Zeeshan Ahmad ◽

Adnan Shahid Khan ◽

Kashif Nisar ◽

Iram Haider ◽

Rosilah Hassan ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Anomaly Detection ◽

Deep Neural Network ◽

Detection System ◽

Traffic Monitoring ◽

Detection Accuracy ◽

Learning Models ◽

Prime Concern ◽

Entry Points

The revolutionary idea of the internet of things (IoT) architecture has gained enormous popularity over the last decade, resulting in an exponential growth in the IoT networks, connected devices, and the data processed therein. Since IoT devices generate and exchange sensitive data over the traditional internet, security has become a prime concern due to the generation of zero-day cyberattacks. A network-based intrusion detection system (NIDS) can provide the much-needed efficient security solution to the IoT network by protecting the network entry points through constant network traffic monitoring. Recent NIDS have a high false alarm rate (FAR) in detecting the anomalies, including the novel and zero-day anomalies. This paper proposes an efficient anomaly detection mechanism using mutual information (MI), considering a deep neural network (DNN) for an IoT network. A comparative analysis of different deep-learning models such as DNN, Convolutional Neural Network, Recurrent Neural Network, and its different variants, such as Gated Recurrent Unit and Long Short-term Memory is performed considering the IoT-Botnet 2020 dataset. Experimental results show the improvement of 0.57–2.6% in terms of the model’s accuracy, while at the same time reducing the FAR by 0.23–7.98% to show the effectiveness of the DNN-based NIDS model compared to the well-known deep learning models. It was also observed that using only the 16–35 best numerical features selected using MI instead of 80 features of the dataset result in almost negligible degradation in the model’s performance but helped in decreasing the overall model’s complexity. In addition, the overall accuracy of the DL-based models is further improved by almost 0.99–3.45% in terms of the detection accuracy considering only the top five categorical and numerical features.

Download Full-text

Automatic Handgun Detection with Deep Learning in Video Surveillance Images

Applied Sciences ◽

10.3390/app11136085 ◽

2021 ◽

Vol 11 (13) ◽

pp. 6085

Author(s):

Jesus Salido ◽

Vanesa Lomas ◽

Jesus Ruiz-Santaquiteria ◽

Oscar Deniz

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Video Surveillance ◽

Automatic Detection ◽

Public Spaces ◽

Detection Methods ◽

Training Dataset ◽

Average Precision ◽

Terrorist Acts

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.

Download Full-text

Utilizing a convolutional neural network to predict HIV-1 Tat biological functions and the impact of Tat genetic variation on neurocognitive impairment

10.17918/t3e4-8w38 ◽

2021 ◽

Author(s):

Angela Tomita

Keyword(s):

Neural Network ◽

Genetic Variation ◽

Convolutional Neural Network ◽

Neurocognitive Impairment ◽

Biological Functions ◽

The Impact ◽

Hiv 1

Download Full-text

Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network

Sensors ◽

10.3390/s18072327 ◽

2018 ◽

Vol 18 (7) ◽

pp. 2327 ◽

Cited By ~ 14

Author(s):

Jinsong Zhang ◽

Wenjie Xing ◽

Mengdao Xing ◽

Guangcai Sun

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Detection System ◽

Terahertz Imaging ◽

Image Detection ◽

Data Format ◽

Standard Data ◽

Concealed Weapons ◽

Special Distribution ◽

Effectiveness And Efficiency

In recent years, terahertz imaging systems and techniques have been developed and have gradually become a leading frontier field. With the advantages of low radiation and clothing-penetrable, terahertz imaging technology has been widely used for the detection of concealed weapons or other contraband carried on personnel at airports and other secure locations. This paper aims to detect these concealed items with deep learning method for its well detection performance and real-time detection speed. Based on the analysis of the characteristics of terahertz images, an effective detection system is proposed in this paper. First, a lots of terahertz images are collected and labeled as the standard data format. Secondly, this paper establishes the terahertz classification dataset and proposes a classification method based on transfer learning. Then considering the special distribution of terahertz image, an improved faster region-based convolutional neural network (Faster R-CNN) method based on threshold segmentation is proposed for detecting human body and other objects independently. Finally, experimental results demonstrate the effectiveness and efficiency of the proposed method for terahertz image detection.

Download Full-text