scholarly journals Deep Ensemble Learning for Automatic Modulation Classification

2021 ◽  
Author(s):  
Jiali Nie ◽  
Wenke Tan ◽  
Houmei Zhang
Keyword(s):  
Ensemble Learning ◽  
Vital Role ◽  
Learning Ability ◽  
Sample Length ◽  
Complex Data ◽  
Ensemble Model ◽  
Modulation Classification ◽  
Single Model ◽  
Automatic Modulation Classification ◽  
The Impact

Abstract Automatic modulation classification (AMC) plays an increasingly vital role in cognitive radio (CR), cognitive electronic warfare, and other areas. It aims at classifying the modulated modes of the received signals accurately and provides a guarantee for the subsequent detailed parameter identification. Deep learning (DL) methods allow the computer to automatically learn the pattern features and integrate features into the process of building the model, thereby reducing the incompleteness caused by artificial design features. At the same time, the DL methods have been applied in the AMC field as its powerful ability to process complex data and have achieved excellent performance in recent years. In this paper, we propose a deep ensemble learning AMC network, which uses a multi-model ensemble method to fuse multiple DL features. Specifically, different DL models are integrated by ensemble learning, which enhances the learning ability of the single model. With the proposed ensemble model trained on a measured wireless signal dataset, we conclude that the ensemble structure of Inception and CLDNN can fuse spatial features and temporal features, and achieve state-of-the-art performance in AMC tasks. Besides, the impact of the inphase/quadrature (I/Q) sample-length on wireless signals is further investigated, and find that the classification accuracy of the deep ensemble model is improved by 0.7% to 10% compared to the single model under various sample-length. Simultaneously, we visualize convergence clustering with t-distributed stochastic neighbor embedding (t-SNE), and the visualization results prove that the deep ensemble model has a stronger clustering ability than a single model.

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

scholarly journals Ensemble Model of Precipitation Change Over Indonesia Caused by El Nino Modoki

2021 ◽  
Vol 4 (1) ◽  
pp. 72
Author(s):  
Ida Bagus Mandhara Brasika
Keyword(s):  
El Niño ◽  
El Nino ◽  
Skill Score ◽  
Ensemble Model ◽  
Single Model ◽  
Model Quality ◽  
El Niño Modoki ◽  
Squared Error ◽  
The Impact

The aim of this research is to understand the impact of El Nino Modoki into Indonesian precipitation and how ensemble models can simulate this changing. Ensemble model has been recognized as a method to improve the quality of model and/or prediction of climate phenomenon. Every model has their own algorithm which causes strength and weakness in many aspects. Ensemble will improve the quality of simulation while reducing the weakness. However, the combination of models for ensembles is differ for each event and/or location. Here we utilize the Squared Error Skill Score (SESS) method to examine each model quality and to compare the ensemble model with the single model. El Nino Modoki is a unique phenomenon. It remains debatable amongst scientists, many features of this phenomenon are unfold. So, it is important to find out how El Nino Modoki has changed precipitation over Indonesia. To verify the changing precipitation, the composite of precipitation on El Nino Modoki Year is divided with the composite of all years. Last, validating ensemble model with Satellite-gauge precipitation dataset. El Nino Modoki decreases precipitation in most of Indonesian regions. The ensemble, while statistically promising, has failed to simulate precipitation in some region.

scholarly journals Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization

2020 ◽  
Author(s):  
Guan Gui ◽  
Yu Wang ◽  
Yue Yin ◽  
Juan Wang ◽  
Jinlong Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Communication Systems ◽  
Mimo Systems ◽  
Modulation Classification ◽  
Imperfect Csi ◽  
Zero Forcing ◽  
Automatic Modulation Classification ◽  
Simulation Results ◽  
The Impact

Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.<br>

scholarly journals The Impact and Efficiency of Electronic Libraries In Various Districts of Punjab, Pakistan

2021 ◽  
Vol 38 (1) ◽  
Author(s):  
Ehsan Bhutta ◽  
Yasir Rasool ◽  
Chaudhry Abdul Rehman
Keyword(s):  
Structural Equation ◽  
Positive Influence ◽  
Vital Role ◽  
Learning Ability ◽  
Equation Modeling ◽  
Digital Learning ◽  
Learning Capacity ◽  
Dynamic Methods ◽  
And Performance ◽  
The Impact

The present research study is conducted with the aim to assess and analyze the impact of electronic libraries (EL) by using usability criteria which include consistency, efficiency, learning and satisfaction in digital learning and reading stimulus among the general public and youth in specific. The structural equation modeling (SEM) of variables like effectiveness (EEF), efficiency (EFT), learning ability (LER) and performance & satisfaction (PES) was followed by research design. Survey was conducted in divisional headquarters of the Punjab province to collect data. The population was N=270 persons from 9 out of 20 districts having EL facilities. The findings revealed that E-Libraries have a positive correlation between productivity, effectiveness, learning and success. Performance, efficacy and learning capacity had a substantial and positive influence on user’s satisfaction. The study found that the provision of a conducive atmosphere that ensures productivity, effectiveness and learning capacity plays a vital role in enhancing performance of EL. It is proposed that we follow more efficient and dynamic methods in order to support the concept of EL for promotion of culture of digital learning philosophy among the public.

scholarly journals Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization

2020 ◽  
Author(s):  
Guan Gui ◽  
Yu Wang ◽  
Yue Yin ◽  
Juan Wang ◽  
Jinlong Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Communication Systems ◽  
Mimo Systems ◽  
Modulation Classification ◽  
Imperfect Csi ◽  
Zero Forcing ◽  
Automatic Modulation Classification ◽  
Simulation Results ◽  
The Impact

Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.<br>

The Impact Of Emotional Intelligence On Leadership Excellence Of Executive Empoloyees In Public Sector Organizationin Ampara District Of Sri Lanka

2019 ◽  
Vol 118 (9) ◽  
pp. 52-60
Author(s):  
Dr.S. Gunapalan ◽  
Dr.K. Maran
Keyword(s):  
Emotional Intelligence ◽  
Public Sector ◽  
Vital Role ◽  
Public Organization ◽  
Self Awareness ◽  
Public Sector Organization ◽  
Expression Of Emotion ◽  
Asking Questions ◽  
Private Sector Organizations ◽  
The Impact

Emotional Intelligence is play a vital role to decide  leadership excellence. So this paper to study the  impact of emotional intelligence on leadership excellence of executive employee in public sector organization.Hence the objective of this  research   is to identify the  impact of emotional intelligence on leadership excellence of executive employee in Public Sector Organization in Ampara districtof Sri Lanka.emotional intelligence includes the verbal and non-verbal appraisal and expression of emotion, the regulation of emotion in the self and others, and the utilization of emotional content in problem solving. Cook (2006)[1]. Emotional intelligence is one of the  essential skill for leaders to manage their subordinate. Accordingly although there is some research done under “Emotional intelligence on leadership excellence of the executive employee in the public organization in Ampara district so this study full filed the gap. Based on the analysis, Self-awareness, Self-management, Social-awareness and Relationship management are the positively affect to the Leadership excellence. So, executive employees should consider about the Emotions of their subordinators when they completing their targets. leaders should pay the attention for recognize the situation, hove to impact their feelings for the performance & recognized their own feelings. Leaders should consider and see their own emotions when they work with others by listening carefully, understand the person by asking questions, identifying non-verbal expressions and solving problems without helming someone’s. Leadersshould consider their subordinators emotions when they find a common idea, government should give to moderate freedom to executive employees in public organization to take the decision with competing the private sector organizations.

Fluoxetine Protects against Dendritic Spine Loss in Middle-aged APPswe/PSEN1dE9 Double Transgenic Alzheimer’s Disease Mice

2020 ◽  
Vol 17 (1) ◽  
pp. 93-103 ◽  
Author(s):  
Jing Ma ◽  
Yuan Gao ◽  
Wei Tang ◽  
Wei Huang ◽  
Yong Tang
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Dendritic Spines ◽  
Dendritic Spine ◽  
Early Stage ◽  
Learning Ability ◽  
Middle Aged ◽  
Protein Levels ◽  
Spine Pathology ◽  
The Impact

Background: Studies have suggested that cognitive impairment in Alzheimer’s disease (AD) is associated with dendritic spine loss, especially in the hippocampus. Fluoxetine (FLX) has been shown to improve cognition in the early stage of AD and to be associated with diminishing synapse degeneration in the hippocampus. However, little is known about whether FLX affects the pathogenesis of AD in the middle-tolate stage and whether its effects are correlated with the amelioration of hippocampal dendritic dysfunction. Previously, it has been observed that FLX improves the spatial learning ability of middleaged APP/PS1 mice. Objective: In the present study, we further characterized the impact of FLX on dendritic spines in the hippocampus of middle-aged APP/PS1 mice. Results: It has been found that the numbers of dendritic spines in dentate gyrus (DG), CA1 and CA2/3 of hippocampus were significantly increased by FLX. Meanwhile, FLX effectively attenuated hyperphosphorylation of tau at Ser396 and elevated protein levels of postsynaptic density 95 (PSD-95) and synapsin-1 (SYN-1) in the hippocampus. Conclusion: These results indicated that the enhanced learning ability observed in FLX-treated middle-aged APP/PS1 mice might be associated with remarkable mitigation of hippocampal dendritic spine pathology by FLX and suggested that FLX might be explored as a new strategy for therapy of AD in the middle-to-late stage.

scholarly journals High Expression of KLF10 Is Associated with Favorable Survival in Patients with Oral Squamous Cell Carcinoma

Medicina ◽  
2020 ◽  
Vol 57 (1) ◽  
pp. 17
Author(s):  
Chung-Min Yeh ◽  
Yi-Ju Lee ◽  
Po-Yun Ko ◽  
Yueh-Min Lin ◽  
Wen-Wei Sung
Keyword(s):  
Survival Rate ◽  
Oral Cancer ◽  
Cancer Patients ◽  
Protective Factor ◽  
Female Gender ◽  
Vital Role ◽  
Cancer Stage ◽  
Independent Prognostic Marker ◽  
Oral Cancer Patients ◽  
The Impact

Background and objectives: Krüppel-like transcription factor 10 (KLF10) plays a vital role in regulating cell proliferation, including the anti-proliferative process, activation of apoptosis, and differentiation control. KLF10 may also act as a protective factor against oral cancer. We studied the impact of KLF10 expression on the clinical outcomes of oral cancer patients to identify its role as a prognostic factor in oral cancer. Materials and Methods: KLF10 immunoreactivity was analyzed by immunohistochemical (IHC) stain analysis in 286 cancer specimens from primary oral cancer patients. The prognostic value of KLF10 on overall survival was determined by Kaplan–Meier analysis and the Cox proportional hazard model. Results: High KLF10 expression was significantly associated with male gender and betel quid chewing. The 5-year survival rate was greater for patients with high KLF10 expression than for those with low KLF10 expression (62.5% vs. 51.3%, respectively; p = 0.005), and multivariate analyses showed that high KLF10 expression was the only independent factor correlated with greater overall patient survival. The significant correlation between high KLF10 expression and a higher 5-year survival rate was observed in certain subgroups of clinical parameters, including female gender, non-smokers, cancer stage T1, and cancer stage N0. Conclusions: KLF10 expression, detected by IHC staining, could be an independent prognostic marker for oral cancer patients.

Sign in / Sign up

Export Citation Format

Share Document