O-WCNN: an optimized integration of spatial and spectral feature map for arrhythmia classification

AbstractThe regular monitoring and accurate diagnosis of arrhythmia are critically important, leading to a reduction in mortality rate due to cardiovascular diseases (CVD) such as heart stroke or cardiac arrest. This paper proposes a novel convolutional neural network (CNN) model for arrhythmia classification. The proposed model offers the following improvements compared with traditional CNN models. Firstly, the multi-channel model can concatenate spectral and spatial feature maps. Secondly, the structural unit is composed of a depthwise separable convolution layer followed by activation and batch normalization layers. The structural unit offers effective utilization of network parameters. Also, the optimization of hyperparameters is done using Hyperopt library, based on Sequential Model-Based Global Optimization algorithm (SMBO). These improvements make the network more efficient and accurate for arrhythmia classification. The proposed model is evaluated using tenfold cross-validation following both subject-oriented inter-patient and class-oriented intra-patient evaluation protocols. Our model achieved 99.48% and 99.46% accuracy in VEB (ventricular ectopic beat) and SVEB (supraventricular ectopic beat) class classification, respectively. The model is compared with state-of-the-art models and has shown significant performance improvement.

Download Full-text

A line-of-sight channel model for the 100–450 gigahertz frequency band

EURASIP Journal on Wireless Communications and Networking ◽

10.1186/s13638-021-01974-8 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Joonas Kokkoniemi ◽

Janne Lehtomäki ◽

Markku Juntti

Keyword(s):

Channel Model ◽

Full Range ◽

Line Of Sight ◽

Absorption Loss ◽

Radio Communication ◽

International Telecommunication Union ◽

International Telecommunication ◽

Fifth Generation ◽

Proposed Model ◽

Actual Response

AbstractThis paper documents a simple parametric polynomial line-of-sight channel model for 100–450 GHz band. The band comprises two popular beyond fifth generation (B5G) frequency bands, namely, the D band (110–170 GHz) and the low-THz band (around 275–325 GHz). The main focus herein is to derive a simple, compact, and accurate molecular absorption loss model for the 100–450 GHz band. The derived model relies on simple absorption line shape functions that are fitted to the actual response given by complex but exact database approach. The model is also reducible for particular sub-bands within the full range of 100–450 GHz, further simplifying the absorption loss estimate. The proposed model is shown to be very accurate by benchmarking it against the exact response and the similar models given by International Telecommunication Union Radio Communication Sector. The loss is shown to be within ±2 dBs from the exact response for one kilometer link in highly humid environment. Therefore, its accuracy is even much better in the case of usually considered shorter range future B5G wireless systems.

Download Full-text

Research on Spatial Channel Model for Vehicle-to-Vehicle Communication Channel in Roadside Scattering Environment

International Journal of Antennas and Propagation ◽

10.1155/2017/3098198 ◽

2017 ◽

Vol 2017 ◽

pp. 1-12 ◽

Cited By ~ 4

Author(s):

Xin Chen ◽

Yong Fang ◽

Weidong Xiang ◽

Liang Zhou

Keyword(s):

Communication Channel ◽

Channel Model ◽

Critical Distance ◽

Traffic Density ◽

Vehicle Speed ◽

Angle Of Arrival ◽

Vehicle To Vehicle ◽

Proposed Model ◽

Spatial Channel Model ◽

The Impact

In this paper, an extension of spatial channel model (SCM) for vehicle-to-vehicle (V2V) communication channel in roadside scattering environment is investigated for the first time theoretically and by simulations. Subsequently, to efficiently describe the roadside scattering environment and reflect the nonstationary properties of V2V channels, the proposed SCM V2V model divides the scattering objects into three categories of clusters according to the location of effective scatterers by introducing critical distance. We derive general expressions for the most important statistical properties of V2V channels, such as channel impulse response, power spectral density, angular power density, autocorrelation function, and Doppler spread of the proposed model. The impact of vehicle speed, traffic density, and angle of departure, angle of arrival, and other statistical performances on the V2V channel model is thoroughly discussed. Numerical simulation results are presented to validate the accuracy and effectiveness of the proposed model.

Download Full-text

A TWO-CHANNEL MODEL FOR REPRESENTATION LEARNING IN VIETNAMESE SENTIMENT CLASSIFICATION PROBLEM

Journal of Computer Science and Cybernetics ◽

10.15625/1813-9663/36/4/14829 ◽

2020 ◽

Vol 36 (4) ◽

pp. 305-323

Author(s):

Quan Hoang Nguyen ◽

Ly Vu ◽

Quang Uy Nguyen

Keyword(s):

Channel Model ◽

Rapid Development ◽

Representation Learning ◽

Classification Problem ◽

Sentiment Classification ◽

Complex Sentences ◽

Digital World ◽

Part Of Speech ◽

Proposed Model ◽

Important Research Topic

Sentiment classification (SC) aims to determine whether a document conveys a positive or negative opinion. Due to the rapid development of the digital world, SC has become an important research topic that affects many aspects of our life. In SC based on machine learning, the representation of the document strongly influences on its accuracy. Word Embedding (WE)-based techniques, i.e., Word2vec techniques, are proved to be beneficial techniques to the SC problem. However, Word2vec is often not enough to represent the semantic of documents with complex sentences of Vietnamese. In this paper, we propose a new representation learning model called a \textbf{two-channel vector} to learn a higher-level feature of a document in SC. Our model uses two neural networks to learn the semantic feature, i.e., Word2vec and the syntactic feature, i.e., Part of Speech tag (POS). Two features are then combined and input to a \textit{Softmax} function to make the final classification. We carry out intensive experiments on $4$ recent Vietnamese sentiment datasets to evaluate the performance of the proposed architecture. The experimental results demonstrate that the proposed model can significantly enhance the accuracy of SC problems compared to two single models and a state-of-the-art ensemble method.

Download Full-text

Optimization technique combined with deep learning method for teeth recognition in dental panoramic radiographs

Scientific Reports ◽

10.1038/s41598-020-75887-9 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Fahad Parvez Mahdi ◽

Kota Motoki ◽

Syoji Kobashi

Keyword(s):

Dental Care ◽

Cross Validation ◽

Optimization Technique ◽

Confidence Score ◽

Computer Assisted ◽

Proposed Model ◽

Tenfold Cross Validation ◽

Stress Fatigue ◽

Assisted Analysis ◽

High Degree

Abstract Computer-assisted analysis of dental radiograph in dentistry is getting increasing attention from the researchers in recent years. This is mainly because it can successfully reduce human-made error due to stress, fatigue or lack of experience. Furthermore, it reduces diagnosis time and thus, improves overall efficiency and accuracy of dental care system. An automatic teeth recognition model is proposed here using residual network-based faster R-CNN technique. The detection result obtained from faster R-CNN is further refined by using a candidate optimization technique that evaluates both positional relationship and confidence score of the candidates. It achieves 0.974 and 0.981 mAPs for ResNet-50 and ResNet-101, respectively with faster R-CNN technique. The optimization technique further improves the results i.e. F1 score improves from 0.978 to 0.982 for ResNet-101. These results verify the proposed method’s ability to recognize teeth with high degree of accuracy. To test the feasibility and robustness of the model, a tenfold cross validation (CV) is presented in this paper. The result of tenfold CV effectively verifies the robustness of the model as the average F1 score obtained is more than 0.970. Thus, the proposed model can be used as a useful and reliable tool to assist dental care professionals in dentistry.

Download Full-text

Tracking- and Scintillation-Aware Channel Model for GEO Satellite to Land Mobile Terminals at Ku-Band

International Journal of Antennas and Propagation ◽

10.1155/2015/392714 ◽

2015 ◽

Vol 2015 ◽

pp. 1-15 ◽

Cited By ~ 3

Author(s):

Ali M. Al-Saegh ◽

A. Sali ◽

J. S. Mandeep ◽

Alyani Ismail

Keyword(s):

Channel Model ◽

Signal To Noise Ratio ◽

Wide Band ◽

Mobile Terminal ◽

Directional Antennas ◽

Coding Schemes ◽

Significant Performance ◽

Mobile Satellite ◽

Tropospheric Scintillation ◽

Ku Band

Recent advances in satellite to land mobile terminal services and technologies, which utilize high frequencies with directional antennas, have made the design of an appropriate model for land mobile satellite (LMS) channels a necessity. This paper presents LMS channel model at Ku-band with features that enhance accuracy, comprehensiveness, and reliability. The effect of satellite tracking loss at different mobile terminal speeds is considered for directional mobile antenna systems, a reliable tropospheric scintillation model for an LMS scenario at tropical and temperate regions is presented, and finally a new quality indicator module for different modulation and coding schemes is included. The proposedextended LMS channel (ELMSC)model is designed based on actual experimental measurements and can be applied to narrow- and wide-band signals at different regions and at different speeds and multichannel states. The proposed model exhibits lower root mean square error (RMSE) and significant performance observation compared with the conventional model in terms of the signal fluctuations, fade depth, signal-to-noise ratio (SNR), and quality indicators accompanied for several transmission schemes.

Download Full-text

Monaural Singing Voice and Accompaniment Separation Based on Gated Nested U-Net Architecture

Symmetry ◽

10.3390/sym12061051 ◽

2020 ◽

Vol 12 (6) ◽

pp. 1051

Author(s):

Haibo Geng ◽

Ying Hu ◽

Hao Huang

Keyword(s):

Time Domain ◽

Singing Voice ◽

Feature Maps ◽

Time Frequency ◽

Convolutional Networks ◽

Full Resolution ◽

Mask Layer ◽

Proposed Model ◽

Phase Spectra ◽

Separation Model

This paper proposes a separation model adopting gated nested U-Net (GNU-Net) architecture, which is essentially a deeply supervised symmetric encoder–decoder network that can generate full-resolution feature maps. Through a series of nested skip pathways, it can reduce the semantic gap between the feature maps of encoder and decoder subnetworks. In the GNU-Net architecture, only the backbone not including nested part is applied with gated linear units (GLUs) instead of conventional convolutional networks. The outputs of GNU-Net are further fed into a time-frequency (T-F) mask layer to generate two masks of singing voice and accompaniment. Then, those two estimated masks along with the magnitude and phase spectra of mixture can be transformed into time-domain signals. We explored two types of T-F mask layer, discriminative training network and difference mask layer. The experiment results show the latter to be better. We evaluated our proposed model by comparing with three models, and also with ideal T-F masks. The results demonstrate that our proposed model outperforms compared models, and it’s performance comes near to ideal ratio mask (IRM). More importantly, our proposed model can output separated singing voice and accompaniment simultaneously, while the three compared models can only separate one source with trained model.

Download Full-text

Ventricular Ectopic Beat Classification Using KNN Multi-Feature Classifier

2018 International Conference on Communication, Computing and Internet of Things (IC3IoT) ◽

10.1109/ic3iot.2018.8668116 ◽

2018 ◽

Author(s):

Avvaru Srinivasulu ◽

N. Sriraam

Keyword(s):

Ectopic Beat ◽

Ventricular Ectopic Beat ◽

Beat Classification

Download Full-text

Ventricular ectopic beat detection using a wavelet transform and a convolutional neural network

Physiological Measurement ◽

10.1088/1361-6579/ab17f0 ◽

2019 ◽

Vol 40 (5) ◽

pp. 055002 ◽

Cited By ~ 4

Author(s):

Qichen Li ◽

Chengyu Liu ◽

Qiao Li ◽

Supreeth P Shashikumar ◽

Shamim Nemati ◽

...

Keyword(s):

Neural Network ◽

Wavelet Transform ◽

Convolutional Neural Network ◽

Ectopic Beat ◽

Ventricular Ectopic Beat ◽

Beat Detection

Download Full-text

A Saliency Detection Method Based on Wavelet Transform and Simple Priors

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.2238 ◽

2014 ◽

Vol 602-605 ◽

pp. 2238-2241

Author(s):

Jian Kun Chen ◽

Zhi Wei Kang

Keyword(s):

Wavelet Transform ◽

Detection Method ◽

Saliency Detection ◽

Visual Saliency ◽

Feature Maps ◽

Multi Scale ◽

Saliency Model ◽

Proposed Model ◽

Visual Saliency Model ◽

Better Than

In this paper, we present a new visual saliency model, which based on Wavelet Transform and simple Priors. Firstly, we create multi-scale feature maps to represent different features from edge to texture in wavelet transform. Then we modulate local saliency at a location and its global saliency, combine the local saliency and global saliency to generate a new saliency .Finally, the final saliency is generated by combining the new saliency and two simple priors (color prior an location prior). Experimental evaluation shows the proposed model can achieve state-of-the-art results and better than the other models on a public available benchmark dataset.

Download Full-text