| |
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNISA996464412603316 |
|
|
Titolo |
Soft computing in data science : 6th international conference, SCDS 2021, virtual event, November 2-3, 2021 : proceedings / / Azlinah Mohamed [and three others] editors |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
Singapore : , : Springer, , [2021] |
|
©2021 |
|
|
|
|
|
|
|
|
|
ISBN |
|
|
|
|
|
|
Descrizione fisica |
|
1 online resource (450 pages) |
|
|
|
|
|
|
Collana |
|
Communications in Computer and Information Science ; ; 1489 |
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
Soft computing |
Data mining |
Evolutionary computation |
|
|
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
Nota di contenuto |
|
Intro -- Preface -- Organization -- Contents -- AI Techniques and Applications -- Comparison Performance of Long Short-Term Memory and Convolution Neural Network Variants on Online Learning Tweet Sentiment Analysis -- 1 Introduction -- 2 Proposed Methodology -- 2.1 Data Collection -- 2.2 Data Pre-processing -- 2.3 Sentiment Labelling -- 2.4 Sentiment Visualization -- 2.5 Dataset Normalization -- 2.6 Online Learning Dataset Analysis -- 2.7 Splitting Dataset -- 2.8 Deep Learning Model Design -- 2.9 Deep Learning Model Evaluation -- 3 Results -- 3.1 Pre-processed Datasets -- 3.2 Results from Experiment 1: 64 Batch Size and 10 Epoch -- 3.3 Results from Experiment 2: 64 Batch Size and 30 Epochs -- 3.4 Results from Experiment 3: 32 Batch Size and 30 Epoch -- 3.5 Results from Experiment 4: 32 Batch Size and 30 Epochs with Random Oversampling -- 3.6 Results from Experiment 5: 64 Batch Size 64 and 50 Epoch with Random Oversampling -- 4 Summary of the Results and Analysis -- 5 Conclusion -- References -- Performance Analysis of Hybrid Architectures of Deep Learning for Indonesian Sentiment Analysis -- 1 Introduction -- 2 Materials and Method -- 2.1 Dataset -- 2.2 Preprocessing -- 2.3 Convolutional Neural Network (CNN) -- 2.4 Long Short-Term Memory (LSTM) -- 2.5 Gated Recurrent Unit (GRU) -- |
|
|
|
|
|
|
|
|
|
2.6 RNN-CNN -- 2.7 CNN-RNN -- 3 Result and Discussion -- 3.1 Experimental Setup -- 3.2 Results -- 4 Conclusion -- References -- Machine Learning Based Biosignals Mental Stress Detection -- 1 Introduction -- 2 Literature Review on Stress and Its Effect -- 2.1 Concept of Stress -- 2.2 Stressors Maintaining and Integrity -- 2.3 Stress Effects on Emotion and Mental Health -- 2.4 Mental Stress Impact on Health -- 2.5 Biosignals Connected to Predict Acute Mental Stress -- 2.6 Machine Learning Approach to Detect Mental Stress -- 3 Data Collection -- 4 Methodology. |
4.1 Filtering and Preprocessing -- 4.2 Feature Extraction -- 4.3 Modeling -- 5 Result -- 6 Conclusion -- References -- Sentences Prediction Based on Automatic Lip-Reading Detection with Deep Learning Convolutional Neural Networks Using Video-Based Features -- 1 Introduction -- 2 Literature Review -- 3 Pre-processing and Methodology -- 4 Results and Discussion -- 5 Conclusion -- References -- Unsupervised Learning Approach for Evaluating the Impact of COVID-19 on Economic Growth in Indonesia -- 1 Introduction -- 2 Unsupervised Learning -- 2.1 Biplot Analysis -- 2.2 K-Means Clustering -- 2.3 K-Medoids Clustering -- 2.4 Self-Organizing Map (SOM) -- 2.5 Silhouette Coefficient -- 2.6 Gross Regional Domestic Product (GRDP) -- 3 Data and Methodology -- 4 Result and Discussion -- 4.1 Descriptive Statistic -- 4.2 Biplot Analysis -- 4.3 K-Medoids Clustering -- 4.4 K-Means Clustering -- 4.5 Self-Organizing Map (SOM) -- 4.6 Hybrid SOM - K-MeansClustering -- 4.7 Comparison Unsupervised Learning Method -- 5 Conclusion and Future Research -- References -- Rainfall Prediction in Flood Prone Area Using Deep Learning Approach -- 1 Introduction -- 2 Methodology -- 2.1 Study Area and Data Preparation -- 2.2 Model Development -- 2.3 Model Evaluation -- 3 Result and Discussion -- 3.1 Preliminary Studies -- 3.2 Performance Evaluation -- 3.3 Model Comparison and Discussion -- 4 Conclusion and Recommendation -- 4.1 Conclusion -- 4.2 Recommendation -- References -- Auto-DL: A Platform to Generate Deep Learning Models -- 1 Introduction -- 2 Related Work -- 3 Methodology Applied -- 4 Auto-DL Platform -- 4.1 React Application (Frontend) -- 4.2 Django Application (Backend) -- 4.3 MongoDB Instance (Database) -- 5 Testing and Result Analysis -- 5.1 Testing Model and Suite -- 5.2 About Datasets -- 5.3 Platform Usability Report -- 5.4 Comparative Study with Other Products. |
5.5 Generated Code Evaluation -- 5.6 Stress Testing the Auto-DL Platform -- 6 Conclusion -- 7 Future Scope -- References -- A Smart Predictive Maintenance Scheme for Classifying Diagnostic and Prognostic Statuses -- 1 Introduction -- 2 Related Studies -- 3 Method -- 3.1 Notations and Problems -- 3.2 Machine State Annotation -- 3.3 Machine State Model Construction -- 3.4 Future Machine State Prediction -- 4 Discussions -- 4.1 Data Information and Experiment Setups -- 4.2 State Annotation Analysis -- 4.3 Diagnostic and Prognostic Engine State Models Analysis -- 4.4 Testing Model Performances Analysis -- 5 Conclusion -- References -- Data Analytics and Technologies -- Optimal Portfolio Construction of Islamic Financing Instrument in Malaysia -- 1 Introduction -- 1.1 Equity Financing Instruments: Profit Sharing Contracts -- 1.2 Debt Financing Instruments -- 2 Literature Review -- 3 Methodology -- 3.1 Capital Asset Pricing Model -- 3.2 Construction of Optimal Portfolio -- 3.3 Portfolio Return and Risk -- 4 Results and Discussion -- 4.1 A Composition of Islamic Financing Instrument (IFI) -- 4.2 Comparing Mean Return, Variance and Risk of IFI -- 4.3 Capital Asset Pricing Model of IFI -- 4.4 Excess Return to Beta Ratio and Ranking Procedure -- 4.5 Selecting Instrument from Cut-Off Rate -- 4.6 Proportion of Each |
|
|
|
|
|
|
|
Selected Instruments -- 4.7 Portfolio Return and Risk -- 5 Conclusion -- References -- Analytics-Based on Classification and Clustering Methods for Local Community Empowerment in Indonesia -- 1 Introduction -- 2 Methodology -- 2.1 Classification -- 2.2 Clustering -- 3 Data Set -- 4 Result and Discussion -- 4.1 Classification (Supervised Learning) -- 4.2 Clustering (Unsupervised Learning) -- 5 Conclusion -- References -- Two-Step Estimation for Modeling the Earthquake Occurrences in Sumatra by Neyman-Scott Cox Point Processes -- 1 Introduction. |
2 Study Area and Data Description -- 3 Methodology -- 3.1 Neyman-Scott Cox Processes (NSCP) -- 3.2 Parameter Estimation -- 3.3 Model Assessment -- 4 Result -- 4.1 Spatial Trend and Clustering Detection -- 4.2 Model Comparison -- 4.3 Model Interpretation and Prediction -- 5 Conclusion -- References -- Construction of Optimal Stock Market Portfolios Using Outlier Detection Algorithm -- 1 Introduction -- 2 Related Work -- 2.1 Utilising Data Mining Methods -- 2.2 Utilising MVPO and Sharpe Ratio -- 3 Methodology -- 3.1 Preparing Stock Data -- 3.2 Preparing Proxy Data -- 3.3 Identifying Outliers -- 3.4 Measuring Performance of the Stock Portfolios Using MVPO -- 3.5 Assessing the Stock Portfolios Using the Sharpe Ratio -- 4 Results and Discussion -- 5 Conclusion -- References -- Simulating the Upcoming Trend of Malaysia's Unemployment Rate Using Multiple Linear Regression -- 1 Introduction -- 2 Literature Review -- 2.1 Overview and Definition of Unemployment -- 2.2 Issues of Unemployment -- 2.3 Contributing Factors of Unemployment -- 2.4 Multiple Linear Regression -- 2.5 Monte Carlo Simulation -- 3 Methodology -- 3.1 Multiple Linear Regression -- 3.2 Simulation of the Upcoming Trend of Malaysia's Unemployment Rate -- 4 Result -- 4.1 Multiple Linear Regression -- 4.2 Building the Regression Model -- 4.3 Simulation of Malaysia's Upcoming Trend of Unemployment Rate -- 5 Conclusion -- References -- Time Series Forecasting Using a Hybrid Prophet and Long Short-Term Memory Model -- 1 Introduction -- 2 Literature Review -- 2.1 Time Series Forecasting Model -- 2.2 Hybrid Methodology -- 3 Hybrid Methodology Framework -- 3.1 Linear Prediction -- 3.2 Nonlinear Prediction -- 3.3 Hybrid Time Series Forecasting Model -- 3.4 Data -- 3.5 Performance Metric -- 4 Empirical Results -- 4.1 Prophet Decomposition Result -- 4.2 Hybrid Algorithm -- 5 Conclusions -- References. |
Financial Analytics on Malaysia's Equity Fund Performance and Its Timing Liquidity -- 1 Introduction -- 1.1 Mutual Fund in Malaysia -- 2 Methodology -- 2.1 Return and Traditional Financial Ratios -- 2.2 Capital Asset Pricing Model -- 2.3 Liquidity Measures, Trading Volume and Turnover -- 2.4 Multiple Linear Regression -- 3 Analysis and Findings -- 3.1 Performance of Equity Funds Versus Market Return -- 3.2 Performance of Equity Funds Versus Market Return: A Month Before and After the 14thGeneral Election (GE14) -- 3.3 Relationship Between Expected Return of CAPM and Liquidity Timing -- 4 Conclusion -- References -- An Autoregressive Distributed Lag (ARDL) Analysis of the Relationships Between Employees Provident Fund's Wealth and Its Determinants -- 1 Introduction -- 2 Methodology -- 3 Analysis and Findings -- 3.1 Time Series Plots -- 3.2 Unit Root Test -- 3.3 Testing for the Presence of Co-integration -- 3.4 Unit Root Test -- 4 Conclusion -- References -- Data Mining and Image Processing -- Iris Segmentation Based on an Adaptive Initial Contour and Partly-Normalization -- 1 Introduction -- 2 Methodology -- 2.1 Pre-processing -- 2.2 Adaptive Initial Contour (AIC) -- 2.3 Partly-Normalization -- 3 Results and Discussion -- 3.1 Pre-test on Iris Images -- 3.2 Adaptive Initial Contour (AIC) -- 3.3 Iris Segmentation |
|
|
|
|
|
|
|
|
on Blurry Iris Images -- 3.4 Computational Time -- 4 Conclusion -- References -- Identifying the Important Demographic and Financial Factors Related to the Mortality Rate of COVID-19 with Data Mining Techniques -- 1 Introduction -- 2 Literature Review -- 2.1 Related Work -- 2.2 Feature Selection -- 2.3 Supervised Machine Learning -- 3 Methodology -- 3.1 Data Collection -- 3.2 Data Set Pre-processing -- 3.3 Creating Target Variable -- 3.4 Feature Selection Methods -- 3.5 Supervised Machine Learning Models -- 3.6 Evaluation. |
3.7 Data Visualization. |
|
|
|
|
|
| |