Classification Applications with Deep Learning and Machine Learning Technologies

Description

This book is very beneficial for early researchers/faculty who want to work in deep learning and machine learning for the classification domain. It helps them study, formulate, and design their research goal by aligning the latest technologies studies’ image and data classifications. The early start-up can use it to work with product or prototype design requirement analysis and its design and development. Preface Contents Artocarpus Classification Technique Using Deep Learning Based Convolutional Neural Network 1 Introduction 2 Propose Deep Learning 2.1 Proposed Convolutional Neural Network (CNN) Architecture 2.2 Transfer Learning Model for Artocarpus Classification 2.3 Dataset 2.4 Augmentation 3 Performance Result 3.1 Experimental Setup 3.2 Performance of Proposed CNN Model 3.3 Accuracy Comparison 3.4 Model Performance Comparison 4 Conclusion References Rambutan Image Classification Using Various Deep Learning Approaches 1 Introduction 2 Literature Review 3 Proposed Deep Learning Method 3.1 CNN 3.2 Transfer Learning 3.3 Dataset 4 Performance Results and Recommendation 4.1 Convolutional Neural Network (CNN) 4.2 Transfer Learning Model 5 Concluding Remarks References Mango Varieties Classification-Based Optimization with Transfer Learning and Deep Learning Approaches 1 Introduction 2 Methodology 2.1 Dataset 2.2 Data Preparation 2.3 Proposed CNN Architecture 2.4 Transfer Learning Model 3 Experiment Result 3.1 CNN 3.2 Transfer Learning 3.3 Xception 3.4 Accuracy Comparison 4 Conclusion References Salak Image Classification Method Based Deep Learning Technique Using Two Transfer Learning Models 1 Introduction 2 Dataset 2.1 Dataset Description 2.2 Dataset Preparation 3 Proposed Deep Learning 3.1 CNN 3.2 VGG16 3.3 ResNet50 4 Performance Result 4.1 Experimental Setup 4.2 Effect of Kernel Size: CNN 4.3 Effect of Pool Size: CNN 4.4 Effect of Epoch 4.5 Effect of Optimizer 4.6 Effect of Learning Rate 4.7 Effect of Dense Layer 4.8 Effect of Fine-Tuning for Pre-trained Models (VGG16 and ResNet50) 4.9 Accuracy Comparison 5 Conclusion References Image Processing Identification for Sapodilla Using Convolution Neural Network (CNN) and Transfer Learning Techniques 1 Introduction 2 Literature Survey 3 Proposed Deep Learning for Sapodilla Recognition 3.1 The Proposed CNN Architecture 3.2 Transfer Learning Model 3.3 Dataset 3.4 Augmentation 4 Performance Result 4.1 Experimental Setup 4.2 Performance of Proposed CNN Model 4.3 Accuracy Comparison 5 Conclusion References Comparison of Pre-trained and Convolutional Neural Networks for Classification of Jackfruit Artocarpus integer and Artocarpus heterophyllus 1 Introduction 2 Literature Review 3 Methodology 3.1 Dataset 3.2 Data Preprocessing and Partition 3.3 Convolutional Neural Networks 3.4 Transfer Learning 4 Result and Discussion 5 Conclusion References Markisa/Passion Fruit Image Classification Based Improved Deep Learning Approach Using Transfer Learning 1 Introduction 2 Literature Survey 3 Proposed CNN Architecture for Passion Food Recognition 3.1 The Proposed CNN Architectures 3.2 Transfer Learning Models 3.3 Dataset 3.4 Augmentation 4 Performance Result 4.1 Experimental Setup 4.2 Performance of Proposed CNN Model 4.3 Performance of Proposed Transfer Learning Model 4.4 Accuracy Comparison 5 Conclusion Appendix References Enhanced MapReduce Performance for the Distributed Parallel Computing: Application of the Big Data 1 Introduction 2 Background 2.1 Big Data (BD) 2.2 Hadoop 2.3 Apriori Algorithm 3 Related Work 4 Methodology (Prescriptive Study) 4.1 Hadoop Architecture 4.2 MR Programming Model 4.3 Apriori Algorithm 5 Result and Discussion (Proposed Framework) 6 Conclusion References A Novel Big Data Classification Technique for Healthcare Application Using Support Vector Machine, Random Forest and J48 1 Introduction 2 Literature Review 3 Methodology 4 The Proposed Method 5 Experiments and Results 6 Conclusion References Comparative Study on Arabic Text Classification: Challenges and Opportunities 1 Introduction 2 Literature Review 3 Background 4 Literature Review Results and Discussion 5 Results and Discussion 6 Conclusions and Future Work References Pedestrian Speed Prediction Using Feed Forward Neural Network 1 Introduction 2 Material and Method 2.1 Data Collection Location 2.2 Data Capturing and Extraction 2.3 Data Preparation 2.4 Sensitivity Analysis 2.5 ANN Model Formulation 2.6 ANN Model Validations 3 Results Analysis and Discussion 3.1 Descriptive of Observed Pedestrian Data. 3.2 Speed Characteristic and Distribution Results 3.3 Result of Sensitivity Analysis 3.4 Model Estimation Analysis Results 4 Conclusion References 12 Arabic Text Classification Using Modified Artificial Bee Colony Algorithm for Sentiment Analysis: The Case of Jordanian Dialect Abstract 1 Introduction 2 Related Works 2.1 Introduction 3 The Proposed Method 3.1 Introduction 3.2 Data Preparation 3.3 Data Annotation 3.4 Preprocessing 3.4.1 Tokenization 3.4.2 Text Pre-processing 3.4.3 Stemming 3.4.4 Text to Numeric Data Representation 3.4.5 Most Affective Jordanian Words 3.5 Modified Artificial Bee Colony Algorithm with Upper Confidence Bound Algorithm 3.5.1 The Original Artificial Bee Colony Algorithm 3.5.2 Enhancing Artificial Bee Algorithm with Upper Confidence Bound 3.5.3 Obtain the Number of Feature Selection Using the Modified ABC-UBC 3.6 Feature Selection 3.7 The Text Classification 3.7.1 Support Vector Machines Classifier (SVM) 3.7.2 K-Nearest Neighbors Classifier (KNN) 3.7.3 Naïve- Bayes Classifier 3.7.4 Polynomial Neural Networks Classifier 4 Results 4.1 Results Information 4.2 The Jordanian Dialect Dataset Experiments 4.2.1 The Result of Arabic Text Classifiers with Pre-processing Phase 4.2.2 The Result of Arabic Text Classifiers Without Pre-Processing Phase 4.2.3 The Result of Arabic Text Using Forward Feature Selection with ABC-UBC and Pre-Processing Phase 4.2.4 The Result of Arabic Text Using Forward Feature Selection with ABC-UBC Without Pre-Processing Phase 4.3 The Algerian Dialect Dataset Experiments 4.3.1 The Result of Arabic Text Classifiers with Pre-processing Phase 4.3.2 The Result of Arabic Text Classifiers Without Pre-processing Phase 4.3.3 The Result of Arabic Text Using Forward Feature Selection with ABC-UBC and Pre-processing Phase 4.3.4 The Result of Arabic Text Using Forward Feature Selection with ABC-UBC Without Pre-processing Phase 4.4 Experimental Results and Discussion 4.5 Experimental Results and Discussion 5 Conclusion References