scholarly journals Artificial Intelligence-Enabled ECG Algorithm Based on Improved Residual Network for Wearable ECG

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6043
Author(s):  
Hongqiang Li ◽  
Zhixuan An ◽  
Shasha Zuo ◽  
Wei Zhu ◽  
Zhen Zhang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Sinus Bradycardia ◽  
Recognition Rate ◽  
Mobile Terminal ◽  
Activation Function ◽  
Ventricular Premature Beat ◽  
Residual Network ◽  
Ecg Signals ◽  
Average Recognition Rate ◽  
Residual Block

Heart disease is the leading cause of death for men and women globally. The residual network (ResNet) evolution of electrocardiogram (ECG) technology has contributed to our understanding of cardiac physiology. We propose an artificial intelligence-enabled ECG algorithm based on an improved ResNet for a wearable ECG. The system hardware consists of a wearable ECG with conductive fabric electrodes, a wireless ECG acquisition module, a mobile terminal App, and a cloud diagnostic platform. The algorithm adopted in this study is based on an improved ResNet for the rapid classification of different types of arrhythmia. First, we visualize ECG data and convert one-dimensional ECG signals into two-dimensional images using Gramian angular fields. Then, we improve the ResNet-50 network model, add multistage shortcut branches to the network, and optimize the residual block. The ReLu activation function is replaced by a scaled exponential linear units (SELUs) activation function to improve the expression ability of the model. Finally, the images are input into the improved ResNet network for classification. The average recognition rate of this classification algorithm against seven types of arrhythmia signals (atrial fibrillation, atrial premature beat, ventricular premature beat, normal beat, ventricular tachycardia, atrial tachycardia, and sinus bradycardia) is 98.3%.

scholarly journals RPA and Artificial Intelligence in Budget Management Based on Multiperspective Recognition Based on Network Communication Integration

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Haiying Luo ◽  
Haichang Luo
Keyword(s):  
Artificial Intelligence ◽  
Human Resources ◽  
Recognition Rate ◽  
Kernel Functions ◽  
Network Communication ◽  
Labor Costs ◽  
Budget Management ◽  
Average Recognition Rate ◽  
Artificial Intelligence Technology ◽  
Periodic Transmission

Nowadays, RPA robots are increasingly used in daily office tasks such as finance and human resources. They play an increasingly important role in realizing office automation, which can improve work efficiency and reduce labor costs. In order to improve the efficiency of budget management and save human resources, this paper conducts related research based on the multiview recognition technology of network communication integration, combined with RPA in artificial intelligence technology. In the method part, this article introduces the mode of network communication integration and the principles that should be followed, as well as the related processes of RPA. In the algorithm, this paper introduces an integrated algorithm based on ELM. In the experimental part, this article predicts the performance of each model, compares identification functions with different signal-to-voice signals, and compares timing functions on different signal-to-voice signals, periodic transmission mode indicators, recognition rates of different kernel functions, and comparison of average recognition rates and multiview recognition rate comprehensive analysis of these multiple aspects. Under the same conditions, the recognition rate of some angles is lower than other angles; 0 degrees, 18 degrees, 126 degrees, and 180 degrees are slightly lower than other angles, which will affect the average recognition rate of the entire recognition. But for multiview gait features, considering the influence of each angle on the recognition rate, the characteristics of each angle are merged together, so that the recognition rate is significantly higher than the average recognition rate of 11 angles. It can be seen that multiview recognition based on network communication integration does have obvious effects on RPA and artificial intelligence in budget management and can improve the efficiency of budget management. The multiperspective recognition technology designed in this study can realize modernization and digitization in budget management.

scholarly journals Non-Intrusive Load Disaggregation Based on a Multi-Scale Attention Residual Network

2020 ◽  
Vol 10 (24) ◽  
pp. 9132
Author(s):  
Liguo Weng ◽  
Xiaodong Zhang ◽  
Junhao Qian ◽  
Min Xia ◽  
Yiqing Xu ◽  
...  
Keyword(s):  
Smart Grids ◽  
Recognition Rate ◽  
Low Frequency ◽  
Attention Mechanism ◽  
Learning Ability ◽  
Residual Network ◽  
Multi Scale ◽  
Energy Disaggregation ◽  
Benchmark Datasets ◽  
Load Disaggregation

Non-intrusive load disaggregation (NILD) is of great significance to the development of smart grids. Current energy disaggregation methods extract features from sequences, and this process easily leads to a loss of load features and difficulties in detecting, resulting in a low recognition rate of low-use electrical appliances. To solve this problem, a non-intrusive sequential energy disaggregation method based on a multi-scale attention residual network is proposed. Multi-scale convolutions are used to learn features, and the attention mechanism is used to enhance the learning ability of load features. The residual learning further improves the performance of the algorithm, avoids network degradation, and improves the precision of load decomposition. The experimental results on two benchmark datasets show that the proposed algorithm has more advantages than the existing algorithms in terms of load disaggregation accuracy and judgments of the on/off state, and the attention mechanism can further improve the disaggregation accuracy of low-frequency electrical appliances.

scholarly journals Practical Recognition System for Text Printed on Clear Reflected Material

2012 ◽  
Vol 2012 ◽  
pp. 1-16 ◽  
Author(s):  
Khader Mohammad ◽  
Sos Agaian
Keyword(s):  
Processing Time ◽  
Recognition Rate ◽  
Recognition System ◽  
Experimental Results ◽  
Research Fields ◽  
Average Recognition Rate ◽  
Clear Plastic ◽  
Novel Methods ◽  
Processor Speed ◽  
Background Contrast

Text embedded in an image contains useful information for applications in the medical, industrial, commercial, and research fields. While many systems have been designed to correctly identify text in images, no work addressing the recognition of degraded text on clear plastic has been found. This paper posits novel methods and an apparatus for extracting text from an image with the practical assumption: (a) poor background contrast, (b) white, curved, and/or differing fonts or character width between sets of images, (c) dotted text printed on curved reflective material, and/or (d) touching characters. Methods were evaluated using a total of 100 unique test images containing a variety of texts captured from water bottles. These tests averaged a processing time of ~10 seconds (using MATLAB R2008A on an HP 8510 W with 4 G of RAM and 2.3 GHz of processor speed), and experimental results yielded an average recognition rate of 90 to 93% using customized systems generated by the proposed development.

Automatic detection of the Cyclic Alternating Pattern of sleep and diagnosis of sleep-related pathologies (Preprint)

2021 ◽  
Author(s):  
Jiajia Cui ◽  
Zhipei Huang ◽  
Jiankang Wu
Keyword(s):  
Random Forest ◽  
Eye Movement ◽  
Hidden Markov ◽  
Recognition Rate ◽  
Automatic Recognition ◽  
Rapid Eye Movement Sleep ◽  
Cyclic Alternating Pattern ◽  
Average Recognition Rate ◽  
The Stability ◽  
Cardiopulmonary System

UNSTRUCTURED The Cyclic Alternating Pattern is a periodic electroencephalogram activity occurring during No Rapid Eye Movement sleep. It is a marker of sleep instability and correlated with several sleep-related pathologies. In this article, considering the connection between heart and brain of people, by statistically analysising and comparing the cardiopulmonary characteristics of people with no pathology and patients with sleep-related diseases, an automatic recognition scheme of Cyclic Alternating Pattern is proposed based on the Cardiopulmonary Resonance Indices. Using improved Hidden Markov and Random Forest, the scheme combines both the measurements of coupling state and the stability of the cardiopulmonary system during sleep. The average recognition rate of A-phase reaches 84.67% and F1 score reaches 80.35%. Results show that our scheme could automatically recognize the Cyclic Alternating Pattern accurately, and diagnose insomnia and narcolepsy.

Automatic detection of the Cyclic Alternating Pattern of sleep and diagnosis of sleep-related pathologies (Preprint)

2021 ◽  
Author(s):  
Jiajia Cui ◽  
Zhipei Huang ◽  
Jiankang Wu
Keyword(s):  
Random Forest ◽  
Eye Movement ◽  
Hidden Markov ◽  
Recognition Rate ◽  
Automatic Recognition ◽  
Rapid Eye Movement Sleep ◽  
Cyclic Alternating Pattern ◽  
Average Recognition Rate ◽  
The Stability ◽  
Cardiopulmonary System

BACKGROUND The Cyclic Alternating Pattern is a periodic electroencephalogram activity occurring during No Rapid Eye Movement sleep. It is a marker of sleep instability and correlated with several sleep-related pathologies. OBJECTIVE The objective of our study is to automatic detect the Cyclic Alternating Pattern of sleep and to diagnose sleep-related pathologies based on ECG and respiratory signals. METHODS Considering the connection between heart and brain of people, by statistically analysising and comparing the cardiopulmonary characteristics of people with no pathology and patients with sleep-related diseases, an automatic recognition scheme of Cyclic Alternating Pattern is proposed based on the Cardiopulmonary Resonance Indices. Using improved Hidden Markov and Random Forest, the scheme combines both the measurements of coupling state and the stability of the cardiopulmonary system during sleep. RESULTS In this article, the average recognition rate of A-phase reaches 84.67% and F1 score reaches 80.35% on the CAP Sleep Database in MIT-BIH database. CONCLUSIONS The scheme could automatically recognize the Cyclic Alternating Pattern accurately, and diagnose insomnia and narcolepsy using ECG and respiratory signals.

Plastic Classification with X-ray Absorption Spectroscopy Based on Back Propagation Neural Network

2017 ◽  
Vol 71 (11) ◽  
pp. 2538-2548 ◽  
Author(s):  
Qian Wang ◽  
Xiaomei Wu ◽  
Lingcong Chen ◽  
Zheng Yang ◽  
Zheng Fang
Keyword(s):  
Absorption Spectroscopy ◽  
Recognition Rate ◽  
Back Propagation ◽  
Principal Component ◽  
Back Propagation Neural Network ◽  
X Ray ◽  
Analysis Methods ◽  
Average Recognition Rate ◽  
The Stability ◽  
X Ray Absorption

Currently, spectral analysis methods used in the classification of plastics have limitations that do not apply to opaque plastics or the stability of experimental results is not strong. In this paper, X-ray absorption spectroscopy (XAS) has been applied to classify plastics due to its strong penetrability and stability. Fifteen kinds of plastics are selected as specimens. X-ray, which is excited by a voltage of 60 kV, penetrated these specimens. The spectral data acquired by CdTe X-ray detector are processed by principal component analysis (PCA) and other data analysis methods. Then the back propagation neural networks (BPNN) algorithm is used to classify the processed data. The average recognition rate reached 96.95% and classification results of all types of plastic results were analyzed in detail. It indicates that XAS has the potential to classify plastics and that XAS can be used in some fields such as plastic waste sorting and recycling. At the same time, the technology of XAS, in the future, can also be used to classify more substances.

Research on Indicator Diagram of Shock Absorber Fault Recognition Based on Support Vector Machine

2013 ◽  
Vol 765-767 ◽  
pp. 2195-2198
Author(s):  
Wei Dong Xie ◽  
Kan Gao ◽  
Ji Sheng Shen
Keyword(s):  
Support Vector Machine ◽  
Shock Absorber ◽  
Recognition Rate ◽  
Support Vector ◽  
Indicator Diagram ◽  
Fault Recognition ◽  
Average Recognition Rate ◽  
Rbf Kernel ◽  
On Line ◽  
Rbf Kernel Function

In order to meet the development of shock absorber on-line detection, a new method of indicator diagrams recognition for shock absorber based on support vector machine (SVM) is proposed. Different fault patterns of shock absorber indicator diagram are discussed, including their main causes. The recognition model is constructed each with Linear, Polynomial and Radial Basis Function (RBF) kernel function. The experimental results show that the best average recognition rate is 96.4%. This method is effective in indicator diagram fault recognition of shock absorber.

scholarly journals Personalized Rehabilitation Recognition for Ubiquitous Healthcare Measurements

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1679
Author(s):  
Yao-Chiang Kan ◽  
Yu-Chieh Kuo ◽  
Hsueh-Chun Lin
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Recognition Rate ◽  
Mobile App ◽  
Ubiquitous Healthcare ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Average Recognition Rate ◽  
Self Development ◽  
The Subject

The physical therapeutic application needs personalized rehabilitation recognition (PRR) for ubiquitous healthcare measurements (UHMs). This study employed the adaptive neuro-fuzzy inference system (ANFIS) to generate a PRR model for a self-development system of UHM. The subjects wore a sensor-enabled wristband during physiotherapy exercises to measure the scheduled motions of their limbs. In the model, the sampling data collected from the scheduled motions are labeled by an arbitrary number within a defined range. The sample datasets are referred as the design of an initial fuzzy inference system (FIS) with data preprocessing, feature visualizing, fuzzification, and fuzzy logic rules. The ANFIS then processes data training to adjust the FIS for optimization. The trained FIS then can infer the motion labels via defuzzification to recognize the features in the test data. The average recognition rate was higher than 90% for the testing motions if the subject followed the sampling schedule. With model implementation, the middle section of motion datasets in each second is recommended for recognition in the UHM system which also includes a mobile App to retrieve the personalized FIS in order to trace the exercise. This approach contributes a PRR model with trackable diagrams for the physicians to explore the rehabilitation motions in details.

Fault Diagnosis of Pump Based on a Hybrid HMM/SVM Model

2011 ◽  
Vol 188 ◽  
pp. 629-635
Author(s):  
Xia Yue ◽  
Chun Liang Zhang ◽  
Jian Li ◽  
H.Y. Zhu
Keyword(s):  
Fault Diagnosis ◽  
Hybrid Model ◽  
Large Scale ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Double Layers ◽  
Support Vector ◽  
Practical Applications ◽  
Average Recognition Rate ◽  
Svm Model

A hybrid support vector machine (SVM) and hidden Markov model (HMM) model was introduced into the fault diagnosis of pump. This model had double layers: the first layer used HMM to classify preliminarily in order to get the coverage of possible faults; the second layer utilized this information to activate the corresponding SVMs for improving the recognition accuracy. The structure of this hybrid model was clear and feasible. Especially the model had the potential of large-scale multiclass application in fault diagnosis because of its good scalability. The recognition experiments of 26 statuses on the ZLH600-2 pump showed that the recognition capability of this model was sound in multiclass problems. The recognition rate of one bearing eccentricity increased from SVM’s 84.42% to 89.61% while the average recognition rate of hybrid model reached 95.05%. Although some goals while model constructed did not be fully realized, this model was still very good in practical applications.

Sign in / Sign up

Export Citation Format

Share Document